1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
11382
11383
11384
11385
11386
11387
11388
11389
11390
11391
11392
11393
11394
11395
11396
11397
11398
11399
11400
11401
11402
11403
11404
11405
11406
11407
11408
11409
11410
11411
11412
11413
11414
11415
11416
11417
11418
11419
11420
11421
11422
11423
11424
11425
11426
11427
11428
11429
11430
11431
11432
11433
11434
11435
11436
11437
11438
11439
11440
11441
11442
11443
11444
11445
11446
11447
11448
11449
11450
11451
11452
11453
11454
11455
11456
11457
11458
11459
11460
11461
11462
11463
11464
11465
11466
11467
11468
11469
11470
11471
11472
11473
11474
11475
11476
11477
11478
11479
11480
11481
11482
11483
11484
11485
11486
11487
11488
11489
11490
11491
11492
11493
11494
11495
11496
11497
11498
11499
11500
11501
11502
11503
11504
11505
11506
11507
11508
11509
11510
11511
11512
11513
11514
11515
11516
11517
11518
11519
11520
11521
11522
11523
11524
11525
11526
11527
11528
11529
11530
11531
11532
11533
11534
11535
11536
11537
11538
11539
11540
11541
11542
11543
11544
11545
11546
11547
11548
11549
11550
11551
11552
11553
11554
11555
11556
11557
11558
11559
11560
11561
11562
11563
11564
11565
11566
11567
11568
11569
11570
11571
11572
11573
11574
11575
11576
11577
11578
11579
11580
11581
11582
11583
11584
11585
11586
11587
11588
11589
11590
11591
11592
11593
11594
11595
11596
11597
11598
11599
11600
11601
11602
11603
11604
11605
11606
11607
11608
11609
11610
11611
11612
11613
11614
11615
11616
11617
11618
11619
11620
11621
11622
11623
11624
11625
11626
11627
11628
11629
11630
11631
11632
11633
11634
11635
11636
11637
11638
11639
11640
11641
11642
11643
11644
11645
11646
11647
11648
11649
11650
11651
11652
11653
11654
11655
11656
11657
11658
11659
11660
11661
11662
11663
11664
11665
11666
11667
11668
11669
11670
11671
11672
11673
11674
11675
11676
11677
11678
11679
11680
11681
11682
11683
11684
11685
11686
11687
11688
11689
11690
11691
11692
11693
11694
11695
11696
11697
11698
11699
11700
11701
11702
11703
11704
11705
11706
11707
11708
11709
11710
11711
11712
11713
11714
11715
11716
11717
11718
11719
11720
11721
11722
11723
11724
11725
11726
11727
11728
11729
11730
11731
11732
11733
11734
11735
11736
11737
11738
11739
11740
11741
11742
11743
11744
11745
11746
11747
11748
11749
11750
11751
11752
11753
11754
11755
11756
11757
11758
11759
11760
11761
11762
11763
11764
11765
11766
11767
11768
11769
11770
11771
11772
11773
11774
11775
11776
11777
11778
11779
11780
11781
11782
11783
11784
11785
11786
11787
11788
11789
11790
11791
11792
11793
11794
11795
11796
11797
11798
11799
11800
11801
11802
11803
11804
11805
11806
11807
11808
11809
11810
11811
11812
11813
11814
11815
11816
11817
11818
11819
11820
11821
11822
11823
11824
11825
11826
11827
11828
11829
11830
11831
11832
11833
11834
11835
11836
11837
11838
11839
11840
11841
11842
11843
11844
11845
11846
11847
11848
11849
11850
11851
11852
11853
11854
11855
11856
11857
11858
11859
11860
11861
11862
11863
11864
11865
11866
11867
11868
11869
11870
11871
11872
11873
11874
11875
11876
11877
11878
11879
11880
11881
11882
11883
11884
11885
11886
11887
11888
11889
11890
11891
11892
11893
11894
11895
11896
11897
11898
11899
11900
11901
11902
11903
11904
11905
11906
11907
11908
11909
11910
11911
11912
11913
11914
11915
11916
11917
11918
11919
11920
11921
11922
11923
11924
11925
11926
11927
11928
11929
11930
11931
11932
11933
11934
11935
11936
11937
11938
11939
11940
11941
11942
11943
11944
11945
11946
11947
11948
11949
11950
11951
11952
11953
11954
11955
11956
11957
11958
11959
11960
11961
11962
11963
11964
11965
11966
11967
11968
11969
11970
11971
11972
11973
11974
11975
11976
11977
11978
11979
11980
11981
11982
11983
11984
11985
11986
11987
11988
11989
11990
11991
11992
11993
11994
11995
11996
11997
11998
11999
12000
12001
12002
12003
12004
12005
12006
12007
12008
12009
12010
12011
12012
12013
12014
12015
12016
12017
12018
12019
12020
12021
12022
12023
12024
12025
12026
12027
12028
12029
12030
12031
12032
12033
12034
12035
12036
12037
12038
12039
12040
12041
12042
12043
12044
12045
12046
12047
12048
12049
12050
12051
12052
12053
12054
12055
12056
12057
12058
12059
12060
12061
12062
12063
12064
12065
12066
12067
12068
12069
12070
12071
12072
12073
12074
12075
12076
12077
12078
12079
12080
12081
12082
12083
12084
12085
12086
12087
12088
12089
12090
12091
12092
12093
12094
12095
12096
12097
12098
12099
12100
12101
12102
12103
12104
12105
12106
12107
12108
12109
12110
12111
12112
12113
12114
12115
12116
12117
12118
12119
12120
12121
12122
12123
12124
12125
12126
12127
12128
12129
12130
12131
12132
12133
12134
12135
12136
12137
12138
12139
12140
12141
12142
12143
12144
12145
12146
12147
12148
12149
12150
12151
12152
12153
12154
12155
12156
12157
12158
12159
12160
12161
12162
12163
12164
12165
12166
12167
12168
12169
12170
12171
12172
12173
12174
12175
12176
12177
12178
12179
12180
12181
12182
12183
12184
12185
12186
12187
12188
12189
12190
12191
12192
12193
12194
12195
12196
12197
12198
12199
12200
12201
12202
12203
12204
12205
12206
12207
12208
12209
12210
12211
12212
12213
12214
12215
12216
12217
12218
12219
12220
12221
12222
12223
12224
12225
12226
12227
12228
12229
12230
12231
12232
12233
12234
12235
12236
12237
12238
12239
12240
12241
12242
12243
12244
12245
12246
12247
12248
12249
12250
12251
12252
12253
12254
12255
12256
12257
12258
12259
12260
12261
12262
12263
12264
12265
12266
12267
12268
12269
12270
12271
12272
12273
12274
12275
12276
12277
12278
12279
12280
12281
12282
12283
12284
12285
12286
12287
12288
12289
12290
12291
12292
12293
12294
12295
12296
12297
12298
12299
12300
12301
12302
12303
12304
12305
12306
12307
12308
12309
12310
12311
12312
12313
12314
12315
12316
12317
12318
12319
12320
12321
12322
12323
12324
12325
12326
12327
12328
12329
12330
12331
12332
12333
12334
12335
12336
12337
12338
12339
12340
12341
12342
12343
12344
12345
12346
12347
12348
12349
12350
12351
12352
12353
12354
12355
12356
12357
12358
12359
12360
12361
12362
12363
12364
12365
12366
12367
12368
12369
12370
12371
12372
12373
12374
12375
12376
12377
12378
12379
12380
12381
12382
12383
12384
12385
12386
12387
12388
12389
12390
12391
12392
12393
12394
12395
12396
12397
12398
12399
12400
12401
12402
12403
12404
12405
12406
12407
12408
12409
12410
12411
12412
12413
12414
12415
12416
12417
12418
12419
12420
12421
12422
12423
12424
12425
12426
12427
12428
12429
12430
12431
12432
12433
12434
12435
12436
12437
12438
12439
12440
12441
12442
12443
12444
12445
12446
12447
12448
12449
12450
12451
12452
12453
12454
12455
12456
12457
12458
12459
12460
12461
12462
12463
12464
12465
12466
12467
12468
12469
12470
12471
12472
12473
12474
12475
12476
12477
12478
12479
12480
12481
12482
12483
12484
12485
12486
12487
12488
12489
12490
12491
12492
12493
12494
12495
12496
12497
12498
12499
12500
12501
12502
12503
12504
12505
12506
12507
12508
12509
12510
12511
12512
12513
12514
12515
12516
12517
12518
12519
12520
12521
12522
12523
12524
12525
12526
12527
12528
12529
12530
12531
12532
12533
12534
12535
12536
12537
12538
12539
12540
12541
12542
12543
12544
12545
12546
12547
12548
12549
12550
12551
12552
12553
12554
12555
12556
12557
12558
12559
12560
12561
12562
12563
12564
12565
12566
12567
12568
12569
12570
12571
12572
12573
12574
12575
12576
12577
12578
12579
12580
12581
12582
12583
12584
12585
12586
12587
12588
12589
12590
12591
12592
12593
12594
12595
12596
12597
12598
12599
12600
12601
12602
12603
12604
12605
12606
12607
12608
12609
12610
12611
12612
12613
12614
12615
12616
12617
12618
12619
12620
12621
12622
12623
12624
12625
12626
12627
12628
12629
12630
12631
12632
12633
12634
12635
12636
12637
12638
12639
12640
12641
12642
12643
12644
12645
12646
12647
12648
12649
12650
12651
12652
12653
12654
12655
12656
12657
12658
12659
12660
12661
12662
12663
12664
12665
12666
12667
12668
12669
12670
12671
12672
12673
12674
12675
12676
12677
12678
12679
12680
12681
12682
12683
12684
12685
12686
12687
12688
12689
12690
12691
12692
12693
12694
12695
12696
12697
12698
12699
12700
12701
12702
12703
12704
12705
12706
12707
12708
12709
12710
12711
12712
12713
12714
12715
12716
12717
12718
12719
12720
12721
12722
12723
12724
12725
12726
12727
12728
12729
12730
12731
12732
12733
12734
12735
12736
12737
12738
12739
12740
12741
12742
12743
12744
12745
12746
12747
12748
12749
12750
12751
12752
12753
12754
12755
12756
12757
12758
12759
12760
12761
12762
12763
12764
12765
12766
12767
12768
12769
12770
12771
12772
12773
12774
12775
12776
12777
12778
12779
12780
12781
12782
12783
12784
12785
12786
12787
12788
12789
12790
12791
12792
12793
12794
12795
12796
12797
12798
12799
12800
12801
12802
12803
12804
12805
12806
12807
12808
12809
12810
12811
12812
12813
12814
12815
12816
12817
12818
12819
12820
12821
12822
12823
12824
12825
12826
12827
12828
12829
12830
12831
12832
12833
12834
12835
12836
12837
12838
12839
12840
12841
12842
12843
12844
12845
12846
12847
12848
12849
12850
12851
12852
12853
12854
12855
12856
12857
12858
12859
12860
12861
12862
12863
12864
12865
12866
12867
12868
12869
12870
12871
12872
12873
12874
12875
12876
12877
12878
12879
12880
12881
12882
12883
12884
12885
12886
12887
12888
12889
12890
12891
12892
12893
12894
12895
12896
12897
12898
12899
12900
12901
12902
12903
12904
12905
12906
12907
12908
12909
12910
12911
12912
12913
12914
12915
12916
12917
12918
12919
12920
12921
12922
12923
12924
12925
12926
12927
12928
12929
12930
12931
12932
12933
12934
12935
12936
12937
12938
12939
12940
12941
12942
12943
12944
12945
12946
12947
12948
12949
12950
12951
12952
12953
12954
12955
12956
12957
12958
12959
12960
12961
12962
12963
12964
12965
12966
12967
12968
12969
12970
12971
12972
12973
12974
12975
12976
12977
12978
12979
12980
12981
12982
12983
12984
12985
12986
12987
12988
12989
12990
12991
12992
12993
12994
12995
12996
12997
12998
12999
13000
13001
13002
13003
13004
13005
13006
13007
13008
13009
13010
13011
13012
13013
13014
13015
13016
13017
13018
13019
13020
13021
13022
13023
13024
13025
13026
13027
13028
13029
13030
13031
13032
13033
13034
13035
13036
13037
13038
13039
13040
13041
13042
13043
13044
13045
13046
13047
13048
13049
13050
13051
13052
13053
13054
13055
13056
13057
13058
13059
13060
13061
13062
13063
13064
13065
13066
13067
13068
13069
13070
13071
13072
13073
13074
13075
13076
13077
13078
13079
13080
13081
13082
13083
13084
13085
13086
13087
13088
13089
13090
13091
13092
13093
13094
13095
13096
13097
13098
13099
13100
13101
13102
13103
13104
13105
13106
13107
13108
13109
13110
13111
13112
13113
13114
13115
13116
13117
13118
13119
13120
13121
13122
13123
13124
13125
13126
13127
13128
13129
13130
13131
13132
13133
13134
13135
13136
13137
13138
13139
13140
13141
13142
13143
13144
13145
13146
13147
13148
13149
13150
13151
13152
13153
13154
13155
13156
13157
13158
13159
13160
13161
13162
13163
13164
13165
13166
13167
13168
13169
13170
13171
13172
13173
13174
13175
13176
13177
13178
13179
13180
13181
13182
13183
13184
13185
13186
13187
13188
13189
13190
13191
13192
13193
13194
13195
13196
13197
13198
13199
13200
13201
13202
13203
13204
13205
13206
13207
13208
13209
13210
13211
13212
13213
13214
13215
13216
13217
13218
13219
13220
13221
13222
13223
13224
13225
13226
13227
13228
13229
13230
13231
13232
13233
13234
13235
13236
13237
13238
13239
13240
13241
13242
13243
13244
13245
13246
13247
13248
13249
13250
13251
13252
13253
13254
13255
13256
13257
13258
13259
13260
13261
13262
13263
13264
13265
13266
13267
13268
13269
13270
13271
13272
13273
13274
13275
13276
13277
13278
13279
13280
13281
13282
13283
13284
13285
13286
13287
13288
13289
13290
13291
13292
13293
13294
13295
13296
13297
13298
13299
13300
13301
13302
13303
13304
13305
13306
13307
13308
13309
13310
13311
13312
13313
13314
13315
13316
13317
13318
13319
13320
13321
13322
13323
13324
13325
13326
13327
13328
13329
13330
13331
13332
13333
13334
13335
13336
13337
13338
13339
13340
13341
13342
13343
13344
13345
13346
13347
13348
13349
13350
13351
13352
13353
13354
13355
13356
13357
13358
13359
13360
13361
13362
13363
13364
13365
13366
13367
13368
13369
13370
13371
13372
13373
13374
13375
13376
13377
13378
13379
13380
13381
13382
13383
13384
13385
13386
13387
13388
13389
13390
13391
13392
13393
13394
13395
13396
13397
13398
13399
13400
13401
13402
13403
13404
13405
13406
13407
13408
13409
13410
13411
13412
13413
13414
13415
13416
13417
13418
13419
13420
13421
13422
13423
13424
13425
13426
13427
13428
13429
13430
13431
13432
13433
13434
13435
13436
13437
13438
13439
13440
13441
13442
13443
13444
13445
13446
13447
13448
13449
13450
13451
13452
13453
13454
13455
13456
13457
13458
13459
13460
13461
13462
13463
13464
13465
13466
13467
13468
13469
13470
13471
13472
13473
13474
13475
13476
13477
13478
13479
13480
13481
13482
13483
13484
13485
13486
13487
13488
13489
13490
13491
13492
13493
13494
13495
13496
13497
13498
13499
13500
13501
13502
13503
13504
13505
13506
13507
13508
13509
13510
13511
13512
13513
13514
13515
13516
13517
13518
13519
13520
13521
13522
13523
13524
13525
13526
13527
13528
13529
13530
13531
13532
13533
13534
13535
13536
13537
13538
13539
13540
13541
13542
13543
13544
13545
13546
13547
13548
13549
13550
13551
13552
13553
13554
13555
13556
13557
13558
13559
13560
13561
13562
13563
13564
13565
13566
13567
13568
13569
13570
13571
13572
13573
13574
13575
13576
13577
13578
13579
13580
13581
13582
13583
13584
13585
13586
13587
13588
13589
13590
13591
13592
13593
13594
13595
13596
13597
13598
13599
13600
13601
13602
13603
13604
13605
13606
13607
13608
13609
13610
13611
13612
13613
13614
13615
13616
13617
13618
13619
13620
13621
13622
13623
13624
13625
13626
13627
13628
13629
13630
13631
13632
13633
13634
13635
13636
13637
13638
13639
13640
13641
13642
13643
13644
13645
13646
13647
13648
13649
13650
13651
13652
13653
13654
13655
13656
13657
13658
13659
13660
13661
13662
13663
13664
13665
13666
13667
13668
13669
13670
13671
13672
13673
13674
13675
13676
13677
13678
13679
13680
13681
13682
13683
13684
13685
13686
13687
13688
13689
13690
13691
13692
13693
13694
13695
13696
13697
13698
13699
13700
13701
13702
13703
13704
13705
13706
13707
13708
13709
13710
13711
13712
13713
13714
13715
13716
13717
13718
13719
13720
13721
13722
13723
13724
13725
13726
13727
13728
13729
13730
13731
13732
13733
13734
13735
13736
13737
13738
13739
13740
13741
13742
13743
13744
13745
13746
13747
13748
13749
13750
13751
13752
13753
13754
13755
13756
13757
13758
13759
13760
13761
13762
13763
13764
13765
13766
13767
13768
13769
13770
13771
13772
13773
13774
13775
13776
13777
13778
13779
13780
13781
13782
13783
13784
13785
13786
13787
13788
13789
13790
13791
13792
13793
13794
13795
13796
13797
13798
13799
13800
13801
13802
13803
13804
13805
13806
13807
13808
13809
13810
13811
13812
13813
13814
13815
13816
13817
13818
13819
13820
13821
13822
13823
13824
13825
13826
13827
13828
13829
13830
13831
13832
13833
13834
13835
13836
13837
13838
13839
13840
13841
13842
13843
13844
13845
13846
13847
13848
13849
13850
13851
13852
13853
13854
13855
13856
13857
13858
13859
13860
13861
13862
13863
13864
13865
13866
13867
13868
13869
13870
13871
13872
13873
13874
13875
13876
13877
13878
13879
13880
13881
13882
13883
13884
13885
13886
13887
13888
13889
13890
13891
13892
13893
13894
13895
13896
13897
13898
13899
13900
13901
13902
13903
13904
13905
13906
13907
13908
13909
13910
13911
13912
13913
13914
13915
13916
13917
13918
13919
13920
13921
13922
13923
13924
13925
13926
13927
13928
13929
13930
13931
13932
13933
13934
13935
13936
13937
13938
13939
13940
13941
13942
13943
13944
13945
13946
13947
13948
13949
13950
13951
13952
13953
13954
13955
13956
13957
13958
13959
13960
13961
13962
13963
13964
13965
13966
13967
13968
13969
13970
13971
13972
13973
13974
13975
13976
13977
13978
13979
13980
13981
13982
13983
13984
13985
13986
13987
13988
13989
13990
13991
13992
13993
13994
13995
13996
13997
13998
13999
14000
14001
14002
14003
14004
14005
14006
14007
14008
14009
14010
14011
14012
14013
14014
14015
14016
14017
14018
14019
14020
14021
14022
14023
14024
14025
14026
14027
14028
14029
14030
14031
14032
14033
14034
14035
14036
14037
14038
14039
14040
14041
14042
14043
14044
14045
14046
14047
14048
14049
14050
14051
14052
14053
14054
14055
14056
14057
14058
14059
14060
14061
14062
14063
14064
14065
14066
14067
14068
14069
14070
14071
14072
14073
14074
14075
14076
14077
14078
14079
14080
14081
14082
14083
14084
14085
14086
14087
14088
14089
14090
14091
14092
14093
14094
14095
14096
14097
14098
14099
14100
14101
14102
14103
14104
14105
14106
14107
14108
14109
14110
14111
14112
14113
14114
14115
14116
14117
14118
14119
14120
14121
14122
14123
14124
14125
14126
14127
14128
14129
14130
14131
14132
14133
14134
14135
14136
14137
14138
14139
14140
14141
14142
14143
14144
14145
14146
14147
14148
14149
14150
14151
14152
14153
14154
14155
14156
14157
14158
14159
14160
14161
14162
14163
14164
14165
14166
14167
14168
14169
14170
14171
14172
14173
14174
14175
14176
14177
14178
14179
14180
14181
14182
14183
14184
14185
14186
14187
14188
14189
14190
14191
14192
14193
14194
14195
14196
14197
14198
14199
14200
14201
14202
14203
14204
14205
14206
14207
14208
14209
14210
14211
14212
14213
14214
14215
14216
14217
14218
14219
14220
14221
14222
14223
14224
14225
14226
14227
14228
14229
14230
14231
14232
14233
14234
14235
14236
14237
14238
14239
14240
14241
14242
14243
14244
14245
14246
14247
14248
14249
14250
14251
14252
14253
14254
14255
14256
14257
14258
14259
14260
14261
14262
14263
14264
14265
14266
14267
14268
14269
14270
14271
14272
14273
14274
14275
14276
14277
14278
14279
14280
14281
14282
14283
14284
14285
14286
14287
14288
14289
14290
14291
14292
14293
14294
14295
14296
14297
14298
14299
14300
14301
14302
14303
14304
14305
14306
14307
14308
14309
14310
14311
14312
14313
14314
14315
14316
14317
14318
14319
14320
14321
14322
14323
14324
14325
14326
14327
14328
14329
14330
14331
14332
14333
14334
14335
14336
14337
14338
14339
14340
14341
14342
14343
14344
14345
14346
14347
14348
14349
14350
14351
14352
14353
14354
14355
14356
14357
14358
14359
14360
14361
14362
14363
14364
14365
14366
14367
14368
14369
14370
14371
14372
14373
14374
14375
14376
14377
14378
14379
14380
14381
14382
14383
14384
14385
14386
14387
14388
14389
14390
14391
14392
14393
14394
14395
14396
14397
14398
14399
14400
14401
14402
14403
14404
14405
14406
14407
14408
14409
14410
14411
14412
14413
14414
14415
14416
14417
14418
14419
14420
14421
14422
14423
14424
14425
14426
14427
14428
14429
14430
14431
14432
14433
14434
14435
14436
14437
14438
14439
14440
14441
14442
14443
14444
14445
14446
14447
14448
14449
14450
14451
14452
14453
14454
14455
14456
14457
14458
14459
14460
14461
14462
14463
14464
14465
14466
14467
14468
14469
14470
14471
14472
14473
14474
14475
14476
14477
14478
14479
14480
14481
14482
14483
14484
14485
14486
14487
14488
14489
14490
14491
14492
14493
14494
14495
14496
14497
14498
14499
14500
14501
14502
14503
14504
14505
14506
14507
14508
14509
14510
14511
14512
14513
14514
14515
14516
14517
14518
14519
14520
14521
14522
14523
14524
14525
14526
14527
14528
14529
14530
14531
14532
14533
14534
14535
14536
14537
14538
14539
14540
14541
14542
14543
14544
14545
14546
14547
14548
14549
14550
14551
14552
14553
14554
14555
14556
14557
14558
14559
14560
14561
14562
14563
14564
14565
14566
14567
14568
14569
14570
14571
14572
14573
14574
14575
14576
14577
14578
14579
14580
14581
14582
14583
14584
14585
14586
14587
14588
14589
14590
14591
14592
14593
14594
14595
14596
14597
14598
14599
14600
14601
14602
14603
14604
14605
14606
14607
14608
14609
14610
14611
14612
14613
14614
14615
14616
14617
14618
14619
14620
14621
14622
14623
14624
14625
14626
14627
14628
14629
14630
14631
14632
14633
14634
14635
14636
14637
14638
14639
14640
14641
14642
14643
14644
14645
14646
14647
14648
14649
14650
14651
14652
14653
14654
14655
14656
14657
14658
14659
14660
14661
14662
14663
14664
14665
14666
14667
14668
14669
14670
14671
14672
14673
14674
14675
14676
14677
14678
14679
14680
14681
14682
14683
14684
14685
14686
14687
14688
14689
14690
14691
14692
14693
14694
14695
14696
14697
14698
14699
14700
14701
14702
14703
14704
14705
14706
14707
14708
14709
14710
14711
14712
14713
14714
14715
14716
14717
14718
14719
14720
14721
14722
14723
14724
14725
14726
14727
14728
14729
14730
14731
14732
14733
14734
14735
14736
14737
14738
14739
14740
14741
14742
14743
14744
14745
14746
14747
14748
14749
14750
14751
14752
14753
14754
14755
14756
14757
14758
14759
14760
14761
14762
14763
14764
14765
14766
14767
14768
14769
14770
14771
14772
14773
14774
14775
14776
14777
14778
14779
14780
14781
14782
14783
14784
14785
14786
14787
14788
14789
14790
14791
14792
14793
14794
14795
14796
14797
14798
14799
14800
14801
14802
14803
14804
14805
14806
14807
14808
14809
14810
14811
14812
14813
14814
14815
14816
14817
14818
14819
14820
14821
14822
14823
14824
14825
14826
14827
14828
14829
14830
14831
14832
14833
14834
14835
14836
14837
14838
14839
14840
14841
14842
14843
14844
14845
14846
14847
14848
14849
14850
14851
14852
14853
14854
14855
14856
14857
14858
14859
14860
14861
14862
14863
14864
14865
14866
14867
14868
14869
14870
14871
14872
14873
14874
14875
14876
14877
14878
14879
14880
14881
14882
14883
14884
14885
14886
14887
14888
14889
14890
14891
14892
14893
14894
14895
14896
14897
14898
14899
14900
14901
14902
14903
14904
14905
14906
14907
14908
14909
14910
14911
14912
14913
14914
14915
14916
14917
14918
14919
14920
14921
14922
14923
14924
14925
14926
14927
14928
14929
14930
14931
14932
14933
14934
14935
14936
14937
14938
14939
14940
14941
14942
14943
14944
14945
14946
14947
14948
14949
14950
14951
14952
14953
14954
14955
14956
14957
14958
14959
14960
14961
14962
14963
14964
14965
14966
14967
14968
14969
14970
14971
14972
14973
14974
14975
14976
14977
14978
14979
14980
14981
14982
14983
14984
14985
14986
14987
14988
14989
14990
14991
14992
14993
14994
14995
14996
14997
14998
14999
15000
15001
15002
15003
15004
15005
15006
15007
15008
15009
15010
15011
15012
15013
15014
15015
15016
15017
15018
15019
15020
15021
15022
15023
15024
15025
15026
15027
15028
15029
15030
15031
15032
15033
15034
15035
15036
15037
15038
15039
15040
15041
15042
15043
15044
15045
15046
15047
15048
15049
15050
15051
15052
15053
15054
15055
15056
15057
15058
15059
15060
15061
15062
15063
15064
15065
15066
15067
15068
15069
15070
15071
15072
15073
15074
15075
15076
15077
15078
15079
15080
15081
15082
15083
15084
15085
15086
15087
15088
15089
15090
15091
15092
15093
15094
15095
15096
15097
15098
15099
15100
15101
15102
15103
15104
15105
15106
15107
15108
15109
15110
15111
15112
15113
15114
15115
15116
15117
15118
15119
15120
15121
15122
15123
15124
15125
15126
15127
15128
15129
15130
15131
15132
15133
15134
15135
15136
15137
15138
15139
15140
15141
15142
15143
15144
15145
15146
15147
15148
15149
15150
15151
15152
15153
15154
15155
15156
15157
15158
15159
15160
15161
15162
15163
15164
15165
15166
15167
15168
15169
15170
15171
15172
15173
15174
15175
15176
15177
15178
15179
15180
15181
15182
15183
15184
15185
15186
15187
15188
15189
15190
15191
15192
15193
15194
15195
15196
15197
15198
15199
15200
15201
15202
15203
15204
15205
15206
15207
15208
15209
15210
15211
15212
15213
15214
15215
15216
15217
15218
15219
15220
15221
15222
15223
15224
15225
15226
15227
15228
15229
15230
15231
15232
15233
15234
15235
15236
15237
15238
15239
15240
15241
15242
15243
15244
15245
15246
15247
15248
15249
15250
15251
15252
15253
15254
15255
15256
15257
15258
15259
15260
15261
15262
15263
15264
15265
15266
15267
15268
15269
15270
15271
15272
15273
15274
15275
15276
15277
15278
15279
15280
15281
15282
15283
15284
15285
15286
15287
15288
15289
15290
15291
15292
15293
15294
15295
15296
15297
15298
15299
15300
15301
15302
15303
15304
15305
15306
15307
15308
15309
15310
15311
15312
15313
15314
15315
15316
15317
15318
15319
15320
15321
15322
15323
15324
15325
15326
15327
15328
15329
15330
15331
15332
15333
15334
15335
15336
15337
15338
15339
15340
15341
15342
15343
15344
15345
15346
15347
15348
15349
15350
15351
15352
15353
15354
15355
15356
15357
15358
15359
15360
15361
15362
15363
15364
15365
15366
15367
15368
15369
15370
15371
15372
15373
15374
15375
15376
15377
15378
15379
15380
15381
15382
15383
15384
15385
15386
15387
15388
15389
15390
15391
15392
15393
15394
15395
15396
15397
15398
15399
15400
15401
15402
15403
15404
15405
15406
15407
15408
15409
15410
15411
15412
15413
15414
15415
15416
15417
15418
15419
15420
15421
15422
15423
15424
15425
15426
15427
15428
15429
15430
15431
15432
15433
15434
15435
15436
15437
15438
15439
15440
15441
15442
15443
15444
15445
15446
15447
15448
15449
15450
15451
15452
15453
15454
15455
15456
15457
15458
15459
15460
15461
15462
15463
15464
15465
15466
15467
15468
15469
15470
15471
15472
15473
15474
15475
15476
15477
15478
15479
15480
15481
15482
15483
15484
15485
15486
15487
15488
15489
15490
15491
15492
15493
15494
15495
15496
15497
15498
15499
15500
15501
15502
15503
15504
15505
15506
15507
15508
15509
15510
15511
15512
15513
15514
15515
15516
15517
15518
15519
15520
15521
15522
15523
15524
15525
15526
15527
15528
15529
15530
15531
15532
15533
15534
15535
15536
15537
15538
15539
15540
15541
15542
15543
15544
15545
15546
15547
15548
15549
15550
15551
15552
15553
15554
15555
15556
15557
15558
15559
15560
15561
15562
15563
15564
15565
15566
15567
15568
15569
15570
15571
15572
15573
15574
15575
15576
15577
15578
15579
15580
15581
15582
15583
15584
15585
15586
15587
15588
15589
15590
15591
15592
15593
15594
15595
15596
15597
15598
15599
15600
15601
15602
15603
15604
15605
15606
15607
15608
15609
15610
15611
15612
15613
15614
15615
15616
15617
15618
15619
15620
15621
15622
15623
15624
15625
15626
15627
15628
15629
15630
15631
15632
15633
15634
15635
15636
15637
15638
15639
15640
15641
15642
15643
15644
15645
15646
15647
15648
15649
15650
15651
15652
15653
15654
15655
15656
15657
15658
15659
15660
15661
15662
15663
15664
15665
15666
15667
15668
15669
15670
15671
15672
15673
15674
15675
15676
15677
15678
15679
15680
15681
15682
15683
15684
15685
15686
15687
15688
15689
15690
15691
15692
15693
15694
15695
15696
15697
15698
15699
15700
15701
15702
15703
15704
15705
15706
15707
15708
15709
15710
15711
15712
15713
15714
15715
15716
15717
15718
15719
15720
15721
15722
15723
15724
15725
15726
15727
15728
15729
15730
15731
15732
15733
15734
15735
15736
15737
15738
15739
15740
15741
15742
15743
15744
15745
15746
15747
15748
15749
15750
15751
15752
15753
15754
15755
15756
15757
15758
15759
15760
15761
15762
15763
15764
15765
15766
15767
15768
15769
15770
15771
15772
15773
15774
15775
15776
15777
15778
15779
15780
15781
15782
15783
15784
15785
15786
15787
15788
15789
15790
15791
15792
15793
15794
15795
15796
15797
15798
15799
15800
15801
15802
15803
15804
15805
15806
15807
15808
15809
15810
15811
15812
15813
15814
15815
15816
15817
15818
15819
15820
15821
15822
15823
15824
15825
15826
15827
15828
15829
15830
15831
15832
15833
15834
15835
15836
15837
15838
15839
15840
15841
15842
15843
15844
15845
15846
15847
15848
15849
15850
15851
15852
15853
15854
15855
15856
15857
15858
15859
15860
15861
15862
15863
15864
15865
15866
15867
15868
15869
15870
15871
15872
15873
15874
15875
15876
15877
15878
15879
15880
15881
15882
15883
15884
15885
15886
15887
15888
15889
15890
15891
15892
15893
15894
15895
15896
15897
15898
15899
15900
15901
15902
15903
15904
15905
15906
15907
15908
15909
15910
15911
15912
15913
15914
15915
15916
15917
15918
15919
15920
15921
15922
15923
15924
15925
15926
15927
15928
15929
15930
15931
15932
15933
15934
15935
15936
15937
15938
15939
15940
15941
15942
15943
15944
15945
15946
15947
15948
15949
15950
15951
15952
15953
15954
15955
15956
15957
15958
15959
15960
15961
15962
15963
15964
15965
15966
15967
15968
15969
15970
15971
15972
15973
15974
15975
15976
15977
15978
15979
15980
15981
15982
15983
15984
15985
15986
15987
15988
15989
15990
15991
15992
15993
15994
15995
15996
15997
15998
15999
16000
16001
16002
16003
16004
16005
16006
16007
16008
16009
16010
16011
16012
16013
16014
16015
16016
16017
16018
16019
16020
16021
16022
16023
16024
16025
16026
16027
16028
16029
16030
16031
16032
16033
16034
16035
16036
16037
16038
16039
16040
16041
16042
16043
16044
16045
16046
16047
16048
16049
16050
16051
16052
16053
16054
16055
16056
16057
16058
16059
16060
16061
16062
16063
16064
16065
16066
16067
16068
16069
16070
16071
16072
16073
16074
16075
16076
16077
16078
16079
16080
16081
16082
16083
16084
16085
16086
16087
16088
16089
16090
16091
16092
16093
16094
16095
16096
16097
16098
16099
16100
16101
16102
16103
16104
16105
16106
16107
16108
16109
16110
16111
16112
16113
16114
16115
16116
16117
16118
16119
16120
16121
16122
16123
16124
16125
16126
16127
16128
16129
16130
16131
16132
16133
16134
16135
16136
16137
16138
16139
16140
16141
16142
16143
16144
16145
16146
16147
16148
16149
16150
16151
16152
16153
16154
16155
16156
16157
16158
16159
16160
16161
16162
16163
16164
16165
16166
16167
16168
16169
16170
16171
16172
16173
16174
16175
16176
16177
16178
16179
16180
16181
16182
16183
16184
16185
16186
16187
16188
16189
16190
16191
16192
16193
16194
16195
16196
16197
16198
16199
16200
16201
16202
16203
16204
16205
16206
16207
16208
16209
16210
16211
16212
16213
16214
16215
16216
16217
16218
16219
16220
16221
16222
16223
16224
16225
16226
16227
16228
16229
16230
16231
16232
16233
16234
16235
16236
16237
16238
16239
16240
16241
16242
16243
16244
16245
16246
16247
16248
16249
16250
16251
16252
16253
16254
16255
16256
16257
16258
16259
16260
16261
16262
16263
16264
16265
16266
16267
16268
16269
16270
16271
16272
16273
16274
16275
16276
16277
16278
16279
16280
16281
16282
16283
16284
16285
16286
16287
16288
16289
16290
16291
16292
16293
16294
16295
16296
16297
16298
16299
16300
16301
16302
16303
16304
16305
16306
16307
16308
16309
16310
16311
16312
16313
16314
16315
16316
16317
16318
16319
16320
16321
16322
16323
16324
16325
16326
16327
16328
16329
16330
16331
16332
16333
16334
16335
16336
16337
16338
16339
16340
16341
16342
16343
16344
16345
16346
16347
16348
16349
16350
16351
16352
16353
16354
16355
16356
16357
16358
16359
16360
16361
16362
16363
16364
16365
16366
16367
16368
16369
16370
16371
16372
16373
16374
16375
16376
16377
16378
16379
16380
16381
16382
16383
16384
16385
16386
16387
16388
16389
16390
16391
16392
16393
16394
16395
16396
16397
16398
16399
16400
16401
16402
16403
16404
16405
16406
16407
16408
16409
16410
16411
16412
16413
16414
16415
16416
16417
16418
16419
16420
16421
16422
16423
16424
16425
16426
16427
16428
16429
16430
16431
16432
16433
16434
16435
16436
16437
16438
16439
16440
16441
16442
16443
16444
16445
16446
16447
16448
16449
16450
16451
16452
16453
16454
16455
16456
16457
16458
16459
16460
16461
16462
16463
16464
16465
16466
16467
16468
16469
16470
16471
16472
16473
16474
16475
16476
16477
16478
16479
16480
16481
16482
16483
16484
16485
16486
16487
16488
16489
16490
16491
16492
16493
16494
16495
16496
16497
16498
16499
16500
16501
16502
16503
16504
16505
16506
16507
16508
16509
16510
16511
16512
16513
16514
16515
16516
16517
16518
16519
16520
16521
16522
16523
16524
16525
16526
16527
16528
16529
16530
16531
16532
16533
16534
16535
16536
16537
16538
16539
16540
16541
16542
16543
16544
16545
16546
16547
16548
16549
16550
16551
16552
16553
16554
16555
16556
16557
16558
16559
16560
16561
16562
16563
16564
16565
16566
16567
16568
16569
16570
16571
16572
16573
16574
16575
16576
16577
16578
16579
16580
16581
16582
16583
16584
16585
16586
16587
16588
16589
16590
16591
16592
16593
16594
16595
16596
16597
16598
16599
16600
16601
16602
16603
16604
16605
16606
16607
16608
16609
16610
16611
16612
16613
16614
16615
16616
16617
16618
16619
16620
16621
16622
16623
16624
16625
16626
16627
16628
16629
16630
16631
16632
16633
16634
16635
16636
16637
16638
16639
16640
16641
16642
16643
16644
16645
16646
16647
16648
16649
16650
16651
16652
16653
16654
16655
16656
16657
16658
16659
16660
16661
16662
16663
16664
16665
16666
16667
16668
16669
16670
16671
16672
16673
16674
16675
16676
16677
16678
16679
16680
16681
16682
16683
16684
16685
16686
16687
16688
16689
16690
16691
16692
16693
16694
16695
16696
16697
16698
16699
16700
16701
16702
16703
16704
16705
16706
16707
16708
16709
16710
16711
16712
16713
16714
16715
16716
16717
16718
16719
16720
16721
16722
16723
16724
16725
16726
16727
16728
16729
16730
16731
16732
16733
16734
16735
16736
16737
16738
16739
16740
16741
16742
16743
16744
16745
16746
16747
16748
16749
16750
16751
16752
16753
16754
16755
16756
16757
16758
16759
16760
16761
16762
16763
16764
16765
16766
16767
16768
16769
16770
16771
16772
16773
16774
16775
16776
16777
16778
16779
16780
16781
16782
16783
16784
16785
16786
16787
16788
16789
16790
16791
16792
16793
16794
16795
16796
16797
16798
16799
16800
16801
16802
16803
16804
16805
16806
16807
16808
16809
16810
16811
16812
16813
16814
16815
16816
16817
16818
16819
16820
16821
16822
16823
16824
16825
16826
16827
16828
16829
16830
16831
16832
16833
16834
16835
16836
16837
16838
16839
16840
16841
16842
16843
16844
16845
16846
16847
16848
16849
16850
16851
16852
16853
16854
16855
16856
16857
16858
16859
16860
16861
16862
16863
16864
16865
16866
16867
16868
16869
16870
16871
16872
16873
16874
16875
16876
16877
16878
16879
16880
16881
16882
16883
16884
16885
16886
16887
16888
16889
16890
16891
16892
16893
16894
16895
16896
16897
16898
16899
16900
16901
16902
16903
16904
16905
16906
16907
16908
16909
16910
16911
16912
16913
16914
16915
16916
16917
16918
16919
16920
16921
16922
16923
16924
16925
16926
16927
16928
16929
16930
16931
16932
16933
16934
16935
16936
16937
16938
16939
16940
16941
16942
16943
16944
16945
16946
16947
16948
16949
16950
16951
16952
16953
16954
16955
16956
16957
16958
16959
16960
16961
16962
16963
16964
16965
16966
16967
16968
16969
16970
16971
16972
16973
16974
16975
16976
16977
16978
16979
16980
16981
16982
16983
16984
16985
16986
16987
16988
16989
16990
16991
16992
16993
16994
16995
16996
16997
16998
16999
17000
17001
17002
17003
17004
17005
17006
17007
17008
17009
17010
17011
17012
17013
17014
17015
17016
17017
17018
17019
17020
17021
17022
17023
17024
17025
17026
17027
17028
17029
17030
17031
17032
17033
17034
17035
17036
17037
17038
17039
17040
17041
17042
17043
17044
17045
17046
17047
17048
17049
17050
17051
17052
17053
17054
17055
17056
17057
17058
17059
17060
17061
17062
17063
17064
17065
17066
17067
17068
17069
17070
17071
17072
17073
17074
17075
17076
17077
17078
17079
17080
17081
17082
17083
17084
17085
17086
17087
17088
17089
17090
17091
17092
17093
17094
17095
17096
17097
17098
17099
17100
17101
17102
17103
17104
17105
17106
17107
17108
17109
17110
17111
17112
17113
17114
17115
17116
17117
17118
17119
17120
17121
17122
17123
17124
17125
17126
17127
17128
17129
17130
17131
17132
17133
17134
17135
17136
17137
17138
17139
17140
17141
17142
17143
17144
17145
17146
17147
17148
17149
17150
17151
17152
17153
17154
17155
17156
17157
17158
17159
17160
17161
17162
17163
17164
17165
17166
17167
17168
17169
17170
17171
17172
17173
17174
17175
17176
17177
17178
17179
17180
17181
17182
17183
17184
17185
17186
17187
17188
17189
17190
17191
17192
17193
17194
17195
17196
17197
17198
17199
17200
17201
17202
17203
17204
17205
17206
17207
17208
17209
17210
17211
17212
17213
17214
17215
17216
17217
17218
17219
17220
17221
17222
17223
17224
17225
17226
17227
17228
17229
17230
17231
17232
17233
17234
17235
17236
17237
17238
17239
17240
17241
17242
17243
17244
17245
17246
17247
17248
17249
17250
17251
17252
17253
17254
17255
17256
17257
17258
17259
17260
17261
17262
17263
17264
17265
17266
17267
17268
17269
17270
17271
17272
17273
17274
17275
17276
17277
17278
17279
17280
17281
17282
17283
17284
17285
17286
17287
17288
17289
17290
17291
17292
17293
17294
17295
17296
17297
17298
17299
17300
17301
17302
17303
17304
17305
17306
17307
17308
17309
17310
17311
17312
17313
17314
17315
17316
17317
17318
17319
17320
17321
17322
17323
17324
17325
17326
17327
17328
17329
17330
17331
17332
17333
17334
17335
17336
17337
17338
17339
17340
17341
17342
17343
17344
17345
17346
17347
17348
17349
17350
17351
17352
17353
17354
17355
17356
17357
17358
17359
17360
17361
17362
17363
17364
17365
17366
17367
17368
17369
17370
17371
17372
17373
17374
17375
17376
17377
17378
17379
17380
17381
17382
17383
17384
17385
17386
17387
17388
17389
17390
17391
17392
17393
17394
17395
17396
17397
17398
17399
17400
17401
17402
17403
17404
17405
17406
17407
17408
17409
17410
17411
17412
17413
17414
17415
17416
17417
17418
17419
17420
17421
17422
17423
17424
17425
17426
17427
17428
17429
17430
17431
17432
17433
17434
17435
17436
17437
17438
17439
17440
17441
17442
17443
17444
17445
17446
17447
17448
17449
17450
17451
17452
17453
17454
17455
17456
17457
17458
17459
17460
17461
17462
17463
17464
17465
17466
17467
17468
17469
17470
17471
17472
17473
17474
17475
17476
17477
17478
17479
17480
17481
17482
17483
17484
17485
17486
17487
17488
17489
17490
17491
17492
17493
17494
17495
17496
17497
17498
17499
17500
17501
17502
17503
17504
17505
17506
17507
17508
17509
17510
17511
17512
17513
17514
17515
17516
17517
17518
17519
17520
17521
17522
17523
17524
17525
17526
17527
17528
17529
17530
17531
17532
17533
17534
17535
17536
17537
17538
17539
17540
17541
17542
17543
17544
17545
17546
17547
17548
17549
17550
17551
17552
17553
17554
17555
17556
17557
17558
17559
17560
17561
17562
17563
17564
17565
17566
17567
17568
17569
17570
17571
17572
17573
17574
17575
17576
17577
17578
17579
17580
17581
17582
17583
17584
17585
17586
17587
17588
17589
17590
17591
17592
17593
17594
17595
17596
17597
17598
17599
17600
17601
17602
17603
17604
17605
17606
17607
17608
17609
17610
17611
17612
17613
17614
17615
17616
17617
17618
17619
17620
17621
17622
17623
17624
17625
17626
17627
17628
17629
17630
17631
17632
17633
17634
17635
17636
17637
17638
17639
17640
17641
17642
17643
17644
17645
17646
17647
17648
17649
17650
17651
17652
17653
17654
17655
17656
17657
17658
17659
17660
17661
17662
17663
17664
17665
17666
17667
17668
17669
17670
17671
17672
17673
17674
17675
17676
17677
17678
17679
17680
17681
17682
17683
17684
17685
17686
17687
17688
17689
17690
17691
17692
17693
17694
17695
17696
17697
17698
17699
17700
17701
17702
17703
17704
17705
17706
17707
17708
17709
17710
17711
17712
17713
17714
17715
17716
17717
17718
17719
17720
17721
17722
17723
17724
17725
17726
17727
17728
17729
17730
17731
17732
17733
17734
17735
17736
17737
17738
17739
17740
17741
17742
17743
17744
17745
17746
17747
17748
17749
17750
17751
17752
17753
17754
17755
17756
17757
17758
17759
17760
17761
17762
17763
17764
17765
17766
17767
17768
17769
17770
17771
17772
17773
17774
17775
17776
17777
17778
17779
17780
17781
17782
17783
17784
17785
17786
17787
17788
17789
17790
17791
17792
17793
17794
17795
17796
17797
17798
17799
17800
17801
17802
17803
17804
17805
17806
17807
17808
17809
17810
17811
17812
17813
17814
17815
17816
17817
17818
17819
17820
17821
17822
17823
17824
17825
17826
17827
17828
17829
17830
17831
17832
17833
17834
17835
17836
17837
17838
17839
17840
17841
17842
17843
17844
17845
17846
17847
17848
17849
17850
17851
17852
17853
17854
17855
17856
17857
17858
17859
17860
17861
17862
17863
17864
17865
17866
17867
17868
17869
17870
17871
17872
17873
17874
17875
17876
17877
17878
17879
17880
17881
17882
17883
17884
17885
17886
17887
17888
17889
17890
17891
17892
17893
17894
17895
17896
17897
17898
17899
17900
17901
17902
17903
17904
17905
17906
17907
17908
17909
17910
17911
17912
17913
17914
17915
17916
17917
17918
17919
17920
17921
17922
17923
17924
17925
17926
17927
17928
17929
17930
17931
17932
17933
17934
17935
17936
17937
17938
17939
17940
17941
17942
17943
17944
17945
17946
17947
17948
17949
17950
17951
17952
17953
17954
17955
17956
17957
17958
17959
17960
17961
17962
17963
17964
17965
17966
17967
17968
17969
17970
17971
17972
17973
17974
17975
17976
17977
17978
17979
17980
17981
17982
17983
17984
17985
17986
17987
17988
17989
17990
17991
17992
17993
17994
17995
17996
17997
17998
17999
18000
18001
18002
18003
18004
18005
18006
18007
18008
18009
18010
18011
18012
18013
18014
18015
18016
18017
18018
18019
18020
18021
18022
18023
18024
18025
18026
18027
18028
18029
18030
18031
18032
18033
18034
18035
18036
18037
18038
18039
18040
18041
18042
18043
18044
18045
18046
18047
18048
18049
18050
18051
18052
18053
18054
18055
18056
18057
18058
18059
18060
18061
18062
18063
18064
18065
18066
18067
18068
18069
18070
18071
18072
18073
18074
18075
18076
18077
18078
18079
18080
18081
18082
18083
18084
18085
18086
18087
18088
18089
18090
18091
18092
18093
18094
18095
18096
18097
18098
18099
18100
18101
18102
18103
18104
18105
18106
18107
18108
18109
18110
18111
18112
18113
18114
18115
18116
18117
18118
18119
18120
18121
18122
18123
18124
18125
18126
18127
18128
18129
18130
18131
18132
18133
18134
18135
18136
18137
18138
18139
18140
18141
18142
18143
18144
18145
18146
18147
18148
18149
18150
18151
18152
18153
18154
18155
18156
18157
18158
18159
18160
18161
18162
18163
18164
18165
18166
18167
18168
18169
18170
18171
18172
18173
18174
18175
18176
18177
18178
18179
18180
18181
18182
18183
18184
18185
18186
18187
18188
18189
18190
18191
18192
18193
18194
18195
18196
18197
18198
18199
18200
18201
18202
18203
18204
18205
18206
18207
18208
18209
18210
18211
18212
18213
18214
18215
18216
18217
18218
18219
18220
18221
18222
18223
18224
18225
18226
18227
18228
18229
18230
18231
18232
18233
18234
18235
18236
18237
18238
18239
18240
18241
18242
18243
18244
18245
18246
18247
18248
18249
18250
18251
18252
18253
18254
18255
18256
18257
18258
18259
18260
18261
18262
18263
18264
18265
18266
18267
18268
18269
18270
18271
18272
18273
18274
18275
18276
18277
18278
18279
18280
18281
18282
18283
18284
18285
18286
18287
18288
18289
18290
18291
18292
18293
18294
18295
18296
18297
18298
18299
18300
18301
18302
18303
18304
18305
18306
18307
18308
18309
18310
18311
18312
18313
18314
18315
18316
18317
18318
18319
18320
18321
18322
18323
18324
18325
18326
18327
18328
18329
18330
18331
18332
18333
18334
18335
18336
18337
18338
18339
18340
18341
18342
18343
18344
18345
18346
18347
18348
18349
18350
18351
18352
18353
18354
18355
18356
18357
18358
18359
18360
18361
18362
18363
18364
18365
18366
18367
18368
18369
18370
18371
18372
18373
18374
18375
18376
18377
18378
18379
18380
18381
18382
18383
18384
18385
18386
18387
18388
18389
18390
18391
18392
18393
18394
18395
18396
18397
18398
18399
18400
18401
18402
18403
18404
18405
18406
18407
18408
18409
18410
18411
18412
18413
18414
18415
18416
18417
18418
18419
18420
18421
18422
18423
18424
18425
18426
18427
18428
18429
18430
18431
18432
18433
18434
18435
18436
18437
18438
18439
18440
18441
18442
18443
18444
18445
18446
18447
18448
18449
18450
18451
18452
18453
18454
18455
18456
18457
18458
18459
18460
18461
18462
18463
18464
18465
18466
18467
18468
18469
18470
18471
18472
18473
18474
18475
18476
18477
18478
18479
18480
18481
18482
18483
18484
18485
18486
18487
18488
18489
18490
18491
18492
18493
18494
18495
18496
18497
18498
18499
18500
18501
18502
18503
18504
18505
18506
18507
18508
18509
18510
18511
18512
18513
18514
18515
18516
18517
18518
18519
18520
18521
18522
18523
18524
18525
18526
18527
18528
18529
18530
18531
18532
18533
18534
18535
18536
18537
18538
18539
18540
18541
18542
18543
18544
18545
18546
18547
18548
18549
18550
18551
18552
18553
18554
18555
18556
18557
18558
18559
18560
18561
18562
18563
18564
18565
18566
18567
18568
18569
18570
18571
18572
18573
18574
18575
18576
18577
18578
18579
18580
18581
18582
18583
18584
18585
18586
18587
18588
18589
18590
18591
18592
18593
18594
18595
18596
18597
18598
18599
18600
18601
18602
18603
18604
18605
18606
18607
18608
18609
18610
18611
18612
18613
18614
18615
18616
18617
18618
18619
18620
18621
18622
18623
18624
18625
18626
18627
18628
18629
18630
18631
18632
18633
18634
18635
18636
18637
18638
18639
18640
18641
18642
18643
18644
18645
18646
18647
18648
18649
18650
18651
18652
18653
18654
18655
18656
18657
18658
18659
18660
18661
18662
18663
18664
18665
18666
18667
18668
18669
18670
18671
18672
18673
18674
18675
18676
18677
18678
18679
18680
18681
18682
18683
18684
18685
18686
18687
18688
18689
18690
18691
18692
18693
18694
18695
18696
18697
18698
18699
18700
18701
18702
18703
18704
18705
18706
18707
18708
18709
18710
18711
18712
18713
18714
18715
18716
18717
18718
18719
18720
18721
18722
18723
18724
18725
18726
18727
18728
18729
18730
18731
18732
18733
18734
18735
18736
18737
18738
18739
18740
18741
18742
18743
18744
18745
18746
18747
18748
18749
18750
18751
18752
18753
18754
18755
18756
18757
18758
18759
18760
18761
18762
18763
18764
18765
18766
18767
18768
18769
18770
18771
18772
18773
18774
18775
18776
18777
18778
18779
18780
18781
18782
18783
18784
18785
18786
18787
18788
18789
18790
18791
18792
18793
18794
18795
18796
18797
18798
18799
18800
18801
18802
18803
18804
18805
18806
18807
18808
18809
18810
18811
18812
18813
18814
18815
18816
18817
18818
18819
18820
18821
18822
18823
18824
18825
18826
18827
18828
18829
18830
18831
18832
18833
18834
18835
18836
18837
18838
18839
18840
18841
18842
18843
18844
18845
18846
18847
18848
18849
18850
18851
18852
18853
18854
18855
18856
18857
18858
18859
18860
18861
18862
18863
18864
18865
18866
18867
18868
18869
18870
18871
18872
18873
18874
18875
18876
18877
18878
18879
18880
18881
18882
18883
18884
18885
18886
18887
18888
18889
18890
18891
18892
18893
18894
18895
18896
18897
18898
18899
18900
18901
18902
18903
18904
18905
18906
18907
18908
18909
18910
18911
18912
18913
18914
18915
18916
18917
18918
18919
18920
18921
18922
18923
18924
18925
18926
18927
18928
18929
18930
18931
18932
18933
18934
18935
18936
18937
18938
18939
18940
18941
18942
18943
18944
18945
18946
18947
18948
18949
18950
18951
18952
18953
18954
18955
18956
18957
18958
18959
18960
18961
18962
18963
18964
18965
18966
18967
18968
18969
18970
18971
18972
18973
18974
18975
18976
18977
18978
18979
18980
18981
18982
18983
18984
18985
18986
18987
18988
18989
18990
18991
18992
18993
18994
18995
18996
18997
18998
18999
19000
19001
19002
19003
19004
19005
19006
19007
19008
19009
19010
19011
19012
19013
19014
19015
19016
19017
19018
19019
19020
19021
19022
19023
19024
19025
19026
19027
19028
19029
19030
19031
19032
19033
19034
19035
19036
19037
19038
19039
19040
19041
19042
19043
19044
19045
19046
19047
19048
19049
19050
19051
19052
19053
19054
19055
19056
19057
19058
19059
19060
19061
19062
19063
19064
19065
19066
19067
19068
19069
19070
19071
19072
19073
19074
19075
19076
19077
19078
19079
19080
19081
19082
19083
19084
19085
19086
19087
19088
19089
19090
19091
19092
19093
19094
19095
19096
19097
19098
19099
19100
19101
19102
19103
19104
19105
19106
19107
19108
19109
19110
19111
19112
19113
19114
19115
19116
19117
19118
19119
19120
19121
19122
19123
19124
19125
19126
19127
19128
19129
19130
19131
19132
19133
19134
19135
19136
19137
19138
19139
19140
19141
19142
19143
19144
19145
19146
19147
19148
19149
19150
19151
19152
19153
19154
19155
19156
19157
19158
19159
19160
19161
19162
19163
19164
19165
19166
19167
19168
19169
19170
19171
19172
19173
19174
19175
19176
19177
19178
19179
19180
19181
19182
19183
19184
19185
19186
19187
19188
19189
19190
19191
19192
19193
19194
19195
19196
19197
19198
19199
19200
19201
19202
19203
19204
19205
19206
19207
19208
19209
19210
19211
19212
19213
19214
19215
19216
19217
19218
19219
19220
19221
19222
19223
19224
19225
19226
19227
19228
19229
19230
19231
19232
19233
19234
19235
19236
19237
19238
19239
19240
19241
19242
19243
19244
19245
19246
19247
19248
19249
19250
19251
19252
19253
19254
19255
19256
19257
19258
19259
19260
19261
19262
19263
19264
19265
19266
19267
19268
19269
19270
19271
19272
19273
19274
19275
19276
19277
19278
19279
19280
19281
19282
19283
19284
19285
19286
19287
19288
19289
19290
19291
19292
19293
19294
19295
19296
19297
19298
19299
19300
19301
19302
19303
19304
19305
19306
19307
19308
19309
19310
19311
19312
19313
19314
19315
19316
19317
19318
19319
19320
19321
19322
19323
19324
19325
19326
19327
19328
19329
19330
19331
19332
19333
19334
19335
19336
19337
19338
19339
19340
19341
19342
19343
19344
19345
19346
19347
19348
19349
19350
19351
19352
19353
19354
19355
19356
19357
19358
19359
19360
19361
19362
19363
19364
19365
19366
19367
19368
19369
19370
19371
19372
19373
19374
19375
19376
19377
19378
19379
19380
19381
19382
19383
19384
19385
19386
19387
19388
19389
19390
19391
19392
19393
19394
19395
19396
19397
19398
19399
19400
19401
19402
19403
19404
19405
19406
19407
19408
19409
19410
19411
19412
19413
19414
19415
19416
19417
19418
19419
19420
19421
19422
19423
19424
19425
19426
19427
19428
19429
19430
19431
19432
19433
19434
19435
19436
19437
19438
19439
19440
19441
19442
19443
19444
19445
19446
19447
19448
19449
19450
19451
19452
19453
19454
19455
19456
19457
19458
19459
19460
19461
19462
19463
19464
19465
19466
19467
19468
19469
19470
19471
19472
19473
19474
19475
19476
19477
19478
19479
19480
19481
19482
19483
19484
19485
19486
19487
19488
19489
19490
19491
19492
19493
19494
19495
19496
19497
19498
19499
19500
19501
19502
19503
19504
19505
19506
19507
19508
19509
19510
19511
19512
19513
19514
19515
19516
19517
19518
19519
19520
19521
19522
19523
19524
19525
19526
19527
19528
19529
19530
19531
19532
19533
19534
19535
19536
19537
19538
19539
19540
19541
19542
19543
19544
19545
19546
19547
19548
19549
19550
19551
19552
19553
19554
19555
19556
19557
19558
19559
19560
19561
19562
19563
19564
19565
19566
19567
19568
19569
19570
19571
19572
19573
19574
19575
19576
19577
19578
19579
19580
19581
19582
19583
19584
19585
19586
19587
19588
19589
19590
19591
19592
19593
19594
19595
19596
19597
19598
19599
19600
19601
19602
19603
19604
19605
19606
19607
19608
19609
19610
19611
19612
19613
19614
19615
19616
19617
19618
19619
19620
19621
19622
19623
19624
19625
19626
19627
19628
19629
19630
19631
19632
19633
19634
19635
19636
19637
19638
19639
19640
19641
19642
19643
19644
19645
19646
19647
19648
19649
19650
19651
19652
19653
19654
19655
19656
19657
19658
19659
19660
19661
19662
19663
19664
19665
19666
19667
19668
19669
19670
19671
19672
19673
19674
19675
19676
19677
19678
19679
19680
19681
19682
19683
19684
19685
19686
19687
19688
19689
19690
19691
19692
19693
19694
19695
19696
19697
19698
19699
19700
19701
19702
19703
19704
19705
19706
19707
19708
19709
19710
19711
19712
19713
19714
19715
19716
19717
19718
19719
19720
19721
19722
19723
19724
19725
19726
19727
19728
19729
19730
19731
19732
19733
19734
19735
19736
19737
19738
19739
19740
19741
19742
19743
19744
19745
19746
19747
19748
19749
19750
19751
19752
19753
19754
19755
19756
19757
19758
19759
19760
19761
19762
19763
19764
19765
19766
19767
19768
19769
19770
19771
19772
19773
19774
19775
19776
19777
19778
19779
19780
19781
19782
19783
19784
19785
19786
19787
19788
19789
19790
19791
19792
19793
19794
19795
19796
19797
19798
19799
19800
19801
19802
19803
19804
19805
19806
19807
19808
19809
19810
19811
19812
19813
19814
19815
19816
19817
19818
19819
19820
19821
19822
19823
19824
19825
19826
19827
19828
19829
19830
19831
19832
19833
19834
19835
19836
19837
19838
19839
19840
19841
19842
19843
19844
19845
19846
19847
19848
19849
19850
19851
19852
19853
19854
19855
19856
19857
19858
19859
19860
19861
19862
19863
19864
19865
19866
19867
19868
19869
19870
19871
19872
19873
19874
19875
19876
19877
19878
19879
19880
19881
19882
19883
19884
19885
19886
19887
19888
19889
19890
19891
19892
19893
19894
19895
19896
19897
19898
19899
19900
19901
19902
19903
19904
19905
19906
19907
19908
19909
19910
19911
19912
19913
19914
19915
19916
19917
19918
19919
19920
19921
19922
19923
19924
19925
19926
19927
19928
19929
19930
19931
19932
19933
19934
19935
19936
19937
19938
19939
19940
19941
19942
19943
19944
19945
19946
19947
19948
19949
19950
19951
19952
19953
19954
19955
19956
19957
19958
19959
19960
19961
19962
19963
19964
19965
19966
19967
19968
19969
19970
19971
19972
19973
19974
19975
19976
19977
19978
19979
19980
19981
19982
19983
19984
19985
19986
19987
19988
19989
19990
19991
19992
19993
19994
19995
19996
19997
19998
19999
20000
20001
20002
20003
20004
20005
20006
20007
20008
20009
20010
20011
20012
20013
20014
20015
20016
20017
20018
20019
20020
20021
20022
20023
20024
20025
20026
20027
20028
20029
20030
20031
20032
20033
20034
20035
20036
20037
20038
20039
20040
20041
20042
20043
20044
20045
20046
20047
20048
20049
20050
20051
20052
20053
20054
20055
20056
20057
20058
20059
20060
20061
20062
20063
20064
20065
20066
20067
20068
20069
20070
20071
20072
20073
20074
20075
20076
20077
20078
20079
20080
20081
20082
20083
20084
20085
20086
20087
20088
20089
20090
20091
20092
20093
20094
20095
20096
20097
20098
20099
20100
20101
20102
20103
20104
20105
20106
20107
20108
20109
20110
20111
20112
20113
20114
20115
20116
20117
20118
20119
20120
20121
20122
20123
20124
20125
20126
20127
20128
20129
20130
20131
20132
20133
20134
20135
20136
20137
20138
20139
20140
20141
20142
20143
20144
20145
20146
20147
20148
20149
20150
20151
20152
20153
20154
20155
20156
20157
20158
20159
20160
20161
20162
20163
20164
20165
20166
20167
20168
20169
20170
20171
20172
20173
20174
20175
20176
20177
20178
20179
20180
20181
20182
20183
20184
20185
20186
20187
20188
20189
20190
20191
20192
20193
20194
20195
20196
20197
20198
20199
20200
20201
20202
20203
20204
20205
20206
20207
20208
20209
20210
20211
20212
20213
20214
20215
20216
20217
20218
20219
20220
20221
20222
20223
20224
20225
20226
20227
20228
20229
20230
20231
20232
20233
20234
20235
20236
20237
20238
20239
20240
20241
20242
20243
20244
20245
20246
20247
20248
20249
20250
20251
20252
20253
20254
20255
20256
20257
20258
20259
20260
20261
20262
20263
20264
20265
20266
20267
20268
20269
20270
20271
20272
20273
20274
20275
20276
20277
20278
20279
20280
20281
20282
20283
20284
20285
20286
20287
20288
20289
20290
20291
20292
20293
20294
20295
20296
20297
20298
20299
20300
20301
20302
20303
20304
20305
20306
20307
20308
20309
20310
20311
20312
20313
20314
20315
20316
20317
20318
20319
20320
20321
20322
20323
20324
20325
20326
20327
20328
20329
20330
20331
20332
20333
20334
20335
20336
20337
20338
20339
20340
20341
20342
20343
20344
20345
20346
20347
20348
20349
20350
20351
20352
20353
20354
20355
20356
20357
20358
20359
20360
20361
20362
20363
20364
20365
20366
20367
20368
20369
20370
20371
20372
20373
20374
20375
20376
20377
20378
20379
20380
20381
20382
20383
20384
20385
20386
20387
20388
20389
20390
20391
20392
20393
20394
20395
20396
20397
20398
20399
20400
20401
20402
20403
20404
20405
20406
20407
20408
20409
20410
20411
20412
20413
20414
20415
20416
20417
20418
20419
20420
20421
20422
20423
20424
20425
20426
20427
20428
20429
20430
20431
20432
20433
20434
20435
20436
20437
20438
20439
20440
20441
20442
20443
20444
20445
20446
20447
20448
20449
20450
20451
20452
20453
20454
20455
20456
20457
20458
20459
20460
20461
20462
20463
20464
20465
20466
20467
20468
20469
20470
20471
20472
20473
20474
20475
20476
20477
20478
20479
20480
20481
20482
20483
20484
20485
20486
20487
20488
20489
20490
20491
20492
20493
20494
20495
20496
20497
20498
20499
20500
20501
20502
20503
20504
20505
20506
20507
20508
20509
20510
20511
20512
20513
20514
20515
20516
20517
20518
20519
20520
20521
20522
20523
20524
20525
20526
20527
20528
20529
20530
20531
20532
20533
20534
20535
20536
20537
20538
20539
20540
20541
20542
20543
20544
20545
20546
20547
20548
20549
20550
20551
20552
20553
20554
20555
20556
20557
20558
20559
20560
20561
20562
20563
20564
20565
20566
20567
20568
20569
20570
20571
20572
20573
20574
20575
20576
20577
20578
20579
20580
20581
20582
20583
20584
20585
20586
20587
20588
20589
20590
20591
20592
20593
20594
20595
20596
20597
20598
20599
20600
20601
20602
20603
20604
20605
20606
20607
20608
20609
20610
20611
20612
20613
20614
20615
20616
20617
20618
20619
20620
20621
20622
20623
20624
20625
20626
20627
20628
20629
20630
20631
20632
20633
20634
20635
20636
20637
20638
20639
20640
20641
20642
20643
20644
20645
20646
20647
20648
20649
20650
20651
20652
20653
20654
20655
20656
20657
20658
20659
20660
20661
20662
20663
20664
20665
20666
20667
20668
20669
20670
20671
20672
20673
20674
20675
20676
20677
20678
20679
20680
20681
20682
20683
20684
20685
20686
20687
20688
20689
20690
20691
20692
20693
20694
20695
20696
20697
20698
20699
20700
20701
20702
20703
20704
20705
20706
20707
20708
20709
20710
20711
20712
20713
20714
20715
20716
20717
20718
20719
20720
20721
20722
20723
20724
20725
20726
20727
20728
20729
20730
20731
20732
20733
20734
20735
20736
20737
20738
20739
20740
20741
20742
20743
20744
20745
20746
20747
20748
20749
20750
20751
20752
20753
20754
20755
20756
20757
20758
20759
20760
20761
20762
20763
20764
20765
20766
20767
20768
20769
20770
20771
20772
20773
20774
20775
20776
20777
20778
20779
20780
20781
20782
20783
20784
20785
20786
20787
20788
20789
20790
20791
20792
20793
20794
20795
20796
20797
20798
20799
20800
20801
20802
20803
20804
20805
20806
20807
20808
20809
20810
20811
20812
20813
20814
20815
20816
20817
20818
20819
20820
20821
20822
20823
20824
20825
20826
20827
20828
20829
20830
20831
20832
20833
20834
20835
20836
20837
20838
20839
20840
20841
20842
20843
20844
20845
20846
20847
20848
20849
20850
20851
20852
20853
20854
20855
20856
20857
20858
20859
20860
20861
20862
20863
20864
20865
20866
20867
20868
20869
20870
20871
20872
20873
20874
20875
20876
20877
20878
20879
20880
20881
20882
20883
20884
20885
20886
20887
20888
20889
20890
20891
20892
20893
20894
20895
20896
20897
20898
20899
20900
20901
20902
20903
20904
20905
20906
20907
20908
20909
20910
20911
20912
20913
20914
20915
20916
20917
20918
20919
20920
20921
20922
20923
20924
20925
20926
20927
20928
20929
20930
20931
20932
20933
20934
20935
20936
20937
20938
20939
20940
20941
20942
20943
20944
20945
20946
20947
20948
20949
20950
20951
20952
20953
20954
20955
20956
20957
20958
20959
20960
20961
20962
20963
20964
20965
20966
20967
20968
20969
20970
20971
20972
20973
20974
20975
20976
20977
20978
20979
20980
20981
20982
20983
20984
20985
20986
20987
20988
20989
20990
20991
20992
20993
20994
20995
20996
20997
20998
20999
21000
21001
21002
21003
21004
21005
21006
21007
21008
21009
21010
21011
21012
21013
21014
21015
21016
21017
21018
21019
21020
21021
21022
21023
21024
21025
21026
21027
21028
21029
21030
21031
21032
21033
21034
21035
21036
21037
21038
21039
21040
21041
21042
21043
21044
21045
21046
21047
21048
21049
21050
21051
21052
21053
21054
21055
21056
21057
21058
21059
21060
21061
21062
21063
21064
21065
21066
21067
21068
21069
21070
21071
21072
21073
21074
21075
21076
21077
21078
21079
21080
21081
21082
21083
21084
21085
21086
21087
21088
21089
21090
21091
21092
21093
21094
21095
21096
21097
21098
21099
21100
21101
21102
21103
21104
21105
21106
21107
21108
21109
21110
21111
21112
21113
21114
21115
21116
21117
21118
21119
21120
21121
21122
21123
21124
21125
21126
21127
21128
21129
21130
21131
21132
21133
21134
21135
21136
21137
21138
21139
21140
21141
21142
21143
21144
21145
21146
21147
21148
21149
21150
21151
21152
21153
21154
21155
21156
21157
21158
21159
21160
21161
21162
21163
21164
21165
21166
21167
21168
21169
21170
21171
21172
21173
21174
21175
21176
21177
21178
21179
21180
21181
21182
21183
21184
21185
21186
21187
21188
21189
21190
21191
21192
21193
21194
21195
21196
21197
21198
21199
21200
21201
21202
21203
21204
21205
21206
21207
21208
21209
21210
21211
21212
21213
21214
21215
21216
21217
21218
21219
21220
21221
21222
21223
21224
21225
21226
21227
21228
21229
21230
21231
21232
21233
21234
21235
21236
21237
21238
21239
21240
21241
21242
21243
21244
21245
21246
21247
21248
21249
21250
21251
21252
21253
21254
21255
21256
21257
21258
21259
21260
21261
21262
21263
21264
21265
21266
21267
21268
21269
21270
21271
21272
21273
21274
21275
21276
21277
21278
21279
21280
21281
21282
21283
21284
21285
21286
21287
21288
21289
21290
21291
21292
21293
21294
21295
21296
21297
21298
21299
21300
21301
21302
21303
21304
21305
21306
21307
21308
21309
21310
21311
21312
21313
21314
21315
21316
21317
21318
21319
21320
21321
21322
21323
21324
21325
21326
21327
21328
21329
21330
21331
21332
21333
21334
21335
21336
21337
21338
21339
21340
21341
21342
21343
21344
21345
21346
21347
21348
21349
21350
21351
21352
21353
21354
21355
21356
21357
21358
21359
21360
21361
21362
21363
21364
21365
21366
21367
21368
21369
21370
21371
21372
21373
21374
21375
21376
21377
21378
21379
21380
21381
21382
21383
21384
21385
21386
21387
21388
21389
21390
21391
21392
21393
21394
21395
21396
21397
21398
21399
21400
21401
21402
21403
21404
21405
21406
21407
21408
21409
21410
21411
21412
21413
21414
21415
21416
21417
21418
21419
21420
21421
21422
21423
21424
21425
21426
21427
21428
21429
21430
21431
21432
21433
21434
21435
21436
21437
21438
21439
21440
21441
21442
21443
21444
21445
21446
21447
21448
21449
21450
21451
21452
21453
21454
21455
21456
21457
21458
21459
21460
21461
21462
21463
21464
21465
21466
21467
21468
21469
21470
21471
21472
21473
21474
21475
21476
21477
21478
21479
21480
21481
21482
21483
21484
21485
21486
21487
21488
21489
21490
21491
21492
21493
21494
21495
21496
21497
21498
21499
21500
21501
21502
21503
21504
21505
21506
21507
21508
21509
21510
21511
21512
21513
21514
21515
21516
21517
21518
21519
21520
21521
21522
21523
21524
21525
21526
21527
21528
21529
21530
21531
21532
21533
21534
21535
21536
21537
21538
21539
21540
21541
21542
21543
21544
21545
21546
21547
21548
21549
21550
21551
21552
21553
21554
21555
21556
21557
21558
21559
21560
21561
21562
21563
21564
21565
21566
21567
21568
21569
21570
21571
21572
21573
21574
21575
21576
21577
21578
21579
21580
21581
21582
21583
21584
21585
21586
21587
21588
21589
21590
21591
21592
21593
21594
21595
21596
21597
21598
21599
21600
21601
21602
21603
21604
21605
21606
21607
21608
21609
21610
21611
21612
21613
21614
21615
21616
21617
21618
21619
21620
21621
21622
21623
21624
21625
21626
21627
21628
21629
21630
21631
21632
21633
21634
21635
21636
21637
21638
21639
21640
21641
21642
21643
21644
21645
21646
21647
21648
21649
21650
21651
21652
21653
21654
21655
21656
21657
21658
21659
21660
21661
21662
21663
21664
21665
21666
21667
21668
21669
21670
21671
21672
21673
21674
21675
21676
21677
21678
21679
21680
21681
21682
21683
21684
21685
21686
21687
21688
21689
21690
21691
21692
21693
21694
21695
21696
21697
21698
21699
21700
21701
21702
21703
21704
21705
21706
21707
21708
21709
21710
21711
21712
21713
21714
21715
21716
21717
21718
21719
21720
21721
21722
21723
21724
21725
21726
21727
21728
21729
21730
21731
21732
21733
21734
21735
21736
21737
21738
21739
21740
21741
21742
21743
21744
21745
21746
21747
21748
21749
21750
21751
21752
21753
21754
21755
21756
21757
21758
21759
21760
21761
21762
21763
21764
21765
21766
21767
21768
21769
21770
21771
21772
21773
21774
21775
21776
21777
21778
21779
21780
21781
21782
21783
21784
21785
21786
21787
21788
21789
21790
21791
21792
21793
21794
21795
21796
21797
21798
21799
21800
21801
21802
21803
21804
21805
21806
21807
21808
21809
21810
21811
21812
21813
21814
21815
21816
21817
21818
21819
21820
21821
21822
21823
21824
21825
21826
21827
21828
21829
21830
21831
21832
21833
21834
21835
21836
21837
21838
21839
21840
21841
21842
21843
21844
21845
21846
21847
21848
21849
21850
21851
21852
21853
21854
21855
21856
21857
21858
21859
21860
21861
21862
21863
21864
21865
21866
21867
21868
21869
21870
21871
21872
21873
21874
21875
21876
21877
21878
21879
21880
21881
21882
21883
21884
21885
21886
21887
21888
21889
21890
21891
21892
21893
21894
21895
21896
21897
21898
21899
21900
21901
21902
21903
21904
21905
21906
21907
21908
21909
21910
21911
21912
21913
21914
21915
21916
21917
21918
21919
21920
21921
21922
21923
21924
21925
21926
21927
21928
21929
21930
21931
21932
21933
21934
21935
21936
21937
21938
21939
21940
21941
21942
21943
21944
21945
21946
21947
21948
21949
21950
21951
21952
21953
21954
21955
21956
21957
21958
21959
21960
21961
21962
21963
21964
21965
21966
21967
21968
21969
21970
21971
21972
21973
21974
21975
21976
21977
21978
21979
21980
21981
21982
21983
21984
21985
21986
21987
21988
21989
21990
21991
21992
21993
21994
21995
21996
21997
21998
21999
22000
22001
22002
22003
22004
22005
22006
22007
22008
22009
22010
22011
22012
22013
22014
22015
22016
22017
22018
22019
22020
22021
22022
22023
22024
22025
22026
22027
22028
22029
22030
22031
22032
22033
22034
22035
22036
22037
22038
22039
22040
22041
22042
22043
22044
22045
22046
22047
22048
22049
22050
22051
22052
22053
22054
22055
22056
22057
22058
22059
22060
22061
22062
22063
22064
22065
22066
22067
22068
22069
22070
22071
22072
22073
22074
22075
22076
22077
22078
22079
22080
22081
22082
22083
22084
22085
22086
22087
22088
22089
22090
22091
22092
22093
22094
22095
22096
22097
22098
22099
22100
22101
22102
22103
22104
22105
22106
22107
22108
22109
22110
22111
22112
22113
22114
22115
22116
22117
22118
22119
22120
22121
22122
22123
22124
22125
22126
22127
22128
22129
22130
22131
22132
22133
22134
22135
22136
22137
22138
22139
22140
22141
22142
22143
22144
22145
22146
22147
22148
22149
22150
22151
22152
22153
22154
22155
22156
22157
22158
22159
22160
22161
22162
22163
22164
22165
22166
22167
22168
22169
22170
22171
22172
22173
22174
22175
22176
22177
22178
22179
22180
22181
22182
22183
22184
22185
22186
22187
22188
22189
22190
22191
22192
22193
22194
22195
22196
22197
22198
22199
22200
22201
22202
22203
22204
22205
22206
22207
22208
22209
22210
22211
22212
22213
22214
22215
22216
22217
22218
22219
22220
22221
22222
22223
22224
22225
22226
22227
22228
22229
22230
22231
22232
22233
22234
22235
22236
22237
22238
22239
22240
22241
22242
22243
22244
22245
22246
22247
22248
22249
22250
22251
22252
22253
22254
22255
22256
22257
22258
22259
22260
22261
22262
22263
22264
22265
22266
22267
22268
22269
22270
22271
22272
22273
22274
22275
22276
22277
22278
22279
22280
22281
22282
22283
22284
22285
22286
22287
22288
22289
22290
22291
22292
22293
22294
22295
22296
22297
22298
22299
22300
22301
22302
22303
22304
22305
22306
22307
22308
22309
22310
22311
22312
22313
22314
22315
22316
22317
22318
22319
22320
22321
22322
22323
22324
22325
22326
22327
22328
22329
22330
22331
22332
22333
22334
22335
22336
22337
22338
22339
22340
22341
22342
22343
22344
22345
22346
22347
22348
22349
22350
22351
22352
22353
22354
22355
22356
22357
22358
22359
22360
22361
22362
22363
22364
22365
22366
22367
22368
22369
22370
22371
22372
22373
22374
22375
22376
22377
22378
22379
22380
22381
22382
22383
22384
22385
22386
22387
22388
22389
22390
22391
22392
22393
22394
22395
22396
22397
22398
22399
22400
22401
22402
22403
22404
22405
22406
22407
22408
22409
22410
22411
22412
22413
22414
22415
22416
22417
22418
22419
22420
22421
22422
22423
22424
22425
22426
22427
22428
22429
22430
22431
22432
22433
22434
22435
22436
22437
22438
22439
22440
22441
22442
22443
22444
22445
22446
22447
22448
22449
22450
22451
22452
22453
22454
22455
22456
22457
22458
22459
22460
22461
22462
22463
22464
22465
22466
22467
22468
22469
22470
22471
22472
22473
22474
22475
22476
22477
22478
22479
22480
22481
22482
22483
22484
22485
22486
22487
22488
22489
22490
22491
22492
22493
22494
22495
22496
22497
22498
22499
22500
22501
22502
22503
22504
22505
22506
22507
22508
22509
22510
22511
22512
22513
22514
22515
22516
22517
22518
22519
22520
22521
22522
22523
22524
22525
22526
22527
22528
22529
22530
22531
22532
22533
22534
22535
22536
22537
22538
22539
22540
22541
22542
22543
22544
22545
22546
22547
22548
22549
22550
22551
22552
22553
22554
22555
22556
22557
22558
22559
22560
22561
22562
22563
22564
22565
22566
22567
22568
22569
22570
22571
22572
22573
22574
22575
22576
22577
22578
22579
22580
22581
22582
22583
22584
22585
22586
22587
22588
22589
22590
22591
22592
22593
22594
22595
22596
22597
22598
22599
22600
22601
22602
22603
22604
22605
22606
22607
22608
22609
22610
22611
22612
22613
22614
22615
22616
22617
22618
22619
22620
22621
22622
22623
22624
22625
22626
22627
22628
22629
22630
22631
22632
22633
22634
22635
22636
22637
22638
22639
22640
22641
22642
22643
22644
22645
22646
22647
22648
22649
22650
22651
22652
22653
22654
22655
22656
22657
22658
22659
22660
22661
22662
22663
22664
22665
22666
22667
22668
22669
22670
22671
22672
22673
22674
22675
22676
22677
22678
22679
22680
22681
22682
22683
22684
22685
22686
22687
22688
22689
22690
22691
22692
22693
22694
22695
22696
22697
22698
22699
22700
22701
22702
22703
22704
22705
22706
22707
22708
22709
22710
22711
22712
22713
22714
22715
22716
22717
22718
22719
22720
22721
22722
22723
22724
22725
22726
22727
22728
22729
22730
22731
22732
22733
22734
22735
22736
22737
22738
22739
22740
22741
22742
22743
22744
22745
22746
22747
22748
22749
22750
22751
22752
22753
22754
22755
22756
22757
22758
22759
22760
22761
22762
22763
22764
22765
22766
22767
22768
22769
22770
22771
22772
22773
22774
22775
22776
22777
22778
22779
22780
22781
22782
22783
22784
22785
22786
22787
22788
22789
22790
22791
22792
22793
22794
22795
22796
22797
22798
22799
22800
22801
22802
22803
22804
22805
22806
22807
22808
22809
22810
22811
22812
22813
22814
22815
22816
22817
22818
22819
22820
22821
22822
22823
22824
22825
22826
22827
22828
22829
22830
22831
22832
22833
22834
22835
22836
22837
22838
22839
22840
22841
22842
22843
22844
22845
22846
22847
22848
22849
22850
22851
22852
22853
22854
22855
22856
22857
22858
22859
22860
22861
22862
22863
22864
22865
22866
22867
22868
22869
22870
22871
22872
22873
22874
22875
22876
22877
22878
22879
22880
22881
22882
22883
22884
22885
22886
22887
22888
22889
22890
22891
22892
22893
22894
22895
22896
22897
22898
22899
22900
22901
22902
22903
22904
22905
22906
22907
22908
22909
22910
22911
22912
22913
22914
22915
22916
22917
22918
22919
22920
22921
22922
22923
22924
22925
22926
22927
22928
22929
22930
22931
22932
22933
22934
22935
22936
22937
22938
22939
22940
22941
22942
22943
22944
22945
22946
22947
22948
22949
22950
22951
22952
22953
22954
22955
22956
22957
22958
22959
22960
22961
22962
22963
22964
22965
22966
22967
22968
22969
22970
22971
22972
22973
22974
22975
22976
22977
22978
22979
22980
22981
22982
22983
22984
22985
22986
22987
22988
22989
22990
22991
22992
22993
22994
22995
22996
22997
22998
22999
23000
23001
23002
23003
23004
23005
23006
23007
23008
23009
23010
23011
23012
23013
23014
23015
23016
23017
23018
23019
23020
23021
23022
23023
23024
23025
23026
23027
23028
23029
23030
23031
23032
23033
23034
23035
23036
23037
23038
23039
23040
23041
23042
23043
23044
23045
23046
23047
23048
23049
23050
23051
23052
23053
23054
23055
23056
23057
23058
23059
23060
23061
23062
23063
23064
23065
23066
23067
23068
23069
23070
23071
23072
23073
23074
23075
23076
23077
23078
23079
23080
23081
23082
23083
23084
23085
23086
23087
23088
23089
23090
23091
23092
23093
23094
23095
23096
23097
23098
23099
23100
23101
23102
23103
23104
23105
23106
23107
23108
23109
23110
23111
23112
23113
23114
23115
23116
23117
23118
23119
23120
23121
23122
23123
23124
23125
23126
23127
23128
23129
23130
23131
23132
23133
23134
23135
23136
23137
23138
23139
23140
23141
23142
23143
23144
23145
23146
23147
23148
23149
23150
23151
23152
23153
23154
23155
23156
23157
23158
23159
23160
23161
23162
23163
23164
23165
23166
23167
23168
23169
23170
23171
23172
23173
23174
23175
23176
23177
23178
23179
23180
23181
23182
23183
23184
23185
23186
23187
23188
23189
23190
23191
23192
23193
23194
23195
23196
23197
23198
23199
23200
23201
23202
23203
23204
23205
23206
23207
23208
23209
23210
23211
23212
23213
23214
23215
23216
23217
23218
23219
23220
23221
23222
23223
23224
23225
23226
23227
23228
23229
23230
23231
23232
23233
23234
23235
23236
23237
23238
23239
23240
23241
23242
23243
23244
23245
23246
23247
23248
23249
23250
23251
23252
23253
23254
23255
23256
23257
23258
23259
23260
23261
23262
23263
23264
23265
23266
23267
23268
23269
23270
23271
23272
23273
23274
23275
23276
23277
23278
23279
23280
23281
23282
23283
23284
23285
23286
23287
23288
23289
23290
23291
23292
23293
23294
23295
23296
23297
23298
23299
23300
23301
23302
23303
23304
23305
23306
23307
23308
23309
23310
23311
23312
23313
23314
23315
23316
23317
23318
23319
23320
23321
23322
23323
23324
23325
23326
23327
23328
23329
23330
23331
23332
23333
23334
23335
23336
23337
23338
23339
23340
23341
23342
23343
23344
23345
23346
23347
23348
23349
23350
23351
23352
23353
23354
23355
23356
23357
23358
23359
23360
23361
23362
23363
23364
23365
23366
23367
23368
23369
23370
23371
23372
23373
23374
23375
23376
23377
23378
23379
23380
23381
23382
23383
23384
23385
23386
23387
23388
23389
23390
23391
23392
23393
23394
23395
23396
23397
23398
23399
23400
23401
23402
23403
23404
23405
23406
23407
23408
23409
23410
23411
23412
23413
23414
23415
23416
23417
23418
23419
23420
23421
23422
23423
23424
23425
23426
23427
23428
23429
23430
23431
23432
23433
23434
23435
23436
23437
23438
23439
23440
23441
23442
23443
23444
23445
23446
23447
23448
23449
23450
23451
23452
23453
23454
23455
23456
23457
23458
23459
23460
23461
23462
23463
23464
23465
23466
23467
23468
23469
23470
23471
23472
23473
23474
23475
23476
23477
23478
23479
23480
23481
23482
23483
23484
23485
23486
23487
23488
23489
23490
23491
23492
23493
23494
23495
23496
23497
23498
23499
23500
23501
23502
23503
23504
23505
23506
23507
23508
23509
23510
23511
23512
23513
23514
23515
23516
23517
23518
23519
23520
23521
23522
23523
23524
23525
23526
23527
23528
23529
23530
23531
23532
23533
23534
23535
23536
23537
23538
23539
23540
23541
23542
23543
23544
23545
23546
23547
23548
23549
23550
23551
23552
23553
23554
23555
23556
23557
23558
23559
23560
23561
23562
23563
23564
23565
23566
23567
23568
23569
23570
23571
23572
23573
23574
23575
23576
23577
23578
23579
23580
23581
23582
23583
23584
23585
23586
23587
23588
23589
23590
23591
23592
23593
23594
23595
23596
23597
23598
23599
23600
23601
23602
23603
23604
23605
23606
23607
23608
23609
23610
23611
23612
23613
23614
23615
23616
23617
23618
23619
23620
23621
23622
23623
23624
23625
23626
23627
23628
23629
23630
23631
23632
23633
23634
23635
23636
23637
23638
23639
23640
23641
23642
23643
23644
23645
23646
23647
23648
23649
23650
23651
23652
23653
23654
23655
23656
23657
23658
23659
23660
23661
23662
23663
23664
23665
23666
23667
23668
23669
23670
23671
23672
23673
23674
23675
23676
23677
23678
23679
23680
23681
23682
23683
23684
23685
23686
23687
23688
23689
23690
23691
23692
23693
23694
23695
23696
23697
23698
23699
23700
23701
23702
23703
23704
23705
23706
23707
23708
23709
23710
23711
23712
23713
23714
23715
23716
23717
23718
23719
23720
23721
23722
23723
23724
23725
23726
23727
23728
23729
23730
23731
23732
23733
23734
23735
23736
23737
23738
23739
23740
23741
23742
23743
23744
23745
23746
23747
23748
23749
23750
23751
23752
23753
23754
23755
23756
23757
23758
23759
23760
23761
23762
23763
23764
23765
23766
23767
23768
23769
23770
23771
23772
23773
23774
23775
23776
23777
23778
23779
23780
23781
23782
23783
23784
23785
23786
23787
23788
23789
23790
23791
23792
23793
23794
23795
23796
23797
23798
23799
23800
23801
23802
23803
23804
23805
23806
23807
23808
23809
23810
23811
23812
23813
23814
23815
23816
23817
23818
23819
23820
23821
23822
23823
23824
23825
23826
23827
23828
23829
23830
23831
23832
23833
23834
23835
23836
23837
23838
23839
23840
23841
23842
23843
23844
23845
23846
23847
23848
23849
23850
23851
23852
23853
23854
23855
23856
23857
23858
23859
23860
23861
23862
23863
23864
23865
23866
23867
23868
23869
23870
23871
23872
23873
23874
23875
23876
23877
23878
23879
23880
23881
23882
23883
23884
23885
23886
23887
23888
23889
23890
23891
23892
23893
23894
23895
23896
23897
23898
23899
23900
23901
23902
23903
23904
23905
23906
23907
23908
23909
23910
23911
23912
23913
23914
23915
23916
23917
23918
23919
23920
23921
23922
23923
23924
23925
23926
23927
23928
23929
23930
23931
23932
23933
23934
23935
23936
23937
23938
23939
23940
23941
23942
23943
23944
23945
23946
23947
23948
23949
23950
23951
23952
23953
23954
23955
23956
23957
23958
23959
23960
23961
23962
23963
23964
23965
23966
23967
23968
23969
23970
23971
23972
23973
23974
23975
23976
23977
23978
23979
23980
23981
23982
23983
23984
23985
23986
23987
23988
23989
23990
23991
23992
23993
23994
23995
23996
23997
23998
23999
24000
24001
24002
24003
24004
24005
24006
24007
24008
24009
24010
24011
24012
24013
24014
24015
24016
24017
24018
24019
24020
24021
24022
24023
24024
24025
24026
24027
24028
24029
24030
24031
24032
24033
24034
24035
24036
24037
24038
24039
24040
24041
24042
24043
24044
24045
24046
24047
24048
24049
24050
24051
24052
24053
24054
24055
24056
24057
24058
24059
24060
24061
24062
24063
24064
24065
24066
24067
24068
24069
24070
24071
24072
24073
24074
24075
24076
24077
24078
24079
24080
24081
24082
24083
24084
24085
24086
24087
24088
24089
24090
24091
24092
24093
24094
24095
24096
24097
24098
24099
24100
24101
24102
24103
24104
24105
24106
24107
24108
24109
24110
24111
24112
24113
24114
24115
24116
24117
24118
24119
24120
24121
24122
24123
24124
24125
24126
24127
24128
24129
24130
24131
24132
24133
24134
24135
24136
24137
24138
24139
24140
24141
24142
24143
24144
24145
24146
24147
24148
24149
24150
24151
24152
24153
24154
24155
24156
24157
24158
24159
24160
24161
24162
24163
24164
24165
24166
24167
24168
24169
24170
24171
24172
24173
24174
24175
24176
24177
24178
24179
24180
24181
24182
24183
24184
24185
24186
24187
24188
24189
24190
24191
24192
24193
24194
24195
24196
24197
24198
24199
24200
24201
24202
24203
24204
24205
24206
24207
24208
24209
24210
24211
24212
24213
24214
24215
24216
24217
24218
24219
24220
24221
24222
24223
24224
24225
24226
24227
24228
24229
24230
24231
24232
24233
24234
24235
24236
24237
24238
24239
24240
24241
24242
24243
24244
24245
24246
24247
24248
24249
24250
24251
24252
24253
24254
24255
24256
24257
24258
24259
24260
24261
24262
24263
24264
24265
24266
24267
24268
24269
24270
24271
24272
24273
24274
24275
24276
24277
24278
24279
24280
24281
24282
24283
24284
24285
24286
24287
24288
24289
24290
24291
24292
24293
24294
24295
24296
24297
24298
24299
24300
24301
24302
24303
24304
24305
24306
24307
24308
24309
24310
24311
24312
24313
24314
24315
24316
24317
24318
24319
24320
24321
24322
24323
24324
24325
24326
24327
24328
24329
24330
24331
24332
24333
24334
24335
24336
24337
24338
24339
24340
24341
24342
24343
24344
24345
24346
24347
24348
24349
24350
24351
24352
24353
24354
24355
24356
24357
24358
24359
24360
24361
24362
24363
24364
24365
24366
24367
24368
24369
24370
24371
24372
24373
24374
24375
24376
24377
24378
24379
24380
24381
24382
24383
24384
24385
24386
24387
24388
24389
24390
24391
24392
24393
24394
24395
24396
24397
24398
24399
24400
24401
24402
24403
24404
24405
24406
24407
24408
24409
24410
24411
24412
24413
24414
24415
24416
24417
24418
24419
24420
24421
24422
24423
24424
24425
24426
24427
24428
24429
24430
24431
24432
24433
24434
24435
24436
24437
24438
24439
24440
24441
24442
24443
24444
24445
24446
24447
24448
24449
24450
24451
24452
24453
24454
24455
24456
24457
24458
24459
24460
24461
24462
24463
24464
24465
24466
24467
24468
24469
24470
24471
24472
24473
24474
24475
24476
24477
24478
24479
24480
24481
24482
24483
24484
24485
24486
24487
24488
24489
24490
24491
24492
24493
24494
24495
24496
24497
24498
24499
24500
24501
24502
24503
24504
24505
24506
24507
24508
24509
24510
24511
24512
24513
24514
24515
24516
24517
24518
24519
24520
24521
24522
24523
24524
24525
24526
24527
24528
24529
24530
24531
24532
24533
24534
24535
24536
24537
24538
24539
24540
24541
24542
24543
24544
24545
24546
24547
24548
24549
24550
24551
24552
24553
24554
24555
24556
24557
24558
24559
24560
24561
24562
24563
24564
24565
24566
24567
24568
24569
24570
24571
24572
24573
24574
24575
24576
24577
24578
24579
24580
24581
24582
24583
24584
24585
24586
24587
24588
24589
24590
24591
24592
24593
24594
24595
24596
24597
24598
24599
24600
24601
24602
24603
24604
24605
24606
24607
24608
24609
24610
24611
24612
24613
24614
24615
24616
24617
24618
24619
24620
24621
24622
24623
24624
24625
24626
24627
24628
24629
24630
24631
24632
24633
24634
24635
24636
24637
24638
24639
24640
24641
24642
24643
24644
24645
24646
24647
24648
24649
24650
24651
24652
24653
24654
24655
24656
24657
24658
24659
24660
24661
24662
24663
24664
24665
24666
24667
24668
24669
24670
24671
24672
24673
24674
24675
24676
24677
24678
24679
24680
24681
24682
24683
24684
24685
24686
24687
24688
24689
24690
24691
24692
24693
24694
24695
24696
24697
24698
24699
24700
24701
24702
24703
24704
24705
24706
24707
24708
24709
24710
24711
24712
24713
24714
24715
24716
24717
24718
24719
24720
24721
24722
24723
24724
24725
24726
24727
24728
24729
24730
24731
24732
24733
24734
24735
24736
24737
24738
24739
24740
24741
24742
24743
24744
24745
24746
24747
24748
24749
24750
24751
24752
24753
24754
24755
24756
24757
24758
24759
24760
24761
24762
24763
24764
24765
24766
24767
24768
24769
24770
24771
24772
24773
24774
24775
24776
24777
24778
24779
24780
24781
24782
24783
24784
24785
24786
24787
24788
24789
24790
24791
24792
24793
24794
24795
24796
24797
24798
24799
24800
24801
24802
24803
24804
24805
24806
24807
24808
24809
24810
24811
24812
24813
24814
24815
24816
24817
24818
24819
24820
24821
24822
24823
24824
24825
24826
24827
24828
24829
24830
24831
24832
24833
24834
24835
24836
24837
24838
24839
24840
24841
24842
24843
24844
24845
24846
24847
24848
24849
24850
24851
24852
24853
24854
24855
24856
24857
24858
24859
24860
24861
24862
24863
24864
24865
24866
24867
24868
24869
24870
24871
24872
24873
24874
24875
24876
24877
24878
24879
24880
24881
24882
24883
24884
24885
24886
24887
24888
24889
24890
24891
24892
24893
24894
24895
24896
24897
24898
24899
24900
24901
24902
24903
24904
24905
24906
24907
24908
24909
24910
24911
24912
24913
24914
24915
24916
24917
24918
24919
24920
24921
24922
24923
24924
24925
24926
24927
24928
24929
24930
24931
24932
24933
24934
24935
24936
24937
24938
24939
24940
24941
24942
24943
24944
24945
24946
24947
24948
24949
24950
24951
24952
24953
24954
24955
24956
24957
24958
24959
24960
24961
24962
24963
24964
24965
24966
24967
24968
24969
24970
24971
24972
24973
24974
24975
24976
24977
24978
24979
24980
24981
24982
24983
24984
24985
24986
24987
24988
24989
24990
24991
24992
24993
24994
24995
24996
24997
24998
24999
25000
25001
25002
25003
25004
25005
25006
25007
25008
25009
25010
25011
25012
25013
25014
25015
25016
25017
25018
25019
25020
25021
25022
25023
25024
25025
25026
25027
25028
25029
25030
25031
25032
25033
25034
25035
25036
25037
25038
25039
25040
25041
25042
25043
25044
25045
25046
25047
25048
25049
25050
25051
25052
25053
25054
25055
25056
25057
25058
25059
25060
25061
25062
25063
25064
25065
25066
25067
25068
25069
25070
25071
25072
25073
25074
25075
25076
25077
25078
25079
25080
25081
25082
25083
25084
25085
25086
25087
25088
25089
25090
25091
25092
25093
25094
25095
25096
25097
25098
25099
25100
25101
25102
25103
25104
25105
25106
25107
25108
25109
25110
25111
25112
25113
25114
25115
25116
25117
25118
25119
25120
25121
25122
25123
25124
25125
25126
25127
25128
25129
25130
25131
25132
25133
25134
25135
25136
25137
25138
25139
25140
25141
25142
25143
25144
25145
25146
25147
25148
25149
25150
25151
25152
25153
25154
25155
25156
25157
25158
25159
25160
25161
25162
25163
25164
25165
25166
25167
25168
25169
25170
25171
25172
25173
25174
25175
25176
25177
25178
25179
25180
25181
25182
25183
25184
25185
25186
25187
25188
25189
25190
25191
25192
25193
25194
25195
25196
25197
25198
25199
25200
25201
25202
25203
25204
25205
25206
25207
25208
25209
25210
25211
25212
25213
25214
25215
25216
25217
25218
25219
25220
25221
25222
25223
25224
25225
25226
25227
25228
25229
25230
25231
25232
25233
25234
25235
25236
25237
25238
25239
25240
25241
25242
25243
25244
25245
25246
25247
25248
25249
25250
25251
25252
25253
25254
25255
25256
25257
25258
25259
25260
25261
25262
25263
25264
25265
25266
25267
25268
25269
25270
25271
25272
25273
25274
25275
25276
25277
25278
25279
25280
25281
25282
25283
25284
25285
25286
25287
25288
25289
25290
25291
25292
25293
25294
25295
25296
25297
25298
25299
25300
25301
25302
25303
25304
25305
25306
25307
25308
25309
25310
25311
25312
25313
25314
25315
25316
25317
25318
25319
25320
25321
25322
25323
25324
25325
25326
25327
25328
25329
25330
25331
25332
25333
25334
25335
25336
25337
25338
25339
25340
25341
25342
25343
25344
25345
25346
25347
25348
25349
25350
25351
25352
25353
25354
25355
25356
25357
25358
25359
25360
25361
25362
25363
25364
25365
25366
25367
25368
25369
25370
25371
25372
25373
25374
25375
25376
25377
25378
25379
25380
25381
25382
25383
25384
25385
25386
25387
25388
25389
25390
25391
25392
25393
25394
25395
25396
25397
25398
25399
25400
25401
25402
25403
25404
25405
25406
25407
25408
25409
25410
25411
25412
25413
25414
25415
25416
25417
25418
25419
25420
25421
25422
25423
25424
25425
25426
25427
25428
25429
25430
25431
25432
25433
25434
25435
25436
25437
25438
25439
25440
25441
25442
25443
25444
25445
25446
25447
25448
25449
25450
25451
25452
25453
25454
25455
25456
25457
25458
25459
25460
25461
25462
25463
25464
25465
25466
25467
25468
25469
25470
25471
25472
25473
25474
25475
25476
25477
25478
25479
25480
25481
25482
25483
25484
25485
25486
25487
25488
25489
25490
25491
25492
25493
25494
25495
25496
25497
25498
25499
25500
25501
25502
25503
25504
25505
25506
25507
25508
25509
25510
25511
25512
25513
25514
25515
25516
25517
25518
25519
25520
25521
25522
25523
25524
25525
25526
25527
25528
25529
25530
25531
25532
25533
25534
25535
25536
25537
25538
25539
25540
25541
25542
25543
25544
25545
25546
25547
25548
25549
25550
25551
25552
25553
25554
25555
25556
25557
25558
25559
25560
25561
25562
25563
25564
25565
25566
25567
25568
25569
25570
25571
25572
25573
25574
25575
25576
25577
25578
25579
25580
25581
25582
25583
25584
25585
25586
25587
25588
25589
25590
25591
25592
25593
25594
25595
25596
25597
25598
25599
25600
25601
25602
25603
25604
25605
25606
25607
25608
25609
25610
25611
25612
25613
25614
25615
25616
25617
25618
25619
25620
25621
25622
25623
25624
25625
25626
25627
25628
25629
25630
25631
25632
25633
25634
25635
25636
25637
25638
25639
25640
25641
25642
25643
25644
25645
25646
25647
25648
25649
25650
25651
25652
25653
25654
25655
25656
25657
25658
25659
25660
25661
25662
25663
25664
25665
25666
25667
25668
25669
25670
25671
25672
25673
25674
25675
25676
25677
25678
25679
25680
25681
25682
25683
25684
25685
25686
25687
25688
25689
25690
25691
25692
25693
25694
25695
25696
25697
25698
25699
25700
25701
25702
25703
25704
25705
25706
25707
25708
25709
25710
25711
25712
25713
25714
25715
25716
25717
25718
25719
25720
25721
25722
25723
25724
25725
25726
25727
25728
25729
25730
25731
25732
25733
25734
25735
25736
25737
25738
25739
25740
25741
25742
25743
25744
25745
25746
25747
25748
25749
25750
25751
25752
25753
25754
25755
25756
25757
25758
25759
25760
25761
25762
25763
25764
25765
25766
25767
25768
25769
25770
25771
25772
25773
25774
25775
25776
25777
25778
25779
25780
25781
25782
25783
25784
25785
25786
25787
25788
25789
25790
25791
25792
25793
25794
25795
25796
25797
25798
25799
25800
25801
25802
25803
25804
25805
25806
25807
25808
25809
25810
25811
25812
25813
25814
25815
25816
25817
25818
25819
25820
25821
25822
25823
25824
25825
25826
25827
25828
25829
25830
25831
25832
25833
25834
25835
25836
25837
25838
25839
25840
25841
25842
25843
25844
25845
25846
25847
25848
25849
25850
25851
25852
25853
25854
25855
25856
25857
25858
25859
25860
25861
25862
25863
25864
25865
25866
25867
25868
25869
25870
25871
25872
25873
25874
25875
25876
25877
25878
25879
25880
25881
25882
25883
25884
25885
25886
25887
25888
25889
25890
25891
25892
25893
25894
25895
25896
25897
25898
25899
25900
25901
25902
25903
25904
25905
25906
25907
25908
25909
25910
25911
25912
25913
25914
25915
25916
25917
25918
25919
25920
25921
25922
25923
25924
25925
25926
25927
25928
25929
25930
25931
25932
25933
25934
25935
25936
25937
25938
25939
25940
25941
25942
25943
25944
25945
25946
25947
25948
25949
25950
25951
25952
25953
25954
25955
25956
25957
25958
25959
25960
25961
25962
25963
25964
25965
25966
25967
25968
25969
25970
25971
25972
25973
25974
25975
25976
25977
25978
25979
25980
25981
25982
25983
25984
25985
25986
25987
25988
25989
25990
25991
25992
25993
25994
25995
25996
25997
25998
25999
26000
26001
26002
26003
26004
26005
26006
26007
26008
26009
26010
26011
26012
26013
26014
26015
26016
26017
26018
26019
26020
26021
26022
26023
26024
26025
26026
26027
26028
26029
26030
26031
26032
26033
26034
26035
26036
26037
26038
26039
26040
26041
26042
26043
26044
26045
26046
26047
26048
26049
26050
26051
26052
26053
26054
26055
26056
26057
26058
26059
26060
26061
26062
26063
26064
26065
26066
26067
26068
26069
26070
26071
26072
26073
26074
26075
26076
26077
26078
26079
26080
26081
26082
26083
26084
26085
26086
26087
26088
26089
26090
26091
26092
26093
26094
26095
26096
26097
26098
26099
26100
26101
26102
26103
26104
26105
26106
26107
26108
26109
26110
26111
26112
26113
26114
26115
26116
26117
26118
26119
26120
26121
26122
26123
26124
26125
26126
26127
26128
26129
26130
26131
26132
26133
26134
26135
26136
26137
26138
26139
26140
26141
26142
26143
26144
26145
26146
26147
26148
26149
26150
26151
26152
26153
26154
26155
26156
26157
26158
26159
26160
26161
26162
26163
26164
26165
26166
26167
26168
26169
26170
26171
26172
26173
26174
26175
26176
26177
26178
26179
26180
26181
26182
26183
26184
26185
26186
26187
26188
26189
26190
26191
26192
26193
26194
26195
26196
26197
26198
26199
26200
26201
26202
26203
26204
26205
26206
26207
26208
26209
26210
26211
26212
26213
26214
26215
26216
26217
26218
26219
26220
26221
26222
26223
26224
26225
26226
26227
26228
26229
26230
26231
26232
26233
26234
26235
26236
26237
26238
26239
26240
26241
26242
26243
26244
26245
26246
26247
26248
26249
26250
26251
26252
26253
26254
26255
26256
26257
26258
26259
26260
26261
26262
26263
26264
26265
26266
26267
26268
26269
26270
26271
26272
26273
26274
26275
26276
26277
26278
26279
26280
26281
26282
26283
26284
26285
26286
26287
26288
26289
26290
26291
26292
26293
26294
26295
26296
26297
26298
26299
26300
26301
26302
26303
26304
26305
26306
26307
26308
26309
26310
26311
26312
26313
26314
26315
26316
26317
26318
26319
26320
26321
26322
26323
26324
26325
26326
26327
26328
26329
26330
26331
26332
26333
26334
26335
26336
26337
26338
26339
26340
26341
26342
26343
26344
26345
26346
26347
26348
26349
26350
26351
26352
26353
26354
26355
26356
26357
26358
26359
26360
26361
26362
26363
26364
26365
26366
26367
26368
26369
26370
26371
26372
26373
26374
26375
26376
26377
26378
26379
26380
26381
26382
26383
26384
26385
26386
26387
26388
26389
26390
26391
26392
26393
26394
26395
26396
26397
26398
26399
26400
26401
26402
26403
26404
26405
26406
26407
26408
26409
26410
26411
26412
26413
26414
26415
26416
26417
26418
26419
26420
26421
26422
26423
26424
26425
26426
26427
26428
26429
26430
26431
26432
26433
26434
26435
26436
26437
26438
26439
26440
26441
26442
26443
26444
26445
26446
26447
26448
26449
26450
26451
26452
26453
26454
26455
26456
26457
26458
26459
26460
26461
26462
26463
26464
26465
26466
26467
26468
26469
26470
26471
26472
26473
26474
26475
26476
26477
26478
26479
26480
26481
26482
26483
26484
26485
26486
26487
26488
26489
26490
26491
26492
26493
26494
26495
26496
26497
26498
26499
26500
26501
26502
26503
26504
26505
26506
26507
26508
26509
26510
26511
26512
26513
26514
26515
26516
26517
26518
26519
26520
26521
26522
26523
26524
26525
26526
26527
26528
26529
26530
26531
26532
26533
26534
26535
26536
26537
26538
26539
26540
26541
26542
26543
26544
26545
26546
26547
26548
26549
26550
26551
26552
26553
26554
26555
26556
26557
26558
26559
26560
26561
26562
26563
26564
26565
26566
26567
26568
26569
26570
26571
26572
26573
26574
26575
26576
26577
26578
26579
26580
26581
26582
26583
26584
26585
26586
26587
26588
26589
26590
26591
26592
26593
26594
26595
26596
26597
26598
26599
26600
26601
26602
26603
26604
26605
26606
26607
26608
26609
26610
26611
26612
26613
26614
26615
26616
26617
26618
26619
26620
26621
26622
26623
26624
26625
26626
26627
26628
26629
26630
26631
26632
26633
26634
26635
26636
26637
26638
26639
26640
26641
26642
26643
26644
26645
26646
26647
26648
26649
26650
26651
26652
26653
26654
26655
26656
26657
26658
26659
26660
26661
26662
26663
26664
26665
26666
26667
26668
26669
26670
26671
26672
26673
26674
26675
26676
26677
26678
26679
26680
26681
26682
26683
26684
26685
26686
26687
26688
26689
26690
26691
26692
26693
26694
26695
26696
26697
26698
26699
26700
26701
26702
26703
26704
26705
26706
26707
26708
26709
26710
26711
26712
26713
26714
26715
26716
26717
26718
26719
26720
26721
26722
26723
26724
26725
26726
26727
26728
26729
26730
26731
26732
26733
26734
26735
26736
26737
26738
26739
26740
26741
26742
26743
26744
26745
26746
26747
26748
26749
26750
26751
26752
26753
26754
26755
26756
26757
26758
26759
26760
26761
26762
26763
26764
26765
26766
26767
26768
26769
26770
26771
26772
26773
26774
26775
26776
26777
26778
26779
26780
26781
26782
26783
26784
26785
26786
26787
26788
26789
26790
26791
26792
26793
26794
26795
26796
26797
26798
26799
26800
26801
26802
26803
26804
26805
26806
26807
26808
26809
26810
26811
26812
26813
26814
26815
26816
26817
26818
26819
26820
26821
26822
26823
26824
26825
26826
26827
26828
26829
26830
26831
26832
26833
26834
26835
26836
26837
26838
26839
26840
26841
26842
26843
26844
26845
26846
26847
26848
26849
26850
26851
26852
26853
26854
26855
26856
26857
26858
26859
26860
26861
26862
26863
26864
26865
26866
26867
26868
26869
26870
26871
26872
26873
26874
26875
26876
26877
26878
26879
26880
26881
26882
26883
26884
26885
26886
26887
26888
26889
26890
26891
26892
26893
26894
26895
26896
26897
26898
26899
26900
26901
26902
26903
26904
26905
26906
26907
26908
26909
26910
26911
26912
26913
26914
26915
26916
26917
26918
26919
26920
26921
26922
26923
26924
26925
26926
26927
26928
26929
26930
26931
26932
26933
26934
26935
26936
26937
26938
26939
26940
26941
26942
26943
26944
26945
26946
26947
26948
26949
26950
26951
26952
26953
26954
26955
26956
26957
26958
26959
26960
26961
26962
26963
26964
26965
26966
26967
26968
26969
26970
26971
26972
26973
26974
26975
26976
26977
26978
26979
26980
26981
26982
26983
26984
26985
26986
26987
26988
26989
26990
26991
26992
26993
26994
26995
26996
26997
26998
26999
27000
27001
27002
27003
27004
27005
27006
27007
27008
27009
27010
27011
27012
27013
27014
27015
27016
27017
27018
27019
27020
27021
27022
27023
27024
27025
27026
27027
27028
27029
27030
27031
27032
27033
27034
27035
27036
27037
27038
27039
27040
27041
27042
27043
27044
27045
27046
27047
27048
27049
27050
27051
27052
27053
27054
27055
27056
27057
27058
27059
27060
27061
27062
27063
27064
27065
27066
27067
27068
27069
27070
27071
27072
27073
27074
27075
27076
27077
27078
27079
27080
27081
27082
27083
27084
27085
27086
27087
27088
27089
27090
27091
27092
27093
27094
27095
27096
27097
27098
27099
27100
27101
27102
27103
27104
27105
27106
27107
27108
27109
27110
27111
27112
27113
27114
27115
27116
27117
27118
27119
27120
27121
27122
27123
27124
27125
27126
27127
27128
27129
27130
27131
27132
27133
27134
27135
27136
27137
27138
27139
27140
27141
27142
27143
27144
27145
27146
27147
27148
27149
27150
27151
27152
27153
27154
27155
27156
27157
27158
27159
27160
27161
27162
27163
27164
27165
27166
27167
27168
27169
27170
27171
27172
27173
27174
27175
27176
27177
27178
27179
27180
27181
27182
27183
27184
27185
27186
27187
27188
27189
27190
27191
27192
27193
27194
27195
27196
27197
27198
27199
27200
27201
27202
27203
27204
27205
27206
27207
27208
27209
27210
27211
27212
27213
27214
27215
27216
27217
27218
27219
27220
27221
27222
27223
27224
27225
27226
27227
27228
27229
27230
27231
27232
27233
27234
27235
27236
27237
27238
27239
27240
27241
27242
27243
27244
27245
27246
27247
27248
27249
27250
27251
27252
27253
27254
27255
27256
27257
27258
27259
27260
27261
27262
27263
27264
27265
27266
27267
27268
27269
27270
27271
27272
27273
27274
27275
27276
27277
27278
27279
27280
27281
27282
27283
27284
27285
27286
27287
27288
27289
27290
27291
27292
27293
27294
27295
27296
27297
27298
27299
27300
27301
27302
27303
27304
27305
27306
27307
27308
27309
27310
27311
27312
27313
27314
27315
27316
27317
27318
27319
27320
27321
27322
27323
27324
27325
27326
27327
27328
27329
27330
27331
27332
27333
27334
27335
27336
27337
27338
27339
27340
27341
27342
27343
27344
27345
27346
27347
27348
27349
27350
27351
27352
27353
27354
27355
27356
27357
27358
27359
27360
27361
27362
27363
27364
27365
27366
27367
27368
27369
27370
27371
27372
27373
27374
27375
27376
27377
27378
27379
27380
27381
27382
27383
27384
27385
27386
27387
27388
27389
27390
27391
27392
27393
27394
27395
27396
27397
27398
27399
27400
27401
27402
27403
27404
27405
27406
27407
27408
27409
27410
27411
27412
27413
27414
27415
27416
27417
27418
27419
27420
27421
27422
27423
27424
27425
27426
27427
27428
27429
27430
27431
27432
27433
27434
27435
27436
27437
27438
27439
27440
27441
27442
27443
27444
27445
27446
27447
27448
27449
27450
27451
27452
27453
27454
27455
27456
27457
27458
27459
27460
27461
27462
27463
27464
27465
27466
27467
27468
27469
27470
27471
27472
27473
27474
27475
27476
27477
27478
27479
27480
27481
27482
27483
27484
27485
27486
27487
27488
27489
27490
27491
27492
27493
27494
27495
27496
27497
27498
27499
27500
27501
27502
27503
27504
27505
27506
27507
27508
27509
27510
27511
27512
27513
27514
27515
27516
27517
27518
27519
27520
27521
27522
27523
27524
27525
27526
27527
27528
27529
27530
27531
27532
27533
27534
27535
27536
27537
27538
27539
27540
27541
27542
27543
27544
27545
27546
27547
27548
27549
27550
27551
27552
27553
27554
27555
27556
27557
27558
27559
27560
27561
27562
27563
27564
27565
27566
27567
27568
27569
27570
27571
27572
27573
27574
27575
27576
27577
27578
27579
27580
27581
27582
27583
27584
27585
27586
27587
27588
27589
27590
27591
27592
27593
27594
27595
27596
27597
27598
27599
27600
27601
27602
27603
27604
27605
27606
27607
27608
27609
27610
27611
27612
27613
27614
27615
27616
27617
27618
27619
27620
27621
27622
27623
27624
27625
27626
27627
27628
27629
27630
27631
27632
27633
27634
27635
27636
27637
27638
27639
27640
27641
27642
27643
27644
27645
27646
27647
27648
27649
27650
27651
27652
27653
27654
27655
27656
27657
27658
27659
27660
27661
27662
27663
27664
27665
27666
27667
27668
27669
27670
27671
27672
27673
27674
27675
27676
27677
27678
27679
27680
27681
27682
27683
27684
27685
27686
27687
27688
27689
27690
27691
27692
27693
27694
27695
27696
27697
27698
27699
27700
27701
27702
27703
27704
27705
27706
27707
27708
27709
27710
27711
27712
27713
27714
27715
27716
27717
27718
27719
27720
27721
27722
27723
27724
27725
27726
27727
27728
27729
27730
27731
27732
27733
27734
27735
27736
27737
27738
27739
27740
27741
27742
27743
27744
27745
27746
27747
27748
27749
27750
27751
27752
27753
27754
27755
27756
27757
27758
27759
27760
27761
27762
27763
27764
27765
27766
27767
27768
27769
27770
27771
27772
27773
27774
27775
27776
27777
27778
27779
27780
27781
27782
27783
27784
27785
27786
27787
27788
27789
27790
27791
27792
27793
27794
27795
27796
27797
27798
27799
27800
27801
27802
27803
27804
27805
27806
27807
27808
27809
27810
27811
27812
27813
27814
27815
27816
27817
27818
27819
27820
27821
27822
27823
27824
27825
27826
27827
27828
27829
27830
27831
27832
27833
27834
27835
27836
27837
27838
27839
27840
27841
27842
27843
27844
27845
27846
27847
27848
27849
27850
27851
27852
27853
27854
27855
27856
27857
27858
27859
27860
27861
27862
27863
27864
27865
27866
27867
27868
27869
27870
27871
27872
27873
27874
27875
27876
27877
27878
27879
27880
27881
27882
27883
27884
27885
27886
27887
27888
27889
27890
27891
27892
27893
27894
27895
27896
27897
27898
27899
27900
27901
27902
27903
27904
27905
27906
27907
27908
27909
27910
27911
27912
27913
27914
27915
27916
27917
27918
27919
27920
27921
27922
27923
27924
27925
27926
27927
27928
27929
27930
27931
27932
27933
27934
27935
27936
27937
27938
27939
27940
27941
27942
27943
27944
27945
27946
27947
27948
27949
27950
27951
27952
27953
27954
27955
27956
27957
27958
27959
27960
27961
27962
27963
27964
27965
27966
27967
27968
27969
27970
27971
27972
27973
27974
27975
27976
27977
27978
27979
27980
27981
27982
27983
|
==============================
LLVM Language Reference Manual
==============================
.. contents::
:local:
:depth: 3
Abstract
========
This document is a reference manual for the LLVM assembly language. LLVM
is a Static Single Assignment (SSA) based representation that provides
type safety, low-level operations, flexibility, and the capability of
representing 'all' high-level languages cleanly. It is the common code
representation used throughout all phases of the LLVM compilation
strategy.
Introduction
============
The LLVM code representation is designed to be used in three different
forms: as an in-memory compiler IR, as an on-disk bitcode representation
(suitable for fast loading by a Just-In-Time compiler), and as a human
readable assembly language representation. This allows LLVM to provide a
powerful intermediate representation for efficient compiler
transformations and analysis, while providing a natural means to debug
and visualize the transformations. The three different forms of LLVM are
all equivalent. This document describes the human readable
representation and notation.
The LLVM representation aims to be light-weight and low-level while
being expressive, typed, and extensible at the same time. It aims to be
a "universal IR" of sorts, by being at a low enough level that
high-level ideas may be cleanly mapped to it (similar to how
microprocessors are "universal IR's", allowing many source languages to
be mapped to them). By providing type information, LLVM can be used as
the target of optimizations: for example, through pointer analysis, it
can be proven that a C automatic variable is never accessed outside of
the current function, allowing it to be promoted to a simple SSA value
instead of a memory location.
.. _wellformed:
Well-Formedness
---------------
It is important to note that this document describes 'well formed' LLVM
assembly language. There is a difference between what the parser accepts
and what is considered 'well formed'. For example, the following
instruction is syntactically okay, but not well formed:
.. code-block:: llvm
%x = add i32 1, %x
because the definition of ``%x`` does not dominate all of its uses. The
LLVM infrastructure provides a verification pass that may be used to
verify that an LLVM module is well formed. This pass is automatically
run by the parser after parsing input assembly and by the optimizer
before it outputs bitcode. The violations pointed out by the verifier
pass indicate bugs in transformation passes or input to the parser.
.. _identifiers:
Identifiers
===========
LLVM identifiers come in two basic types: global and local. Global
identifiers (functions, global variables) begin with the ``'@'``
character. Local identifiers (register names, types) begin with the
``'%'`` character. Additionally, there are three different formats for
identifiers, for different purposes:
#. Named values are represented as a string of characters with their
prefix. For example, ``%foo``, ``@DivisionByZero``,
``%a.really.long.identifier``. The actual regular expression used is
'``[%@][-a-zA-Z$._][-a-zA-Z$._0-9]*``'. Identifiers that require other
characters in their names can be surrounded with quotes. Special
characters may be escaped using ``"\xx"`` where ``xx`` is the ASCII
code for the character in hexadecimal. In this way, any character can
be used in a name value, even quotes themselves. The ``"\01"`` prefix
can be used on global values to suppress mangling.
#. Unnamed values are represented as an unsigned numeric value with
their prefix. For example, ``%12``, ``@2``, ``%44``.
#. Constants, which are described in the section Constants_ below.
LLVM requires that values start with a prefix for two reasons: Compilers
don't need to worry about name clashes with reserved words, and the set
of reserved words may be expanded in the future without penalty.
Additionally, unnamed identifiers allow a compiler to quickly come up
with a temporary variable without having to avoid symbol table
conflicts.
Reserved words in LLVM are very similar to reserved words in other
languages. There are keywords for different opcodes ('``add``',
'``bitcast``', '``ret``', etc...), for primitive type names ('``void``',
'``i32``', etc...), and others. These reserved words cannot conflict
with variable names, because none of them start with a prefix character
(``'%'`` or ``'@'``).
Here is an example of LLVM code to multiply the integer variable
'``%X``' by 8:
The easy way:
.. code-block:: llvm
%result = mul i32 %X, 8
After strength reduction:
.. code-block:: llvm
%result = shl i32 %X, 3
And the hard way:
.. code-block:: llvm
%0 = add i32 %X, %X ; yields i32:%0
%1 = add i32 %0, %0 ; yields i32:%1
%result = add i32 %1, %1
This last way of multiplying ``%X`` by 8 illustrates several important
lexical features of LLVM:
#. Comments are delimited with a '``;``' and go until the end of line.
#. Unnamed temporaries are created when the result of a computation is
not assigned to a named value.
#. Unnamed temporaries are numbered sequentially (using a per-function
incrementing counter, starting with 0). Note that basic blocks and unnamed
function parameters are included in this numbering. For example, if the
entry basic block is not given a label name and all function parameters are
named, then it will get number 0.
It also shows a convention that we follow in this document. When
demonstrating instructions, we will follow an instruction with a comment
that defines the type and name of value produced.
High Level Structure
====================
Module Structure
----------------
LLVM programs are composed of ``Module``'s, each of which is a
translation unit of the input programs. Each module consists of
functions, global variables, and symbol table entries. Modules may be
combined together with the LLVM linker, which merges function (and
global variable) definitions, resolves forward declarations, and merges
symbol table entries. Here is an example of the "hello world" module:
.. code-block:: llvm
; Declare the string constant as a global constant.
@.str = private unnamed_addr constant [13 x i8] c"hello world\0A\00"
; External declaration of the puts function
declare i32 @puts(ptr nocapture) nounwind
; Definition of main function
define i32 @main() {
; Call puts function to write out the string to stdout.
call i32 @puts(ptr @.str)
ret i32 0
}
; Named metadata
!0 = !{i32 42, null, !"string"}
!foo = !{!0}
This example is made up of a :ref:`global variable <globalvars>` named
"``.str``", an external declaration of the "``puts``" function, a
:ref:`function definition <functionstructure>` for "``main``" and
:ref:`named metadata <namedmetadatastructure>` "``foo``".
In general, a module is made up of a list of global values (where both
functions and global variables are global values). Global values are
represented by a pointer to a memory location (in this case, a pointer
to an array of char, and a pointer to a function), and have one of the
following :ref:`linkage types <linkage>`.
.. _linkage:
Linkage Types
-------------
All Global Variables and Functions have one of the following types of
linkage:
``private``
Global values with "``private``" linkage are only directly
accessible by objects in the current module. In particular, linking
code into a module with a private global value may cause the
private to be renamed as necessary to avoid collisions. Because the
symbol is private to the module, all references can be updated. This
doesn't show up in any symbol table in the object file.
``internal``
Similar to private, but the value shows as a local symbol
(``STB_LOCAL`` in the case of ELF) in the object file. This
corresponds to the notion of the '``static``' keyword in C.
``available_externally``
Globals with "``available_externally``" linkage are never emitted into
the object file corresponding to the LLVM module. From the linker's
perspective, an ``available_externally`` global is equivalent to
an external declaration. They exist to allow inlining and other
optimizations to take place given knowledge of the definition of the
global, which is known to be somewhere outside the module. Globals
with ``available_externally`` linkage are allowed to be discarded at
will, and allow inlining and other optimizations. This linkage type is
only allowed on definitions, not declarations.
``linkonce``
Globals with "``linkonce``" linkage are merged with other globals of
the same name when linkage occurs. This can be used to implement
some forms of inline functions, templates, or other code which must
be generated in each translation unit that uses it, but where the
body may be overridden with a more definitive definition later.
Unreferenced ``linkonce`` globals are allowed to be discarded. Note
that ``linkonce`` linkage does not actually allow the optimizer to
inline the body of this function into callers because it doesn't
know if this definition of the function is the definitive definition
within the program or whether it will be overridden by a stronger
definition. To enable inlining and other optimizations, use
"``linkonce_odr``" linkage.
``weak``
"``weak``" linkage has the same merging semantics as ``linkonce``
linkage, except that unreferenced globals with ``weak`` linkage may
not be discarded. This is used for globals that are declared "weak"
in C source code.
``common``
"``common``" linkage is most similar to "``weak``" linkage, but they
are used for tentative definitions in C, such as "``int X;``" at
global scope. Symbols with "``common``" linkage are merged in the
same way as ``weak symbols``, and they may not be deleted if
unreferenced. ``common`` symbols may not have an explicit section,
must have a zero initializer, and may not be marked
':ref:`constant <globalvars>`'. Functions and aliases may not have
common linkage.
.. _linkage_appending:
``appending``
"``appending``" linkage may only be applied to global variables of
pointer to array type. When two global variables with appending
linkage are linked together, the two global arrays are appended
together. This is the LLVM, typesafe, equivalent of having the
system linker append together "sections" with identical names when
.o files are linked.
Unfortunately this doesn't correspond to any feature in .o files, so it
can only be used for variables like ``llvm.global_ctors`` which llvm
interprets specially.
``extern_weak``
The semantics of this linkage follow the ELF object file model: the
symbol is weak until linked, if not linked, the symbol becomes null
instead of being an undefined reference.
``linkonce_odr``, ``weak_odr``
Some languages allow differing globals to be merged, such as two
functions with different semantics. Other languages, such as
``C++``, ensure that only equivalent globals are ever merged (the
"one definition rule" --- "ODR"). Such languages can use the
``linkonce_odr`` and ``weak_odr`` linkage types to indicate that the
global will only be merged with equivalent globals. These linkage
types are otherwise the same as their non-``odr`` versions.
``external``
If none of the above identifiers are used, the global is externally
visible, meaning that it participates in linkage and can be used to
resolve external symbol references.
It is illegal for a global variable or function *declaration* to have any
linkage type other than ``external`` or ``extern_weak``.
.. _callingconv:
Calling Conventions
-------------------
LLVM :ref:`functions <functionstructure>`, :ref:`calls <i_call>` and
:ref:`invokes <i_invoke>` can all have an optional calling convention
specified for the call. The calling convention of any pair of dynamic
caller/callee must match, or the behavior of the program is undefined.
The following calling conventions are supported by LLVM, and more may be
added in the future:
"``ccc``" - The C calling convention
This calling convention (the default if no other calling convention
is specified) matches the target C calling conventions. This calling
convention supports varargs function calls and tolerates some
mismatch in the declared prototype and implemented declaration of
the function (as does normal C).
"``fastcc``" - The fast calling convention
This calling convention attempts to make calls as fast as possible
(e.g. by passing things in registers). This calling convention
allows the target to use whatever tricks it wants to produce fast
code for the target, without having to conform to an externally
specified ABI (Application Binary Interface). `Tail calls can only
be optimized when this, the tailcc, the GHC or the HiPE convention is
used. <CodeGenerator.html#tail-call-optimization>`_ This calling
convention does not support varargs and requires the prototype of all
callees to exactly match the prototype of the function definition.
"``coldcc``" - The cold calling convention
This calling convention attempts to make code in the caller as
efficient as possible under the assumption that the call is not
commonly executed. As such, these calls often preserve all registers
so that the call does not break any live ranges in the caller side.
This calling convention does not support varargs and requires the
prototype of all callees to exactly match the prototype of the
function definition. Furthermore the inliner doesn't consider such function
calls for inlining.
"``ghccc``" - GHC convention
This calling convention has been implemented specifically for use by
the `Glasgow Haskell Compiler (GHC) <http://www.haskell.org/ghc>`_.
It passes everything in registers, going to extremes to achieve this
by disabling callee save registers. This calling convention should
not be used lightly but only for specific situations such as an
alternative to the *register pinning* performance technique often
used when implementing functional programming languages. At the
moment only X86 and AArch64 support this convention. The following
limitations exist:
- On *X86-32* only up to 4 bit type parameters are supported. No
floating-point types are supported.
- On *X86-64* only up to 10 bit type parameters and 6
floating-point parameters are supported.
- On *AArch64* only up to 4 32-bit floating-point parameters,
4 64-bit floating-point parameters, and 10 bit type parameters
are supported.
This calling convention supports `tail call
optimization <CodeGenerator.html#tail-call-optimization>`_ but requires
both the caller and callee are using it.
"``cc 11``" - The HiPE calling convention
This calling convention has been implemented specifically for use by
the `High-Performance Erlang
(HiPE) <http://www.it.uu.se/research/group/hipe/>`_ compiler, *the*
native code compiler of the `Ericsson's Open Source Erlang/OTP
system <http://www.erlang.org/download.shtml>`_. It uses more
registers for argument passing than the ordinary C calling
convention and defines no callee-saved registers. The calling
convention properly supports `tail call
optimization <CodeGenerator.html#tail-call-optimization>`_ but requires
that both the caller and the callee use it. It uses a *register pinning*
mechanism, similar to GHC's convention, for keeping frequently
accessed runtime components pinned to specific hardware registers.
At the moment only X86 supports this convention (both 32 and 64
bit).
"``anyregcc``" - Dynamic calling convention for code patching
This is a special convention that supports patching an arbitrary code
sequence in place of a call site. This convention forces the call
arguments into registers but allows them to be dynamically
allocated. This can currently only be used with calls to
llvm.experimental.patchpoint because only this intrinsic records
the location of its arguments in a side table. See :doc:`StackMaps`.
"``preserve_mostcc``" - The `PreserveMost` calling convention
This calling convention attempts to make the code in the caller as
unintrusive as possible. This convention behaves identically to the `C`
calling convention on how arguments and return values are passed, but it
uses a different set of caller/callee-saved registers. This alleviates the
burden of saving and recovering a large register set before and after the
call in the caller. If the arguments are passed in callee-saved registers,
then they will be preserved by the callee across the call. This doesn't
apply for values returned in callee-saved registers.
- On X86-64 the callee preserves all general purpose registers, except for
R11 and return registers, if any. R11 can be used as a scratch register.
The treatment of floating-point registers (XMMs/YMMs) matches the OS's C
calling convention: on most platforms, they are not preserved and need to
be saved by the caller, but on Windows, xmm6-xmm15 are preserved.
- On AArch64 the callee preserve all general purpose registers, except X0-X8
and X16-X18.
The idea behind this convention is to support calls to runtime functions
that have a hot path and a cold path. The hot path is usually a small piece
of code that doesn't use many registers. The cold path might need to call out to
another function and therefore only needs to preserve the caller-saved
registers, which haven't already been saved by the caller. The
`PreserveMost` calling convention is very similar to the `cold` calling
convention in terms of caller/callee-saved registers, but they are used for
different types of function calls. `coldcc` is for function calls that are
rarely executed, whereas `preserve_mostcc` function calls are intended to be
on the hot path and definitely executed a lot. Furthermore `preserve_mostcc`
doesn't prevent the inliner from inlining the function call.
This calling convention will be used by a future version of the ObjectiveC
runtime and should therefore still be considered experimental at this time.
Although this convention was created to optimize certain runtime calls to
the ObjectiveC runtime, it is not limited to this runtime and might be used
by other runtimes in the future too. The current implementation only
supports X86-64, but the intention is to support more architectures in the
future.
"``preserve_allcc``" - The `PreserveAll` calling convention
This calling convention attempts to make the code in the caller even less
intrusive than the `PreserveMost` calling convention. This calling
convention also behaves identical to the `C` calling convention on how
arguments and return values are passed, but it uses a different set of
caller/callee-saved registers. This removes the burden of saving and
recovering a large register set before and after the call in the caller. If
the arguments are passed in callee-saved registers, then they will be
preserved by the callee across the call. This doesn't apply for values
returned in callee-saved registers.
- On X86-64 the callee preserves all general purpose registers, except for
R11. R11 can be used as a scratch register. Furthermore it also preserves
all floating-point registers (XMMs/YMMs).
- On AArch64 the callee preserve all general purpose registers, except X0-X8
and X16-X18. Furthermore it also preserves lower 128 bits of V8-V31 SIMD -
floating point registers.
The idea behind this convention is to support calls to runtime functions
that don't need to call out to any other functions.
This calling convention, like the `PreserveMost` calling convention, will be
used by a future version of the ObjectiveC runtime and should be considered
experimental at this time.
"``cxx_fast_tlscc``" - The `CXX_FAST_TLS` calling convention for access functions
Clang generates an access function to access C++-style TLS. The access
function generally has an entry block, an exit block and an initialization
block that is run at the first time. The entry and exit blocks can access
a few TLS IR variables, each access will be lowered to a platform-specific
sequence.
This calling convention aims to minimize overhead in the caller by
preserving as many registers as possible (all the registers that are
preserved on the fast path, composed of the entry and exit blocks).
This calling convention behaves identical to the `C` calling convention on
how arguments and return values are passed, but it uses a different set of
caller/callee-saved registers.
Given that each platform has its own lowering sequence, hence its own set
of preserved registers, we can't use the existing `PreserveMost`.
- On X86-64 the callee preserves all general purpose registers, except for
RDI and RAX.
"``tailcc``" - Tail callable calling convention
This calling convention ensures that calls in tail position will always be
tail call optimized. This calling convention is equivalent to fastcc,
except for an additional guarantee that tail calls will be produced
whenever possible. `Tail calls can only be optimized when this, the fastcc,
the GHC or the HiPE convention is used. <CodeGenerator.html#tail-call-optimization>`_
This calling convention does not support varargs and requires the prototype of
all callees to exactly match the prototype of the function definition.
"``swiftcc``" - This calling convention is used for Swift language.
- On X86-64 RCX and R8 are available for additional integer returns, and
XMM2 and XMM3 are available for additional FP/vector returns.
- On iOS platforms, we use AAPCS-VFP calling convention.
"``swifttailcc``"
This calling convention is like ``swiftcc`` in most respects, but also the
callee pops the argument area of the stack so that mandatory tail calls are
possible as in ``tailcc``.
"``cfguard_checkcc``" - Windows Control Flow Guard (Check mechanism)
This calling convention is used for the Control Flow Guard check function,
calls to which can be inserted before indirect calls to check that the call
target is a valid function address. The check function has no return value,
but it will trigger an OS-level error if the address is not a valid target.
The set of registers preserved by the check function, and the register
containing the target address are architecture-specific.
- On X86 the target address is passed in ECX.
- On ARM the target address is passed in R0.
- On AArch64 the target address is passed in X15.
"``cc <n>``" - Numbered convention
Any calling convention may be specified by number, allowing
target-specific calling conventions to be used. Target specific
calling conventions start at 64.
More calling conventions can be added/defined on an as-needed basis, to
support Pascal conventions or any other well-known target-independent
convention.
.. _visibilitystyles:
Visibility Styles
-----------------
All Global Variables and Functions have one of the following visibility
styles:
"``default``" - Default style
On targets that use the ELF object file format, default visibility
means that the declaration is visible to other modules and, in
shared libraries, means that the declared entity may be overridden.
On Darwin, default visibility means that the declaration is visible
to other modules. On XCOFF, default visibility means no explicit
visibility bit will be set and whether the symbol is visible
(i.e "exported") to other modules depends primarily on export lists
provided to the linker. Default visibility corresponds to "external
linkage" in the language.
"``hidden``" - Hidden style
Two declarations of an object with hidden visibility refer to the
same object if they are in the same shared object. Usually, hidden
visibility indicates that the symbol will not be placed into the
dynamic symbol table, so no other module (executable or shared
library) can reference it directly.
"``protected``" - Protected style
On ELF, protected visibility indicates that the symbol will be
placed in the dynamic symbol table, but that references within the
defining module will bind to the local symbol. That is, the symbol
cannot be overridden by another module.
A symbol with ``internal`` or ``private`` linkage must have ``default``
visibility.
.. _dllstorageclass:
DLL Storage Classes
-------------------
All Global Variables, Functions and Aliases can have one of the following
DLL storage class:
``dllimport``
"``dllimport``" causes the compiler to reference a function or variable via
a global pointer to a pointer that is set up by the DLL exporting the
symbol. On Microsoft Windows targets, the pointer name is formed by
combining ``__imp_`` and the function or variable name.
``dllexport``
On Microsoft Windows targets, "``dllexport``" causes the compiler to provide
a global pointer to a pointer in a DLL, so that it can be referenced with the
``dllimport`` attribute. the pointer name is formed by combining ``__imp_``
and the function or variable name. On XCOFF targets, ``dllexport`` indicates
that the symbol will be made visible to other modules using "exported"
visibility and thus placed by the linker in the loader section symbol table.
Since this storage class exists for defining a dll interface, the compiler,
assembler and linker know it is externally referenced and must refrain from
deleting the symbol.
A symbol with ``internal`` or ``private`` linkage cannot have a DLL storage
class.
.. _tls_model:
Thread Local Storage Models
---------------------------
A variable may be defined as ``thread_local``, which means that it will
not be shared by threads (each thread will have a separated copy of the
variable). Not all targets support thread-local variables. Optionally, a
TLS model may be specified:
``localdynamic``
For variables that are only used within the current shared library.
``initialexec``
For variables in modules that will not be loaded dynamically.
``localexec``
For variables defined in the executable and only used within it.
If no explicit model is given, the "general dynamic" model is used.
The models correspond to the ELF TLS models; see `ELF Handling For
Thread-Local Storage <http://people.redhat.com/drepper/tls.pdf>`_ for
more information on under which circumstances the different models may
be used. The target may choose a different TLS model if the specified
model is not supported, or if a better choice of model can be made.
A model can also be specified in an alias, but then it only governs how
the alias is accessed. It will not have any effect in the aliasee.
For platforms without linker support of ELF TLS model, the -femulated-tls
flag can be used to generate GCC compatible emulated TLS code.
.. _runtime_preemption_model:
Runtime Preemption Specifiers
-----------------------------
Global variables, functions and aliases may have an optional runtime preemption
specifier. If a preemption specifier isn't given explicitly, then a
symbol is assumed to be ``dso_preemptable``.
``dso_preemptable``
Indicates that the function or variable may be replaced by a symbol from
outside the linkage unit at runtime.
``dso_local``
The compiler may assume that a function or variable marked as ``dso_local``
will resolve to a symbol within the same linkage unit. Direct access will
be generated even if the definition is not within this compilation unit.
.. _namedtypes:
Structure Types
---------------
LLVM IR allows you to specify both "identified" and "literal" :ref:`structure
types <t_struct>`. Literal types are uniqued structurally, but identified types
are never uniqued. An :ref:`opaque structural type <t_opaque>` can also be used
to forward declare a type that is not yet available.
An example of an identified structure specification is:
.. code-block:: llvm
%mytype = type { %mytype*, i32 }
Prior to the LLVM 3.0 release, identified types were structurally uniqued. Only
literal types are uniqued in recent versions of LLVM.
.. _nointptrtype:
Non-Integral Pointer Type
-------------------------
Note: non-integral pointer types are a work in progress, and they should be
considered experimental at this time.
LLVM IR optionally allows the frontend to denote pointers in certain address
spaces as "non-integral" via the :ref:`datalayout string<langref_datalayout>`.
Non-integral pointer types represent pointers that have an *unspecified* bitwise
representation; that is, the integral representation may be target dependent or
unstable (not backed by a fixed integer).
``inttoptr`` and ``ptrtoint`` instructions have the same semantics as for
integral (i.e. normal) pointers in that they convert integers to and from
corresponding pointer types, but there are additional implications to be
aware of. Because the bit-representation of a non-integral pointer may
not be stable, two identical casts of the same operand may or may not
return the same value. Said differently, the conversion to or from the
non-integral type depends on environmental state in an implementation
defined manner.
If the frontend wishes to observe a *particular* value following a cast, the
generated IR must fence with the underlying environment in an implementation
defined manner. (In practice, this tends to require ``noinline`` routines for
such operations.)
From the perspective of the optimizer, ``inttoptr`` and ``ptrtoint`` for
non-integral types are analogous to ones on integral types with one
key exception: the optimizer may not, in general, insert new dynamic
occurrences of such casts. If a new cast is inserted, the optimizer would
need to either ensure that a) all possible values are valid, or b)
appropriate fencing is inserted. Since the appropriate fencing is
implementation defined, the optimizer can't do the latter. The former is
challenging as many commonly expected properties, such as
``ptrtoint(v)-ptrtoint(v) == 0``, don't hold for non-integral types.
Similar restrictions apply to intrinsics that might examine the pointer bits,
such as :ref:`llvm.ptrmask<int_ptrmask>`.
The alignment information provided by the frontend for a non-integral pointer
(typically using attributes or metadata) must be valid for every possible
representation of the pointer.
.. _globalvars:
Global Variables
----------------
Global variables define regions of memory allocated at compilation time
instead of run-time.
Global variable definitions must be initialized.
Global variables in other translation units can also be declared, in which
case they don't have an initializer.
Global variables can optionally specify a :ref:`linkage type <linkage>`.
Either global variable definitions or declarations may have an explicit section
to be placed in and may have an optional explicit alignment specified. If there
is a mismatch between the explicit or inferred section information for the
variable declaration and its definition the resulting behavior is undefined.
A variable may be defined as a global ``constant``, which indicates that
the contents of the variable will **never** be modified (enabling better
optimization, allowing the global data to be placed in the read-only
section of an executable, etc). Note that variables that need runtime
initialization cannot be marked ``constant`` as there is a store to the
variable.
LLVM explicitly allows *declarations* of global variables to be marked
constant, even if the final definition of the global is not. This
capability can be used to enable slightly better optimization of the
program, but requires the language definition to guarantee that
optimizations based on the 'constantness' are valid for the translation
units that do not include the definition.
As SSA values, global variables define pointer values that are in scope
(i.e. they dominate) all basic blocks in the program. Global variables
always define a pointer to their "content" type because they describe a
region of memory, and all memory objects in LLVM are accessed through
pointers.
Global variables can be marked with ``unnamed_addr`` which indicates
that the address is not significant, only the content. Constants marked
like this can be merged with other constants if they have the same
initializer. Note that a constant with significant address *can* be
merged with a ``unnamed_addr`` constant, the result being a constant
whose address is significant.
If the ``local_unnamed_addr`` attribute is given, the address is known to
not be significant within the module.
A global variable may be declared to reside in a target-specific
numbered address space. For targets that support them, address spaces
may affect how optimizations are performed and/or what target
instructions are used to access the variable. The default address space
is zero. The address space qualifier must precede any other attributes.
LLVM allows an explicit section to be specified for globals. If the
target supports it, it will emit globals to the section specified.
Additionally, the global can placed in a comdat if the target has the necessary
support.
External declarations may have an explicit section specified. Section
information is retained in LLVM IR for targets that make use of this
information. Attaching section information to an external declaration is an
assertion that its definition is located in the specified section. If the
definition is located in a different section, the behavior is undefined.
LLVM allows an explicit code model to be specified for globals. If the
target supports it, it will emit globals in the code model specified,
overriding the code model used to compile the translation unit.
The allowed values are "tiny", "small", "kernel", "medium", "large".
This may be extended in the future to specify global data layout that
doesn't cleanly fit into a specific code model.
By default, global initializers are optimized by assuming that global
variables defined within the module are not modified from their
initial values before the start of the global initializer. This is
true even for variables potentially accessible from outside the
module, including those with external linkage or appearing in
``@llvm.used`` or dllexported variables. This assumption may be suppressed
by marking the variable with ``externally_initialized``.
An explicit alignment may be specified for a global, which must be a
power of 2. If not present, or if the alignment is set to zero, the
alignment of the global is set by the target to whatever it feels
convenient. If an explicit alignment is specified, the global is forced
to have exactly that alignment. Targets and optimizers are not allowed
to over-align the global if the global has an assigned section. In this
case, the extra alignment could be observable: for example, code could
assume that the globals are densely packed in their section and try to
iterate over them as an array, alignment padding would break this
iteration. For TLS variables, the module flag ``MaxTLSAlign``, if present,
limits the alignment to the given value. Optimizers are not allowed to
impose a stronger alignment on these variables. The maximum alignment
is ``1 << 32``.
For global variable declarations, as well as definitions that may be
replaced at link time (``linkonce``, ``weak``, ``extern_weak`` and ``common``
linkage types), the allocation size and alignment of the definition it resolves
to must be greater than or equal to that of the declaration or replaceable
definition, otherwise the behavior is undefined.
Globals can also have a :ref:`DLL storage class <dllstorageclass>`,
an optional :ref:`runtime preemption specifier <runtime_preemption_model>`,
an optional :ref:`global attributes <glattrs>` and
an optional list of attached :ref:`metadata <metadata>`.
Variables and aliases can have a
:ref:`Thread Local Storage Model <tls_model>`.
Globals cannot be or contain :ref:`Scalable vectors <t_vector>` because their
size is unknown at compile time. They are allowed in structs to facilitate
intrinsics returning multiple values. Generally, structs containing scalable
vectors are not considered "sized" and cannot be used in loads, stores, allocas,
or GEPs. The only exception to this rule is for structs that contain scalable
vectors of the same type (e.g. ``{<vscale x 2 x i32>, <vscale x 2 x i32>}``
contains the same type while ``{<vscale x 2 x i32>, <vscale x 2 x i64>}``
doesn't). These kinds of structs (we may call them homogeneous scalable vector
structs) are considered sized and can be used in loads, stores, allocas, but
not GEPs.
Syntax::
@<GlobalVarName> = [Linkage] [PreemptionSpecifier] [Visibility]
[DLLStorageClass] [ThreadLocal]
[(unnamed_addr|local_unnamed_addr)] [AddrSpace]
[ExternallyInitialized]
<global | constant> <Type> [<InitializerConstant>]
[, section "name"] [, partition "name"]
[, comdat [($name)]] [, align <Alignment>]
[, code_model "model"]
[, no_sanitize_address] [, no_sanitize_hwaddress]
[, sanitize_address_dyninit] [, sanitize_memtag]
(, !name !N)*
For example, the following defines a global in a numbered address space
with an initializer, section, and alignment:
.. code-block:: llvm
@G = addrspace(5) constant float 1.0, section "foo", align 4
The following example just declares a global variable
.. code-block:: llvm
@G = external global i32
The following example defines a global variable with the
``large`` code model:
.. code-block:: llvm
@G = internal global i32 0, code_model "large"
The following example defines a thread-local global with the
``initialexec`` TLS model:
.. code-block:: llvm
@G = thread_local(initialexec) global i32 0, align 4
.. _functionstructure:
Functions
---------
LLVM function definitions consist of the "``define``" keyword, an
optional :ref:`linkage type <linkage>`, an optional :ref:`runtime preemption
specifier <runtime_preemption_model>`, an optional :ref:`visibility
style <visibility>`, an optional :ref:`DLL storage class <dllstorageclass>`,
an optional :ref:`calling convention <callingconv>`,
an optional ``unnamed_addr`` attribute, a return type, an optional
:ref:`parameter attribute <paramattrs>` for the return type, a function
name, a (possibly empty) argument list (each with optional :ref:`parameter
attributes <paramattrs>`), optional :ref:`function attributes <fnattrs>`,
an optional address space, an optional section, an optional partition,
an optional alignment, an optional :ref:`comdat <langref_comdats>`,
an optional :ref:`garbage collector name <gc>`, an optional :ref:`prefix <prefixdata>`,
an optional :ref:`prologue <prologuedata>`,
an optional :ref:`personality <personalityfn>`,
an optional list of attached :ref:`metadata <metadata>`,
an opening curly brace, a list of basic blocks, and a closing curly brace.
Syntax::
define [linkage] [PreemptionSpecifier] [visibility] [DLLStorageClass]
[cconv] [ret attrs]
<ResultType> @<FunctionName> ([argument list])
[(unnamed_addr|local_unnamed_addr)] [AddrSpace] [fn Attrs]
[section "name"] [partition "name"] [comdat [($name)]] [align N]
[gc] [prefix Constant] [prologue Constant] [personality Constant]
(!name !N)* { ... }
The argument list is a comma separated sequence of arguments where each
argument is of the following form:
Syntax::
<type> [parameter Attrs] [name]
LLVM function declarations consist of the "``declare``" keyword, an
optional :ref:`linkage type <linkage>`, an optional :ref:`visibility style
<visibility>`, an optional :ref:`DLL storage class <dllstorageclass>`, an
optional :ref:`calling convention <callingconv>`, an optional ``unnamed_addr``
or ``local_unnamed_addr`` attribute, an optional address space, a return type,
an optional :ref:`parameter attribute <paramattrs>` for the return type, a function name, a possibly
empty list of arguments, an optional alignment, an optional :ref:`garbage
collector name <gc>`, an optional :ref:`prefix <prefixdata>`, and an optional
:ref:`prologue <prologuedata>`.
Syntax::
declare [linkage] [visibility] [DLLStorageClass]
[cconv] [ret attrs]
<ResultType> @<FunctionName> ([argument list])
[(unnamed_addr|local_unnamed_addr)] [align N] [gc]
[prefix Constant] [prologue Constant]
A function definition contains a list of basic blocks, forming the CFG (Control
Flow Graph) for the function. Each basic block may optionally start with a label
(giving the basic block a symbol table entry), contains a list of instructions,
and ends with a :ref:`terminator <terminators>` instruction (such as a branch or
function return). If an explicit label name is not provided, a block is assigned
an implicit numbered label, using the next value from the same counter as used
for unnamed temporaries (:ref:`see above<identifiers>`). For example, if a
function entry block does not have an explicit label, it will be assigned label
"%0", then the first unnamed temporary in that block will be "%1", etc. If a
numeric label is explicitly specified, it must match the numeric label that
would be used implicitly.
The first basic block in a function is special in two ways: it is
immediately executed on entrance to the function, and it is not allowed
to have predecessor basic blocks (i.e. there can not be any branches to
the entry block of a function). Because the block can have no
predecessors, it also cannot have any :ref:`PHI nodes <i_phi>`.
LLVM allows an explicit section to be specified for functions. If the
target supports it, it will emit functions to the section specified.
Additionally, the function can be placed in a COMDAT.
An explicit alignment may be specified for a function. If not present,
or if the alignment is set to zero, the alignment of the function is set
by the target to whatever it feels convenient. If an explicit alignment
is specified, the function is forced to have at least that much
alignment. All alignments must be a power of 2.
If the ``unnamed_addr`` attribute is given, the address is known to not
be significant and two identical functions can be merged.
If the ``local_unnamed_addr`` attribute is given, the address is known to
not be significant within the module.
If an explicit address space is not given, it will default to the program
address space from the :ref:`datalayout string<langref_datalayout>`.
.. _langref_aliases:
Aliases
-------
Aliases, unlike function or variables, don't create any new data. They
are just a new symbol and metadata for an existing position.
Aliases have a name and an aliasee that is either a global value or a
constant expression.
Aliases may have an optional :ref:`linkage type <linkage>`, an optional
:ref:`runtime preemption specifier <runtime_preemption_model>`, an optional
:ref:`visibility style <visibility>`, an optional :ref:`DLL storage class
<dllstorageclass>` and an optional :ref:`tls model <tls_model>`.
Syntax::
@<Name> = [Linkage] [PreemptionSpecifier] [Visibility] [DLLStorageClass] [ThreadLocal] [(unnamed_addr|local_unnamed_addr)] alias <AliaseeTy>, <AliaseeTy>* @<Aliasee>
[, partition "name"]
The linkage must be one of ``private``, ``internal``, ``linkonce``, ``weak``,
``linkonce_odr``, ``weak_odr``, ``external``, ``available_externally``. Note
that some system linkers might not correctly handle dropping a weak symbol that
is aliased.
Aliases that are not ``unnamed_addr`` are guaranteed to have the same address as
the aliasee expression. ``unnamed_addr`` ones are only guaranteed to point
to the same content.
If the ``local_unnamed_addr`` attribute is given, the address is known to
not be significant within the module.
Since aliases are only a second name, some restrictions apply, of which
some can only be checked when producing an object file:
* The expression defining the aliasee must be computable at assembly
time. Since it is just a name, no relocations can be used.
* No alias in the expression can be weak as the possibility of the
intermediate alias being overridden cannot be represented in an
object file.
* If the alias has the ``available_externally`` linkage, the aliasee must be an
``available_externally`` global value; otherwise the aliasee can be an
expression but no global value in the expression can be a declaration, since
that would require a relocation, which is not possible.
* If either the alias or the aliasee may be replaced by a symbol outside the
module at link time or runtime, any optimization cannot replace the alias with
the aliasee, since the behavior may be different. The alias may be used as a
name guaranteed to point to the content in the current module.
.. _langref_ifunc:
IFuncs
-------
IFuncs, like as aliases, don't create any new data or func. They are just a new
symbol that is resolved at runtime by calling a resolver function.
On ELF platforms, IFuncs are resolved by the dynamic linker at load time. On
Mach-O platforms, they are lowered in terms of ``.symbol_resolver`` functions,
which lazily resolve the callee the first time they are called.
IFunc may have an optional :ref:`linkage type <linkage>` and an optional
:ref:`visibility style <visibility>`.
Syntax::
@<Name> = [Linkage] [PreemptionSpecifier] [Visibility] ifunc <IFuncTy>, <ResolverTy>* @<Resolver>
[, partition "name"]
.. _langref_comdats:
Comdats
-------
Comdat IR provides access to object file COMDAT/section group functionality
which represents interrelated sections.
Comdats have a name which represents the COMDAT key and a selection kind to
provide input on how the linker deduplicates comdats with the same key in two
different object files. A comdat must be included or omitted as a unit.
Discarding the whole comdat is allowed but discarding a subset is not.
A global object may be a member of at most one comdat. Aliases are placed in the
same COMDAT that their aliasee computes to, if any.
Syntax::
$<Name> = comdat SelectionKind
For selection kinds other than ``nodeduplicate``, only one of the duplicate
comdats may be retained by the linker and the members of the remaining comdats
must be discarded. The following selection kinds are supported:
``any``
The linker may choose any COMDAT key, the choice is arbitrary.
``exactmatch``
The linker may choose any COMDAT key but the sections must contain the
same data.
``largest``
The linker will choose the section containing the largest COMDAT key.
``nodeduplicate``
No deduplication is performed.
``samesize``
The linker may choose any COMDAT key but the sections must contain the
same amount of data.
- XCOFF and Mach-O don't support COMDATs.
- COFF supports all selection kinds. Non-``nodeduplicate`` selection kinds need
a non-local linkage COMDAT symbol.
- ELF supports ``any`` and ``nodeduplicate``.
- WebAssembly only supports ``any``.
Here is an example of a COFF COMDAT where a function will only be selected if
the COMDAT key's section is the largest:
.. code-block:: text
$foo = comdat largest
@foo = global i32 2, comdat($foo)
define void @bar() comdat($foo) {
ret void
}
In a COFF object file, this will create a COMDAT section with selection kind
``IMAGE_COMDAT_SELECT_LARGEST`` containing the contents of the ``@foo`` symbol
and another COMDAT section with selection kind
``IMAGE_COMDAT_SELECT_ASSOCIATIVE`` which is associated with the first COMDAT
section and contains the contents of the ``@bar`` symbol.
As a syntactic sugar the ``$name`` can be omitted if the name is the same as
the global name:
.. code-block:: llvm
$foo = comdat any
@foo = global i32 2, comdat
@bar = global i32 3, comdat($foo)
There are some restrictions on the properties of the global object.
It, or an alias to it, must have the same name as the COMDAT group when
targeting COFF.
The contents and size of this object may be used during link-time to determine
which COMDAT groups get selected depending on the selection kind.
Because the name of the object must match the name of the COMDAT group, the
linkage of the global object must not be local; local symbols can get renamed
if a collision occurs in the symbol table.
The combined use of COMDATS and section attributes may yield surprising results.
For example:
.. code-block:: llvm
$foo = comdat any
$bar = comdat any
@g1 = global i32 42, section "sec", comdat($foo)
@g2 = global i32 42, section "sec", comdat($bar)
From the object file perspective, this requires the creation of two sections
with the same name. This is necessary because both globals belong to different
COMDAT groups and COMDATs, at the object file level, are represented by
sections.
Note that certain IR constructs like global variables and functions may
create COMDATs in the object file in addition to any which are specified using
COMDAT IR. This arises when the code generator is configured to emit globals
in individual sections (e.g. when `-data-sections` or `-function-sections`
is supplied to `llc`).
.. _namedmetadatastructure:
Named Metadata
--------------
Named metadata is a collection of metadata. :ref:`Metadata
nodes <metadata>` (but not metadata strings) are the only valid
operands for a named metadata.
#. Named metadata are represented as a string of characters with the
metadata prefix. The rules for metadata names are the same as for
identifiers, but quoted names are not allowed. ``"\xx"`` type escapes
are still valid, which allows any character to be part of a name.
Syntax::
; Some unnamed metadata nodes, which are referenced by the named metadata.
!0 = !{!"zero"}
!1 = !{!"one"}
!2 = !{!"two"}
; A named metadata.
!name = !{!0, !1, !2}
.. _paramattrs:
Parameter Attributes
--------------------
The return type and each parameter of a function type may have a set of
*parameter attributes* associated with them. Parameter attributes are
used to communicate additional information about the result or
parameters of a function. Parameter attributes are considered to be part
of the function, not of the function type, so functions with different
parameter attributes can have the same function type.
Parameter attributes are simple keywords that follow the type specified.
If multiple parameter attributes are needed, they are space separated.
For example:
.. code-block:: llvm
declare i32 @printf(ptr noalias nocapture, ...)
declare i32 @atoi(i8 zeroext)
declare signext i8 @returns_signed_char()
Note that any attributes for the function result (``nonnull``,
``signext``) come before the result type.
Currently, only the following parameter attributes are defined:
``zeroext``
This indicates to the code generator that the parameter or return
value should be zero-extended to the extent required by the target's
ABI by the caller (for a parameter) or the callee (for a return value).
``signext``
This indicates to the code generator that the parameter or return
value should be sign-extended to the extent required by the target's
ABI (which is usually 32-bits) by the caller (for a parameter) or
the callee (for a return value).
``inreg``
This indicates that this parameter or return value should be treated
in a special target-dependent fashion while emitting code for
a function call or return (usually, by putting it in a register as
opposed to memory, though some targets use it to distinguish between
two different kinds of registers). Use of this attribute is
target-specific.
``byval(<ty>)``
This indicates that the pointer parameter should really be passed by
value to the function. The attribute implies that a hidden copy of
the pointee is made between the caller and the callee, so the callee
is unable to modify the value in the caller. This attribute is only
valid on LLVM pointer arguments. It is generally used to pass
structs and arrays by value, but is also valid on pointers to
scalars. The copy is considered to belong to the caller not the
callee (for example, ``readonly`` functions should not write to
``byval`` parameters). This is not a valid attribute for return
values.
The byval type argument indicates the in-memory value type, and
must be the same as the pointee type of the argument.
The byval attribute also supports specifying an alignment with the
align attribute. It indicates the alignment of the stack slot to
form and the known alignment of the pointer specified to the call
site. If the alignment is not specified, then the code generator
makes a target-specific assumption.
.. _attr_byref:
``byref(<ty>)``
The ``byref`` argument attribute allows specifying the pointee
memory type of an argument. This is similar to ``byval``, but does
not imply a copy is made anywhere, or that the argument is passed
on the stack. This implies the pointer is dereferenceable up to
the storage size of the type.
It is not generally permissible to introduce a write to an
``byref`` pointer. The pointer may have any address space and may
be read only.
This is not a valid attribute for return values.
The alignment for an ``byref`` parameter can be explicitly
specified by combining it with the ``align`` attribute, similar to
``byval``. If the alignment is not specified, then the code generator
makes a target-specific assumption.
This is intended for representing ABI constraints, and is not
intended to be inferred for optimization use.
.. _attr_preallocated:
``preallocated(<ty>)``
This indicates that the pointer parameter should really be passed by
value to the function, and that the pointer parameter's pointee has
already been initialized before the call instruction. This attribute
is only valid on LLVM pointer arguments. The argument must be the value
returned by the appropriate
:ref:`llvm.call.preallocated.arg<int_call_preallocated_arg>` on non
``musttail`` calls, or the corresponding caller parameter in ``musttail``
calls, although it is ignored during codegen.
A non ``musttail`` function call with a ``preallocated`` attribute in
any parameter must have a ``"preallocated"`` operand bundle. A ``musttail``
function call cannot have a ``"preallocated"`` operand bundle.
The preallocated attribute requires a type argument, which must be
the same as the pointee type of the argument.
The preallocated attribute also supports specifying an alignment with the
align attribute. It indicates the alignment of the stack slot to
form and the known alignment of the pointer specified to the call
site. If the alignment is not specified, then the code generator
makes a target-specific assumption.
.. _attr_inalloca:
``inalloca(<ty>)``
The ``inalloca`` argument attribute allows the caller to take the
address of outgoing stack arguments. An ``inalloca`` argument must
be a pointer to stack memory produced by an ``alloca`` instruction.
The alloca, or argument allocation, must also be tagged with the
inalloca keyword. Only the last argument may have the ``inalloca``
attribute, and that argument is guaranteed to be passed in memory.
An argument allocation may be used by a call at most once because
the call may deallocate it. The ``inalloca`` attribute cannot be
used in conjunction with other attributes that affect argument
storage, like ``inreg``, ``nest``, ``sret``, or ``byval``. The
``inalloca`` attribute also disables LLVM's implicit lowering of
large aggregate return values, which means that frontend authors
must lower them with ``sret`` pointers.
When the call site is reached, the argument allocation must have
been the most recent stack allocation that is still live, or the
behavior is undefined. It is possible to allocate additional stack
space after an argument allocation and before its call site, but it
must be cleared off with :ref:`llvm.stackrestore
<int_stackrestore>`.
The inalloca attribute requires a type argument, which must be the
same as the pointee type of the argument.
See :doc:`InAlloca` for more information on how to use this
attribute.
``sret(<ty>)``
This indicates that the pointer parameter specifies the address of a
structure that is the return value of the function in the source
program. This pointer must be guaranteed by the caller to be valid:
loads and stores to the structure may be assumed by the callee not
to trap and to be properly aligned. This is not a valid attribute
for return values.
The sret type argument specifies the in memory type, which must be
the same as the pointee type of the argument.
.. _attr_elementtype:
``elementtype(<ty>)``
The ``elementtype`` argument attribute can be used to specify a pointer
element type in a way that is compatible with `opaque pointers
<OpaquePointers.html>`__.
The ``elementtype`` attribute by itself does not carry any specific
semantics. However, certain intrinsics may require this attribute to be
present and assign it particular semantics. This will be documented on
individual intrinsics.
The attribute may only be applied to pointer typed arguments of intrinsic
calls. It cannot be applied to non-intrinsic calls, and cannot be applied
to parameters on function declarations. For non-opaque pointers, the type
passed to ``elementtype`` must match the pointer element type.
.. _attr_align:
``align <n>`` or ``align(<n>)``
This indicates that the pointer value or vector of pointers has the
specified alignment. If applied to a vector of pointers, *all* pointers
(elements) have the specified alignment. If the pointer value does not have
the specified alignment, :ref:`poison value <poisonvalues>` is returned or
passed instead. The ``align`` attribute should be combined with the
``noundef`` attribute to ensure a pointer is aligned, or otherwise the
behavior is undefined. Note that ``align 1`` has no effect on non-byval,
non-preallocated arguments.
Note that this attribute has additional semantics when combined with the
``byval`` or ``preallocated`` attribute, which are documented there.
.. _noalias:
``noalias``
This indicates that memory locations accessed via pointer values
:ref:`based <pointeraliasing>` on the argument or return value are not also
accessed, during the execution of the function, via pointer values not
*based* on the argument or return value. This guarantee only holds for
memory locations that are *modified*, by any means, during the execution of
the function. The attribute on a return value also has additional semantics
described below. The caller shares the responsibility with the callee for
ensuring that these requirements are met. For further details, please see
the discussion of the NoAlias response in :ref:`alias analysis <Must, May,
or No>`.
Note that this definition of ``noalias`` is intentionally similar
to the definition of ``restrict`` in C99 for function arguments.
For function return values, C99's ``restrict`` is not meaningful,
while LLVM's ``noalias`` is. Furthermore, the semantics of the ``noalias``
attribute on return values are stronger than the semantics of the attribute
when used on function arguments. On function return values, the ``noalias``
attribute indicates that the function acts like a system memory allocation
function, returning a pointer to allocated storage disjoint from the
storage for any other object accessible to the caller.
.. _nocapture:
``nocapture``
This indicates that the callee does not :ref:`capture <pointercapture>` the
pointer. This is not a valid attribute for return values.
This attribute applies only to the particular copy of the pointer passed in
this argument. A caller could pass two copies of the same pointer with one
being annotated nocapture and the other not, and the callee could validly
capture through the non annotated parameter.
.. code-block:: llvm
define void @f(ptr nocapture %a, ptr %b) {
; (capture %b)
}
call void @f(ptr @glb, ptr @glb) ; well-defined
``nofree``
This indicates that callee does not free the pointer argument. This is not
a valid attribute for return values.
.. _nest:
``nest``
This indicates that the pointer parameter can be excised using the
:ref:`trampoline intrinsics <int_trampoline>`. This is not a valid
attribute for return values and can only be applied to one parameter.
``returned``
This indicates that the function always returns the argument as its return
value. This is a hint to the optimizer and code generator used when
generating the caller, allowing value propagation, tail call optimization,
and omission of register saves and restores in some cases; it is not
checked or enforced when generating the callee. The parameter and the
function return type must be valid operands for the
:ref:`bitcast instruction <i_bitcast>`. This is not a valid attribute for
return values and can only be applied to one parameter.
``nonnull``
This indicates that the parameter or return pointer is not null. This
attribute may only be applied to pointer typed parameters. This is not
checked or enforced by LLVM; if the parameter or return pointer is null,
:ref:`poison value <poisonvalues>` is returned or passed instead.
The ``nonnull`` attribute should be combined with the ``noundef`` attribute
to ensure a pointer is not null or otherwise the behavior is undefined.
``dereferenceable(<n>)``
This indicates that the parameter or return pointer is dereferenceable. This
attribute may only be applied to pointer typed parameters. A pointer that
is dereferenceable can be loaded from speculatively without a risk of
trapping. The number of bytes known to be dereferenceable must be provided
in parentheses. It is legal for the number of bytes to be less than the
size of the pointee type. The ``nonnull`` attribute does not imply
dereferenceability (consider a pointer to one element past the end of an
array), however ``dereferenceable(<n>)`` does imply ``nonnull`` in
``addrspace(0)`` (which is the default address space), except if the
``null_pointer_is_valid`` function attribute is present.
``n`` should be a positive number. The pointer should be well defined,
otherwise it is undefined behavior. This means ``dereferenceable(<n>)``
implies ``noundef``.
``dereferenceable_or_null(<n>)``
This indicates that the parameter or return value isn't both
non-null and non-dereferenceable (up to ``<n>`` bytes) at the same
time. All non-null pointers tagged with
``dereferenceable_or_null(<n>)`` are ``dereferenceable(<n>)``.
For address space 0 ``dereferenceable_or_null(<n>)`` implies that
a pointer is exactly one of ``dereferenceable(<n>)`` or ``null``,
and in other address spaces ``dereferenceable_or_null(<n>)``
implies that a pointer is at least one of ``dereferenceable(<n>)``
or ``null`` (i.e. it may be both ``null`` and
``dereferenceable(<n>)``). This attribute may only be applied to
pointer typed parameters.
``swiftself``
This indicates that the parameter is the self/context parameter. This is not
a valid attribute for return values and can only be applied to one
parameter.
.. _swiftasync:
``swiftasync``
This indicates that the parameter is the asynchronous context parameter and
triggers the creation of a target-specific extended frame record to store
this pointer. This is not a valid attribute for return values and can only
be applied to one parameter.
``swifterror``
This attribute is motivated to model and optimize Swift error handling. It
can be applied to a parameter with pointer to pointer type or a
pointer-sized alloca. At the call site, the actual argument that corresponds
to a ``swifterror`` parameter has to come from a ``swifterror`` alloca or
the ``swifterror`` parameter of the caller. A ``swifterror`` value (either
the parameter or the alloca) can only be loaded and stored from, or used as
a ``swifterror`` argument. This is not a valid attribute for return values
and can only be applied to one parameter.
These constraints allow the calling convention to optimize access to
``swifterror`` variables by associating them with a specific register at
call boundaries rather than placing them in memory. Since this does change
the calling convention, a function which uses the ``swifterror`` attribute
on a parameter is not ABI-compatible with one which does not.
These constraints also allow LLVM to assume that a ``swifterror`` argument
does not alias any other memory visible within a function and that a
``swifterror`` alloca passed as an argument does not escape.
``immarg``
This indicates the parameter is required to be an immediate
value. This must be a trivial immediate integer or floating-point
constant. Undef or constant expressions are not valid. This is
only valid on intrinsic declarations and cannot be applied to a
call site or arbitrary function.
``noundef``
This attribute applies to parameters and return values. If the value
representation contains any undefined or poison bits, the behavior is
undefined. Note that this does not refer to padding introduced by the
type's storage representation.
.. _nofpclass:
``nofpclass(<test mask>)``
This attribute applies to parameters and return values with
floating-point and vector of floating-point types, as well as
arrays of such types. The test mask has the same format as the
second argument to the :ref:`llvm.is.fpclass <llvm.is.fpclass>`,
and indicates which classes of floating-point values are not
permitted for the value. For example a bitmask of 3 indicates
the parameter may not be a NaN.
If the value is a floating-point class indicated by the
``nofpclass`` test mask, a :ref:`poison value <poisonvalues>` is
passed or returned instead.
.. code-block:: text
:caption: The following invariants hold
@llvm.is.fpclass(nofpclass(test_mask) %x, test_mask) => false
@llvm.is.fpclass(nofpclass(test_mask) %x, ~test_mask) => true
nofpclass(all) => poison
..
In textual IR, various string names are supported for readability
and can be combined. For example ``nofpclass(nan pinf nzero)``
evaluates to a mask of 547.
This does not depend on the floating-point environment. For
example, a function parameter marked ``nofpclass(zero)`` indicates
no zero inputs. If this is applied to an argument in a function
marked with :ref:`\"denormal-fp-math\" <denormal_fp_math>`
indicating zero treatment of input denormals, it does not imply the
value cannot be a denormal value which would compare equal to 0.
.. table:: Recognized test mask names
+-------+----------------------+---------------+
| Name | floating-point class | Bitmask value |
+=======+======================+===============+
| nan | Any NaN | 3 |
+-------+----------------------+---------------+
| inf | +/- infinity | 516 |
+-------+----------------------+---------------+
| norm | +/- normal | 26 |
+-------+----------------------+---------------+
| sub | +/- subnormal | 144 |
+-------+----------------------+---------------+
| zero | +/- 0 | 96 |
+-------+----------------------+---------------+
| all | All values | 1023 |
+-------+----------------------+---------------+
| snan | Signaling NaN | 1 |
+-------+----------------------+---------------+
| qnan | Quiet NaN | 2 |
+-------+----------------------+---------------+
| ninf | Negative infinity | 4 |
+-------+----------------------+---------------+
| nnorm | Negative normal | 8 |
+-------+----------------------+---------------+
| nsub | Negative subnormal | 16 |
+-------+----------------------+---------------+
| nzero | Negative zero | 32 |
+-------+----------------------+---------------+
| pzero | Positive zero | 64 |
+-------+----------------------+---------------+
| psub | Positive subnormal | 128 |
+-------+----------------------+---------------+
| pnorm | Positive normal | 256 |
+-------+----------------------+---------------+
| pinf | Positive infinity | 512 |
+-------+----------------------+---------------+
``alignstack(<n>)``
This indicates the alignment that should be considered by the backend when
assigning this parameter to a stack slot during calling convention
lowering. The enforcement of the specified alignment is target-dependent,
as target-specific calling convention rules may override this value. This
attribute serves the purpose of carrying language specific alignment
information that is not mapped to base types in the backend (for example,
over-alignment specification through language attributes).
``allocalign``
The function parameter marked with this attribute is the alignment in bytes of the
newly allocated block returned by this function. The returned value must either have
the specified alignment or be the null pointer. The return value MAY be more aligned
than the requested alignment, but not less aligned. Invalid (e.g. non-power-of-2)
alignments are permitted for the allocalign parameter, so long as the returned pointer
is null. This attribute may only be applied to integer parameters.
``allocptr``
The function parameter marked with this attribute is the pointer
that will be manipulated by the allocator. For a realloc-like
function the pointer will be invalidated upon success (but the
same address may be returned), for a free-like function the
pointer will always be invalidated.
``readnone``
This attribute indicates that the function does not dereference that
pointer argument, even though it may read or write the memory that the
pointer points to if accessed through other pointers.
If a function reads from or writes to a readnone pointer argument, the
behavior is undefined.
``readonly``
This attribute indicates that the function does not write through this
pointer argument, even though it may write to the memory that the pointer
points to.
If a function writes to a readonly pointer argument, the behavior is
undefined.
``writeonly``
This attribute indicates that the function may write to, but does not read
through this pointer argument (even though it may read from the memory that
the pointer points to).
If a function reads from a writeonly pointer argument, the behavior is
undefined.
``writable``
This attribute is only meaningful in conjunction with ``dereferenceable(N)``
or another attribute that implies the first ``N`` bytes of the pointer
argument are dereferenceable.
In that case, the attribute indicates that the first ``N`` bytes will be
(non-atomically) loaded and stored back on entry to the function.
This implies that it's possible to introduce spurious stores on entry to
the function without introducing traps or data races. This does not
necessarily hold throughout the whole function, as the pointer may escape
to a different thread during the execution of the function. See also the
:ref:`atomic optimization guide <Optimization outside atomic>`
The "other attributes" that imply dereferenceability are
``dereferenceable_or_null`` (if the pointer is non-null) and the
``sret``, ``byval``, ``byref``, ``inalloca``, ``preallocated`` family of
attributes. Note that not all of these combinations are useful, e.g.
``byval`` arguments are known to be writable even without this attribute.
The ``writable`` attribute cannot be combined with ``readnone``,
``readonly`` or a ``memory`` attribute that does not contain
``argmem: write``.
``dead_on_unwind``
At a high level, this attribute indicates that the pointer argument is dead
if the call unwinds, in the sense that the caller will not depend on the
contents of the memory. Stores that would only be visible on the unwind
path can be elided.
More precisely, the behavior is as-if any memory written through the
pointer during the execution of the function is overwritten with a poison
value on unwind. This includes memory written by the implicit write implied
by the ``writable`` attribute. The caller is allowed to access the affected
memory, but all loads that are not preceded by a store will return poison.
This attribute cannot be applied to return values.
.. _gc:
Garbage Collector Strategy Names
--------------------------------
Each function may specify a garbage collector strategy name, which is simply a
string:
.. code-block:: llvm
define void @f() gc "name" { ... }
The supported values of *name* includes those :ref:`built in to LLVM
<builtin-gc-strategies>` and any provided by loaded plugins. Specifying a GC
strategy will cause the compiler to alter its output in order to support the
named garbage collection algorithm. Note that LLVM itself does not contain a
garbage collector, this functionality is restricted to generating machine code
which can interoperate with a collector provided externally.
.. _prefixdata:
Prefix Data
-----------
Prefix data is data associated with a function which the code
generator will emit immediately before the function's entrypoint.
The purpose of this feature is to allow frontends to associate
language-specific runtime metadata with specific functions and make it
available through the function pointer while still allowing the
function pointer to be called.
To access the data for a given function, a program may bitcast the
function pointer to a pointer to the constant's type and dereference
index -1. This implies that the IR symbol points just past the end of
the prefix data. For instance, take the example of a function annotated
with a single ``i32``,
.. code-block:: llvm
define void @f() prefix i32 123 { ... }
The prefix data can be referenced as,
.. code-block:: llvm
%a = getelementptr inbounds i32, ptr @f, i32 -1
%b = load i32, ptr %a
Prefix data is laid out as if it were an initializer for a global variable
of the prefix data's type. The function will be placed such that the
beginning of the prefix data is aligned. This means that if the size
of the prefix data is not a multiple of the alignment size, the
function's entrypoint will not be aligned. If alignment of the
function's entrypoint is desired, padding must be added to the prefix
data.
A function may have prefix data but no body. This has similar semantics
to the ``available_externally`` linkage in that the data may be used by the
optimizers but will not be emitted in the object file.
.. _prologuedata:
Prologue Data
-------------
The ``prologue`` attribute allows arbitrary code (encoded as bytes) to
be inserted prior to the function body. This can be used for enabling
function hot-patching and instrumentation.
To maintain the semantics of ordinary function calls, the prologue data must
have a particular format. Specifically, it must begin with a sequence of
bytes which decode to a sequence of machine instructions, valid for the
module's target, which transfer control to the point immediately succeeding
the prologue data, without performing any other visible action. This allows
the inliner and other passes to reason about the semantics of the function
definition without needing to reason about the prologue data. Obviously this
makes the format of the prologue data highly target dependent.
A trivial example of valid prologue data for the x86 architecture is ``i8 144``,
which encodes the ``nop`` instruction:
.. code-block:: text
define void @f() prologue i8 144 { ... }
Generally prologue data can be formed by encoding a relative branch instruction
which skips the metadata, as in this example of valid prologue data for the
x86_64 architecture, where the first two bytes encode ``jmp .+10``:
.. code-block:: text
%0 = type <{ i8, i8, ptr }>
define void @f() prologue %0 <{ i8 235, i8 8, ptr @md}> { ... }
A function may have prologue data but no body. This has similar semantics
to the ``available_externally`` linkage in that the data may be used by the
optimizers but will not be emitted in the object file.
.. _personalityfn:
Personality Function
--------------------
The ``personality`` attribute permits functions to specify what function
to use for exception handling.
.. _attrgrp:
Attribute Groups
----------------
Attribute groups are groups of attributes that are referenced by objects within
the IR. They are important for keeping ``.ll`` files readable, because a lot of
functions will use the same set of attributes. In the degenerative case of a
``.ll`` file that corresponds to a single ``.c`` file, the single attribute
group will capture the important command line flags used to build that file.
An attribute group is a module-level object. To use an attribute group, an
object references the attribute group's ID (e.g. ``#37``). An object may refer
to more than one attribute group. In that situation, the attributes from the
different groups are merged.
Here is an example of attribute groups for a function that should always be
inlined, has a stack alignment of 4, and which shouldn't use SSE instructions:
.. code-block:: llvm
; Target-independent attributes:
attributes #0 = { alwaysinline alignstack=4 }
; Target-dependent attributes:
attributes #1 = { "no-sse" }
; Function @f has attributes: alwaysinline, alignstack=4, and "no-sse".
define void @f() #0 #1 { ... }
.. _fnattrs:
Function Attributes
-------------------
Function attributes are set to communicate additional information about
a function. Function attributes are considered to be part of the
function, not of the function type, so functions with different function
attributes can have the same function type.
Function attributes are simple keywords that follow the type specified.
If multiple attributes are needed, they are space separated. For
example:
.. code-block:: llvm
define void @f() noinline { ... }
define void @f() alwaysinline { ... }
define void @f() alwaysinline optsize { ... }
define void @f() optsize { ... }
``alignstack(<n>)``
This attribute indicates that, when emitting the prologue and
epilogue, the backend should forcibly align the stack pointer.
Specify the desired alignment, which must be a power of two, in
parentheses.
``"alloc-family"="FAMILY"``
This indicates which "family" an allocator function is part of. To avoid
collisions, the family name should match the mangled name of the primary
allocator function, that is "malloc" for malloc/calloc/realloc/free,
"_Znwm" for ``::operator::new`` and ``::operator::delete``, and
"_ZnwmSt11align_val_t" for aligned ``::operator::new`` and
``::operator::delete``. Matching malloc/realloc/free calls within a family
can be optimized, but mismatched ones will be left alone.
``allockind("KIND")``
Describes the behavior of an allocation function. The KIND string contains comma
separated entries from the following options:
* "alloc": the function returns a new block of memory or null.
* "realloc": the function returns a new block of memory or null. If the
result is non-null the memory contents from the start of the block up to
the smaller of the original allocation size and the new allocation size
will match that of the ``allocptr`` argument and the ``allocptr``
argument is invalidated, even if the function returns the same address.
* "free": the function frees the block of memory specified by ``allocptr``.
Functions marked as "free" ``allockind`` must return void.
* "uninitialized": Any newly-allocated memory (either a new block from
a "alloc" function or the enlarged capacity from a "realloc" function)
will be uninitialized.
* "zeroed": Any newly-allocated memory (either a new block from a "alloc"
function or the enlarged capacity from a "realloc" function) will be
zeroed.
* "aligned": the function returns memory aligned according to the
``allocalign`` parameter.
The first three options are mutually exclusive, and the remaining options
describe more details of how the function behaves. The remaining options
are invalid for "free"-type functions.
``allocsize(<EltSizeParam>[, <NumEltsParam>])``
This attribute indicates that the annotated function will always return at
least a given number of bytes (or null). Its arguments are zero-indexed
parameter numbers; if one argument is provided, then it's assumed that at
least ``CallSite.Args[EltSizeParam]`` bytes will be available at the
returned pointer. If two are provided, then it's assumed that
``CallSite.Args[EltSizeParam] * CallSite.Args[NumEltsParam]`` bytes are
available. The referenced parameters must be integer types. No assumptions
are made about the contents of the returned block of memory.
``alwaysinline``
This attribute indicates that the inliner should attempt to inline
this function into callers whenever possible, ignoring any active
inlining size threshold for this caller.
``builtin``
This indicates that the callee function at a call site should be
recognized as a built-in function, even though the function's declaration
uses the ``nobuiltin`` attribute. This is only valid at call sites for
direct calls to functions that are declared with the ``nobuiltin``
attribute.
``cold``
This attribute indicates that this function is rarely called. When
computing edge weights, basic blocks post-dominated by a cold
function call are also considered to be cold; and, thus, given low
weight.
.. _attr_convergent:
``convergent``
This attribute indicates that this function is convergent.
When it appears on a call/invoke, the convergent attribute
indicates that we should treat the call as though we’re calling a
convergent function. This is particularly useful on indirect
calls; without this we may treat such calls as though the target
is non-convergent.
See :doc:`ConvergentOperations` for further details.
It is an error to call :ref:`llvm.experimental.convergence.entry
<llvm.experimental.convergence.entry>` from a function that
does not have this attribute.
``disable_sanitizer_instrumentation``
When instrumenting code with sanitizers, it can be important to skip certain
functions to ensure no instrumentation is applied to them.
This attribute is not always similar to absent ``sanitize_<name>``
attributes: depending on the specific sanitizer, code can be inserted into
functions regardless of the ``sanitize_<name>`` attribute to prevent false
positive reports.
``disable_sanitizer_instrumentation`` disables all kinds of instrumentation,
taking precedence over the ``sanitize_<name>`` attributes and other compiler
flags.
``"dontcall-error"``
This attribute denotes that an error diagnostic should be emitted when a
call of a function with this attribute is not eliminated via optimization.
Front ends can provide optional ``srcloc`` metadata nodes on call sites of
such callees to attach information about where in the source language such a
call came from. A string value can be provided as a note.
``"dontcall-warn"``
This attribute denotes that a warning diagnostic should be emitted when a
call of a function with this attribute is not eliminated via optimization.
Front ends can provide optional ``srcloc`` metadata nodes on call sites of
such callees to attach information about where in the source language such a
call came from. A string value can be provided as a note.
``fn_ret_thunk_extern``
This attribute tells the code generator that returns from functions should
be replaced with jumps to externally-defined architecture-specific symbols.
For X86, this symbol's identifier is ``__x86_return_thunk``.
``"frame-pointer"``
This attribute tells the code generator whether the function
should keep the frame pointer. The code generator may emit the frame pointer
even if this attribute says the frame pointer can be eliminated.
The allowed string values are:
* ``"none"`` (default) - the frame pointer can be eliminated.
* ``"non-leaf"`` - the frame pointer should be kept if the function calls
other functions.
* ``"all"`` - the frame pointer should be kept.
``hot``
This attribute indicates that this function is a hot spot of the program
execution. The function will be optimized more aggressively and will be
placed into special subsection of the text section to improving locality.
When profile feedback is enabled, this attribute has the precedence over
the profile information. By marking a function ``hot``, users can work
around the cases where the training input does not have good coverage
on all the hot functions.
``inlinehint``
This attribute indicates that the source code contained a hint that
inlining this function is desirable (such as the "inline" keyword in
C/C++). It is just a hint; it imposes no requirements on the
inliner.
``jumptable``
This attribute indicates that the function should be added to a
jump-instruction table at code-generation time, and that all address-taken
references to this function should be replaced with a reference to the
appropriate jump-instruction-table function pointer. Note that this creates
a new pointer for the original function, which means that code that depends
on function-pointer identity can break. So, any function annotated with
``jumptable`` must also be ``unnamed_addr``.
``memory(...)``
This attribute specifies the possible memory effects of the call-site or
function. It allows specifying the possible access kinds (``none``,
``read``, ``write``, or ``readwrite``) for the possible memory location
kinds (``argmem``, ``inaccessiblemem``, as well as a default). It is best
understood by example:
- ``memory(none)``: Does not access any memory.
- ``memory(read)``: May read (but not write) any memory.
- ``memory(write)``: May write (but not read) any memory.
- ``memory(readwrite)``: May read or write any memory.
- ``memory(argmem: read)``: May only read argument memory.
- ``memory(argmem: read, inaccessiblemem: write)``: May only read argument
memory and only write inaccessible memory.
- ``memory(read, argmem: readwrite)``: May read any memory (default mode)
and additionally write argument memory.
- ``memory(readwrite, argmem: none)``: May access any memory apart from
argument memory.
The supported memory location kinds are:
- ``argmem``: This refers to accesses that are based on pointer arguments
to the function.
- ``inaccessiblemem``: This refers to accesses to memory which is not
accessible by the current module (before return from the function -- an
allocator function may return newly accessible memory while only
accessing inaccessible memory itself). Inaccessible memory is often used
to model control dependencies of intrinsics.
- The default access kind (specified without a location prefix) applies to
all locations that haven't been specified explicitly, including those that
don't currently have a dedicated location kind (e.g. accesses to globals
or captured pointers).
If the ``memory`` attribute is not specified, then ``memory(readwrite)``
is implied (all memory effects are possible).
The memory effects of a call can be computed as
``CallSiteEffects & (FunctionEffects | OperandBundleEffects)``. Thus, the
call-site annotation takes precedence over the potential effects described
by either the function annotation or the operand bundles.
``minsize``
This attribute suggests that optimization passes and code generator
passes make choices that keep the code size of this function as small
as possible and perform optimizations that may sacrifice runtime
performance in order to minimize the size of the generated code.
This attribute is incompatible with the ``optdebug`` and ``optnone``
attributes.
``naked``
This attribute disables prologue / epilogue emission for the
function. This can have very system-specific consequences.
``"no-inline-line-tables"``
When this attribute is set to true, the inliner discards source locations
when inlining code and instead uses the source location of the call site.
Breakpoints set on code that was inlined into the current function will
not fire during the execution of the inlined call sites. If the debugger
stops inside an inlined call site, it will appear to be stopped at the
outermost inlined call site.
``no-jump-tables``
When this attribute is set to true, the jump tables and lookup tables that
can be generated from a switch case lowering are disabled.
``nobuiltin``
This indicates that the callee function at a call site is not recognized as
a built-in function. LLVM will retain the original call and not replace it
with equivalent code based on the semantics of the built-in function, unless
the call site uses the ``builtin`` attribute. This is valid at call sites
and on function declarations and definitions.
``nocallback``
This attribute indicates that the function is only allowed to jump back into
caller's module by a return or an exception, and is not allowed to jump back
by invoking a callback function, a direct, possibly transitive, external
function call, use of ``longjmp``, or other means. It is a compiler hint that
is used at module level to improve dataflow analysis, dropped during linking,
and has no effect on functions defined in the current module.
``noduplicate``
This attribute indicates that calls to the function cannot be
duplicated. A call to a ``noduplicate`` function may be moved
within its parent function, but may not be duplicated within
its parent function.
A function containing a ``noduplicate`` call may still
be an inlining candidate, provided that the call is not
duplicated by inlining. That implies that the function has
internal linkage and only has one call site, so the original
call is dead after inlining.
``nofree``
This function attribute indicates that the function does not, directly or
transitively, call a memory-deallocation function (``free``, for example)
on a memory allocation which existed before the call.
As a result, uncaptured pointers that are known to be dereferenceable
prior to a call to a function with the ``nofree`` attribute are still
known to be dereferenceable after the call. The capturing condition is
necessary in environments where the function might communicate the
pointer to another thread which then deallocates the memory. Alternatively,
``nosync`` would ensure such communication cannot happen and even captured
pointers cannot be freed by the function.
A ``nofree`` function is explicitly allowed to free memory which it
allocated or (if not ``nosync``) arrange for another thread to free
memory on it's behalf. As a result, perhaps surprisingly, a ``nofree``
function can return a pointer to a previously deallocated memory object.
``noimplicitfloat``
Disallows implicit floating-point code. This inhibits optimizations that
use floating-point code and floating-point registers for operations that are
not nominally floating-point. LLVM instructions that perform floating-point
operations or require access to floating-point registers may still cause
floating-point code to be generated.
Also inhibits optimizations that create SIMD/vector code and registers from
scalar code such as vectorization or memcpy/memset optimization. This
includes integer vectors. Vector instructions present in IR may still cause
vector code to be generated.
``noinline``
This attribute indicates that the inliner should never inline this
function in any situation. This attribute may not be used together
with the ``alwaysinline`` attribute.
``nomerge``
This attribute indicates that calls to this function should never be merged
during optimization. For example, it will prevent tail merging otherwise
identical code sequences that raise an exception or terminate the program.
Tail merging normally reduces the precision of source location information,
making stack traces less useful for debugging. This attribute gives the
user control over the tradeoff between code size and debug information
precision.
``nonlazybind``
This attribute suppresses lazy symbol binding for the function. This
may make calls to the function faster, at the cost of extra program
startup time if the function is not called during program startup.
``noprofile``
This function attribute prevents instrumentation based profiling, used for
coverage or profile based optimization, from being added to a function. It
also blocks inlining if the caller and callee have different values of this
attribute.
``skipprofile``
This function attribute prevents instrumentation based profiling, used for
coverage or profile based optimization, from being added to a function. This
attribute does not restrict inlining, so instrumented instruction could end
up in this function.
``noredzone``
This attribute indicates that the code generator should not use a
red zone, even if the target-specific ABI normally permits it.
``indirect-tls-seg-refs``
This attribute indicates that the code generator should not use
direct TLS access through segment registers, even if the
target-specific ABI normally permits it.
``noreturn``
This function attribute indicates that the function never returns
normally, hence through a return instruction. This produces undefined
behavior at runtime if the function ever does dynamically return. Annotated
functions may still raise an exception, i.a., ``nounwind`` is not implied.
``norecurse``
This function attribute indicates that the function does not call itself
either directly or indirectly down any possible call path. This produces
undefined behavior at runtime if the function ever does recurse.
.. _langref_willreturn:
``willreturn``
This function attribute indicates that a call of this function will
either exhibit undefined behavior or comes back and continues execution
at a point in the existing call stack that includes the current invocation.
Annotated functions may still raise an exception, i.a., ``nounwind`` is not implied.
If an invocation of an annotated function does not return control back
to a point in the call stack, the behavior is undefined.
``nosync``
This function attribute indicates that the function does not communicate
(synchronize) with another thread through memory or other well-defined means.
Synchronization is considered possible in the presence of `atomic` accesses
that enforce an order, thus not "unordered" and "monotonic", `volatile` accesses,
as well as `convergent` function calls.
Note that `convergent` operations can involve communication that is
considered to be not through memory and does not necessarily imply an
ordering between threads for the purposes of the memory model. Therefore,
an operation can be both `convergent` and `nosync`.
If a `nosync` function does ever synchronize with another thread,
the behavior is undefined.
``nounwind``
This function attribute indicates that the function never raises an
exception. If the function does raise an exception, its runtime
behavior is undefined. However, functions marked nounwind may still
trap or generate asynchronous exceptions. Exception handling schemes
that are recognized by LLVM to handle asynchronous exceptions, such
as SEH, will still provide their implementation defined semantics.
``nosanitize_bounds``
This attribute indicates that bounds checking sanitizer instrumentation
is disabled for this function.
``nosanitize_coverage``
This attribute indicates that SanitizerCoverage instrumentation is disabled
for this function.
``null_pointer_is_valid``
If ``null_pointer_is_valid`` is set, then the ``null`` address
in address-space 0 is considered to be a valid address for memory loads and
stores. Any analysis or optimization should not treat dereferencing a
pointer to ``null`` as undefined behavior in this function.
Note: Comparing address of a global variable to ``null`` may still
evaluate to false because of a limitation in querying this attribute inside
constant expressions.
``optdebug``
This attribute suggests that optimization passes and code generator passes
should make choices that try to preserve debug info without significantly
degrading runtime performance.
This attribute is incompatible with the ``minsize``, ``optsize``, and
``optnone`` attributes.
``optforfuzzing``
This attribute indicates that this function should be optimized
for maximum fuzzing signal.
``optnone``
This function attribute indicates that most optimization passes will skip
this function, with the exception of interprocedural optimization passes.
Code generation defaults to the "fast" instruction selector.
This attribute cannot be used together with the ``alwaysinline``
attribute; this attribute is also incompatible
with the ``minsize``, ``optsize``, and ``optdebug`` attributes.
This attribute requires the ``noinline`` attribute to be specified on
the function as well, so the function is never inlined into any caller.
Only functions with the ``alwaysinline`` attribute are valid
candidates for inlining into the body of this function.
``optsize``
This attribute suggests that optimization passes and code generator
passes make choices that keep the code size of this function low,
and otherwise do optimizations specifically to reduce code size as
long as they do not significantly impact runtime performance.
This attribute is incompatible with the ``optdebug`` and ``optnone``
attributes.
``"patchable-function"``
This attribute tells the code generator that the code
generated for this function needs to follow certain conventions that
make it possible for a runtime function to patch over it later.
The exact effect of this attribute depends on its string value,
for which there currently is one legal possibility:
* ``"prologue-short-redirect"`` - This style of patchable
function is intended to support patching a function prologue to
redirect control away from the function in a thread safe
manner. It guarantees that the first instruction of the
function will be large enough to accommodate a short jump
instruction, and will be sufficiently aligned to allow being
fully changed via an atomic compare-and-swap instruction.
While the first requirement can be satisfied by inserting large
enough NOP, LLVM can and will try to re-purpose an existing
instruction (i.e. one that would have to be emitted anyway) as
the patchable instruction larger than a short jump.
``"prologue-short-redirect"`` is currently only supported on
x86-64.
This attribute by itself does not imply restrictions on
inter-procedural optimizations. All of the semantic effects the
patching may have to be separately conveyed via the linkage type.
``"probe-stack"``
This attribute indicates that the function will trigger a guard region
in the end of the stack. It ensures that accesses to the stack must be
no further apart than the size of the guard region to a previous
access of the stack. It takes one required string value, the name of
the stack probing function that will be called.
If a function that has a ``"probe-stack"`` attribute is inlined into
a function with another ``"probe-stack"`` attribute, the resulting
function has the ``"probe-stack"`` attribute of the caller. If a
function that has a ``"probe-stack"`` attribute is inlined into a
function that has no ``"probe-stack"`` attribute at all, the resulting
function has the ``"probe-stack"`` attribute of the callee.
``"stack-probe-size"``
This attribute controls the behavior of stack probes: either
the ``"probe-stack"`` attribute, or ABI-required stack probes, if any.
It defines the size of the guard region. It ensures that if the function
may use more stack space than the size of the guard region, stack probing
sequence will be emitted. It takes one required integer value, which
is 4096 by default.
If a function that has a ``"stack-probe-size"`` attribute is inlined into
a function with another ``"stack-probe-size"`` attribute, the resulting
function has the ``"stack-probe-size"`` attribute that has the lower
numeric value. If a function that has a ``"stack-probe-size"`` attribute is
inlined into a function that has no ``"stack-probe-size"`` attribute
at all, the resulting function has the ``"stack-probe-size"`` attribute
of the callee.
``"no-stack-arg-probe"``
This attribute disables ABI-required stack probes, if any.
``returns_twice``
This attribute indicates that this function can return twice. The C
``setjmp`` is an example of such a function. The compiler disables
some optimizations (like tail calls) in the caller of these
functions.
``safestack``
This attribute indicates that
`SafeStack <https://clang.llvm.org/docs/SafeStack.html>`_
protection is enabled for this function.
If a function that has a ``safestack`` attribute is inlined into a
function that doesn't have a ``safestack`` attribute or which has an
``ssp``, ``sspstrong`` or ``sspreq`` attribute, then the resulting
function will have a ``safestack`` attribute.
``sanitize_address``
This attribute indicates that AddressSanitizer checks
(dynamic address safety analysis) are enabled for this function.
``sanitize_memory``
This attribute indicates that MemorySanitizer checks (dynamic detection
of accesses to uninitialized memory) are enabled for this function.
``sanitize_thread``
This attribute indicates that ThreadSanitizer checks
(dynamic thread safety analysis) are enabled for this function.
``sanitize_hwaddress``
This attribute indicates that HWAddressSanitizer checks
(dynamic address safety analysis based on tagged pointers) are enabled for
this function.
``sanitize_memtag``
This attribute indicates that MemTagSanitizer checks
(dynamic address safety analysis based on Armv8 MTE) are enabled for
this function.
``speculative_load_hardening``
This attribute indicates that
`Speculative Load Hardening <https://llvm.org/docs/SpeculativeLoadHardening.html>`_
should be enabled for the function body.
Speculative Load Hardening is a best-effort mitigation against
information leak attacks that make use of control flow
miss-speculation - specifically miss-speculation of whether a branch
is taken or not. Typically vulnerabilities enabling such attacks are
classified as "Spectre variant #1". Notably, this does not attempt to
mitigate against miss-speculation of branch target, classified as
"Spectre variant #2" vulnerabilities.
When inlining, the attribute is sticky. Inlining a function that carries
this attribute will cause the caller to gain the attribute. This is intended
to provide a maximally conservative model where the code in a function
annotated with this attribute will always (even after inlining) end up
hardened.
``speculatable``
This function attribute indicates that the function does not have any
effects besides calculating its result and does not have undefined behavior.
Note that ``speculatable`` is not enough to conclude that along any
particular execution path the number of calls to this function will not be
externally observable. This attribute is only valid on functions
and declarations, not on individual call sites. If a function is
incorrectly marked as speculatable and really does exhibit
undefined behavior, the undefined behavior may be observed even
if the call site is dead code.
``ssp``
This attribute indicates that the function should emit a stack
smashing protector. It is in the form of a "canary" --- a random value
placed on the stack before the local variables that's checked upon
return from the function to see if it has been overwritten. A
heuristic is used to determine if a function needs stack protectors
or not. The heuristic used will enable protectors for functions with:
- Character arrays larger than ``ssp-buffer-size`` (default 8).
- Aggregates containing character arrays larger than ``ssp-buffer-size``.
- Calls to alloca() with variable sizes or constant sizes greater than
``ssp-buffer-size``.
Variables that are identified as requiring a protector will be arranged
on the stack such that they are adjacent to the stack protector guard.
If a function with an ``ssp`` attribute is inlined into a calling function,
the attribute is not carried over to the calling function.
``sspstrong``
This attribute indicates that the function should emit a stack smashing
protector. This attribute causes a strong heuristic to be used when
determining if a function needs stack protectors. The strong heuristic
will enable protectors for functions with:
- Arrays of any size and type
- Aggregates containing an array of any size and type.
- Calls to alloca().
- Local variables that have had their address taken.
Variables that are identified as requiring a protector will be arranged
on the stack such that they are adjacent to the stack protector guard.
The specific layout rules are:
#. Large arrays and structures containing large arrays
(``>= ssp-buffer-size``) are closest to the stack protector.
#. Small arrays and structures containing small arrays
(``< ssp-buffer-size``) are 2nd closest to the protector.
#. Variables that have had their address taken are 3rd closest to the
protector.
This overrides the ``ssp`` function attribute.
If a function with an ``sspstrong`` attribute is inlined into a calling
function which has an ``ssp`` attribute, the calling function's attribute
will be upgraded to ``sspstrong``.
``sspreq``
This attribute indicates that the function should *always* emit a stack
smashing protector. This overrides the ``ssp`` and ``sspstrong`` function
attributes.
Variables that are identified as requiring a protector will be arranged
on the stack such that they are adjacent to the stack protector guard.
The specific layout rules are:
#. Large arrays and structures containing large arrays
(``>= ssp-buffer-size``) are closest to the stack protector.
#. Small arrays and structures containing small arrays
(``< ssp-buffer-size``) are 2nd closest to the protector.
#. Variables that have had their address taken are 3rd closest to the
protector.
If a function with an ``sspreq`` attribute is inlined into a calling
function which has an ``ssp`` or ``sspstrong`` attribute, the calling
function's attribute will be upgraded to ``sspreq``.
``strictfp``
This attribute indicates that the function was called from a scope that
requires strict floating-point semantics. LLVM will not attempt any
optimizations that require assumptions about the floating-point rounding
mode or that might alter the state of floating-point status flags that
might otherwise be set or cleared by calling this function. LLVM will
not introduce any new floating-point instructions that may trap.
.. _denormal_fp_math:
``"denormal-fp-math"``
This indicates the denormal (subnormal) handling that may be
assumed for the default floating-point environment. This is a
comma separated pair. The elements may be one of ``"ieee"``,
``"preserve-sign"``, ``"positive-zero"``, or ``"dynamic"``. The
first entry indicates the flushing mode for the result of floating
point operations. The second indicates the handling of denormal inputs
to floating point instructions. For compatibility with older
bitcode, if the second value is omitted, both input and output
modes will assume the same mode.
If this is attribute is not specified, the default is ``"ieee,ieee"``.
If the output mode is ``"preserve-sign"``, or ``"positive-zero"``,
denormal outputs may be flushed to zero by standard floating-point
operations. It is not mandated that flushing to zero occurs, but if
a denormal output is flushed to zero, it must respect the sign
mode. Not all targets support all modes.
If the mode is ``"dynamic"``, the behavior is derived from the
dynamic state of the floating-point environment. Transformations
which depend on the behavior of denormal values should not be
performed.
While this indicates the expected floating point mode the function
will be executed with, this does not make any attempt to ensure
the mode is consistent. User or platform code is expected to set
the floating point mode appropriately before function entry.
If the input mode is ``"preserve-sign"``, or ``"positive-zero"``,
a floating-point operation must treat any input denormal value as
zero. In some situations, if an instruction does not respect this
mode, the input may need to be converted to 0 as if by
``@llvm.canonicalize`` during lowering for correctness.
``"denormal-fp-math-f32"``
Same as ``"denormal-fp-math"``, but only controls the behavior of
the 32-bit float type (or vectors of 32-bit floats). If both are
are present, this overrides ``"denormal-fp-math"``. Not all targets
support separately setting the denormal mode per type, and no
attempt is made to diagnose unsupported uses. Currently this
attribute is respected by the AMDGPU and NVPTX backends.
``"thunk"``
This attribute indicates that the function will delegate to some other
function with a tail call. The prototype of a thunk should not be used for
optimization purposes. The caller is expected to cast the thunk prototype to
match the thunk target prototype.
``"tls-load-hoist"``
This attribute indicates that the function will try to reduce redundant
tls address calculation by hoisting tls variable.
``uwtable[(sync|async)]``
This attribute indicates that the ABI being targeted requires that
an unwind table entry be produced for this function even if we can
show that no exceptions passes by it. This is normally the case for
the ELF x86-64 abi, but it can be disabled for some compilation
units. The optional parameter describes what kind of unwind tables
to generate: ``sync`` for normal unwind tables, ``async`` for asynchronous
(instruction precise) unwind tables. Without the parameter, the attribute
``uwtable`` is equivalent to ``uwtable(async)``.
``nocf_check``
This attribute indicates that no control-flow check will be performed on
the attributed entity. It disables -fcf-protection=<> for a specific
entity to fine grain the HW control flow protection mechanism. The flag
is target independent and currently appertains to a function or function
pointer.
``shadowcallstack``
This attribute indicates that the ShadowCallStack checks are enabled for
the function. The instrumentation checks that the return address for the
function has not changed between the function prolog and epilog. It is
currently x86_64-specific.
.. _langref_mustprogress:
``mustprogress``
This attribute indicates that the function is required to return, unwind,
or interact with the environment in an observable way e.g. via a volatile
memory access, I/O, or other synchronization. The ``mustprogress``
attribute is intended to model the requirements of the first section of
[intro.progress] of the C++ Standard. As a consequence, a loop in a
function with the `mustprogress` attribute can be assumed to terminate if
it does not interact with the environment in an observable way, and
terminating loops without side-effects can be removed. If a `mustprogress`
function does not satisfy this contract, the behavior is undefined. This
attribute does not apply transitively to callees, but does apply to call
sites within the function. Note that `willreturn` implies `mustprogress`.
``"warn-stack-size"="<threshold>"``
This attribute sets a threshold to emit diagnostics once the frame size is
known should the frame size exceed the specified value. It takes one
required integer value, which should be a non-negative integer, and less
than `UINT_MAX`. It's unspecified which threshold will be used when
duplicate definitions are linked together with differing values.
``vscale_range(<min>[, <max>])``
This function attribute indicates `vscale` is a power-of-two within a
specified range. `min` must be a power-of-two that is greater than 0. When
specified, `max` must be a power-of-two greater-than-or-equal to `min` or 0
to signify an unbounded maximum. The syntax `vscale_range(<val>)` can be
used to set both `min` and `max` to the same value. Functions that don't
include this attribute make no assumptions about the value of `vscale`.
``"nooutline"``
This attribute indicates that outlining passes should not modify the
function.
Call Site Attributes
----------------------
In addition to function attributes the following call site only
attributes are supported:
``vector-function-abi-variant``
This attribute can be attached to a :ref:`call <i_call>` to list
the vector functions associated to the function. Notice that the
attribute cannot be attached to a :ref:`invoke <i_invoke>` or a
:ref:`callbr <i_callbr>` instruction. The attribute consists of a
comma separated list of mangled names. The order of the list does
not imply preference (it is logically a set). The compiler is free
to pick any listed vector function of its choosing.
The syntax for the mangled names is as follows:::
_ZGV<isa><mask><vlen><parameters>_<scalar_name>[(<vector_redirection>)]
When present, the attribute informs the compiler that the function
``<scalar_name>`` has a corresponding vector variant that can be
used to perform the concurrent invocation of ``<scalar_name>`` on
vectors. The shape of the vector function is described by the
tokens between the prefix ``_ZGV`` and the ``<scalar_name>``
token. The standard name of the vector function is
``_ZGV<isa><mask><vlen><parameters>_<scalar_name>``. When present,
the optional token ``(<vector_redirection>)`` informs the compiler
that a custom name is provided in addition to the standard one
(custom names can be provided for example via the use of ``declare
variant`` in OpenMP 5.0). The declaration of the variant must be
present in the IR Module. The signature of the vector variant is
determined by the rules of the Vector Function ABI (VFABI)
specifications of the target. For Arm and X86, the VFABI can be
found at https://github.com/ARM-software/abi-aa and
https://software.intel.com/content/www/us/en/develop/download/vector-simd-function-abi.html,
respectively.
For X86 and Arm targets, the values of the tokens in the standard
name are those that are defined in the VFABI. LLVM has an internal
``<isa>`` token that can be used to create scalar-to-vector
mappings for functions that are not directly associated to any of
the target ISAs (for example, some of the mappings stored in the
TargetLibraryInfo). Valid values for the ``<isa>`` token are:::
<isa>:= b | c | d | e -> X86 SSE, AVX, AVX2, AVX512
| n | s -> Armv8 Advanced SIMD, SVE
| __LLVM__ -> Internal LLVM Vector ISA
For all targets currently supported (x86, Arm and Internal LLVM),
the remaining tokens can have the following values:::
<mask>:= M | N -> mask | no mask
<vlen>:= number -> number of lanes
| x -> VLA (Vector Length Agnostic)
<parameters>:= v -> vector
| l | l <number> -> linear
| R | R <number> -> linear with ref modifier
| L | L <number> -> linear with val modifier
| U | U <number> -> linear with uval modifier
| ls <pos> -> runtime linear
| Rs <pos> -> runtime linear with ref modifier
| Ls <pos> -> runtime linear with val modifier
| Us <pos> -> runtime linear with uval modifier
| u -> uniform
<scalar_name>:= name of the scalar function
<vector_redirection>:= optional, custom name of the vector function
``preallocated(<ty>)``
This attribute is required on calls to ``llvm.call.preallocated.arg``
and cannot be used on any other call. See
:ref:`llvm.call.preallocated.arg<int_call_preallocated_arg>` for more
details.
.. _glattrs:
Global Attributes
-----------------
Attributes may be set to communicate additional information about a global variable.
Unlike :ref:`function attributes <fnattrs>`, attributes on a global variable
are grouped into a single :ref:`attribute group <attrgrp>`.
``no_sanitize_address``
This attribute indicates that the global variable should not have
AddressSanitizer instrumentation applied to it, because it was annotated
with `__attribute__((no_sanitize("address")))`,
`__attribute__((disable_sanitizer_instrumentation))`, or included in the
`-fsanitize-ignorelist` file.
``no_sanitize_hwaddress``
This attribute indicates that the global variable should not have
HWAddressSanitizer instrumentation applied to it, because it was annotated
with `__attribute__((no_sanitize("hwaddress")))`,
`__attribute__((disable_sanitizer_instrumentation))`, or included in the
`-fsanitize-ignorelist` file.
``sanitize_memtag``
This attribute indicates that the global variable should have AArch64 memory
tags (MTE) instrumentation applied to it. This attribute causes the
suppression of certain optimisations, like GlobalMerge, as well as ensuring
extra directives are emitted in the assembly and extra bits of metadata are
placed in the object file so that the linker can ensure the accesses are
protected by MTE. This attribute is added by clang when
`-fsanitize=memtag-globals` is provided, as long as the global is not marked
with `__attribute__((no_sanitize("memtag")))`,
`__attribute__((disable_sanitizer_instrumentation))`, or included in the
`-fsanitize-ignorelist` file. The AArch64 Globals Tagging pass may remove
this attribute when it's not possible to tag the global (e.g. it's a TLS
variable).
``sanitize_address_dyninit``
This attribute indicates that the global variable, when instrumented with
AddressSanitizer, should be checked for ODR violations. This attribute is
applied to global variables that are dynamically initialized according to
C++ rules.
.. _opbundles:
Operand Bundles
---------------
Operand bundles are tagged sets of SSA values that can be associated
with certain LLVM instructions (currently only ``call`` s and
``invoke`` s). In a way they are like metadata, but dropping them is
incorrect and will change program semantics.
Syntax::
operand bundle set ::= '[' operand bundle (, operand bundle )* ']'
operand bundle ::= tag '(' [ bundle operand ] (, bundle operand )* ')'
bundle operand ::= SSA value
tag ::= string constant
Operand bundles are **not** part of a function's signature, and a
given function may be called from multiple places with different kinds
of operand bundles. This reflects the fact that the operand bundles
are conceptually a part of the ``call`` (or ``invoke``), not the
callee being dispatched to.
Operand bundles are a generic mechanism intended to support
runtime-introspection-like functionality for managed languages. While
the exact semantics of an operand bundle depend on the bundle tag,
there are certain limitations to how much the presence of an operand
bundle can influence the semantics of a program. These restrictions
are described as the semantics of an "unknown" operand bundle. As
long as the behavior of an operand bundle is describable within these
restrictions, LLVM does not need to have special knowledge of the
operand bundle to not miscompile programs containing it.
- The bundle operands for an unknown operand bundle escape in unknown
ways before control is transferred to the callee or invokee.
- Calls and invokes with operand bundles have unknown read / write
effect on the heap on entry and exit (even if the call target specifies
a ``memory`` attribute), unless they're overridden with
callsite specific attributes.
- An operand bundle at a call site cannot change the implementation
of the called function. Inter-procedural optimizations work as
usual as long as they take into account the first two properties.
More specific types of operand bundles are described below.
.. _deopt_opbundles:
Deoptimization Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Deoptimization operand bundles are characterized by the ``"deopt"``
operand bundle tag. These operand bundles represent an alternate
"safe" continuation for the call site they're attached to, and can be
used by a suitable runtime to deoptimize the compiled frame at the
specified call site. There can be at most one ``"deopt"`` operand
bundle attached to a call site. Exact details of deoptimization is
out of scope for the language reference, but it usually involves
rewriting a compiled frame into a set of interpreted frames.
From the compiler's perspective, deoptimization operand bundles make
the call sites they're attached to at least ``readonly``. They read
through all of their pointer typed operands (even if they're not
otherwise escaped) and the entire visible heap. Deoptimization
operand bundles do not capture their operands except during
deoptimization, in which case control will not be returned to the
compiled frame.
The inliner knows how to inline through calls that have deoptimization
operand bundles. Just like inlining through a normal call site
involves composing the normal and exceptional continuations, inlining
through a call site with a deoptimization operand bundle needs to
appropriately compose the "safe" deoptimization continuation. The
inliner does this by prepending the parent's deoptimization
continuation to every deoptimization continuation in the inlined body.
E.g. inlining ``@f`` into ``@g`` in the following example
.. code-block:: llvm
define void @f() {
call void @x() ;; no deopt state
call void @y() [ "deopt"(i32 10) ]
call void @y() [ "deopt"(i32 10), "unknown"(ptr null) ]
ret void
}
define void @g() {
call void @f() [ "deopt"(i32 20) ]
ret void
}
will result in
.. code-block:: llvm
define void @g() {
call void @x() ;; still no deopt state
call void @y() [ "deopt"(i32 20, i32 10) ]
call void @y() [ "deopt"(i32 20, i32 10), "unknown"(ptr null) ]
ret void
}
It is the frontend's responsibility to structure or encode the
deoptimization state in a way that syntactically prepending the
caller's deoptimization state to the callee's deoptimization state is
semantically equivalent to composing the caller's deoptimization
continuation after the callee's deoptimization continuation.
.. _ob_funclet:
Funclet Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^
Funclet operand bundles are characterized by the ``"funclet"``
operand bundle tag. These operand bundles indicate that a call site
is within a particular funclet. There can be at most one
``"funclet"`` operand bundle attached to a call site and it must have
exactly one bundle operand.
If any funclet EH pads have been "entered" but not "exited" (per the
`description in the EH doc\ <ExceptionHandling.html#wineh-constraints>`_),
it is undefined behavior to execute a ``call`` or ``invoke`` which:
* does not have a ``"funclet"`` bundle and is not a ``call`` to a nounwind
intrinsic, or
* has a ``"funclet"`` bundle whose operand is not the most-recently-entered
not-yet-exited funclet EH pad.
Similarly, if no funclet EH pads have been entered-but-not-yet-exited,
executing a ``call`` or ``invoke`` with a ``"funclet"`` bundle is undefined behavior.
GC Transition Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
GC transition operand bundles are characterized by the
``"gc-transition"`` operand bundle tag. These operand bundles mark a
call as a transition between a function with one GC strategy to a
function with a different GC strategy. If coordinating the transition
between GC strategies requires additional code generation at the call
site, these bundles may contain any values that are needed by the
generated code. For more details, see :ref:`GC Transitions
<gc_transition_args>`.
The bundle contain an arbitrary list of Values which need to be passed
to GC transition code. They will be lowered and passed as operands to
the appropriate GC_TRANSITION nodes in the selection DAG. It is assumed
that these arguments must be available before and after (but not
necessarily during) the execution of the callee.
.. _assume_opbundles:
Assume Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^
Operand bundles on an :ref:`llvm.assume <int_assume>` allows representing
assumptions, such as that a :ref:`parameter attribute <paramattrs>` or a
:ref:`function attribute <fnattrs>` holds for a certain value at a certain
location. Operand bundles enable assumptions that are either hard or impossible
to represent as a boolean argument of an :ref:`llvm.assume <int_assume>`.
An assume operand bundle has the form:
::
"<tag>"([ <arguments>] ])
In the case of function or parameter attributes, the operand bundle has the
restricted form:
::
"<tag>"([ <holds for value> [, <attribute argument>] ])
* The tag of the operand bundle is usually the name of attribute that can be
assumed to hold. It can also be `ignore`, this tag doesn't contain any
information and should be ignored.
* The first argument if present is the value for which the attribute hold.
* The second argument if present is an argument of the attribute.
If there are no arguments the attribute is a property of the call location.
For example:
.. code-block:: llvm
call void @llvm.assume(i1 true) ["align"(ptr %val, i32 8)]
allows the optimizer to assume that at location of call to
:ref:`llvm.assume <int_assume>` ``%val`` has an alignment of at least 8.
.. code-block:: llvm
call void @llvm.assume(i1 %cond) ["cold"(), "nonnull"(ptr %val)]
allows the optimizer to assume that the :ref:`llvm.assume <int_assume>`
call location is cold and that ``%val`` may not be null.
Just like for the argument of :ref:`llvm.assume <int_assume>`, if any of the
provided guarantees are violated at runtime the behavior is undefined.
While attributes expect constant arguments, assume operand bundles may be
provided a dynamic value, for example:
.. code-block:: llvm
call void @llvm.assume(i1 true) ["align"(ptr %val, i32 %align)]
If the operand bundle value violates any requirements on the attribute value,
the behavior is undefined, unless one of the following exceptions applies:
* ``"align"`` operand bundles may specify a non-power-of-two alignment
(including a zero alignment). If this is the case, then the pointer value
must be a null pointer, otherwise the behavior is undefined.
In addition to allowing operand bundles encoding function and parameter
attributes, an assume operand bundle my also encode a ``separate_storage``
operand bundle. This has the form:
.. code-block:: llvm
separate_storage(<val1>, <val2>)``
This indicates that no pointer :ref:`based <pointeraliasing>` on one of its
arguments can alias any pointer based on the other.
Even if the assumed property can be encoded as a boolean value, like
``nonnull``, using operand bundles to express the property can still have
benefits:
* Attributes that can be expressed via operand bundles are directly the
property that the optimizer uses and cares about. Encoding attributes as
operand bundles removes the need for an instruction sequence that represents
the property (e.g., `icmp ne ptr %p, null` for `nonnull`) and for the
optimizer to deduce the property from that instruction sequence.
* Expressing the property using operand bundles makes it easy to identify the
use of the value as a use in an :ref:`llvm.assume <int_assume>`. This then
simplifies and improves heuristics, e.g., for use "use-sensitive"
optimizations.
.. _ob_preallocated:
Preallocated Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Preallocated operand bundles are characterized by the ``"preallocated"``
operand bundle tag. These operand bundles allow separation of the allocation
of the call argument memory from the call site. This is necessary to pass
non-trivially copyable objects by value in a way that is compatible with MSVC
on some targets. There can be at most one ``"preallocated"`` operand bundle
attached to a call site and it must have exactly one bundle operand, which is
a token generated by ``@llvm.call.preallocated.setup``. A call with this
operand bundle should not adjust the stack before entering the function, as
that will have been done by one of the ``@llvm.call.preallocated.*`` intrinsics.
.. code-block:: llvm
%foo = type { i64, i32 }
...
%t = call token @llvm.call.preallocated.setup(i32 1)
%a = call ptr @llvm.call.preallocated.arg(token %t, i32 0) preallocated(%foo)
; initialize %b
call void @bar(i32 42, ptr preallocated(%foo) %a) ["preallocated"(token %t)]
.. _ob_gc_live:
GC Live Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
A "gc-live" operand bundle is only valid on a :ref:`gc.statepoint <gc_statepoint>`
intrinsic. The operand bundle must contain every pointer to a garbage collected
object which potentially needs to be updated by the garbage collector.
When lowered, any relocated value will be recorded in the corresponding
:ref:`stackmap entry <statepoint-stackmap-format>`. See the intrinsic description
for further details.
ObjC ARC Attached Call Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
A ``"clang.arc.attachedcall"`` operand bundle on a call indicates the call is
implicitly followed by a marker instruction and a call to an ObjC runtime
function that uses the result of the call. The operand bundle takes a mandatory
pointer to the runtime function (``@objc_retainAutoreleasedReturnValue`` or
``@objc_unsafeClaimAutoreleasedReturnValue``).
The return value of a call with this bundle is used by a call to
``@llvm.objc.clang.arc.noop.use`` unless the called function's return type is
void, in which case the operand bundle is ignored.
.. code-block:: llvm
; The marker instruction and a runtime function call are inserted after the call
; to @foo.
call ptr @foo() [ "clang.arc.attachedcall"(ptr @objc_retainAutoreleasedReturnValue) ]
call ptr @foo() [ "clang.arc.attachedcall"(ptr @objc_unsafeClaimAutoreleasedReturnValue) ]
The operand bundle is needed to ensure the call is immediately followed by the
marker instruction and the ObjC runtime call in the final output.
.. _ob_ptrauth:
Pointer Authentication Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Pointer Authentication operand bundles are characterized by the
``"ptrauth"`` operand bundle tag. They are described in the
`Pointer Authentication <PointerAuth.html#operand-bundle>`__ document.
.. _ob_kcfi:
KCFI Operand Bundles
^^^^^^^^^^^^^^^^^^^^
A ``"kcfi"`` operand bundle on an indirect call indicates that the call will
be preceded by a runtime type check, which validates that the call target is
prefixed with a :ref:`type identifier<md_kcfi_type>` that matches the operand
bundle attribute. For example:
.. code-block:: llvm
call void %0() ["kcfi"(i32 1234)]
Clang emits KCFI operand bundles and the necessary metadata with
``-fsanitize=kcfi``.
.. _convergencectrl:
Convergence Control Operand Bundles
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
A "convergencectrl" operand bundle is only valid on a ``convergent`` operation.
When present, the operand bundle must contain exactly one value of token type.
See the :doc:`ConvergentOperations` document for details.
.. _moduleasm:
Module-Level Inline Assembly
----------------------------
Modules may contain "module-level inline asm" blocks, which corresponds
to the GCC "file scope inline asm" blocks. These blocks are internally
concatenated by LLVM and treated as a single unit, but may be separated
in the ``.ll`` file if desired. The syntax is very simple:
.. code-block:: llvm
module asm "inline asm code goes here"
module asm "more can go here"
The strings can contain any character by escaping non-printable
characters. The escape sequence used is simply "\\xx" where "xx" is the
two digit hex code for the number.
Note that the assembly string *must* be parseable by LLVM's integrated assembler
(unless it is disabled), even when emitting a ``.s`` file.
.. _langref_datalayout:
Data Layout
-----------
A module may specify a target specific data layout string that specifies
how data is to be laid out in memory. The syntax for the data layout is
simply:
.. code-block:: llvm
target datalayout = "layout specification"
The *layout specification* consists of a list of specifications
separated by the minus sign character ('-'). Each specification starts
with a letter and may include other information after the letter to
define some aspect of the data layout. The specifications accepted are
as follows:
``E``
Specifies that the target lays out data in big-endian form. That is,
the bits with the most significance have the lowest address
location.
``e``
Specifies that the target lays out data in little-endian form. That
is, the bits with the least significance have the lowest address
location.
``S<size>``
Specifies the natural alignment of the stack in bits. Alignment
promotion of stack variables is limited to the natural stack
alignment to avoid dynamic stack realignment. The stack alignment
must be a multiple of 8-bits. If omitted, the natural stack
alignment defaults to "unspecified", which does not prevent any
alignment promotions.
``P<address space>``
Specifies the address space that corresponds to program memory.
Harvard architectures can use this to specify what space LLVM
should place things such as functions into. If omitted, the
program memory space defaults to the default address space of 0,
which corresponds to a Von Neumann architecture that has code
and data in the same space.
``G<address space>``
Specifies the address space to be used by default when creating global
variables. If omitted, the globals address space defaults to the default
address space 0.
Note: variable declarations without an address space are always created in
address space 0, this property only affects the default value to be used
when creating globals without additional contextual information (e.g. in
LLVM passes).
.. _alloca_addrspace:
``A<address space>``
Specifies the address space of objects created by '``alloca``'.
Defaults to the default address space of 0.
``p[n]:<size>:<abi>[:<pref>][:<idx>]``
This specifies the *size* of a pointer and its ``<abi>`` and
``<pref>``\erred alignments for address space ``n``. ``<pref>`` is optional
and defaults to ``<abi>``. The fourth parameter ``<idx>`` is the size of the
index that used for address calculation, which must be less than or equal
to the pointer size. If not
specified, the default index size is equal to the pointer size. All sizes
are in bits. The address space, ``n``, is optional, and if not specified,
denotes the default address space 0. The value of ``n`` must be
in the range [1,2^24).
``i<size>:<abi>[:<pref>]``
This specifies the alignment for an integer type of a given bit
``<size>``. The value of ``<size>`` must be in the range [1,2^24).
``<pref>`` is optional and defaults to ``<abi>``.
For ``i8``, the ``<abi>`` value must equal 8,
that is, ``i8`` must be naturally aligned.
``v<size>:<abi>[:<pref>]``
This specifies the alignment for a vector type of a given bit
``<size>``. The value of ``<size>`` must be in the range [1,2^24).
``<pref>`` is optional and defaults to ``<abi>``.
``f<size>:<abi>[:<pref>]``
This specifies the alignment for a floating-point type of a given bit
``<size>``. Only values of ``<size>`` that are supported by the target
will work. 32 (float) and 64 (double) are supported on all targets; 80
or 128 (different flavors of long double) are also supported on some
targets. The value of ``<size>`` must be in the range [1,2^24).
``<pref>`` is optional and defaults to ``<abi>``.
``a:<abi>[:<pref>]``
This specifies the alignment for an object of aggregate type.
``<pref>`` is optional and defaults to ``<abi>``.
``F<type><abi>``
This specifies the alignment for function pointers.
The options for ``<type>`` are:
* ``i``: The alignment of function pointers is independent of the alignment
of functions, and is a multiple of ``<abi>``.
* ``n``: The alignment of function pointers is a multiple of the explicit
alignment specified on the function, and is a multiple of ``<abi>``.
``m:<mangling>``
If present, specifies that llvm names are mangled in the output. Symbols
prefixed with the mangling escape character ``\01`` are passed through
directly to the assembler without the escape character. The mangling style
options are
* ``e``: ELF mangling: Private symbols get a ``.L`` prefix.
* ``l``: GOFF mangling: Private symbols get a ``@`` prefix.
* ``m``: Mips mangling: Private symbols get a ``$`` prefix.
* ``o``: Mach-O mangling: Private symbols get ``L`` prefix. Other
symbols get a ``_`` prefix.
* ``x``: Windows x86 COFF mangling: Private symbols get the usual prefix.
Regular C symbols get a ``_`` prefix. Functions with ``__stdcall``,
``__fastcall``, and ``__vectorcall`` have custom mangling that appends
``@N`` where N is the number of bytes used to pass parameters. C++ symbols
starting with ``?`` are not mangled in any way.
* ``w``: Windows COFF mangling: Similar to ``x``, except that normal C
symbols do not receive a ``_`` prefix.
* ``a``: XCOFF mangling: Private symbols get a ``L..`` prefix.
``n<size1>:<size2>:<size3>...``
This specifies a set of native integer widths for the target CPU in
bits. For example, it might contain ``n32`` for 32-bit PowerPC,
``n32:64`` for PowerPC 64, or ``n8:16:32:64`` for X86-64. Elements of
this set are considered to support most general arithmetic operations
efficiently.
``ni:<address space0>:<address space1>:<address space2>...``
This specifies pointer types with the specified address spaces
as :ref:`Non-Integral Pointer Type <nointptrtype>` s. The ``0``
address space cannot be specified as non-integral.
On every specification that takes a ``<abi>:<pref>``, specifying the
``<pref>`` alignment is optional. If omitted, the preceding ``:``
should be omitted too and ``<pref>`` will be equal to ``<abi>``.
When constructing the data layout for a given target, LLVM starts with a
default set of specifications which are then (possibly) overridden by
the specifications in the ``datalayout`` keyword. The default
specifications are given in this list:
- ``e`` - little endian
- ``p:64:64:64`` - 64-bit pointers with 64-bit alignment.
- ``p[n]:64:64:64`` - Other address spaces are assumed to be the
same as the default address space.
- ``S0`` - natural stack alignment is unspecified
- ``i1:8:8`` - i1 is 8-bit (byte) aligned
- ``i8:8:8`` - i8 is 8-bit (byte) aligned as mandated
- ``i16:16:16`` - i16 is 16-bit aligned
- ``i32:32:32`` - i32 is 32-bit aligned
- ``i64:32:64`` - i64 has ABI alignment of 32-bits but preferred
alignment of 64-bits
- ``f16:16:16`` - half is 16-bit aligned
- ``f32:32:32`` - float is 32-bit aligned
- ``f64:64:64`` - double is 64-bit aligned
- ``f128:128:128`` - quad is 128-bit aligned
- ``v64:64:64`` - 64-bit vector is 64-bit aligned
- ``v128:128:128`` - 128-bit vector is 128-bit aligned
- ``a:0:64`` - aggregates are 64-bit aligned
When LLVM is determining the alignment for a given type, it uses the
following rules:
#. If the type sought is an exact match for one of the specifications,
that specification is used.
#. If no match is found, and the type sought is an integer type, then
the smallest integer type that is larger than the bitwidth of the
sought type is used. If none of the specifications are larger than
the bitwidth then the largest integer type is used. For example,
given the default specifications above, the i7 type will use the
alignment of i8 (next largest) while both i65 and i256 will use the
alignment of i64 (largest specified).
The function of the data layout string may not be what you expect.
Notably, this is not a specification from the frontend of what alignment
the code generator should use.
Instead, if specified, the target data layout is required to match what
the ultimate *code generator* expects. This string is used by the
mid-level optimizers to improve code, and this only works if it matches
what the ultimate code generator uses. There is no way to generate IR
that does not embed this target-specific detail into the IR. If you
don't specify the string, the default specifications will be used to
generate a Data Layout and the optimization phases will operate
accordingly and introduce target specificity into the IR with respect to
these default specifications.
.. _langref_triple:
Target Triple
-------------
A module may specify a target triple string that describes the target
host. The syntax for the target triple is simply:
.. code-block:: llvm
target triple = "x86_64-apple-macosx10.7.0"
The *target triple* string consists of a series of identifiers delimited
by the minus sign character ('-'). The canonical forms are:
::
ARCHITECTURE-VENDOR-OPERATING_SYSTEM
ARCHITECTURE-VENDOR-OPERATING_SYSTEM-ENVIRONMENT
This information is passed along to the backend so that it generates
code for the proper architecture. It's possible to override this on the
command line with the ``-mtriple`` command line option.
.. _objectlifetime:
Object Lifetime
----------------------
A memory object, or simply object, is a region of a memory space that is
reserved by a memory allocation such as :ref:`alloca <i_alloca>`, heap
allocation calls, and global variable definitions.
Once it is allocated, the bytes stored in the region can only be read or written
through a pointer that is :ref:`based on <pointeraliasing>` the allocation
value.
If a pointer that is not based on the object tries to read or write to the
object, it is undefined behavior.
A lifetime of a memory object is a property that decides its accessibility.
Unless stated otherwise, a memory object is alive since its allocation, and
dead after its deallocation.
It is undefined behavior to access a memory object that isn't alive, but
operations that don't dereference it such as
:ref:`getelementptr <i_getelementptr>`, :ref:`ptrtoint <i_ptrtoint>` and
:ref:`icmp <i_icmp>` return a valid result.
This explains code motion of these instructions across operations that
impact the object's lifetime.
A stack object's lifetime can be explicitly specified using
:ref:`llvm.lifetime.start <int_lifestart>` and
:ref:`llvm.lifetime.end <int_lifeend>` intrinsic function calls.
.. _pointeraliasing:
Pointer Aliasing Rules
----------------------
Any memory access must be done through a pointer value associated with
an address range of the memory access, otherwise the behavior is
undefined. Pointer values are associated with address ranges according
to the following rules:
- A pointer value is associated with the addresses associated with any
value it is *based* on.
- An address of a global variable is associated with the address range
of the variable's storage.
- The result value of an allocation instruction is associated with the
address range of the allocated storage.
- A null pointer in the default address-space is associated with no
address.
- An :ref:`undef value <undefvalues>` in *any* address-space is
associated with no address.
- An integer constant other than zero or a pointer value returned from
a function not defined within LLVM may be associated with address
ranges allocated through mechanisms other than those provided by
LLVM. Such ranges shall not overlap with any ranges of addresses
allocated by mechanisms provided by LLVM.
A pointer value is *based* on another pointer value according to the
following rules:
- A pointer value formed from a scalar ``getelementptr`` operation is *based* on
the pointer-typed operand of the ``getelementptr``.
- The pointer in lane *l* of the result of a vector ``getelementptr`` operation
is *based* on the pointer in lane *l* of the vector-of-pointers-typed operand
of the ``getelementptr``.
- The result value of a ``bitcast`` is *based* on the operand of the
``bitcast``.
- A pointer value formed by an ``inttoptr`` is *based* on all pointer
values that contribute (directly or indirectly) to the computation of
the pointer's value.
- The "*based* on" relationship is transitive.
Note that this definition of *"based"* is intentionally similar to the
definition of *"based"* in C99, though it is slightly weaker.
LLVM IR does not associate types with memory. The result type of a
``load`` merely indicates the size and alignment of the memory from
which to load, as well as the interpretation of the value. The first
operand type of a ``store`` similarly only indicates the size and
alignment of the store.
Consequently, type-based alias analysis, aka TBAA, aka
``-fstrict-aliasing``, is not applicable to general unadorned LLVM IR.
:ref:`Metadata <metadata>` may be used to encode additional information
which specialized optimization passes may use to implement type-based
alias analysis.
.. _pointercapture:
Pointer Capture
---------------
Given a function call and a pointer that is passed as an argument or stored in
the memory before the call, a pointer is *captured* by the call if it makes a
copy of any part of the pointer that outlives the call.
To be precise, a pointer is captured if one or more of the following conditions
hold:
1. The call stores any bit of the pointer carrying information into a place,
and the stored bits can be read from the place by the caller after this call
exits.
.. code-block:: llvm
@glb = global ptr null
@glb2 = global ptr null
@glb3 = global ptr null
@glbi = global i32 0
define ptr @f(ptr %a, ptr %b, ptr %c, ptr %d, ptr %e) {
store ptr %a, ptr @glb ; %a is captured by this call
store ptr %b, ptr @glb2 ; %b isn't captured because the stored value is overwritten by the store below
store ptr null, ptr @glb2
store ptr %c, ptr @glb3
call void @g() ; If @g makes a copy of %c that outlives this call (@f), %c is captured
store ptr null, ptr @glb3
%i = ptrtoint ptr %d to i64
%j = trunc i64 %i to i32
store i32 %j, ptr @glbi ; %d is captured
ret ptr %e ; %e is captured
}
2. The call stores any bit of the pointer carrying information into a place,
and the stored bits can be safely read from the place by another thread via
synchronization.
.. code-block:: llvm
@lock = global i1 true
define void @f(ptr %a) {
store ptr %a, ptr* @glb
store atomic i1 false, ptr @lock release ; %a is captured because another thread can safely read @glb
store ptr null, ptr @glb
ret void
}
3. The call's behavior depends on any bit of the pointer carrying information.
.. code-block:: llvm
@glb = global i8 0
define void @f(ptr %a) {
%c = icmp eq ptr %a, @glb
br i1 %c, label %BB_EXIT, label %BB_CONTINUE ; escapes %a
BB_EXIT:
call void @exit()
unreachable
BB_CONTINUE:
ret void
}
4. The pointer is used in a volatile access as its address.
.. _volatile:
Volatile Memory Accesses
------------------------
Certain memory accesses, such as :ref:`load <i_load>`'s,
:ref:`store <i_store>`'s, and :ref:`llvm.memcpy <int_memcpy>`'s may be
marked ``volatile``. The optimizers must not change the number of
volatile operations or change their order of execution relative to other
volatile operations. The optimizers *may* change the order of volatile
operations relative to non-volatile operations. This is not Java's
"volatile" and has no cross-thread synchronization behavior.
A volatile load or store may have additional target-specific semantics.
Any volatile operation can have side effects, and any volatile operation
can read and/or modify state which is not accessible via a regular load
or store in this module. Volatile operations may use addresses which do
not point to memory (like MMIO registers). This means the compiler may
not use a volatile operation to prove a non-volatile access to that
address has defined behavior.
The allowed side-effects for volatile accesses are limited. If a
non-volatile store to a given address would be legal, a volatile
operation may modify the memory at that address. A volatile operation
may not modify any other memory accessible by the module being compiled.
A volatile operation may not call any code in the current module.
In general (without target specific context), the address space of a
volatile operation may not be changed. Different address spaces may
have different trapping behavior when dereferencing an invalid
pointer.
The compiler may assume execution will continue after a volatile operation,
so operations which modify memory or may have undefined behavior can be
hoisted past a volatile operation.
As an exception to the preceding rule, the compiler may not assume execution
will continue after a volatile store operation. This restriction is necessary
to support the somewhat common pattern in C of intentionally storing to an
invalid pointer to crash the program. In the future, it might make sense to
allow frontends to control this behavior.
IR-level volatile loads and stores cannot safely be optimized into llvm.memcpy
or llvm.memmove intrinsics even when those intrinsics are flagged volatile.
Likewise, the backend should never split or merge target-legal volatile
load/store instructions. Similarly, IR-level volatile loads and stores cannot
change from integer to floating-point or vice versa.
.. admonition:: Rationale
Platforms may rely on volatile loads and stores of natively supported
data width to be executed as single instruction. For example, in C
this holds for an l-value of volatile primitive type with native
hardware support, but not necessarily for aggregate types. The
frontend upholds these expectations, which are intentionally
unspecified in the IR. The rules above ensure that IR transformations
do not violate the frontend's contract with the language.
.. _memmodel:
Memory Model for Concurrent Operations
--------------------------------------
The LLVM IR does not define any way to start parallel threads of
execution or to register signal handlers. Nonetheless, there are
platform-specific ways to create them, and we define LLVM IR's behavior
in their presence. This model is inspired by the C++0x memory model.
For a more informal introduction to this model, see the :doc:`Atomics`.
We define a *happens-before* partial order as the least partial order
that
- Is a superset of single-thread program order, and
- When a *synchronizes-with* ``b``, includes an edge from ``a`` to
``b``. *Synchronizes-with* pairs are introduced by platform-specific
techniques, like pthread locks, thread creation, thread joining,
etc., and by atomic instructions. (See also :ref:`Atomic Memory Ordering
Constraints <ordering>`).
Note that program order does not introduce *happens-before* edges
between a thread and signals executing inside that thread.
Every (defined) read operation (load instructions, memcpy, atomic
loads/read-modify-writes, etc.) R reads a series of bytes written by
(defined) write operations (store instructions, atomic
stores/read-modify-writes, memcpy, etc.). For the purposes of this
section, initialized globals are considered to have a write of the
initializer which is atomic and happens before any other read or write
of the memory in question. For each byte of a read R, R\ :sub:`byte`
may see any write to the same byte, except:
- If write\ :sub:`1` happens before write\ :sub:`2`, and
write\ :sub:`2` happens before R\ :sub:`byte`, then
R\ :sub:`byte` does not see write\ :sub:`1`.
- If R\ :sub:`byte` happens before write\ :sub:`3`, then
R\ :sub:`byte` does not see write\ :sub:`3`.
Given that definition, R\ :sub:`byte` is defined as follows:
- If R is volatile, the result is target-dependent. (Volatile is
supposed to give guarantees which can support ``sig_atomic_t`` in
C/C++, and may be used for accesses to addresses that do not behave
like normal memory. It does not generally provide cross-thread
synchronization.)
- Otherwise, if there is no write to the same byte that happens before
R\ :sub:`byte`, R\ :sub:`byte` returns ``undef`` for that byte.
- Otherwise, if R\ :sub:`byte` may see exactly one write,
R\ :sub:`byte` returns the value written by that write.
- Otherwise, if R is atomic, and all the writes R\ :sub:`byte` may
see are atomic, it chooses one of the values written. See the :ref:`Atomic
Memory Ordering Constraints <ordering>` section for additional
constraints on how the choice is made.
- Otherwise R\ :sub:`byte` returns ``undef``.
R returns the value composed of the series of bytes it read. This
implies that some bytes within the value may be ``undef`` **without**
the entire value being ``undef``. Note that this only defines the
semantics of the operation; it doesn't mean that targets will emit more
than one instruction to read the series of bytes.
Note that in cases where none of the atomic intrinsics are used, this
model places only one restriction on IR transformations on top of what
is required for single-threaded execution: introducing a store to a byte
which might not otherwise be stored is not allowed in general.
(Specifically, in the case where another thread might write to and read
from an address, introducing a store can change a load that may see
exactly one write into a load that may see multiple writes.)
.. _ordering:
Atomic Memory Ordering Constraints
----------------------------------
Atomic instructions (:ref:`cmpxchg <i_cmpxchg>`,
:ref:`atomicrmw <i_atomicrmw>`, :ref:`fence <i_fence>`,
:ref:`atomic load <i_load>`, and :ref:`atomic store <i_store>`) take
ordering parameters that determine which other atomic instructions on
the same address they *synchronize with*. These semantics are borrowed
from Java and C++0x, but are somewhat more colloquial. If these
descriptions aren't precise enough, check those specs (see spec
references in the :doc:`atomics guide <Atomics>`).
:ref:`fence <i_fence>` instructions treat these orderings somewhat
differently since they don't take an address. See that instruction's
documentation for details.
For a simpler introduction to the ordering constraints, see the
:doc:`Atomics`.
``unordered``
The set of values that can be read is governed by the happens-before
partial order. A value cannot be read unless some operation wrote
it. This is intended to provide a guarantee strong enough to model
Java's non-volatile shared variables. This ordering cannot be
specified for read-modify-write operations; it is not strong enough
to make them atomic in any interesting way.
``monotonic``
In addition to the guarantees of ``unordered``, there is a single
total order for modifications by ``monotonic`` operations on each
address. All modification orders must be compatible with the
happens-before order. There is no guarantee that the modification
orders can be combined to a global total order for the whole program
(and this often will not be possible). The read in an atomic
read-modify-write operation (:ref:`cmpxchg <i_cmpxchg>` and
:ref:`atomicrmw <i_atomicrmw>`) reads the value in the modification
order immediately before the value it writes. If one atomic read
happens before another atomic read of the same address, the later
read must see the same value or a later value in the address's
modification order. This disallows reordering of ``monotonic`` (or
stronger) operations on the same address. If an address is written
``monotonic``-ally by one thread, and other threads ``monotonic``-ally
read that address repeatedly, the other threads must eventually see
the write. This corresponds to the C++0x/C1x
``memory_order_relaxed``.
``acquire``
In addition to the guarantees of ``monotonic``, a
*synchronizes-with* edge may be formed with a ``release`` operation.
This is intended to model C++'s ``memory_order_acquire``.
``release``
In addition to the guarantees of ``monotonic``, if this operation
writes a value which is subsequently read by an ``acquire``
operation, it *synchronizes-with* that operation. (This isn't a
complete description; see the C++0x definition of a release
sequence.) This corresponds to the C++0x/C1x
``memory_order_release``.
``acq_rel`` (acquire+release)
Acts as both an ``acquire`` and ``release`` operation on its
address. This corresponds to the C++0x/C1x ``memory_order_acq_rel``.
``seq_cst`` (sequentially consistent)
In addition to the guarantees of ``acq_rel`` (``acquire`` for an
operation that only reads, ``release`` for an operation that only
writes), there is a global total order on all
sequentially-consistent operations on all addresses, which is
consistent with the *happens-before* partial order and with the
modification orders of all the affected addresses. Each
sequentially-consistent read sees the last preceding write to the
same address in this global order. This corresponds to the C++0x/C1x
``memory_order_seq_cst`` and Java volatile.
.. _syncscope:
If an atomic operation is marked ``syncscope("singlethread")``, it only
*synchronizes with* and only participates in the seq\_cst total orderings of
other operations running in the same thread (for example, in signal handlers).
If an atomic operation is marked ``syncscope("<target-scope>")``, where
``<target-scope>`` is a target specific synchronization scope, then it is target
dependent if it *synchronizes with* and participates in the seq\_cst total
orderings of other operations.
Otherwise, an atomic operation that is not marked ``syncscope("singlethread")``
or ``syncscope("<target-scope>")`` *synchronizes with* and participates in the
seq\_cst total orderings of other operations that are not marked
``syncscope("singlethread")`` or ``syncscope("<target-scope>")``.
.. _floatenv:
Floating-Point Environment
--------------------------
The default LLVM floating-point environment assumes that traps are disabled and
status flags are not observable. Therefore, floating-point math operations do
not have side effects and may be speculated freely. Results assume the
round-to-nearest rounding mode, and subnormals are assumed to be preserved.
Running LLVM code in an environment where these assumptions are not met can lead
to undefined behavior. The ``strictfp`` and ``denormal-fp-math`` attributes as
well as :ref:`Constrained Floating-Point Intrinsics <constrainedfp>` can be used
to weaken LLVM's assumptions and ensure defined behavior in non-default
floating-point environments; see their respective documentation for details.
.. _floatnan:
Behavior of Floating-Point NaN values
-------------------------------------
A floating-point NaN value consists of a sign bit, a quiet/signaling bit, and a
payload (which makes up the rest of the mantissa except for the quiet/signaling
bit). LLVM assumes that the quiet/signaling bit being set to ``1`` indicates a
quiet NaN (QNaN), and a value of ``0`` indicates a signaling NaN (SNaN). In the
following we will hence just call it the "quiet bit".
The representation bits of a floating-point value do not mutate arbitrarily; in
particular, if there is no floating-point operation being performed, NaN signs,
quiet bits, and payloads are preserved.
For the purpose of this section, ``bitcast`` as well as the following operations
are not "floating-point math operations": ``fneg``, ``llvm.fabs``, and
``llvm.copysign``. These operations act directly on the underlying bit
representation and never change anything except possibly for the sign bit.
For floating-point math operations, unless specified otherwise, the following
rules apply when a NaN value is returned: the result has a non-deterministic
sign; the quiet bit and payload are non-deterministically chosen from the
following set of options:
- The quiet bit is set and the payload is all-zero. ("Preferred NaN" case)
- The quiet bit is set and the payload is copied from any input operand that is
a NaN. ("Quieting NaN propagation" case)
- The quiet bit and payload are copied from any input operand that is a NaN.
("Unchanged NaN propagation" case)
- The quiet bit is set and the payload is picked from a target-specific set of
"extra" possible NaN payloads. The set can depend on the input operand values.
This set is empty on x86 and ARM, but can be non-empty on other architectures.
(For instance, on wasm, if any input NaN does not have the preferred all-zero
payload or any input NaN is an SNaN, then this set contains all possible
payloads; otherwise, it is empty. On SPARC, this set consists of the all-one
payload.)
In particular, if all input NaNs are quiet (or if there are no input NaNs), then
the output NaN is definitely quiet. Signaling NaN outputs can only occur if they
are provided as an input value. For example, "fmul SNaN, 1.0" may be simplified
to SNaN rather than QNaN. Similarly, if all input NaNs are preferred (or if
there are no input NaNs) and the target does not have any "extra" NaN payloads,
then the output NaN is guaranteed to be preferred.
Floating-point math operations are allowed to treat all NaNs as if they were
quiet NaNs. For example, "pow(1.0, SNaN)" may be simplified to 1.0.
Code that requires different behavior than this should use the
:ref:`Constrained Floating-Point Intrinsics <constrainedfp>`.
In particular, constrained intrinsics rule out the "Unchanged NaN propagation"
case; they are guaranteed to return a QNaN.
Unfortunately, due to hard-or-impossible-to-fix issues, LLVM violates its own
specification on some architectures:
- x86-32 without SSE2 enabled may convert floating-point values to x86_fp80 and
back when performing floating-point math operations; this can lead to results
with different precision than expected and it can alter NaN values. Since
optimizations can make contradicting assumptions, this can lead to arbitrary
miscompilations. See `issue #44218
<https://github.com/llvm/llvm-project/issues/44218>`_.
- x86-32 (even with SSE2 enabled) may implicitly perform such a conversion on
values returned from a function for some calling conventions. See `issue
#66803 <https://github.com/llvm/llvm-project/issues/66803>`_.
- Older MIPS versions use the opposite polarity for the quiet/signaling bit, and
LLVM does not correctly represent this. See `issue #60796
<https://github.com/llvm/llvm-project/issues/60796>`_.
.. _fastmath:
Fast-Math Flags
---------------
LLVM IR floating-point operations (:ref:`fneg <i_fneg>`, :ref:`fadd <i_fadd>`,
:ref:`fsub <i_fsub>`, :ref:`fmul <i_fmul>`, :ref:`fdiv <i_fdiv>`,
:ref:`frem <i_frem>`, :ref:`fcmp <i_fcmp>`), :ref:`phi <i_phi>`,
:ref:`select <i_select>` and :ref:`call <i_call>`
may use the following flags to enable otherwise unsafe
floating-point transformations.
``nnan``
No NaNs - Allow optimizations to assume the arguments and result are not
NaN. If an argument is a nan, or the result would be a nan, it produces
a :ref:`poison value <poisonvalues>` instead.
``ninf``
No Infs - Allow optimizations to assume the arguments and result are not
+/-Inf. If an argument is +/-Inf, or the result would be +/-Inf, it
produces a :ref:`poison value <poisonvalues>` instead.
``nsz``
No Signed Zeros - Allow optimizations to treat the sign of a zero
argument or zero result as insignificant. This does not imply that -0.0
is poison and/or guaranteed to not exist in the operation.
``arcp``
Allow Reciprocal - Allow optimizations to use the reciprocal of an
argument rather than perform division.
``contract``
Allow floating-point contraction (e.g. fusing a multiply followed by an
addition into a fused multiply-and-add). This does not enable reassociating
to form arbitrary contractions. For example, ``(a*b) + (c*d) + e`` can not
be transformed into ``(a*b) + ((c*d) + e)`` to create two fma operations.
.. _fastmath_afn:
``afn``
Approximate functions - Allow substitution of approximate calculations for
functions (sin, log, sqrt, etc). See floating-point intrinsic definitions
for places where this can apply to LLVM's intrinsic math functions.
``reassoc``
Allow reassociation transformations for floating-point instructions.
This may dramatically change results in floating-point.
``fast``
This flag implies all of the others.
.. _uselistorder:
Use-list Order Directives
-------------------------
Use-list directives encode the in-memory order of each use-list, allowing the
order to be recreated. ``<order-indexes>`` is a comma-separated list of
indexes that are assigned to the referenced value's uses. The referenced
value's use-list is immediately sorted by these indexes.
Use-list directives may appear at function scope or global scope. They are not
instructions, and have no effect on the semantics of the IR. When they're at
function scope, they must appear after the terminator of the final basic block.
If basic blocks have their address taken via ``blockaddress()`` expressions,
``uselistorder_bb`` can be used to reorder their use-lists from outside their
function's scope.
:Syntax:
::
uselistorder <ty> <value>, { <order-indexes> }
uselistorder_bb @function, %block { <order-indexes> }
:Examples:
::
define void @foo(i32 %arg1, i32 %arg2) {
entry:
; ... instructions ...
bb:
; ... instructions ...
; At function scope.
uselistorder i32 %arg1, { 1, 0, 2 }
uselistorder label %bb, { 1, 0 }
}
; At global scope.
uselistorder ptr @global, { 1, 2, 0 }
uselistorder i32 7, { 1, 0 }
uselistorder i32 (i32) @bar, { 1, 0 }
uselistorder_bb @foo, %bb, { 5, 1, 3, 2, 0, 4 }
.. _source_filename:
Source Filename
---------------
The *source filename* string is set to the original module identifier,
which will be the name of the compiled source file when compiling from
source through the clang front end, for example. It is then preserved through
the IR and bitcode.
This is currently necessary to generate a consistent unique global
identifier for local functions used in profile data, which prepends the
source file name to the local function name.
The syntax for the source file name is simply:
.. code-block:: text
source_filename = "/path/to/source.c"
.. _typesystem:
Type System
===========
The LLVM type system is one of the most important features of the
intermediate representation. Being typed enables a number of
optimizations to be performed on the intermediate representation
directly, without having to do extra analyses on the side before the
transformation. A strong type system makes it easier to read the
generated code and enables novel analyses and transformations that are
not feasible to perform on normal three address code representations.
.. _t_void:
Void Type
---------
:Overview:
The void type does not represent any value and has no size.
:Syntax:
::
void
.. _t_function:
Function Type
-------------
:Overview:
The function type can be thought of as a function signature. It consists of a
return type and a list of formal parameter types. The return type of a function
type is a void type or first class type --- except for :ref:`label <t_label>`
and :ref:`metadata <t_metadata>` types.
:Syntax:
::
<returntype> (<parameter list>)
...where '``<parameter list>``' is a comma-separated list of type
specifiers. Optionally, the parameter list may include a type ``...``, which
indicates that the function takes a variable number of arguments. Variable
argument functions can access their arguments with the :ref:`variable argument
handling intrinsic <int_varargs>` functions. '``<returntype>``' is any type
except :ref:`label <t_label>` and :ref:`metadata <t_metadata>`.
:Examples:
+---------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``i32 (i32)`` | function taking an ``i32``, returning an ``i32`` |
+---------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``i32 (ptr, ...)`` | A vararg function that takes at least one :ref:`pointer <t_pointer>` argument and returns an integer. This is the signature for ``printf`` in LLVM. |
+---------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``{i32, i32} (i32)`` | A function taking an ``i32``, returning a :ref:`structure <t_struct>` containing two ``i32`` values |
+---------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------+
.. _t_firstclass:
First Class Types
-----------------
The :ref:`first class <t_firstclass>` types are perhaps the most important.
Values of these types are the only ones which can be produced by
instructions.
.. _t_single_value:
Single Value Types
^^^^^^^^^^^^^^^^^^
These are the types that are valid in registers from CodeGen's perspective.
.. _t_integer:
Integer Type
""""""""""""
:Overview:
The integer type is a very simple type that simply specifies an
arbitrary bit width for the integer type desired. Any bit width from 1
bit to 2\ :sup:`23`\ (about 8 million) can be specified.
:Syntax:
::
iN
The number of bits the integer will occupy is specified by the ``N``
value.
Examples:
*********
+----------------+------------------------------------------------+
| ``i1`` | a single-bit integer. |
+----------------+------------------------------------------------+
| ``i32`` | a 32-bit integer. |
+----------------+------------------------------------------------+
| ``i1942652`` | a really big integer of over 1 million bits. |
+----------------+------------------------------------------------+
.. _t_floating:
Floating-Point Types
""""""""""""""""""""
.. list-table::
:header-rows: 1
* - Type
- Description
* - ``half``
- 16-bit floating-point value
* - ``bfloat``
- 16-bit "brain" floating-point value (7-bit significand). Provides the
same number of exponent bits as ``float``, so that it matches its dynamic
range, but with greatly reduced precision. Used in Intel's AVX-512 BF16
extensions and Arm's ARMv8.6-A extensions, among others.
* - ``float``
- 32-bit floating-point value
* - ``double``
- 64-bit floating-point value
* - ``fp128``
- 128-bit floating-point value (113-bit significand)
* - ``x86_fp80``
- 80-bit floating-point value (X87)
* - ``ppc_fp128``
- 128-bit floating-point value (two 64-bits)
The binary format of half, float, double, and fp128 correspond to the
IEEE-754-2008 specifications for binary16, binary32, binary64, and binary128
respectively.
X86_amx Type
""""""""""""
:Overview:
The x86_amx type represents a value held in an AMX tile register on an x86
machine. The operations allowed on it are quite limited. Only few intrinsics
are allowed: stride load and store, zero and dot product. No instruction is
allowed for this type. There are no arguments, arrays, pointers, vectors
or constants of this type.
:Syntax:
::
x86_amx
X86_mmx Type
""""""""""""
:Overview:
The x86_mmx type represents a value held in an MMX register on an x86
machine. The operations allowed on it are quite limited: parameters and
return values, load and store, and bitcast. User-specified MMX
instructions are represented as intrinsic or asm calls with arguments
and/or results of this type. There are no arrays, vectors or constants
of this type.
:Syntax:
::
x86_mmx
.. _t_pointer:
Pointer Type
""""""""""""
:Overview:
The pointer type ``ptr`` is used to specify memory locations. Pointers are
commonly used to reference objects in memory.
Pointer types may have an optional address space attribute defining
the numbered address space where the pointed-to object resides. For
example, ``ptr addrspace(5)`` is a pointer to address space 5.
In addition to integer constants, ``addrspace`` can also reference one of the
address spaces defined in the :ref:`datalayout string<langref_datalayout>`.
``addrspace("A")`` will use the alloca address space, ``addrspace("G")``
the default globals address space and ``addrspace("P")`` the program address
space.
The default address space is number zero.
The semantics of non-zero address spaces are target-specific. Memory
access through a non-dereferenceable pointer is undefined behavior in
any address space. Pointers with the bit-value 0 are only assumed to
be non-dereferenceable in address space 0, unless the function is
marked with the ``null_pointer_is_valid`` attribute.
If an object can be proven accessible through a pointer with a
different address space, the access may be modified to use that
address space. Exceptions apply if the operation is ``volatile``.
Prior to LLVM 15, pointer types also specified a pointee type, such as
``i8*``, ``[4 x i32]*`` or ``i32 (i32*)*``. In LLVM 15, such "typed
pointers" are still supported under non-default options. See the
`opaque pointers document <OpaquePointers.html>`__ for more information.
.. _t_target_type:
Target Extension Type
"""""""""""""""""""""
:Overview:
Target extension types represent types that must be preserved through
optimization, but are otherwise generally opaque to the compiler. They may be
used as function parameters or arguments, and in :ref:`phi <i_phi>` or
:ref:`select <i_select>` instructions. Some types may be also used in
:ref:`alloca <i_alloca>` instructions or as global values, and correspondingly
it is legal to use :ref:`load <i_load>` and :ref:`store <i_store>` instructions
on them. Full semantics for these types are defined by the target.
The only constants that target extension types may have are ``zeroinitializer``,
``undef``, and ``poison``. Other possible values for target extension types may
arise from target-specific intrinsics and functions.
These types cannot be converted to other types. As such, it is not legal to use
them in :ref:`bitcast <i_bitcast>` instructions (as a source or target type),
nor is it legal to use them in :ref:`ptrtoint <i_ptrtoint>` or
:ref:`inttoptr <i_inttoptr>` instructions. Similarly, they are not legal to use
in an :ref:`icmp <i_icmp>` instruction.
Target extension types have a name and optional type or integer parameters. The
meanings of name and parameters are defined by the target. When being defined in
LLVM IR, all of the type parameters must precede all of the integer parameters.
Specific target extension types are registered with LLVM as having specific
properties. These properties can be used to restrict the type from appearing in
certain contexts, such as being the type of a global variable or having a
``zeroinitializer`` constant be valid. A complete list of type properties may be
found in the documentation for ``llvm::TargetExtType::Property`` (`doxygen
<https://llvm.org/doxygen/classllvm_1_1TargetExtType.html>`_).
:Syntax:
.. code-block:: llvm
target("label")
target("label", void)
target("label", void, i32)
target("label", 0, 1, 2)
target("label", void, i32, 0, 1, 2)
.. _t_vector:
Vector Type
"""""""""""
:Overview:
A vector type is a simple derived type that represents a vector of
elements. Vector types are used when multiple primitive data are
operated in parallel using a single instruction (SIMD). A vector type
requires a size (number of elements), an underlying primitive data type,
and a scalable property to represent vectors where the exact hardware
vector length is unknown at compile time. Vector types are considered
:ref:`first class <t_firstclass>`.
:Memory Layout:
In general vector elements are laid out in memory in the same way as
:ref:`array types <t_array>`. Such an analogy works fine as long as the vector
elements are byte sized. However, when the elements of the vector aren't byte
sized it gets a bit more complicated. One way to describe the layout is by
describing what happens when a vector such as <N x iM> is bitcasted to an
integer type with N*M bits, and then following the rules for storing such an
integer to memory.
A bitcast from a vector type to a scalar integer type will see the elements
being packed together (without padding). The order in which elements are
inserted in the integer depends on endianness. For little endian element zero
is put in the least significant bits of the integer, and for big endian
element zero is put in the most significant bits.
Using a vector such as ``<i4 1, i4 2, i4 3, i4 5>`` as an example, together
with the analogy that we can replace a vector store by a bitcast followed by
an integer store, we get this for big endian:
.. code-block:: llvm
%val = bitcast <4 x i4> <i4 1, i4 2, i4 3, i4 5> to i16
; Bitcasting from a vector to an integral type can be seen as
; concatenating the values:
; %val now has the hexadecimal value 0x1235.
store i16 %val, ptr %ptr
; In memory the content will be (8-bit addressing):
;
; [%ptr + 0]: 00010010 (0x12)
; [%ptr + 1]: 00110101 (0x35)
The same example for little endian:
.. code-block:: llvm
%val = bitcast <4 x i4> <i4 1, i4 2, i4 3, i4 5> to i16
; Bitcasting from a vector to an integral type can be seen as
; concatenating the values:
; %val now has the hexadecimal value 0x5321.
store i16 %val, ptr %ptr
; In memory the content will be (8-bit addressing):
;
; [%ptr + 0]: 00100001 (0x21)
; [%ptr + 1]: 01010011 (0x53)
When ``<N*M>`` isn't evenly divisible by the byte size the exact memory layout
is unspecified (just like it is for an integral type of the same size). This
is because different targets could put the padding at different positions when
the type size is smaller than the type's store size.
:Syntax:
::
< <# elements> x <elementtype> > ; Fixed-length vector
< vscale x <# elements> x <elementtype> > ; Scalable vector
The number of elements is a constant integer value larger than 0;
elementtype may be any integer, floating-point or pointer type. Vectors
of size zero are not allowed. For scalable vectors, the total number of
elements is a constant multiple (called vscale) of the specified number
of elements; vscale is a positive integer that is unknown at compile time
and the same hardware-dependent constant for all scalable vectors at run
time. The size of a specific scalable vector type is thus constant within
IR, even if the exact size in bytes cannot be determined until run time.
:Examples:
+------------------------+----------------------------------------------------+
| ``<4 x i32>`` | Vector of 4 32-bit integer values. |
+------------------------+----------------------------------------------------+
| ``<8 x float>`` | Vector of 8 32-bit floating-point values. |
+------------------------+----------------------------------------------------+
| ``<2 x i64>`` | Vector of 2 64-bit integer values. |
+------------------------+----------------------------------------------------+
| ``<4 x ptr>`` | Vector of 4 pointers |
+------------------------+----------------------------------------------------+
| ``<vscale x 4 x i32>`` | Vector with a multiple of 4 32-bit integer values. |
+------------------------+----------------------------------------------------+
.. _t_label:
Label Type
^^^^^^^^^^
:Overview:
The label type represents code labels.
:Syntax:
::
label
.. _t_token:
Token Type
^^^^^^^^^^
:Overview:
The token type is used when a value is associated with an instruction
but all uses of the value must not attempt to introspect or obscure it.
As such, it is not appropriate to have a :ref:`phi <i_phi>` or
:ref:`select <i_select>` of type token.
:Syntax:
::
token
.. _t_metadata:
Metadata Type
^^^^^^^^^^^^^
:Overview:
The metadata type represents embedded metadata. No derived types may be
created from metadata except for :ref:`function <t_function>` arguments.
:Syntax:
::
metadata
.. _t_aggregate:
Aggregate Types
^^^^^^^^^^^^^^^
Aggregate Types are a subset of derived types that can contain multiple
member types. :ref:`Arrays <t_array>` and :ref:`structs <t_struct>` are
aggregate types. :ref:`Vectors <t_vector>` are not considered to be
aggregate types.
.. _t_array:
Array Type
""""""""""
:Overview:
The array type is a very simple derived type that arranges elements
sequentially in memory. The array type requires a size (number of
elements) and an underlying data type.
:Syntax:
::
[<# elements> x <elementtype>]
The number of elements is a constant integer value; ``elementtype`` may
be any type with a size.
:Examples:
+------------------+--------------------------------------+
| ``[40 x i32]`` | Array of 40 32-bit integer values. |
+------------------+--------------------------------------+
| ``[41 x i32]`` | Array of 41 32-bit integer values. |
+------------------+--------------------------------------+
| ``[4 x i8]`` | Array of 4 8-bit integer values. |
+------------------+--------------------------------------+
Here are some examples of multidimensional arrays:
+-----------------------------+----------------------------------------------------------+
| ``[3 x [4 x i32]]`` | 3x4 array of 32-bit integer values. |
+-----------------------------+----------------------------------------------------------+
| ``[12 x [10 x float]]`` | 12x10 array of single precision floating-point values. |
+-----------------------------+----------------------------------------------------------+
| ``[2 x [3 x [4 x i16]]]`` | 2x3x4 array of 16-bit integer values. |
+-----------------------------+----------------------------------------------------------+
There is no restriction on indexing beyond the end of the array implied
by a static type (though there are restrictions on indexing beyond the
bounds of an allocated object in some cases). This means that
single-dimension 'variable sized array' addressing can be implemented in
LLVM with a zero length array type. An implementation of 'pascal style
arrays' in LLVM could use the type "``{ i32, [0 x float]}``", for
example.
.. _t_struct:
Structure Type
""""""""""""""
:Overview:
The structure type is used to represent a collection of data members
together in memory. The elements of a structure may be any type that has
a size.
Structures in memory are accessed using '``load``' and '``store``' by
getting a pointer to a field with the '``getelementptr``' instruction.
Structures in registers are accessed using the '``extractvalue``' and
'``insertvalue``' instructions.
Structures may optionally be "packed" structures, which indicate that
the alignment of the struct is one byte, and that there is no padding
between the elements. In non-packed structs, padding between field types
is inserted as defined by the DataLayout string in the module, which is
required to match what the underlying code generator expects.
Structures can either be "literal" or "identified". A literal structure
is defined inline with other types (e.g. ``[2 x {i32, i32}]``) whereas
identified types are always defined at the top level with a name.
Literal types are uniqued by their contents and can never be recursive
or opaque since there is no way to write one. Identified types can be
recursive, can be opaqued, and are never uniqued.
:Syntax:
::
%T1 = type { <type list> } ; Identified normal struct type
%T2 = type <{ <type list> }> ; Identified packed struct type
:Examples:
+------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``{ i32, i32, i32 }`` | A triple of three ``i32`` values |
+------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``{ float, ptr }`` | A pair, where the first element is a ``float`` and the second element is a :ref:`pointer <t_pointer>`. |
+------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| ``<{ i8, i32 }>`` | A packed struct known to be 5 bytes in size. |
+------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
.. _t_opaque:
Opaque Structure Types
""""""""""""""""""""""
:Overview:
Opaque structure types are used to represent structure types that
do not have a body specified. This corresponds (for example) to the C
notion of a forward declared structure. They can be named (``%X``) or
unnamed (``%52``).
:Syntax:
::
%X = type opaque
%52 = type opaque
:Examples:
+--------------+-------------------+
| ``opaque`` | An opaque type. |
+--------------+-------------------+
.. _constants:
Constants
=========
LLVM has several different basic types of constants. This section
describes them all and their syntax.
Simple Constants
----------------
**Boolean constants**
The two strings '``true``' and '``false``' are both valid constants
of the ``i1`` type.
**Integer constants**
Standard integers (such as '4') are constants of the :ref:`integer
<t_integer>` type. They can be either decimal or
hexadecimal. Decimal integers can be prefixed with - to represent
negative integers, e.g. '``-1234``'. Hexadecimal integers must be
prefixed with either u or s to indicate whether they are unsigned
or signed respectively. e.g '``u0x8000``' gives 32768, whilst
'``s0x8000``' gives -32768.
Note that hexadecimal integers are sign extended from the number
of active bits, i.e. the bit width minus the number of leading
zeros. So '``s0x0001``' of type '``i16``' will be -1, not 1.
**Floating-point constants**
Floating-point constants use standard decimal notation (e.g.
123.421), exponential notation (e.g. 1.23421e+2), or a more precise
hexadecimal notation (see below). The assembler requires the exact
decimal value of a floating-point constant. For example, the
assembler accepts 1.25 but rejects 1.3 because 1.3 is a repeating
decimal in binary. Floating-point constants must have a
:ref:`floating-point <t_floating>` type.
**Null pointer constants**
The identifier '``null``' is recognized as a null pointer constant
and must be of :ref:`pointer type <t_pointer>`.
**Token constants**
The identifier '``none``' is recognized as an empty token constant
and must be of :ref:`token type <t_token>`.
The one non-intuitive notation for constants is the hexadecimal form of
floating-point constants. For example, the form
'``double 0x432ff973cafa8000``' is equivalent to (but harder to read
than) '``double 4.5e+15``'. The only time hexadecimal floating-point
constants are required (and the only time that they are generated by the
disassembler) is when a floating-point constant must be emitted but it
cannot be represented as a decimal floating-point number in a reasonable
number of digits. For example, NaN's, infinities, and other special
values are represented in their IEEE hexadecimal format so that assembly
and disassembly do not cause any bits to change in the constants.
When using the hexadecimal form, constants of types bfloat, half, float, and
double are represented using the 16-digit form shown above (which matches the
IEEE754 representation for double); bfloat, half and float values must, however,
be exactly representable as bfloat, IEEE 754 half, and IEEE 754 single
precision respectively. Hexadecimal format is always used for long double, and
there are three forms of long double. The 80-bit format used by x86 is
represented as ``0xK`` followed by 20 hexadecimal digits. The 128-bit format
used by PowerPC (two adjacent doubles) is represented by ``0xM`` followed by 32
hexadecimal digits. The IEEE 128-bit format is represented by ``0xL`` followed
by 32 hexadecimal digits. Long doubles will only work if they match the long
double format on your target. The IEEE 16-bit format (half precision) is
represented by ``0xH`` followed by 4 hexadecimal digits. The bfloat 16-bit
format is represented by ``0xR`` followed by 4 hexadecimal digits. All
hexadecimal formats are big-endian (sign bit at the left).
There are no constants of type x86_mmx and x86_amx.
.. _complexconstants:
Complex Constants
-----------------
Complex constants are a (potentially recursive) combination of simple
constants and smaller complex constants.
**Structure constants**
Structure constants are represented with notation similar to
structure type definitions (a comma separated list of elements,
surrounded by braces (``{}``)). For example:
"``{ i32 4, float 17.0, ptr @G }``", where "``@G``" is declared as
"``@G = external global i32``". Structure constants must have
:ref:`structure type <t_struct>`, and the number and types of elements
must match those specified by the type.
**Array constants**
Array constants are represented with notation similar to array type
definitions (a comma separated list of elements, surrounded by
square brackets (``[]``)). For example:
"``[ i32 42, i32 11, i32 74 ]``". Array constants must have
:ref:`array type <t_array>`, and the number and types of elements must
match those specified by the type. As a special case, character array
constants may also be represented as a double-quoted string using the ``c``
prefix. For example: "``c"Hello World\0A\00"``".
**Vector constants**
Vector constants are represented with notation similar to vector
type definitions (a comma separated list of elements, surrounded by
less-than/greater-than's (``<>``)). For example:
"``< i32 42, i32 11, i32 74, i32 100 >``". Vector constants
must have :ref:`vector type <t_vector>`, and the number and types of
elements must match those specified by the type.
When creating a vector whose elements have the same constant value, the
preferred syntax is ``splat (<Ty> Val)``. For example: "``splat (i32 11)``".
These vector constants must have ::ref:`vector type <t_vector>` with an
element type that matches the ``splat`` operand.
**Zero initialization**
The string '``zeroinitializer``' can be used to zero initialize a
value to zero of *any* type, including scalar and
:ref:`aggregate <t_aggregate>` types. This is often used to avoid
having to print large zero initializers (e.g. for large arrays) and
is always exactly equivalent to using explicit zero initializers.
**Metadata node**
A metadata node is a constant tuple without types. For example:
"``!{!0, !{!2, !0}, !"test"}``". Metadata can reference constant values,
for example: "``!{!0, i32 0, ptr @global, ptr @function, !"str"}``".
Unlike other typed constants that are meant to be interpreted as part of
the instruction stream, metadata is a place to attach additional
information such as debug info.
Global Variable and Function Addresses
--------------------------------------
The addresses of :ref:`global variables <globalvars>` and
:ref:`functions <functionstructure>` are always implicitly valid
(link-time) constants. These constants are explicitly referenced when
the :ref:`identifier for the global <identifiers>` is used and always have
:ref:`pointer <t_pointer>` type. For example, the following is a legal LLVM
file:
.. code-block:: llvm
@X = global i32 17
@Y = global i32 42
@Z = global [2 x ptr] [ ptr @X, ptr @Y ]
.. _undefvalues:
Undefined Values
----------------
The string '``undef``' can be used anywhere a constant is expected, and
indicates that the user of the value may receive an unspecified
bit-pattern. Undefined values may be of any type (other than '``label``'
or '``void``') and be used anywhere a constant is permitted.
.. note::
A '``poison``' value (described in the next section) should be used instead of
'``undef``' whenever possible. Poison values are stronger than undef, and
enable more optimizations. Just the existence of '``undef``' blocks certain
optimizations (see the examples below).
Undefined values are useful because they indicate to the compiler that
the program is well defined no matter what value is used. This gives the
compiler more freedom to optimize. Here are some examples of
(potentially surprising) transformations that are valid (in pseudo IR):
.. code-block:: llvm
%A = add %X, undef
%B = sub %X, undef
%C = xor %X, undef
Safe:
%A = undef
%B = undef
%C = undef
This is safe because all of the output bits are affected by the undef
bits. Any output bit can have a zero or one depending on the input bits.
.. code-block:: llvm
%A = or %X, undef
%B = and %X, undef
Safe:
%A = -1
%B = 0
Safe:
%A = %X ;; By choosing undef as 0
%B = %X ;; By choosing undef as -1
Unsafe:
%A = undef
%B = undef
These logical operations have bits that are not always affected by the
input. For example, if ``%X`` has a zero bit, then the output of the
'``and``' operation will always be a zero for that bit, no matter what
the corresponding bit from the '``undef``' is. As such, it is unsafe to
optimize or assume that the result of the '``and``' is '``undef``'.
However, it is safe to assume that all bits of the '``undef``' could be
0, and optimize the '``and``' to 0. Likewise, it is safe to assume that
all the bits of the '``undef``' operand to the '``or``' could be set,
allowing the '``or``' to be folded to -1.
.. code-block:: llvm
%A = select undef, %X, %Y
%B = select undef, 42, %Y
%C = select %X, %Y, undef
Safe:
%A = %X (or %Y)
%B = 42 (or %Y)
%C = %Y (if %Y is provably not poison; unsafe otherwise)
Unsafe:
%A = undef
%B = undef
%C = undef
This set of examples shows that undefined '``select``' (and conditional
branch) conditions can go *either way*, but they have to come from one
of the two operands. In the ``%A`` example, if ``%X`` and ``%Y`` were
both known to have a clear low bit, then ``%A`` would have to have a
cleared low bit. However, in the ``%C`` example, the optimizer is
allowed to assume that the '``undef``' operand could be the same as
``%Y`` if ``%Y`` is provably not '``poison``', allowing the whole '``select``'
to be eliminated. This is because '``poison``' is stronger than '``undef``'.
.. code-block:: llvm
%A = xor undef, undef
%B = undef
%C = xor %B, %B
%D = undef
%E = icmp slt %D, 4
%F = icmp gte %D, 4
Safe:
%A = undef
%B = undef
%C = undef
%D = undef
%E = undef
%F = undef
This example points out that two '``undef``' operands are not
necessarily the same. This can be surprising to people (and also matches
C semantics) where they assume that "``X^X``" is always zero, even if
``X`` is undefined. This isn't true for a number of reasons, but the
short answer is that an '``undef``' "variable" can arbitrarily change
its value over its "live range". This is true because the variable
doesn't actually *have a live range*. Instead, the value is logically
read from arbitrary registers that happen to be around when needed, so
the value is not necessarily consistent over time. In fact, ``%A`` and
``%C`` need to have the same semantics or the core LLVM "replace all
uses with" concept would not hold.
To ensure all uses of a given register observe the same value (even if
'``undef``'), the :ref:`freeze instruction <i_freeze>` can be used.
.. code-block:: llvm
%A = sdiv undef, %X
%B = sdiv %X, undef
Safe:
%A = 0
b: unreachable
These examples show the crucial difference between an *undefined value*
and *undefined behavior*. An undefined value (like '``undef``') is
allowed to have an arbitrary bit-pattern. This means that the ``%A``
operation can be constant folded to '``0``', because the '``undef``'
could be zero, and zero divided by any value is zero.
However, in the second example, we can make a more aggressive
assumption: because the ``undef`` is allowed to be an arbitrary value,
we are allowed to assume that it could be zero. Since a divide by zero
has *undefined behavior*, we are allowed to assume that the operation
does not execute at all. This allows us to delete the divide and all
code after it. Because the undefined operation "can't happen", the
optimizer can assume that it occurs in dead code.
.. code-block:: text
a: store undef -> %X
b: store %X -> undef
Safe:
a: <deleted> (if the stored value in %X is provably not poison)
b: unreachable
A store *of* an undefined value can be assumed to not have any effect;
we can assume that the value is overwritten with bits that happen to
match what was already there. This argument is only valid if the stored value
is provably not ``poison``. However, a store *to* an undefined
location could clobber arbitrary memory, therefore, it has undefined
behavior.
Branching on an undefined value is undefined behavior.
This explains optimizations that depend on branch conditions to construct
predicates, such as Correlated Value Propagation and Global Value Numbering.
In case of switch instruction, the branch condition should be frozen, otherwise
it is undefined behavior.
.. code-block:: llvm
Unsafe:
br undef, BB1, BB2 ; UB
%X = and i32 undef, 255
switch %X, label %ret [ .. ] ; UB
store undef, ptr %ptr
%X = load ptr %ptr ; %X is undef
switch i8 %X, label %ret [ .. ] ; UB
Safe:
%X = or i8 undef, 255 ; always 255
switch i8 %X, label %ret [ .. ] ; Well-defined
%X = freeze i1 undef
br %X, BB1, BB2 ; Well-defined (non-deterministic jump)
.. _poisonvalues:
Poison Values
-------------
A poison value is a result of an erroneous operation.
In order to facilitate speculative execution, many instructions do not
invoke immediate undefined behavior when provided with illegal operands,
and return a poison value instead.
The string '``poison``' can be used anywhere a constant is expected, and
operations such as :ref:`add <i_add>` with the ``nsw`` flag can produce
a poison value.
Most instructions return '``poison``' when one of their arguments is
'``poison``'. A notable exception is the :ref:`select instruction <i_select>`.
Propagation of poison can be stopped with the
:ref:`freeze instruction <i_freeze>`.
It is correct to replace a poison value with an
:ref:`undef value <undefvalues>` or any value of the type.
This means that immediate undefined behavior occurs if a poison value is
used as an instruction operand that has any values that trigger undefined
behavior. Notably this includes (but is not limited to):
- The pointer operand of a :ref:`load <i_load>`, :ref:`store <i_store>` or
any other pointer dereferencing instruction (independent of address
space).
- The divisor operand of a ``udiv``, ``sdiv``, ``urem`` or ``srem``
instruction.
- The condition operand of a :ref:`br <i_br>` instruction.
- The callee operand of a :ref:`call <i_call>` or :ref:`invoke <i_invoke>`
instruction.
- The parameter operand of a :ref:`call <i_call>` or :ref:`invoke <i_invoke>`
instruction, when the function or invoking call site has a ``noundef``
attribute in the corresponding position.
- The operand of a :ref:`ret <i_ret>` instruction if the function or invoking
call site has a `noundef` attribute in the return value position.
Here are some examples:
.. code-block:: llvm
entry:
%poison = sub nuw i32 0, 1 ; Results in a poison value.
%poison2 = sub i32 poison, 1 ; Also results in a poison value.
%still_poison = and i32 %poison, 0 ; 0, but also poison.
%poison_yet_again = getelementptr i32, ptr @h, i32 %still_poison
store i32 0, ptr %poison_yet_again ; Undefined behavior due to
; store to poison.
store i32 %poison, ptr @g ; Poison value stored to memory.
%poison3 = load i32, ptr @g ; Poison value loaded back from memory.
%poison4 = load i16, ptr @g ; Returns a poison value.
%poison5 = load i64, ptr @g ; Returns a poison value.
%cmp = icmp slt i32 %poison, 0 ; Returns a poison value.
br i1 %cmp, label %end, label %end ; undefined behavior
end:
.. _welldefinedvalues:
Well-Defined Values
-------------------
Given a program execution, a value is *well defined* if the value does not
have an undef bit and is not poison in the execution.
An aggregate value or vector is well defined if its elements are well defined.
The padding of an aggregate isn't considered, since it isn't visible
without storing it into memory and loading it with a different type.
A constant of a :ref:`single value <t_single_value>`, non-vector type is well
defined if it is neither '``undef``' constant nor '``poison``' constant.
The result of :ref:`freeze instruction <i_freeze>` is well defined regardless
of its operand.
.. _blockaddress:
Addresses of Basic Blocks
-------------------------
``blockaddress(@function, %block)``
The '``blockaddress``' constant computes the address of the specified
basic block in the specified function.
It always has an ``ptr addrspace(P)`` type, where ``P`` is the address space
of the function containing ``%block`` (usually ``addrspace(0)``).
Taking the address of the entry block is illegal.
This value only has defined behavior when used as an operand to the
':ref:`indirectbr <i_indirectbr>`' or for comparisons against null. Pointer
equality tests between labels addresses results in undefined behavior ---
though, again, comparison against null is ok, and no label is equal to the null
pointer. This may be passed around as an opaque pointer sized value as long as
the bits are not inspected. This allows ``ptrtoint`` and arithmetic to be
performed on these values so long as the original value is reconstituted before
the ``indirectbr`` instruction.
Finally, some targets may provide defined semantics when using the value
as the operand to an inline assembly, but that is target specific.
.. _dso_local_equivalent:
DSO Local Equivalent
--------------------
``dso_local_equivalent @func``
A '``dso_local_equivalent``' constant represents a function which is
functionally equivalent to a given function, but is always defined in the
current linkage unit. The resulting pointer has the same type as the underlying
function. The resulting pointer is permitted, but not required, to be different
from a pointer to the function, and it may have different values in different
translation units.
The target function may not have ``extern_weak`` linkage.
``dso_local_equivalent`` can be implemented as such:
- If the function has local linkage, hidden visibility, or is
``dso_local``, ``dso_local_equivalent`` can be implemented as simply a pointer
to the function.
- ``dso_local_equivalent`` can be implemented with a stub that tail-calls the
function. Many targets support relocations that resolve at link time to either
a function or a stub for it, depending on if the function is defined within the
linkage unit; LLVM will use this when available. (This is commonly called a
"PLT stub".) On other targets, the stub may need to be emitted explicitly.
This can be used wherever a ``dso_local`` instance of a function is needed without
needing to explicitly make the original function ``dso_local``. An instance where
this can be used is for static offset calculations between a function and some other
``dso_local`` symbol. This is especially useful for the Relative VTables C++ ABI,
where dynamic relocations for function pointers in VTables can be replaced with
static relocations for offsets between the VTable and virtual functions which
may not be ``dso_local``.
This is currently only supported for ELF binary formats.
.. _no_cfi:
No CFI
------
``no_cfi @func``
With `Control-Flow Integrity (CFI)
<https://clang.llvm.org/docs/ControlFlowIntegrity.html>`_, a '``no_cfi``'
constant represents a function reference that does not get replaced with a
reference to the CFI jump table in the ``LowerTypeTests`` pass. These constants
may be useful in low-level programs, such as operating system kernels, which
need to refer to the actual function body.
.. _constantexprs:
Constant Expressions
--------------------
Constant expressions are used to allow expressions involving other
constants to be used as constants. Constant expressions may be of any
:ref:`first class <t_firstclass>` type and may involve any LLVM operation
that does not have side effects (e.g. load and call are not supported).
The following is the syntax for constant expressions:
``trunc (CST to TYPE)``
Perform the :ref:`trunc operation <i_trunc>` on constants.
``ptrtoint (CST to TYPE)``
Perform the :ref:`ptrtoint operation <i_ptrtoint>` on constants.
``inttoptr (CST to TYPE)``
Perform the :ref:`inttoptr operation <i_inttoptr>` on constants.
This one is *really* dangerous!
``bitcast (CST to TYPE)``
Convert a constant, CST, to another TYPE.
The constraints of the operands are the same as those for the
:ref:`bitcast instruction <i_bitcast>`.
``addrspacecast (CST to TYPE)``
Convert a constant pointer or constant vector of pointer, CST, to another
TYPE in a different address space. The constraints of the operands are the
same as those for the :ref:`addrspacecast instruction <i_addrspacecast>`.
``getelementptr (TY, CSTPTR, IDX0, IDX1, ...)``, ``getelementptr inbounds (TY, CSTPTR, IDX0, IDX1, ...)``
Perform the :ref:`getelementptr operation <i_getelementptr>` on
constants. As with the :ref:`getelementptr <i_getelementptr>`
instruction, the index list may have one or more indexes, which are
required to make sense for the type of "pointer to TY". These indexes
may be implicitly sign-extended or truncated to match the index size
of CSTPTR's address space.
``icmp COND (VAL1, VAL2)``
Perform the :ref:`icmp operation <i_icmp>` on constants.
``fcmp COND (VAL1, VAL2)``
Perform the :ref:`fcmp operation <i_fcmp>` on constants.
``extractelement (VAL, IDX)``
Perform the :ref:`extractelement operation <i_extractelement>` on
constants.
``insertelement (VAL, ELT, IDX)``
Perform the :ref:`insertelement operation <i_insertelement>` on
constants.
``shufflevector (VEC1, VEC2, IDXMASK)``
Perform the :ref:`shufflevector operation <i_shufflevector>` on
constants.
``add (LHS, RHS)``
Perform an addition on constants.
``sub (LHS, RHS)``
Perform a subtraction on constants.
``mul (LHS, RHS)``
Perform a multiplication on constants.
``shl (LHS, RHS)``
Perform a left shift on constants.
``xor (LHS, RHS)``
Perform a bitwise xor on constants.
Other Values
============
.. _inlineasmexprs:
Inline Assembler Expressions
----------------------------
LLVM supports inline assembler expressions (as opposed to :ref:`Module-Level
Inline Assembly <moduleasm>`) through the use of a special value. This value
represents the inline assembler as a template string (containing the
instructions to emit), a list of operand constraints (stored as a string), a
flag that indicates whether or not the inline asm expression has side effects,
and a flag indicating whether the function containing the asm needs to align its
stack conservatively.
The template string supports argument substitution of the operands using "``$``"
followed by a number, to indicate substitution of the given register/memory
location, as specified by the constraint string. "``${NUM:MODIFIER}``" may also
be used, where ``MODIFIER`` is a target-specific annotation for how to print the
operand (See :ref:`inline-asm-modifiers`).
A literal "``$``" may be included by using "``$$``" in the template. To include
other special characters into the output, the usual "``\XX``" escapes may be
used, just as in other strings. Note that after template substitution, the
resulting assembly string is parsed by LLVM's integrated assembler unless it is
disabled -- even when emitting a ``.s`` file -- and thus must contain assembly
syntax known to LLVM.
LLVM also supports a few more substitutions useful for writing inline assembly:
- ``${:uid}``: Expands to a decimal integer unique to this inline assembly blob.
This substitution is useful when declaring a local label. Many standard
compiler optimizations, such as inlining, may duplicate an inline asm blob.
Adding a blob-unique identifier ensures that the two labels will not conflict
during assembly. This is used to implement `GCC's %= special format
string <https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html>`_.
- ``${:comment}``: Expands to the comment character of the current target's
assembly dialect. This is usually ``#``, but many targets use other strings,
such as ``;``, ``//``, or ``!``.
- ``${:private}``: Expands to the assembler private label prefix. Labels with
this prefix will not appear in the symbol table of the assembled object.
Typically the prefix is ``L``, but targets may use other strings. ``.L`` is
relatively popular.
LLVM's support for inline asm is modeled closely on the requirements of Clang's
GCC-compatible inline-asm support. Thus, the feature-set and the constraint and
modifier codes listed here are similar or identical to those in GCC's inline asm
support. However, to be clear, the syntax of the template and constraint strings
described here is *not* the same as the syntax accepted by GCC and Clang, and,
while most constraint letters are passed through as-is by Clang, some get
translated to other codes when converting from the C source to the LLVM
assembly.
An example inline assembler expression is:
.. code-block:: llvm
i32 (i32) asm "bswap $0", "=r,r"
Inline assembler expressions may **only** be used as the callee operand
of a :ref:`call <i_call>` or an :ref:`invoke <i_invoke>` instruction.
Thus, typically we have:
.. code-block:: llvm
%X = call i32 asm "bswap $0", "=r,r"(i32 %Y)
Inline asms with side effects not visible in the constraint list must be
marked as having side effects. This is done through the use of the
'``sideeffect``' keyword, like so:
.. code-block:: llvm
call void asm sideeffect "eieio", ""()
In some cases inline asms will contain code that will not work unless
the stack is aligned in some way, such as calls or SSE instructions on
x86, yet will not contain code that does that alignment within the asm.
The compiler should make conservative assumptions about what the asm
might contain and should generate its usual stack alignment code in the
prologue if the '``alignstack``' keyword is present:
.. code-block:: llvm
call void asm alignstack "eieio", ""()
Inline asms also support using non-standard assembly dialects. The
assumed dialect is ATT. When the '``inteldialect``' keyword is present,
the inline asm is using the Intel dialect. Currently, ATT and Intel are
the only supported dialects. An example is:
.. code-block:: llvm
call void asm inteldialect "eieio", ""()
In the case that the inline asm might unwind the stack,
the '``unwind``' keyword must be used, so that the compiler emits
unwinding information:
.. code-block:: llvm
call void asm unwind "call func", ""()
If the inline asm unwinds the stack and isn't marked with
the '``unwind``' keyword, the behavior is undefined.
If multiple keywords appear, the '``sideeffect``' keyword must come
first, the '``alignstack``' keyword second, the '``inteldialect``' keyword
third and the '``unwind``' keyword last.
Inline Asm Constraint String
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The constraint list is a comma-separated string, each element containing one or
more constraint codes.
For each element in the constraint list an appropriate register or memory
operand will be chosen, and it will be made available to assembly template
string expansion as ``$0`` for the first constraint in the list, ``$1`` for the
second, etc.
There are three different types of constraints, which are distinguished by a
prefix symbol in front of the constraint code: Output, Input, and Clobber. The
constraints must always be given in that order: outputs first, then inputs, then
clobbers. They cannot be intermingled.
There are also three different categories of constraint codes:
- Register constraint. This is either a register class, or a fixed physical
register. This kind of constraint will allocate a register, and if necessary,
bitcast the argument or result to the appropriate type.
- Memory constraint. This kind of constraint is for use with an instruction
taking a memory operand. Different constraints allow for different addressing
modes used by the target.
- Immediate value constraint. This kind of constraint is for an integer or other
immediate value which can be rendered directly into an instruction. The
various target-specific constraints allow the selection of a value in the
proper range for the instruction you wish to use it with.
Output constraints
""""""""""""""""""
Output constraints are specified by an "``=``" prefix (e.g. "``=r``"). This
indicates that the assembly will write to this operand, and the operand will
then be made available as a return value of the ``asm`` expression. Output
constraints do not consume an argument from the call instruction. (Except, see
below about indirect outputs).
Normally, it is expected that no output locations are written to by the assembly
expression until *all* of the inputs have been read. As such, LLVM may assign
the same register to an output and an input. If this is not safe (e.g. if the
assembly contains two instructions, where the first writes to one output, and
the second reads an input and writes to a second output), then the "``&``"
modifier must be used (e.g. "``=&r``") to specify that the output is an
"early-clobber" output. Marking an output as "early-clobber" ensures that LLVM
will not use the same register for any inputs (other than an input tied to this
output).
Input constraints
"""""""""""""""""
Input constraints do not have a prefix -- just the constraint codes. Each input
constraint will consume one argument from the call instruction. It is not
permitted for the asm to write to any input register or memory location (unless
that input is tied to an output). Note also that multiple inputs may all be
assigned to the same register, if LLVM can determine that they necessarily all
contain the same value.
Instead of providing a Constraint Code, input constraints may also "tie"
themselves to an output constraint, by providing an integer as the constraint
string. Tied inputs still consume an argument from the call instruction, and
take up a position in the asm template numbering as is usual -- they will simply
be constrained to always use the same register as the output they've been tied
to. For example, a constraint string of "``=r,0``" says to assign a register for
output, and use that register as an input as well (it being the 0'th
constraint).
It is permitted to tie an input to an "early-clobber" output. In that case, no
*other* input may share the same register as the input tied to the early-clobber
(even when the other input has the same value).
You may only tie an input to an output which has a register constraint, not a
memory constraint. Only a single input may be tied to an output.
There is also an "interesting" feature which deserves a bit of explanation: if a
register class constraint allocates a register which is too small for the value
type operand provided as input, the input value will be split into multiple
registers, and all of them passed to the inline asm.
However, this feature is often not as useful as you might think.
Firstly, the registers are *not* guaranteed to be consecutive. So, on those
architectures that have instructions which operate on multiple consecutive
instructions, this is not an appropriate way to support them. (e.g. the 32-bit
SparcV8 has a 64-bit load, which instruction takes a single 32-bit register. The
hardware then loads into both the named register, and the next register. This
feature of inline asm would not be useful to support that.)
A few of the targets provide a template string modifier allowing explicit access
to the second register of a two-register operand (e.g. MIPS ``L``, ``M``, and
``D``). On such an architecture, you can actually access the second allocated
register (yet, still, not any subsequent ones). But, in that case, you're still
probably better off simply splitting the value into two separate operands, for
clarity. (e.g. see the description of the ``A`` constraint on X86, which,
despite existing only for use with this feature, is not really a good idea to
use)
Indirect inputs and outputs
"""""""""""""""""""""""""""
Indirect output or input constraints can be specified by the "``*``" modifier
(which goes after the "``=``" in case of an output). This indicates that the asm
will write to or read from the contents of an *address* provided as an input
argument. (Note that in this way, indirect outputs act more like an *input* than
an output: just like an input, they consume an argument of the call expression,
rather than producing a return value. An indirect output constraint is an
"output" only in that the asm is expected to write to the contents of the input
memory location, instead of just read from it).
This is most typically used for memory constraint, e.g. "``=*m``", to pass the
address of a variable as a value.
It is also possible to use an indirect *register* constraint, but only on output
(e.g. "``=*r``"). This will cause LLVM to allocate a register for an output
value normally, and then, separately emit a store to the address provided as
input, after the provided inline asm. (It's not clear what value this
functionality provides, compared to writing the store explicitly after the asm
statement, and it can only produce worse code, since it bypasses many
optimization passes. I would recommend not using it.)
Call arguments for indirect constraints must have pointer type and must specify
the :ref:`elementtype <attr_elementtype>` attribute to indicate the pointer
element type.
Clobber constraints
"""""""""""""""""""
A clobber constraint is indicated by a "``~``" prefix. A clobber does not
consume an input operand, nor generate an output. Clobbers cannot use any of the
general constraint code letters -- they may use only explicit register
constraints, e.g. "``~{eax}``". The one exception is that a clobber string of
"``~{memory}``" indicates that the assembly writes to arbitrary undeclared
memory locations -- not only the memory pointed to by a declared indirect
output.
Note that clobbering named registers that are also present in output
constraints is not legal.
Label constraints
"""""""""""""""""
A label constraint is indicated by a "``!``" prefix and typically used in the
form ``"!i"``. Instead of consuming call arguments, label constraints consume
indirect destination labels of ``callbr`` instructions.
Label constraints can only be used in conjunction with ``callbr`` and the
number of label constraints must match the number of indirect destination
labels in the ``callbr`` instruction.
Constraint Codes
""""""""""""""""
After a potential prefix comes constraint code, or codes.
A Constraint Code is either a single letter (e.g. "``r``"), a "``^``" character
followed by two letters (e.g. "``^wc``"), or "``{``" register-name "``}``"
(e.g. "``{eax}``").
The one and two letter constraint codes are typically chosen to be the same as
GCC's constraint codes.
A single constraint may include one or more than constraint code in it, leaving
it up to LLVM to choose which one to use. This is included mainly for
compatibility with the translation of GCC inline asm coming from clang.
There are two ways to specify alternatives, and either or both may be used in an
inline asm constraint list:
1) Append the codes to each other, making a constraint code set. E.g. "``im``"
or "``{eax}m``". This means "choose any of the options in the set". The
choice of constraint is made independently for each constraint in the
constraint list.
2) Use "``|``" between constraint code sets, creating alternatives. Every
constraint in the constraint list must have the same number of alternative
sets. With this syntax, the same alternative in *all* of the items in the
constraint list will be chosen together.
Putting those together, you might have a two operand constraint string like
``"rm|r,ri|rm"``. This indicates that if operand 0 is ``r`` or ``m``, then
operand 1 may be one of ``r`` or ``i``. If operand 0 is ``r``, then operand 1
may be one of ``r`` or ``m``. But, operand 0 and 1 cannot both be of type m.
However, the use of either of the alternatives features is *NOT* recommended, as
LLVM is not able to make an intelligent choice about which one to use. (At the
point it currently needs to choose, not enough information is available to do so
in a smart way.) Thus, it simply tries to make a choice that's most likely to
compile, not one that will be optimal performance. (e.g., given "``rm``", it'll
always choose to use memory, not registers). And, if given multiple registers,
or multiple register classes, it will simply choose the first one. (In fact, it
doesn't currently even ensure explicitly specified physical registers are
unique, so specifying multiple physical registers as alternatives, like
``{r11}{r12},{r11}{r12}``, will assign r11 to both operands, not at all what was
intended.)
Supported Constraint Code List
""""""""""""""""""""""""""""""
The constraint codes are, in general, expected to behave the same way they do in
GCC. LLVM's support is often implemented on an 'as-needed' basis, to support C
inline asm code which was supported by GCC. A mismatch in behavior between LLVM
and GCC likely indicates a bug in LLVM.
Some constraint codes are typically supported by all targets:
- ``r``: A register in the target's general purpose register class.
- ``m``: A memory address operand. It is target-specific what addressing modes
are supported, typical examples are register, or register + register offset,
or register + immediate offset (of some target-specific size).
- ``p``: An address operand. Similar to ``m``, but used by "load address"
type instructions without touching memory.
- ``i``: An integer constant (of target-specific width). Allows either a simple
immediate, or a relocatable value.
- ``n``: An integer constant -- *not* including relocatable values.
- ``s``: An integer constant, but allowing *only* relocatable values.
- ``X``: Allows an operand of any kind, no constraint whatsoever. Typically
useful to pass a label for an asm branch or call.
.. FIXME: but that surely isn't actually okay to jump out of an asm
block without telling llvm about the control transfer???)
- ``{register-name}``: Requires exactly the named physical register.
Other constraints are target-specific:
AArch64:
- ``z``: An immediate integer 0. Outputs ``WZR`` or ``XZR``, as appropriate.
- ``I``: An immediate integer valid for an ``ADD`` or ``SUB`` instruction,
i.e. 0 to 4095 with optional shift by 12.
- ``J``: An immediate integer that, when negated, is valid for an ``ADD`` or
``SUB`` instruction, i.e. -1 to -4095 with optional left shift by 12.
- ``K``: An immediate integer that is valid for the 'bitmask immediate 32' of a
logical instruction like ``AND``, ``EOR``, or ``ORR`` with a 32-bit register.
- ``L``: An immediate integer that is valid for the 'bitmask immediate 64' of a
logical instruction like ``AND``, ``EOR``, or ``ORR`` with a 64-bit register.
- ``M``: An immediate integer for use with the ``MOV`` assembly alias on a
32-bit register. This is a superset of ``K``: in addition to the bitmask
immediate, also allows immediate integers which can be loaded with a single
``MOVZ`` or ``MOVL`` instruction.
- ``N``: An immediate integer for use with the ``MOV`` assembly alias on a
64-bit register. This is a superset of ``L``.
- ``Q``: Memory address operand must be in a single register (no
offsets). (However, LLVM currently does this for the ``m`` constraint as
well.)
- ``r``: A 32 or 64-bit integer register (W* or X*).
- ``Uci``: Like r, but restricted to registers 8 to 11 inclusive.
- ``Ucj``: Like r, but restricted to registers 12 to 15 inclusive.
- ``w``: A 32, 64, or 128-bit floating-point, SIMD or SVE vector register.
- ``x``: Like w, but restricted to registers 0 to 15 inclusive.
- ``y``: Like w, but restricted to SVE vector registers Z0 to Z7 inclusive.
- ``Uph``: One of the upper eight SVE predicate registers (P8 to P15)
- ``Upl``: One of the lower eight SVE predicate registers (P0 to P7)
- ``Upa``: Any of the SVE predicate registers (P0 to P15)
AMDGPU:
- ``r``: A 32 or 64-bit integer register.
- ``[0-9]v``: The 32-bit VGPR register, number 0-9.
- ``[0-9]s``: The 32-bit SGPR register, number 0-9.
- ``[0-9]a``: The 32-bit AGPR register, number 0-9.
- ``I``: An integer inline constant in the range from -16 to 64.
- ``J``: A 16-bit signed integer constant.
- ``A``: An integer or a floating-point inline constant.
- ``B``: A 32-bit signed integer constant.
- ``C``: A 32-bit unsigned integer constant or an integer inline constant in the range from -16 to 64.
- ``DA``: A 64-bit constant that can be split into two "A" constants.
- ``DB``: A 64-bit constant that can be split into two "B" constants.
All ARM modes:
- ``Q``, ``Um``, ``Un``, ``Uq``, ``Us``, ``Ut``, ``Uv``, ``Uy``: Memory address
operand. Treated the same as operand ``m``, at the moment.
- ``Te``: An even general-purpose 32-bit integer register: ``r0,r2,...,r12,r14``
- ``To``: An odd general-purpose 32-bit integer register: ``r1,r3,...,r11``
ARM and ARM's Thumb2 mode:
- ``j``: An immediate integer between 0 and 65535 (valid for ``MOVW``)
- ``I``: An immediate integer valid for a data-processing instruction.
- ``J``: An immediate integer between -4095 and 4095.
- ``K``: An immediate integer whose bitwise inverse is valid for a
data-processing instruction. (Can be used with template modifier "``B``" to
print the inverted value).
- ``L``: An immediate integer whose negation is valid for a data-processing
instruction. (Can be used with template modifier "``n``" to print the negated
value).
- ``M``: A power of two or an integer between 0 and 32.
- ``N``: Invalid immediate constraint.
- ``O``: Invalid immediate constraint.
- ``r``: A general-purpose 32-bit integer register (``r0-r15``).
- ``l``: In Thumb2 mode, low 32-bit GPR registers (``r0-r7``). In ARM mode, same
as ``r``.
- ``h``: In Thumb2 mode, a high 32-bit GPR register (``r8-r15``). In ARM mode,
invalid.
- ``w``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s31``, ``d0-d31``, or ``q0-q15``, respectively.
- ``t``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s31``, ``d0-d15``, or ``q0-q7``, respectively.
- ``x``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s15``, ``d0-d7``, or ``q0-q3``, respectively.
ARM's Thumb1 mode:
- ``I``: An immediate integer between 0 and 255.
- ``J``: An immediate integer between -255 and -1.
- ``K``: An immediate integer between 0 and 255, with optional left-shift by
some amount.
- ``L``: An immediate integer between -7 and 7.
- ``M``: An immediate integer which is a multiple of 4 between 0 and 1020.
- ``N``: An immediate integer between 0 and 31.
- ``O``: An immediate integer which is a multiple of 4 between -508 and 508.
- ``r``: A low 32-bit GPR register (``r0-r7``).
- ``l``: A low 32-bit GPR register (``r0-r7``).
- ``h``: A high GPR register (``r0-r7``).
- ``w``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s31``, ``d0-d31``, or ``q0-q15``, respectively.
- ``t``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s31``, ``d0-d15``, or ``q0-q7``, respectively.
- ``x``: A 32, 64, or 128-bit floating-point/SIMD register in the ranges
``s0-s15``, ``d0-d7``, or ``q0-q3``, respectively.
Hexagon:
- ``o``, ``v``: A memory address operand, treated the same as constraint ``m``,
at the moment.
- ``r``: A 32 or 64-bit register.
LoongArch:
- ``f``: A floating-point register (if available).
- ``k``: A memory operand whose address is formed by a base register and
(optionally scaled) index register.
- ``l``: A signed 16-bit constant.
- ``m``: A memory operand whose address is formed by a base register and
offset that is suitable for use in instructions with the same addressing
mode as st.w and ld.w.
- ``I``: A signed 12-bit constant (for arithmetic instructions).
- ``J``: An immediate integer zero.
- ``K``: An unsigned 12-bit constant (for logic instructions).
- ``ZB``: An address that is held in a general-purpose register. The offset
is zero.
- ``ZC``: A memory operand whose address is formed by a base register and
offset that is suitable for use in instructions with the same addressing
mode as ll.w and sc.w.
MSP430:
- ``r``: An 8 or 16-bit register.
MIPS:
- ``I``: An immediate signed 16-bit integer.
- ``J``: An immediate integer zero.
- ``K``: An immediate unsigned 16-bit integer.
- ``L``: An immediate 32-bit integer, where the lower 16 bits are 0.
- ``N``: An immediate integer between -65535 and -1.
- ``O``: An immediate signed 15-bit integer.
- ``P``: An immediate integer between 1 and 65535.
- ``m``: A memory address operand. In MIPS-SE mode, allows a base address
register plus 16-bit immediate offset. In MIPS mode, just a base register.
- ``R``: A memory address operand. In MIPS-SE mode, allows a base address
register plus a 9-bit signed offset. In MIPS mode, the same as constraint
``m``.
- ``ZC``: A memory address operand, suitable for use in a ``pref``, ``ll``, or
``sc`` instruction on the given subtarget (details vary).
- ``r``, ``d``, ``y``: A 32 or 64-bit GPR register.
- ``f``: A 32 or 64-bit FPU register (``F0-F31``), or a 128-bit MSA register
(``W0-W31``). In the case of MSA registers, it is recommended to use the ``w``
argument modifier for compatibility with GCC.
- ``c``: A 32-bit or 64-bit GPR register suitable for indirect jump (always
``25``).
- ``l``: The ``lo`` register, 32 or 64-bit.
- ``x``: Invalid.
NVPTX:
- ``b``: A 1-bit integer register.
- ``c`` or ``h``: A 16-bit integer register.
- ``r``: A 32-bit integer register.
- ``l`` or ``N``: A 64-bit integer register.
- ``f``: A 32-bit float register.
- ``d``: A 64-bit float register.
PowerPC:
- ``I``: An immediate signed 16-bit integer.
- ``J``: An immediate unsigned 16-bit integer, shifted left 16 bits.
- ``K``: An immediate unsigned 16-bit integer.
- ``L``: An immediate signed 16-bit integer, shifted left 16 bits.
- ``M``: An immediate integer greater than 31.
- ``N``: An immediate integer that is an exact power of 2.
- ``O``: The immediate integer constant 0.
- ``P``: An immediate integer constant whose negation is a signed 16-bit
constant.
- ``es``, ``o``, ``Q``, ``Z``, ``Zy``: A memory address operand, currently
treated the same as ``m``.
- ``r``: A 32 or 64-bit integer register.
- ``b``: A 32 or 64-bit integer register, excluding ``R0`` (that is:
``R1-R31``).
- ``f``: A 32 or 64-bit float register (``F0-F31``),
- ``v``: For ``4 x f32`` or ``4 x f64`` types, a 128-bit altivec vector
register (``V0-V31``).
- ``y``: Condition register (``CR0-CR7``).
- ``wc``: An individual CR bit in a CR register.
- ``wa``, ``wd``, ``wf``: Any 128-bit VSX vector register, from the full VSX
register set (overlapping both the floating-point and vector register files).
- ``ws``: A 32 or 64-bit floating-point register, from the full VSX register
set.
RISC-V:
- ``A``: An address operand (using a general-purpose register, without an
offset).
- ``I``: A 12-bit signed integer immediate operand.
- ``J``: A zero integer immediate operand.
- ``K``: A 5-bit unsigned integer immediate operand.
- ``f``: A 32- or 64-bit floating-point register (requires F or D extension).
- ``r``: A 32- or 64-bit general-purpose register (depending on the platform
``XLEN``).
- ``vr``: A vector register. (requires V extension).
- ``vm``: A vector register for masking operand. (requires V extension).
Sparc:
- ``I``: An immediate 13-bit signed integer.
- ``r``: A 32-bit integer register.
- ``f``: Any floating-point register on SparcV8, or a floating-point
register in the "low" half of the registers on SparcV9.
- ``e``: Any floating-point register. (Same as ``f`` on SparcV8.)
SystemZ:
- ``I``: An immediate unsigned 8-bit integer.
- ``J``: An immediate unsigned 12-bit integer.
- ``K``: An immediate signed 16-bit integer.
- ``L``: An immediate signed 20-bit integer.
- ``M``: An immediate integer 0x7fffffff.
- ``Q``: A memory address operand with a base address and a 12-bit immediate
unsigned displacement.
- ``R``: A memory address operand with a base address, a 12-bit immediate
unsigned displacement, and an index register.
- ``S``: A memory address operand with a base address and a 20-bit immediate
signed displacement.
- ``T``: A memory address operand with a base address, a 20-bit immediate
signed displacement, and an index register.
- ``r`` or ``d``: A 32, 64, or 128-bit integer register.
- ``a``: A 32, 64, or 128-bit integer address register (excludes R0, which in an
address context evaluates as zero).
- ``h``: A 32-bit value in the high part of a 64bit data register
(LLVM-specific)
- ``f``: A 32, 64, or 128-bit floating-point register.
X86:
- ``I``: An immediate integer between 0 and 31.
- ``J``: An immediate integer between 0 and 64.
- ``K``: An immediate signed 8-bit integer.
- ``L``: An immediate integer, 0xff or 0xffff or (in 64-bit mode only)
0xffffffff.
- ``M``: An immediate integer between 0 and 3.
- ``N``: An immediate unsigned 8-bit integer.
- ``O``: An immediate integer between 0 and 127.
- ``e``: An immediate 32-bit signed integer.
- ``Z``: An immediate 32-bit unsigned integer.
- ``q``: An 8, 16, 32, or 64-bit register which can be accessed as an 8-bit
``l`` integer register. On X86-32, this is the ``a``, ``b``, ``c``, and ``d``
registers, and on X86-64, it is all of the integer registers.
- ``Q``: An 8, 16, 32, or 64-bit register which can be accessed as an 8-bit
``h`` integer register. This is the ``a``, ``b``, ``c``, and ``d`` registers.
- ``r`` or ``l``: An 8, 16, 32, or 64-bit integer register.
- ``R``: An 8, 16, 32, or 64-bit "legacy" integer register -- one which has
existed since i386, and can be accessed without the REX prefix.
- ``f``: A 32, 64, or 80-bit '387 FPU stack pseudo-register.
- ``y``: A 64-bit MMX register, if MMX is enabled.
- ``v``: If SSE is enabled: a 32 or 64-bit scalar operand, or 128-bit vector
operand in a SSE register. If AVX is also enabled, can also be a 256-bit
vector operand in an AVX register. If AVX-512 is also enabled, can also be a
512-bit vector operand in an AVX512 register. Otherwise, an error.
- ``x``: The same as ``v``, except that when AVX-512 is enabled, the ``x`` code
only allocates into the first 16 AVX-512 registers, while the ``v`` code
allocates into any of the 32 AVX-512 registers.
- ``Y``: The same as ``x``, if *SSE2* is enabled, otherwise an error.
- ``A``: Special case: allocates EAX first, then EDX, for a single operand (in
32-bit mode, a 64-bit integer operand will get split into two registers). It
is not recommended to use this constraint, as in 64-bit mode, the 64-bit
operand will get allocated only to RAX -- if two 32-bit operands are needed,
you're better off splitting it yourself, before passing it to the asm
statement.
XCore:
- ``r``: A 32-bit integer register.
.. _inline-asm-modifiers:
Asm template argument modifiers
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
In the asm template string, modifiers can be used on the operand reference, like
"``${0:n}``".
The modifiers are, in general, expected to behave the same way they do in
GCC. LLVM's support is often implemented on an 'as-needed' basis, to support C
inline asm code which was supported by GCC. A mismatch in behavior between LLVM
and GCC likely indicates a bug in LLVM.
Target-independent:
- ``c``: Print an immediate integer constant unadorned, without
the target-specific immediate punctuation (e.g. no ``$`` prefix).
- ``n``: Negate and print immediate integer constant unadorned, without the
target-specific immediate punctuation (e.g. no ``$`` prefix).
- ``l``: Print as an unadorned label, without the target-specific label
punctuation (e.g. no ``$`` prefix).
AArch64:
- ``w``: Print a GPR register with a ``w*`` name instead of ``x*`` name. E.g.,
instead of ``x30``, print ``w30``.
- ``x``: Print a GPR register with a ``x*`` name. (this is the default, anyhow).
- ``b``, ``h``, ``s``, ``d``, ``q``: Print a floating-point/SIMD register with a
``b*``, ``h*``, ``s*``, ``d*``, or ``q*`` name, rather than the default of
``v*``.
AMDGPU:
- ``r``: No effect.
ARM:
- ``a``: Print an operand as an address (with ``[`` and ``]`` surrounding a
register).
- ``P``: No effect.
- ``q``: No effect.
- ``y``: Print a VFP single-precision register as an indexed double (e.g. print
as ``d4[1]`` instead of ``s9``)
- ``B``: Bitwise invert and print an immediate integer constant without ``#``
prefix.
- ``L``: Print the low 16-bits of an immediate integer constant.
- ``M``: Print as a register set suitable for ldm/stm. Also prints *all*
register operands subsequent to the specified one (!), so use carefully.
- ``Q``: Print the low-order register of a register-pair, or the low-order
register of a two-register operand.
- ``R``: Print the high-order register of a register-pair, or the high-order
register of a two-register operand.
- ``H``: Print the second register of a register-pair. (On a big-endian system,
``H`` is equivalent to ``Q``, and on little-endian system, ``H`` is equivalent
to ``R``.)
.. FIXME: H doesn't currently support printing the second register
of a two-register operand.
- ``e``: Print the low doubleword register of a NEON quad register.
- ``f``: Print the high doubleword register of a NEON quad register.
- ``m``: Print the base register of a memory operand without the ``[`` and ``]``
adornment.
Hexagon:
- ``L``: Print the second register of a two-register operand. Requires that it
has been allocated consecutively to the first.
.. FIXME: why is it restricted to consecutive ones? And there's
nothing that ensures that happens, is there?
- ``I``: Print the letter 'i' if the operand is an integer constant, otherwise
nothing. Used to print 'addi' vs 'add' instructions.
LoongArch:
- ``z``: Print $zero register if operand is zero, otherwise print it normally.
MSP430:
No additional modifiers.
MIPS:
- ``X``: Print an immediate integer as hexadecimal
- ``x``: Print the low 16 bits of an immediate integer as hexadecimal.
- ``d``: Print an immediate integer as decimal.
- ``m``: Subtract one and print an immediate integer as decimal.
- ``z``: Print $0 if an immediate zero, otherwise print normally.
- ``L``: Print the low-order register of a two-register operand, or prints the
address of the low-order word of a double-word memory operand.
.. FIXME: L seems to be missing memory operand support.
- ``M``: Print the high-order register of a two-register operand, or prints the
address of the high-order word of a double-word memory operand.
.. FIXME: M seems to be missing memory operand support.
- ``D``: Print the second register of a two-register operand, or prints the
second word of a double-word memory operand. (On a big-endian system, ``D`` is
equivalent to ``L``, and on little-endian system, ``D`` is equivalent to
``M``.)
- ``w``: No effect. Provided for compatibility with GCC which requires this
modifier in order to print MSA registers (``W0-W31``) with the ``f``
constraint.
NVPTX:
- ``r``: No effect.
PowerPC:
- ``L``: Print the second register of a two-register operand. Requires that it
has been allocated consecutively to the first.
.. FIXME: why is it restricted to consecutive ones? And there's
nothing that ensures that happens, is there?
- ``I``: Print the letter 'i' if the operand is an integer constant, otherwise
nothing. Used to print 'addi' vs 'add' instructions.
- ``y``: For a memory operand, prints formatter for a two-register X-form
instruction. (Currently always prints ``r0,OPERAND``).
- ``U``: Prints 'u' if the memory operand is an update form, and nothing
otherwise. (NOTE: LLVM does not support update form, so this will currently
always print nothing)
- ``X``: Prints 'x' if the memory operand is an indexed form. (NOTE: LLVM does
not support indexed form, so this will currently always print nothing)
RISC-V:
- ``i``: Print the letter 'i' if the operand is not a register, otherwise print
nothing. Used to print 'addi' vs 'add' instructions, etc.
- ``z``: Print the register ``zero`` if an immediate zero, otherwise print
normally.
Sparc:
- ``r``: No effect.
SystemZ:
SystemZ implements only ``n``, and does *not* support any of the other
target-independent modifiers.
X86:
- ``c``: Print an unadorned integer or symbol name. (The latter is
target-specific behavior for this typically target-independent modifier).
- ``A``: Print a register name with a '``*``' before it.
- ``b``: Print an 8-bit register name (e.g. ``al``); do nothing on a memory
operand.
- ``h``: Print the upper 8-bit register name (e.g. ``ah``); do nothing on a
memory operand.
- ``w``: Print the 16-bit register name (e.g. ``ax``); do nothing on a memory
operand.
- ``k``: Print the 32-bit register name (e.g. ``eax``); do nothing on a memory
operand.
- ``q``: Print the 64-bit register name (e.g. ``rax``), if 64-bit registers are
available, otherwise the 32-bit register name; do nothing on a memory operand.
- ``n``: Negate and print an unadorned integer, or, for operands other than an
immediate integer (e.g. a relocatable symbol expression), print a '-' before
the operand. (The behavior for relocatable symbol expressions is a
target-specific behavior for this typically target-independent modifier)
- ``H``: Print a memory reference with additional offset +8.
- ``P``: Print a memory reference used as the argument of a call instruction or
used with explicit base reg and index reg as its offset. So it can not use
additional regs to present the memory reference. (E.g. omit ``(rip)``, even
though it's PC-relative.)
XCore:
No additional modifiers.
Inline Asm Metadata
^^^^^^^^^^^^^^^^^^^
The call instructions that wrap inline asm nodes may have a
"``!srcloc``" MDNode attached to it that contains a list of constant
integers. If present, the code generator will use the integer as the
location cookie value when report errors through the ``LLVMContext``
error reporting mechanisms. This allows a front-end to correlate backend
errors that occur with inline asm back to the source code that produced
it. For example:
.. code-block:: llvm
call void asm sideeffect "something bad", ""(), !srcloc !42
...
!42 = !{ i32 1234567 }
It is up to the front-end to make sense of the magic numbers it places
in the IR. If the MDNode contains multiple constants, the code generator
will use the one that corresponds to the line of the asm that the error
occurs on.
.. _metadata:
Metadata
========
LLVM IR allows metadata to be attached to instructions and global objects in the
program that can convey extra information about the code to the optimizers and
code generator. One example application of metadata is source-level
debug information. There are two metadata primitives: strings and nodes.
Metadata does not have a type, and is not a value. If referenced from a
``call`` instruction, it uses the ``metadata`` type.
All metadata are identified in syntax by an exclamation point ('``!``').
.. _metadata-string:
Metadata Nodes and Metadata Strings
-----------------------------------
A metadata string is a string surrounded by double quotes. It can
contain any character by escaping non-printable characters with
"``\xx``" where "``xx``" is the two digit hex code. For example:
"``!"test\00"``".
Metadata nodes are represented with notation similar to structure
constants (a comma separated list of elements, surrounded by braces and
preceded by an exclamation point). Metadata nodes can have any values as
their operand. For example:
.. code-block:: llvm
!{ !"test\00", i32 10}
Metadata nodes that aren't uniqued use the ``distinct`` keyword. For example:
.. code-block:: text
!0 = distinct !{!"test\00", i32 10}
``distinct`` nodes are useful when nodes shouldn't be merged based on their
content. They can also occur when transformations cause uniquing collisions
when metadata operands change.
A :ref:`named metadata <namedmetadatastructure>` is a collection of
metadata nodes, which can be looked up in the module symbol table. For
example:
.. code-block:: llvm
!foo = !{!4, !3}
Metadata can be used as function arguments. Here the ``llvm.dbg.value``
intrinsic is using three metadata arguments:
.. code-block:: llvm
call void @llvm.dbg.value(metadata !24, metadata !25, metadata !26)
Metadata can be attached to an instruction. Here metadata ``!21`` is attached
to the ``add`` instruction using the ``!dbg`` identifier:
.. code-block:: llvm
%indvar.next = add i64 %indvar, 1, !dbg !21
Instructions may not have multiple metadata attachments with the same
identifier.
Metadata can also be attached to a function or a global variable. Here metadata
``!22`` is attached to the ``f1`` and ``f2`` functions, and the globals ``g1``
and ``g2`` using the ``!dbg`` identifier:
.. code-block:: llvm
declare !dbg !22 void @f1()
define void @f2() !dbg !22 {
ret void
}
@g1 = global i32 0, !dbg !22
@g2 = external global i32, !dbg !22
Unlike instructions, global objects (functions and global variables) may have
multiple metadata attachments with the same identifier.
A transformation is required to drop any metadata attachment that it
does not know or know it can't preserve. Currently there is an
exception for metadata attachment to globals for ``!func_sanitize``,
``!type``, ``!absolute_symbol`` and ``!associated`` which can't be
unconditionally dropped unless the global is itself deleted.
Metadata attached to a module using named metadata may not be dropped, with
the exception of debug metadata (named metadata with the name ``!llvm.dbg.*``).
More information about specific metadata nodes recognized by the
optimizers and code generator is found below.
.. _specialized-metadata:
Specialized Metadata Nodes
^^^^^^^^^^^^^^^^^^^^^^^^^^
Specialized metadata nodes are custom data structures in metadata (as opposed
to generic tuples). Their fields are labelled, and can be specified in any
order.
These aren't inherently debug info centric, but currently all the specialized
metadata nodes are related to debug info.
.. _DICompileUnit:
DICompileUnit
"""""""""""""
``DICompileUnit`` nodes represent a compile unit. The ``enums:``,
``retainedTypes:``, ``globals:``, ``imports:`` and ``macros:`` fields are tuples
containing the debug info to be emitted along with the compile unit, regardless
of code optimizations (some nodes are only emitted if there are references to
them from instructions). The ``debugInfoForProfiling:`` field is a boolean
indicating whether or not line-table discriminators are updated to provide
more-accurate debug info for profiling results.
.. code-block:: text
!0 = !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang",
isOptimized: true, flags: "-O2", runtimeVersion: 2,
splitDebugFilename: "abc.debug", emissionKind: FullDebug,
enums: !2, retainedTypes: !3, globals: !4, imports: !5,
macros: !6, dwoId: 0x0abcd)
Compile unit descriptors provide the root scope for objects declared in a
specific compilation unit. File descriptors are defined using this scope. These
descriptors are collected by a named metadata node ``!llvm.dbg.cu``. They keep
track of global variables, type information, and imported entities (declarations
and namespaces).
.. _DIFile:
DIFile
""""""
``DIFile`` nodes represent files. The ``filename:`` can include slashes.
.. code-block:: none
!0 = !DIFile(filename: "path/to/file", directory: "/path/to/dir",
checksumkind: CSK_MD5,
checksum: "000102030405060708090a0b0c0d0e0f")
Files are sometimes used in ``scope:`` fields, and are the only valid target
for ``file:`` fields.
The ``checksum:`` and ``checksumkind:`` fields are optional. If one of these
fields is present, then the other is required to be present as well. Valid
values for ``checksumkind:`` field are: {CSK_MD5, CSK_SHA1, CSK_SHA256}
.. _DIBasicType:
DIBasicType
"""""""""""
``DIBasicType`` nodes represent primitive types, such as ``int``, ``bool`` and
``float``. ``tag:`` defaults to ``DW_TAG_base_type``.
.. code-block:: text
!0 = !DIBasicType(name: "unsigned char", size: 8, align: 8,
encoding: DW_ATE_unsigned_char)
!1 = !DIBasicType(tag: DW_TAG_unspecified_type, name: "decltype(nullptr)")
The ``encoding:`` describes the details of the type. Usually it's one of the
following:
.. code-block:: text
DW_ATE_address = 1
DW_ATE_boolean = 2
DW_ATE_float = 4
DW_ATE_signed = 5
DW_ATE_signed_char = 6
DW_ATE_unsigned = 7
DW_ATE_unsigned_char = 8
.. _DISubroutineType:
DISubroutineType
""""""""""""""""
``DISubroutineType`` nodes represent subroutine types. Their ``types:`` field
refers to a tuple; the first operand is the return type, while the rest are the
types of the formal arguments in order. If the first operand is ``null``, that
represents a function with no return value (such as ``void foo() {}`` in C++).
.. code-block:: text
!0 = !BasicType(name: "int", size: 32, align: 32, DW_ATE_signed)
!1 = !BasicType(name: "char", size: 8, align: 8, DW_ATE_signed_char)
!2 = !DISubroutineType(types: !{null, !0, !1}) ; void (int, char)
.. _DIDerivedType:
DIDerivedType
"""""""""""""
``DIDerivedType`` nodes represent types derived from other types, such as
qualified types.
.. code-block:: text
!0 = !DIBasicType(name: "unsigned char", size: 8, align: 8,
encoding: DW_ATE_unsigned_char)
!1 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !0, size: 32,
align: 32)
The following ``tag:`` values are valid:
.. code-block:: text
DW_TAG_member = 13
DW_TAG_pointer_type = 15
DW_TAG_reference_type = 16
DW_TAG_typedef = 22
DW_TAG_inheritance = 28
DW_TAG_ptr_to_member_type = 31
DW_TAG_const_type = 38
DW_TAG_friend = 42
DW_TAG_volatile_type = 53
DW_TAG_restrict_type = 55
DW_TAG_atomic_type = 71
DW_TAG_immutable_type = 75
.. _DIDerivedTypeMember:
``DW_TAG_member`` is used to define a member of a :ref:`composite type
<DICompositeType>`. The type of the member is the ``baseType:``. The
``offset:`` is the member's bit offset. If the composite type has an ODR
``identifier:`` and does not set ``flags: DIFwdDecl``, then the member is
uniqued based only on its ``name:`` and ``scope:``.
``DW_TAG_inheritance`` and ``DW_TAG_friend`` are used in the ``elements:``
field of :ref:`composite types <DICompositeType>` to describe parents and
friends.
``DW_TAG_typedef`` is used to provide a name for the ``baseType:``.
``DW_TAG_pointer_type``, ``DW_TAG_reference_type``, ``DW_TAG_const_type``,
``DW_TAG_volatile_type``, ``DW_TAG_restrict_type``, ``DW_TAG_atomic_type`` and
``DW_TAG_immutable_type`` are used to qualify the ``baseType:``.
Note that the ``void *`` type is expressed as a type derived from NULL.
.. _DICompositeType:
DICompositeType
"""""""""""""""
``DICompositeType`` nodes represent types composed of other types, like
structures and unions. ``elements:`` points to a tuple of the composed types.
If the source language supports ODR, the ``identifier:`` field gives the unique
identifier used for type merging between modules. When specified,
:ref:`subprogram declarations <DISubprogramDeclaration>` and :ref:`member
derived types <DIDerivedTypeMember>` that reference the ODR-type in their
``scope:`` change uniquing rules.
For a given ``identifier:``, there should only be a single composite type that
does not have ``flags: DIFlagFwdDecl`` set. LLVM tools that link modules
together will unique such definitions at parse time via the ``identifier:``
field, even if the nodes are ``distinct``.
.. code-block:: text
!0 = !DIEnumerator(name: "SixKind", value: 7)
!1 = !DIEnumerator(name: "SevenKind", value: 7)
!2 = !DIEnumerator(name: "NegEightKind", value: -8)
!3 = !DICompositeType(tag: DW_TAG_enumeration_type, name: "Enum", file: !12,
line: 2, size: 32, align: 32, identifier: "_M4Enum",
elements: !{!0, !1, !2})
The following ``tag:`` values are valid:
.. code-block:: text
DW_TAG_array_type = 1
DW_TAG_class_type = 2
DW_TAG_enumeration_type = 4
DW_TAG_structure_type = 19
DW_TAG_union_type = 23
For ``DW_TAG_array_type``, the ``elements:`` should be :ref:`subrange
descriptors <DISubrange>`, each representing the range of subscripts at that
level of indexing. The ``DIFlagVector`` flag to ``flags:`` indicates that an
array type is a native packed vector. The optional ``dataLocation`` is a
DIExpression that describes how to get from an object's address to the actual
raw data, if they aren't equivalent. This is only supported for array types,
particularly to describe Fortran arrays, which have an array descriptor in
addition to the array data. Alternatively it can also be DIVariable which
has the address of the actual raw data. The Fortran language supports pointer
arrays which can be attached to actual arrays, this attachment between pointer
and pointee is called association. The optional ``associated`` is a
DIExpression that describes whether the pointer array is currently associated.
The optional ``allocated`` is a DIExpression that describes whether the
allocatable array is currently allocated. The optional ``rank`` is a
DIExpression that describes the rank (number of dimensions) of fortran assumed
rank array (rank is known at runtime).
For ``DW_TAG_enumeration_type``, the ``elements:`` should be :ref:`enumerator
descriptors <DIEnumerator>`, each representing the definition of an enumeration
value for the set. All enumeration type descriptors are collected in the
``enums:`` field of the :ref:`compile unit <DICompileUnit>`.
For ``DW_TAG_structure_type``, ``DW_TAG_class_type``, and
``DW_TAG_union_type``, the ``elements:`` should be :ref:`derived types
<DIDerivedType>` with ``tag: DW_TAG_member``, ``tag: DW_TAG_inheritance``, or
``tag: DW_TAG_friend``; or :ref:`subprograms <DISubprogram>` with
``isDefinition: false``.
.. _DISubrange:
DISubrange
""""""""""
``DISubrange`` nodes are the elements for ``DW_TAG_array_type`` variants of
:ref:`DICompositeType`.
- ``count: -1`` indicates an empty array.
- ``count: !10`` describes the count with a :ref:`DILocalVariable`.
- ``count: !12`` describes the count with a :ref:`DIGlobalVariable`.
.. code-block:: text
!0 = !DISubrange(count: 5, lowerBound: 0) ; array counting from 0
!1 = !DISubrange(count: 5, lowerBound: 1) ; array counting from 1
!2 = !DISubrange(count: -1) ; empty array.
; Scopes used in rest of example
!6 = !DIFile(filename: "vla.c", directory: "/path/to/file")
!7 = distinct !DICompileUnit(language: DW_LANG_C99, file: !6)
!8 = distinct !DISubprogram(name: "foo", scope: !7, file: !6, line: 5)
; Use of local variable as count value
!9 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
!10 = !DILocalVariable(name: "count", scope: !8, file: !6, line: 42, type: !9)
!11 = !DISubrange(count: !10, lowerBound: 0)
; Use of global variable as count value
!12 = !DIGlobalVariable(name: "count", scope: !8, file: !6, line: 22, type: !9)
!13 = !DISubrange(count: !12, lowerBound: 0)
.. _DIEnumerator:
DIEnumerator
""""""""""""
``DIEnumerator`` nodes are the elements for ``DW_TAG_enumeration_type``
variants of :ref:`DICompositeType`.
.. code-block:: text
!0 = !DIEnumerator(name: "SixKind", value: 7)
!1 = !DIEnumerator(name: "SevenKind", value: 7)
!2 = !DIEnumerator(name: "NegEightKind", value: -8)
DITemplateTypeParameter
"""""""""""""""""""""""
``DITemplateTypeParameter`` nodes represent type parameters to generic source
language constructs. They are used (optionally) in :ref:`DICompositeType` and
:ref:`DISubprogram` ``templateParams:`` fields.
.. code-block:: text
!0 = !DITemplateTypeParameter(name: "Ty", type: !1)
DITemplateValueParameter
""""""""""""""""""""""""
``DITemplateValueParameter`` nodes represent value parameters to generic source
language constructs. ``tag:`` defaults to ``DW_TAG_template_value_parameter``,
but if specified can also be set to ``DW_TAG_GNU_template_template_param`` or
``DW_TAG_GNU_template_param_pack``. They are used (optionally) in
:ref:`DICompositeType` and :ref:`DISubprogram` ``templateParams:`` fields.
.. code-block:: text
!0 = !DITemplateValueParameter(name: "Ty", type: !1, value: i32 7)
DINamespace
"""""""""""
``DINamespace`` nodes represent namespaces in the source language.
.. code-block:: text
!0 = !DINamespace(name: "myawesomeproject", scope: !1, file: !2, line: 7)
.. _DIGlobalVariable:
DIGlobalVariable
""""""""""""""""
``DIGlobalVariable`` nodes represent global variables in the source language.
.. code-block:: text
@foo = global i32, !dbg !0
!0 = !DIGlobalVariableExpression(var: !1, expr: !DIExpression())
!1 = !DIGlobalVariable(name: "foo", linkageName: "foo", scope: !2,
file: !3, line: 7, type: !4, isLocal: true,
isDefinition: false, declaration: !5)
DIGlobalVariableExpression
""""""""""""""""""""""""""
``DIGlobalVariableExpression`` nodes tie a :ref:`DIGlobalVariable` together
with a :ref:`DIExpression`.
.. code-block:: text
@lower = global i32, !dbg !0
@upper = global i32, !dbg !1
!0 = !DIGlobalVariableExpression(
var: !2,
expr: !DIExpression(DW_OP_LLVM_fragment, 0, 32)
)
!1 = !DIGlobalVariableExpression(
var: !2,
expr: !DIExpression(DW_OP_LLVM_fragment, 32, 32)
)
!2 = !DIGlobalVariable(name: "split64", linkageName: "split64", scope: !3,
file: !4, line: 8, type: !5, declaration: !6)
All global variable expressions should be referenced by the `globals:` field of
a :ref:`compile unit <DICompileUnit>`.
.. _DISubprogram:
DISubprogram
""""""""""""
``DISubprogram`` nodes represent functions from the source language. A distinct
``DISubprogram`` may be attached to a function definition using ``!dbg``
metadata. A unique ``DISubprogram`` may be attached to a function declaration
used for call site debug info. The ``retainedNodes:`` field is a list of
:ref:`variables <DILocalVariable>` and :ref:`labels <DILabel>` that must be
retained, even if their IR counterparts are optimized out of the IR. The
``type:`` field must point at an :ref:`DISubroutineType`.
.. _DISubprogramDeclaration:
When ``spFlags: DISPFlagDefinition`` is not present, subprograms describe a
declaration in the type tree as opposed to a definition of a function. In this
case, the ``declaration`` field must be empty. If the scope is a composite type
with an ODR ``identifier:`` and that does not set ``flags: DIFwdDecl``, then
the subprogram declaration is uniqued based only on its ``linkageName:`` and
``scope:``.
.. code-block:: text
define void @_Z3foov() !dbg !0 {
...
}
!0 = distinct !DISubprogram(name: "foo", linkageName: "_Zfoov", scope: !1,
file: !2, line: 7, type: !3,
spFlags: DISPFlagDefinition | DISPFlagLocalToUnit,
scopeLine: 8, containingType: !4,
virtuality: DW_VIRTUALITY_pure_virtual,
virtualIndex: 10, flags: DIFlagPrototyped,
isOptimized: true, unit: !5, templateParams: !6,
declaration: !7, retainedNodes: !8,
thrownTypes: !9)
.. _DILexicalBlock:
DILexicalBlock
""""""""""""""
``DILexicalBlock`` nodes describe nested blocks within a :ref:`subprogram
<DISubprogram>`. The line number and column numbers are used to distinguish
two lexical blocks at same depth. They are valid targets for ``scope:``
fields.
.. code-block:: text
!0 = distinct !DILexicalBlock(scope: !1, file: !2, line: 7, column: 35)
Usually lexical blocks are ``distinct`` to prevent node merging based on
operands.
.. _DILexicalBlockFile:
DILexicalBlockFile
""""""""""""""""""
``DILexicalBlockFile`` nodes are used to discriminate between sections of a
:ref:`lexical block <DILexicalBlock>`. The ``file:`` field can be changed to
indicate textual inclusion, or the ``discriminator:`` field can be used to
discriminate between control flow within a single block in the source language.
.. code-block:: text
!0 = !DILexicalBlock(scope: !3, file: !4, line: 7, column: 35)
!1 = !DILexicalBlockFile(scope: !0, file: !4, discriminator: 0)
!2 = !DILexicalBlockFile(scope: !0, file: !4, discriminator: 1)
.. _DILocation:
DILocation
""""""""""
``DILocation`` nodes represent source debug locations. The ``scope:`` field is
mandatory, and points at an :ref:`DILexicalBlockFile`, an
:ref:`DILexicalBlock`, or an :ref:`DISubprogram`.
.. code-block:: text
!0 = !DILocation(line: 2900, column: 42, scope: !1, inlinedAt: !2)
.. _DILocalVariable:
DILocalVariable
"""""""""""""""
``DILocalVariable`` nodes represent local variables in the source language. If
the ``arg:`` field is set to non-zero, then this variable is a subprogram
parameter, and it will be included in the ``retainedNodes:`` field of its
:ref:`DISubprogram`.
.. code-block:: text
!0 = !DILocalVariable(name: "this", arg: 1, scope: !3, file: !2, line: 7,
type: !3, flags: DIFlagArtificial)
!1 = !DILocalVariable(name: "x", arg: 2, scope: !4, file: !2, line: 7,
type: !3)
!2 = !DILocalVariable(name: "y", scope: !5, file: !2, line: 7, type: !3)
.. _DIExpression:
DIExpression
""""""""""""
``DIExpression`` nodes represent expressions that are inspired by the DWARF
expression language. They are used in :ref:`debug intrinsics<dbg_intrinsics>`
(such as ``llvm.dbg.declare`` and ``llvm.dbg.value``) to describe how the
referenced LLVM variable relates to the source language variable. Debug
intrinsics are interpreted left-to-right: start by pushing the value/address
operand of the intrinsic onto a stack, then repeatedly push and evaluate
opcodes from the DIExpression until the final variable description is produced.
The current supported opcode vocabulary is limited:
- ``DW_OP_deref`` dereferences the top of the expression stack.
- ``DW_OP_plus`` pops the last two entries from the expression stack, adds
them together and appends the result to the expression stack.
- ``DW_OP_minus`` pops the last two entries from the expression stack, subtracts
the last entry from the second last entry and appends the result to the
expression stack.
- ``DW_OP_plus_uconst, 93`` adds ``93`` to the working expression.
- ``DW_OP_LLVM_fragment, 16, 8`` specifies the offset and size (``16`` and ``8``
here, respectively) of the variable fragment from the working expression. Note
that contrary to DW_OP_bit_piece, the offset is describing the location
within the described source variable.
- ``DW_OP_LLVM_convert, 16, DW_ATE_signed`` specifies a bit size and encoding
(``16`` and ``DW_ATE_signed`` here, respectively) to which the top of the
expression stack is to be converted. Maps into a ``DW_OP_convert`` operation
that references a base type constructed from the supplied values.
- ``DW_OP_LLVM_tag_offset, tag_offset`` specifies that a memory tag should be
optionally applied to the pointer. The memory tag is derived from the
given tag offset in an implementation-defined manner.
- ``DW_OP_swap`` swaps top two stack entries.
- ``DW_OP_xderef`` provides extended dereference mechanism. The entry at the top
of the stack is treated as an address. The second stack entry is treated as an
address space identifier.
- ``DW_OP_stack_value`` marks a constant value.
- ``DW_OP_LLVM_entry_value, N`` refers to the value a register had upon
function entry. When targeting DWARF, a ``DBG_VALUE(reg, ...,
DIExpression(DW_OP_LLVM_entry_value, 1, ...)`` is lowered to
``DW_OP_entry_value [reg], ...``, which pushes the value ``reg`` had upon
function entry onto the DWARF expression stack.
The next ``(N - 1)`` operations will be part of the ``DW_OP_entry_value``
block argument. For example, ``!DIExpression(DW_OP_LLVM_entry_value, 1,
DW_OP_plus_uconst, 123, DW_OP_stack_value)`` specifies an expression where
the entry value of ``reg`` is pushed onto the stack, and is added with 123.
Due to framework limitations ``N`` must be 1, in other words,
``DW_OP_entry_value`` always refers to the value/address operand of the
instruction.
Because ``DW_OP_LLVM_entry_value`` is defined in terms of registers, it is
usually used in MIR, but it is also allowed in LLVM IR when targeting a
:ref:`swiftasync <swiftasync>` argument. The operation is introduced by:
- ``LiveDebugValues`` pass, which applies it to function parameters that
are unmodified throughout the function. Support is limited to simple
register location descriptions, or as indirect locations (e.g.,
parameters passed-by-value to a callee via a pointer to a temporary copy
made in the caller).
- ``AsmPrinter`` pass when a call site parameter value
(``DW_AT_call_site_parameter_value``) is represented as entry value of
the parameter.
- ``CoroSplit`` pass, which may move variables from allocas into a
coroutine frame. If the coroutine frame is a
:ref:`swiftasync <swiftasync>` argument, the variable is described with
an ``DW_OP_LLVM_entry_value`` operation.
- ``DW_OP_LLVM_arg, N`` is used in debug intrinsics that refer to more than one
value, such as one that calculates the sum of two registers. This is always
used in combination with an ordered list of values, such that
``DW_OP_LLVM_arg, N`` refers to the ``N``\ :sup:`th` element in that list. For
example, ``!DIExpression(DW_OP_LLVM_arg, 0, DW_OP_LLVM_arg, 1, DW_OP_minus,
DW_OP_stack_value)`` used with the list ``(%reg1, %reg2)`` would evaluate to
``%reg1 - reg2``. This list of values should be provided by the containing
intrinsic/instruction.
- ``DW_OP_breg`` (or ``DW_OP_bregx``) represents a content on the provided
signed offset of the specified register. The opcode is only generated by the
``AsmPrinter`` pass to describe call site parameter value which requires an
expression over two registers.
- ``DW_OP_push_object_address`` pushes the address of the object which can then
serve as a descriptor in subsequent calculation. This opcode can be used to
calculate bounds of fortran allocatable array which has array descriptors.
- ``DW_OP_over`` duplicates the entry currently second in the stack at the top
of the stack. This opcode can be used to calculate bounds of fortran assumed
rank array which has rank known at run time and current dimension number is
implicitly first element of the stack.
- ``DW_OP_LLVM_implicit_pointer`` It specifies the dereferenced value. It can
be used to represent pointer variables which are optimized out but the value
it points to is known. This operator is required as it is different than DWARF
operator DW_OP_implicit_pointer in representation and specification (number
and types of operands) and later can not be used as multiple level.
.. code-block:: text
IR for "*ptr = 4;"
--------------
call void @llvm.dbg.value(metadata i32 4, metadata !17, metadata !20)
!17 = !DILocalVariable(name: "ptr1", scope: !12, file: !3, line: 5,
type: !18)
!18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !19, size: 64)
!19 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
!20 = !DIExpression(DW_OP_LLVM_implicit_pointer))
IR for "**ptr = 4;"
--------------
call void @llvm.dbg.value(metadata i32 4, metadata !17, metadata !21)
!17 = !DILocalVariable(name: "ptr1", scope: !12, file: !3, line: 5,
type: !18)
!18 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !19, size: 64)
!19 = !DIDerivedType(tag: DW_TAG_pointer_type, baseType: !20, size: 64)
!20 = !DIBasicType(name: "int", size: 32, encoding: DW_ATE_signed)
!21 = !DIExpression(DW_OP_LLVM_implicit_pointer,
DW_OP_LLVM_implicit_pointer))
DWARF specifies three kinds of simple location descriptions: Register, memory,
and implicit location descriptions. Note that a location description is
defined over certain ranges of a program, i.e the location of a variable may
change over the course of the program. Register and memory location
descriptions describe the *concrete location* of a source variable (in the
sense that a debugger might modify its value), whereas *implicit locations*
describe merely the actual *value* of a source variable which might not exist
in registers or in memory (see ``DW_OP_stack_value``).
A ``llvm.dbg.declare`` intrinsic describes an indirect value (the address) of a
source variable. The first operand of the intrinsic must be an address of some
kind. A DIExpression attached to the intrinsic refines this address to produce a
concrete location for the source variable.
A ``llvm.dbg.value`` intrinsic describes the direct value of a source variable.
The first operand of the intrinsic may be a direct or indirect value. A
DIExpression attached to the intrinsic refines the first operand to produce a
direct value. For example, if the first operand is an indirect value, it may be
necessary to insert ``DW_OP_deref`` into the DIExpression in order to produce a
valid debug intrinsic.
.. note::
A DIExpression is interpreted in the same way regardless of which kind of
debug intrinsic it's attached to.
.. code-block:: text
!0 = !DIExpression(DW_OP_deref)
!1 = !DIExpression(DW_OP_plus_uconst, 3)
!1 = !DIExpression(DW_OP_constu, 3, DW_OP_plus)
!2 = !DIExpression(DW_OP_bit_piece, 3, 7)
!3 = !DIExpression(DW_OP_deref, DW_OP_constu, 3, DW_OP_plus, DW_OP_LLVM_fragment, 3, 7)
!4 = !DIExpression(DW_OP_constu, 2, DW_OP_swap, DW_OP_xderef)
!5 = !DIExpression(DW_OP_constu, 42, DW_OP_stack_value)
DIAssignID
""""""""""""
``DIAssignID`` nodes have no operands and are always distinct. They are used to
link together `@llvm.dbg.assign` intrinsics (:ref:`debug
intrinsics<dbg_intrinsics>`) and instructions that store in IR. See `Debug Info
Assignment Tracking <AssignmentTracking.html>`_ for more info.
.. code-block:: llvm
store i32 %a, ptr %a.addr, align 4, !DIAssignID !2
llvm.dbg.assign(metadata %a, metadata !1, metadata !DIExpression(), !2, metadata %a.addr, metadata !DIExpression()), !dbg !3
!2 = distinct !DIAssignID()
DIArgList
""""""""""""
``DIArgList`` nodes hold a list of constant or SSA value references. These are
used in :ref:`debug intrinsics<dbg_intrinsics>` (currently only in
``llvm.dbg.value``) in combination with a ``DIExpression`` that uses the
``DW_OP_LLVM_arg`` operator. Because a DIArgList may refer to local values
within a function, it must only be used as a function argument, must always be
inlined, and cannot appear in named metadata.
.. code-block:: text
llvm.dbg.value(metadata !DIArgList(i32 %a, i32 %b),
metadata !16,
metadata !DIExpression(DW_OP_LLVM_arg, 0, DW_OP_LLVM_arg, 1, DW_OP_plus))
DIFlags
"""""""""""""""
These flags encode various properties of DINodes.
The `ExportSymbols` flag marks a class, struct or union whose members
may be referenced as if they were defined in the containing class or
union. This flag is used to decide whether the DW_AT_export_symbols can
be used for the structure type.
DIObjCProperty
""""""""""""""
``DIObjCProperty`` nodes represent Objective-C property nodes.
.. code-block:: text
!3 = !DIObjCProperty(name: "foo", file: !1, line: 7, setter: "setFoo",
getter: "getFoo", attributes: 7, type: !2)
DIImportedEntity
""""""""""""""""
``DIImportedEntity`` nodes represent entities (such as modules) imported into a
compile unit. The ``elements`` field is a list of renamed entities (such as
variables and subprograms) in the imported entity (such as module).
.. code-block:: text
!2 = !DIImportedEntity(tag: DW_TAG_imported_module, name: "foo", scope: !0,
entity: !1, line: 7, elements: !3)
!3 = !{!4}
!4 = !DIImportedEntity(tag: DW_TAG_imported_declaration, name: "bar", scope: !0,
entity: !5, line: 7)
DIMacro
"""""""
``DIMacro`` nodes represent definition or undefinition of a macro identifiers.
The ``name:`` field is the macro identifier, followed by macro parameters when
defining a function-like macro, and the ``value`` field is the token-string
used to expand the macro identifier.
.. code-block:: text
!2 = !DIMacro(macinfo: DW_MACINFO_define, line: 7, name: "foo(x)",
value: "((x) + 1)")
!3 = !DIMacro(macinfo: DW_MACINFO_undef, line: 30, name: "foo")
DIMacroFile
"""""""""""
``DIMacroFile`` nodes represent inclusion of source files.
The ``nodes:`` field is a list of ``DIMacro`` and ``DIMacroFile`` nodes that
appear in the included source file.
.. code-block:: text
!2 = !DIMacroFile(macinfo: DW_MACINFO_start_file, line: 7, file: !2,
nodes: !3)
.. _DILabel:
DILabel
"""""""
``DILabel`` nodes represent labels within a :ref:`DISubprogram`. All fields of
a ``DILabel`` are mandatory. The ``scope:`` field must be one of either a
:ref:`DILexicalBlockFile`, a :ref:`DILexicalBlock`, or a :ref:`DISubprogram`.
The ``name:`` field is the label identifier. The ``file:`` field is the
:ref:`DIFile` the label is present in. The ``line:`` field is the source line
within the file where the label is declared.
.. code-block:: text
!2 = !DILabel(scope: !0, name: "foo", file: !1, line: 7)
'``tbaa``' Metadata
^^^^^^^^^^^^^^^^^^^
In LLVM IR, memory does not have types, so LLVM's own type system is not
suitable for doing type based alias analysis (TBAA). Instead, metadata is
added to the IR to describe a type system of a higher level language. This
can be used to implement C/C++ strict type aliasing rules, but it can also
be used to implement custom alias analysis behavior for other languages.
This description of LLVM's TBAA system is broken into two parts:
:ref:`Semantics<tbaa_node_semantics>` talks about high level issues, and
:ref:`Representation<tbaa_node_representation>` talks about the metadata
encoding of various entities.
It is always possible to trace any TBAA node to a "root" TBAA node (details
in the :ref:`Representation<tbaa_node_representation>` section). TBAA
nodes with different roots have an unknown aliasing relationship, and LLVM
conservatively infers ``MayAlias`` between them. The rules mentioned in
this section only pertain to TBAA nodes living under the same root.
.. _tbaa_node_semantics:
Semantics
"""""""""
The TBAA metadata system, referred to as "struct path TBAA" (not to be
confused with ``tbaa.struct``), consists of the following high level
concepts: *Type Descriptors*, further subdivided into scalar type
descriptors and struct type descriptors; and *Access Tags*.
**Type descriptors** describe the type system of the higher level language
being compiled. **Scalar type descriptors** describe types that do not
contain other types. Each scalar type has a parent type, which must also
be a scalar type or the TBAA root. Via this parent relation, scalar types
within a TBAA root form a tree. **Struct type descriptors** denote types
that contain a sequence of other type descriptors, at known offsets. These
contained type descriptors can either be struct type descriptors themselves
or scalar type descriptors.
**Access tags** are metadata nodes attached to load and store instructions.
Access tags use type descriptors to describe the *location* being accessed
in terms of the type system of the higher level language. Access tags are
tuples consisting of a base type, an access type and an offset. The base
type is a scalar type descriptor or a struct type descriptor, the access
type is a scalar type descriptor, and the offset is a constant integer.
The access tag ``(BaseTy, AccessTy, Offset)`` can describe one of two
things:
* If ``BaseTy`` is a struct type, the tag describes a memory access (load
or store) of a value of type ``AccessTy`` contained in the struct type
``BaseTy`` at offset ``Offset``.
* If ``BaseTy`` is a scalar type, ``Offset`` must be 0 and ``BaseTy`` and
``AccessTy`` must be the same; and the access tag describes a scalar
access with scalar type ``AccessTy``.
We first define an ``ImmediateParent`` relation on ``(BaseTy, Offset)``
tuples this way:
* If ``BaseTy`` is a scalar type then ``ImmediateParent(BaseTy, 0)`` is
``(ParentTy, 0)`` where ``ParentTy`` is the parent of the scalar type as
described in the TBAA metadata. ``ImmediateParent(BaseTy, Offset)`` is
undefined if ``Offset`` is non-zero.
* If ``BaseTy`` is a struct type then ``ImmediateParent(BaseTy, Offset)``
is ``(NewTy, NewOffset)`` where ``NewTy`` is the type contained in
``BaseTy`` at offset ``Offset`` and ``NewOffset`` is ``Offset`` adjusted
to be relative within that inner type.
A memory access with an access tag ``(BaseTy1, AccessTy1, Offset1)``
aliases a memory access with an access tag ``(BaseTy2, AccessTy2,
Offset2)`` if either ``(BaseTy1, Offset1)`` is reachable from ``(Base2,
Offset2)`` via the ``Parent`` relation or vice versa.
As a concrete example, the type descriptor graph for the following program
.. code-block:: c
struct Inner {
int i; // offset 0
float f; // offset 4
};
struct Outer {
float f; // offset 0
double d; // offset 4
struct Inner inner_a; // offset 12
};
void f(struct Outer* outer, struct Inner* inner, float* f, int* i, char* c) {
outer->f = 0; // tag0: (OuterStructTy, FloatScalarTy, 0)
outer->inner_a.i = 0; // tag1: (OuterStructTy, IntScalarTy, 12)
outer->inner_a.f = 0.0; // tag2: (OuterStructTy, FloatScalarTy, 16)
*f = 0.0; // tag3: (FloatScalarTy, FloatScalarTy, 0)
}
is (note that in C and C++, ``char`` can be used to access any arbitrary
type):
.. code-block:: text
Root = "TBAA Root"
CharScalarTy = ("char", Root, 0)
FloatScalarTy = ("float", CharScalarTy, 0)
DoubleScalarTy = ("double", CharScalarTy, 0)
IntScalarTy = ("int", CharScalarTy, 0)
InnerStructTy = {"Inner" (IntScalarTy, 0), (FloatScalarTy, 4)}
OuterStructTy = {"Outer", (FloatScalarTy, 0), (DoubleScalarTy, 4),
(InnerStructTy, 12)}
with (e.g.) ``ImmediateParent(OuterStructTy, 12)`` = ``(InnerStructTy,
0)``, ``ImmediateParent(InnerStructTy, 0)`` = ``(IntScalarTy, 0)``, and
``ImmediateParent(IntScalarTy, 0)`` = ``(CharScalarTy, 0)``.
.. _tbaa_node_representation:
Representation
""""""""""""""
The root node of a TBAA type hierarchy is an ``MDNode`` with 0 operands or
with exactly one ``MDString`` operand.
Scalar type descriptors are represented as an ``MDNode`` s with two
operands. The first operand is an ``MDString`` denoting the name of the
struct type. LLVM does not assign meaning to the value of this operand, it
only cares about it being an ``MDString``. The second operand is an
``MDNode`` which points to the parent for said scalar type descriptor,
which is either another scalar type descriptor or the TBAA root. Scalar
type descriptors can have an optional third argument, but that must be the
constant integer zero.
Struct type descriptors are represented as ``MDNode`` s with an odd number
of operands greater than 1. The first operand is an ``MDString`` denoting
the name of the struct type. Like in scalar type descriptors the actual
value of this name operand is irrelevant to LLVM. After the name operand,
the struct type descriptors have a sequence of alternating ``MDNode`` and
``ConstantInt`` operands. With N starting from 1, the 2N - 1 th operand,
an ``MDNode``, denotes a contained field, and the 2N th operand, a
``ConstantInt``, is the offset of the said contained field. The offsets
must be in non-decreasing order.
Access tags are represented as ``MDNode`` s with either 3 or 4 operands.
The first operand is an ``MDNode`` pointing to the node representing the
base type. The second operand is an ``MDNode`` pointing to the node
representing the access type. The third operand is a ``ConstantInt`` that
states the offset of the access. If a fourth field is present, it must be
a ``ConstantInt`` valued at 0 or 1. If it is 1 then the access tag states
that the location being accessed is "constant" (meaning
``pointsToConstantMemory`` should return true; see `other useful
AliasAnalysis methods <AliasAnalysis.html#OtherItfs>`_). The TBAA root of
the access type and the base type of an access tag must be the same, and
that is the TBAA root of the access tag.
'``tbaa.struct``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^
The :ref:`llvm.memcpy <int_memcpy>` is often used to implement
aggregate assignment operations in C and similar languages, however it
is defined to copy a contiguous region of memory, which is more than
strictly necessary for aggregate types which contain holes due to
padding. Also, it doesn't contain any TBAA information about the fields
of the aggregate.
``!tbaa.struct`` metadata can describe which memory subregions in a
memcpy are padding and what the TBAA tags of the struct are.
The current metadata format is very simple. ``!tbaa.struct`` metadata
nodes are a list of operands which are in conceptual groups of three.
For each group of three, the first operand gives the byte offset of a
field in bytes, the second gives its size in bytes, and the third gives
its tbaa tag. e.g.:
.. code-block:: llvm
!4 = !{ i64 0, i64 4, !1, i64 8, i64 4, !2 }
This describes a struct with two fields. The first is at offset 0 bytes
with size 4 bytes, and has tbaa tag !1. The second is at offset 8 bytes
and has size 4 bytes and has tbaa tag !2.
Note that the fields need not be contiguous. In this example, there is a
4 byte gap between the two fields. This gap represents padding which
does not carry useful data and need not be preserved.
'``noalias``' and '``alias.scope``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
``noalias`` and ``alias.scope`` metadata provide the ability to specify generic
noalias memory-access sets. This means that some collection of memory access
instructions (loads, stores, memory-accessing calls, etc.) that carry
``noalias`` metadata can specifically be specified not to alias with some other
collection of memory access instructions that carry ``alias.scope`` metadata.
Each type of metadata specifies a list of scopes where each scope has an id and
a domain.
When evaluating an aliasing query, if for some domain, the set
of scopes with that domain in one instruction's ``alias.scope`` list is a
subset of (or equal to) the set of scopes for that domain in another
instruction's ``noalias`` list, then the two memory accesses are assumed not to
alias.
Because scopes in one domain don't affect scopes in other domains, separate
domains can be used to compose multiple independent noalias sets. This is
used for example during inlining. As the noalias function parameters are
turned into noalias scope metadata, a new domain is used every time the
function is inlined.
The metadata identifying each domain is itself a list containing one or two
entries. The first entry is the name of the domain. Note that if the name is a
string then it can be combined across functions and translation units. A
self-reference can be used to create globally unique domain names. A
descriptive string may optionally be provided as a second list entry.
The metadata identifying each scope is also itself a list containing two or
three entries. The first entry is the name of the scope. Note that if the name
is a string then it can be combined across functions and translation units. A
self-reference can be used to create globally unique scope names. A metadata
reference to the scope's domain is the second entry. A descriptive string may
optionally be provided as a third list entry.
For example,
.. code-block:: llvm
; Two scope domains:
!0 = !{!0}
!1 = !{!1}
; Some scopes in these domains:
!2 = !{!2, !0}
!3 = !{!3, !0}
!4 = !{!4, !1}
; Some scope lists:
!5 = !{!4} ; A list containing only scope !4
!6 = !{!4, !3, !2}
!7 = !{!3}
; These two instructions don't alias:
%0 = load float, ptr %c, align 4, !alias.scope !5
store float %0, ptr %arrayidx.i, align 4, !noalias !5
; These two instructions also don't alias (for domain !1, the set of scopes
; in the !alias.scope equals that in the !noalias list):
%2 = load float, ptr %c, align 4, !alias.scope !5
store float %2, ptr %arrayidx.i2, align 4, !noalias !6
; These two instructions may alias (for domain !0, the set of scopes in
; the !noalias list is not a superset of, or equal to, the scopes in the
; !alias.scope list):
%2 = load float, ptr %c, align 4, !alias.scope !6
store float %0, ptr %arrayidx.i, align 4, !noalias !7
'``fpmath``' Metadata
^^^^^^^^^^^^^^^^^^^^^
``fpmath`` metadata may be attached to any instruction of floating-point
type. It can be used to express the maximum acceptable error in the
result of that instruction, in ULPs, thus potentially allowing the
compiler to use a more efficient but less accurate method of computing
it. ULP is defined as follows:
If ``x`` is a real number that lies between two finite consecutive
floating-point numbers ``a`` and ``b``, without being equal to one
of them, then ``ulp(x) = |b - a|``, otherwise ``ulp(x)`` is the
distance between the two non-equal finite floating-point numbers
nearest ``x``. Moreover, ``ulp(NaN)`` is ``NaN``.
The metadata node shall consist of a single positive float type number
representing the maximum relative error, for example:
.. code-block:: llvm
!0 = !{ float 2.5 } ; maximum acceptable inaccuracy is 2.5 ULPs
.. _range-metadata:
'``range``' Metadata
^^^^^^^^^^^^^^^^^^^^
``range`` metadata may be attached only to ``load``, ``call`` and ``invoke`` of
integer or vector of integer types. It expresses the possible ranges the loaded
value or the value returned by the called function at this call site is in. If
the loaded or returned value is not in the specified range, a poison value is
returned instead. The ranges are represented with a flattened list of integers.
The loaded value or the value returned is known to be in the union of the ranges
defined by each consecutive pair. Each pair has the following properties:
- The type must match the scalar type of the instruction.
- The pair ``a,b`` represents the range ``[a,b)``.
- Both ``a`` and ``b`` are constants.
- The range is allowed to wrap.
- The range should not represent the full or empty set. That is,
``a!=b``.
In addition, the pairs must be in signed order of the lower bound and
they must be non-contiguous.
For vector-typed instructions, the range is applied element-wise.
Examples:
.. code-block:: llvm
%a = load i8, ptr %x, align 1, !range !0 ; Can only be 0 or 1
%b = load i8, ptr %y, align 1, !range !1 ; Can only be 255 (-1), 0 or 1
%c = call i8 @foo(), !range !2 ; Can only be 0, 1, 3, 4 or 5
%d = invoke i8 @bar() to label %cont
unwind label %lpad, !range !3 ; Can only be -2, -1, 3, 4 or 5
%e = load <2 x i8>, ptr %x, !range 0 ; Can only be <0 or 1, 0 or 1>
...
!0 = !{ i8 0, i8 2 }
!1 = !{ i8 255, i8 2 }
!2 = !{ i8 0, i8 2, i8 3, i8 6 }
!3 = !{ i8 -2, i8 0, i8 3, i8 6 }
'``absolute_symbol``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
``absolute_symbol`` metadata may be attached to a global variable
declaration. It marks the declaration as a reference to an absolute symbol,
which causes the backend to use absolute relocations for the symbol even
in position independent code, and expresses the possible ranges that the
global variable's *address* (not its value) is in, in the same format as
``range`` metadata, with the extension that the pair ``all-ones,all-ones``
may be used to represent the full set.
Example (assuming 64-bit pointers):
.. code-block:: llvm
@a = external global i8, !absolute_symbol !0 ; Absolute symbol in range [0,256)
@b = external global i8, !absolute_symbol !1 ; Absolute symbol in range [0,2^64)
...
!0 = !{ i64 0, i64 256 }
!1 = !{ i64 -1, i64 -1 }
'``callees``' Metadata
^^^^^^^^^^^^^^^^^^^^^^
``callees`` metadata may be attached to indirect call sites. If ``callees``
metadata is attached to a call site, and any callee is not among the set of
functions provided by the metadata, the behavior is undefined. The intent of
this metadata is to facilitate optimizations such as indirect-call promotion.
For example, in the code below, the call instruction may only target the
``add`` or ``sub`` functions:
.. code-block:: llvm
%result = call i64 %binop(i64 %x, i64 %y), !callees !0
...
!0 = !{ptr @add, ptr @sub}
'``callback``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^
``callback`` metadata may be attached to a function declaration, or definition.
(Call sites are excluded only due to the lack of a use case.) For ease of
exposition, we'll refer to the function annotated w/ metadata as a broker
function. The metadata describes how the arguments of a call to the broker are
in turn passed to the callback function specified by the metadata. Thus, the
``callback`` metadata provides a partial description of a call site inside the
broker function with regards to the arguments of a call to the broker. The only
semantic restriction on the broker function itself is that it is not allowed to
inspect or modify arguments referenced in the ``callback`` metadata as
pass-through to the callback function.
The broker is not required to actually invoke the callback function at runtime.
However, the assumptions about not inspecting or modifying arguments that would
be passed to the specified callback function still hold, even if the callback
function is not dynamically invoked. The broker is allowed to invoke the
callback function more than once per invocation of the broker. The broker is
also allowed to invoke (directly or indirectly) the function passed as a
callback through another use. Finally, the broker is also allowed to relay the
callback callee invocation to a different thread.
The metadata is structured as follows: At the outer level, ``callback``
metadata is a list of ``callback`` encodings. Each encoding starts with a
constant ``i64`` which describes the argument position of the callback function
in the call to the broker. The following elements, except the last, describe
what arguments are passed to the callback function. Each element is again an
``i64`` constant identifying the argument of the broker that is passed through,
or ``i64 -1`` to indicate an unknown or inspected argument. The order in which
they are listed has to be the same in which they are passed to the callback
callee. The last element of the encoding is a boolean which specifies how
variadic arguments of the broker are handled. If it is true, all variadic
arguments of the broker are passed through to the callback function *after* the
arguments encoded explicitly before.
In the code below, the ``pthread_create`` function is marked as a broker
through the ``!callback !1`` metadata. In the example, there is only one
callback encoding, namely ``!2``, associated with the broker. This encoding
identifies the callback function as the second argument of the broker (``i64
2``) and the sole argument of the callback function as the third one of the
broker function (``i64 3``).
.. FIXME why does the llvm-sphinx-docs builder give a highlighting
error if the below is set to highlight as 'llvm', despite that we
have misc.highlighting_failure set?
.. code-block:: text
declare !callback !1 dso_local i32 @pthread_create(ptr, ptr, ptr, ptr)
...
!2 = !{i64 2, i64 3, i1 false}
!1 = !{!2}
Another example is shown below. The callback callee is the second argument of
the ``__kmpc_fork_call`` function (``i64 2``). The callee is given two unknown
values (each identified by a ``i64 -1``) and afterwards all
variadic arguments that are passed to the ``__kmpc_fork_call`` call (due to the
final ``i1 true``).
.. FIXME why does the llvm-sphinx-docs builder give a highlighting
error if the below is set to highlight as 'llvm', despite that we
have misc.highlighting_failure set?
.. code-block:: text
declare !callback !0 dso_local void @__kmpc_fork_call(ptr, i32, ptr, ...)
...
!1 = !{i64 2, i64 -1, i64 -1, i1 true}
!0 = !{!1}
'``exclude``' Metadata
^^^^^^^^^^^^^^^^^^^^^^
``exclude`` metadata may be attached to a global variable to signify that its
section should not be included in the final executable or shared library. This
option is only valid for global variables with an explicit section targeting ELF
or COFF. This is done using the ``SHF_EXCLUDE`` flag on ELF targets and the
``IMAGE_SCN_LNK_REMOVE`` and ``IMAGE_SCN_MEM_DISCARDABLE`` flags for COFF
targets. Additionally, this metadata is only used as a flag, so the associated
node must be empty. The explicit section should not conflict with any other
sections that the user does not want removed after linking.
.. code-block:: text
@object = private constant [1 x i8] c"\00", section ".foo" !exclude !0
...
!0 = !{}
'``unpredictable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
``unpredictable`` metadata may be attached to any branch or switch
instruction. It can be used to express the unpredictability of control
flow. Similar to the llvm.expect intrinsic, it may be used to alter
optimizations related to compare and branch instructions. The metadata
is treated as a boolean value; if it exists, it signals that the branch
or switch that it is attached to is completely unpredictable.
.. _md_dereferenceable:
'``dereferenceable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The existence of the ``!dereferenceable`` metadata on the instruction
tells the optimizer that the value loaded is known to be dereferenceable,
otherwise the behavior is undefined.
The number of bytes known to be dereferenceable is specified by the integer
value in the metadata node. This is analogous to the ''dereferenceable''
attribute on parameters and return values.
.. _md_dereferenceable_or_null:
'``dereferenceable_or_null``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The existence of the ``!dereferenceable_or_null`` metadata on the
instruction tells the optimizer that the value loaded is known to be either
dereferenceable or null, otherwise the behavior is undefined.
The number of bytes known to be dereferenceable is specified by the integer
value in the metadata node. This is analogous to the ''dereferenceable_or_null''
attribute on parameters and return values.
.. _llvm.loop:
'``llvm.loop``'
^^^^^^^^^^^^^^^
It is sometimes useful to attach information to loop constructs. Currently,
loop metadata is implemented as metadata attached to the branch instruction
in the loop latch block. The loop metadata node is a list of
other metadata nodes, each representing a property of the loop. Usually,
the first item of the property node is a string. For example, the
``llvm.loop.unroll.count`` suggests an unroll factor to the loop
unroller:
.. code-block:: llvm
br i1 %exitcond, label %._crit_edge, label %.lr.ph, !llvm.loop !0
...
!0 = !{!0, !1, !2}
!1 = !{!"llvm.loop.unroll.enable"}
!2 = !{!"llvm.loop.unroll.count", i32 4}
For legacy reasons, the first item of a loop metadata node must be a
reference to itself. Before the advent of the 'distinct' keyword, this
forced the preservation of otherwise identical metadata nodes. Since
the loop-metadata node can be attached to multiple nodes, the 'distinct'
keyword has become unnecessary.
Prior to the property nodes, one or two ``DILocation`` (debug location)
nodes can be present in the list. The first, if present, identifies the
source-code location where the loop begins. The second, if present,
identifies the source-code location where the loop ends.
Loop metadata nodes cannot be used as unique identifiers. They are
neither persistent for the same loop through transformations nor
necessarily unique to just one loop.
'``llvm.loop.disable_nonforced``'
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata disables all optional loop transformations unless
explicitly instructed using other transformation metadata such as
``llvm.loop.unroll.enable``. That is, no heuristic will try to determine
whether a transformation is profitable. The purpose is to avoid that the
loop is transformed to a different loop before an explicitly requested
(forced) transformation is applied. For instance, loop fusion can make
other transformations impossible. Mandatory loop canonicalizations such
as loop rotation are still applied.
It is recommended to use this metadata in addition to any llvm.loop.*
transformation directive. Also, any loop should have at most one
directive applied to it (and a sequence of transformations built using
followup-attributes). Otherwise, which transformation will be applied
depends on implementation details such as the pass pipeline order.
See :ref:`transformation-metadata` for details.
'``llvm.loop.vectorize``' and '``llvm.loop.interleave``'
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Metadata prefixed with ``llvm.loop.vectorize`` or ``llvm.loop.interleave`` are
used to control per-loop vectorization and interleaving parameters such as
vectorization width and interleave count. These metadata should be used in
conjunction with ``llvm.loop`` loop identification metadata. The
``llvm.loop.vectorize`` and ``llvm.loop.interleave`` metadata are only
optimization hints and the optimizer will only interleave and vectorize loops if
it believes it is safe to do so. The ``llvm.loop.parallel_accesses`` metadata
which contains information about loop-carried memory dependencies can be helpful
in determining the safety of these transformations.
'``llvm.loop.interleave.count``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests an interleave count to the loop interleaver.
The first operand is the string ``llvm.loop.interleave.count`` and the
second operand is an integer specifying the interleave count. For
example:
.. code-block:: llvm
!0 = !{!"llvm.loop.interleave.count", i32 4}
Note that setting ``llvm.loop.interleave.count`` to 1 disables interleaving
multiple iterations of the loop. If ``llvm.loop.interleave.count`` is set to 0
then the interleave count will be determined automatically.
'``llvm.loop.vectorize.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata selectively enables or disables vectorization for the loop. The
first operand is the string ``llvm.loop.vectorize.enable`` and the second operand
is a bit. If the bit operand value is 1 vectorization is enabled. A value of
0 disables vectorization:
.. code-block:: llvm
!0 = !{!"llvm.loop.vectorize.enable", i1 0}
!1 = !{!"llvm.loop.vectorize.enable", i1 1}
'``llvm.loop.vectorize.predicate.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata selectively enables or disables creating predicated instructions
for the loop, which can enable folding of the scalar epilogue loop into the
main loop. The first operand is the string
``llvm.loop.vectorize.predicate.enable`` and the second operand is a bit. If
the bit operand value is 1 vectorization is enabled. A value of 0 disables
vectorization:
.. code-block:: llvm
!0 = !{!"llvm.loop.vectorize.predicate.enable", i1 0}
!1 = !{!"llvm.loop.vectorize.predicate.enable", i1 1}
'``llvm.loop.vectorize.scalable.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata selectively enables or disables scalable vectorization for the
loop, and only has any effect if vectorization for the loop is already enabled.
The first operand is the string ``llvm.loop.vectorize.scalable.enable``
and the second operand is a bit. If the bit operand value is 1 scalable
vectorization is enabled, whereas a value of 0 reverts to the default fixed
width vectorization:
.. code-block:: llvm
!0 = !{!"llvm.loop.vectorize.scalable.enable", i1 0}
!1 = !{!"llvm.loop.vectorize.scalable.enable", i1 1}
'``llvm.loop.vectorize.width``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata sets the target width of the vectorizer. The first
operand is the string ``llvm.loop.vectorize.width`` and the second
operand is an integer specifying the width. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.vectorize.width", i32 4}
Note that setting ``llvm.loop.vectorize.width`` to 1 disables
vectorization of the loop. If ``llvm.loop.vectorize.width`` is set to
0 or if the loop does not have this metadata the width will be
determined automatically.
'``llvm.loop.vectorize.followup_vectorized``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the vectorized loop will
have. See :ref:`transformation-metadata` for details.
'``llvm.loop.vectorize.followup_epilogue``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the epilogue will have. The
epilogue is not vectorized and is executed when either the vectorized
loop is not known to preserve semantics (because e.g., it processes two
arrays that are found to alias by a runtime check) or for the last
iterations that do not fill a complete set of vector lanes. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.vectorize.followup_all``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Attributes in the metadata will be added to both the vectorized and
epilogue loop.
See :ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.unroll``'
^^^^^^^^^^^^^^^^^^^^^^
Metadata prefixed with ``llvm.loop.unroll`` are loop unrolling
optimization hints such as the unroll factor. ``llvm.loop.unroll``
metadata should be used in conjunction with ``llvm.loop`` loop
identification metadata. The ``llvm.loop.unroll`` metadata are only
optimization hints and the unrolling will only be performed if the
optimizer believes it is safe to do so.
'``llvm.loop.unroll.count``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests an unroll factor to the loop unroller. The
first operand is the string ``llvm.loop.unroll.count`` and the second
operand is a positive integer specifying the unroll factor. For
example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll.count", i32 4}
If the trip count of the loop is less than the unroll count the loop
will be partially unrolled.
'``llvm.loop.unroll.disable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata disables loop unrolling. The metadata has a single operand
which is the string ``llvm.loop.unroll.disable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll.disable"}
'``llvm.loop.unroll.runtime.disable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata disables runtime loop unrolling. The metadata has a single
operand which is the string ``llvm.loop.unroll.runtime.disable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll.runtime.disable"}
'``llvm.loop.unroll.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests that the loop should be fully unrolled if the trip count
is known at compile time and partially unrolled if the trip count is not known
at compile time. The metadata has a single operand which is the string
``llvm.loop.unroll.enable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll.enable"}
'``llvm.loop.unroll.full``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests that the loop should be unrolled fully. The
metadata has a single operand which is the string ``llvm.loop.unroll.full``.
For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll.full"}
'``llvm.loop.unroll.followup``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the unrolled loop will have.
See :ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.unroll.followup_remainder``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the remainder loop after
partial/runtime unrolling will have. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.unroll_and_jam``'
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata is treated very similarly to the ``llvm.loop.unroll`` metadata
above, but affect the unroll and jam pass. In addition any loop with
``llvm.loop.unroll`` metadata but no ``llvm.loop.unroll_and_jam`` metadata will
disable unroll and jam (so ``llvm.loop.unroll`` metadata will be left to the
unroller, plus ``llvm.loop.unroll.disable`` metadata will disable unroll and jam
too.)
The metadata for unroll and jam otherwise is the same as for ``unroll``.
``llvm.loop.unroll_and_jam.enable``, ``llvm.loop.unroll_and_jam.disable`` and
``llvm.loop.unroll_and_jam.count`` do the same as for unroll.
``llvm.loop.unroll_and_jam.full`` is not supported. Again these are only hints
and the normal safety checks will still be performed.
'``llvm.loop.unroll_and_jam.count``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests an unroll and jam factor to use, similarly to
``llvm.loop.unroll.count``. The first operand is the string
``llvm.loop.unroll_and_jam.count`` and the second operand is a positive integer
specifying the unroll factor. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll_and_jam.count", i32 4}
If the trip count of the loop is less than the unroll count the loop
will be partially unroll and jammed.
'``llvm.loop.unroll_and_jam.disable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata disables loop unroll and jamming. The metadata has a single
operand which is the string ``llvm.loop.unroll_and_jam.disable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll_and_jam.disable"}
'``llvm.loop.unroll_and_jam.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata suggests that the loop should be fully unroll and jammed if the
trip count is known at compile time and partially unrolled if the trip count is
not known at compile time. The metadata has a single operand which is the
string ``llvm.loop.unroll_and_jam.enable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.unroll_and_jam.enable"}
'``llvm.loop.unroll_and_jam.followup_outer``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the outer unrolled loop will
have. See :ref:`Transformation Metadata <transformation-metadata>` for
details.
'``llvm.loop.unroll_and_jam.followup_inner``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which loop attributes the inner jammed loop will
have. See :ref:`Transformation Metadata <transformation-metadata>` for
details.
'``llvm.loop.unroll_and_jam.followup_remainder_outer``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which attributes the epilogue of the outer loop
will have. This loop is usually unrolled, meaning there is no such
loop. This attribute will be ignored in this case. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.unroll_and_jam.followup_remainder_inner``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which attributes the inner loop of the epilogue
will have. The outer epilogue will usually be unrolled, meaning there
can be multiple inner remainder loops. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.unroll_and_jam.followup_all``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Attributes specified in the metadata is added to all
``llvm.loop.unroll_and_jam.*`` loops. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.licm_versioning.disable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata indicates that the loop should not be versioned for the purpose
of enabling loop-invariant code motion (LICM). The metadata has a single operand
which is the string ``llvm.loop.licm_versioning.disable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.loop.licm_versioning.disable"}
'``llvm.loop.distribute.enable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Loop distribution allows splitting a loop into multiple loops. Currently,
this is only performed if the entire loop cannot be vectorized due to unsafe
memory dependencies. The transformation will attempt to isolate the unsafe
dependencies into their own loop.
This metadata can be used to selectively enable or disable distribution of the
loop. The first operand is the string ``llvm.loop.distribute.enable`` and the
second operand is a bit. If the bit operand value is 1 distribution is
enabled. A value of 0 disables distribution:
.. code-block:: llvm
!0 = !{!"llvm.loop.distribute.enable", i1 0}
!1 = !{!"llvm.loop.distribute.enable", i1 1}
This metadata should be used in conjunction with ``llvm.loop`` loop
identification metadata.
'``llvm.loop.distribute.followup_coincident``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which attributes extracted loops with no cyclic
dependencies will have (i.e. can be vectorized). See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.distribute.followup_sequential``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata defines which attributes the isolated loops with unsafe
memory dependencies will have. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.distribute.followup_fallback``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If loop versioning is necessary, this metadata defined the attributes
the non-distributed fallback version will have. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.loop.distribute.followup_all``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The attributes in this metadata is added to all followup loops of the
loop distribution pass. See
:ref:`Transformation Metadata <transformation-metadata>` for details.
'``llvm.licm.disable``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This metadata indicates that loop-invariant code motion (LICM) should not be
performed on this loop. The metadata has a single operand which is the string
``llvm.licm.disable``. For example:
.. code-block:: llvm
!0 = !{!"llvm.licm.disable"}
Note that although it operates per loop it isn't given the llvm.loop prefix
as it is not affected by the ``llvm.loop.disable_nonforced`` metadata.
'``llvm.access.group``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
``llvm.access.group`` metadata can be attached to any instruction that
potentially accesses memory. It can point to a single distinct metadata
node, which we call access group. This node represents all memory access
instructions referring to it via ``llvm.access.group``. When an
instruction belongs to multiple access groups, it can also point to a
list of accesses groups, illustrated by the following example.
.. code-block:: llvm
%val = load i32, ptr %arrayidx, !llvm.access.group !0
...
!0 = !{!1, !2}
!1 = distinct !{}
!2 = distinct !{}
It is illegal for the list node to be empty since it might be confused
with an access group.
The access group metadata node must be 'distinct' to avoid collapsing
multiple access groups by content. An access group metadata node must
always be empty which can be used to distinguish an access group
metadata node from a list of access groups. Being empty avoids the
situation that the content must be updated which, because metadata is
immutable by design, would required finding and updating all references
to the access group node.
The access group can be used to refer to a memory access instruction
without pointing to it directly (which is not possible in global
metadata). Currently, the only metadata making use of it is
``llvm.loop.parallel_accesses``.
'``llvm.loop.parallel_accesses``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The ``llvm.loop.parallel_accesses`` metadata refers to one or more
access group metadata nodes (see ``llvm.access.group``). It denotes that
no loop-carried memory dependence exist between it and other instructions
in the loop with this metadata.
Let ``m1`` and ``m2`` be two instructions that both have the
``llvm.access.group`` metadata to the access group ``g1``, respectively
``g2`` (which might be identical). If a loop contains both access groups
in its ``llvm.loop.parallel_accesses`` metadata, then the compiler can
assume that there is no dependency between ``m1`` and ``m2`` carried by
this loop. Instructions that belong to multiple access groups are
considered having this property if at least one of the access groups
matches the ``llvm.loop.parallel_accesses`` list.
If all memory-accessing instructions in a loop have
``llvm.access.group`` metadata that each refer to one of the access
groups of a loop's ``llvm.loop.parallel_accesses`` metadata, then the
loop has no loop carried memory dependences and is considered to be a
parallel loop.
Note that if not all memory access instructions belong to an access
group referred to by ``llvm.loop.parallel_accesses``, then the loop must
not be considered trivially parallel. Additional
memory dependence analysis is required to make that determination. As a fail
safe mechanism, this causes loops that were originally parallel to be considered
sequential (if optimization passes that are unaware of the parallel semantics
insert new memory instructions into the loop body).
Example of a loop that is considered parallel due to its correct use of
both ``llvm.access.group`` and ``llvm.loop.parallel_accesses``
metadata types.
.. code-block:: llvm
for.body:
...
%val0 = load i32, ptr %arrayidx, !llvm.access.group !1
...
store i32 %val0, ptr %arrayidx1, !llvm.access.group !1
...
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end:
...
!0 = distinct !{!0, !{!"llvm.loop.parallel_accesses", !1}}
!1 = distinct !{}
It is also possible to have nested parallel loops:
.. code-block:: llvm
outer.for.body:
...
%val1 = load i32, ptr %arrayidx3, !llvm.access.group !4
...
br label %inner.for.body
inner.for.body:
...
%val0 = load i32, ptr %arrayidx1, !llvm.access.group !3
...
store i32 %val0, ptr %arrayidx2, !llvm.access.group !3
...
br i1 %exitcond, label %inner.for.end, label %inner.for.body, !llvm.loop !1
inner.for.end:
...
store i32 %val1, ptr %arrayidx4, !llvm.access.group !4
...
br i1 %exitcond, label %outer.for.end, label %outer.for.body, !llvm.loop !2
outer.for.end: ; preds = %for.body
...
!1 = distinct !{!1, !{!"llvm.loop.parallel_accesses", !3}} ; metadata for the inner loop
!2 = distinct !{!2, !{!"llvm.loop.parallel_accesses", !3, !4}} ; metadata for the outer loop
!3 = distinct !{} ; access group for instructions in the inner loop (which are implicitly contained in outer loop as well)
!4 = distinct !{} ; access group for instructions in the outer, but not the inner loop
.. _langref_llvm_loop_mustprogress:
'``llvm.loop.mustprogress``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The ``llvm.loop.mustprogress`` metadata indicates that this loop is required to
terminate, unwind, or interact with the environment in an observable way e.g.
via a volatile memory access, I/O, or other synchronization. If such a loop is
not found to interact with the environment in an observable way, the loop may
be removed. This corresponds to the ``mustprogress`` function attribute.
'``irr_loop``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^
``irr_loop`` metadata may be attached to the terminator instruction of a basic
block that's an irreducible loop header (note that an irreducible loop has more
than once header basic blocks.) If ``irr_loop`` metadata is attached to the
terminator instruction of a basic block that is not really an irreducible loop
header, the behavior is undefined. The intent of this metadata is to improve the
accuracy of the block frequency propagation. For example, in the code below, the
block ``header0`` may have a loop header weight (relative to the other headers of
the irreducible loop) of 100:
.. code-block:: llvm
header0:
...
br i1 %cmp, label %t1, label %t2, !irr_loop !0
...
!0 = !{"loop_header_weight", i64 100}
Irreducible loop header weights are typically based on profile data.
.. _md_invariant.group:
'``invariant.group``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The experimental ``invariant.group`` metadata may be attached to
``load``/``store`` instructions referencing a single metadata with no entries.
The existence of the ``invariant.group`` metadata on the instruction tells
the optimizer that every ``load`` and ``store`` to the same pointer operand
can be assumed to load or store the same
value (but see the ``llvm.launder.invariant.group`` intrinsic which affects
when two pointers are considered the same). Pointers returned by bitcast or
getelementptr with only zero indices are considered the same.
Examples:
.. code-block:: llvm
@unknownPtr = external global i8
...
%ptr = alloca i8
store i8 42, ptr %ptr, !invariant.group !0
call void @foo(ptr %ptr)
%a = load i8, ptr %ptr, !invariant.group !0 ; Can assume that value under %ptr didn't change
call void @foo(ptr %ptr)
%newPtr = call ptr @getPointer(ptr %ptr)
%c = load i8, ptr %newPtr, !invariant.group !0 ; Can't assume anything, because we only have information about %ptr
%unknownValue = load i8, ptr @unknownPtr
store i8 %unknownValue, ptr %ptr, !invariant.group !0 ; Can assume that %unknownValue == 42
call void @foo(ptr %ptr)
%newPtr2 = call ptr @llvm.launder.invariant.group.p0(ptr %ptr)
%d = load i8, ptr %newPtr2, !invariant.group !0 ; Can't step through launder.invariant.group to get value of %ptr
...
declare void @foo(ptr)
declare ptr @getPointer(ptr)
declare ptr @llvm.launder.invariant.group.p0(ptr)
!0 = !{}
The invariant.group metadata must be dropped when replacing one pointer by
another based on aliasing information. This is because invariant.group is tied
to the SSA value of the pointer operand.
.. code-block:: llvm
%v = load i8, ptr %x, !invariant.group !0
; if %x mustalias %y then we can replace the above instruction with
%v = load i8, ptr %y
Note that this is an experimental feature, which means that its semantics might
change in the future.
'``type``' Metadata
^^^^^^^^^^^^^^^^^^^
See :doc:`TypeMetadata`.
'``associated``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^
The ``associated`` metadata may be attached to a global variable definition with
a single argument that references a global object (optionally through an alias).
This metadata lowers to the ELF section flag ``SHF_LINK_ORDER`` which prevents
discarding of the global variable in linker GC unless the referenced object is
also discarded. The linker support for this feature is spotty. For best
compatibility, globals carrying this metadata should:
- Be in ``@llvm.compiler.used``.
- If the referenced global variable is in a comdat, be in the same comdat.
``!associated`` can not express many-to-one relationship. A global variable with
the metadata should generally not be referenced by a function: the function may
be inlined into other functions, leading to more references to the metadata.
Ideally we would want to keep metadata alive as long as any inline location is
alive, but this many-to-one relationship is not representable. Moreover, if the
metadata is retained while the function is discarded, the linker will report an
error of a relocation referencing a discarded section.
The metadata is often used with an explicit section consisting of valid C
identifiers so that the runtime can find the metadata section with
linker-defined encapsulation symbols ``__start_<section_name>`` and
``__stop_<section_name>``.
It does not have any effect on non-ELF targets.
Example:
.. code-block:: text
$a = comdat any
@a = global i32 1, comdat $a
@b = internal global i32 2, comdat $a, section "abc", !associated !0
!0 = !{ptr @a}
'``prof``' Metadata
^^^^^^^^^^^^^^^^^^^
The ``prof`` metadata is used to record profile data in the IR.
The first operand of the metadata node indicates the profile metadata
type. There are currently 3 types:
:ref:`branch_weights<prof_node_branch_weights>`,
:ref:`function_entry_count<prof_node_function_entry_count>`, and
:ref:`VP<prof_node_VP>`.
.. _prof_node_branch_weights:
branch_weights
""""""""""""""
Branch weight metadata attached to a branch, select, switch or call instruction
represents the likeliness of the associated branch being taken.
For more information, see :doc:`BranchWeightMetadata`.
.. _prof_node_function_entry_count:
function_entry_count
""""""""""""""""""""
Function entry count metadata can be attached to function definitions
to record the number of times the function is called. Used with BFI
information, it is also used to derive the basic block profile count.
For more information, see :doc:`BranchWeightMetadata`.
.. _prof_node_VP:
VP
""
VP (value profile) metadata can be attached to instructions that have
value profile information. Currently this is indirect calls (where it
records the hottest callees) and calls to memory intrinsics such as memcpy,
memmove, and memset (where it records the hottest byte lengths).
Each VP metadata node contains "VP" string, then a uint32_t value for the value
profiling kind, a uint64_t value for the total number of times the instruction
is executed, followed by uint64_t value and execution count pairs.
The value profiling kind is 0 for indirect call targets and 1 for memory
operations. For indirect call targets, each profile value is a hash
of the callee function name, and for memory operations each value is the
byte length.
Note that the value counts do not need to add up to the total count
listed in the third operand (in practice only the top hottest values
are tracked and reported).
Indirect call example:
.. code-block:: llvm
call void %f(), !prof !1
!1 = !{!"VP", i32 0, i64 1600, i64 7651369219802541373, i64 1030, i64 -4377547752858689819, i64 410}
Note that the VP type is 0 (the second operand), which indicates this is
an indirect call value profile data. The third operand indicates that the
indirect call executed 1600 times. The 4th and 6th operands give the
hashes of the 2 hottest target functions' names (this is the same hash used
to represent function names in the profile database), and the 5th and 7th
operands give the execution count that each of the respective prior target
functions was called.
.. _md_annotation:
'``annotation``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^
The ``annotation`` metadata can be used to attach a tuple of annotation strings
or a tuple of a tuple of annotation strings to any instruction. This metadata does
not impact the semantics of the program and may only be used to provide additional
insight about the program and transformations to users.
Example:
.. code-block:: text
%a.addr = alloca ptr, align 8, !annotation !0
!0 = !{!"auto-init"}
Embedding tuple of strings example:
.. code-block:: text
%a.ptr = getelementptr ptr, ptr %base, i64 0. !annotation !0
!0 = !{!1}
!1 = !{!"gep offset", !"0"}
'``func_sanitize``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
The ``func_sanitize`` metadata is used to attach two values for the function
sanitizer instrumentation. The first value is the ubsan function signature.
The second value is the address of the proxy variable which stores the address
of the RTTI descriptor. If :ref:`prologue <prologuedata>` and '``func_sanitize``'
are used at the same time, :ref:`prologue <prologuedata>` is emitted before
'``func_sanitize``' in the output.
Example:
.. code-block:: text
@__llvm_rtti_proxy = private unnamed_addr constant ptr @_ZTIFvvE
define void @_Z3funv() !func_sanitize !0 {
return void
}
!0 = !{i32 846595819, ptr @__llvm_rtti_proxy}
.. _md_kcfi_type:
'``kcfi_type``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^
The ``kcfi_type`` metadata can be used to attach a type identifier to
functions that can be called indirectly. The type data is emitted before the
function entry in the assembly. Indirect calls with the :ref:`kcfi operand
bundle<ob_kcfi>` will emit a check that compares the type identifier to the
metadata.
Example:
.. code-block:: text
define dso_local i32 @f() !kcfi_type !0 {
ret i32 0
}
!0 = !{i32 12345678}
Clang emits ``kcfi_type`` metadata nodes for address-taken functions with
``-fsanitize=kcfi``.
.. _md_memprof:
'``memprof``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^
The ``memprof`` metadata is used to record memory profile data on heap
allocation calls. Multiple context-sensitive profiles can be represented
with a single ``memprof`` metadata attachment.
Example:
.. code-block:: text
%call = call ptr @_Znam(i64 10), !memprof !0, !callsite !5
!0 = !{!1, !3}
!1 = !{!2, !"cold"}
!2 = !{i64 4854880825882961848, i64 1905834578520680781}
!3 = !{!4, !"notcold"}
!4 = !{i64 4854880825882961848, i64 -6528110295079665978}
!5 = !{i64 4854880825882961848}
Each operand in the ``memprof`` metadata attachment describes the profiled
behavior of memory allocated by the associated allocation for a given context.
In the above example, there were 2 profiled contexts, one allocating memory
that was typically cold and one allocating memory that was typically not cold.
The format of the metadata describing a context specific profile (e.g.
``!1`` and ``!3`` above) requires a first operand that is a metadata node
describing the context, followed by a list of string metadata tags describing
the profile behavior (e.g. ``cold`` and ``notcold``) above. The metadata nodes
describing the context (e.g. ``!2`` and ``!4`` above) are unique ids
corresponding to callsites, which can be matched to associated IR calls via
:ref:`callsite metadata<md_callsite>`. In practice these ids are formed via
a hash of the callsite's debug info, and the associated call may be in a
different module. The contexts are listed in order from leaf-most call (the
allocation itself) to the outermost callsite context required for uniquely
identifying the described profile behavior (note this may not be the top of
the profiled call stack).
.. _md_callsite:
'``callsite``' Metadata
^^^^^^^^^^^^^^^^^^^^^^^^
The ``callsite`` metadata is used to identify callsites involved in memory
profile contexts described in :ref:`memprof metadata<md_memprof>`.
It is attached both to the profile allocation calls (see the example in
:ref:`memprof metadata<md_memprof>`), as well as to other callsites
in profiled contexts described in heap allocation ``memprof`` metadata.
Example:
.. code-block:: text
%call = call ptr @_Z1Bb(void), !callsite !0
!0 = !{i64 -6528110295079665978, i64 5462047985461644151}
Each operand in the ``callsite`` metadata attachment is a unique id
corresponding to a callsite (possibly inlined). In practice these ids are
formed via a hash of the callsite's debug info. If the call was not inlined
into any callers it will contain a single operand (id). If it was inlined
it will contain a list of ids, including the ids of the callsites in the
full inline sequence, in order from the leaf-most call's id to the outermost
inlined call.
Module Flags Metadata
=====================
Information about the module as a whole is difficult to convey to LLVM's
subsystems. The LLVM IR isn't sufficient to transmit this information.
The ``llvm.module.flags`` named metadata exists in order to facilitate
this. These flags are in the form of key / value pairs --- much like a
dictionary --- making it easy for any subsystem who cares about a flag to
look it up.
The ``llvm.module.flags`` metadata contains a list of metadata triplets.
Each triplet has the following form:
- The first element is a *behavior* flag, which specifies the behavior
when two (or more) modules are merged together, and it encounters two
(or more) metadata with the same ID. The supported behaviors are
described below.
- The second element is a metadata string that is a unique ID for the
metadata. Each module may only have one flag entry for each unique ID (not
including entries with the **Require** behavior).
- The third element is the value of the flag.
When two (or more) modules are merged together, the resulting
``llvm.module.flags`` metadata is the union of the modules' flags. That is, for
each unique metadata ID string, there will be exactly one entry in the merged
modules ``llvm.module.flags`` metadata table, and the value for that entry will
be determined by the merge behavior flag, as described below. The only exception
is that entries with the *Require* behavior are always preserved.
The following behaviors are supported:
.. list-table::
:header-rows: 1
:widths: 10 90
* - Value
- Behavior
* - 1
- **Error**
Emits an error if two values disagree, otherwise the resulting value
is that of the operands.
* - 2
- **Warning**
Emits a warning if two values disagree. The result value will be the
operand for the flag from the first module being linked, unless the
other module uses **Min** or **Max**, in which case the result will
be **Min** (with the min value) or **Max** (with the max value),
respectively.
* - 3
- **Require**
Adds a requirement that another module flag be present and have a
specified value after linking is performed. The value must be a
metadata pair, where the first element of the pair is the ID of the
module flag to be restricted, and the second element of the pair is
the value the module flag should be restricted to. This behavior can
be used to restrict the allowable results (via triggering of an
error) of linking IDs with the **Override** behavior.
* - 4
- **Override**
Uses the specified value, regardless of the behavior or value of the
other module. If both modules specify **Override**, but the values
differ, an error will be emitted.
* - 5
- **Append**
Appends the two values, which are required to be metadata nodes.
* - 6
- **AppendUnique**
Appends the two values, which are required to be metadata
nodes. However, duplicate entries in the second list are dropped
during the append operation.
* - 7
- **Max**
Takes the max of the two values, which are required to be integers.
* - 8
- **Min**
Takes the min of the two values, which are required to be non-negative integers.
An absent module flag is treated as having the value 0.
It is an error for a particular unique flag ID to have multiple behaviors,
except in the case of **Require** (which adds restrictions on another metadata
value) or **Override**.
An example of module flags:
.. code-block:: llvm
!0 = !{ i32 1, !"foo", i32 1 }
!1 = !{ i32 4, !"bar", i32 37 }
!2 = !{ i32 2, !"qux", i32 42 }
!3 = !{ i32 3, !"qux",
!{
!"foo", i32 1
}
}
!llvm.module.flags = !{ !0, !1, !2, !3 }
- Metadata ``!0`` has the ID ``!"foo"`` and the value '1'. The behavior
if two or more ``!"foo"`` flags are seen is to emit an error if their
values are not equal.
- Metadata ``!1`` has the ID ``!"bar"`` and the value '37'. The
behavior if two or more ``!"bar"`` flags are seen is to use the value
'37'.
- Metadata ``!2`` has the ID ``!"qux"`` and the value '42'. The
behavior if two or more ``!"qux"`` flags are seen is to emit a
warning if their values are not equal.
- Metadata ``!3`` has the ID ``!"qux"`` and the value:
::
!{ !"foo", i32 1 }
The behavior is to emit an error if the ``llvm.module.flags`` does not
contain a flag with the ID ``!"foo"`` that has the value '1' after linking is
performed.
Synthesized Functions Module Flags Metadata
-------------------------------------------
These metadata specify the default attributes synthesized functions should have.
These metadata are currently respected by a few instrumentation passes, such as
sanitizers.
These metadata correspond to a few function attributes with significant code
generation behaviors. Function attributes with just optimization purposes
should not be listed because the performance impact of these synthesized
functions is small.
- "frame-pointer": **Max**. The value can be 0, 1, or 2. A synthesized function
will get the "frame-pointer" function attribute, with value being "none",
"non-leaf", or "all", respectively.
- "function_return_thunk_extern": The synthesized function will get the
``fn_return_thunk_extern`` function attribute.
- "uwtable": **Max**. The value can be 0, 1, or 2. If the value is 1, a synthesized
function will get the ``uwtable(sync)`` function attribute, if the value is 2,
a synthesized function will get the ``uwtable(async)`` function attribute.
Objective-C Garbage Collection Module Flags Metadata
----------------------------------------------------
On the Mach-O platform, Objective-C stores metadata about garbage
collection in a special section called "image info". The metadata
consists of a version number and a bitmask specifying what types of
garbage collection are supported (if any) by the file. If two or more
modules are linked together their garbage collection metadata needs to
be merged rather than appended together.
The Objective-C garbage collection module flags metadata consists of the
following key-value pairs:
.. list-table::
:header-rows: 1
:widths: 30 70
* - Key
- Value
* - ``Objective-C Version``
- **[Required]** --- The Objective-C ABI version. Valid values are 1 and 2.
* - ``Objective-C Image Info Version``
- **[Required]** --- The version of the image info section. Currently
always 0.
* - ``Objective-C Image Info Section``
- **[Required]** --- The section to place the metadata. Valid values are
``"__OBJC, __image_info, regular"`` for Objective-C ABI version 1, and
``"__DATA,__objc_imageinfo, regular, no_dead_strip"`` for
Objective-C ABI version 2.
* - ``Objective-C Garbage Collection``
- **[Required]** --- Specifies whether garbage collection is supported or
not. Valid values are 0, for no garbage collection, and 2, for garbage
collection supported.
* - ``Objective-C GC Only``
- **[Optional]** --- Specifies that only garbage collection is supported.
If present, its value must be 6. This flag requires that the
``Objective-C Garbage Collection`` flag have the value 2.
Some important flag interactions:
- If a module with ``Objective-C Garbage Collection`` set to 0 is
merged with a module with ``Objective-C Garbage Collection`` set to
2, then the resulting module has the
``Objective-C Garbage Collection`` flag set to 0.
- A module with ``Objective-C Garbage Collection`` set to 0 cannot be
merged with a module with ``Objective-C GC Only`` set to 6.
C type width Module Flags Metadata
----------------------------------
The ARM backend emits a section into each generated object file describing the
options that it was compiled with (in a compiler-independent way) to prevent
linking incompatible objects, and to allow automatic library selection. Some
of these options are not visible at the IR level, namely wchar_t width and enum
width.
To pass this information to the backend, these options are encoded in module
flags metadata, using the following key-value pairs:
.. list-table::
:header-rows: 1
:widths: 30 70
* - Key
- Value
* - short_wchar
- * 0 --- sizeof(wchar_t) == 4
* 1 --- sizeof(wchar_t) == 2
* - short_enum
- * 0 --- Enums are at least as large as an ``int``.
* 1 --- Enums are stored in the smallest integer type which can
represent all of its values.
For example, the following metadata section specifies that the module was
compiled with a ``wchar_t`` width of 4 bytes, and the underlying type of an
enum is the smallest type which can represent all of its values::
!llvm.module.flags = !{!0, !1}
!0 = !{i32 1, !"short_wchar", i32 1}
!1 = !{i32 1, !"short_enum", i32 0}
Stack Alignment Metadata
------------------------
Changes the default stack alignment from the target ABI's implicit default
stack alignment. Takes an i32 value in bytes. It is considered an error to link
two modules together with different values for this metadata.
For example:
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"override-stack-alignment", i32 8}
This will change the stack alignment to 8B.
Embedded Objects Names Metadata
===============================
Offloading compilations need to embed device code into the host section table to
create a fat binary. This metadata node references each global that will be
embedded in the module. The primary use for this is to make referencing these
globals more efficient in the IR. The metadata references nodes containing
pointers to the global to be embedded followed by the section name it will be
stored at::
!llvm.embedded.objects = !{!0}
!0 = !{ptr @object, !".section"}
Automatic Linker Flags Named Metadata
=====================================
Some targets support embedding of flags to the linker inside individual object
files. Typically this is used in conjunction with language extensions which
allow source files to contain linker command line options, and have these
automatically be transmitted to the linker via object files.
These flags are encoded in the IR using named metadata with the name
``!llvm.linker.options``. Each operand is expected to be a metadata node
which should be a list of other metadata nodes, each of which should be a
list of metadata strings defining linker options.
For example, the following metadata section specifies two separate sets of
linker options, presumably to link against ``libz`` and the ``Cocoa``
framework::
!0 = !{ !"-lz" }
!1 = !{ !"-framework", !"Cocoa" }
!llvm.linker.options = !{ !0, !1 }
The metadata encoding as lists of lists of options, as opposed to a collapsed
list of options, is chosen so that the IR encoding can use multiple option
strings to specify e.g., a single library, while still having that specifier be
preserved as an atomic element that can be recognized by a target specific
assembly writer or object file emitter.
Each individual option is required to be either a valid option for the target's
linker, or an option that is reserved by the target specific assembly writer or
object file emitter. No other aspect of these options is defined by the IR.
Dependent Libs Named Metadata
=============================
Some targets support embedding of strings into object files to indicate
a set of libraries to add to the link. Typically this is used in conjunction
with language extensions which allow source files to explicitly declare the
libraries they depend on, and have these automatically be transmitted to the
linker via object files.
The list is encoded in the IR using named metadata with the name
``!llvm.dependent-libraries``. Each operand is expected to be a metadata node
which should contain a single string operand.
For example, the following metadata section contains two library specifiers::
!0 = !{!"a library specifier"}
!1 = !{!"another library specifier"}
!llvm.dependent-libraries = !{ !0, !1 }
Each library specifier will be handled independently by the consuming linker.
The effect of the library specifiers are defined by the consuming linker.
.. _summary:
ThinLTO Summary
===============
Compiling with `ThinLTO <https://clang.llvm.org/docs/ThinLTO.html>`_
causes the building of a compact summary of the module that is emitted into
the bitcode. The summary is emitted into the LLVM assembly and identified
in syntax by a caret ('``^``').
The summary is parsed into a bitcode output, along with the Module
IR, via the "``llvm-as``" tool. Tools that parse the Module IR for the purposes
of optimization (e.g. "``clang -x ir``" and "``opt``"), will ignore the
summary entries (just as they currently ignore summary entries in a bitcode
input file).
Eventually, the summary will be parsed into a ModuleSummaryIndex object under
the same conditions where summary index is currently built from bitcode.
Specifically, tools that test the Thin Link portion of a ThinLTO compile
(i.e. llvm-lto and llvm-lto2), or when parsing a combined index
for a distributed ThinLTO backend via clang's "``-fthinlto-index=<>``" flag
(this part is not yet implemented, use llvm-as to create a bitcode object
before feeding into thin link tools for now).
There are currently 3 types of summary entries in the LLVM assembly:
:ref:`module paths<module_path_summary>`,
:ref:`global values<gv_summary>`, and
:ref:`type identifiers<typeid_summary>`.
.. _module_path_summary:
Module Path Summary Entry
-------------------------
Each module path summary entry lists a module containing global values included
in the summary. For a single IR module there will be one such entry, but
in a combined summary index produced during the thin link, there will be
one module path entry per linked module with summary.
Example:
.. code-block:: text
^0 = module: (path: "/path/to/file.o", hash: (2468601609, 1329373163, 1565878005, 638838075, 3148790418))
The ``path`` field is a string path to the bitcode file, and the ``hash``
field is the 160-bit SHA-1 hash of the IR bitcode contents, used for
incremental builds and caching.
.. _gv_summary:
Global Value Summary Entry
--------------------------
Each global value summary entry corresponds to a global value defined or
referenced by a summarized module.
Example:
.. code-block:: text
^4 = gv: (name: "f"[, summaries: (Summary)[, (Summary)]*]?) ; guid = 14740650423002898831
For declarations, there will not be a summary list. For definitions, a
global value will contain a list of summaries, one per module containing
a definition. There can be multiple entries in a combined summary index
for symbols with weak linkage.
Each ``Summary`` format will depend on whether the global value is a
:ref:`function<function_summary>`, :ref:`variable<variable_summary>`, or
:ref:`alias<alias_summary>`.
.. _function_summary:
Function Summary
^^^^^^^^^^^^^^^^
If the global value is a function, the ``Summary`` entry will look like:
.. code-block:: text
function: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0), insts: 2[, FuncFlags]?[, Calls]?[, TypeIdInfo]?[, Params]?[, Refs]?
The ``module`` field includes the summary entry id for the module containing
this definition, and the ``flags`` field contains information such as
the linkage type, a flag indicating whether it is legal to import the
definition, whether it is globally live and whether the linker resolved it
to a local definition (the latter two are populated during the thin link).
The ``insts`` field contains the number of IR instructions in the function.
Finally, there are several optional fields: :ref:`FuncFlags<funcflags_summary>`,
:ref:`Calls<calls_summary>`, :ref:`TypeIdInfo<typeidinfo_summary>`,
:ref:`Params<params_summary>`, :ref:`Refs<refs_summary>`.
.. _variable_summary:
Global Variable Summary
^^^^^^^^^^^^^^^^^^^^^^^
If the global value is a variable, the ``Summary`` entry will look like:
.. code-block:: text
variable: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0)[, Refs]?
The variable entry contains a subset of the fields in a
:ref:`function summary <function_summary>`, see the descriptions there.
.. _alias_summary:
Alias Summary
^^^^^^^^^^^^^
If the global value is an alias, the ``Summary`` entry will look like:
.. code-block:: text
alias: (module: ^0, flags: (linkage: external, notEligibleToImport: 0, live: 0, dsoLocal: 0), aliasee: ^2)
The ``module`` and ``flags`` fields are as described for a
:ref:`function summary <function_summary>`. The ``aliasee`` field
contains a reference to the global value summary entry of the aliasee.
.. _funcflags_summary:
Function Flags
^^^^^^^^^^^^^^
The optional ``FuncFlags`` field looks like:
.. code-block:: text
funcFlags: (readNone: 0, readOnly: 0, noRecurse: 0, returnDoesNotAlias: 0, noInline: 0, alwaysInline: 0, noUnwind: 1, mayThrow: 0, hasUnknownCall: 0)
If unspecified, flags are assumed to hold the conservative ``false`` value of
``0``.
.. _calls_summary:
Calls
^^^^^
The optional ``Calls`` field looks like:
.. code-block:: text
calls: ((Callee)[, (Callee)]*)
where each ``Callee`` looks like:
.. code-block:: text
callee: ^1[, hotness: None]?[, relbf: 0]?
The ``callee`` refers to the summary entry id of the callee. At most one
of ``hotness`` (which can take the values ``Unknown``, ``Cold``, ``None``,
``Hot``, and ``Critical``), and ``relbf`` (which holds the integer
branch frequency relative to the entry frequency, scaled down by 2^8)
may be specified. The defaults are ``Unknown`` and ``0``, respectively.
.. _params_summary:
Params
^^^^^^
The optional ``Params`` is used by ``StackSafety`` and looks like:
.. code-block:: text
Params: ((Param)[, (Param)]*)
where each ``Param`` describes pointer parameter access inside of the
function and looks like:
.. code-block:: text
param: 4, offset: [0, 5][, calls: ((Callee)[, (Callee)]*)]?
where the first ``param`` is the number of the parameter it describes,
``offset`` is the inclusive range of offsets from the pointer parameter to bytes
which can be accessed by the function. This range does not include accesses by
function calls from ``calls`` list.
where each ``Callee`` describes how parameter is forwarded into other
functions and looks like:
.. code-block:: text
callee: ^3, param: 5, offset: [-3, 3]
The ``callee`` refers to the summary entry id of the callee, ``param`` is
the number of the callee parameter which points into the callers parameter
with offset known to be inside of the ``offset`` range. ``calls`` will be
consumed and removed by thin link stage to update ``Param::offset`` so it
covers all accesses possible by ``calls``.
Pointer parameter without corresponding ``Param`` is considered unsafe and we
assume that access with any offset is possible.
Example:
If we have the following function:
.. code-block:: text
define i64 @foo(ptr %0, ptr %1, ptr %2, i8 %3) {
store ptr %1, ptr @x
%5 = getelementptr inbounds i8, ptr %2, i64 5
%6 = load i8, ptr %5
%7 = getelementptr inbounds i8, ptr %2, i8 %3
tail call void @bar(i8 %3, ptr %7)
%8 = load i64, ptr %0
ret i64 %8
}
We can expect the record like this:
.. code-block:: text
params: ((param: 0, offset: [0, 7]),(param: 2, offset: [5, 5], calls: ((callee: ^3, param: 1, offset: [-128, 127]))))
The function may access just 8 bytes of the parameter %0 . ``calls`` is empty,
so the parameter is either not used for function calls or ``offset`` already
covers all accesses from nested function calls.
Parameter %1 escapes, so access is unknown.
The function itself can access just a single byte of the parameter %2. Additional
access is possible inside of the ``@bar`` or ``^3``. The function adds signed
offset to the pointer and passes the result as the argument %1 into ``^3``.
This record itself does not tell us how ``^3`` will access the parameter.
Parameter %3 is not a pointer.
.. _refs_summary:
Refs
^^^^
The optional ``Refs`` field looks like:
.. code-block:: text
refs: ((Ref)[, (Ref)]*)
where each ``Ref`` contains a reference to the summary id of the referenced
value (e.g. ``^1``).
.. _typeidinfo_summary:
TypeIdInfo
^^^^^^^^^^
The optional ``TypeIdInfo`` field, used for
`Control Flow Integrity <https://clang.llvm.org/docs/ControlFlowIntegrity.html>`_,
looks like:
.. code-block:: text
typeIdInfo: [(TypeTests)]?[, (TypeTestAssumeVCalls)]?[, (TypeCheckedLoadVCalls)]?[, (TypeTestAssumeConstVCalls)]?[, (TypeCheckedLoadConstVCalls)]?
These optional fields have the following forms:
TypeTests
"""""""""
.. code-block:: text
typeTests: (TypeIdRef[, TypeIdRef]*)
Where each ``TypeIdRef`` refers to a :ref:`type id<typeid_summary>`
by summary id or ``GUID``.
TypeTestAssumeVCalls
""""""""""""""""""""
.. code-block:: text
typeTestAssumeVCalls: (VFuncId[, VFuncId]*)
Where each VFuncId has the format:
.. code-block:: text
vFuncId: (TypeIdRef, offset: 16)
Where each ``TypeIdRef`` refers to a :ref:`type id<typeid_summary>`
by summary id or ``GUID`` preceded by a ``guid:`` tag.
TypeCheckedLoadVCalls
"""""""""""""""""""""
.. code-block:: text
typeCheckedLoadVCalls: (VFuncId[, VFuncId]*)
Where each VFuncId has the format described for ``TypeTestAssumeVCalls``.
TypeTestAssumeConstVCalls
"""""""""""""""""""""""""
.. code-block:: text
typeTestAssumeConstVCalls: (ConstVCall[, ConstVCall]*)
Where each ConstVCall has the format:
.. code-block:: text
(VFuncId, args: (Arg[, Arg]*))
and where each VFuncId has the format described for ``TypeTestAssumeVCalls``,
and each Arg is an integer argument number.
TypeCheckedLoadConstVCalls
""""""""""""""""""""""""""
.. code-block:: text
typeCheckedLoadConstVCalls: (ConstVCall[, ConstVCall]*)
Where each ConstVCall has the format described for
``TypeTestAssumeConstVCalls``.
.. _typeid_summary:
Type ID Summary Entry
---------------------
Each type id summary entry corresponds to a type identifier resolution
which is generated during the LTO link portion of the compile when building
with `Control Flow Integrity <https://clang.llvm.org/docs/ControlFlowIntegrity.html>`_,
so these are only present in a combined summary index.
Example:
.. code-block:: text
^4 = typeid: (name: "_ZTS1A", summary: (typeTestRes: (kind: allOnes, sizeM1BitWidth: 7[, alignLog2: 0]?[, sizeM1: 0]?[, bitMask: 0]?[, inlineBits: 0]?)[, WpdResolutions]?)) ; guid = 7004155349499253778
The ``typeTestRes`` gives the type test resolution ``kind`` (which may
be ``unsat``, ``byteArray``, ``inline``, ``single``, or ``allOnes``), and
the ``size-1`` bit width. It is followed by optional flags, which default to 0,
and an optional WpdResolutions (whole program devirtualization resolution)
field that looks like:
.. code-block:: text
wpdResolutions: ((offset: 0, WpdRes)[, (offset: 1, WpdRes)]*
where each entry is a mapping from the given byte offset to the whole-program
devirtualization resolution WpdRes, that has one of the following formats:
.. code-block:: text
wpdRes: (kind: branchFunnel)
wpdRes: (kind: singleImpl, singleImplName: "_ZN1A1nEi")
wpdRes: (kind: indir)
Additionally, each wpdRes has an optional ``resByArg`` field, which
describes the resolutions for calls with all constant integer arguments:
.. code-block:: text
resByArg: (ResByArg[, ResByArg]*)
where ResByArg is:
.. code-block:: text
args: (Arg[, Arg]*), byArg: (kind: UniformRetVal[, info: 0][, byte: 0][, bit: 0])
Where the ``kind`` can be ``Indir``, ``UniformRetVal``, ``UniqueRetVal``
or ``VirtualConstProp``. The ``info`` field is only used if the kind
is ``UniformRetVal`` (indicates the uniform return value), or
``UniqueRetVal`` (holds the return value associated with the unique vtable
(0 or 1)). The ``byte`` and ``bit`` fields are only used if the target does
not support the use of absolute symbols to store constants.
.. _intrinsicglobalvariables:
Intrinsic Global Variables
==========================
LLVM has a number of "magic" global variables that contain data that
affect code generation or other IR semantics. These are documented here.
All globals of this sort should have a section specified as
"``llvm.metadata``". This section and all globals that start with
"``llvm.``" are reserved for use by LLVM.
.. _gv_llvmused:
The '``llvm.used``' Global Variable
-----------------------------------
The ``@llvm.used`` global is an array which has
:ref:`appending linkage <linkage_appending>`. This array contains a list of
pointers to named global variables, functions and aliases which may optionally
have a pointer cast formed of bitcast or getelementptr. For example, a legal
use of it is:
.. code-block:: llvm
@X = global i8 4
@Y = global i32 123
@llvm.used = appending global [2 x ptr] [
ptr @X,
ptr @Y
], section "llvm.metadata"
If a symbol appears in the ``@llvm.used`` list, then the compiler, assembler,
and linker are required to treat the symbol as if there is a reference to the
symbol that it cannot see (which is why they have to be named). For example, if
a variable has internal linkage and no references other than that from the
``@llvm.used`` list, it cannot be deleted. This is commonly used to represent
references from inline asms and other things the compiler cannot "see", and
corresponds to "``attribute((used))``" in GNU C.
On some targets, the code generator must emit a directive to the
assembler or object file to prevent the assembler and linker from
removing the symbol.
.. _gv_llvmcompilerused:
The '``llvm.compiler.used``' Global Variable
--------------------------------------------
The ``@llvm.compiler.used`` directive is the same as the ``@llvm.used``
directive, except that it only prevents the compiler from touching the
symbol. On targets that support it, this allows an intelligent linker to
optimize references to the symbol without being impeded as it would be
by ``@llvm.used``.
This is a rare construct that should only be used in rare circumstances,
and should not be exposed to source languages.
.. _gv_llvmglobalctors:
The '``llvm.global_ctors``' Global Variable
-------------------------------------------
.. code-block:: llvm
%0 = type { i32, ptr, ptr }
@llvm.global_ctors = appending global [1 x %0] [%0 { i32 65535, ptr @ctor, ptr @data }]
The ``@llvm.global_ctors`` array contains a list of constructor
functions, priorities, and an associated global or function.
The functions referenced by this array will be called in ascending order
of priority (i.e. lowest first) when the module is loaded. The order of
functions with the same priority is not defined.
If the third field is non-null, and points to a global variable
or function, the initializer function will only run if the associated
data from the current module is not discarded.
On ELF the referenced global variable or function must be in a comdat.
.. _llvmglobaldtors:
The '``llvm.global_dtors``' Global Variable
-------------------------------------------
.. code-block:: llvm
%0 = type { i32, ptr, ptr }
@llvm.global_dtors = appending global [1 x %0] [%0 { i32 65535, ptr @dtor, ptr @data }]
The ``@llvm.global_dtors`` array contains a list of destructor
functions, priorities, and an associated global or function.
The functions referenced by this array will be called in descending
order of priority (i.e. highest first) when the module is unloaded. The
order of functions with the same priority is not defined.
If the third field is non-null, and points to a global variable
or function, the destructor function will only run if the associated
data from the current module is not discarded.
On ELF the referenced global variable or function must be in a comdat.
Instruction Reference
=====================
The LLVM instruction set consists of several different classifications
of instructions: :ref:`terminator instructions <terminators>`, :ref:`binary
instructions <binaryops>`, :ref:`bitwise binary
instructions <bitwiseops>`, :ref:`memory instructions <memoryops>`, and
:ref:`other instructions <otherops>`.
.. _terminators:
Terminator Instructions
-----------------------
As mentioned :ref:`previously <functionstructure>`, every basic block in a
program ends with a "Terminator" instruction, which indicates which
block should be executed after the current block is finished. These
terminator instructions typically yield a '``void``' value: they produce
control flow, not values (the one exception being the
':ref:`invoke <i_invoke>`' instruction).
The terminator instructions are: ':ref:`ret <i_ret>`',
':ref:`br <i_br>`', ':ref:`switch <i_switch>`',
':ref:`indirectbr <i_indirectbr>`', ':ref:`invoke <i_invoke>`',
':ref:`callbr <i_callbr>`'
':ref:`resume <i_resume>`', ':ref:`catchswitch <i_catchswitch>`',
':ref:`catchret <i_catchret>`',
':ref:`cleanupret <i_cleanupret>`',
and ':ref:`unreachable <i_unreachable>`'.
.. _i_ret:
'``ret``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
ret <type> <value> ; Return a value from a non-void function
ret void ; Return from void function
Overview:
"""""""""
The '``ret``' instruction is used to return control flow (and optionally
a value) from a function back to the caller.
There are two forms of the '``ret``' instruction: one that returns a
value and then causes control flow, and one that just causes control
flow to occur.
Arguments:
""""""""""
The '``ret``' instruction optionally accepts a single argument, the
return value. The type of the return value must be a ':ref:`first
class <t_firstclass>`' type.
A function is not :ref:`well formed <wellformed>` if it has a non-void
return type and contains a '``ret``' instruction with no return value or
a return value with a type that does not match its type, or if it has a
void return type and contains a '``ret``' instruction with a return
value.
Semantics:
""""""""""
When the '``ret``' instruction is executed, control flow returns back to
the calling function's context. If the caller is a
":ref:`call <i_call>`" instruction, execution continues at the
instruction after the call. If the caller was an
":ref:`invoke <i_invoke>`" instruction, execution continues at the
beginning of the "normal" destination block. If the instruction returns
a value, that value shall set the call or invoke instruction's return
value.
Example:
""""""""
.. code-block:: llvm
ret i32 5 ; Return an integer value of 5
ret void ; Return from a void function
ret { i32, i8 } { i32 4, i8 2 } ; Return a struct of values 4 and 2
.. _i_br:
'``br``' Instruction
^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
br i1 <cond>, label <iftrue>, label <iffalse>
br label <dest> ; Unconditional branch
Overview:
"""""""""
The '``br``' instruction is used to cause control flow to transfer to a
different basic block in the current function. There are two forms of
this instruction, corresponding to a conditional branch and an
unconditional branch.
Arguments:
""""""""""
The conditional branch form of the '``br``' instruction takes a single
'``i1``' value and two '``label``' values. The unconditional form of the
'``br``' instruction takes a single '``label``' value as a target.
Semantics:
""""""""""
Upon execution of a conditional '``br``' instruction, the '``i1``'
argument is evaluated. If the value is ``true``, control flows to the
'``iftrue``' ``label`` argument. If "cond" is ``false``, control flows
to the '``iffalse``' ``label`` argument.
If '``cond``' is ``poison`` or ``undef``, this instruction has undefined
behavior.
Example:
""""""""
.. code-block:: llvm
Test:
%cond = icmp eq i32 %a, %b
br i1 %cond, label %IfEqual, label %IfUnequal
IfEqual:
ret i32 1
IfUnequal:
ret i32 0
.. _i_switch:
'``switch``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
switch <intty> <value>, label <defaultdest> [ <intty> <val>, label <dest> ... ]
Overview:
"""""""""
The '``switch``' instruction is used to transfer control flow to one of
several different places. It is a generalization of the '``br``'
instruction, allowing a branch to occur to one of many possible
destinations.
Arguments:
""""""""""
The '``switch``' instruction uses three parameters: an integer
comparison value '``value``', a default '``label``' destination, and an
array of pairs of comparison value constants and '``label``'s. The table
is not allowed to contain duplicate constant entries.
Semantics:
""""""""""
The ``switch`` instruction specifies a table of values and destinations.
When the '``switch``' instruction is executed, this table is searched
for the given value. If the value is found, control flow is transferred
to the corresponding destination; otherwise, control flow is transferred
to the default destination.
If '``value``' is ``poison`` or ``undef``, this instruction has undefined
behavior.
Implementation:
"""""""""""""""
Depending on properties of the target machine and the particular
``switch`` instruction, this instruction may be code generated in
different ways. For example, it could be generated as a series of
chained conditional branches or with a lookup table.
Example:
""""""""
.. code-block:: llvm
; Emulate a conditional br instruction
%Val = zext i1 %value to i32
switch i32 %Val, label %truedest [ i32 0, label %falsedest ]
; Emulate an unconditional br instruction
switch i32 0, label %dest [ ]
; Implement a jump table:
switch i32 %val, label %otherwise [ i32 0, label %onzero
i32 1, label %onone
i32 2, label %ontwo ]
.. _i_indirectbr:
'``indirectbr``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
indirectbr ptr <address>, [ label <dest1>, label <dest2>, ... ]
Overview:
"""""""""
The '``indirectbr``' instruction implements an indirect branch to a
label within the current function, whose address is specified by
"``address``". Address must be derived from a
:ref:`blockaddress <blockaddress>` constant.
Arguments:
""""""""""
The '``address``' argument is the address of the label to jump to. The
rest of the arguments indicate the full set of possible destinations
that the address may point to. Blocks are allowed to occur multiple
times in the destination list, though this isn't particularly useful.
This destination list is required so that dataflow analysis has an
accurate understanding of the CFG.
Semantics:
""""""""""
Control transfers to the block specified in the address argument. All
possible destination blocks must be listed in the label list, otherwise
this instruction has undefined behavior. This implies that jumps to
labels defined in other functions have undefined behavior as well.
If '``address``' is ``poison`` or ``undef``, this instruction has undefined
behavior.
Implementation:
"""""""""""""""
This is typically implemented with a jump through a register.
Example:
""""""""
.. code-block:: llvm
indirectbr ptr %Addr, [ label %bb1, label %bb2, label %bb3 ]
.. _i_invoke:
'``invoke``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = invoke [cconv] [ret attrs] [addrspace(<num>)] <ty>|<fnty> <fnptrval>(<function args>) [fn attrs]
[operand bundles] to label <normal label> unwind label <exception label>
Overview:
"""""""""
The '``invoke``' instruction causes control to transfer to a specified
function, with the possibility of control flow transfer to either the
'``normal``' label or the '``exception``' label. If the callee function
returns with the "``ret``" instruction, control flow will return to the
"normal" label. If the callee (or any indirect callees) returns via the
":ref:`resume <i_resume>`" instruction or other exception handling
mechanism, control is interrupted and continued at the dynamically
nearest "exception" label.
The '``exception``' label is a `landing
pad <ExceptionHandling.html#overview>`_ for the exception. As such,
'``exception``' label is required to have the
":ref:`landingpad <i_landingpad>`" instruction, which contains the
information about the behavior of the program after unwinding happens,
as its first non-PHI instruction. The restrictions on the
"``landingpad``" instruction's tightly couples it to the "``invoke``"
instruction, so that the important information contained within the
"``landingpad``" instruction can't be lost through normal code motion.
Arguments:
""""""""""
This instruction requires several arguments:
#. The optional "cconv" marker indicates which :ref:`calling
convention <callingconv>` the call should use. If none is
specified, the call defaults to using C calling conventions.
#. The optional :ref:`Parameter Attributes <paramattrs>` list for return
values. Only '``zeroext``', '``signext``', and '``inreg``' attributes
are valid here.
#. The optional addrspace attribute can be used to indicate the address space
of the called function. If it is not specified, the program address space
from the :ref:`datalayout string<langref_datalayout>` will be used.
#. '``ty``': the type of the call instruction itself which is also the
type of the return value. Functions that return no value are marked
``void``.
#. '``fnty``': shall be the signature of the function being invoked. The
argument types must match the types implied by this signature. This
type can be omitted if the function is not varargs.
#. '``fnptrval``': An LLVM value containing a pointer to a function to
be invoked. In most cases, this is a direct function invocation, but
indirect ``invoke``'s are just as possible, calling an arbitrary pointer
to function value.
#. '``function args``': argument list whose types match the function
signature argument types and parameter attributes. All arguments must
be of :ref:`first class <t_firstclass>` type. If the function signature
indicates the function accepts a variable number of arguments, the
extra arguments can be specified.
#. '``normal label``': the label reached when the called function
executes a '``ret``' instruction.
#. '``exception label``': the label reached when a callee returns via
the :ref:`resume <i_resume>` instruction or other exception handling
mechanism.
#. The optional :ref:`function attributes <fnattrs>` list.
#. The optional :ref:`operand bundles <opbundles>` list.
Semantics:
""""""""""
This instruction is designed to operate as a standard '``call``'
instruction in most regards. The primary difference is that it
establishes an association with a label, which is used by the runtime
library to unwind the stack.
This instruction is used in languages with destructors to ensure that
proper cleanup is performed in the case of either a ``longjmp`` or a
thrown exception. Additionally, this is important for implementation of
'``catch``' clauses in high-level languages that support them.
For the purposes of the SSA form, the definition of the value returned
by the '``invoke``' instruction is deemed to occur on the edge from the
current block to the "normal" label. If the callee unwinds then no
return value is available.
Example:
""""""""
.. code-block:: llvm
%retval = invoke i32 @Test(i32 15) to label %Continue
unwind label %TestCleanup ; i32:retval set
%retval = invoke coldcc i32 %Testfnptr(i32 15) to label %Continue
unwind label %TestCleanup ; i32:retval set
.. _i_callbr:
'``callbr``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = callbr [cconv] [ret attrs] [addrspace(<num>)] <ty>|<fnty> <fnptrval>(<function args>) [fn attrs]
[operand bundles] to label <fallthrough label> [indirect labels]
Overview:
"""""""""
The '``callbr``' instruction causes control to transfer to a specified
function, with the possibility of control flow transfer to either the
'``fallthrough``' label or one of the '``indirect``' labels.
This instruction should only be used to implement the "goto" feature of gcc
style inline assembly. Any other usage is an error in the IR verifier.
Note that in order to support outputs along indirect edges, LLVM may need to
split critical edges, which may require synthesizing a replacement block for
the ``indirect labels``. Therefore, the address of a label as seen by another
``callbr`` instruction, or for a :ref:`blockaddress <blockaddress>` constant,
may not be equal to the address provided for the same block to this
instruction's ``indirect labels`` operand. The assembly code may only transfer
control to addresses provided via this instruction's ``indirect labels``.
Arguments:
""""""""""
This instruction requires several arguments:
#. The optional "cconv" marker indicates which :ref:`calling
convention <callingconv>` the call should use. If none is
specified, the call defaults to using C calling conventions.
#. The optional :ref:`Parameter Attributes <paramattrs>` list for return
values. Only '``zeroext``', '``signext``', and '``inreg``' attributes
are valid here.
#. The optional addrspace attribute can be used to indicate the address space
of the called function. If it is not specified, the program address space
from the :ref:`datalayout string<langref_datalayout>` will be used.
#. '``ty``': the type of the call instruction itself which is also the
type of the return value. Functions that return no value are marked
``void``.
#. '``fnty``': shall be the signature of the function being called. The
argument types must match the types implied by this signature. This
type can be omitted if the function is not varargs.
#. '``fnptrval``': An LLVM value containing a pointer to a function to
be called. In most cases, this is a direct function call, but
other ``callbr``'s are just as possible, calling an arbitrary pointer
to function value.
#. '``function args``': argument list whose types match the function
signature argument types and parameter attributes. All arguments must
be of :ref:`first class <t_firstclass>` type. If the function signature
indicates the function accepts a variable number of arguments, the
extra arguments can be specified.
#. '``fallthrough label``': the label reached when the inline assembly's
execution exits the bottom.
#. '``indirect labels``': the labels reached when a callee transfers control
to a location other than the '``fallthrough label``'. Label constraints
refer to these destinations.
#. The optional :ref:`function attributes <fnattrs>` list.
#. The optional :ref:`operand bundles <opbundles>` list.
Semantics:
""""""""""
This instruction is designed to operate as a standard '``call``'
instruction in most regards. The primary difference is that it
establishes an association with additional labels to define where control
flow goes after the call.
The output values of a '``callbr``' instruction are available only to
the '``fallthrough``' block, not to any '``indirect``' blocks(s).
The only use of this today is to implement the "goto" feature of gcc inline
assembly where additional labels can be provided as locations for the inline
assembly to jump to.
Example:
""""""""
.. code-block:: llvm
; "asm goto" without output constraints.
callbr void asm "", "r,!i"(i32 %x)
to label %fallthrough [label %indirect]
; "asm goto" with output constraints.
<result> = callbr i32 asm "", "=r,r,!i"(i32 %x)
to label %fallthrough [label %indirect]
.. _i_resume:
'``resume``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
resume <type> <value>
Overview:
"""""""""
The '``resume``' instruction is a terminator instruction that has no
successors.
Arguments:
""""""""""
The '``resume``' instruction requires one argument, which must have the
same type as the result of any '``landingpad``' instruction in the same
function.
Semantics:
""""""""""
The '``resume``' instruction resumes propagation of an existing
(in-flight) exception whose unwinding was interrupted with a
:ref:`landingpad <i_landingpad>` instruction.
Example:
""""""""
.. code-block:: llvm
resume { ptr, i32 } %exn
.. _i_catchswitch:
'``catchswitch``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<resultval> = catchswitch within <parent> [ label <handler1>, label <handler2>, ... ] unwind to caller
<resultval> = catchswitch within <parent> [ label <handler1>, label <handler2>, ... ] unwind label <default>
Overview:
"""""""""
The '``catchswitch``' instruction is used by `LLVM's exception handling system
<ExceptionHandling.html#overview>`_ to describe the set of possible catch handlers
that may be executed by the :ref:`EH personality routine <personalityfn>`.
Arguments:
""""""""""
The ``parent`` argument is the token of the funclet that contains the
``catchswitch`` instruction. If the ``catchswitch`` is not inside a funclet,
this operand may be the token ``none``.
The ``default`` argument is the label of another basic block beginning with
either a ``cleanuppad`` or ``catchswitch`` instruction. This unwind destination
must be a legal target with respect to the ``parent`` links, as described in
the `exception handling documentation\ <ExceptionHandling.html#wineh-constraints>`_.
The ``handlers`` are a nonempty list of successor blocks that each begin with a
:ref:`catchpad <i_catchpad>` instruction.
Semantics:
""""""""""
Executing this instruction transfers control to one of the successors in
``handlers``, if appropriate, or continues to unwind via the unwind label if
present.
The ``catchswitch`` is both a terminator and a "pad" instruction, meaning that
it must be both the first non-phi instruction and last instruction in the basic
block. Therefore, it must be the only non-phi instruction in the block.
Example:
""""""""
.. code-block:: text
dispatch1:
%cs1 = catchswitch within none [label %handler0, label %handler1] unwind to caller
dispatch2:
%cs2 = catchswitch within %parenthandler [label %handler0] unwind label %cleanup
.. _i_catchret:
'``catchret``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
catchret from <token> to label <normal>
Overview:
"""""""""
The '``catchret``' instruction is a terminator instruction that has a
single successor.
Arguments:
""""""""""
The first argument to a '``catchret``' indicates which ``catchpad`` it
exits. It must be a :ref:`catchpad <i_catchpad>`.
The second argument to a '``catchret``' specifies where control will
transfer to next.
Semantics:
""""""""""
The '``catchret``' instruction ends an existing (in-flight) exception whose
unwinding was interrupted with a :ref:`catchpad <i_catchpad>` instruction. The
:ref:`personality function <personalityfn>` gets a chance to execute arbitrary
code to, for example, destroy the active exception. Control then transfers to
``normal``.
The ``token`` argument must be a token produced by a ``catchpad`` instruction.
If the specified ``catchpad`` is not the most-recently-entered not-yet-exited
funclet pad (as described in the `EH documentation\ <ExceptionHandling.html#wineh-constraints>`_),
the ``catchret``'s behavior is undefined.
Example:
""""""""
.. code-block:: text
catchret from %catch to label %continue
.. _i_cleanupret:
'``cleanupret``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
cleanupret from <value> unwind label <continue>
cleanupret from <value> unwind to caller
Overview:
"""""""""
The '``cleanupret``' instruction is a terminator instruction that has
an optional successor.
Arguments:
""""""""""
The '``cleanupret``' instruction requires one argument, which indicates
which ``cleanuppad`` it exits, and must be a :ref:`cleanuppad <i_cleanuppad>`.
If the specified ``cleanuppad`` is not the most-recently-entered not-yet-exited
funclet pad (as described in the `EH documentation\ <ExceptionHandling.html#wineh-constraints>`_),
the ``cleanupret``'s behavior is undefined.
The '``cleanupret``' instruction also has an optional successor, ``continue``,
which must be the label of another basic block beginning with either a
``cleanuppad`` or ``catchswitch`` instruction. This unwind destination must
be a legal target with respect to the ``parent`` links, as described in the
`exception handling documentation\ <ExceptionHandling.html#wineh-constraints>`_.
Semantics:
""""""""""
The '``cleanupret``' instruction indicates to the
:ref:`personality function <personalityfn>` that one
:ref:`cleanuppad <i_cleanuppad>` it transferred control to has ended.
It transfers control to ``continue`` or unwinds out of the function.
Example:
""""""""
.. code-block:: text
cleanupret from %cleanup unwind to caller
cleanupret from %cleanup unwind label %continue
.. _i_unreachable:
'``unreachable``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
unreachable
Overview:
"""""""""
The '``unreachable``' instruction has no defined semantics. This
instruction is used to inform the optimizer that a particular portion of
the code is not reachable. This can be used to indicate that the code
after a no-return function cannot be reached, and other facts.
Semantics:
""""""""""
The '``unreachable``' instruction has no defined semantics.
.. _unaryops:
Unary Operations
-----------------
Unary operators require a single operand, execute an operation on
it, and produce a single value. The operand might represent multiple
data, as is the case with the :ref:`vector <t_vector>` data type. The
result value has the same type as its operand.
.. _i_fneg:
'``fneg``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fneg [fast-math flags]* <ty> <op1> ; yields ty:result
Overview:
"""""""""
The '``fneg``' instruction returns the negation of its operand.
Arguments:
""""""""""
The argument to the '``fneg``' instruction must be a
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values.
Semantics:
""""""""""
The value produced is a copy of the operand with its sign bit flipped.
The value is otherwise completely identical; in particular, if the input is a
NaN, then the quiet/signaling bit and payload are perfectly preserved.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = fneg float %val ; yields float:result = -%var
.. _binaryops:
Binary Operations
-----------------
Binary operators are used to do most of the computation in a program.
They require two operands of the same type, execute an operation on
them, and produce a single value. The operands might represent multiple
data, as is the case with the :ref:`vector <t_vector>` data type. The
result value has the same type as its operands.
There are several different binary operators:
.. _i_add:
'``add``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = add <ty> <op1>, <op2> ; yields ty:result
<result> = add nuw <ty> <op1>, <op2> ; yields ty:result
<result> = add nsw <ty> <op1>, <op2> ; yields ty:result
<result> = add nuw nsw <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``add``' instruction returns the sum of its two operands.
Arguments:
""""""""""
The two arguments to the '``add``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The value produced is the integer sum of the two operands.
If the sum has unsigned overflow, the result returned is the
mathematical result modulo 2\ :sup:`n`\ , where n is the bit width of
the result.
Because LLVM integers use a two's complement representation, this
instruction is appropriate for both signed and unsigned integers.
``nuw`` and ``nsw`` stand for "No Unsigned Wrap" and "No Signed Wrap",
respectively. If the ``nuw`` and/or ``nsw`` keywords are present, the
result value of the ``add`` is a :ref:`poison value <poisonvalues>` if
unsigned and/or signed overflow, respectively, occurs.
Example:
""""""""
.. code-block:: text
<result> = add i32 4, %var ; yields i32:result = 4 + %var
.. _i_fadd:
'``fadd``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fadd [fast-math flags]* <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``fadd``' instruction returns the sum of its two operands.
Arguments:
""""""""""
The two arguments to the '``fadd``' instruction must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values. Both arguments must have identical types.
Semantics:
""""""""""
The value produced is the floating-point sum of the two operands.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = fadd float 4.0, %var ; yields float:result = 4.0 + %var
.. _i_sub:
'``sub``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = sub <ty> <op1>, <op2> ; yields ty:result
<result> = sub nuw <ty> <op1>, <op2> ; yields ty:result
<result> = sub nsw <ty> <op1>, <op2> ; yields ty:result
<result> = sub nuw nsw <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``sub``' instruction returns the difference of its two operands.
Note that the '``sub``' instruction is used to represent the '``neg``'
instruction present in most other intermediate representations.
Arguments:
""""""""""
The two arguments to the '``sub``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The value produced is the integer difference of the two operands.
If the difference has unsigned overflow, the result returned is the
mathematical result modulo 2\ :sup:`n`\ , where n is the bit width of
the result.
Because LLVM integers use a two's complement representation, this
instruction is appropriate for both signed and unsigned integers.
``nuw`` and ``nsw`` stand for "No Unsigned Wrap" and "No Signed Wrap",
respectively. If the ``nuw`` and/or ``nsw`` keywords are present, the
result value of the ``sub`` is a :ref:`poison value <poisonvalues>` if
unsigned and/or signed overflow, respectively, occurs.
Example:
""""""""
.. code-block:: text
<result> = sub i32 4, %var ; yields i32:result = 4 - %var
<result> = sub i32 0, %val ; yields i32:result = -%var
.. _i_fsub:
'``fsub``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fsub [fast-math flags]* <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``fsub``' instruction returns the difference of its two operands.
Arguments:
""""""""""
The two arguments to the '``fsub``' instruction must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values. Both arguments must have identical types.
Semantics:
""""""""""
The value produced is the floating-point difference of the two operands.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = fsub float 4.0, %var ; yields float:result = 4.0 - %var
<result> = fsub float -0.0, %val ; yields float:result = -%var
.. _i_mul:
'``mul``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = mul <ty> <op1>, <op2> ; yields ty:result
<result> = mul nuw <ty> <op1>, <op2> ; yields ty:result
<result> = mul nsw <ty> <op1>, <op2> ; yields ty:result
<result> = mul nuw nsw <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``mul``' instruction returns the product of its two operands.
Arguments:
""""""""""
The two arguments to the '``mul``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The value produced is the integer product of the two operands.
If the result of the multiplication has unsigned overflow, the result
returned is the mathematical result modulo 2\ :sup:`n`\ , where n is the
bit width of the result.
Because LLVM integers use a two's complement representation, and the
result is the same width as the operands, this instruction returns the
correct result for both signed and unsigned integers. If a full product
(e.g. ``i32`` * ``i32`` -> ``i64``) is needed, the operands should be
sign-extended or zero-extended as appropriate to the width of the full
product.
``nuw`` and ``nsw`` stand for "No Unsigned Wrap" and "No Signed Wrap",
respectively. If the ``nuw`` and/or ``nsw`` keywords are present, the
result value of the ``mul`` is a :ref:`poison value <poisonvalues>` if
unsigned and/or signed overflow, respectively, occurs.
Example:
""""""""
.. code-block:: text
<result> = mul i32 4, %var ; yields i32:result = 4 * %var
.. _i_fmul:
'``fmul``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fmul [fast-math flags]* <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``fmul``' instruction returns the product of its two operands.
Arguments:
""""""""""
The two arguments to the '``fmul``' instruction must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values. Both arguments must have identical types.
Semantics:
""""""""""
The value produced is the floating-point product of the two operands.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = fmul float 4.0, %var ; yields float:result = 4.0 * %var
.. _i_udiv:
'``udiv``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = udiv <ty> <op1>, <op2> ; yields ty:result
<result> = udiv exact <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``udiv``' instruction returns the quotient of its two operands.
Arguments:
""""""""""
The two arguments to the '``udiv``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The value produced is the unsigned integer quotient of the two operands.
Note that unsigned integer division and signed integer division are
distinct operations; for signed integer division, use '``sdiv``'.
Division by zero is undefined behavior. For vectors, if any element
of the divisor is zero, the operation has undefined behavior.
If the ``exact`` keyword is present, the result value of the ``udiv`` is
a :ref:`poison value <poisonvalues>` if %op1 is not a multiple of %op2 (as
such, "((a udiv exact b) mul b) == a").
Example:
""""""""
.. code-block:: text
<result> = udiv i32 4, %var ; yields i32:result = 4 / %var
.. _i_sdiv:
'``sdiv``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = sdiv <ty> <op1>, <op2> ; yields ty:result
<result> = sdiv exact <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``sdiv``' instruction returns the quotient of its two operands.
Arguments:
""""""""""
The two arguments to the '``sdiv``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The value produced is the signed integer quotient of the two operands
rounded towards zero.
Note that signed integer division and unsigned integer division are
distinct operations; for unsigned integer division, use '``udiv``'.
Division by zero is undefined behavior. For vectors, if any element
of the divisor is zero, the operation has undefined behavior.
Overflow also leads to undefined behavior; this is a rare case, but can
occur, for example, by doing a 32-bit division of -2147483648 by -1.
If the ``exact`` keyword is present, the result value of the ``sdiv`` is
a :ref:`poison value <poisonvalues>` if the result would be rounded.
Example:
""""""""
.. code-block:: text
<result> = sdiv i32 4, %var ; yields i32:result = 4 / %var
.. _i_fdiv:
'``fdiv``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fdiv [fast-math flags]* <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``fdiv``' instruction returns the quotient of its two operands.
Arguments:
""""""""""
The two arguments to the '``fdiv``' instruction must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values. Both arguments must have identical types.
Semantics:
""""""""""
The value produced is the floating-point quotient of the two operands.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = fdiv float 4.0, %var ; yields float:result = 4.0 / %var
.. _i_urem:
'``urem``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = urem <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``urem``' instruction returns the remainder from the unsigned
division of its two arguments.
Arguments:
""""""""""
The two arguments to the '``urem``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
This instruction returns the unsigned integer *remainder* of a division.
This instruction always performs an unsigned division to get the
remainder.
Note that unsigned integer remainder and signed integer remainder are
distinct operations; for signed integer remainder, use '``srem``'.
Taking the remainder of a division by zero is undefined behavior.
For vectors, if any element of the divisor is zero, the operation has
undefined behavior.
Example:
""""""""
.. code-block:: text
<result> = urem i32 4, %var ; yields i32:result = 4 % %var
.. _i_srem:
'``srem``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = srem <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``srem``' instruction returns the remainder from the signed
division of its two operands. This instruction can also take
:ref:`vector <t_vector>` versions of the values in which case the elements
must be integers.
Arguments:
""""""""""
The two arguments to the '``srem``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
This instruction returns the *remainder* of a division (where the result
is either zero or has the same sign as the dividend, ``op1``), not the
*modulo* operator (where the result is either zero or has the same sign
as the divisor, ``op2``) of a value. For more information about the
difference, see `The Math
Forum <http://mathforum.org/dr.math/problems/anne.4.28.99.html>`_. For a
table of how this is implemented in various languages, please see
`Wikipedia: modulo
operation <http://en.wikipedia.org/wiki/Modulo_operation>`_.
Note that signed integer remainder and unsigned integer remainder are
distinct operations; for unsigned integer remainder, use '``urem``'.
Taking the remainder of a division by zero is undefined behavior.
For vectors, if any element of the divisor is zero, the operation has
undefined behavior.
Overflow also leads to undefined behavior; this is a rare case, but can
occur, for example, by taking the remainder of a 32-bit division of
-2147483648 by -1. (The remainder doesn't actually overflow, but this
rule lets srem be implemented using instructions that return both the
result of the division and the remainder.)
Example:
""""""""
.. code-block:: text
<result> = srem i32 4, %var ; yields i32:result = 4 % %var
.. _i_frem:
'``frem``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = frem [fast-math flags]* <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``frem``' instruction returns the remainder from the division of
its two operands.
.. note::
The instruction is implemented as a call to libm's '``fmod``'
for some targets, and using the instruction may thus require linking libm.
Arguments:
""""""""""
The two arguments to the '``frem``' instruction must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>` of
floating-point values. Both arguments must have identical types.
Semantics:
""""""""""
The value produced is the floating-point remainder of the two operands.
This is the same output as a libm '``fmod``' function, but without any
possibility of setting ``errno``. The remainder has the same sign as the
dividend.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
This instruction can also take any number of :ref:`fast-math
flags <fastmath>`, which are optimization hints to enable otherwise
unsafe floating-point optimizations:
Example:
""""""""
.. code-block:: text
<result> = frem float 4.0, %var ; yields float:result = 4.0 % %var
.. _bitwiseops:
Bitwise Binary Operations
-------------------------
Bitwise binary operators are used to do various forms of bit-twiddling
in a program. They are generally very efficient instructions and can
commonly be strength reduced from other instructions. They require two
operands of the same type, execute an operation on them, and produce a
single value. The resulting value is the same type as its operands.
.. _i_shl:
'``shl``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = shl <ty> <op1>, <op2> ; yields ty:result
<result> = shl nuw <ty> <op1>, <op2> ; yields ty:result
<result> = shl nsw <ty> <op1>, <op2> ; yields ty:result
<result> = shl nuw nsw <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``shl``' instruction returns the first operand shifted to the left
a specified number of bits.
Arguments:
""""""""""
Both arguments to the '``shl``' instruction must be the same
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer type.
'``op2``' is treated as an unsigned value.
Semantics:
""""""""""
The value produced is ``op1`` \* 2\ :sup:`op2` mod 2\ :sup:`n`,
where ``n`` is the width of the result. If ``op2`` is (statically or
dynamically) equal to or larger than the number of bits in
``op1``, this instruction returns a :ref:`poison value <poisonvalues>`.
If the arguments are vectors, each vector element of ``op1`` is shifted
by the corresponding shift amount in ``op2``.
If the ``nuw`` keyword is present, then the shift produces a poison
value if it shifts out any non-zero bits.
If the ``nsw`` keyword is present, then the shift produces a poison
value if it shifts out any bits that disagree with the resultant sign bit.
Example:
""""""""
.. code-block:: text
<result> = shl i32 4, %var ; yields i32: 4 << %var
<result> = shl i32 4, 2 ; yields i32: 16
<result> = shl i32 1, 10 ; yields i32: 1024
<result> = shl i32 1, 32 ; undefined
<result> = shl <2 x i32> < i32 1, i32 1>, < i32 1, i32 2> ; yields: result=<2 x i32> < i32 2, i32 4>
.. _i_lshr:
'``lshr``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = lshr <ty> <op1>, <op2> ; yields ty:result
<result> = lshr exact <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``lshr``' instruction (logical shift right) returns the first
operand shifted to the right a specified number of bits with zero fill.
Arguments:
""""""""""
Both arguments to the '``lshr``' instruction must be the same
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer type.
'``op2``' is treated as an unsigned value.
Semantics:
""""""""""
This instruction always performs a logical shift right operation. The
most significant bits of the result will be filled with zero bits after
the shift. If ``op2`` is (statically or dynamically) equal to or larger
than the number of bits in ``op1``, this instruction returns a :ref:`poison
value <poisonvalues>`. If the arguments are vectors, each vector element
of ``op1`` is shifted by the corresponding shift amount in ``op2``.
If the ``exact`` keyword is present, the result value of the ``lshr`` is
a poison value if any of the bits shifted out are non-zero.
Example:
""""""""
.. code-block:: text
<result> = lshr i32 4, 1 ; yields i32:result = 2
<result> = lshr i32 4, 2 ; yields i32:result = 1
<result> = lshr i8 4, 3 ; yields i8:result = 0
<result> = lshr i8 -2, 1 ; yields i8:result = 0x7F
<result> = lshr i32 1, 32 ; undefined
<result> = lshr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 2> ; yields: result=<2 x i32> < i32 0x7FFFFFFF, i32 1>
.. _i_ashr:
'``ashr``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = ashr <ty> <op1>, <op2> ; yields ty:result
<result> = ashr exact <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``ashr``' instruction (arithmetic shift right) returns the first
operand shifted to the right a specified number of bits with sign
extension.
Arguments:
""""""""""
Both arguments to the '``ashr``' instruction must be the same
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer type.
'``op2``' is treated as an unsigned value.
Semantics:
""""""""""
This instruction always performs an arithmetic shift right operation,
The most significant bits of the result will be filled with the sign bit
of ``op1``. If ``op2`` is (statically or dynamically) equal to or larger
than the number of bits in ``op1``, this instruction returns a :ref:`poison
value <poisonvalues>`. If the arguments are vectors, each vector element
of ``op1`` is shifted by the corresponding shift amount in ``op2``.
If the ``exact`` keyword is present, the result value of the ``ashr`` is
a poison value if any of the bits shifted out are non-zero.
Example:
""""""""
.. code-block:: text
<result> = ashr i32 4, 1 ; yields i32:result = 2
<result> = ashr i32 4, 2 ; yields i32:result = 1
<result> = ashr i8 4, 3 ; yields i8:result = 0
<result> = ashr i8 -2, 1 ; yields i8:result = -1
<result> = ashr i32 1, 32 ; undefined
<result> = ashr <2 x i32> < i32 -2, i32 4>, < i32 1, i32 3> ; yields: result=<2 x i32> < i32 -1, i32 0>
.. _i_and:
'``and``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = and <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``and``' instruction returns the bitwise logical and of its two
operands.
Arguments:
""""""""""
The two arguments to the '``and``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The truth table used for the '``and``' instruction is:
+-----+-----+-----+
| In0 | In1 | Out |
+-----+-----+-----+
| 0 | 0 | 0 |
+-----+-----+-----+
| 0 | 1 | 0 |
+-----+-----+-----+
| 1 | 0 | 0 |
+-----+-----+-----+
| 1 | 1 | 1 |
+-----+-----+-----+
Example:
""""""""
.. code-block:: text
<result> = and i32 4, %var ; yields i32:result = 4 & %var
<result> = and i32 15, 40 ; yields i32:result = 8
<result> = and i32 4, 8 ; yields i32:result = 0
.. _i_or:
'``or``' Instruction
^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = or <ty> <op1>, <op2> ; yields ty:result
<result> = or disjoint <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``or``' instruction returns the bitwise logical inclusive or of its
two operands.
Arguments:
""""""""""
The two arguments to the '``or``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The truth table used for the '``or``' instruction is:
+-----+-----+-----+
| In0 | In1 | Out |
+-----+-----+-----+
| 0 | 0 | 0 |
+-----+-----+-----+
| 0 | 1 | 1 |
+-----+-----+-----+
| 1 | 0 | 1 |
+-----+-----+-----+
| 1 | 1 | 1 |
+-----+-----+-----+
``disjoint`` means that for each bit, that bit is zero in at least one of the
inputs. This allows the Or to be treated as an Add since no carry can occur from
any bit. If the disjoint keyword is present, the result value of the ``or`` is a
:ref:`poison value <poisonvalues>` if both inputs have a one in the same bit
position. For vectors, only the element containing the bit is poison.
Example:
""""""""
::
<result> = or i32 4, %var ; yields i32:result = 4 | %var
<result> = or i32 15, 40 ; yields i32:result = 47
<result> = or i32 4, 8 ; yields i32:result = 12
.. _i_xor:
'``xor``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = xor <ty> <op1>, <op2> ; yields ty:result
Overview:
"""""""""
The '``xor``' instruction returns the bitwise logical exclusive or of
its two operands. The ``xor`` is used to implement the "one's
complement" operation, which is the "~" operator in C.
Arguments:
""""""""""
The two arguments to the '``xor``' instruction must be
:ref:`integer <t_integer>` or :ref:`vector <t_vector>` of integer values. Both
arguments must have identical types.
Semantics:
""""""""""
The truth table used for the '``xor``' instruction is:
+-----+-----+-----+
| In0 | In1 | Out |
+-----+-----+-----+
| 0 | 0 | 0 |
+-----+-----+-----+
| 0 | 1 | 1 |
+-----+-----+-----+
| 1 | 0 | 1 |
+-----+-----+-----+
| 1 | 1 | 0 |
+-----+-----+-----+
Example:
""""""""
.. code-block:: text
<result> = xor i32 4, %var ; yields i32:result = 4 ^ %var
<result> = xor i32 15, 40 ; yields i32:result = 39
<result> = xor i32 4, 8 ; yields i32:result = 12
<result> = xor i32 %V, -1 ; yields i32:result = ~%V
Vector Operations
-----------------
LLVM supports several instructions to represent vector operations in a
target-independent manner. These instructions cover the element-access
and vector-specific operations needed to process vectors effectively.
While LLVM does directly support these vector operations, many
sophisticated algorithms will want to use target-specific intrinsics to
take full advantage of a specific target.
.. _i_extractelement:
'``extractelement``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = extractelement <n x <ty>> <val>, <ty2> <idx> ; yields <ty>
<result> = extractelement <vscale x n x <ty>> <val>, <ty2> <idx> ; yields <ty>
Overview:
"""""""""
The '``extractelement``' instruction extracts a single scalar element
from a vector at a specified index.
Arguments:
""""""""""
The first operand of an '``extractelement``' instruction is a value of
:ref:`vector <t_vector>` type. The second operand is an index indicating
the position from which to extract the element. The index may be a
variable of any integer type, and will be treated as an unsigned integer.
Semantics:
""""""""""
The result is a scalar of the same type as the element type of ``val``.
Its value is the value at position ``idx`` of ``val``. If ``idx``
exceeds the length of ``val`` for a fixed-length vector, the result is a
:ref:`poison value <poisonvalues>`. For a scalable vector, if the value
of ``idx`` exceeds the runtime length of the vector, the result is a
:ref:`poison value <poisonvalues>`.
Example:
""""""""
.. code-block:: text
<result> = extractelement <4 x i32> %vec, i32 0 ; yields i32
.. _i_insertelement:
'``insertelement``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = insertelement <n x <ty>> <val>, <ty> <elt>, <ty2> <idx> ; yields <n x <ty>>
<result> = insertelement <vscale x n x <ty>> <val>, <ty> <elt>, <ty2> <idx> ; yields <vscale x n x <ty>>
Overview:
"""""""""
The '``insertelement``' instruction inserts a scalar element into a
vector at a specified index.
Arguments:
""""""""""
The first operand of an '``insertelement``' instruction is a value of
:ref:`vector <t_vector>` type. The second operand is a scalar value whose
type must equal the element type of the first operand. The third operand
is an index indicating the position at which to insert the value. The
index may be a variable of any integer type, and will be treated as an
unsigned integer.
Semantics:
""""""""""
The result is a vector of the same type as ``val``. Its element values
are those of ``val`` except at position ``idx``, where it gets the value
``elt``. If ``idx`` exceeds the length of ``val`` for a fixed-length vector,
the result is a :ref:`poison value <poisonvalues>`. For a scalable vector,
if the value of ``idx`` exceeds the runtime length of the vector, the result
is a :ref:`poison value <poisonvalues>`.
Example:
""""""""
.. code-block:: text
<result> = insertelement <4 x i32> %vec, i32 1, i32 0 ; yields <4 x i32>
.. _i_shufflevector:
'``shufflevector``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = shufflevector <n x <ty>> <v1>, <n x <ty>> <v2>, <m x i32> <mask> ; yields <m x <ty>>
<result> = shufflevector <vscale x n x <ty>> <v1>, <vscale x n x <ty>> v2, <vscale x m x i32> <mask> ; yields <vscale x m x <ty>>
Overview:
"""""""""
The '``shufflevector``' instruction constructs a permutation of elements
from two input vectors, returning a vector with the same element type as
the input and length that is the same as the shuffle mask.
Arguments:
""""""""""
The first two operands of a '``shufflevector``' instruction are vectors
with the same type. The third argument is a shuffle mask vector constant
whose element type is ``i32``. The mask vector elements must be constant
integers or ``poison`` values. The result of the instruction is a vector
whose length is the same as the shuffle mask and whose element type is the
same as the element type of the first two operands.
Semantics:
""""""""""
The elements of the two input vectors are numbered from left to right
across both of the vectors. For each element of the result vector, the
shuffle mask selects an element from one of the input vectors to copy
to the result. Non-negative elements in the mask represent an index
into the concatenated pair of input vectors.
A ``poison`` element in the mask vector specifies that the resulting element
is ``poison``.
For backwards-compatibility reasons, LLVM temporarily also accepts ``undef``
mask elements, which will be interpreted the same way as ``poison`` elements.
If the shuffle mask selects an ``undef`` element from one of the input
vectors, the resulting element is ``undef``.
For scalable vectors, the only valid mask values at present are
``zeroinitializer``, ``undef`` and ``poison``, since we cannot write all indices as
literals for a vector with a length unknown at compile time.
Example:
""""""""
.. code-block:: text
<result> = shufflevector <4 x i32> %v1, <4 x i32> %v2,
<4 x i32> <i32 0, i32 4, i32 1, i32 5> ; yields <4 x i32>
<result> = shufflevector <4 x i32> %v1, <4 x i32> poison,
<4 x i32> <i32 0, i32 1, i32 2, i32 3> ; yields <4 x i32> - Identity shuffle.
<result> = shufflevector <8 x i32> %v1, <8 x i32> poison,
<4 x i32> <i32 0, i32 1, i32 2, i32 3> ; yields <4 x i32>
<result> = shufflevector <4 x i32> %v1, <4 x i32> %v2,
<8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7 > ; yields <8 x i32>
Aggregate Operations
--------------------
LLVM supports several instructions for working with
:ref:`aggregate <t_aggregate>` values.
.. _i_extractvalue:
'``extractvalue``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = extractvalue <aggregate type> <val>, <idx>{, <idx>}*
Overview:
"""""""""
The '``extractvalue``' instruction extracts the value of a member field
from an :ref:`aggregate <t_aggregate>` value.
Arguments:
""""""""""
The first operand of an '``extractvalue``' instruction is a value of
:ref:`struct <t_struct>` or :ref:`array <t_array>` type. The other operands are
constant indices to specify which value to extract in a similar manner
as indices in a '``getelementptr``' instruction.
The major differences to ``getelementptr`` indexing are:
- Since the value being indexed is not a pointer, the first index is
omitted and assumed to be zero.
- At least one index must be specified.
- Not only struct indices but also array indices must be in bounds.
Semantics:
""""""""""
The result is the value at the position in the aggregate specified by
the index operands.
Example:
""""""""
.. code-block:: text
<result> = extractvalue {i32, float} %agg, 0 ; yields i32
.. _i_insertvalue:
'``insertvalue``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = insertvalue <aggregate type> <val>, <ty> <elt>, <idx>{, <idx>}* ; yields <aggregate type>
Overview:
"""""""""
The '``insertvalue``' instruction inserts a value into a member field in
an :ref:`aggregate <t_aggregate>` value.
Arguments:
""""""""""
The first operand of an '``insertvalue``' instruction is a value of
:ref:`struct <t_struct>` or :ref:`array <t_array>` type. The second operand is
a first-class value to insert. The following operands are constant
indices indicating the position at which to insert the value in a
similar manner as indices in a '``extractvalue``' instruction. The value
to insert must have the same type as the value identified by the
indices.
Semantics:
""""""""""
The result is an aggregate of the same type as ``val``. Its value is
that of ``val`` except that the value at the position specified by the
indices is that of ``elt``.
Example:
""""""""
.. code-block:: llvm
%agg1 = insertvalue {i32, float} undef, i32 1, 0 ; yields {i32 1, float undef}
%agg2 = insertvalue {i32, float} %agg1, float %val, 1 ; yields {i32 1, float %val}
%agg3 = insertvalue {i32, {float}} undef, float %val, 1, 0 ; yields {i32 undef, {float %val}}
.. _memoryops:
Memory Access and Addressing Operations
---------------------------------------
A key design point of an SSA-based representation is how it represents
memory. In LLVM, no memory locations are in SSA form, which makes things
very simple. This section describes how to read, write, and allocate
memory in LLVM.
.. _i_alloca:
'``alloca``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = alloca [inalloca] <type> [, <ty> <NumElements>] [, align <alignment>] [, addrspace(<num>)] ; yields type addrspace(num)*:result
Overview:
"""""""""
The '``alloca``' instruction allocates memory on the stack frame of the
currently executing function, to be automatically released when this
function returns to its caller. If the address space is not explicitly
specified, the object is allocated in the alloca address space from the
:ref:`datalayout string<langref_datalayout>`.
Arguments:
""""""""""
The '``alloca``' instruction allocates ``sizeof(<type>)*NumElements``
bytes of memory on the runtime stack, returning a pointer of the
appropriate type to the program. If "NumElements" is specified, it is
the number of elements allocated, otherwise "NumElements" is defaulted
to be one.
If a constant alignment is specified, the value result of the
allocation is guaranteed to be aligned to at least that boundary. The
alignment may not be greater than ``1 << 32``.
The alignment is only optional when parsing textual IR; for in-memory IR,
it is always present. If not specified, the target can choose to align the
allocation on any convenient boundary compatible with the type.
'``type``' may be any sized type.
Structs containing scalable vectors cannot be used in allocas unless all
fields are the same scalable vector type (e.g. ``{<vscale x 2 x i32>,
<vscale x 2 x i32>}`` contains the same type while ``{<vscale x 2 x i32>,
<vscale x 2 x i64>}`` doesn't).
Semantics:
""""""""""
Memory is allocated; a pointer is returned. The allocated memory is
uninitialized, and loading from uninitialized memory produces an undefined
value. The operation itself is undefined if there is insufficient stack
space for the allocation.'``alloca``'d memory is automatically released
when the function returns. The '``alloca``' instruction is commonly used
to represent automatic variables that must have an address available. When
the function returns (either with the ``ret`` or ``resume`` instructions),
the memory is reclaimed. Allocating zero bytes is legal, but the returned
pointer may not be unique. The order in which memory is allocated (ie.,
which way the stack grows) is not specified.
Note that '``alloca``' outside of the alloca address space from the
:ref:`datalayout string<langref_datalayout>` is meaningful only if the
target has assigned it a semantics.
If the returned pointer is used by :ref:`llvm.lifetime.start <int_lifestart>`,
the returned object is initially dead.
See :ref:`llvm.lifetime.start <int_lifestart>` and
:ref:`llvm.lifetime.end <int_lifeend>` for the precise semantics of
lifetime-manipulating intrinsics.
Example:
""""""""
.. code-block:: llvm
%ptr = alloca i32 ; yields ptr
%ptr = alloca i32, i32 4 ; yields ptr
%ptr = alloca i32, i32 4, align 1024 ; yields ptr
%ptr = alloca i32, align 1024 ; yields ptr
.. _i_load:
'``load``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = load [volatile] <ty>, ptr <pointer>[, align <alignment>][, !nontemporal !<nontemp_node>][, !invariant.load !<empty_node>][, !invariant.group !<empty_node>][, !nonnull !<empty_node>][, !dereferenceable !<deref_bytes_node>][, !dereferenceable_or_null !<deref_bytes_node>][, !align !<align_node>][, !noundef !<empty_node>]
<result> = load atomic [volatile] <ty>, ptr <pointer> [syncscope("<target-scope>")] <ordering>, align <alignment> [, !invariant.group !<empty_node>]
!<nontemp_node> = !{ i32 1 }
!<empty_node> = !{}
!<deref_bytes_node> = !{ i64 <dereferenceable_bytes> }
!<align_node> = !{ i64 <value_alignment> }
Overview:
"""""""""
The '``load``' instruction is used to read from memory.
Arguments:
""""""""""
The argument to the ``load`` instruction specifies the memory address from which
to load. The type specified must be a :ref:`first class <t_firstclass>` type of
known size (i.e. not containing an :ref:`opaque structural type <t_opaque>`). If
the ``load`` is marked as ``volatile``, then the optimizer is not allowed to
modify the number or order of execution of this ``load`` with other
:ref:`volatile operations <volatile>`.
If the ``load`` is marked as ``atomic``, it takes an extra :ref:`ordering
<ordering>` and optional ``syncscope("<target-scope>")`` argument. The
``release`` and ``acq_rel`` orderings are not valid on ``load`` instructions.
Atomic loads produce :ref:`defined <memmodel>` results when they may see
multiple atomic stores. The type of the pointee must be an integer, pointer, or
floating-point type whose bit width is a power of two greater than or equal to
eight and less than or equal to a target-specific size limit. ``align`` must be
explicitly specified on atomic loads. Note: if the alignment is not greater or
equal to the size of the `<value>` type, the atomic operation is likely to
require a lock and have poor performance. ``!nontemporal`` does not have any
defined semantics for atomic loads.
The optional constant ``align`` argument specifies the alignment of the
operation (that is, the alignment of the memory address). It is the
responsibility of the code emitter to ensure that the alignment information is
correct. Overestimating the alignment results in undefined behavior.
Underestimating the alignment may produce less efficient code. An alignment of
1 is always safe. The maximum possible alignment is ``1 << 32``. An alignment
value higher than the size of the loaded type implies memory up to the
alignment value bytes can be safely loaded without trapping in the default
address space. Access of the high bytes can interfere with debugging tools, so
should not be accessed if the function has the ``sanitize_thread`` or
``sanitize_address`` attributes.
The alignment is only optional when parsing textual IR; for in-memory IR, it is
always present. An omitted ``align`` argument means that the operation has the
ABI alignment for the target.
The optional ``!nontemporal`` metadata must reference a single
metadata name ``<nontemp_node>`` corresponding to a metadata node with one
``i32`` entry of value 1. The existence of the ``!nontemporal``
metadata on the instruction tells the optimizer and code generator
that this load is not expected to be reused in the cache. The code
generator may select special instructions to save cache bandwidth, such
as the ``MOVNT`` instruction on x86.
The optional ``!invariant.load`` metadata must reference a single
metadata name ``<empty_node>`` corresponding to a metadata node with no
entries. If a load instruction tagged with the ``!invariant.load``
metadata is executed, the memory location referenced by the load has
to contain the same value at all points in the program where the
memory location is dereferenceable; otherwise, the behavior is
undefined.
The optional ``!invariant.group`` metadata must reference a single metadata name
``<empty_node>`` corresponding to a metadata node with no entries.
See ``invariant.group`` metadata :ref:`invariant.group <md_invariant.group>`.
The optional ``!nonnull`` metadata must reference a single
metadata name ``<empty_node>`` corresponding to a metadata node with no
entries. The existence of the ``!nonnull`` metadata on the
instruction tells the optimizer that the value loaded is known to
never be null. If the value is null at runtime, a poison value is returned
instead. This is analogous to the ``nonnull`` attribute on parameters and
return values. This metadata can only be applied to loads of a pointer type.
The optional ``!dereferenceable`` metadata must reference a single metadata
name ``<deref_bytes_node>`` corresponding to a metadata node with one ``i64``
entry.
See ``dereferenceable`` metadata :ref:`dereferenceable <md_dereferenceable>`.
The optional ``!dereferenceable_or_null`` metadata must reference a single
metadata name ``<deref_bytes_node>`` corresponding to a metadata node with one
``i64`` entry.
See ``dereferenceable_or_null`` metadata :ref:`dereferenceable_or_null
<md_dereferenceable_or_null>`.
The optional ``!align`` metadata must reference a single metadata name
``<align_node>`` corresponding to a metadata node with one ``i64`` entry.
The existence of the ``!align`` metadata on the instruction tells the
optimizer that the value loaded is known to be aligned to a boundary specified
by the integer value in the metadata node. The alignment must be a power of 2.
This is analogous to the ''align'' attribute on parameters and return values.
This metadata can only be applied to loads of a pointer type. If the returned
value is not appropriately aligned at runtime, a poison value is returned
instead.
The optional ``!noundef`` metadata must reference a single metadata name
``<empty_node>`` corresponding to a node with no entries. The existence of
``!noundef`` metadata on the instruction tells the optimizer that the value
loaded is known to be :ref:`well defined <welldefinedvalues>`.
If the value isn't well defined, the behavior is undefined. If the ``!noundef``
metadata is combined with poison-generating metadata like ``!nonnull``,
violation of that metadata constraint will also result in undefined behavior.
Semantics:
""""""""""
The location of memory pointed to is loaded. If the value being loaded
is of scalar type then the number of bytes read does not exceed the
minimum number of bytes needed to hold all bits of the type. For
example, loading an ``i24`` reads at most three bytes. When loading a
value of a type like ``i20`` with a size that is not an integral number
of bytes, the result is undefined if the value was not originally
written using a store of the same type.
If the value being loaded is of aggregate type, the bytes that correspond to
padding may be accessed but are ignored, because it is impossible to observe
padding from the loaded aggregate value.
If ``<pointer>`` is not a well-defined value, the behavior is undefined.
Examples:
"""""""""
.. code-block:: llvm
%ptr = alloca i32 ; yields ptr
store i32 3, ptr %ptr ; yields void
%val = load i32, ptr %ptr ; yields i32:val = i32 3
.. _i_store:
'``store``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
store [volatile] <ty> <value>, ptr <pointer>[, align <alignment>][, !nontemporal !<nontemp_node>][, !invariant.group !<empty_node>] ; yields void
store atomic [volatile] <ty> <value>, ptr <pointer> [syncscope("<target-scope>")] <ordering>, align <alignment> [, !invariant.group !<empty_node>] ; yields void
!<nontemp_node> = !{ i32 1 }
!<empty_node> = !{}
Overview:
"""""""""
The '``store``' instruction is used to write to memory.
Arguments:
""""""""""
There are two arguments to the ``store`` instruction: a value to store and an
address at which to store it. The type of the ``<pointer>`` operand must be a
pointer to the :ref:`first class <t_firstclass>` type of the ``<value>``
operand. If the ``store`` is marked as ``volatile``, then the optimizer is not
allowed to modify the number or order of execution of this ``store`` with other
:ref:`volatile operations <volatile>`. Only values of :ref:`first class
<t_firstclass>` types of known size (i.e. not containing an :ref:`opaque
structural type <t_opaque>`) can be stored.
If the ``store`` is marked as ``atomic``, it takes an extra :ref:`ordering
<ordering>` and optional ``syncscope("<target-scope>")`` argument. The
``acquire`` and ``acq_rel`` orderings aren't valid on ``store`` instructions.
Atomic loads produce :ref:`defined <memmodel>` results when they may see
multiple atomic stores. The type of the pointee must be an integer, pointer, or
floating-point type whose bit width is a power of two greater than or equal to
eight and less than or equal to a target-specific size limit. ``align`` must be
explicitly specified on atomic stores. Note: if the alignment is not greater or
equal to the size of the `<value>` type, the atomic operation is likely to
require a lock and have poor performance. ``!nontemporal`` does not have any
defined semantics for atomic stores.
The optional constant ``align`` argument specifies the alignment of the
operation (that is, the alignment of the memory address). It is the
responsibility of the code emitter to ensure that the alignment information is
correct. Overestimating the alignment results in undefined behavior.
Underestimating the alignment may produce less efficient code. An alignment of
1 is always safe. The maximum possible alignment is ``1 << 32``. An alignment
value higher than the size of the loaded type implies memory up to the
alignment value bytes can be safely loaded without trapping in the default
address space. Access of the high bytes can interfere with debugging tools, so
should not be accessed if the function has the ``sanitize_thread`` or
``sanitize_address`` attributes.
The alignment is only optional when parsing textual IR; for in-memory IR, it is
always present. An omitted ``align`` argument means that the operation has the
ABI alignment for the target.
The optional ``!nontemporal`` metadata must reference a single metadata
name ``<nontemp_node>`` corresponding to a metadata node with one ``i32`` entry
of value 1. The existence of the ``!nontemporal`` metadata on the instruction
tells the optimizer and code generator that this load is not expected to
be reused in the cache. The code generator may select special
instructions to save cache bandwidth, such as the ``MOVNT`` instruction on
x86.
The optional ``!invariant.group`` metadata must reference a
single metadata name ``<empty_node>``. See ``invariant.group`` metadata.
Semantics:
""""""""""
The contents of memory are updated to contain ``<value>`` at the
location specified by the ``<pointer>`` operand. If ``<value>`` is
of scalar type then the number of bytes written does not exceed the
minimum number of bytes needed to hold all bits of the type. For
example, storing an ``i24`` writes at most three bytes. When writing a
value of a type like ``i20`` with a size that is not an integral number
of bytes, it is unspecified what happens to the extra bits that do not
belong to the type, but they will typically be overwritten.
If ``<value>`` is of aggregate type, padding is filled with
:ref:`undef <undefvalues>`.
If ``<pointer>`` is not a well-defined value, the behavior is undefined.
Example:
""""""""
.. code-block:: llvm
%ptr = alloca i32 ; yields ptr
store i32 3, ptr %ptr ; yields void
%val = load i32, ptr %ptr ; yields i32:val = i32 3
.. _i_fence:
'``fence``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
fence [syncscope("<target-scope>")] <ordering> ; yields void
Overview:
"""""""""
The '``fence``' instruction is used to introduce happens-before edges
between operations.
Arguments:
""""""""""
'``fence``' instructions take an :ref:`ordering <ordering>` argument which
defines what *synchronizes-with* edges they add. They can only be given
``acquire``, ``release``, ``acq_rel``, and ``seq_cst`` orderings.
Semantics:
""""""""""
A fence A which has (at least) ``release`` ordering semantics
*synchronizes with* a fence B with (at least) ``acquire`` ordering
semantics if and only if there exist atomic operations X and Y, both
operating on some atomic object M, such that A is sequenced before X, X
modifies M (either directly or through some side effect of a sequence
headed by X), Y is sequenced before B, and Y observes M. This provides a
*happens-before* dependency between A and B. Rather than an explicit
``fence``, one (but not both) of the atomic operations X or Y might
provide a ``release`` or ``acquire`` (resp.) ordering constraint and
still *synchronize-with* the explicit ``fence`` and establish the
*happens-before* edge.
A ``fence`` which has ``seq_cst`` ordering, in addition to having both
``acquire`` and ``release`` semantics specified above, participates in
the global program order of other ``seq_cst`` operations and/or fences.
A ``fence`` instruction can also take an optional
":ref:`syncscope <syncscope>`" argument.
Example:
""""""""
.. code-block:: text
fence acquire ; yields void
fence syncscope("singlethread") seq_cst ; yields void
fence syncscope("agent") seq_cst ; yields void
.. _i_cmpxchg:
'``cmpxchg``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
cmpxchg [weak] [volatile] ptr <pointer>, <ty> <cmp>, <ty> <new> [syncscope("<target-scope>")] <success ordering> <failure ordering>[, align <alignment>] ; yields { ty, i1 }
Overview:
"""""""""
The '``cmpxchg``' instruction is used to atomically modify memory. It
loads a value in memory and compares it to a given value. If they are
equal, it tries to store a new value into the memory.
Arguments:
""""""""""
There are three arguments to the '``cmpxchg``' instruction: an address
to operate on, a value to compare to the value currently be at that
address, and a new value to place at that address if the compared values
are equal. The type of '<cmp>' must be an integer or pointer type whose
bit width is a power of two greater than or equal to eight and less
than or equal to a target-specific size limit. '<cmp>' and '<new>' must
have the same type, and the type of '<pointer>' must be a pointer to
that type. If the ``cmpxchg`` is marked as ``volatile``, then the
optimizer is not allowed to modify the number or order of execution of
this ``cmpxchg`` with other :ref:`volatile operations <volatile>`.
The success and failure :ref:`ordering <ordering>` arguments specify how this
``cmpxchg`` synchronizes with other atomic operations. Both ordering parameters
must be at least ``monotonic``, the failure ordering cannot be either
``release`` or ``acq_rel``.
A ``cmpxchg`` instruction can also take an optional
":ref:`syncscope <syncscope>`" argument.
Note: if the alignment is not greater or equal to the size of the `<value>`
type, the atomic operation is likely to require a lock and have poor
performance.
The alignment is only optional when parsing textual IR; for in-memory IR, it is
always present. If unspecified, the alignment is assumed to be equal to the
size of the '<value>' type. Note that this default alignment assumption is
different from the alignment used for the load/store instructions when align
isn't specified.
The pointer passed into cmpxchg must have alignment greater than or
equal to the size in memory of the operand.
Semantics:
""""""""""
The contents of memory at the location specified by the '``<pointer>``' operand
is read and compared to '``<cmp>``'; if the values are equal, '``<new>``' is
written to the location. The original value at the location is returned,
together with a flag indicating success (true) or failure (false).
If the cmpxchg operation is marked as ``weak`` then a spurious failure is
permitted: the operation may not write ``<new>`` even if the comparison
matched.
If the cmpxchg operation is strong (the default), the i1 value is 1 if and only
if the value loaded equals ``cmp``.
A successful ``cmpxchg`` is a read-modify-write instruction for the purpose of
identifying release sequences. A failed ``cmpxchg`` is equivalent to an atomic
load with an ordering parameter determined the second ordering parameter.
Example:
""""""""
.. code-block:: llvm
entry:
%orig = load atomic i32, ptr %ptr unordered, align 4 ; yields i32
br label %loop
loop:
%cmp = phi i32 [ %orig, %entry ], [%value_loaded, %loop]
%squared = mul i32 %cmp, %cmp
%val_success = cmpxchg ptr %ptr, i32 %cmp, i32 %squared acq_rel monotonic ; yields { i32, i1 }
%value_loaded = extractvalue { i32, i1 } %val_success, 0
%success = extractvalue { i32, i1 } %val_success, 1
br i1 %success, label %done, label %loop
done:
...
.. _i_atomicrmw:
'``atomicrmw``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
atomicrmw [volatile] <operation> ptr <pointer>, <ty> <value> [syncscope("<target-scope>")] <ordering>[, align <alignment>] ; yields ty
Overview:
"""""""""
The '``atomicrmw``' instruction is used to atomically modify memory.
Arguments:
""""""""""
There are three arguments to the '``atomicrmw``' instruction: an
operation to apply, an address whose value to modify, an argument to the
operation. The operation must be one of the following keywords:
- xchg
- add
- sub
- and
- nand
- or
- xor
- max
- min
- umax
- umin
- fadd
- fsub
- fmax
- fmin
- uinc_wrap
- udec_wrap
For most of these operations, the type of '<value>' must be an integer
type whose bit width is a power of two greater than or equal to eight
and less than or equal to a target-specific size limit. For xchg, this
may also be a floating point or a pointer type with the same size constraints
as integers. For fadd/fsub/fmax/fmin, this must be a floating point type. The
type of the '``<pointer>``' operand must be a pointer to that type. If
the ``atomicrmw`` is marked as ``volatile``, then the optimizer is not
allowed to modify the number or order of execution of this
``atomicrmw`` with other :ref:`volatile operations <volatile>`.
Note: if the alignment is not greater or equal to the size of the `<value>`
type, the atomic operation is likely to require a lock and have poor
performance.
The alignment is only optional when parsing textual IR; for in-memory IR, it is
always present. If unspecified, the alignment is assumed to be equal to the
size of the '<value>' type. Note that this default alignment assumption is
different from the alignment used for the load/store instructions when align
isn't specified.
A ``atomicrmw`` instruction can also take an optional
":ref:`syncscope <syncscope>`" argument.
Semantics:
""""""""""
The contents of memory at the location specified by the '``<pointer>``'
operand are atomically read, modified, and written back. The original
value at the location is returned. The modification is specified by the
operation argument:
- xchg: ``*ptr = val``
- add: ``*ptr = *ptr + val``
- sub: ``*ptr = *ptr - val``
- and: ``*ptr = *ptr & val``
- nand: ``*ptr = ~(*ptr & val)``
- or: ``*ptr = *ptr | val``
- xor: ``*ptr = *ptr ^ val``
- max: ``*ptr = *ptr > val ? *ptr : val`` (using a signed comparison)
- min: ``*ptr = *ptr < val ? *ptr : val`` (using a signed comparison)
- umax: ``*ptr = *ptr > val ? *ptr : val`` (using an unsigned comparison)
- umin: ``*ptr = *ptr < val ? *ptr : val`` (using an unsigned comparison)
- fadd: ``*ptr = *ptr + val`` (using floating point arithmetic)
- fsub: ``*ptr = *ptr - val`` (using floating point arithmetic)
- fmax: ``*ptr = maxnum(*ptr, val)`` (match the `llvm.maxnum.*`` intrinsic)
- fmin: ``*ptr = minnum(*ptr, val)`` (match the `llvm.minnum.*`` intrinsic)
- uinc_wrap: ``*ptr = (*ptr u>= val) ? 0 : (*ptr + 1)`` (increment value with wraparound to zero when incremented above input value)
- udec_wrap: ``*ptr = ((*ptr == 0) || (*ptr u> val)) ? val : (*ptr - 1)`` (decrement with wraparound to input value when decremented below zero).
Example:
""""""""
.. code-block:: llvm
%old = atomicrmw add ptr %ptr, i32 1 acquire ; yields i32
.. _i_getelementptr:
'``getelementptr``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = getelementptr <ty>, ptr <ptrval>{, [inrange] <ty> <idx>}*
<result> = getelementptr inbounds <ty>, ptr <ptrval>{, [inrange] <ty> <idx>}*
<result> = getelementptr <ty>, <N x ptr> <ptrval>, [inrange] <vector index type> <idx>
Overview:
"""""""""
The '``getelementptr``' instruction is used to get the address of a
subelement of an :ref:`aggregate <t_aggregate>` data structure. It performs
address calculation only and does not access memory. The instruction can also
be used to calculate a vector of such addresses.
Arguments:
""""""""""
The first argument is always a type used as the basis for the calculations.
The second argument is always a pointer or a vector of pointers, and is the
base address to start from. The remaining arguments are indices
that indicate which of the elements of the aggregate object are indexed.
The interpretation of each index is dependent on the type being indexed
into. The first index always indexes the pointer value given as the
second argument, the second index indexes a value of the type pointed to
(not necessarily the value directly pointed to, since the first index
can be non-zero), etc. The first type indexed into must be a pointer
value, subsequent types can be arrays, vectors, and structs. Note that
subsequent types being indexed into can never be pointers, since that
would require loading the pointer before continuing calculation.
The type of each index argument depends on the type it is indexing into.
When indexing into a (optionally packed) structure, only ``i32`` integer
**constants** are allowed (when using a vector of indices they must all
be the **same** ``i32`` integer constant). When indexing into an array,
pointer or vector, integers of any width are allowed, and they are not
required to be constant. These integers are treated as signed values
where relevant.
For example, let's consider a C code fragment and how it gets compiled
to LLVM:
.. code-block:: c
struct RT {
char A;
int B[10][20];
char C;
};
struct ST {
int X;
double Y;
struct RT Z;
};
int *foo(struct ST *s) {
return &s[1].Z.B[5][13];
}
The LLVM code generated by Clang is approximately:
.. code-block:: llvm
%struct.RT = type { i8, [10 x [20 x i32]], i8 }
%struct.ST = type { i32, double, %struct.RT }
define ptr @foo(ptr %s) {
entry:
%arrayidx = getelementptr inbounds %struct.ST, ptr %s, i64 1, i32 2, i32 1, i64 5, i64 13
ret ptr %arrayidx
}
Semantics:
""""""""""
In the example above, the first index is indexing into the
'``%struct.ST*``' type, which is a pointer, yielding a '``%struct.ST``'
= '``{ i32, double, %struct.RT }``' type, a structure. The second index
indexes into the third element of the structure, yielding a
'``%struct.RT``' = '``{ i8 , [10 x [20 x i32]], i8 }``' type, another
structure. The third index indexes into the second element of the
structure, yielding a '``[10 x [20 x i32]]``' type, an array. The two
dimensions of the array are subscripted into, yielding an '``i32``'
type. The '``getelementptr``' instruction returns a pointer to this
element.
Note that it is perfectly legal to index partially through a structure,
returning a pointer to an inner element. Because of this, the LLVM code
for the given testcase is equivalent to:
.. code-block:: llvm
define ptr @foo(ptr %s) {
%t1 = getelementptr %struct.ST, ptr %s, i32 1
%t2 = getelementptr %struct.ST, ptr %t1, i32 0, i32 2
%t3 = getelementptr %struct.RT, ptr %t2, i32 0, i32 1
%t4 = getelementptr [10 x [20 x i32]], ptr %t3, i32 0, i32 5
%t5 = getelementptr [20 x i32], ptr %t4, i32 0, i32 13
ret ptr %t5
}
The indices are first converted to offsets in the pointer's index type. If the
currently indexed type is a struct type, the struct offset corresponding to the
index is sign-extended or truncated to the pointer index type. Otherwise, the
index itself is sign-extended or truncated, and then multiplied by the type
allocation size (that is, the size rounded up to the ABI alignment) of the
currently indexed type.
The offsets are then added to the low bits of the base address up to the index
type width, with silently-wrapping two's complement arithmetic. If the pointer
size is larger than the index size, this means that the bits outside the index
type width will not be affected.
The result value of the ``getelementptr`` may be outside the object pointed
to by the base pointer. The result value may not necessarily be used to access
memory though, even if it happens to point into allocated storage. See the
:ref:`Pointer Aliasing Rules <pointeraliasing>` section for more
information.
If the ``inbounds`` keyword is present, the result value of a
``getelementptr`` with any non-zero indices is a
:ref:`poison value <poisonvalues>` if one of the following rules is violated:
* The base pointer has an *in bounds* address of an allocated object, which
means that it points into an allocated object, or to its end. Note that the
object does not have to be live anymore; being in-bounds of a deallocated
object is sufficient.
* If the type of an index is larger than the pointer index type, the
truncation to the pointer index type preserves the signed value.
* The multiplication of an index by the type size does not wrap the pointer
index type in a signed sense (``nsw``).
* The successive addition of each offset (without adding the base address) does
not wrap the pointer index type in a signed sense (``nsw``).
* The successive addition of the current address, interpreted as an unsigned
number, and each offset, interpreted as a signed number, does not wrap the
unsigned address space and remains *in bounds* of the allocated object.
As a corollary, if the added offset is non-negative, the addition does not
wrap in an unsigned sense (``nuw``).
* In cases where the base is a vector of pointers, the ``inbounds`` keyword
applies to each of the computations element-wise.
Note that ``getelementptr`` with all-zero indices is always considered to be
``inbounds``, even if the base pointer does not point to an allocated object.
As a corollary, the only pointer in bounds of the null pointer in the default
address space is the null pointer itself.
These rules are based on the assumption that no allocated object may cross
the unsigned address space boundary, and no allocated object may be larger
than half the pointer index type space.
If the ``inrange`` keyword is present before any index, loading from or
storing to any pointer derived from the ``getelementptr`` has undefined
behavior if the load or store would access memory outside of the bounds of
the element selected by the index marked as ``inrange``. The result of a
pointer comparison or ``ptrtoint`` (including ``ptrtoint``-like operations
involving memory) involving a pointer derived from a ``getelementptr`` with
the ``inrange`` keyword is undefined, with the exception of comparisons
in the case where both operands are in the range of the element selected
by the ``inrange`` keyword, inclusive of the address one past the end of
that element. Note that the ``inrange`` keyword is currently only allowed
in constant ``getelementptr`` expressions.
The getelementptr instruction is often confusing. For some more insight
into how it works, see :doc:`the getelementptr FAQ <GetElementPtr>`.
Example:
""""""""
.. code-block:: llvm
%aptr = getelementptr {i32, [12 x i8]}, ptr %saptr, i64 0, i32 1
%vptr = getelementptr {i32, <2 x i8>}, ptr %svptr, i64 0, i32 1, i32 1
%eptr = getelementptr [12 x i8], ptr %aptr, i64 0, i32 1
%iptr = getelementptr [10 x i32], ptr @arr, i16 0, i16 0
Vector of pointers:
"""""""""""""""""""
The ``getelementptr`` returns a vector of pointers, instead of a single address,
when one or more of its arguments is a vector. In such cases, all vector
arguments should have the same number of elements, and every scalar argument
will be effectively broadcast into a vector during address calculation.
.. code-block:: llvm
; All arguments are vectors:
; A[i] = ptrs[i] + offsets[i]*sizeof(i8)
%A = getelementptr i8, <4 x i8*> %ptrs, <4 x i64> %offsets
; Add the same scalar offset to each pointer of a vector:
; A[i] = ptrs[i] + offset*sizeof(i8)
%A = getelementptr i8, <4 x ptr> %ptrs, i64 %offset
; Add distinct offsets to the same pointer:
; A[i] = ptr + offsets[i]*sizeof(i8)
%A = getelementptr i8, ptr %ptr, <4 x i64> %offsets
; In all cases described above the type of the result is <4 x ptr>
The two following instructions are equivalent:
.. code-block:: llvm
getelementptr %struct.ST, <4 x ptr> %s, <4 x i64> %ind1,
<4 x i32> <i32 2, i32 2, i32 2, i32 2>,
<4 x i32> <i32 1, i32 1, i32 1, i32 1>,
<4 x i32> %ind4,
<4 x i64> <i64 13, i64 13, i64 13, i64 13>
getelementptr %struct.ST, <4 x ptr> %s, <4 x i64> %ind1,
i32 2, i32 1, <4 x i32> %ind4, i64 13
Let's look at the C code, where the vector version of ``getelementptr``
makes sense:
.. code-block:: c
// Let's assume that we vectorize the following loop:
double *A, *B; int *C;
for (int i = 0; i < size; ++i) {
A[i] = B[C[i]];
}
.. code-block:: llvm
; get pointers for 8 elements from array B
%ptrs = getelementptr double, ptr %B, <8 x i32> %C
; load 8 elements from array B into A
%A = call <8 x double> @llvm.masked.gather.v8f64.v8p0f64(<8 x ptr> %ptrs,
i32 8, <8 x i1> %mask, <8 x double> %passthru)
Conversion Operations
---------------------
The instructions in this category are the conversion instructions
(casting) which all take a single operand and a type. They perform
various bit conversions on the operand.
.. _i_trunc:
'``trunc .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = trunc <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``trunc``' instruction truncates its operand to the type ``ty2``.
Arguments:
""""""""""
The '``trunc``' instruction takes a value to trunc, and a type to trunc
it to. Both types must be of :ref:`integer <t_integer>` types, or vectors
of the same number of integers. The bit size of the ``value`` must be
larger than the bit size of the destination type, ``ty2``. Equal sized
types are not allowed.
Semantics:
""""""""""
The '``trunc``' instruction truncates the high order bits in ``value``
and converts the remaining bits to ``ty2``. Since the source size must
be larger than the destination size, ``trunc`` cannot be a *no-op cast*.
It will always truncate bits.
Example:
""""""""
.. code-block:: llvm
%X = trunc i32 257 to i8 ; yields i8:1
%Y = trunc i32 123 to i1 ; yields i1:true
%Z = trunc i32 122 to i1 ; yields i1:false
%W = trunc <2 x i16> <i16 8, i16 7> to <2 x i8> ; yields <i8 8, i8 7>
.. _i_zext:
'``zext .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = zext <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``zext``' instruction zero extends its operand to type ``ty2``.
The ``nneg`` (non-negative) flag, if present, specifies that the operand is
non-negative. This property may be used by optimization passes to later
convert the ``zext`` into a ``sext``.
Arguments:
""""""""""
The '``zext``' instruction takes a value to cast, and a type to cast it
to. Both types must be of :ref:`integer <t_integer>` types, or vectors of
the same number of integers. The bit size of the ``value`` must be
smaller than the bit size of the destination type, ``ty2``.
Semantics:
""""""""""
The ``zext`` fills the high order bits of the ``value`` with zero bits
until it reaches the size of the destination type, ``ty2``.
When zero extending from i1, the result will always be either 0 or 1.
If the ``nneg`` flag is set, and the ``zext`` argument is negative, the result
is a poison value.
Example:
""""""""
.. code-block:: llvm
%X = zext i32 257 to i64 ; yields i64:257
%Y = zext i1 true to i32 ; yields i32:1
%Z = zext <2 x i16> <i16 8, i16 7> to <2 x i32> ; yields <i32 8, i32 7>
%a = zext nneg i8 127 to i16 ; yields i16 127
%b = zext nneg i8 -1 to i16 ; yields i16 poison
.. _i_sext:
'``sext .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = sext <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``sext``' sign extends ``value`` to the type ``ty2``.
Arguments:
""""""""""
The '``sext``' instruction takes a value to cast, and a type to cast it
to. Both types must be of :ref:`integer <t_integer>` types, or vectors of
the same number of integers. The bit size of the ``value`` must be
smaller than the bit size of the destination type, ``ty2``.
Semantics:
""""""""""
The '``sext``' instruction performs a sign extension by copying the sign
bit (highest order bit) of the ``value`` until it reaches the bit size
of the type ``ty2``.
When sign extending from i1, the extension always results in -1 or 0.
Example:
""""""""
.. code-block:: llvm
%X = sext i8 -1 to i16 ; yields i16 :65535
%Y = sext i1 true to i32 ; yields i32:-1
%Z = sext <2 x i16> <i16 8, i16 7> to <2 x i32> ; yields <i32 8, i32 7>
'``fptrunc .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fptrunc <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``fptrunc``' instruction truncates ``value`` to type ``ty2``.
Arguments:
""""""""""
The '``fptrunc``' instruction takes a :ref:`floating-point <t_floating>`
value to cast and a :ref:`floating-point <t_floating>` type to cast it to.
The size of ``value`` must be larger than the size of ``ty2``. This
implies that ``fptrunc`` cannot be used to make a *no-op cast*.
Semantics:
""""""""""
The '``fptrunc``' instruction casts a ``value`` from a larger
:ref:`floating-point <t_floating>` type to a smaller :ref:`floating-point
<t_floating>` type.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`.
NaN values follow the usual :ref:`NaN behaviors <floatnan>`, except that _if_ a
NaN payload is propagated from the input ("Quieting NaN propagation" or
"Unchanged NaN propagation" cases), then the low order bits of the NaN payload
which cannot fit in the resulting type are discarded. Note that if discarding
the low order bits leads to an all-0 payload, this cannot be represented as a
signaling NaN (it would represent an infinity instead), so in that case
"Unchanged NaN propagation" is not possible.
Example:
""""""""
.. code-block:: llvm
%X = fptrunc double 16777217.0 to float ; yields float:16777216.0
%Y = fptrunc double 1.0E+300 to half ; yields half:+infinity
'``fpext .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fpext <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``fpext``' extends a floating-point ``value`` to a larger floating-point
value.
Arguments:
""""""""""
The '``fpext``' instruction takes a :ref:`floating-point <t_floating>`
``value`` to cast, and a :ref:`floating-point <t_floating>` type to cast it
to. The source type must be smaller than the destination type.
Semantics:
""""""""""
The '``fpext``' instruction extends the ``value`` from a smaller
:ref:`floating-point <t_floating>` type to a larger :ref:`floating-point
<t_floating>` type. The ``fpext`` cannot be used to make a
*no-op cast* because it always changes bits. Use ``bitcast`` to make a
*no-op cast* for a floating-point cast.
NaN values follow the usual :ref:`NaN behaviors <floatnan>`, except that _if_ a
NaN payload is propagated from the input ("Quieting NaN propagation" or
"Unchanged NaN propagation" cases), then it is copied to the high order bits of
the resulting payload, and the remaining low order bits are zero.
Example:
""""""""
.. code-block:: llvm
%X = fpext float 3.125 to double ; yields double:3.125000e+00
%Y = fpext double %X to fp128 ; yields fp128:0xL00000000000000004000900000000000
'``fptoui .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fptoui <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``fptoui``' converts a floating-point ``value`` to its unsigned
integer equivalent of type ``ty2``.
Arguments:
""""""""""
The '``fptoui``' instruction takes a value to cast, which must be a
scalar or vector :ref:`floating-point <t_floating>` value, and a type to
cast it to ``ty2``, which must be an :ref:`integer <t_integer>` type. If
``ty`` is a vector floating-point type, ``ty2`` must be a vector integer
type with the same number of elements as ``ty``
Semantics:
""""""""""
The '``fptoui``' instruction converts its :ref:`floating-point
<t_floating>` operand into the nearest (rounding towards zero)
unsigned integer value. If the value cannot fit in ``ty2``, the result
is a :ref:`poison value <poisonvalues>`.
Example:
""""""""
.. code-block:: llvm
%X = fptoui double 123.0 to i32 ; yields i32:123
%Y = fptoui float 1.0E+300 to i1 ; yields undefined:1
%Z = fptoui float 1.04E+17 to i8 ; yields undefined:1
'``fptosi .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fptosi <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``fptosi``' instruction converts :ref:`floating-point <t_floating>`
``value`` to type ``ty2``.
Arguments:
""""""""""
The '``fptosi``' instruction takes a value to cast, which must be a
scalar or vector :ref:`floating-point <t_floating>` value, and a type to
cast it to ``ty2``, which must be an :ref:`integer <t_integer>` type. If
``ty`` is a vector floating-point type, ``ty2`` must be a vector integer
type with the same number of elements as ``ty``
Semantics:
""""""""""
The '``fptosi``' instruction converts its :ref:`floating-point
<t_floating>` operand into the nearest (rounding towards zero)
signed integer value. If the value cannot fit in ``ty2``, the result
is a :ref:`poison value <poisonvalues>`.
Example:
""""""""
.. code-block:: llvm
%X = fptosi double -123.0 to i32 ; yields i32:-123
%Y = fptosi float 1.0E-247 to i1 ; yields undefined:1
%Z = fptosi float 1.04E+17 to i8 ; yields undefined:1
'``uitofp .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = uitofp <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``uitofp``' instruction regards ``value`` as an unsigned integer
and converts that value to the ``ty2`` type.
Arguments:
""""""""""
The '``uitofp``' instruction takes a value to cast, which must be a
scalar or vector :ref:`integer <t_integer>` value, and a type to cast it to
``ty2``, which must be an :ref:`floating-point <t_floating>` type. If
``ty`` is a vector integer type, ``ty2`` must be a vector floating-point
type with the same number of elements as ``ty``
Semantics:
""""""""""
The '``uitofp``' instruction interprets its operand as an unsigned
integer quantity and converts it to the corresponding floating-point
value. If the value cannot be exactly represented, it is rounded using
the default rounding mode.
Example:
""""""""
.. code-block:: llvm
%X = uitofp i32 257 to float ; yields float:257.0
%Y = uitofp i8 -1 to double ; yields double:255.0
'``sitofp .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = sitofp <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``sitofp``' instruction regards ``value`` as a signed integer and
converts that value to the ``ty2`` type.
Arguments:
""""""""""
The '``sitofp``' instruction takes a value to cast, which must be a
scalar or vector :ref:`integer <t_integer>` value, and a type to cast it to
``ty2``, which must be an :ref:`floating-point <t_floating>` type. If
``ty`` is a vector integer type, ``ty2`` must be a vector floating-point
type with the same number of elements as ``ty``
Semantics:
""""""""""
The '``sitofp``' instruction interprets its operand as a signed integer
quantity and converts it to the corresponding floating-point value. If the
value cannot be exactly represented, it is rounded using the default rounding
mode.
Example:
""""""""
.. code-block:: llvm
%X = sitofp i32 257 to float ; yields float:257.0
%Y = sitofp i8 -1 to double ; yields double:-1.0
.. _i_ptrtoint:
'``ptrtoint .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = ptrtoint <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``ptrtoint``' instruction converts the pointer or a vector of
pointers ``value`` to the integer (or vector of integers) type ``ty2``.
Arguments:
""""""""""
The '``ptrtoint``' instruction takes a ``value`` to cast, which must be
a value of type :ref:`pointer <t_pointer>` or a vector of pointers, and a
type to cast it to ``ty2``, which must be an :ref:`integer <t_integer>` or
a vector of integers type.
Semantics:
""""""""""
The '``ptrtoint``' instruction converts ``value`` to integer type
``ty2`` by interpreting the pointer value as an integer and either
truncating or zero extending that value to the size of the integer type.
If ``value`` is smaller than ``ty2`` then a zero extension is done. If
``value`` is larger than ``ty2`` then a truncation is done. If they are
the same size, then nothing is done (*no-op cast*) other than a type
change.
Example:
""""""""
.. code-block:: llvm
%X = ptrtoint ptr %P to i8 ; yields truncation on 32-bit architecture
%Y = ptrtoint ptr %P to i64 ; yields zero extension on 32-bit architecture
%Z = ptrtoint <4 x ptr> %P to <4 x i64>; yields vector zero extension for a vector of addresses on 32-bit architecture
.. _i_inttoptr:
'``inttoptr .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = inttoptr <ty> <value> to <ty2>[, !dereferenceable !<deref_bytes_node>][, !dereferenceable_or_null !<deref_bytes_node>] ; yields ty2
Overview:
"""""""""
The '``inttoptr``' instruction converts an integer ``value`` to a
pointer type, ``ty2``.
Arguments:
""""""""""
The '``inttoptr``' instruction takes an :ref:`integer <t_integer>` value to
cast, and a type to cast it to, which must be a :ref:`pointer <t_pointer>`
type.
The optional ``!dereferenceable`` metadata must reference a single metadata
name ``<deref_bytes_node>`` corresponding to a metadata node with one ``i64``
entry.
See ``dereferenceable`` metadata.
The optional ``!dereferenceable_or_null`` metadata must reference a single
metadata name ``<deref_bytes_node>`` corresponding to a metadata node with one
``i64`` entry.
See ``dereferenceable_or_null`` metadata.
Semantics:
""""""""""
The '``inttoptr``' instruction converts ``value`` to type ``ty2`` by
applying either a zero extension or a truncation depending on the size
of the integer ``value``. If ``value`` is larger than the size of a
pointer then a truncation is done. If ``value`` is smaller than the size
of a pointer then a zero extension is done. If they are the same size,
nothing is done (*no-op cast*).
Example:
""""""""
.. code-block:: llvm
%X = inttoptr i32 255 to ptr ; yields zero extension on 64-bit architecture
%Y = inttoptr i32 255 to ptr ; yields no-op on 32-bit architecture
%Z = inttoptr i64 0 to ptr ; yields truncation on 32-bit architecture
%Z = inttoptr <4 x i32> %G to <4 x ptr>; yields truncation of vector G to four pointers
.. _i_bitcast:
'``bitcast .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = bitcast <ty> <value> to <ty2> ; yields ty2
Overview:
"""""""""
The '``bitcast``' instruction converts ``value`` to type ``ty2`` without
changing any bits.
Arguments:
""""""""""
The '``bitcast``' instruction takes a value to cast, which must be a
non-aggregate first class value, and a type to cast it to, which must
also be a non-aggregate :ref:`first class <t_firstclass>` type. The
bit sizes of ``value`` and the destination type, ``ty2``, must be
identical. If the source type is a pointer, the destination type must
also be a pointer of the same size. This instruction supports bitwise
conversion of vectors to integers and to vectors of other types (as
long as they have the same size).
Semantics:
""""""""""
The '``bitcast``' instruction converts ``value`` to type ``ty2``. It
is always a *no-op cast* because no bits change with this
conversion. The conversion is done as if the ``value`` had been stored
to memory and read back as type ``ty2``. Pointer (or vector of
pointers) types may only be converted to other pointer (or vector of
pointers) types with the same address space through this instruction.
To convert pointers to other types, use the :ref:`inttoptr <i_inttoptr>`
or :ref:`ptrtoint <i_ptrtoint>` instructions first.
There is a caveat for bitcasts involving vector types in relation to
endianness. For example ``bitcast <2 x i8> <value> to i16`` puts element zero
of the vector in the least significant bits of the i16 for little-endian while
element zero ends up in the most significant bits for big-endian.
Example:
""""""""
.. code-block:: text
%X = bitcast i8 255 to i8 ; yields i8 :-1
%Y = bitcast i32* %x to i16* ; yields i16*:%x
%Z = bitcast <2 x i32> %V to i64; ; yields i64: %V (depends on endianness)
%Z = bitcast <2 x i32*> %V to <2 x i64*> ; yields <2 x i64*>
.. _i_addrspacecast:
'``addrspacecast .. to``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = addrspacecast <pty> <ptrval> to <pty2> ; yields pty2
Overview:
"""""""""
The '``addrspacecast``' instruction converts ``ptrval`` from ``pty`` in
address space ``n`` to type ``pty2`` in address space ``m``.
Arguments:
""""""""""
The '``addrspacecast``' instruction takes a pointer or vector of pointer value
to cast and a pointer type to cast it to, which must have a different
address space.
Semantics:
""""""""""
The '``addrspacecast``' instruction converts the pointer value
``ptrval`` to type ``pty2``. It can be a *no-op cast* or a complex
value modification, depending on the target and the address space
pair. Pointer conversions within the same address space must be
performed with the ``bitcast`` instruction. Note that if the address
space conversion produces a dereferenceable result then both result
and operand refer to the same memory location. The conversion must
have no side effects, and must not capture the value of the pointer.
If the source is :ref:`poison <poisonvalues>`, the result is
:ref:`poison <poisonvalues>`.
If the source is not :ref:`poison <poisonvalues>`, and both source and
destination are :ref:`integral pointers <nointptrtype>`, and the
result pointer is dereferenceable, the cast is assumed to be
reversible (i.e. casting the result back to the original address space
should yield the original bit pattern).
Example:
""""""""
.. code-block:: llvm
%X = addrspacecast ptr %x to ptr addrspace(1)
%Y = addrspacecast ptr addrspace(1) %y to ptr addrspace(2)
%Z = addrspacecast <4 x ptr> %z to <4 x ptr addrspace(3)>
.. _otherops:
Other Operations
----------------
The instructions in this category are the "miscellaneous" instructions,
which defy better classification.
.. _i_icmp:
'``icmp``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = icmp <cond> <ty> <op1>, <op2> ; yields i1 or <N x i1>:result
Overview:
"""""""""
The '``icmp``' instruction returns a boolean value or a vector of
boolean values based on comparison of its two integer, integer vector,
pointer, or pointer vector operands.
Arguments:
""""""""""
The '``icmp``' instruction takes three operands. The first operand is
the condition code indicating the kind of comparison to perform. It is
not a value, just a keyword. The possible condition codes are:
.. _icmp_md_cc:
#. ``eq``: equal
#. ``ne``: not equal
#. ``ugt``: unsigned greater than
#. ``uge``: unsigned greater or equal
#. ``ult``: unsigned less than
#. ``ule``: unsigned less or equal
#. ``sgt``: signed greater than
#. ``sge``: signed greater or equal
#. ``slt``: signed less than
#. ``sle``: signed less or equal
The remaining two arguments must be :ref:`integer <t_integer>` or
:ref:`pointer <t_pointer>` or integer :ref:`vector <t_vector>` typed. They
must also be identical types.
Semantics:
""""""""""
The '``icmp``' compares ``op1`` and ``op2`` according to the condition
code given as ``cond``. The comparison performed always yields either an
:ref:`i1 <t_integer>` or vector of ``i1`` result, as follows:
.. _icmp_md_cc_sem:
#. ``eq``: yields ``true`` if the operands are equal, ``false``
otherwise. No sign interpretation is necessary or performed.
#. ``ne``: yields ``true`` if the operands are unequal, ``false``
otherwise. No sign interpretation is necessary or performed.
#. ``ugt``: interprets the operands as unsigned values and yields
``true`` if ``op1`` is greater than ``op2``.
#. ``uge``: interprets the operands as unsigned values and yields
``true`` if ``op1`` is greater than or equal to ``op2``.
#. ``ult``: interprets the operands as unsigned values and yields
``true`` if ``op1`` is less than ``op2``.
#. ``ule``: interprets the operands as unsigned values and yields
``true`` if ``op1`` is less than or equal to ``op2``.
#. ``sgt``: interprets the operands as signed values and yields ``true``
if ``op1`` is greater than ``op2``.
#. ``sge``: interprets the operands as signed values and yields ``true``
if ``op1`` is greater than or equal to ``op2``.
#. ``slt``: interprets the operands as signed values and yields ``true``
if ``op1`` is less than ``op2``.
#. ``sle``: interprets the operands as signed values and yields ``true``
if ``op1`` is less than or equal to ``op2``.
If the operands are :ref:`pointer <t_pointer>` typed, the pointer values
are compared as if they were integers.
If the operands are integer vectors, then they are compared element by
element. The result is an ``i1`` vector with the same number of elements
as the values being compared. Otherwise, the result is an ``i1``.
Example:
""""""""
.. code-block:: text
<result> = icmp eq i32 4, 5 ; yields: result=false
<result> = icmp ne ptr %X, %X ; yields: result=false
<result> = icmp ult i16 4, 5 ; yields: result=true
<result> = icmp sgt i16 4, 5 ; yields: result=false
<result> = icmp ule i16 -4, 5 ; yields: result=false
<result> = icmp sge i16 4, 5 ; yields: result=false
.. _i_fcmp:
'``fcmp``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = fcmp [fast-math flags]* <cond> <ty> <op1>, <op2> ; yields i1 or <N x i1>:result
Overview:
"""""""""
The '``fcmp``' instruction returns a boolean value or vector of boolean
values based on comparison of its operands.
If the operands are floating-point scalars, then the result type is a
boolean (:ref:`i1 <t_integer>`).
If the operands are floating-point vectors, then the result type is a
vector of boolean with the same number of elements as the operands being
compared.
Arguments:
""""""""""
The '``fcmp``' instruction takes three operands. The first operand is
the condition code indicating the kind of comparison to perform. It is
not a value, just a keyword. The possible condition codes are:
#. ``false``: no comparison, always returns false
#. ``oeq``: ordered and equal
#. ``ogt``: ordered and greater than
#. ``oge``: ordered and greater than or equal
#. ``olt``: ordered and less than
#. ``ole``: ordered and less than or equal
#. ``one``: ordered and not equal
#. ``ord``: ordered (no nans)
#. ``ueq``: unordered or equal
#. ``ugt``: unordered or greater than
#. ``uge``: unordered or greater than or equal
#. ``ult``: unordered or less than
#. ``ule``: unordered or less than or equal
#. ``une``: unordered or not equal
#. ``uno``: unordered (either nans)
#. ``true``: no comparison, always returns true
*Ordered* means that neither operand is a QNAN while *unordered* means
that either operand may be a QNAN.
Each of ``val1`` and ``val2`` arguments must be either a :ref:`floating-point
<t_floating>` type or a :ref:`vector <t_vector>` of floating-point type.
They must have identical types.
Semantics:
""""""""""
The '``fcmp``' instruction compares ``op1`` and ``op2`` according to the
condition code given as ``cond``. If the operands are vectors, then the
vectors are compared element by element. Each comparison performed
always yields an :ref:`i1 <t_integer>` result, as follows:
#. ``false``: always yields ``false``, regardless of operands.
#. ``oeq``: yields ``true`` if both operands are not a QNAN and ``op1``
is equal to ``op2``.
#. ``ogt``: yields ``true`` if both operands are not a QNAN and ``op1``
is greater than ``op2``.
#. ``oge``: yields ``true`` if both operands are not a QNAN and ``op1``
is greater than or equal to ``op2``.
#. ``olt``: yields ``true`` if both operands are not a QNAN and ``op1``
is less than ``op2``.
#. ``ole``: yields ``true`` if both operands are not a QNAN and ``op1``
is less than or equal to ``op2``.
#. ``one``: yields ``true`` if both operands are not a QNAN and ``op1``
is not equal to ``op2``.
#. ``ord``: yields ``true`` if both operands are not a QNAN.
#. ``ueq``: yields ``true`` if either operand is a QNAN or ``op1`` is
equal to ``op2``.
#. ``ugt``: yields ``true`` if either operand is a QNAN or ``op1`` is
greater than ``op2``.
#. ``uge``: yields ``true`` if either operand is a QNAN or ``op1`` is
greater than or equal to ``op2``.
#. ``ult``: yields ``true`` if either operand is a QNAN or ``op1`` is
less than ``op2``.
#. ``ule``: yields ``true`` if either operand is a QNAN or ``op1`` is
less than or equal to ``op2``.
#. ``une``: yields ``true`` if either operand is a QNAN or ``op1`` is
not equal to ``op2``.
#. ``uno``: yields ``true`` if either operand is a QNAN.
#. ``true``: always yields ``true``, regardless of operands.
The ``fcmp`` instruction can also optionally take any number of
:ref:`fast-math flags <fastmath>`, which are optimization hints to enable
otherwise unsafe floating-point optimizations.
Any set of fast-math flags are legal on an ``fcmp`` instruction, but the
only flags that have any effect on its semantics are those that allow
assumptions to be made about the values of input arguments; namely
``nnan``, ``ninf``, and ``reassoc``. See :ref:`fastmath` for more information.
Example:
""""""""
.. code-block:: text
<result> = fcmp oeq float 4.0, 5.0 ; yields: result=false
<result> = fcmp one float 4.0, 5.0 ; yields: result=true
<result> = fcmp olt float 4.0, 5.0 ; yields: result=true
<result> = fcmp ueq double 1.0, 2.0 ; yields: result=false
.. _i_phi:
'``phi``' Instruction
^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = phi [fast-math-flags] <ty> [ <val0>, <label0>], ...
Overview:
"""""""""
The '``phi``' instruction is used to implement the φ node in the SSA
graph representing the function.
Arguments:
""""""""""
The type of the incoming values is specified with the first type field.
After this, the '``phi``' instruction takes a list of pairs as
arguments, with one pair for each predecessor basic block of the current
block. Only values of :ref:`first class <t_firstclass>` type may be used as
the value arguments to the PHI node. Only labels may be used as the
label arguments.
There must be no non-phi instructions between the start of a basic block
and the PHI instructions: i.e. PHI instructions must be first in a basic
block.
For the purposes of the SSA form, the use of each incoming value is
deemed to occur on the edge from the corresponding predecessor block to
the current block (but after any definition of an '``invoke``'
instruction's return value on the same edge).
The optional ``fast-math-flags`` marker indicates that the phi has one
or more :ref:`fast-math-flags <fastmath>`. These are optimization hints
to enable otherwise unsafe floating-point optimizations. Fast-math-flags
are only valid for phis that return a floating-point scalar or vector
type, or an array (nested to any depth) of floating-point scalar or vector
types.
Semantics:
""""""""""
At runtime, the '``phi``' instruction logically takes on the value
specified by the pair corresponding to the predecessor basic block that
executed just prior to the current block.
Example:
""""""""
.. code-block:: llvm
Loop: ; Infinite loop that counts from 0 on up...
%indvar = phi i32 [ 0, %LoopHeader ], [ %nextindvar, %Loop ]
%nextindvar = add i32 %indvar, 1
br label %Loop
.. _i_select:
'``select``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = select [fast-math flags] selty <cond>, <ty> <val1>, <ty> <val2> ; yields ty
selty is either i1 or {<N x i1>}
Overview:
"""""""""
The '``select``' instruction is used to choose one value based on a
condition, without IR-level branching.
Arguments:
""""""""""
The '``select``' instruction requires an 'i1' value or a vector of 'i1'
values indicating the condition, and two values of the same :ref:`first
class <t_firstclass>` type.
#. The optional ``fast-math flags`` marker indicates that the select has one or more
:ref:`fast-math flags <fastmath>`. These are optimization hints to enable
otherwise unsafe floating-point optimizations. Fast-math flags are only valid
for selects that return a floating-point scalar or vector type, or an array
(nested to any depth) of floating-point scalar or vector types.
Semantics:
""""""""""
If the condition is an i1 and it evaluates to 1, the instruction returns
the first value argument; otherwise, it returns the second value
argument.
If the condition is a vector of i1, then the value arguments must be
vectors of the same size, and the selection is done element by element.
If the condition is an i1 and the value arguments are vectors of the
same size, then an entire vector is selected.
Example:
""""""""
.. code-block:: llvm
%X = select i1 true, i8 17, i8 42 ; yields i8:17
.. _i_freeze:
'``freeze``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = freeze ty <val> ; yields ty:result
Overview:
"""""""""
The '``freeze``' instruction is used to stop propagation of
:ref:`undef <undefvalues>` and :ref:`poison <poisonvalues>` values.
Arguments:
""""""""""
The '``freeze``' instruction takes a single argument.
Semantics:
""""""""""
If the argument is ``undef`` or ``poison``, '``freeze``' returns an
arbitrary, but fixed, value of type '``ty``'.
Otherwise, this instruction is a no-op and returns the input argument.
All uses of a value returned by the same '``freeze``' instruction are
guaranteed to always observe the same value, while different '``freeze``'
instructions may yield different values.
While ``undef`` and ``poison`` pointers can be frozen, the result is a
non-dereferenceable pointer. See the
:ref:`Pointer Aliasing Rules <pointeraliasing>` section for more information.
If an aggregate value or vector is frozen, the operand is frozen element-wise.
The padding of an aggregate isn't considered, since it isn't visible
without storing it into memory and loading it with a different type.
Example:
""""""""
.. code-block:: text
%w = i32 undef
%x = freeze i32 %w
%y = add i32 %w, %w ; undef
%z = add i32 %x, %x ; even number because all uses of %x observe
; the same value
%x2 = freeze i32 %w
%cmp = icmp eq i32 %x, %x2 ; can be true or false
; example with vectors
%v = <2 x i32> <i32 undef, i32 poison>
%a = extractelement <2 x i32> %v, i32 0 ; undef
%b = extractelement <2 x i32> %v, i32 1 ; poison
%add = add i32 %a, %a ; undef
%v.fr = freeze <2 x i32> %v ; element-wise freeze
%d = extractelement <2 x i32> %v.fr, i32 0 ; not undef
%add.f = add i32 %d, %d ; even number
; branching on frozen value
%poison = add nsw i1 %k, undef ; poison
%c = freeze i1 %poison
br i1 %c, label %foo, label %bar ; non-deterministic branch to %foo or %bar
.. _i_call:
'``call``' Instruction
^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<result> = [tail | musttail | notail ] call [fast-math flags] [cconv] [ret attrs] [addrspace(<num>)]
<ty>|<fnty> <fnptrval>(<function args>) [fn attrs] [ operand bundles ]
Overview:
"""""""""
The '``call``' instruction represents a simple function call.
Arguments:
""""""""""
This instruction requires several arguments:
#. The optional ``tail`` and ``musttail`` markers indicate that the optimizers
should perform tail call optimization. The ``tail`` marker is a hint that
`can be ignored <CodeGenerator.html#tail-call-optimization>`_. The
``musttail`` marker means that the call must be tail call optimized in order
for the program to be correct. This is true even in the presence of
attributes like "disable-tail-calls". The ``musttail`` marker provides these
guarantees:
#. The call will not cause unbounded stack growth if it is part of a
recursive cycle in the call graph.
#. Arguments with the :ref:`inalloca <attr_inalloca>` or
:ref:`preallocated <attr_preallocated>` attribute are forwarded in place.
#. If the musttail call appears in a function with the ``"thunk"`` attribute
and the caller and callee both have varargs, then any unprototyped
arguments in register or memory are forwarded to the callee. Similarly,
the return value of the callee is returned to the caller's caller, even
if a void return type is in use.
Both markers imply that the callee does not access allocas from the caller.
The ``tail`` marker additionally implies that the callee does not access
varargs from the caller. Calls marked ``musttail`` must obey the following
additional rules:
- The call must immediately precede a :ref:`ret <i_ret>` instruction,
or a pointer bitcast followed by a ret instruction.
- The ret instruction must return the (possibly bitcasted) value
produced by the call, undef, or void.
- The calling conventions of the caller and callee must match.
- The callee must be varargs iff the caller is varargs. Bitcasting a
non-varargs function to the appropriate varargs type is legal so
long as the non-varargs prefixes obey the other rules.
- The return type must not undergo automatic conversion to an `sret` pointer.
In addition, if the calling convention is not `swifttailcc` or `tailcc`:
- All ABI-impacting function attributes, such as sret, byval, inreg,
returned, and inalloca, must match.
- The caller and callee prototypes must match. Pointer types of parameters
or return types may differ in pointee type, but not in address space.
On the other hand, if the calling convention is `swifttailcc` or `swiftcc`:
- Only these ABI-impacting attributes attributes are allowed: sret, byval,
swiftself, and swiftasync.
- Prototypes are not required to match.
Tail call optimization for calls marked ``tail`` is guaranteed to occur if
the following conditions are met:
- Caller and callee both have the calling convention ``fastcc`` or ``tailcc``.
- The call is in tail position (ret immediately follows call and ret
uses value of call or is void).
- Option ``-tailcallopt`` is enabled,
``llvm::GuaranteedTailCallOpt`` is ``true``, or the calling convention
is ``tailcc``
- `Platform-specific constraints are
met. <CodeGenerator.html#tailcallopt>`_
#. The optional ``notail`` marker indicates that the optimizers should not add
``tail`` or ``musttail`` markers to the call. It is used to prevent tail
call optimization from being performed on the call.
#. The optional ``fast-math flags`` marker indicates that the call has one or more
:ref:`fast-math flags <fastmath>`, which are optimization hints to enable
otherwise unsafe floating-point optimizations. Fast-math flags are only valid
for calls that return a floating-point scalar or vector type, or an array
(nested to any depth) of floating-point scalar or vector types.
#. The optional "cconv" marker indicates which :ref:`calling
convention <callingconv>` the call should use. If none is
specified, the call defaults to using C calling conventions. The
calling convention of the call must match the calling convention of
the target function, or else the behavior is undefined.
#. The optional :ref:`Parameter Attributes <paramattrs>` list for return
values. Only '``zeroext``', '``signext``', and '``inreg``' attributes
are valid here.
#. The optional addrspace attribute can be used to indicate the address space
of the called function. If it is not specified, the program address space
from the :ref:`datalayout string<langref_datalayout>` will be used.
#. '``ty``': the type of the call instruction itself which is also the
type of the return value. Functions that return no value are marked
``void``.
#. '``fnty``': shall be the signature of the function being called. The
argument types must match the types implied by this signature. This
type can be omitted if the function is not varargs.
#. '``fnptrval``': An LLVM value containing a pointer to a function to
be called. In most cases, this is a direct function call, but
indirect ``call``'s are just as possible, calling an arbitrary pointer
to function value.
#. '``function args``': argument list whose types match the function
signature argument types and parameter attributes. All arguments must
be of :ref:`first class <t_firstclass>` type. If the function signature
indicates the function accepts a variable number of arguments, the
extra arguments can be specified.
#. The optional :ref:`function attributes <fnattrs>` list.
#. The optional :ref:`operand bundles <opbundles>` list.
Semantics:
""""""""""
The '``call``' instruction is used to cause control flow to transfer to
a specified function, with its incoming arguments bound to the specified
values. Upon a '``ret``' instruction in the called function, control
flow continues with the instruction after the function call, and the
return value of the function is bound to the result argument.
Example:
""""""""
.. code-block:: llvm
%retval = call i32 @test(i32 %argc)
call i32 (ptr, ...) @printf(ptr %msg, i32 12, i8 42) ; yields i32
%X = tail call i32 @foo() ; yields i32
%Y = tail call fastcc i32 @foo() ; yields i32
call void %foo(i8 signext 97)
%struct.A = type { i32, i8 }
%r = call %struct.A @foo() ; yields { i32, i8 }
%gr = extractvalue %struct.A %r, 0 ; yields i32
%gr1 = extractvalue %struct.A %r, 1 ; yields i8
%Z = call void @foo() noreturn ; indicates that %foo never returns normally
%ZZ = call zeroext i32 @bar() ; Return value is %zero extended
llvm treats calls to some functions with names and arguments that match
the standard C99 library as being the C99 library functions, and may
perform optimizations or generate code for them under that assumption.
This is something we'd like to change in the future to provide better
support for freestanding environments and non-C-based languages.
.. _i_va_arg:
'``va_arg``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<resultval> = va_arg <va_list*> <arglist>, <argty>
Overview:
"""""""""
The '``va_arg``' instruction is used to access arguments passed through
the "variable argument" area of a function call. It is used to implement
the ``va_arg`` macro in C.
Arguments:
""""""""""
This instruction takes a ``va_list*`` value and the type of the
argument. It returns a value of the specified argument type and
increments the ``va_list`` to point to the next argument. The actual
type of ``va_list`` is target specific.
Semantics:
""""""""""
The '``va_arg``' instruction loads an argument of the specified type
from the specified ``va_list`` and causes the ``va_list`` to point to
the next argument. For more information, see the variable argument
handling :ref:`Intrinsic Functions <int_varargs>`.
It is legal for this instruction to be called in a function which does
not take a variable number of arguments, for example, the ``vfprintf``
function.
``va_arg`` is an LLVM instruction instead of an :ref:`intrinsic
function <intrinsics>` because it takes a type as an argument.
Example:
""""""""
See the :ref:`variable argument processing <int_varargs>` section.
Note that the code generator does not yet fully support va\_arg on many
targets. Also, it does not currently support va\_arg with aggregate
types on any target.
.. _i_landingpad:
'``landingpad``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<resultval> = landingpad <resultty> <clause>+
<resultval> = landingpad <resultty> cleanup <clause>*
<clause> := catch <type> <value>
<clause> := filter <array constant type> <array constant>
Overview:
"""""""""
The '``landingpad``' instruction is used by `LLVM's exception handling
system <ExceptionHandling.html#overview>`_ to specify that a basic block
is a landing pad --- one where the exception lands, and corresponds to the
code found in the ``catch`` portion of a ``try``/``catch`` sequence. It
defines values supplied by the :ref:`personality function <personalityfn>` upon
re-entry to the function. The ``resultval`` has the type ``resultty``.
Arguments:
""""""""""
The optional
``cleanup`` flag indicates that the landing pad block is a cleanup.
A ``clause`` begins with the clause type --- ``catch`` or ``filter`` --- and
contains the global variable representing the "type" that may be caught
or filtered respectively. Unlike the ``catch`` clause, the ``filter``
clause takes an array constant as its argument. Use
"``[0 x ptr] undef``" for a filter which cannot throw. The
'``landingpad``' instruction must contain *at least* one ``clause`` or
the ``cleanup`` flag.
Semantics:
""""""""""
The '``landingpad``' instruction defines the values which are set by the
:ref:`personality function <personalityfn>` upon re-entry to the function, and
therefore the "result type" of the ``landingpad`` instruction. As with
calling conventions, how the personality function results are
represented in LLVM IR is target specific.
The clauses are applied in order from top to bottom. If two
``landingpad`` instructions are merged together through inlining, the
clauses from the calling function are appended to the list of clauses.
When the call stack is being unwound due to an exception being thrown,
the exception is compared against each ``clause`` in turn. If it doesn't
match any of the clauses, and the ``cleanup`` flag is not set, then
unwinding continues further up the call stack.
The ``landingpad`` instruction has several restrictions:
- A landing pad block is a basic block which is the unwind destination
of an '``invoke``' instruction.
- A landing pad block must have a '``landingpad``' instruction as its
first non-PHI instruction.
- There can be only one '``landingpad``' instruction within the landing
pad block.
- A basic block that is not a landing pad block may not include a
'``landingpad``' instruction.
Example:
""""""""
.. code-block:: llvm
;; A landing pad which can catch an integer.
%res = landingpad { ptr, i32 }
catch ptr @_ZTIi
;; A landing pad that is a cleanup.
%res = landingpad { ptr, i32 }
cleanup
;; A landing pad which can catch an integer and can only throw a double.
%res = landingpad { ptr, i32 }
catch ptr @_ZTIi
filter [1 x ptr] [ptr @_ZTId]
.. _i_catchpad:
'``catchpad``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<resultval> = catchpad within <catchswitch> [<args>*]
Overview:
"""""""""
The '``catchpad``' instruction is used by `LLVM's exception handling
system <ExceptionHandling.html#overview>`_ to specify that a basic block
begins a catch handler --- one where a personality routine attempts to transfer
control to catch an exception.
Arguments:
""""""""""
The ``catchswitch`` operand must always be a token produced by a
:ref:`catchswitch <i_catchswitch>` instruction in a predecessor block. This
ensures that each ``catchpad`` has exactly one predecessor block, and it always
terminates in a ``catchswitch``.
The ``args`` correspond to whatever information the personality routine
requires to know if this is an appropriate handler for the exception. Control
will transfer to the ``catchpad`` if this is the first appropriate handler for
the exception.
The ``resultval`` has the type :ref:`token <t_token>` and is used to match the
``catchpad`` to corresponding :ref:`catchrets <i_catchret>` and other nested EH
pads.
Semantics:
""""""""""
When the call stack is being unwound due to an exception being thrown, the
exception is compared against the ``args``. If it doesn't match, control will
not reach the ``catchpad`` instruction. The representation of ``args`` is
entirely target and personality function-specific.
Like the :ref:`landingpad <i_landingpad>` instruction, the ``catchpad``
instruction must be the first non-phi of its parent basic block.
The meaning of the tokens produced and consumed by ``catchpad`` and other "pad"
instructions is described in the
`Windows exception handling documentation\ <ExceptionHandling.html#wineh>`_.
When a ``catchpad`` has been "entered" but not yet "exited" (as
described in the `EH documentation\ <ExceptionHandling.html#wineh-constraints>`_),
it is undefined behavior to execute a :ref:`call <i_call>` or :ref:`invoke <i_invoke>`
that does not carry an appropriate :ref:`"funclet" bundle <ob_funclet>`.
Example:
""""""""
.. code-block:: text
dispatch:
%cs = catchswitch within none [label %handler0] unwind to caller
;; A catch block which can catch an integer.
handler0:
%tok = catchpad within %cs [ptr @_ZTIi]
.. _i_cleanuppad:
'``cleanuppad``' Instruction
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
<resultval> = cleanuppad within <parent> [<args>*]
Overview:
"""""""""
The '``cleanuppad``' instruction is used by `LLVM's exception handling
system <ExceptionHandling.html#overview>`_ to specify that a basic block
is a cleanup block --- one where a personality routine attempts to
transfer control to run cleanup actions.
The ``args`` correspond to whatever additional
information the :ref:`personality function <personalityfn>` requires to
execute the cleanup.
The ``resultval`` has the type :ref:`token <t_token>` and is used to
match the ``cleanuppad`` to corresponding :ref:`cleanuprets <i_cleanupret>`.
The ``parent`` argument is the token of the funclet that contains the
``cleanuppad`` instruction. If the ``cleanuppad`` is not inside a funclet,
this operand may be the token ``none``.
Arguments:
""""""""""
The instruction takes a list of arbitrary values which are interpreted
by the :ref:`personality function <personalityfn>`.
Semantics:
""""""""""
When the call stack is being unwound due to an exception being thrown,
the :ref:`personality function <personalityfn>` transfers control to the
``cleanuppad`` with the aid of the personality-specific arguments.
As with calling conventions, how the personality function results are
represented in LLVM IR is target specific.
The ``cleanuppad`` instruction has several restrictions:
- A cleanup block is a basic block which is the unwind destination of
an exceptional instruction.
- A cleanup block must have a '``cleanuppad``' instruction as its
first non-PHI instruction.
- There can be only one '``cleanuppad``' instruction within the
cleanup block.
- A basic block that is not a cleanup block may not include a
'``cleanuppad``' instruction.
When a ``cleanuppad`` has been "entered" but not yet "exited" (as
described in the `EH documentation\ <ExceptionHandling.html#wineh-constraints>`_),
it is undefined behavior to execute a :ref:`call <i_call>` or :ref:`invoke <i_invoke>`
that does not carry an appropriate :ref:`"funclet" bundle <ob_funclet>`.
Example:
""""""""
.. code-block:: text
%tok = cleanuppad within %cs []
.. _intrinsics:
Intrinsic Functions
===================
LLVM supports the notion of an "intrinsic function". These functions
have well known names and semantics and are required to follow certain
restrictions. Overall, these intrinsics represent an extension mechanism
for the LLVM language that does not require changing all of the
transformations in LLVM when adding to the language (or the bitcode
reader/writer, the parser, etc...).
Intrinsic function names must all start with an "``llvm.``" prefix. This
prefix is reserved in LLVM for intrinsic names; thus, function names may
not begin with this prefix. Intrinsic functions must always be external
functions: you cannot define the body of intrinsic functions. Intrinsic
functions may only be used in call or invoke instructions: it is illegal
to take the address of an intrinsic function. Additionally, because
intrinsic functions are part of the LLVM language, it is required if any
are added that they be documented here.
Some intrinsic functions can be overloaded, i.e., the intrinsic
represents a family of functions that perform the same operation but on
different data types. Because LLVM can represent over 8 million
different integer types, overloading is used commonly to allow an
intrinsic function to operate on any integer type. One or more of the
argument types or the result type can be overloaded to accept any
integer type. Argument types may also be defined as exactly matching a
previous argument's type or the result type. This allows an intrinsic
function which accepts multiple arguments, but needs all of them to be
of the same type, to only be overloaded with respect to a single
argument or the result.
Overloaded intrinsics will have the names of its overloaded argument
types encoded into its function name, each preceded by a period. Only
those types which are overloaded result in a name suffix. Arguments
whose type is matched against another type do not. For example, the
``llvm.ctpop`` function can take an integer of any width and returns an
integer of exactly the same integer width. This leads to a family of
functions such as ``i8 @llvm.ctpop.i8(i8 %val)`` and
``i29 @llvm.ctpop.i29(i29 %val)``. Only one type, the return type, is
overloaded, and only one type suffix is required. Because the argument's
type is matched against the return type, it does not require its own
name suffix.
:ref:`Unnamed types <t_opaque>` are encoded as ``s_s``. Overloaded intrinsics
that depend on an unnamed type in one of its overloaded argument types get an
additional ``.<number>`` suffix. This allows differentiating intrinsics with
different unnamed types as arguments. (For example:
``llvm.ssa.copy.p0s_s.2(%42*)``) The number is tracked in the LLVM module and
it ensures unique names in the module. While linking together two modules, it is
still possible to get a name clash. In that case one of the names will be
changed by getting a new number.
For target developers who are defining intrinsics for back-end code
generation, any intrinsic overloads based solely the distinction between
integer or floating point types should not be relied upon for correct
code generation. In such cases, the recommended approach for target
maintainers when defining intrinsics is to create separate integer and
FP intrinsics rather than rely on overloading. For example, if different
codegen is required for ``llvm.target.foo(<4 x i32>)`` and
``llvm.target.foo(<4 x float>)`` then these should be split into
different intrinsics.
To learn how to add an intrinsic function, please see the `Extending
LLVM Guide <ExtendingLLVM.html>`_.
.. _int_varargs:
Variable Argument Handling Intrinsics
-------------------------------------
Variable argument support is defined in LLVM with the
:ref:`va_arg <i_va_arg>` instruction and these three intrinsic
functions. These functions are related to the similarly named macros
defined in the ``<stdarg.h>`` header file.
All of these functions operate on arguments that use a target-specific
value type "``va_list``". The LLVM assembly language reference manual
does not define what this type is, so all transformations should be
prepared to handle these functions regardless of the type used.
This example shows how the :ref:`va_arg <i_va_arg>` instruction and the
variable argument handling intrinsic functions are used.
.. code-block:: llvm
; This struct is different for every platform. For most platforms,
; it is merely a ptr.
%struct.va_list = type { ptr }
; For Unix x86_64 platforms, va_list is the following struct:
; %struct.va_list = type { i32, i32, ptr, ptr }
define i32 @test(i32 %X, ...) {
; Initialize variable argument processing
%ap = alloca %struct.va_list
call void @llvm.va_start(ptr %ap)
; Read a single integer argument
%tmp = va_arg ptr %ap, i32
; Demonstrate usage of llvm.va_copy and llvm.va_end
%aq = alloca ptr
call void @llvm.va_copy(ptr %aq, ptr %ap)
call void @llvm.va_end(ptr %aq)
; Stop processing of arguments.
call void @llvm.va_end(ptr %ap)
ret i32 %tmp
}
declare void @llvm.va_start(ptr)
declare void @llvm.va_copy(ptr, ptr)
declare void @llvm.va_end(ptr)
.. _int_va_start:
'``llvm.va_start``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.va_start(ptr <arglist>)
Overview:
"""""""""
The '``llvm.va_start``' intrinsic initializes ``<arglist>`` for
subsequent use by ``va_arg``.
Arguments:
""""""""""
The argument is a pointer to a ``va_list`` element to initialize.
Semantics:
""""""""""
The '``llvm.va_start``' intrinsic works just like the ``va_start`` macro
available in C. In a target-dependent way, it initializes the
``va_list`` element to which the argument points, so that the next call
to ``va_arg`` will produce the first variable argument passed to the
function. Unlike the C ``va_start`` macro, this intrinsic does not need
to know the last argument of the function as the compiler can figure
that out.
'``llvm.va_end``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.va_end(ptr <arglist>)
Overview:
"""""""""
The '``llvm.va_end``' intrinsic destroys ``<arglist>``, which has been
initialized previously with ``llvm.va_start`` or ``llvm.va_copy``.
Arguments:
""""""""""
The argument is a pointer to a ``va_list`` to destroy.
Semantics:
""""""""""
The '``llvm.va_end``' intrinsic works just like the ``va_end`` macro
available in C. In a target-dependent way, it destroys the ``va_list``
element to which the argument points. Calls to
:ref:`llvm.va_start <int_va_start>` and
:ref:`llvm.va_copy <int_va_copy>` must be matched exactly with calls to
``llvm.va_end``.
.. _int_va_copy:
'``llvm.va_copy``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.va_copy(ptr <destarglist>, ptr <srcarglist>)
Overview:
"""""""""
The '``llvm.va_copy``' intrinsic copies the current argument position
from the source argument list to the destination argument list.
Arguments:
""""""""""
The first argument is a pointer to a ``va_list`` element to initialize.
The second argument is a pointer to a ``va_list`` element to copy from.
Semantics:
""""""""""
The '``llvm.va_copy``' intrinsic works just like the ``va_copy`` macro
available in C. In a target-dependent way, it copies the source
``va_list`` element into the destination ``va_list`` element. This
intrinsic is necessary because the `` llvm.va_start`` intrinsic may be
arbitrarily complex and require, for example, memory allocation.
Accurate Garbage Collection Intrinsics
--------------------------------------
LLVM's support for `Accurate Garbage Collection <GarbageCollection.html>`_
(GC) requires the frontend to generate code containing appropriate intrinsic
calls and select an appropriate GC strategy which knows how to lower these
intrinsics in a manner which is appropriate for the target collector.
These intrinsics allow identification of :ref:`GC roots on the
stack <int_gcroot>`, as well as garbage collector implementations that
require :ref:`read <int_gcread>` and :ref:`write <int_gcwrite>` barriers.
Frontends for type-safe garbage collected languages should generate
these intrinsics to make use of the LLVM garbage collectors. For more
details, see `Garbage Collection with LLVM <GarbageCollection.html>`_.
LLVM provides an second experimental set of intrinsics for describing garbage
collection safepoints in compiled code. These intrinsics are an alternative
to the ``llvm.gcroot`` intrinsics, but are compatible with the ones for
:ref:`read <int_gcread>` and :ref:`write <int_gcwrite>` barriers. The
differences in approach are covered in the `Garbage Collection with LLVM
<GarbageCollection.html>`_ documentation. The intrinsics themselves are
described in :doc:`Statepoints`.
.. _int_gcroot:
'``llvm.gcroot``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.gcroot(ptr %ptrloc, ptr %metadata)
Overview:
"""""""""
The '``llvm.gcroot``' intrinsic declares the existence of a GC root to
the code generator, and allows some metadata to be associated with it.
Arguments:
""""""""""
The first argument specifies the address of a stack object that contains
the root pointer. The second pointer (which must be either a constant or
a global value address) contains the meta-data to be associated with the
root.
Semantics:
""""""""""
At runtime, a call to this intrinsic stores a null pointer into the
"ptrloc" location. At compile-time, the code generator generates
information to allow the runtime to find the pointer at GC safe points.
The '``llvm.gcroot``' intrinsic may only be used in a function which
:ref:`specifies a GC algorithm <gc>`.
.. _int_gcread:
'``llvm.gcread``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.gcread(ptr %ObjPtr, ptr %Ptr)
Overview:
"""""""""
The '``llvm.gcread``' intrinsic identifies reads of references from heap
locations, allowing garbage collector implementations that require read
barriers.
Arguments:
""""""""""
The second argument is the address to read from, which should be an
address allocated from the garbage collector. The first object is a
pointer to the start of the referenced object, if needed by the language
runtime (otherwise null).
Semantics:
""""""""""
The '``llvm.gcread``' intrinsic has the same semantics as a load
instruction, but may be replaced with substantially more complex code by
the garbage collector runtime, as needed. The '``llvm.gcread``'
intrinsic may only be used in a function which :ref:`specifies a GC
algorithm <gc>`.
.. _int_gcwrite:
'``llvm.gcwrite``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.gcwrite(ptr %P1, ptr %Obj, ptr %P2)
Overview:
"""""""""
The '``llvm.gcwrite``' intrinsic identifies writes of references to heap
locations, allowing garbage collector implementations that require write
barriers (such as generational or reference counting collectors).
Arguments:
""""""""""
The first argument is the reference to store, the second is the start of
the object to store it to, and the third is the address of the field of
Obj to store to. If the runtime does not require a pointer to the
object, Obj may be null.
Semantics:
""""""""""
The '``llvm.gcwrite``' intrinsic has the same semantics as a store
instruction, but may be replaced with substantially more complex code by
the garbage collector runtime, as needed. The '``llvm.gcwrite``'
intrinsic may only be used in a function which :ref:`specifies a GC
algorithm <gc>`.
.. _gc_statepoint:
'``llvm.experimental.gc.statepoint``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare token
@llvm.experimental.gc.statepoint(i64 <id>, i32 <num patch bytes>,
ptr elementtype(func_type) <target>,
i64 <#call args>, i64 <flags>,
... (call parameters),
i64 0, i64 0)
Overview:
"""""""""
The statepoint intrinsic represents a call which is parse-able by the
runtime.
Operands:
"""""""""
The 'id' operand is a constant integer that is reported as the ID
field in the generated stackmap. LLVM does not interpret this
parameter in any way and its meaning is up to the statepoint user to
decide. Note that LLVM is free to duplicate code containing
statepoint calls, and this may transform IR that had a unique 'id' per
lexical call to statepoint to IR that does not.
If 'num patch bytes' is non-zero then the call instruction
corresponding to the statepoint is not emitted and LLVM emits 'num
patch bytes' bytes of nops in its place. LLVM will emit code to
prepare the function arguments and retrieve the function return value
in accordance to the calling convention; the former before the nop
sequence and the latter after the nop sequence. It is expected that
the user will patch over the 'num patch bytes' bytes of nops with a
calling sequence specific to their runtime before executing the
generated machine code. There are no guarantees with respect to the
alignment of the nop sequence. Unlike :doc:`StackMaps` statepoints do
not have a concept of shadow bytes. Note that semantically the
statepoint still represents a call or invoke to 'target', and the nop
sequence after patching is expected to represent an operation
equivalent to a call or invoke to 'target'.
The 'target' operand is the function actually being called. The operand
must have an :ref:`elementtype <attr_elementtype>` attribute specifying
the function type of the target. The target can be specified as either
a symbolic LLVM function, or as an arbitrary Value of pointer type. Note
that the function type must match the signature of the callee and the
types of the 'call parameters' arguments.
The '#call args' operand is the number of arguments to the actual
call. It must exactly match the number of arguments passed in the
'call parameters' variable length section.
The 'flags' operand is used to specify extra information about the
statepoint. This is currently only used to mark certain statepoints
as GC transitions. This operand is a 64-bit integer with the following
layout, where bit 0 is the least significant bit:
+-------+---------------------------------------------------+
| Bit # | Usage |
+=======+===================================================+
| 0 | Set if the statepoint is a GC transition, cleared |
| | otherwise. |
+-------+---------------------------------------------------+
| 1-63 | Reserved for future use; must be cleared. |
+-------+---------------------------------------------------+
The 'call parameters' arguments are simply the arguments which need to
be passed to the call target. They will be lowered according to the
specified calling convention and otherwise handled like a normal call
instruction. The number of arguments must exactly match what is
specified in '# call args'. The types must match the signature of
'target'.
The 'call parameter' attributes must be followed by two 'i64 0' constants.
These were originally the length prefixes for 'gc transition parameter' and
'deopt parameter' arguments, but the role of these parameter sets have been
entirely replaced with the corresponding operand bundles. In a future
revision, these now redundant arguments will be removed.
Semantics:
""""""""""
A statepoint is assumed to read and write all memory. As a result,
memory operations can not be reordered past a statepoint. It is
illegal to mark a statepoint as being either 'readonly' or 'readnone'.
Note that legal IR can not perform any memory operation on a 'gc
pointer' argument of the statepoint in a location statically reachable
from the statepoint. Instead, the explicitly relocated value (from a
``gc.relocate``) must be used.
'``llvm.experimental.gc.result``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare type
@llvm.experimental.gc.result(token %statepoint_token)
Overview:
"""""""""
``gc.result`` extracts the result of the original call instruction
which was replaced by the ``gc.statepoint``. The ``gc.result``
intrinsic is actually a family of three intrinsics due to an
implementation limitation. Other than the type of the return value,
the semantics are the same.
Operands:
"""""""""
The first and only argument is the ``gc.statepoint`` which starts
the safepoint sequence of which this ``gc.result`` is a part.
Despite the typing of this as a generic token, *only* the value defined
by a ``gc.statepoint`` is legal here.
Semantics:
""""""""""
The ``gc.result`` represents the return value of the call target of
the ``statepoint``. The type of the ``gc.result`` must exactly match
the type of the target. If the call target returns void, there will
be no ``gc.result``.
A ``gc.result`` is modeled as a 'readnone' pure function. It has no
side effects since it is just a projection of the return value of the
previous call represented by the ``gc.statepoint``.
'``llvm.experimental.gc.relocate``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <pointer type>
@llvm.experimental.gc.relocate(token %statepoint_token,
i32 %base_offset,
i32 %pointer_offset)
Overview:
"""""""""
A ``gc.relocate`` returns the potentially relocated value of a pointer
at the safepoint.
Operands:
"""""""""
The first argument is the ``gc.statepoint`` which starts the
safepoint sequence of which this ``gc.relocation`` is a part.
Despite the typing of this as a generic token, *only* the value defined
by a ``gc.statepoint`` is legal here.
The second and third arguments are both indices into operands of the
corresponding statepoint's :ref:`gc-live <ob_gc_live>` operand bundle.
The second argument is an index which specifies the allocation for the pointer
being relocated. The associated value must be within the object with which the
pointer being relocated is associated. The optimizer is free to change *which*
interior derived pointer is reported, provided that it does not replace an
actual base pointer with another interior derived pointer. Collectors are
allowed to rely on the base pointer operand remaining an actual base pointer if
so constructed.
The third argument is an index which specify the (potentially) derived pointer
being relocated. It is legal for this index to be the same as the second
argument if-and-only-if a base pointer is being relocated.
Semantics:
""""""""""
The return value of ``gc.relocate`` is the potentially relocated value
of the pointer specified by its arguments. It is unspecified how the
value of the returned pointer relates to the argument to the
``gc.statepoint`` other than that a) it points to the same source
language object with the same offset, and b) the 'based-on'
relationship of the newly relocated pointers is a projection of the
unrelocated pointers. In particular, the integer value of the pointer
returned is unspecified.
A ``gc.relocate`` is modeled as a ``readnone`` pure function. It has no
side effects since it is just a way to extract information about work
done during the actual call modeled by the ``gc.statepoint``.
.. _gc.get.pointer.base:
'``llvm.experimental.gc.get.pointer.base``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <pointer type>
@llvm.experimental.gc.get.pointer.base(
<pointer type> readnone nocapture %derived_ptr)
nounwind willreturn memory(none)
Overview:
"""""""""
``gc.get.pointer.base`` for a derived pointer returns its base pointer.
Operands:
"""""""""
The only argument is a pointer which is based on some object with
an unknown offset from the base of said object.
Semantics:
""""""""""
This intrinsic is used in the abstract machine model for GC to represent
the base pointer for an arbitrary derived pointer.
This intrinsic is inlined by the :ref:`RewriteStatepointsForGC` pass by
replacing all uses of this callsite with the offset of a derived pointer from
its base pointer value. The replacement is done as part of the lowering to the
explicit statepoint model.
The return pointer type must be the same as the type of the parameter.
'``llvm.experimental.gc.get.pointer.offset``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i64
@llvm.experimental.gc.get.pointer.offset(
<pointer type> readnone nocapture %derived_ptr)
nounwind willreturn memory(none)
Overview:
"""""""""
``gc.get.pointer.offset`` for a derived pointer returns the offset from its
base pointer.
Operands:
"""""""""
The only argument is a pointer which is based on some object with
an unknown offset from the base of said object.
Semantics:
""""""""""
This intrinsic is used in the abstract machine model for GC to represent
the offset of an arbitrary derived pointer from its base pointer.
This intrinsic is inlined by the :ref:`RewriteStatepointsForGC` pass by
replacing all uses of this callsite with the offset of a derived pointer from
its base pointer value. The replacement is done as part of the lowering to the
explicit statepoint model.
Basically this call calculates difference between the derived pointer and its
base pointer (see :ref:`gc.get.pointer.base`) both ptrtoint casted. But
this cast done outside the :ref:`RewriteStatepointsForGC` pass could result
in the pointers lost for further lowering from the abstract model to the
explicit physical one.
Code Generator Intrinsics
-------------------------
These intrinsics are provided by LLVM to expose special features that
may only be implemented with code generator support.
'``llvm.returnaddress``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.returnaddress(i32 <level>)
Overview:
"""""""""
The '``llvm.returnaddress``' intrinsic attempts to compute a
target-specific value indicating the return address of the current
function or one of its callers.
Arguments:
""""""""""
The argument to this intrinsic indicates which function to return the
address for. Zero indicates the calling function, one indicates its
caller, etc. The argument is **required** to be a constant integer
value.
Semantics:
""""""""""
The '``llvm.returnaddress``' intrinsic either returns a pointer
indicating the return address of the specified call frame, or zero if it
cannot be identified. The value returned by this intrinsic is likely to
be incorrect or 0 for arguments other than zero, so it should only be
used for debugging purposes.
Note that calling this intrinsic does not prevent function inlining or
other aggressive transformations, so the value returned may not be that
of the obvious source-language caller.
'``llvm.addressofreturnaddress``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.addressofreturnaddress()
Overview:
"""""""""
The '``llvm.addressofreturnaddress``' intrinsic returns a target-specific
pointer to the place in the stack frame where the return address of the
current function is stored.
Semantics:
""""""""""
Note that calling this intrinsic does not prevent function inlining or
other aggressive transformations, so the value returned may not be that
of the obvious source-language caller.
This intrinsic is only implemented for x86 and aarch64.
'``llvm.sponentry``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.sponentry()
Overview:
"""""""""
The '``llvm.sponentry``' intrinsic returns the stack pointer value at
the entry of the current function calling this intrinsic.
Semantics:
""""""""""
Note this intrinsic is only verified on AArch64 and ARM.
'``llvm.frameaddress``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.frameaddress(i32 <level>)
Overview:
"""""""""
The '``llvm.frameaddress``' intrinsic attempts to return the
target-specific frame pointer value for the specified stack frame.
Arguments:
""""""""""
The argument to this intrinsic indicates which function to return the
frame pointer for. Zero indicates the calling function, one indicates
its caller, etc. The argument is **required** to be a constant integer
value.
Semantics:
""""""""""
The '``llvm.frameaddress``' intrinsic either returns a pointer
indicating the frame address of the specified call frame, or zero if it
cannot be identified. The value returned by this intrinsic is likely to
be incorrect or 0 for arguments other than zero, so it should only be
used for debugging purposes.
Note that calling this intrinsic does not prevent function inlining or
other aggressive transformations, so the value returned may not be that
of the obvious source-language caller.
'``llvm.swift.async.context.addr``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.swift.async.context.addr()
Overview:
"""""""""
The '``llvm.swift.async.context.addr``' intrinsic returns a pointer to
the part of the extended frame record containing the asynchronous
context of a Swift execution.
Semantics:
""""""""""
If the caller has a ``swiftasync`` parameter, that argument will initially
be stored at the returned address. If not, it will be initialized to null.
'``llvm.localescape``' and '``llvm.localrecover``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.localescape(...)
declare ptr @llvm.localrecover(ptr %func, ptr %fp, i32 %idx)
Overview:
"""""""""
The '``llvm.localescape``' intrinsic escapes offsets of a collection of static
allocas, and the '``llvm.localrecover``' intrinsic applies those offsets to a
live frame pointer to recover the address of the allocation. The offset is
computed during frame layout of the caller of ``llvm.localescape``.
Arguments:
""""""""""
All arguments to '``llvm.localescape``' must be pointers to static allocas or
casts of static allocas. Each function can only call '``llvm.localescape``'
once, and it can only do so from the entry block.
The ``func`` argument to '``llvm.localrecover``' must be a constant
bitcasted pointer to a function defined in the current module. The code
generator cannot determine the frame allocation offset of functions defined in
other modules.
The ``fp`` argument to '``llvm.localrecover``' must be a frame pointer of a
call frame that is currently live. The return value of '``llvm.localaddress``'
is one way to produce such a value, but various runtimes also expose a suitable
pointer in platform-specific ways.
The ``idx`` argument to '``llvm.localrecover``' indicates which alloca passed to
'``llvm.localescape``' to recover. It is zero-indexed.
Semantics:
""""""""""
These intrinsics allow a group of functions to share access to a set of local
stack allocations of a one parent function. The parent function may call the
'``llvm.localescape``' intrinsic once from the function entry block, and the
child functions can use '``llvm.localrecover``' to access the escaped allocas.
The '``llvm.localescape``' intrinsic blocks inlining, as inlining changes where
the escaped allocas are allocated, which would break attempts to use
'``llvm.localrecover``'.
'``llvm.seh.try.begin``' and '``llvm.seh.try.end``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.seh.try.begin()
declare void @llvm.seh.try.end()
Overview:
"""""""""
The '``llvm.seh.try.begin``' and '``llvm.seh.try.end``' intrinsics mark
the boundary of a _try region for Windows SEH Asynchrous Exception Handling.
Semantics:
""""""""""
When a C-function is compiled with Windows SEH Asynchrous Exception option,
-feh_asynch (aka MSVC -EHa), these two intrinsics are injected to mark _try
boundary and to prevent potential exceptions from being moved across boundary.
Any set of operations can then be confined to the region by reading their leaf
inputs via volatile loads and writing their root outputs via volatile stores.
'``llvm.seh.scope.begin``' and '``llvm.seh.scope.end``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.seh.scope.begin()
declare void @llvm.seh.scope.end()
Overview:
"""""""""
The '``llvm.seh.scope.begin``' and '``llvm.seh.scope.end``' intrinsics mark
the boundary of a CPP object lifetime for Windows SEH Asynchrous Exception
Handling (MSVC option -EHa).
Semantics:
""""""""""
LLVM's ordinary exception-handling representation associates EH cleanups and
handlers only with ``invoke``s, which normally correspond only to call sites. To
support arbitrary faulting instructions, it must be possible to recover the current
EH scope for any instruction. Turning every operation in LLVM that could fault
into an ``invoke`` of a new, potentially-throwing intrinsic would require adding a
large number of intrinsics, impede optimization of those operations, and make
compilation slower by introducing many extra basic blocks. These intrinsics can
be used instead to mark the region protected by a cleanup, such as for a local
C++ object with a non-trivial destructor. ``llvm.seh.scope.begin`` is used to mark
the start of the region; it is always called with ``invoke``, with the unwind block
being the desired unwind destination for any potentially-throwing instructions
within the region. `llvm.seh.scope.end` is used to mark when the scope ends
and the EH cleanup is no longer required (e.g. because the destructor is being
called).
.. _int_read_register:
.. _int_read_volatile_register:
.. _int_write_register:
'``llvm.read_register``', '``llvm.read_volatile_register``', and '``llvm.write_register``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.read_register.i32(metadata)
declare i64 @llvm.read_register.i64(metadata)
declare i32 @llvm.read_volatile_register.i32(metadata)
declare i64 @llvm.read_volatile_register.i64(metadata)
declare void @llvm.write_register.i32(metadata, i32 @value)
declare void @llvm.write_register.i64(metadata, i64 @value)
!0 = !{!"sp\00"}
Overview:
"""""""""
The '``llvm.read_register``', '``llvm.read_volatile_register``', and
'``llvm.write_register``' intrinsics provide access to the named register.
The register must be valid on the architecture being compiled to. The type
needs to be compatible with the register being read.
Semantics:
""""""""""
The '``llvm.read_register``' and '``llvm.read_volatile_register``' intrinsics
return the current value of the register, where possible. The
'``llvm.write_register``' intrinsic sets the current value of the register,
where possible.
A call to '``llvm.read_volatile_register``' is assumed to have side-effects
and possibly return a different value each time (e.g. for a timer register).
This is useful to implement named register global variables that need
to always be mapped to a specific register, as is common practice on
bare-metal programs including OS kernels.
The compiler doesn't check for register availability or use of the used
register in surrounding code, including inline assembly. Because of that,
allocatable registers are not supported.
Warning: So far it only works with the stack pointer on selected
architectures (ARM, AArch64, PowerPC and x86_64). Significant amount of
work is needed to support other registers and even more so, allocatable
registers.
.. _int_stacksave:
'``llvm.stacksave``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.stacksave.p0()
declare ptr addrspace(5) @llvm.stacksave.p5()
Overview:
"""""""""
The '``llvm.stacksave``' intrinsic is used to remember the current state
of the function stack, for use with
:ref:`llvm.stackrestore <int_stackrestore>`. This is useful for
implementing language features like scoped automatic variable sized
arrays in C99.
Semantics:
""""""""""
This intrinsic returns an opaque pointer value that can be passed to
:ref:`llvm.stackrestore <int_stackrestore>`. When an
``llvm.stackrestore`` intrinsic is executed with a value saved from
``llvm.stacksave``, it effectively restores the state of the stack to
the state it was in when the ``llvm.stacksave`` intrinsic executed. In
practice, this pops any :ref:`alloca <i_alloca>` blocks from the stack
that were allocated after the ``llvm.stacksave`` was executed. The
address space should typically be the
:ref:`alloca address space <alloca_addrspace>`.
.. _int_stackrestore:
'``llvm.stackrestore``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.stackrestore.p0(ptr %ptr)
declare void @llvm.stackrestore.p5(ptr addrspace(5) %ptr)
Overview:
"""""""""
The '``llvm.stackrestore``' intrinsic is used to restore the state of
the function stack to the state it was in when the corresponding
:ref:`llvm.stacksave <int_stacksave>` intrinsic executed. This is
useful for implementing language features like scoped automatic
variable sized arrays in C99. The address space should typically be
the :ref:`alloca address space <alloca_addrspace>`.
Semantics:
""""""""""
See the description for :ref:`llvm.stacksave <int_stacksave>`.
.. _int_get_dynamic_area_offset:
'``llvm.get.dynamic.area.offset``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.get.dynamic.area.offset.i32()
declare i64 @llvm.get.dynamic.area.offset.i64()
Overview:
"""""""""
The '``llvm.get.dynamic.area.offset.*``' intrinsic family is used to
get the offset from native stack pointer to the address of the most
recent dynamic alloca on the caller's stack. These intrinsics are
intended for use in combination with
:ref:`llvm.stacksave <int_stacksave>` to get a
pointer to the most recent dynamic alloca. This is useful, for example,
for AddressSanitizer's stack unpoisoning routines.
Semantics:
""""""""""
These intrinsics return a non-negative integer value that can be used to
get the address of the most recent dynamic alloca, allocated by :ref:`alloca <i_alloca>`
on the caller's stack. In particular, for targets where stack grows downwards,
adding this offset to the native stack pointer would get the address of the most
recent dynamic alloca. For targets where stack grows upwards, the situation is a bit more
complicated, because subtracting this value from stack pointer would get the address
one past the end of the most recent dynamic alloca.
Although for most targets `llvm.get.dynamic.area.offset <int_get_dynamic_area_offset>`
returns just a zero, for others, such as PowerPC and PowerPC64, it returns a
compile-time-known constant value.
The return value type of :ref:`llvm.get.dynamic.area.offset <int_get_dynamic_area_offset>`
must match the target's default address space's (address space 0) pointer type.
'``llvm.prefetch``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.prefetch(ptr <address>, i32 <rw>, i32 <locality>, i32 <cache type>)
Overview:
"""""""""
The '``llvm.prefetch``' intrinsic is a hint to the code generator to
insert a prefetch instruction if supported; otherwise, it is a noop.
Prefetches have no effect on the behavior of the program but can change
its performance characteristics.
Arguments:
""""""""""
``address`` is the address to be prefetched, ``rw`` is the specifier
determining if the fetch should be for a read (0) or write (1), and
``locality`` is a temporal locality specifier ranging from (0) - no
locality, to (3) - extremely local keep in cache. The ``cache type``
specifies whether the prefetch is performed on the data (1) or
instruction (0) cache. The ``rw``, ``locality`` and ``cache type``
arguments must be constant integers.
Semantics:
""""""""""
This intrinsic does not modify the behavior of the program. In
particular, prefetches cannot trap and do not produce a value. On
targets that support this intrinsic, the prefetch can provide hints to
the processor cache for better performance.
'``llvm.pcmarker``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.pcmarker(i32 <id>)
Overview:
"""""""""
The '``llvm.pcmarker``' intrinsic is a method to export a Program
Counter (PC) in a region of code to simulators and other tools. The
method is target specific, but it is expected that the marker will use
exported symbols to transmit the PC of the marker. The marker makes no
guarantees that it will remain with any specific instruction after
optimizations. It is possible that the presence of a marker will inhibit
optimizations. The intended use is to be inserted after optimizations to
allow correlations of simulation runs.
Arguments:
""""""""""
``id`` is a numerical id identifying the marker.
Semantics:
""""""""""
This intrinsic does not modify the behavior of the program. Backends
that do not support this intrinsic may ignore it.
'``llvm.readcyclecounter``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i64 @llvm.readcyclecounter()
Overview:
"""""""""
The '``llvm.readcyclecounter``' intrinsic provides access to the cycle
counter register (or similar low latency, high accuracy clocks) on those
targets that support it. On X86, it should map to RDTSC. On Alpha, it
should map to RPCC. As the backing counters overflow quickly (on the
order of 9 seconds on alpha), this should only be used for small
timings.
Semantics:
""""""""""
When directly supported, reading the cycle counter should not modify any
memory. Implementations are allowed to either return an application
specific value or a system wide value. On backends without support, this
is lowered to a constant 0.
Note that runtime support may be conditional on the privilege-level code is
running at and the host platform.
'``llvm.clear_cache``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.clear_cache(ptr, ptr)
Overview:
"""""""""
The '``llvm.clear_cache``' intrinsic ensures visibility of modifications
in the specified range to the execution unit of the processor. On
targets with non-unified instruction and data cache, the implementation
flushes the instruction cache.
Semantics:
""""""""""
On platforms with coherent instruction and data caches (e.g. x86), this
intrinsic is a nop. On platforms with non-coherent instruction and data
cache (e.g. ARM, MIPS), the intrinsic is lowered either to appropriate
instructions or a system call, if cache flushing requires special
privileges.
The default behavior is to emit a call to ``__clear_cache`` from the run
time library.
This intrinsic does *not* empty the instruction pipeline. Modifications
of the current function are outside the scope of the intrinsic.
'``llvm.instrprof.increment``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.increment(ptr <name>, i64 <hash>,
i32 <num-counters>, i32 <index>)
Overview:
"""""""""
The '``llvm.instrprof.increment``' intrinsic can be emitted by a
frontend for use with instrumentation based profiling. These will be
lowered by the ``-instrprof`` pass to generate execution counts of a
program at runtime.
Arguments:
""""""""""
The first argument is a pointer to a global variable containing the
name of the entity being instrumented. This should generally be the
(mangled) function name for a set of counters.
The second argument is a hash value that can be used by the consumer
of the profile data to detect changes to the instrumented source, and
the third is the number of counters associated with ``name``. It is an
error if ``hash`` or ``num-counters`` differ between two instances of
``instrprof.increment`` that refer to the same name.
The last argument refers to which of the counters for ``name`` should
be incremented. It should be a value between 0 and ``num-counters``.
Semantics:
""""""""""
This intrinsic represents an increment of a profiling counter. It will
cause the ``-instrprof`` pass to generate the appropriate data
structures and the code to increment the appropriate value, in a
format that can be written out by a compiler runtime and consumed via
the ``llvm-profdata`` tool.
'``llvm.instrprof.increment.step``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.increment.step(ptr <name>, i64 <hash>,
i32 <num-counters>,
i32 <index>, i64 <step>)
Overview:
"""""""""
The '``llvm.instrprof.increment.step``' intrinsic is an extension to
the '``llvm.instrprof.increment``' intrinsic with an additional fifth
argument to specify the step of the increment.
Arguments:
""""""""""
The first four arguments are the same as '``llvm.instrprof.increment``'
intrinsic.
The last argument specifies the value of the increment of the counter variable.
Semantics:
""""""""""
See description of '``llvm.instrprof.increment``' intrinsic.
'``llvm.instrprof.timestamp``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.timestamp(i8* <name>, i64 <hash>,
i32 <num-counters>, i32 <index>)
Overview:
"""""""""
The '``llvm.instrprof.timestamp``' intrinsic is used to implement temporal
profiling.
Arguments:
""""""""""
The arguments are the same as '``llvm.instrprof.increment``'. The ``index`` is
expected to always be zero.
Semantics:
""""""""""
Similar to the '``llvm.instrprof.increment``' intrinsic, but it stores a
timestamp representing when this function was executed for the first time.
'``llvm.instrprof.cover``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.cover(ptr <name>, i64 <hash>,
i32 <num-counters>, i32 <index>)
Overview:
"""""""""
The '``llvm.instrprof.cover``' intrinsic is used to implement coverage
instrumentation.
Arguments:
""""""""""
The arguments are the same as the first four arguments of
'``llvm.instrprof.increment``'.
Semantics:
""""""""""
Similar to the '``llvm.instrprof.increment``' intrinsic, but it stores zero to
the profiling variable to signify that the function has been covered. We store
zero because this is more efficient on some targets.
'``llvm.instrprof.value.profile``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.value.profile(ptr <name>, i64 <hash>,
i64 <value>, i32 <value_kind>,
i32 <index>)
Overview:
"""""""""
The '``llvm.instrprof.value.profile``' intrinsic can be emitted by a
frontend for use with instrumentation based profiling. This will be
lowered by the ``-instrprof`` pass to find out the target values,
instrumented expressions take in a program at runtime.
Arguments:
""""""""""
The first argument is a pointer to a global variable containing the
name of the entity being instrumented. ``name`` should generally be the
(mangled) function name for a set of counters.
The second argument is a hash value that can be used by the consumer
of the profile data to detect changes to the instrumented source. It
is an error if ``hash`` differs between two instances of
``llvm.instrprof.*`` that refer to the same name.
The third argument is the value of the expression being profiled. The profiled
expression's value should be representable as an unsigned 64-bit value. The
fourth argument represents the kind of value profiling that is being done. The
supported value profiling kinds are enumerated through the
``InstrProfValueKind`` type declared in the
``<include/llvm/ProfileData/InstrProf.h>`` header file. The last argument is the
index of the instrumented expression within ``name``. It should be >= 0.
Semantics:
""""""""""
This intrinsic represents the point where a call to a runtime routine
should be inserted for value profiling of target expressions. ``-instrprof``
pass will generate the appropriate data structures and replace the
``llvm.instrprof.value.profile`` intrinsic with the call to the profile
runtime library with proper arguments.
'``llvm.instrprof.mcdc.parameters``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.mcdc.parameters(ptr <name>, i64 <hash>,
i32 <bitmap-bytes>)
Overview:
"""""""""
The '``llvm.instrprof.mcdc.parameters``' intrinsic is used to initiate MC/DC
code coverage instrumentation for a function.
Arguments:
""""""""""
The first argument is a pointer to a global variable containing the
name of the entity being instrumented. This should generally be the
(mangled) function name for a set of counters.
The second argument is a hash value that can be used by the consumer
of the profile data to detect changes to the instrumented source.
The third argument is the number of bitmap bytes required by the function to
record the number of test vectors executed for each boolean expression.
Semantics:
""""""""""
This intrinsic represents basic MC/DC parameters initiating one or more MC/DC
instrumentation sequences in a function. It will cause the ``-instrprof`` pass
to generate the appropriate data structures and the code to instrument MC/DC
test vectors in a format that can be written out by a compiler runtime and
consumed via the ``llvm-profdata`` tool.
'``llvm.instrprof.mcdc.condbitmap.update``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.mcdc.condbitmap.update(ptr <name>, i64 <hash>,
i32 <condition-id>,
ptr <mcdc-temp-addr>,
i1 <bool-value>)
Overview:
"""""""""
The '``llvm.instrprof.mcdc.condbitmap.update``' intrinsic is used to track
MC/DC condition evaluation for each condition in a boolean expression.
Arguments:
""""""""""
The first argument is a pointer to a global variable containing the
name of the entity being instrumented. This should generally be the
(mangled) function name for a set of counters.
The second argument is a hash value that can be used by the consumer
of the profile data to detect changes to the instrumented source.
The third argument is an ID of a condition to track. This value is used as a
bit index into the condition bitmap.
The fourth argument is the address of the condition bitmap.
The fifth argument is the boolean value representing the evaluation of the
condition (true or false)
Semantics:
""""""""""
This intrinsic represents the update of a condition bitmap that is local to a
function and will cause the ``-instrprof`` pass to generate the code to
instrument the control flow around each condition in a boolean expression. The
ID of each condition corresponds to a bit index in the condition bitmap which
is set based on the evaluation of the condition.
'``llvm.instrprof.mcdc.tvbitmap.update``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.instrprof.mcdc.tvbitmap.update(ptr <name>, i64 <hash>,
i32 <bitmap-bytes>)
i32 <bitmap-index>,
ptr <mcdc-temp-addr>)
Overview:
"""""""""
The '``llvm.instrprof.mcdc.tvbitmap.update``' intrinsic is used to track MC/DC
test vector execution after each boolean expression has been fully executed.
The overall value of the condition bitmap, after it has been successively
updated using the '``llvm.instrprof.mcdc.condbitmap.update``' intrinsic with
the true or false evaluation of each condition, uniquely identifies an executed
MC/DC test vector and is used as a bit index into the global test vector
bitmap.
Arguments:
""""""""""
The first argument is a pointer to a global variable containing the
name of the entity being instrumented. This should generally be the
(mangled) function name for a set of counters.
The second argument is a hash value that can be used by the consumer
of the profile data to detect changes to the instrumented source.
The third argument is the number of bitmap bytes required by the function to
record the number of test vectors executed for each boolean expression.
The fourth argument is the byte index into the global test vector bitmap
corresponding to the function.
The fifth argument is the address of the condition bitmap, which contains a
value representing an executed MC/DC test vector. It is loaded and used as the
bit index of the test vector bitmap.
Semantics:
""""""""""
This intrinsic represents the final operation of an MC/DC instrumentation
sequence and will cause the ``-instrprof`` pass to generate the code to
instrument an update of a function's global test vector bitmap to indicate that
a test vector has been executed. The global test vector bitmap can be consumed
by the ``llvm-profdata`` and ``llvm-cov`` tools.
'``llvm.thread.pointer``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.thread.pointer()
Overview:
"""""""""
The '``llvm.thread.pointer``' intrinsic returns the value of the thread
pointer.
Semantics:
""""""""""
The '``llvm.thread.pointer``' intrinsic returns a pointer to the TLS area
for the current thread. The exact semantics of this value are target
specific: it may point to the start of TLS area, to the end, or somewhere
in the middle. Depending on the target, this intrinsic may read a register,
call a helper function, read from an alternate memory space, or perform
other operations necessary to locate the TLS area. Not all targets support
this intrinsic.
'``llvm.call.preallocated.setup``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare token @llvm.call.preallocated.setup(i32 %num_args)
Overview:
"""""""""
The '``llvm.call.preallocated.setup``' intrinsic returns a token which can
be used with a call's ``"preallocated"`` operand bundle to indicate that
certain arguments are allocated and initialized before the call.
Semantics:
""""""""""
The '``llvm.call.preallocated.setup``' intrinsic returns a token which is
associated with at most one call. The token can be passed to
'``@llvm.call.preallocated.arg``' to get a pointer to get that
corresponding argument. The token must be the parameter to a
``"preallocated"`` operand bundle for the corresponding call.
Nested calls to '``llvm.call.preallocated.setup``' are allowed, but must
be properly nested. e.g.
:: code-block:: llvm
%t1 = call token @llvm.call.preallocated.setup(i32 0)
%t2 = call token @llvm.call.preallocated.setup(i32 0)
call void foo() ["preallocated"(token %t2)]
call void foo() ["preallocated"(token %t1)]
is allowed, but not
:: code-block:: llvm
%t1 = call token @llvm.call.preallocated.setup(i32 0)
%t2 = call token @llvm.call.preallocated.setup(i32 0)
call void foo() ["preallocated"(token %t1)]
call void foo() ["preallocated"(token %t2)]
.. _int_call_preallocated_arg:
'``llvm.call.preallocated.arg``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.call.preallocated.arg(token %setup_token, i32 %arg_index)
Overview:
"""""""""
The '``llvm.call.preallocated.arg``' intrinsic returns a pointer to the
corresponding preallocated argument for the preallocated call.
Semantics:
""""""""""
The '``llvm.call.preallocated.arg``' intrinsic returns a pointer to the
``%arg_index``th argument with the ``preallocated`` attribute for
the call associated with the ``%setup_token``, which must be from
'``llvm.call.preallocated.setup``'.
A call to '``llvm.call.preallocated.arg``' must have a call site
``preallocated`` attribute. The type of the ``preallocated`` attribute must
match the type used by the ``preallocated`` attribute of the corresponding
argument at the preallocated call. The type is used in the case that an
``llvm.call.preallocated.setup`` does not have a corresponding call (e.g. due
to DCE), where otherwise we cannot know how large the arguments are.
It is undefined behavior if this is called with a token from an
'``llvm.call.preallocated.setup``' if another
'``llvm.call.preallocated.setup``' has already been called or if the
preallocated call corresponding to the '``llvm.call.preallocated.setup``'
has already been called.
.. _int_call_preallocated_teardown:
'``llvm.call.preallocated.teardown``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.call.preallocated.teardown(token %setup_token)
Overview:
"""""""""
The '``llvm.call.preallocated.teardown``' intrinsic cleans up the stack
created by a '``llvm.call.preallocated.setup``'.
Semantics:
""""""""""
The token argument must be a '``llvm.call.preallocated.setup``'.
The '``llvm.call.preallocated.teardown``' intrinsic cleans up the stack
allocated by the corresponding '``llvm.call.preallocated.setup``'. Exactly
one of this or the preallocated call must be called to prevent stack leaks.
It is undefined behavior to call both a '``llvm.call.preallocated.teardown``'
and the preallocated call for a given '``llvm.call.preallocated.setup``'.
For example, if the stack is allocated for a preallocated call by a
'``llvm.call.preallocated.setup``', then an initializer function called on an
allocated argument throws an exception, there should be a
'``llvm.call.preallocated.teardown``' in the exception handler to prevent
stack leaks.
Following the nesting rules in '``llvm.call.preallocated.setup``', nested
calls to '``llvm.call.preallocated.setup``' and
'``llvm.call.preallocated.teardown``' are allowed but must be properly
nested.
Example:
""""""""
.. code-block:: llvm
%cs = call token @llvm.call.preallocated.setup(i32 1)
%x = call ptr @llvm.call.preallocated.arg(token %cs, i32 0) preallocated(i32)
invoke void @constructor(ptr %x) to label %conta unwind label %contb
conta:
call void @foo1(ptr preallocated(i32) %x) ["preallocated"(token %cs)]
ret void
contb:
%s = catchswitch within none [label %catch] unwind to caller
catch:
%p = catchpad within %s []
call void @llvm.call.preallocated.teardown(token %cs)
ret void
Standard C/C++ Library Intrinsics
---------------------------------
LLVM provides intrinsics for a few important standard C/C++ library
functions. These intrinsics allow source-language front-ends to pass
information about the alignment of the pointer arguments to the code
generator, providing opportunity for more efficient code generation.
.. _int_abs:
'``llvm.abs.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.abs`` on any
integer bit width or any vector of integer elements.
::
declare i32 @llvm.abs.i32(i32 <src>, i1 <is_int_min_poison>)
declare <4 x i32> @llvm.abs.v4i32(<4 x i32> <src>, i1 <is_int_min_poison>)
Overview:
"""""""""
The '``llvm.abs``' family of intrinsic functions returns the absolute value
of an argument.
Arguments:
""""""""""
The first argument is the value for which the absolute value is to be returned.
This argument may be of any integer type or a vector with integer element type.
The return type must match the first argument type.
The second argument must be a constant and is a flag to indicate whether the
result value of the '``llvm.abs``' intrinsic is a
:ref:`poison value <poisonvalues>` if the argument is statically or dynamically
an ``INT_MIN`` value.
Semantics:
""""""""""
The '``llvm.abs``' intrinsic returns the magnitude (always positive) of the
argument or each element of a vector argument.". If the argument is ``INT_MIN``,
then the result is also ``INT_MIN`` if ``is_int_min_poison == 0`` and
``poison`` otherwise.
.. _int_smax:
'``llvm.smax.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``@llvm.smax`` on any
integer bit width or any vector of integer elements.
::
declare i32 @llvm.smax.i32(i32 %a, i32 %b)
declare <4 x i32> @llvm.smax.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
Return the larger of ``%a`` and ``%b`` comparing the values as signed integers.
Vector intrinsics operate on a per-element basis. The larger element of ``%a``
and ``%b`` at a given index is returned for that index.
Arguments:
""""""""""
The arguments (``%a`` and ``%b``) may be of any integer type or a vector with
integer element type. The argument types must match each other, and the return
type must match the argument type.
.. _int_smin:
'``llvm.smin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``@llvm.smin`` on any
integer bit width or any vector of integer elements.
::
declare i32 @llvm.smin.i32(i32 %a, i32 %b)
declare <4 x i32> @llvm.smin.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
Return the smaller of ``%a`` and ``%b`` comparing the values as signed integers.
Vector intrinsics operate on a per-element basis. The smaller element of ``%a``
and ``%b`` at a given index is returned for that index.
Arguments:
""""""""""
The arguments (``%a`` and ``%b``) may be of any integer type or a vector with
integer element type. The argument types must match each other, and the return
type must match the argument type.
.. _int_umax:
'``llvm.umax.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``@llvm.umax`` on any
integer bit width or any vector of integer elements.
::
declare i32 @llvm.umax.i32(i32 %a, i32 %b)
declare <4 x i32> @llvm.umax.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
Return the larger of ``%a`` and ``%b`` comparing the values as unsigned
integers. Vector intrinsics operate on a per-element basis. The larger element
of ``%a`` and ``%b`` at a given index is returned for that index.
Arguments:
""""""""""
The arguments (``%a`` and ``%b``) may be of any integer type or a vector with
integer element type. The argument types must match each other, and the return
type must match the argument type.
.. _int_umin:
'``llvm.umin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``@llvm.umin`` on any
integer bit width or any vector of integer elements.
::
declare i32 @llvm.umin.i32(i32 %a, i32 %b)
declare <4 x i32> @llvm.umin.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
Return the smaller of ``%a`` and ``%b`` comparing the values as unsigned
integers. Vector intrinsics operate on a per-element basis. The smaller element
of ``%a`` and ``%b`` at a given index is returned for that index.
Arguments:
""""""""""
The arguments (``%a`` and ``%b``) may be of any integer type or a vector with
integer element type. The argument types must match each other, and the return
type must match the argument type.
.. _int_memcpy:
'``llvm.memcpy``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.memcpy`` on any
integer bit width and for different address spaces. Not all targets
support all bit widths however.
::
declare void @llvm.memcpy.p0.p0.i32(ptr <dest>, ptr <src>,
i32 <len>, i1 <isvolatile>)
declare void @llvm.memcpy.p0.p0.i64(ptr <dest>, ptr <src>,
i64 <len>, i1 <isvolatile>)
Overview:
"""""""""
The '``llvm.memcpy.*``' intrinsics copy a block of memory from the
source location to the destination location.
Note that, unlike the standard libc function, the ``llvm.memcpy.*``
intrinsics do not return a value, takes extra isvolatile
arguments and the pointers can be in specified address spaces.
Arguments:
""""""""""
The first argument is a pointer to the destination, the second is a
pointer to the source. The third argument is an integer argument
specifying the number of bytes to copy, and the fourth is a
boolean indicating a volatile access.
The :ref:`align <attr_align>` parameter attribute can be provided
for the first and second arguments.
If the ``isvolatile`` parameter is ``true``, the ``llvm.memcpy`` call is
a :ref:`volatile operation <volatile>`. The detailed access behavior is not
very cleanly specified and it is unwise to depend on it.
Semantics:
""""""""""
The '``llvm.memcpy.*``' intrinsics copy a block of memory from the source
location to the destination location, which must either be equal or
non-overlapping. It copies "len" bytes of memory over. If the argument is known
to be aligned to some boundary, this can be specified as an attribute on the
argument.
If ``<len>`` is 0, it is no-op modulo the behavior of attributes attached to
the arguments.
If ``<len>`` is not a well-defined value, the behavior is undefined.
If ``<len>`` is not zero, both ``<dest>`` and ``<src>`` should be well-defined,
otherwise the behavior is undefined.
.. _int_memcpy_inline:
'``llvm.memcpy.inline``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.memcpy.inline`` on any
integer bit width and for different address spaces. Not all targets
support all bit widths however.
::
declare void @llvm.memcpy.inline.p0.p0.i32(ptr <dest>, ptr <src>,
i32 <len>, i1 <isvolatile>)
declare void @llvm.memcpy.inline.p0.p0.i64(ptr <dest>, ptr <src>,
i64 <len>, i1 <isvolatile>)
Overview:
"""""""""
The '``llvm.memcpy.inline.*``' intrinsics copy a block of memory from the
source location to the destination location and guarantees that no external
functions are called.
Note that, unlike the standard libc function, the ``llvm.memcpy.inline.*``
intrinsics do not return a value, takes extra isvolatile
arguments and the pointers can be in specified address spaces.
Arguments:
""""""""""
The first argument is a pointer to the destination, the second is a
pointer to the source. The third argument is a constant integer argument
specifying the number of bytes to copy, and the fourth is a
boolean indicating a volatile access.
The :ref:`align <attr_align>` parameter attribute can be provided
for the first and second arguments.
If the ``isvolatile`` parameter is ``true``, the ``llvm.memcpy.inline`` call is
a :ref:`volatile operation <volatile>`. The detailed access behavior is not
very cleanly specified and it is unwise to depend on it.
Semantics:
""""""""""
The '``llvm.memcpy.inline.*``' intrinsics copy a block of memory from the
source location to the destination location, which are not allowed to
overlap. It copies "len" bytes of memory over. If the argument is known
to be aligned to some boundary, this can be specified as an attribute on
the argument.
The behavior of '``llvm.memcpy.inline.*``' is equivalent to the behavior of
'``llvm.memcpy.*``', but the generated code is guaranteed not to call any
external functions.
.. _int_memmove:
'``llvm.memmove``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use llvm.memmove on any integer
bit width and for different address space. Not all targets support all
bit widths however.
::
declare void @llvm.memmove.p0.p0.i32(ptr <dest>, ptr <src>,
i32 <len>, i1 <isvolatile>)
declare void @llvm.memmove.p0.p0.i64(ptr <dest>, ptr <src>,
i64 <len>, i1 <isvolatile>)
Overview:
"""""""""
The '``llvm.memmove.*``' intrinsics move a block of memory from the
source location to the destination location. It is similar to the
'``llvm.memcpy``' intrinsic but allows the two memory locations to
overlap.
Note that, unlike the standard libc function, the ``llvm.memmove.*``
intrinsics do not return a value, takes an extra isvolatile
argument and the pointers can be in specified address spaces.
Arguments:
""""""""""
The first argument is a pointer to the destination, the second is a
pointer to the source. The third argument is an integer argument
specifying the number of bytes to copy, and the fourth is a
boolean indicating a volatile access.
The :ref:`align <attr_align>` parameter attribute can be provided
for the first and second arguments.
If the ``isvolatile`` parameter is ``true``, the ``llvm.memmove`` call
is a :ref:`volatile operation <volatile>`. The detailed access behavior is
not very cleanly specified and it is unwise to depend on it.
Semantics:
""""""""""
The '``llvm.memmove.*``' intrinsics copy a block of memory from the
source location to the destination location, which may overlap. It
copies "len" bytes of memory over. If the argument is known to be
aligned to some boundary, this can be specified as an attribute on
the argument.
If ``<len>`` is 0, it is no-op modulo the behavior of attributes attached to
the arguments.
If ``<len>`` is not a well-defined value, the behavior is undefined.
If ``<len>`` is not zero, both ``<dest>`` and ``<src>`` should be well-defined,
otherwise the behavior is undefined.
.. _int_memset:
'``llvm.memset.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use llvm.memset on any integer
bit width and for different address spaces. However, not all targets
support all bit widths.
::
declare void @llvm.memset.p0.i32(ptr <dest>, i8 <val>,
i32 <len>, i1 <isvolatile>)
declare void @llvm.memset.p0.i64(ptr <dest>, i8 <val>,
i64 <len>, i1 <isvolatile>)
Overview:
"""""""""
The '``llvm.memset.*``' intrinsics fill a block of memory with a
particular byte value.
Note that, unlike the standard libc function, the ``llvm.memset``
intrinsic does not return a value and takes an extra volatile
argument. Also, the destination can be in an arbitrary address space.
Arguments:
""""""""""
The first argument is a pointer to the destination to fill, the second
is the byte value with which to fill it, the third argument is an
integer argument specifying the number of bytes to fill, and the fourth
is a boolean indicating a volatile access.
The :ref:`align <attr_align>` parameter attribute can be provided
for the first arguments.
If the ``isvolatile`` parameter is ``true``, the ``llvm.memset`` call is
a :ref:`volatile operation <volatile>`. The detailed access behavior is not
very cleanly specified and it is unwise to depend on it.
Semantics:
""""""""""
The '``llvm.memset.*``' intrinsics fill "len" bytes of memory starting
at the destination location. If the argument is known to be
aligned to some boundary, this can be specified as an attribute on
the argument.
If ``<len>`` is 0, it is no-op modulo the behavior of attributes attached to
the arguments.
If ``<len>`` is not a well-defined value, the behavior is undefined.
If ``<len>`` is not zero, ``<dest>`` should be well-defined, otherwise the
behavior is undefined.
.. _int_memset_inline:
'``llvm.memset.inline``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.memset.inline`` on any
integer bit width and for different address spaces. Not all targets
support all bit widths however.
::
declare void @llvm.memset.inline.p0.p0i8.i32(ptr <dest>, i8 <val>,
i32 <len>, i1 <isvolatile>)
declare void @llvm.memset.inline.p0.p0.i64(ptr <dest>, i8 <val>,
i64 <len>, i1 <isvolatile>)
Overview:
"""""""""
The '``llvm.memset.inline.*``' intrinsics fill a block of memory with a
particular byte value and guarantees that no external functions are called.
Note that, unlike the standard libc function, the ``llvm.memset.inline.*``
intrinsics do not return a value, take an extra isvolatile argument and the
pointer can be in specified address spaces.
Arguments:
""""""""""
The first argument is a pointer to the destination to fill, the second
is the byte value with which to fill it, the third argument is a constant
integer argument specifying the number of bytes to fill, and the fourth
is a boolean indicating a volatile access.
The :ref:`align <attr_align>` parameter attribute can be provided
for the first argument.
If the ``isvolatile`` parameter is ``true``, the ``llvm.memset.inline`` call is
a :ref:`volatile operation <volatile>`. The detailed access behavior is not
very cleanly specified and it is unwise to depend on it.
Semantics:
""""""""""
The '``llvm.memset.inline.*``' intrinsics fill "len" bytes of memory starting
at the destination location. If the argument is known to be
aligned to some boundary, this can be specified as an attribute on
the argument.
``len`` must be a constant expression.
If ``<len>`` is 0, it is no-op modulo the behavior of attributes attached to
the arguments.
If ``<len>`` is not a well-defined value, the behavior is undefined.
If ``<len>`` is not zero, ``<dest>`` should be well-defined, otherwise the
behavior is undefined.
The behavior of '``llvm.memset.inline.*``' is equivalent to the behavior of
'``llvm.memset.*``', but the generated code is guaranteed not to call any
external functions.
.. _int_sqrt:
'``llvm.sqrt.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.sqrt`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.sqrt.f32(float %Val)
declare double @llvm.sqrt.f64(double %Val)
declare x86_fp80 @llvm.sqrt.f80(x86_fp80 %Val)
declare fp128 @llvm.sqrt.f128(fp128 %Val)
declare ppc_fp128 @llvm.sqrt.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.sqrt``' intrinsics return the square root of the specified value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``sqrt``' function but without
trapping or setting ``errno``. For types specified by IEEE-754, the result
matches a conforming libm implementation.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
'``llvm.powi.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.powi`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
Generally, the only supported type for the exponent is the one matching
with the C type ``int``.
::
declare float @llvm.powi.f32.i32(float %Val, i32 %power)
declare double @llvm.powi.f64.i16(double %Val, i16 %power)
declare x86_fp80 @llvm.powi.f80.i32(x86_fp80 %Val, i32 %power)
declare fp128 @llvm.powi.f128.i32(fp128 %Val, i32 %power)
declare ppc_fp128 @llvm.powi.ppcf128.i32(ppc_fp128 %Val, i32 %power)
Overview:
"""""""""
The '``llvm.powi.*``' intrinsics return the first operand raised to the
specified (positive or negative) power. The order of evaluation of
multiplications is not defined. When a vector of floating-point type is
used, the second argument remains a scalar integer value.
Arguments:
""""""""""
The second argument is an integer power, and the first is a value to
raise to that power.
Semantics:
""""""""""
This function returns the first value raised to the second power with an
unspecified sequence of rounding operations.
'``llvm.sin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.sin`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.sin.f32(float %Val)
declare double @llvm.sin.f64(double %Val)
declare x86_fp80 @llvm.sin.f80(x86_fp80 %Val)
declare fp128 @llvm.sin.f128(fp128 %Val)
declare ppc_fp128 @llvm.sin.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.sin.*``' intrinsics return the sine of the operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``sin``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
'``llvm.cos.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.cos`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.cos.f32(float %Val)
declare double @llvm.cos.f64(double %Val)
declare x86_fp80 @llvm.cos.f80(x86_fp80 %Val)
declare fp128 @llvm.cos.f128(fp128 %Val)
declare ppc_fp128 @llvm.cos.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.cos.*``' intrinsics return the cosine of the operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``cos``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
'``llvm.pow.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.pow`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.pow.f32(float %Val, float %Power)
declare double @llvm.pow.f64(double %Val, double %Power)
declare x86_fp80 @llvm.pow.f80(x86_fp80 %Val, x86_fp80 %Power)
declare fp128 @llvm.pow.f128(fp128 %Val, fp128 %Power)
declare ppc_fp128 @llvm.pow.ppcf128(ppc_fp128 %Val, ppc_fp128 Power)
Overview:
"""""""""
The '``llvm.pow.*``' intrinsics return the first operand raised to the
specified (positive or negative) power.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``pow``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_exp:
'``llvm.exp.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.exp`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.exp.f32(float %Val)
declare double @llvm.exp.f64(double %Val)
declare x86_fp80 @llvm.exp.f80(x86_fp80 %Val)
declare fp128 @llvm.exp.f128(fp128 %Val)
declare ppc_fp128 @llvm.exp.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.exp.*``' intrinsics compute the base-e exponential of the specified
value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``exp``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_exp2:
'``llvm.exp2.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.exp2`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.exp2.f32(float %Val)
declare double @llvm.exp2.f64(double %Val)
declare x86_fp80 @llvm.exp2.f80(x86_fp80 %Val)
declare fp128 @llvm.exp2.f128(fp128 %Val)
declare ppc_fp128 @llvm.exp2.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.exp2.*``' intrinsics compute the base-2 exponential of the
specified value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``exp2``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_exp10:
'``llvm.exp10.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.exp10`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.exp10.f32(float %Val)
declare double @llvm.exp10.f64(double %Val)
declare x86_fp80 @llvm.exp10.f80(x86_fp80 %Val)
declare fp128 @llvm.exp10.f128(fp128 %Val)
declare ppc_fp128 @llvm.exp10.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.exp10.*``' intrinsics compute the base-10 exponential of the
specified value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``exp10``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
'``llvm.ldexp.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.ldexp`` on any
floating point or vector of floating point type. Not all targets support
all types however.
::
declare float @llvm.ldexp.f32.i32(float %Val, i32 %Exp)
declare double @llvm.ldexp.f64.i32(double %Val, i32 %Exp)
declare x86_fp80 @llvm.ldexp.f80.i32(x86_fp80 %Val, i32 %Exp)
declare fp128 @llvm.ldexp.f128.i32(fp128 %Val, i32 %Exp)
declare ppc_fp128 @llvm.ldexp.ppcf128.i32(ppc_fp128 %Val, i32 %Exp)
declare <2 x float> @llvm.ldexp.v2f32.v2i32(<2 x float> %Val, <2 x i32> %Exp)
Overview:
"""""""""
The '``llvm.ldexp.*``' intrinsics perform the ldexp function.
Arguments:
""""""""""
The first argument and the return value are :ref:`floating-point
<t_floating>` or :ref:`vector <t_vector>` of floating-point values of
the same type. The second argument is an integer with the same number
of elements.
Semantics:
""""""""""
This function multiplies the first argument by 2 raised to the second
argument's power. If the first argument is NaN or infinite, the same
value is returned. If the result underflows a zero with the same sign
is returned. If the result overflows, the result is an infinity with
the same sign.
.. _int_frexp:
'``llvm.frexp.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.frexp`` on any
floating point or vector of floating point type. Not all targets support
all types however.
::
declare { float, i32 } @llvm.frexp.f32.i32(float %Val)
declare { double, i32 } @llvm.frexp.f64.i32(double %Val)
declare { x86_fp80, i32 } @llvm.frexp.f80.i32(x86_fp80 %Val)
declare { fp128, i32 } @llvm.frexp.f128.i32(fp128 %Val)
declare { ppc_fp128, i32 } @llvm.frexp.ppcf128.i32(ppc_fp128 %Val)
declare { <2 x float>, <2 x i32> } @llvm.frexp.v2f32.v2i32(<2 x float> %Val)
Overview:
"""""""""
The '``llvm.frexp.*``' intrinsics perform the frexp function.
Arguments:
""""""""""
The argument is a :ref:`floating-point <t_floating>` or
:ref:`vector <t_vector>` of floating-point values. Returns two values
in a struct. The first struct field matches the argument type, and the
second field is an integer or a vector of integer values with the same
number of elements as the argument.
Semantics:
""""""""""
This intrinsic splits a floating point value into a normalized
fractional component and integral exponent.
For a non-zero argument, returns the argument multiplied by some power
of two such that the absolute value of the returned value is in the
range [0.5, 1.0), with the same sign as the argument. The second
result is an integer such that the first result raised to the power of
the second result is the input argument.
If the argument is a zero, returns a zero with the same sign and a 0
exponent.
If the argument is a NaN, a NaN is returned and the returned exponent
is unspecified.
If the argument is an infinity, returns an infinity with the same sign
and an unspecified exponent.
.. _int_log:
'``llvm.log.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.log`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.log.f32(float %Val)
declare double @llvm.log.f64(double %Val)
declare x86_fp80 @llvm.log.f80(x86_fp80 %Val)
declare fp128 @llvm.log.f128(fp128 %Val)
declare ppc_fp128 @llvm.log.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.log.*``' intrinsics compute the base-e logarithm of the specified
value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``log``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_log10:
'``llvm.log10.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.log10`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.log10.f32(float %Val)
declare double @llvm.log10.f64(double %Val)
declare x86_fp80 @llvm.log10.f80(x86_fp80 %Val)
declare fp128 @llvm.log10.f128(fp128 %Val)
declare ppc_fp128 @llvm.log10.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.log10.*``' intrinsics compute the base-10 logarithm of the
specified value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``log10``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_log2:
'``llvm.log2.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.log2`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.log2.f32(float %Val)
declare double @llvm.log2.f64(double %Val)
declare x86_fp80 @llvm.log2.f80(x86_fp80 %Val)
declare fp128 @llvm.log2.f128(fp128 %Val)
declare ppc_fp128 @llvm.log2.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.log2.*``' intrinsics compute the base-2 logarithm of the specified
value.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``log2``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_fma:
'``llvm.fma.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fma`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.fma.f32(float %a, float %b, float %c)
declare double @llvm.fma.f64(double %a, double %b, double %c)
declare x86_fp80 @llvm.fma.f80(x86_fp80 %a, x86_fp80 %b, x86_fp80 %c)
declare fp128 @llvm.fma.f128(fp128 %a, fp128 %b, fp128 %c)
declare ppc_fp128 @llvm.fma.ppcf128(ppc_fp128 %a, ppc_fp128 %b, ppc_fp128 %c)
Overview:
"""""""""
The '``llvm.fma.*``' intrinsics perform the fused multiply-add operation.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same type.
Semantics:
""""""""""
Return the same value as a corresponding libm '``fma``' function but without
trapping or setting ``errno``.
When specified with the fast-math-flag 'afn', the result may be approximated
using a less accurate calculation.
.. _int_fabs:
'``llvm.fabs.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fabs`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.fabs.f32(float %Val)
declare double @llvm.fabs.f64(double %Val)
declare x86_fp80 @llvm.fabs.f80(x86_fp80 %Val)
declare fp128 @llvm.fabs.f128(fp128 %Val)
declare ppc_fp128 @llvm.fabs.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.fabs.*``' intrinsics return the absolute value of the
operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``fabs`` functions
would, and handles error conditions in the same way.
The returned value is completely identical to the input except for the sign bit;
in particular, if the input is a NaN, then the quiet/signaling bit and payload
are perfectly preserved.
.. _i_minnum:
'``llvm.minnum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.minnum`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.minnum.f32(float %Val0, float %Val1)
declare double @llvm.minnum.f64(double %Val0, double %Val1)
declare x86_fp80 @llvm.minnum.f80(x86_fp80 %Val0, x86_fp80 %Val1)
declare fp128 @llvm.minnum.f128(fp128 %Val0, fp128 %Val1)
declare ppc_fp128 @llvm.minnum.ppcf128(ppc_fp128 %Val0, ppc_fp128 %Val1)
Overview:
"""""""""
The '``llvm.minnum.*``' intrinsics return the minimum of the two
arguments.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
Follows the IEEE-754 semantics for minNum, except for handling of
signaling NaNs. This match's the behavior of libm's fmin.
If either operand is a NaN, returns the other non-NaN operand. Returns
NaN only if both operands are NaN. If the operands compare equal,
returns either one of the operands. For example, this means that
fmin(+0.0, -0.0) returns either operand.
Unlike the IEEE-754 2008 behavior, this does not distinguish between
signaling and quiet NaN inputs. If a target's implementation follows
the standard and returns a quiet NaN if either input is a signaling
NaN, the intrinsic lowering is responsible for quieting the inputs to
correctly return the non-NaN input (e.g. by using the equivalent of
``llvm.canonicalize``).
.. _i_maxnum:
'``llvm.maxnum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.maxnum`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.maxnum.f32(float %Val0, float %Val1)
declare double @llvm.maxnum.f64(double %Val0, double %Val1)
declare x86_fp80 @llvm.maxnum.f80(x86_fp80 %Val0, x86_fp80 %Val1)
declare fp128 @llvm.maxnum.f128(fp128 %Val0, fp128 %Val1)
declare ppc_fp128 @llvm.maxnum.ppcf128(ppc_fp128 %Val0, ppc_fp128 %Val1)
Overview:
"""""""""
The '``llvm.maxnum.*``' intrinsics return the maximum of the two
arguments.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
Follows the IEEE-754 semantics for maxNum except for the handling of
signaling NaNs. This matches the behavior of libm's fmax.
If either operand is a NaN, returns the other non-NaN operand. Returns
NaN only if both operands are NaN. If the operands compare equal,
returns either one of the operands. For example, this means that
fmax(+0.0, -0.0) returns either -0.0 or 0.0.
Unlike the IEEE-754 2008 behavior, this does not distinguish between
signaling and quiet NaN inputs. If a target's implementation follows
the standard and returns a quiet NaN if either input is a signaling
NaN, the intrinsic lowering is responsible for quieting the inputs to
correctly return the non-NaN input (e.g. by using the equivalent of
``llvm.canonicalize``).
'``llvm.minimum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.minimum`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.minimum.f32(float %Val0, float %Val1)
declare double @llvm.minimum.f64(double %Val0, double %Val1)
declare x86_fp80 @llvm.minimum.f80(x86_fp80 %Val0, x86_fp80 %Val1)
declare fp128 @llvm.minimum.f128(fp128 %Val0, fp128 %Val1)
declare ppc_fp128 @llvm.minimum.ppcf128(ppc_fp128 %Val0, ppc_fp128 %Val1)
Overview:
"""""""""
The '``llvm.minimum.*``' intrinsics return the minimum of the two
arguments, propagating NaNs and treating -0.0 as less than +0.0.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
If either operand is a NaN, returns NaN. Otherwise returns the lesser
of the two arguments. -0.0 is considered to be less than +0.0 for this
intrinsic. Note that these are the semantics specified in the draft of
IEEE 754-2018.
'``llvm.maximum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.maximum`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.maximum.f32(float %Val0, float %Val1)
declare double @llvm.maximum.f64(double %Val0, double %Val1)
declare x86_fp80 @llvm.maximum.f80(x86_fp80 %Val0, x86_fp80 %Val1)
declare fp128 @llvm.maximum.f128(fp128 %Val0, fp128 %Val1)
declare ppc_fp128 @llvm.maximum.ppcf128(ppc_fp128 %Val0, ppc_fp128 %Val1)
Overview:
"""""""""
The '``llvm.maximum.*``' intrinsics return the maximum of the two
arguments, propagating NaNs and treating -0.0 as less than +0.0.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
If either operand is a NaN, returns NaN. Otherwise returns the greater
of the two arguments. -0.0 is considered to be less than +0.0 for this
intrinsic. Note that these are the semantics specified in the draft of
IEEE 754-2018.
.. _int_copysign:
'``llvm.copysign.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.copysign`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.copysign.f32(float %Mag, float %Sgn)
declare double @llvm.copysign.f64(double %Mag, double %Sgn)
declare x86_fp80 @llvm.copysign.f80(x86_fp80 %Mag, x86_fp80 %Sgn)
declare fp128 @llvm.copysign.f128(fp128 %Mag, fp128 %Sgn)
declare ppc_fp128 @llvm.copysign.ppcf128(ppc_fp128 %Mag, ppc_fp128 %Sgn)
Overview:
"""""""""
The '``llvm.copysign.*``' intrinsics return a value with the magnitude of the
first operand and the sign of the second operand.
Arguments:
""""""""""
The arguments and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``copysign``
functions would, and handles error conditions in the same way.
The returned value is completely identical to the first operand except for the
sign bit; in particular, if the input is a NaN, then the quiet/signaling bit and
payload are perfectly preserved.
.. _int_floor:
'``llvm.floor.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.floor`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.floor.f32(float %Val)
declare double @llvm.floor.f64(double %Val)
declare x86_fp80 @llvm.floor.f80(x86_fp80 %Val)
declare fp128 @llvm.floor.f128(fp128 %Val)
declare ppc_fp128 @llvm.floor.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.floor.*``' intrinsics return the floor of the operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``floor`` functions
would, and handles error conditions in the same way.
.. _int_ceil:
'``llvm.ceil.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.ceil`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.ceil.f32(float %Val)
declare double @llvm.ceil.f64(double %Val)
declare x86_fp80 @llvm.ceil.f80(x86_fp80 %Val)
declare fp128 @llvm.ceil.f128(fp128 %Val)
declare ppc_fp128 @llvm.ceil.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.ceil.*``' intrinsics return the ceiling of the operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``ceil`` functions
would, and handles error conditions in the same way.
.. _int_llvm_trunc:
'``llvm.trunc.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.trunc`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.trunc.f32(float %Val)
declare double @llvm.trunc.f64(double %Val)
declare x86_fp80 @llvm.trunc.f80(x86_fp80 %Val)
declare fp128 @llvm.trunc.f128(fp128 %Val)
declare ppc_fp128 @llvm.trunc.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.trunc.*``' intrinsics returns the operand rounded to the
nearest integer not larger in magnitude than the operand.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``trunc`` functions
would, and handles error conditions in the same way.
.. _int_rint:
'``llvm.rint.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.rint`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.rint.f32(float %Val)
declare double @llvm.rint.f64(double %Val)
declare x86_fp80 @llvm.rint.f80(x86_fp80 %Val)
declare fp128 @llvm.rint.f128(fp128 %Val)
declare ppc_fp128 @llvm.rint.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.rint.*``' intrinsics returns the operand rounded to the
nearest integer. It may raise an inexact floating-point exception if the
operand isn't an integer.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``rint`` functions
would, and handles error conditions in the same way.
.. _int_nearbyint:
'``llvm.nearbyint.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.nearbyint`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.nearbyint.f32(float %Val)
declare double @llvm.nearbyint.f64(double %Val)
declare x86_fp80 @llvm.nearbyint.f80(x86_fp80 %Val)
declare fp128 @llvm.nearbyint.f128(fp128 %Val)
declare ppc_fp128 @llvm.nearbyint.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.nearbyint.*``' intrinsics returns the operand rounded to the
nearest integer.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``nearbyint``
functions would, and handles error conditions in the same way.
.. _int_round:
'``llvm.round.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.round`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.round.f32(float %Val)
declare double @llvm.round.f64(double %Val)
declare x86_fp80 @llvm.round.f80(x86_fp80 %Val)
declare fp128 @llvm.round.f128(fp128 %Val)
declare ppc_fp128 @llvm.round.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.round.*``' intrinsics returns the operand rounded to the
nearest integer.
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same
type.
Semantics:
""""""""""
This function returns the same values as the libm ``round``
functions would, and handles error conditions in the same way.
.. _int_roundeven:
'``llvm.roundeven.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.roundeven`` on any
floating-point or vector of floating-point type. Not all targets support
all types however.
::
declare float @llvm.roundeven.f32(float %Val)
declare double @llvm.roundeven.f64(double %Val)
declare x86_fp80 @llvm.roundeven.f80(x86_fp80 %Val)
declare fp128 @llvm.roundeven.f128(fp128 %Val)
declare ppc_fp128 @llvm.roundeven.ppcf128(ppc_fp128 %Val)
Overview:
"""""""""
The '``llvm.roundeven.*``' intrinsics returns the operand rounded to the nearest
integer in floating-point format rounding halfway cases to even (that is, to the
nearest value that is an even integer).
Arguments:
""""""""""
The argument and return value are floating-point numbers of the same type.
Semantics:
""""""""""
This function implements IEEE-754 operation ``roundToIntegralTiesToEven``. It
also behaves in the same way as C standard function ``roundeven``, except that
it does not raise floating point exceptions.
'``llvm.lround.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.lround`` on any
floating-point type. Not all targets support all types however.
::
declare i32 @llvm.lround.i32.f32(float %Val)
declare i32 @llvm.lround.i32.f64(double %Val)
declare i32 @llvm.lround.i32.f80(float %Val)
declare i32 @llvm.lround.i32.f128(double %Val)
declare i32 @llvm.lround.i32.ppcf128(double %Val)
declare i64 @llvm.lround.i64.f32(float %Val)
declare i64 @llvm.lround.i64.f64(double %Val)
declare i64 @llvm.lround.i64.f80(float %Val)
declare i64 @llvm.lround.i64.f128(double %Val)
declare i64 @llvm.lround.i64.ppcf128(double %Val)
Overview:
"""""""""
The '``llvm.lround.*``' intrinsics return the operand rounded to the nearest
integer with ties away from zero.
Arguments:
""""""""""
The argument is a floating-point number and the return value is an integer
type.
Semantics:
""""""""""
This function returns the same values as the libm ``lround`` functions
would, but without setting errno. If the rounded value is too large to
be stored in the result type, the return value is a non-deterministic
value (equivalent to `freeze poison`).
'``llvm.llround.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.llround`` on any
floating-point type. Not all targets support all types however.
::
declare i64 @llvm.lround.i64.f32(float %Val)
declare i64 @llvm.lround.i64.f64(double %Val)
declare i64 @llvm.lround.i64.f80(float %Val)
declare i64 @llvm.lround.i64.f128(double %Val)
declare i64 @llvm.lround.i64.ppcf128(double %Val)
Overview:
"""""""""
The '``llvm.llround.*``' intrinsics return the operand rounded to the nearest
integer with ties away from zero.
Arguments:
""""""""""
The argument is a floating-point number and the return value is an integer
type.
Semantics:
""""""""""
This function returns the same values as the libm ``llround``
functions would, but without setting errno. If the rounded value is
too large to be stored in the result type, the return value is a
non-deterministic value (equivalent to `freeze poison`).
'``llvm.lrint.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.lrint`` on any
floating-point type or vector of floating-point type. Not all targets
support all types however.
::
declare i32 @llvm.lrint.i32.f32(float %Val)
declare i32 @llvm.lrint.i32.f64(double %Val)
declare i32 @llvm.lrint.i32.f80(float %Val)
declare i32 @llvm.lrint.i32.f128(double %Val)
declare i32 @llvm.lrint.i32.ppcf128(double %Val)
declare i64 @llvm.lrint.i64.f32(float %Val)
declare i64 @llvm.lrint.i64.f64(double %Val)
declare i64 @llvm.lrint.i64.f80(float %Val)
declare i64 @llvm.lrint.i64.f128(double %Val)
declare i64 @llvm.lrint.i64.ppcf128(double %Val)
Overview:
"""""""""
The '``llvm.lrint.*``' intrinsics return the operand rounded to the nearest
integer.
Arguments:
""""""""""
The argument is a floating-point number and the return value is an integer
type.
Semantics:
""""""""""
This function returns the same values as the libm ``lrint`` functions
would, but without setting errno. If the rounded value is too large to
be stored in the result type, the return value is a non-deterministic
value (equivalent to `freeze poison`).
'``llvm.llrint.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.llrint`` on any
floating-point type or vector of floating-point type. Not all targets
support all types however.
::
declare i64 @llvm.llrint.i64.f32(float %Val)
declare i64 @llvm.llrint.i64.f64(double %Val)
declare i64 @llvm.llrint.i64.f80(float %Val)
declare i64 @llvm.llrint.i64.f128(double %Val)
declare i64 @llvm.llrint.i64.ppcf128(double %Val)
Overview:
"""""""""
The '``llvm.llrint.*``' intrinsics return the operand rounded to the nearest
integer.
Arguments:
""""""""""
The argument is a floating-point number and the return value is an integer
type.
Semantics:
""""""""""
This function returns the same values as the libm ``llrint`` functions
would, but without setting errno. If the rounded value is too large to
be stored in the result type, the return value is a non-deterministic
value (equivalent to `freeze poison`).
Bit Manipulation Intrinsics
---------------------------
LLVM provides intrinsics for a few important bit manipulation
operations. These allow efficient code generation for some algorithms.
.. _int_bitreverse:
'``llvm.bitreverse.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic function. You can use bitreverse on any
integer type.
::
declare i16 @llvm.bitreverse.i16(i16 <id>)
declare i32 @llvm.bitreverse.i32(i32 <id>)
declare i64 @llvm.bitreverse.i64(i64 <id>)
declare <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> <id>)
Overview:
"""""""""
The '``llvm.bitreverse``' family of intrinsics is used to reverse the
bitpattern of an integer value or vector of integer values; for example
``0b10110110`` becomes ``0b01101101``.
Semantics:
""""""""""
The ``llvm.bitreverse.iN`` intrinsic returns an iN value that has bit
``M`` in the input moved to bit ``N-M-1`` in the output. The vector
intrinsics, such as ``llvm.bitreverse.v4i32``, operate on a per-element
basis and the element order is not affected.
.. _int_bswap:
'``llvm.bswap.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic function. You can use bswap on any
integer type that is an even number of bytes (i.e. BitWidth % 16 == 0).
::
declare i16 @llvm.bswap.i16(i16 <id>)
declare i32 @llvm.bswap.i32(i32 <id>)
declare i64 @llvm.bswap.i64(i64 <id>)
declare <4 x i32> @llvm.bswap.v4i32(<4 x i32> <id>)
Overview:
"""""""""
The '``llvm.bswap``' family of intrinsics is used to byte swap an integer
value or vector of integer values with an even number of bytes (positive
multiple of 16 bits).
Semantics:
""""""""""
The ``llvm.bswap.i16`` intrinsic returns an i16 value that has the high
and low byte of the input i16 swapped. Similarly, the ``llvm.bswap.i32``
intrinsic returns an i32 value that has the four bytes of the input i32
swapped, so that if the input bytes are numbered 0, 1, 2, 3 then the
returned i32 will have its bytes in 3, 2, 1, 0 order. The
``llvm.bswap.i48``, ``llvm.bswap.i64`` and other intrinsics extend this
concept to additional even-byte lengths (6 bytes, 8 bytes and more,
respectively). The vector intrinsics, such as ``llvm.bswap.v4i32``,
operate on a per-element basis and the element order is not affected.
.. _int_ctpop:
'``llvm.ctpop.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use llvm.ctpop on any integer
bit width, or on any vector with integer elements. Not all targets
support all bit widths or vector types, however.
::
declare i8 @llvm.ctpop.i8(i8 <src>)
declare i16 @llvm.ctpop.i16(i16 <src>)
declare i32 @llvm.ctpop.i32(i32 <src>)
declare i64 @llvm.ctpop.i64(i64 <src>)
declare i256 @llvm.ctpop.i256(i256 <src>)
declare <2 x i32> @llvm.ctpop.v2i32(<2 x i32> <src>)
Overview:
"""""""""
The '``llvm.ctpop``' family of intrinsics counts the number of bits set
in a value.
Arguments:
""""""""""
The only argument is the value to be counted. The argument may be of any
integer type, or a vector with integer elements. The return type must
match the argument type.
Semantics:
""""""""""
The '``llvm.ctpop``' intrinsic counts the 1's in a variable, or within
each element of a vector.
.. _int_ctlz:
'``llvm.ctlz.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.ctlz`` on any
integer bit width, or any vector whose elements are integers. Not all
targets support all bit widths or vector types, however.
::
declare i8 @llvm.ctlz.i8 (i8 <src>, i1 <is_zero_poison>)
declare <2 x i37> @llvm.ctlz.v2i37(<2 x i37> <src>, i1 <is_zero_poison>)
Overview:
"""""""""
The '``llvm.ctlz``' family of intrinsic functions counts the number of
leading zeros in a variable.
Arguments:
""""""""""
The first argument is the value to be counted. This argument may be of
any integer type, or a vector with integer element type. The return
type must match the first argument type.
The second argument is a constant flag that indicates whether the intrinsic
returns a valid result if the first argument is zero. If the first
argument is zero and the second argument is true, the result is poison.
Historically some architectures did not provide a defined result for zero
values as efficiently, and many algorithms are now predicated on avoiding
zero-value inputs.
Semantics:
""""""""""
The '``llvm.ctlz``' intrinsic counts the leading (most significant)
zeros in a variable, or within each element of the vector. If
``src == 0`` then the result is the size in bits of the type of ``src``
if ``is_zero_poison == 0`` and ``poison`` otherwise. For example,
``llvm.ctlz(i32 2) = 30``.
.. _int_cttz:
'``llvm.cttz.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.cttz`` on any
integer bit width, or any vector of integer elements. Not all targets
support all bit widths or vector types, however.
::
declare i42 @llvm.cttz.i42 (i42 <src>, i1 <is_zero_poison>)
declare <2 x i32> @llvm.cttz.v2i32(<2 x i32> <src>, i1 <is_zero_poison>)
Overview:
"""""""""
The '``llvm.cttz``' family of intrinsic functions counts the number of
trailing zeros.
Arguments:
""""""""""
The first argument is the value to be counted. This argument may be of
any integer type, or a vector with integer element type. The return
type must match the first argument type.
The second argument is a constant flag that indicates whether the intrinsic
returns a valid result if the first argument is zero. If the first
argument is zero and the second argument is true, the result is poison.
Historically some architectures did not provide a defined result for zero
values as efficiently, and many algorithms are now predicated on avoiding
zero-value inputs.
Semantics:
""""""""""
The '``llvm.cttz``' intrinsic counts the trailing (least significant)
zeros in a variable, or within each element of a vector. If ``src == 0``
then the result is the size in bits of the type of ``src`` if
``is_zero_poison == 0`` and ``poison`` otherwise. For example,
``llvm.cttz(2) = 1``.
.. _int_overflow:
.. _int_fshl:
'``llvm.fshl.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fshl`` on any
integer bit width or any vector of integer elements. Not all targets
support all bit widths or vector types, however.
::
declare i8 @llvm.fshl.i8 (i8 %a, i8 %b, i8 %c)
declare i64 @llvm.fshl.i64(i64 %a, i64 %b, i64 %c)
declare <2 x i32> @llvm.fshl.v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c)
Overview:
"""""""""
The '``llvm.fshl``' family of intrinsic functions performs a funnel shift left:
the first two values are concatenated as { %a : %b } (%a is the most significant
bits of the wide value), the combined value is shifted left, and the most
significant bits are extracted to produce a result that is the same size as the
original arguments. If the first 2 arguments are identical, this is equivalent
to a rotate left operation. For vector types, the operation occurs for each
element of the vector. The shift argument is treated as an unsigned amount
modulo the element size of the arguments.
Arguments:
""""""""""
The first two arguments are the values to be concatenated. The third
argument is the shift amount. The arguments may be any integer type or a
vector with integer element type. All arguments and the return value must
have the same type.
Example:
""""""""
.. code-block:: text
%r = call i8 @llvm.fshl.i8(i8 %x, i8 %y, i8 %z) ; %r = i8: msb_extract((concat(x, y) << (z % 8)), 8)
%r = call i8 @llvm.fshl.i8(i8 255, i8 0, i8 15) ; %r = i8: 128 (0b10000000)
%r = call i8 @llvm.fshl.i8(i8 15, i8 15, i8 11) ; %r = i8: 120 (0b01111000)
%r = call i8 @llvm.fshl.i8(i8 0, i8 255, i8 8) ; %r = i8: 0 (0b00000000)
.. _int_fshr:
'``llvm.fshr.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fshr`` on any
integer bit width or any vector of integer elements. Not all targets
support all bit widths or vector types, however.
::
declare i8 @llvm.fshr.i8 (i8 %a, i8 %b, i8 %c)
declare i64 @llvm.fshr.i64(i64 %a, i64 %b, i64 %c)
declare <2 x i32> @llvm.fshr.v2i32(<2 x i32> %a, <2 x i32> %b, <2 x i32> %c)
Overview:
"""""""""
The '``llvm.fshr``' family of intrinsic functions performs a funnel shift right:
the first two values are concatenated as { %a : %b } (%a is the most significant
bits of the wide value), the combined value is shifted right, and the least
significant bits are extracted to produce a result that is the same size as the
original arguments. If the first 2 arguments are identical, this is equivalent
to a rotate right operation. For vector types, the operation occurs for each
element of the vector. The shift argument is treated as an unsigned amount
modulo the element size of the arguments.
Arguments:
""""""""""
The first two arguments are the values to be concatenated. The third
argument is the shift amount. The arguments may be any integer type or a
vector with integer element type. All arguments and the return value must
have the same type.
Example:
""""""""
.. code-block:: text
%r = call i8 @llvm.fshr.i8(i8 %x, i8 %y, i8 %z) ; %r = i8: lsb_extract((concat(x, y) >> (z % 8)), 8)
%r = call i8 @llvm.fshr.i8(i8 255, i8 0, i8 15) ; %r = i8: 254 (0b11111110)
%r = call i8 @llvm.fshr.i8(i8 15, i8 15, i8 11) ; %r = i8: 225 (0b11100001)
%r = call i8 @llvm.fshr.i8(i8 0, i8 255, i8 8) ; %r = i8: 255 (0b11111111)
Arithmetic with Overflow Intrinsics
-----------------------------------
LLVM provides intrinsics for fast arithmetic overflow checking.
Each of these intrinsics returns a two-element struct. The first
element of this struct contains the result of the corresponding
arithmetic operation modulo 2\ :sup:`n`\ , where n is the bit width of
the result. Therefore, for example, the first element of the struct
returned by ``llvm.sadd.with.overflow.i32`` is always the same as the
result of a 32-bit ``add`` instruction with the same operands, where
the ``add`` is *not* modified by an ``nsw`` or ``nuw`` flag.
The second element of the result is an ``i1`` that is 1 if the
arithmetic operation overflowed and 0 otherwise. An operation
overflows if, for any values of its operands ``A`` and ``B`` and for
any ``N`` larger than the operands' width, ``ext(A op B) to iN`` is
not equal to ``(ext(A) to iN) op (ext(B) to iN)`` where ``ext`` is
``sext`` for signed overflow and ``zext`` for unsigned overflow, and
``op`` is the underlying arithmetic operation.
The behavior of these intrinsics is well-defined for all argument
values.
'``llvm.sadd.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.sadd.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.sadd.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.sadd.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.sadd.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.sadd.with.overflow``' family of intrinsic functions perform
a signed addition of the two arguments, and indicate whether an overflow
occurred during the signed summation.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo signed
addition.
Semantics:
""""""""""
The '``llvm.sadd.with.overflow``' family of intrinsic functions perform
a signed addition of the two variables. They return a structure --- the
first element of which is the signed summation, and the second element
of which is a bit specifying if the signed summation resulted in an
overflow.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.sadd.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %overflow, label %normal
'``llvm.uadd.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.uadd.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.uadd.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.uadd.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.uadd.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.uadd.with.overflow``' family of intrinsic functions perform
an unsigned addition of the two arguments, and indicate whether a carry
occurred during the unsigned summation.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo unsigned
addition.
Semantics:
""""""""""
The '``llvm.uadd.with.overflow``' family of intrinsic functions perform
an unsigned addition of the two arguments. They return a structure --- the
first element of which is the sum, and the second element of which is a
bit specifying if the unsigned summation resulted in a carry.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %carry, label %normal
'``llvm.ssub.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.ssub.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.ssub.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.ssub.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.ssub.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.ssub.with.overflow``' family of intrinsic functions perform
a signed subtraction of the two arguments, and indicate whether an
overflow occurred during the signed subtraction.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo signed
subtraction.
Semantics:
""""""""""
The '``llvm.ssub.with.overflow``' family of intrinsic functions perform
a signed subtraction of the two arguments. They return a structure --- the
first element of which is the subtraction, and the second element of
which is a bit specifying if the signed subtraction resulted in an
overflow.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.ssub.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %overflow, label %normal
'``llvm.usub.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.usub.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.usub.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.usub.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.usub.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.usub.with.overflow``' family of intrinsic functions perform
an unsigned subtraction of the two arguments, and indicate whether an
overflow occurred during the unsigned subtraction.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo unsigned
subtraction.
Semantics:
""""""""""
The '``llvm.usub.with.overflow``' family of intrinsic functions perform
an unsigned subtraction of the two arguments. They return a structure ---
the first element of which is the subtraction, and the second element of
which is a bit specifying if the unsigned subtraction resulted in an
overflow.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.usub.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %overflow, label %normal
'``llvm.smul.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.smul.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.smul.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.smul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.smul.with.overflow``' family of intrinsic functions perform
a signed multiplication of the two arguments, and indicate whether an
overflow occurred during the signed multiplication.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo signed
multiplication.
Semantics:
""""""""""
The '``llvm.smul.with.overflow``' family of intrinsic functions perform
a signed multiplication of the two arguments. They return a structure ---
the first element of which is the multiplication, and the second element
of which is a bit specifying if the signed multiplication resulted in an
overflow.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %overflow, label %normal
'``llvm.umul.with.overflow.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.umul.with.overflow``
on any integer bit width or vectors of integers.
::
declare {i16, i1} @llvm.umul.with.overflow.i16(i16 %a, i16 %b)
declare {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
declare {i64, i1} @llvm.umul.with.overflow.i64(i64 %a, i64 %b)
declare {<4 x i32>, <4 x i1>} @llvm.umul.with.overflow.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview:
"""""""""
The '``llvm.umul.with.overflow``' family of intrinsic functions perform
a unsigned multiplication of the two arguments, and indicate whether an
overflow occurred during the unsigned multiplication.
Arguments:
""""""""""
The arguments (%a and %b) and the first element of the result structure
may be of integer types of any bit width, but they must have the same
bit width. The second element of the result structure must be of type
``i1``. ``%a`` and ``%b`` are the two values that will undergo unsigned
multiplication.
Semantics:
""""""""""
The '``llvm.umul.with.overflow``' family of intrinsic functions perform
an unsigned multiplication of the two arguments. They return a structure ---
the first element of which is the multiplication, and the second
element of which is a bit specifying if the unsigned multiplication
resulted in an overflow.
Examples:
"""""""""
.. code-block:: llvm
%res = call {i32, i1} @llvm.umul.with.overflow.i32(i32 %a, i32 %b)
%sum = extractvalue {i32, i1} %res, 0
%obit = extractvalue {i32, i1} %res, 1
br i1 %obit, label %overflow, label %normal
Saturation Arithmetic Intrinsics
---------------------------------
Saturation arithmetic is a version of arithmetic in which operations are
limited to a fixed range between a minimum and maximum value. If the result of
an operation is greater than the maximum value, the result is set (or
"clamped") to this maximum. If it is below the minimum, it is clamped to this
minimum.
'``llvm.sadd.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.sadd.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.sadd.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.sadd.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.sadd.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.sadd.sat``' family of intrinsic functions perform signed
saturating addition on the 2 arguments.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo signed addition.
Semantics:
""""""""""
The maximum value this operation can clamp to is the largest signed value
representable by the bit width of the arguments. The minimum value is the
smallest signed value representable by this bit width.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.sadd.sat.i4(i4 1, i4 2) ; %res = 3
%res = call i4 @llvm.sadd.sat.i4(i4 5, i4 6) ; %res = 7
%res = call i4 @llvm.sadd.sat.i4(i4 -4, i4 2) ; %res = -2
%res = call i4 @llvm.sadd.sat.i4(i4 -4, i4 -5) ; %res = -8
'``llvm.uadd.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.uadd.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.uadd.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.uadd.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.uadd.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.uadd.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.uadd.sat``' family of intrinsic functions perform unsigned
saturating addition on the 2 arguments.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo unsigned addition.
Semantics:
""""""""""
The maximum value this operation can clamp to is the largest unsigned value
representable by the bit width of the arguments. Because this is an unsigned
operation, the result will never saturate towards zero.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.uadd.sat.i4(i4 1, i4 2) ; %res = 3
%res = call i4 @llvm.uadd.sat.i4(i4 5, i4 6) ; %res = 11
%res = call i4 @llvm.uadd.sat.i4(i4 8, i4 8) ; %res = 15
'``llvm.ssub.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.ssub.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.ssub.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.ssub.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.ssub.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.ssub.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.ssub.sat``' family of intrinsic functions perform signed
saturating subtraction on the 2 arguments.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo signed subtraction.
Semantics:
""""""""""
The maximum value this operation can clamp to is the largest signed value
representable by the bit width of the arguments. The minimum value is the
smallest signed value representable by this bit width.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.ssub.sat.i4(i4 2, i4 1) ; %res = 1
%res = call i4 @llvm.ssub.sat.i4(i4 2, i4 6) ; %res = -4
%res = call i4 @llvm.ssub.sat.i4(i4 -4, i4 5) ; %res = -8
%res = call i4 @llvm.ssub.sat.i4(i4 4, i4 -5) ; %res = 7
'``llvm.usub.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.usub.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.usub.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.usub.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.usub.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.usub.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.usub.sat``' family of intrinsic functions perform unsigned
saturating subtraction on the 2 arguments.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo unsigned subtraction.
Semantics:
""""""""""
The minimum value this operation can clamp to is 0, which is the smallest
unsigned value representable by the bit width of the unsigned arguments.
Because this is an unsigned operation, the result will never saturate towards
the largest possible value representable by this bit width.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.usub.sat.i4(i4 2, i4 1) ; %res = 1
%res = call i4 @llvm.usub.sat.i4(i4 2, i4 6) ; %res = 0
'``llvm.sshl.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.sshl.sat``
on integers or vectors of integers of any bit width.
::
declare i16 @llvm.sshl.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.sshl.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.sshl.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.sshl.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.sshl.sat``' family of intrinsic functions perform signed
saturating left shift on the first argument.
Arguments
""""""""""
The arguments (``%a`` and ``%b``) and the result may be of integer types of any
bit width, but they must have the same bit width. ``%a`` is the value to be
shifted, and ``%b`` is the amount to shift by. If ``b`` is (statically or
dynamically) equal to or larger than the integer bit width of the arguments,
the result is a :ref:`poison value <poisonvalues>`. If the arguments are
vectors, each vector element of ``a`` is shifted by the corresponding shift
amount in ``b``.
Semantics:
""""""""""
The maximum value this operation can clamp to is the largest signed value
representable by the bit width of the arguments. The minimum value is the
smallest signed value representable by this bit width.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.sshl.sat.i4(i4 2, i4 1) ; %res = 4
%res = call i4 @llvm.sshl.sat.i4(i4 2, i4 2) ; %res = 7
%res = call i4 @llvm.sshl.sat.i4(i4 -5, i4 1) ; %res = -8
%res = call i4 @llvm.sshl.sat.i4(i4 -1, i4 1) ; %res = -2
'``llvm.ushl.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.ushl.sat``
on integers or vectors of integers of any bit width.
::
declare i16 @llvm.ushl.sat.i16(i16 %a, i16 %b)
declare i32 @llvm.ushl.sat.i32(i32 %a, i32 %b)
declare i64 @llvm.ushl.sat.i64(i64 %a, i64 %b)
declare <4 x i32> @llvm.ushl.sat.v4i32(<4 x i32> %a, <4 x i32> %b)
Overview
"""""""""
The '``llvm.ushl.sat``' family of intrinsic functions perform unsigned
saturating left shift on the first argument.
Arguments
""""""""""
The arguments (``%a`` and ``%b``) and the result may be of integer types of any
bit width, but they must have the same bit width. ``%a`` is the value to be
shifted, and ``%b`` is the amount to shift by. If ``b`` is (statically or
dynamically) equal to or larger than the integer bit width of the arguments,
the result is a :ref:`poison value <poisonvalues>`. If the arguments are
vectors, each vector element of ``a`` is shifted by the corresponding shift
amount in ``b``.
Semantics:
""""""""""
The maximum value this operation can clamp to is the largest unsigned value
representable by the bit width of the arguments.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.ushl.sat.i4(i4 2, i4 1) ; %res = 4
%res = call i4 @llvm.ushl.sat.i4(i4 3, i4 3) ; %res = 15
Fixed Point Arithmetic Intrinsics
---------------------------------
A fixed point number represents a real data type for a number that has a fixed
number of digits after a radix point (equivalent to the decimal point '.').
The number of digits after the radix point is referred as the `scale`. These
are useful for representing fractional values to a specific precision. The
following intrinsics perform fixed point arithmetic operations on 2 operands
of the same scale, specified as the third argument.
The ``llvm.*mul.fix`` family of intrinsic functions represents a multiplication
of fixed point numbers through scaled integers. Therefore, fixed point
multiplication can be represented as
.. code-block:: llvm
%result = call i4 @llvm.smul.fix.i4(i4 %a, i4 %b, i32 %scale)
; Expands to
%a2 = sext i4 %a to i8
%b2 = sext i4 %b to i8
%mul = mul nsw nuw i8 %a2, %b2
%scale2 = trunc i32 %scale to i8
%r = ashr i8 %mul, i8 %scale2 ; this is for a target rounding down towards negative infinity
%result = trunc i8 %r to i4
The ``llvm.*div.fix`` family of intrinsic functions represents a division of
fixed point numbers through scaled integers. Fixed point division can be
represented as:
.. code-block:: llvm
%result call i4 @llvm.sdiv.fix.i4(i4 %a, i4 %b, i32 %scale)
; Expands to
%a2 = sext i4 %a to i8
%b2 = sext i4 %b to i8
%scale2 = trunc i32 %scale to i8
%a3 = shl i8 %a2, %scale2
%r = sdiv i8 %a3, %b2 ; this is for a target rounding towards zero
%result = trunc i8 %r to i4
For each of these functions, if the result cannot be represented exactly with
the provided scale, the result is rounded. Rounding is unspecified since
preferred rounding may vary for different targets. Rounding is specified
through a target hook. Different pipelines should legalize or optimize this
using the rounding specified by this hook if it is provided. Operations like
constant folding, instruction combining, KnownBits, and ValueTracking should
also use this hook, if provided, and not assume the direction of rounding. A
rounded result must always be within one unit of precision from the true
result. That is, the error between the returned result and the true result must
be less than 1/2^(scale).
'``llvm.smul.fix.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.smul.fix``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.smul.fix.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.smul.fix.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.smul.fix.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.smul.fix``' family of intrinsic functions perform signed
fixed point multiplication on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. The arguments may also work with
int vectors of the same length and int size. ``%a`` and ``%b`` are the two
values that will undergo signed fixed point multiplication. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point multiplication on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
It is undefined behavior if the result value does not fit within the range of
the fixed point type.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.smul.fix.i4(i4 3, i4 2, i32 0) ; %res = 6 (2 x 3 = 6)
%res = call i4 @llvm.smul.fix.i4(i4 3, i4 2, i32 1) ; %res = 3 (1.5 x 1 = 1.5)
%res = call i4 @llvm.smul.fix.i4(i4 3, i4 -2, i32 1) ; %res = -3 (1.5 x -1 = -1.5)
; The result in the following could be rounded up to -2 or down to -2.5
%res = call i4 @llvm.smul.fix.i4(i4 3, i4 -3, i32 1) ; %res = -5 (or -4) (1.5 x -1.5 = -2.25)
'``llvm.umul.fix.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.umul.fix``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.umul.fix.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.umul.fix.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.umul.fix.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.umul.fix.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.umul.fix``' family of intrinsic functions perform unsigned
fixed point multiplication on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. The arguments may also work with
int vectors of the same length and int size. ``%a`` and ``%b`` are the two
values that will undergo unsigned fixed point multiplication. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs unsigned fixed point multiplication on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
It is undefined behavior if the result value does not fit within the range of
the fixed point type.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.umul.fix.i4(i4 3, i4 2, i32 0) ; %res = 6 (2 x 3 = 6)
%res = call i4 @llvm.umul.fix.i4(i4 3, i4 2, i32 1) ; %res = 3 (1.5 x 1 = 1.5)
; The result in the following could be rounded down to 3.5 or up to 4
%res = call i4 @llvm.umul.fix.i4(i4 15, i4 1, i32 1) ; %res = 7 (or 8) (7.5 x 0.5 = 3.75)
'``llvm.smul.fix.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.smul.fix.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.smul.fix.sat.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.smul.fix.sat.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.smul.fix.sat.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.smul.fix.sat.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.smul.fix.sat``' family of intrinsic functions perform signed
fixed point saturating multiplication on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo signed fixed point multiplication. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point multiplication on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
The maximum value this operation can clamp to is the largest signed value
representable by the bit width of the first 2 arguments. The minimum value is the
smallest signed value representable by this bit width.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.smul.fix.sat.i4(i4 3, i4 2, i32 0) ; %res = 6 (2 x 3 = 6)
%res = call i4 @llvm.smul.fix.sat.i4(i4 3, i4 2, i32 1) ; %res = 3 (1.5 x 1 = 1.5)
%res = call i4 @llvm.smul.fix.sat.i4(i4 3, i4 -2, i32 1) ; %res = -3 (1.5 x -1 = -1.5)
; The result in the following could be rounded up to -2 or down to -2.5
%res = call i4 @llvm.smul.fix.sat.i4(i4 3, i4 -3, i32 1) ; %res = -5 (or -4) (1.5 x -1.5 = -2.25)
; Saturation
%res = call i4 @llvm.smul.fix.sat.i4(i4 7, i4 2, i32 0) ; %res = 7
%res = call i4 @llvm.smul.fix.sat.i4(i4 7, i4 4, i32 2) ; %res = 7
%res = call i4 @llvm.smul.fix.sat.i4(i4 -8, i4 5, i32 2) ; %res = -8
%res = call i4 @llvm.smul.fix.sat.i4(i4 -8, i4 -2, i32 1) ; %res = 7
; Scale can affect the saturation result
%res = call i4 @llvm.smul.fix.sat.i4(i4 2, i4 4, i32 0) ; %res = 7 (2 x 4 -> clamped to 7)
%res = call i4 @llvm.smul.fix.sat.i4(i4 2, i4 4, i32 1) ; %res = 4 (1 x 2 = 2)
'``llvm.umul.fix.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.umul.fix.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.umul.fix.sat.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.umul.fix.sat.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.umul.fix.sat.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.umul.fix.sat.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.umul.fix.sat``' family of intrinsic functions perform unsigned
fixed point saturating multiplication on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo unsigned fixed point multiplication. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point multiplication on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
The maximum value this operation can clamp to is the largest unsigned value
representable by the bit width of the first 2 arguments. The minimum value is the
smallest unsigned value representable by this bit width (zero).
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.umul.fix.sat.i4(i4 3, i4 2, i32 0) ; %res = 6 (2 x 3 = 6)
%res = call i4 @llvm.umul.fix.sat.i4(i4 3, i4 2, i32 1) ; %res = 3 (1.5 x 1 = 1.5)
; The result in the following could be rounded down to 2 or up to 2.5
%res = call i4 @llvm.umul.fix.sat.i4(i4 3, i4 3, i32 1) ; %res = 4 (or 5) (1.5 x 1.5 = 2.25)
; Saturation
%res = call i4 @llvm.umul.fix.sat.i4(i4 8, i4 2, i32 0) ; %res = 15 (8 x 2 -> clamped to 15)
%res = call i4 @llvm.umul.fix.sat.i4(i4 8, i4 8, i32 2) ; %res = 15 (2 x 2 -> clamped to 3.75)
; Scale can affect the saturation result
%res = call i4 @llvm.umul.fix.sat.i4(i4 2, i4 4, i32 0) ; %res = 7 (2 x 4 -> clamped to 7)
%res = call i4 @llvm.umul.fix.sat.i4(i4 2, i4 4, i32 1) ; %res = 4 (1 x 2 = 2)
'``llvm.sdiv.fix.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.sdiv.fix``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.sdiv.fix.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.sdiv.fix.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.sdiv.fix.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.sdiv.fix.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.sdiv.fix``' family of intrinsic functions perform signed
fixed point division on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. The arguments may also work with
int vectors of the same length and int size. ``%a`` and ``%b`` are the two
values that will undergo signed fixed point division. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point division on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
It is undefined behavior if the result value does not fit within the range of
the fixed point type, or if the second argument is zero.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.sdiv.fix.i4(i4 6, i4 2, i32 0) ; %res = 3 (6 / 2 = 3)
%res = call i4 @llvm.sdiv.fix.i4(i4 6, i4 4, i32 1) ; %res = 3 (3 / 2 = 1.5)
%res = call i4 @llvm.sdiv.fix.i4(i4 3, i4 -2, i32 1) ; %res = -3 (1.5 / -1 = -1.5)
; The result in the following could be rounded up to 1 or down to 0.5
%res = call i4 @llvm.sdiv.fix.i4(i4 3, i4 4, i32 1) ; %res = 2 (or 1) (1.5 / 2 = 0.75)
'``llvm.udiv.fix.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.udiv.fix``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.udiv.fix.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.udiv.fix.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.udiv.fix.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.udiv.fix.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.udiv.fix``' family of intrinsic functions perform unsigned
fixed point division on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. The arguments may also work with
int vectors of the same length and int size. ``%a`` and ``%b`` are the two
values that will undergo unsigned fixed point division. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point division on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
It is undefined behavior if the result value does not fit within the range of
the fixed point type, or if the second argument is zero.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.udiv.fix.i4(i4 6, i4 2, i32 0) ; %res = 3 (6 / 2 = 3)
%res = call i4 @llvm.udiv.fix.i4(i4 6, i4 4, i32 1) ; %res = 3 (3 / 2 = 1.5)
%res = call i4 @llvm.udiv.fix.i4(i4 1, i4 -8, i32 4) ; %res = 2 (0.0625 / 0.5 = 0.125)
; The result in the following could be rounded up to 1 or down to 0.5
%res = call i4 @llvm.udiv.fix.i4(i4 3, i4 4, i32 1) ; %res = 2 (or 1) (1.5 / 2 = 0.75)
'``llvm.sdiv.fix.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.sdiv.fix.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.sdiv.fix.sat.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.sdiv.fix.sat.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.sdiv.fix.sat.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.sdiv.fix.sat.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.sdiv.fix.sat``' family of intrinsic functions perform signed
fixed point saturating division on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo signed fixed point division. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point division on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
The maximum value this operation can clamp to is the largest signed value
representable by the bit width of the first 2 arguments. The minimum value is the
smallest signed value representable by this bit width.
It is undefined behavior if the second argument is zero.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 6, i4 2, i32 0) ; %res = 3 (6 / 2 = 3)
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 6, i4 4, i32 1) ; %res = 3 (3 / 2 = 1.5)
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 3, i4 -2, i32 1) ; %res = -3 (1.5 / -1 = -1.5)
; The result in the following could be rounded up to 1 or down to 0.5
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 3, i4 4, i32 1) ; %res = 2 (or 1) (1.5 / 2 = 0.75)
; Saturation
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 -8, i4 -1, i32 0) ; %res = 7 (-8 / -1 = 8 => 7)
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 4, i4 2, i32 2) ; %res = 7 (1 / 0.5 = 2 => 1.75)
%res = call i4 @llvm.sdiv.fix.sat.i4(i4 -4, i4 1, i32 2) ; %res = -8 (-1 / 0.25 = -4 => -2)
'``llvm.udiv.fix.sat.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax
"""""""
This is an overloaded intrinsic. You can use ``llvm.udiv.fix.sat``
on any integer bit width or vectors of integers.
::
declare i16 @llvm.udiv.fix.sat.i16(i16 %a, i16 %b, i32 %scale)
declare i32 @llvm.udiv.fix.sat.i32(i32 %a, i32 %b, i32 %scale)
declare i64 @llvm.udiv.fix.sat.i64(i64 %a, i64 %b, i32 %scale)
declare <4 x i32> @llvm.udiv.fix.sat.v4i32(<4 x i32> %a, <4 x i32> %b, i32 %scale)
Overview
"""""""""
The '``llvm.udiv.fix.sat``' family of intrinsic functions perform unsigned
fixed point saturating division on 2 arguments of the same scale.
Arguments
""""""""""
The arguments (%a and %b) and the result may be of integer types of any bit
width, but they must have the same bit width. ``%a`` and ``%b`` are the two
values that will undergo unsigned fixed point division. The argument
``%scale`` represents the scale of both operands, and must be a constant
integer.
Semantics:
""""""""""
This operation performs fixed point division on the 2 arguments of a
specified scale. The result will also be returned in the same scale specified
in the third argument.
If the result value cannot be precisely represented in the given scale, the
value is rounded up or down to the closest representable value. The rounding
direction is unspecified.
The maximum value this operation can clamp to is the largest unsigned value
representable by the bit width of the first 2 arguments. The minimum value is the
smallest unsigned value representable by this bit width (zero).
It is undefined behavior if the second argument is zero.
Examples
"""""""""
.. code-block:: llvm
%res = call i4 @llvm.udiv.fix.sat.i4(i4 6, i4 2, i32 0) ; %res = 3 (6 / 2 = 3)
%res = call i4 @llvm.udiv.fix.sat.i4(i4 6, i4 4, i32 1) ; %res = 3 (3 / 2 = 1.5)
; The result in the following could be rounded down to 0.5 or up to 1
%res = call i4 @llvm.udiv.fix.sat.i4(i4 3, i4 4, i32 1) ; %res = 1 (or 2) (1.5 / 2 = 0.75)
; Saturation
%res = call i4 @llvm.udiv.fix.sat.i4(i4 8, i4 2, i32 2) ; %res = 15 (2 / 0.5 = 4 => 3.75)
Specialised Arithmetic Intrinsics
---------------------------------
.. _i_intr_llvm_canonicalize:
'``llvm.canonicalize.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.canonicalize.f32(float %a)
declare double @llvm.canonicalize.f64(double %b)
Overview:
"""""""""
The '``llvm.canonicalize.*``' intrinsic returns the platform specific canonical
encoding of a floating-point number. This canonicalization is useful for
implementing certain numeric primitives such as frexp. The canonical encoding is
defined by IEEE-754-2008 to be:
::
2.1.8 canonical encoding: The preferred encoding of a floating-point
representation in a format. Applied to declets, significands of finite
numbers, infinities, and NaNs, especially in decimal formats.
This operation can also be considered equivalent to the IEEE-754-2008
conversion of a floating-point value to the same format. NaNs are handled
according to section 6.2.
Examples of non-canonical encodings:
- x87 pseudo denormals, pseudo NaNs, pseudo Infinity, Unnormals. These are
converted to a canonical representation per hardware-specific protocol.
- Many normal decimal floating-point numbers have non-canonical alternative
encodings.
- Some machines, like GPUs or ARMv7 NEON, do not support subnormal values.
These are treated as non-canonical encodings of zero and will be flushed to
a zero of the same sign by this operation.
Note that per IEEE-754-2008 6.2, systems that support signaling NaNs with
default exception handling must signal an invalid exception, and produce a
quiet NaN result.
This function should always be implementable as multiplication by 1.0, provided
that the compiler does not constant fold the operation. Likewise, division by
1.0 and ``llvm.minnum(x, x)`` are possible implementations. Addition with
-0.0 is also sufficient provided that the rounding mode is not -Infinity.
``@llvm.canonicalize`` must preserve the equality relation. That is:
- ``(@llvm.canonicalize(x) == x)`` is equivalent to ``(x == x)``
- ``(@llvm.canonicalize(x) == @llvm.canonicalize(y))`` is equivalent
to ``(x == y)``
Additionally, the sign of zero must be conserved:
``@llvm.canonicalize(-0.0) = -0.0`` and ``@llvm.canonicalize(+0.0) = +0.0``
The payload bits of a NaN must be conserved, with two exceptions.
First, environments which use only a single canonical representation of NaN
must perform said canonicalization. Second, SNaNs must be quieted per the
usual methods.
The canonicalization operation may be optimized away if:
- The input is known to be canonical. For example, it was produced by a
floating-point operation that is required by the standard to be canonical.
- The result is consumed only by (or fused with) other floating-point
operations. That is, the bits of the floating-point value are not examined.
.. _int_fmuladd:
'``llvm.fmuladd.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.fmuladd.f32(float %a, float %b, float %c)
declare double @llvm.fmuladd.f64(double %a, double %b, double %c)
Overview:
"""""""""
The '``llvm.fmuladd.*``' intrinsic functions represent multiply-add
expressions that can be fused if the code generator determines that (a) the
target instruction set has support for a fused operation, and (b) that the
fused operation is more efficient than the equivalent, separate pair of mul
and add instructions.
Arguments:
""""""""""
The '``llvm.fmuladd.*``' intrinsics each take three arguments: two
multiplicands, a and b, and an addend c.
Semantics:
""""""""""
The expression:
::
%0 = call float @llvm.fmuladd.f32(%a, %b, %c)
is equivalent to the expression a \* b + c, except that it is unspecified
whether rounding will be performed between the multiplication and addition
steps. Fusion is not guaranteed, even if the target platform supports it.
If a fused multiply-add is required, the corresponding
:ref:`llvm.fma <int_fma>` intrinsic function should be used instead.
This never sets errno, just as '``llvm.fma.*``'.
Examples:
"""""""""
.. code-block:: llvm
%r2 = call float @llvm.fmuladd.f32(float %a, float %b, float %c) ; yields float:r2 = (a * b) + c
Hardware-Loop Intrinsics
------------------------
LLVM support several intrinsics to mark a loop as a hardware-loop. They are
hints to the backend which are required to lower these intrinsics further to target
specific instructions, or revert the hardware-loop to a normal loop if target
specific restriction are not met and a hardware-loop can't be generated.
These intrinsics may be modified in the future and are not intended to be used
outside the backend. Thus, front-end and mid-level optimizations should not be
generating these intrinsics.
'``llvm.set.loop.iterations.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare void @llvm.set.loop.iterations.i32(i32)
declare void @llvm.set.loop.iterations.i64(i64)
Overview:
"""""""""
The '``llvm.set.loop.iterations.*``' intrinsics are used to specify the
hardware-loop trip count. They are placed in the loop preheader basic block and
are marked as ``IntrNoDuplicate`` to avoid optimizers duplicating these
instructions.
Arguments:
""""""""""
The integer operand is the loop trip count of the hardware-loop, and thus
not e.g. the loop back-edge taken count.
Semantics:
""""""""""
The '``llvm.set.loop.iterations.*``' intrinsics do not perform any arithmetic
on their operand. It's a hint to the backend that can use this to set up the
hardware-loop count with a target specific instruction, usually a move of this
value to a special register or a hardware-loop instruction.
'``llvm.start.loop.iterations.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.start.loop.iterations.i32(i32)
declare i64 @llvm.start.loop.iterations.i64(i64)
Overview:
"""""""""
The '``llvm.start.loop.iterations.*``' intrinsics are similar to the
'``llvm.set.loop.iterations.*``' intrinsics, used to specify the
hardware-loop trip count but also produce a value identical to the input
that can be used as the input to the loop. They are placed in the loop
preheader basic block and the output is expected to be the input to the
phi for the induction variable of the loop, decremented by the
'``llvm.loop.decrement.reg.*``'.
Arguments:
""""""""""
The integer operand is the loop trip count of the hardware-loop, and thus
not e.g. the loop back-edge taken count.
Semantics:
""""""""""
The '``llvm.start.loop.iterations.*``' intrinsics do not perform any arithmetic
on their operand. It's a hint to the backend that can use this to set up the
hardware-loop count with a target specific instruction, usually a move of this
value to a special register or a hardware-loop instruction.
'``llvm.test.set.loop.iterations.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i1 @llvm.test.set.loop.iterations.i32(i32)
declare i1 @llvm.test.set.loop.iterations.i64(i64)
Overview:
"""""""""
The '``llvm.test.set.loop.iterations.*``' intrinsics are used to specify the
the loop trip count, and also test that the given count is not zero, allowing
it to control entry to a while-loop. They are placed in the loop preheader's
predecessor basic block, and are marked as ``IntrNoDuplicate`` to avoid
optimizers duplicating these instructions.
Arguments:
""""""""""
The integer operand is the loop trip count of the hardware-loop, and thus
not e.g. the loop back-edge taken count.
Semantics:
""""""""""
The '``llvm.test.set.loop.iterations.*``' intrinsics do not perform any
arithmetic on their operand. It's a hint to the backend that can use this to
set up the hardware-loop count with a target specific instruction, usually a
move of this value to a special register or a hardware-loop instruction.
The result is the conditional value of whether the given count is not zero.
'``llvm.test.start.loop.iterations.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare {i32, i1} @llvm.test.start.loop.iterations.i32(i32)
declare {i64, i1} @llvm.test.start.loop.iterations.i64(i64)
Overview:
"""""""""
The '``llvm.test.start.loop.iterations.*``' intrinsics are similar to the
'``llvm.test.set.loop.iterations.*``' and '``llvm.start.loop.iterations.*``'
intrinsics, used to specify the hardware-loop trip count, but also produce a
value identical to the input that can be used as the input to the loop. The
second i1 output controls entry to a while-loop.
Arguments:
""""""""""
The integer operand is the loop trip count of the hardware-loop, and thus
not e.g. the loop back-edge taken count.
Semantics:
""""""""""
The '``llvm.test.start.loop.iterations.*``' intrinsics do not perform any
arithmetic on their operand. It's a hint to the backend that can use this to
set up the hardware-loop count with a target specific instruction, usually a
move of this value to a special register or a hardware-loop instruction.
The result is a pair of the input and a conditional value of whether the
given count is not zero.
'``llvm.loop.decrement.reg.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.loop.decrement.reg.i32(i32, i32)
declare i64 @llvm.loop.decrement.reg.i64(i64, i64)
Overview:
"""""""""
The '``llvm.loop.decrement.reg.*``' intrinsics are used to lower the loop
iteration counter and return an updated value that will be used in the next
loop test check.
Arguments:
""""""""""
Both arguments must have identical integer types. The first operand is the
loop iteration counter. The second operand is the maximum number of elements
processed in an iteration.
Semantics:
""""""""""
The '``llvm.loop.decrement.reg.*``' intrinsics do an integer ``SUB`` of its
two operands, which is not allowed to wrap. They return the remaining number of
iterations still to be executed, and can be used together with a ``PHI``,
``ICMP`` and ``BR`` to control the number of loop iterations executed. Any
optimisations are allowed to treat it is a ``SUB``, and it is supported by
SCEV, so it's the backends responsibility to handle cases where it may be
optimised. These intrinsics are marked as ``IntrNoDuplicate`` to avoid
optimizers duplicating these instructions.
'``llvm.loop.decrement.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i1 @llvm.loop.decrement.i32(i32)
declare i1 @llvm.loop.decrement.i64(i64)
Overview:
"""""""""
The HardwareLoops pass allows the loop decrement value to be specified with an
option. It defaults to a loop decrement value of 1, but it can be an unsigned
integer value provided by this option. The '``llvm.loop.decrement.*``'
intrinsics decrement the loop iteration counter with this value, and return a
false predicate if the loop should exit, and true otherwise.
This is emitted if the loop counter is not updated via a ``PHI`` node, which
can also be controlled with an option.
Arguments:
""""""""""
The integer argument is the loop decrement value used to decrement the loop
iteration counter.
Semantics:
""""""""""
The '``llvm.loop.decrement.*``' intrinsics do a ``SUB`` of the loop iteration
counter with the given loop decrement value, and return false if the loop
should exit, this ``SUB`` is not allowed to wrap. The result is a condition
that is used by the conditional branch controlling the loop.
Vector Reduction Intrinsics
---------------------------
Horizontal reductions of vectors can be expressed using the following
intrinsics. Each one takes a vector operand as an input and applies its
respective operation across all elements of the vector, returning a single
scalar result of the same element type.
.. _int_vector_reduce_add:
'``llvm.vector.reduce.add.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %a)
declare i64 @llvm.vector.reduce.add.v2i64(<2 x i64> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.add.*``' intrinsics do an integer ``ADD``
reduction of a vector, returning the result as a scalar. The return type matches
the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_fadd:
'``llvm.vector.reduce.fadd.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.vector.reduce.fadd.v4f32(float %start_value, <4 x float> %a)
declare double @llvm.vector.reduce.fadd.v2f64(double %start_value, <2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fadd.*``' intrinsics do a floating-point
``ADD`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
If the intrinsic call has the 'reassoc' flag set, then the reduction will not
preserve the associativity of an equivalent scalarized counterpart. Otherwise
the reduction will be *sequential*, thus implying that the operation respects
the associativity of a scalarized reduction. That is, the reduction begins with
the start value and performs an fadd operation with consecutively increasing
vector element indices. See the following pseudocode:
::
float sequential_fadd(start_value, input_vector)
result = start_value
for i = 0 to length(input_vector)
result = result + input_vector[i]
return result
Arguments:
""""""""""
The first argument to this intrinsic is a scalar start value for the reduction.
The type of the start value matches the element-type of the vector input.
The second argument must be a vector of floating-point values.
To ignore the start value, negative zero (``-0.0``) can be used, as it is
the neutral value of floating point addition.
Examples:
"""""""""
::
%unord = call reassoc float @llvm.vector.reduce.fadd.v4f32(float -0.0, <4 x float> %input) ; relaxed reduction
%ord = call float @llvm.vector.reduce.fadd.v4f32(float %start_value, <4 x float> %input) ; sequential reduction
.. _int_vector_reduce_mul:
'``llvm.vector.reduce.mul.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> %a)
declare i64 @llvm.vector.reduce.mul.v2i64(<2 x i64> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.mul.*``' intrinsics do an integer ``MUL``
reduction of a vector, returning the result as a scalar. The return type matches
the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_fmul:
'``llvm.vector.reduce.fmul.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.vector.reduce.fmul.v4f32(float %start_value, <4 x float> %a)
declare double @llvm.vector.reduce.fmul.v2f64(double %start_value, <2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fmul.*``' intrinsics do a floating-point
``MUL`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
If the intrinsic call has the 'reassoc' flag set, then the reduction will not
preserve the associativity of an equivalent scalarized counterpart. Otherwise
the reduction will be *sequential*, thus implying that the operation respects
the associativity of a scalarized reduction. That is, the reduction begins with
the start value and performs an fmul operation with consecutively increasing
vector element indices. See the following pseudocode:
::
float sequential_fmul(start_value, input_vector)
result = start_value
for i = 0 to length(input_vector)
result = result * input_vector[i]
return result
Arguments:
""""""""""
The first argument to this intrinsic is a scalar start value for the reduction.
The type of the start value matches the element-type of the vector input.
The second argument must be a vector of floating-point values.
To ignore the start value, one (``1.0``) can be used, as it is the neutral
value of floating point multiplication.
Examples:
"""""""""
::
%unord = call reassoc float @llvm.vector.reduce.fmul.v4f32(float 1.0, <4 x float> %input) ; relaxed reduction
%ord = call float @llvm.vector.reduce.fmul.v4f32(float %start_value, <4 x float> %input) ; sequential reduction
.. _int_vector_reduce_and:
'``llvm.vector.reduce.and.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.and.*``' intrinsics do a bitwise ``AND``
reduction of a vector, returning the result as a scalar. The return type matches
the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_or:
'``llvm.vector.reduce.or.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.or.*``' intrinsics do a bitwise ``OR`` reduction
of a vector, returning the result as a scalar. The return type matches the
element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_xor:
'``llvm.vector.reduce.xor.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.xor.*``' intrinsics do a bitwise ``XOR``
reduction of a vector, returning the result as a scalar. The return type matches
the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_smax:
'``llvm.vector.reduce.smax.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.smax.*``' intrinsics do a signed integer
``MAX`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_smin:
'``llvm.vector.reduce.smin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.smin.*``' intrinsics do a signed integer
``MIN`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_umax:
'``llvm.vector.reduce.umax.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.umax.*``' intrinsics do an unsigned
integer ``MAX`` reduction of a vector, returning the result as a scalar. The
return type matches the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_umin:
'``llvm.vector.reduce.umin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.umin.*``' intrinsics do an unsigned
integer ``MIN`` reduction of a vector, returning the result as a scalar. The
return type matches the element-type of the vector input.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of integer values.
.. _int_vector_reduce_fmax:
'``llvm.vector.reduce.fmax.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.vector.reduce.fmax.v4f32(<4 x float> %a)
declare double @llvm.vector.reduce.fmax.v2f64(<2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fmax.*``' intrinsics do a floating-point
``MAX`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
This instruction has the same comparison semantics as the '``llvm.maxnum.*``'
intrinsic. That is, the result will always be a number unless all elements of
the vector are NaN. For a vector with maximum element magnitude 0.0 and
containing both +0.0 and -0.0 elements, the sign of the result is unspecified.
If the intrinsic call has the ``nnan`` fast-math flag, then the operation can
assume that NaNs are not present in the input vector.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of floating-point values.
.. _int_vector_reduce_fmin:
'``llvm.vector.reduce.fmin.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vector.reduce.fmin.v4f32(<4 x float> %a)
declare double @llvm.vector.reduce.fmin.v2f64(<2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fmin.*``' intrinsics do a floating-point
``MIN`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
This instruction has the same comparison semantics as the '``llvm.minnum.*``'
intrinsic. That is, the result will always be a number unless all elements of
the vector are NaN. For a vector with minimum element magnitude 0.0 and
containing both +0.0 and -0.0 elements, the sign of the result is unspecified.
If the intrinsic call has the ``nnan`` fast-math flag, then the operation can
assume that NaNs are not present in the input vector.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of floating-point values.
.. _int_vector_reduce_fmaximum:
'``llvm.vector.reduce.fmaximum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vector.reduce.fmaximum.v4f32(<4 x float> %a)
declare double @llvm.vector.reduce.fmaximum.v2f64(<2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fmaximum.*``' intrinsics do a floating-point
``MAX`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
This instruction has the same comparison semantics as the '``llvm.maximum.*``'
intrinsic. That is, this intrinsic propagates NaNs and +0.0 is considered
greater than -0.0. If any element of the vector is a NaN, the result is NaN.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of floating-point values.
.. _int_vector_reduce_fminimum:
'``llvm.vector.reduce.fminimum.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vector.reduce.fminimum.v4f32(<4 x float> %a)
declare double @llvm.vector.reduce.fminimum.v2f64(<2 x double> %a)
Overview:
"""""""""
The '``llvm.vector.reduce.fminimum.*``' intrinsics do a floating-point
``MIN`` reduction of a vector, returning the result as a scalar. The return type
matches the element-type of the vector input.
This instruction has the same comparison semantics as the '``llvm.minimum.*``'
intrinsic. That is, this intrinsic propagates NaNs and -0.0 is considered less
than +0.0. If any element of the vector is a NaN, the result is NaN.
Arguments:
""""""""""
The argument to this intrinsic must be a vector of floating-point values.
'``llvm.vector.insert``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
; Insert fixed type into scalable type
declare <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> %vec, <4 x float> %subvec, i64 <idx>)
declare <vscale x 2 x double> @llvm.vector.insert.nxv2f64.v2f64(<vscale x 2 x double> %vec, <2 x double> %subvec, i64 <idx>)
; Insert scalable type into scalable type
declare <vscale x 4 x float> @llvm.vector.insert.nxv4f64.nxv2f64(<vscale x 4 x float> %vec, <vscale x 2 x float> %subvec, i64 <idx>)
; Insert fixed type into fixed type
declare <4 x double> @llvm.vector.insert.v4f64.v2f64(<4 x double> %vec, <2 x double> %subvec, i64 <idx>)
Overview:
"""""""""
The '``llvm.vector.insert.*``' intrinsics insert a vector into another vector
starting from a given index. The return type matches the type of the vector we
insert into. Conceptually, this can be used to build a scalable vector out of
non-scalable vectors, however this intrinsic can also be used on purely fixed
types.
Scalable vectors can only be inserted into other scalable vectors.
Arguments:
""""""""""
The ``vec`` is the vector which ``subvec`` will be inserted into.
The ``subvec`` is the vector that will be inserted.
``idx`` represents the starting element number at which ``subvec`` will be
inserted. ``idx`` must be a constant multiple of ``subvec``'s known minimum
vector length. If ``subvec`` is a scalable vector, ``idx`` is first scaled by
the runtime scaling factor of ``subvec``. The elements of ``vec`` starting at
``idx`` are overwritten with ``subvec``. Elements ``idx`` through (``idx`` +
num_elements(``subvec``) - 1) must be valid ``vec`` indices. If this condition
cannot be determined statically but is false at runtime, then the result vector
is a :ref:`poison value <poisonvalues>`.
'``llvm.vector.extract``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
; Extract fixed type from scalable type
declare <4 x float> @llvm.vector.extract.v4f32.nxv4f32(<vscale x 4 x float> %vec, i64 <idx>)
declare <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> %vec, i64 <idx>)
; Extract scalable type from scalable type
declare <vscale x 2 x float> @llvm.vector.extract.nxv2f32.nxv4f32(<vscale x 4 x float> %vec, i64 <idx>)
; Extract fixed type from fixed type
declare <2 x double> @llvm.vector.extract.v2f64.v4f64(<4 x double> %vec, i64 <idx>)
Overview:
"""""""""
The '``llvm.vector.extract.*``' intrinsics extract a vector from within another
vector starting from a given index. The return type must be explicitly
specified. Conceptually, this can be used to decompose a scalable vector into
non-scalable parts, however this intrinsic can also be used on purely fixed
types.
Scalable vectors can only be extracted from other scalable vectors.
Arguments:
""""""""""
The ``vec`` is the vector from which we will extract a subvector.
The ``idx`` specifies the starting element number within ``vec`` from which a
subvector is extracted. ``idx`` must be a constant multiple of the known-minimum
vector length of the result type. If the result type is a scalable vector,
``idx`` is first scaled by the result type's runtime scaling factor. Elements
``idx`` through (``idx`` + num_elements(result_type) - 1) must be valid vector
indices. If this condition cannot be determined statically but is false at
runtime, then the result vector is a :ref:`poison value <poisonvalues>`. The
``idx`` parameter must be a vector index constant type (for most targets this
will be an integer pointer type).
'``llvm.experimental.vector.reverse``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <2 x i8> @llvm.experimental.vector.reverse.v2i8(<2 x i8> %a)
declare <vscale x 4 x i32> @llvm.experimental.vector.reverse.nxv4i32(<vscale x 4 x i32> %a)
Overview:
"""""""""
The '``llvm.experimental.vector.reverse.*``' intrinsics reverse a vector.
The intrinsic takes a single vector and returns a vector of matching type but
with the original lane order reversed. These intrinsics work for both fixed
and scalable vectors. While this intrinsic is marked as experimental the
recommended way to express reverse operations for fixed-width vectors is still
to use a shufflevector, as that may allow for more optimization opportunities.
Arguments:
""""""""""
The argument to this intrinsic must be a vector.
'``llvm.experimental.vector.deinterleave2``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare {<2 x double>, <2 x double>} @llvm.experimental.vector.deinterleave2.v4f64(<4 x double> %vec1)
declare {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.experimental.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %vec1)
Overview:
"""""""""
The '``llvm.experimental.vector.deinterleave2``' intrinsic constructs two
vectors by deinterleaving the even and odd lanes of the input vector.
This intrinsic works for both fixed and scalable vectors. While this intrinsic
supports all vector types the recommended way to express this operation for
fixed-width vectors is still to use a shufflevector, as that may allow for more
optimization opportunities.
For example:
.. code-block:: text
{<2 x i64>, <2 x i64>} llvm.experimental.vector.deinterleave2.v4i64(<4 x i64> <i64 0, i64 1, i64 2, i64 3>); ==> {<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>}
Arguments:
""""""""""
The argument is a vector whose type corresponds to the logical concatenation of
the two result types.
'``llvm.experimental.vector.interleave2``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <4 x double> @llvm.experimental.vector.interleave2.v4f64(<2 x double> %vec1, <2 x double> %vec2)
declare <vscale x 8 x i32> @llvm.experimental.vector.interleave2.nxv8i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2)
Overview:
"""""""""
The '``llvm.experimental.vector.interleave2``' intrinsic constructs a vector
by interleaving two input vectors.
This intrinsic works for both fixed and scalable vectors. While this intrinsic
supports all vector types the recommended way to express this operation for
fixed-width vectors is still to use a shufflevector, as that may allow for more
optimization opportunities.
For example:
.. code-block:: text
<4 x i64> llvm.experimental.vector.interleave2.v4i64(<2 x i64> <i64 0, i64 2>, <2 x i64> <i64 1, i64 3>); ==> <4 x i64> <i64 0, i64 1, i64 2, i64 3>
Arguments:
""""""""""
Both arguments must be vectors of the same type whereby their logical
concatenation matches the result type.
'``llvm.experimental.cttz.elts``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ```llvm.experimental.cttz.elts```
on any vector of integer elements, both fixed width and scalable.
::
declare i8 @llvm.experimental.cttz.elts.i8.v8i1(<8 x i1> <src>, i1 <is_zero_poison>)
Overview:
"""""""""
The '``llvm.experimental.cttz.elts``' intrinsic counts the number of trailing
zero elements of a vector.
Arguments:
""""""""""
The first argument is the vector to be counted. This argument must be a vector
with integer element type. The return type must also be an integer type which is
wide enough to hold the maximum number of elements of the source vector. The
behaviour of this intrinsic is undefined if the return type is not wide enough
for the number of elements in the input vector.
The second argument is a constant flag that indicates whether the intrinsic
returns a valid result if the first argument is all zero. If the first argument
is all zero and the second argument is true, the result is poison.
Semantics:
""""""""""
The '``llvm.experimental.cttz.elts``' intrinsic counts the trailing (least
significant) zero elements in a vector. If ``src == 0`` the result is the
number of elements in the input vector.
'``llvm.experimental.vector.splice``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <2 x double> @llvm.experimental.vector.splice.v2f64(<2 x double> %vec1, <2 x double> %vec2, i32 %imm)
declare <vscale x 4 x i32> @llvm.experimental.vector.splice.nxv4i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2, i32 %imm)
Overview:
"""""""""
The '``llvm.experimental.vector.splice.*``' intrinsics construct a vector by
concatenating elements from the first input vector with elements of the second
input vector, returning a vector of the same type as the input vectors. The
signed immediate, modulo the number of elements in the vector, is the index
into the first vector from which to extract the result value. This means
conceptually that for a positive immediate, a vector is extracted from
``concat(%vec1, %vec2)`` starting at index ``imm``, whereas for a negative
immediate, it extracts ``-imm`` trailing elements from the first vector, and
the remaining elements from ``%vec2``.
These intrinsics work for both fixed and scalable vectors. While this intrinsic
is marked as experimental, the recommended way to express this operation for
fixed-width vectors is still to use a shufflevector, as that may allow for more
optimization opportunities.
For example:
.. code-block:: text
llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, 1); ==> <B, C, D, E> index
llvm.experimental.vector.splice(<A,B,C,D>, <E,F,G,H>, -3); ==> <B, C, D, E> trailing elements
Arguments:
""""""""""
The first two operands are vectors with the same type. The start index is imm
modulo the runtime number of elements in the source vector. For a fixed-width
vector <N x eltty>, imm is a signed integer constant in the range
-N <= imm < N. For a scalable vector <vscale x N x eltty>, imm is a signed
integer constant in the range -X <= imm < X where X=vscale_range_min * N.
'``llvm.experimental.stepvector``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This is an overloaded intrinsic. You can use ``llvm.experimental.stepvector``
to generate a vector whose lane values comprise the linear sequence
<0, 1, 2, ...>. It is primarily intended for scalable vectors.
::
declare <vscale x 4 x i32> @llvm.experimental.stepvector.nxv4i32()
declare <vscale x 8 x i16> @llvm.experimental.stepvector.nxv8i16()
The '``llvm.experimental.stepvector``' intrinsics are used to create vectors
of integers whose elements contain a linear sequence of values starting from 0
with a step of 1. This experimental intrinsic can only be used for vectors
with integer elements that are at least 8 bits in size. If the sequence value
exceeds the allowed limit for the element type then the result for that lane is
undefined.
These intrinsics work for both fixed and scalable vectors. While this intrinsic
is marked as experimental, the recommended way to express this operation for
fixed-width vectors is still to generate a constant vector instead.
Arguments:
""""""""""
None.
'``llvm.experimental.get.vector.length``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.experimental.get.vector.length.i32(i32 %cnt, i32 immarg %vf, i1 immarg %scalable)
declare i32 @llvm.experimental.get.vector.length.i64(i64 %cnt, i32 immarg %vf, i1 immarg %scalable)
Overview:
"""""""""
The '``llvm.experimental.get.vector.length.*``' intrinsics take a number of
elements to process and returns how many of the elements can be processed
with the requested vectorization factor.
Arguments:
""""""""""
The first argument is an unsigned value of any scalar integer type and specifies
the total number of elements to be processed. The second argument is an i32
immediate for the vectorization factor. The third argument indicates if the
vectorization factor should be multiplied by vscale.
Semantics:
""""""""""
Returns a positive i32 value (explicit vector length) that is unknown at compile
time and depends on the hardware specification.
If the result value does not fit in the result type, then the result is
a :ref:`poison value <poisonvalues>`.
This intrinsic is intended to be used by loop vectorization with VP intrinsics
in order to get the number of elements to process on each loop iteration. The
result should be used to decrease the count for the next iteration until the
count reaches zero.
If the count is larger than the number of lanes in the type described by the
last 2 arguments, this intrinsic may return a value less than the number of
lanes implied by the type. The result will be at least as large as the result
will be on any later loop iteration.
This intrinsic will only return 0 if the input count is also 0. A non-zero input
count will produce a non-zero result.
Matrix Intrinsics
-----------------
Operations on matrixes requiring shape information (like number of rows/columns
or the memory layout) can be expressed using the matrix intrinsics. These
intrinsics require matrix dimensions to be passed as immediate arguments, and
matrixes are passed and returned as vectors. This means that for a ``R`` x
``C`` matrix, element ``i`` of column ``j`` is at index ``j * R + i`` in the
corresponding vector, with indices starting at 0. Currently column-major layout
is assumed. The intrinsics support both integer and floating point matrixes.
'``llvm.matrix.transpose.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare vectorty @llvm.matrix.transpose.*(vectorty %In, i32 <Rows>, i32 <Cols>)
Overview:
"""""""""
The '``llvm.matrix.transpose.*``' intrinsics treat ``%In`` as a ``<Rows> x
<Cols>`` matrix and return the transposed matrix in the result vector.
Arguments:
""""""""""
The first argument ``%In`` is a vector that corresponds to a ``<Rows> x
<Cols>`` matrix. Thus, arguments ``<Rows>`` and ``<Cols>`` correspond to the
number of rows and columns, respectively, and must be positive, constant
integers. The returned vector must have ``<Rows> * <Cols>`` elements, and have
the same float or integer element type as ``%In``.
'``llvm.matrix.multiply.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare vectorty @llvm.matrix.multiply.*(vectorty %A, vectorty %B, i32 <OuterRows>, i32 <Inner>, i32 <OuterColumns>)
Overview:
"""""""""
The '``llvm.matrix.multiply.*``' intrinsics treat ``%A`` as a ``<OuterRows> x
<Inner>`` matrix, ``%B`` as a ``<Inner> x <OuterColumns>`` matrix, and
multiplies them. The result matrix is returned in the result vector.
Arguments:
""""""""""
The first vector argument ``%A`` corresponds to a matrix with ``<OuterRows> *
<Inner>`` elements, and the second argument ``%B`` to a matrix with
``<Inner> * <OuterColumns>`` elements. Arguments ``<OuterRows>``,
``<Inner>`` and ``<OuterColumns>`` must be positive, constant integers. The
returned vector must have ``<OuterRows> * <OuterColumns>`` elements.
Vectors ``%A``, ``%B``, and the returned vector all have the same float or
integer element type.
'``llvm.matrix.column.major.load.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare vectorty @llvm.matrix.column.major.load.*(
ptrty %Ptr, i64 %Stride, i1 <IsVolatile>, i32 <Rows>, i32 <Cols>)
Overview:
"""""""""
The '``llvm.matrix.column.major.load.*``' intrinsics load a ``<Rows> x <Cols>``
matrix using a stride of ``%Stride`` to compute the start address of the
different columns. The offset is computed using ``%Stride``'s bitwidth. This
allows for convenient loading of sub matrixes. If ``<IsVolatile>`` is true, the
intrinsic is considered a :ref:`volatile memory access <volatile>`. The result
matrix is returned in the result vector. If the ``%Ptr`` argument is known to
be aligned to some boundary, this can be specified as an attribute on the
argument.
Arguments:
""""""""""
The first argument ``%Ptr`` is a pointer type to the returned vector type, and
corresponds to the start address to load from. The second argument ``%Stride``
is a positive, constant integer with ``%Stride >= <Rows>``. ``%Stride`` is used
to compute the column memory addresses. I.e., for a column ``C``, its start
memory addresses is calculated with ``%Ptr + C * %Stride``. The third Argument
``<IsVolatile>`` is a boolean value. The fourth and fifth arguments,
``<Rows>`` and ``<Cols>``, correspond to the number of rows and columns,
respectively, and must be positive, constant integers. The returned vector must
have ``<Rows> * <Cols>`` elements.
The :ref:`align <attr_align>` parameter attribute can be provided for the
``%Ptr`` arguments.
'``llvm.matrix.column.major.store.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.matrix.column.major.store.*(
vectorty %In, ptrty %Ptr, i64 %Stride, i1 <IsVolatile>, i32 <Rows>, i32 <Cols>)
Overview:
"""""""""
The '``llvm.matrix.column.major.store.*``' intrinsics store the ``<Rows> x
<Cols>`` matrix in ``%In`` to memory using a stride of ``%Stride`` between
columns. The offset is computed using ``%Stride``'s bitwidth. If
``<IsVolatile>`` is true, the intrinsic is considered a
:ref:`volatile memory access <volatile>`.
If the ``%Ptr`` argument is known to be aligned to some boundary, this can be
specified as an attribute on the argument.
Arguments:
""""""""""
The first argument ``%In`` is a vector that corresponds to a ``<Rows> x
<Cols>`` matrix to be stored to memory. The second argument ``%Ptr`` is a
pointer to the vector type of ``%In``, and is the start address of the matrix
in memory. The third argument ``%Stride`` is a positive, constant integer with
``%Stride >= <Rows>``. ``%Stride`` is used to compute the column memory
addresses. I.e., for a column ``C``, its start memory addresses is calculated
with ``%Ptr + C * %Stride``. The fourth argument ``<IsVolatile>`` is a boolean
value. The arguments ``<Rows>`` and ``<Cols>`` correspond to the number of rows
and columns, respectively, and must be positive, constant integers.
The :ref:`align <attr_align>` parameter attribute can be provided
for the ``%Ptr`` arguments.
Half Precision Floating-Point Intrinsics
----------------------------------------
For most target platforms, half precision floating-point is a
storage-only format. This means that it is a dense encoding (in memory)
but does not support computation in the format.
This means that code must first load the half-precision floating-point
value as an i16, then convert it to float with
:ref:`llvm.convert.from.fp16 <int_convert_from_fp16>`. Computation can
then be performed on the float value (including extending to double
etc). To store the value back to memory, it is first converted to float
if needed, then converted to i16 with
:ref:`llvm.convert.to.fp16 <int_convert_to_fp16>`, then storing as an
i16 value.
.. _int_convert_to_fp16:
'``llvm.convert.to.fp16``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i16 @llvm.convert.to.fp16.f32(float %a)
declare i16 @llvm.convert.to.fp16.f64(double %a)
Overview:
"""""""""
The '``llvm.convert.to.fp16``' intrinsic function performs a conversion from a
conventional floating-point type to half precision floating-point format.
Arguments:
""""""""""
The intrinsic function contains single argument - the value to be
converted.
Semantics:
""""""""""
The '``llvm.convert.to.fp16``' intrinsic function performs a conversion from a
conventional floating-point format to half precision floating-point format. The
return value is an ``i16`` which contains the converted number.
Examples:
"""""""""
.. code-block:: llvm
%res = call i16 @llvm.convert.to.fp16.f32(float %a)
store i16 %res, i16* @x, align 2
.. _int_convert_from_fp16:
'``llvm.convert.from.fp16``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare float @llvm.convert.from.fp16.f32(i16 %a)
declare double @llvm.convert.from.fp16.f64(i16 %a)
Overview:
"""""""""
The '``llvm.convert.from.fp16``' intrinsic function performs a
conversion from half precision floating-point format to single precision
floating-point format.
Arguments:
""""""""""
The intrinsic function contains single argument - the value to be
converted.
Semantics:
""""""""""
The '``llvm.convert.from.fp16``' intrinsic function performs a
conversion from half single precision floating-point format to single
precision floating-point format. The input half-float value is
represented by an ``i16`` value.
Examples:
"""""""""
.. code-block:: llvm
%a = load i16, ptr @x, align 2
%res = call float @llvm.convert.from.fp16(i16 %a)
Saturating floating-point to integer conversions
------------------------------------------------
The ``fptoui`` and ``fptosi`` instructions return a
:ref:`poison value <poisonvalues>` if the rounded-towards-zero value is not
representable by the result type. These intrinsics provide an alternative
conversion, which will saturate towards the smallest and largest representable
integer values instead.
'``llvm.fptoui.sat.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fptoui.sat`` on any
floating-point argument type and any integer result type, or vectors thereof.
Not all targets may support all types, however.
::
declare i32 @llvm.fptoui.sat.i32.f32(float %f)
declare i19 @llvm.fptoui.sat.i19.f64(double %f)
declare <4 x i100> @llvm.fptoui.sat.v4i100.v4f128(<4 x fp128> %f)
Overview:
"""""""""
This intrinsic converts the argument into an unsigned integer using saturating
semantics.
Arguments:
""""""""""
The argument may be any floating-point or vector of floating-point type. The
return value may be any integer or vector of integer type. The number of vector
elements in argument and return must be the same.
Semantics:
""""""""""
The conversion to integer is performed subject to the following rules:
- If the argument is any NaN, zero is returned.
- If the argument is smaller than zero (this includes negative infinity),
zero is returned.
- If the argument is larger than the largest representable unsigned integer of
the result type (this includes positive infinity), the largest representable
unsigned integer is returned.
- Otherwise, the result of rounding the argument towards zero is returned.
Example:
""""""""
.. code-block:: text
%a = call i8 @llvm.fptoui.sat.i8.f32(float 123.9) ; yields i8: 123
%b = call i8 @llvm.fptoui.sat.i8.f32(float -5.7) ; yields i8: 0
%c = call i8 @llvm.fptoui.sat.i8.f32(float 377.0) ; yields i8: 255
%d = call i8 @llvm.fptoui.sat.i8.f32(float 0xFFF8000000000000) ; yields i8: 0
'``llvm.fptosi.sat.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.fptosi.sat`` on any
floating-point argument type and any integer result type, or vectors thereof.
Not all targets may support all types, however.
::
declare i32 @llvm.fptosi.sat.i32.f32(float %f)
declare i19 @llvm.fptosi.sat.i19.f64(double %f)
declare <4 x i100> @llvm.fptosi.sat.v4i100.v4f128(<4 x fp128> %f)
Overview:
"""""""""
This intrinsic converts the argument into a signed integer using saturating
semantics.
Arguments:
""""""""""
The argument may be any floating-point or vector of floating-point type. The
return value may be any integer or vector of integer type. The number of vector
elements in argument and return must be the same.
Semantics:
""""""""""
The conversion to integer is performed subject to the following rules:
- If the argument is any NaN, zero is returned.
- If the argument is smaller than the smallest representable signed integer of
the result type (this includes negative infinity), the smallest
representable signed integer is returned.
- If the argument is larger than the largest representable signed integer of
the result type (this includes positive infinity), the largest representable
signed integer is returned.
- Otherwise, the result of rounding the argument towards zero is returned.
Example:
""""""""
.. code-block:: text
%a = call i8 @llvm.fptosi.sat.i8.f32(float 23.9) ; yields i8: 23
%b = call i8 @llvm.fptosi.sat.i8.f32(float -130.8) ; yields i8: -128
%c = call i8 @llvm.fptosi.sat.i8.f32(float 999.0) ; yields i8: 127
%d = call i8 @llvm.fptosi.sat.i8.f32(float 0xFFF8000000000000) ; yields i8: 0
Convergence Intrinsics
----------------------
The LLVM convergence intrinsics for controlling the semantics of ``convergent``
operations, which all start with the ``llvm.experimental.convergence.``
prefix, are described in the :doc:`ConvergentOperations` document.
.. _dbg_intrinsics:
Debugger Intrinsics
-------------------
The LLVM debugger intrinsics (which all start with ``llvm.dbg.``
prefix), are described in the `LLVM Source Level
Debugging <SourceLevelDebugging.html#format-common-intrinsics>`_
document.
Exception Handling Intrinsics
-----------------------------
The LLVM exception handling intrinsics (which all start with
``llvm.eh.`` prefix), are described in the `LLVM Exception
Handling <ExceptionHandling.html#format-common-intrinsics>`_ document.
Pointer Authentication Intrinsics
---------------------------------
The LLVM pointer authentication intrinsics (which all start with
``llvm.ptrauth.`` prefix), are described in the `Pointer Authentication
<PointerAuth.html#intrinsics>`_ document.
.. _int_trampoline:
Trampoline Intrinsics
---------------------
These intrinsics make it possible to excise one parameter, marked with
the :ref:`nest <nest>` attribute, from a function. The result is a
callable function pointer lacking the nest parameter - the caller does
not need to provide a value for it. Instead, the value to use is stored
in advance in a "trampoline", a block of memory usually allocated on the
stack, which also contains code to splice the nest value into the
argument list. This is used to implement the GCC nested function address
extension.
For example, if the function is ``i32 f(ptr nest %c, i32 %x, i32 %y)``
then the resulting function pointer has signature ``i32 (i32, i32)``.
It can be created as follows:
.. code-block:: llvm
%tramp = alloca [10 x i8], align 4 ; size and alignment only correct for X86
call ptr @llvm.init.trampoline(ptr %tramp, ptr @f, ptr %nval)
%fp = call ptr @llvm.adjust.trampoline(ptr %tramp)
The call ``%val = call i32 %fp(i32 %x, i32 %y)`` is then equivalent to
``%val = call i32 %f(ptr %nval, i32 %x, i32 %y)``.
.. _int_it:
'``llvm.init.trampoline``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.init.trampoline(ptr <tramp>, ptr <func>, ptr <nval>)
Overview:
"""""""""
This fills the memory pointed to by ``tramp`` with executable code,
turning it into a trampoline.
Arguments:
""""""""""
The ``llvm.init.trampoline`` intrinsic takes three arguments, all
pointers. The ``tramp`` argument must point to a sufficiently large and
sufficiently aligned block of memory; this memory is written to by the
intrinsic. Note that the size and the alignment are target-specific -
LLVM currently provides no portable way of determining them, so a
front-end that generates this intrinsic needs to have some
target-specific knowledge. The ``func`` argument must hold a function.
Semantics:
""""""""""
The block of memory pointed to by ``tramp`` is filled with target
dependent code, turning it into a function. Then ``tramp`` needs to be
passed to :ref:`llvm.adjust.trampoline <int_at>` to get a pointer which can
be :ref:`bitcast (to a new function) and called <int_trampoline>`. The new
function's signature is the same as that of ``func`` with any arguments
marked with the ``nest`` attribute removed. At most one such ``nest``
argument is allowed, and it must be of pointer type. Calling the new
function is equivalent to calling ``func`` with the same argument list,
but with ``nval`` used for the missing ``nest`` argument. If, after
calling ``llvm.init.trampoline``, the memory pointed to by ``tramp`` is
modified, then the effect of any later call to the returned function
pointer is undefined.
.. _int_at:
'``llvm.adjust.trampoline``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.adjust.trampoline(ptr <tramp>)
Overview:
"""""""""
This performs any required machine-specific adjustment to the address of
a trampoline (passed as ``tramp``).
Arguments:
""""""""""
``tramp`` must point to a block of memory which already has trampoline
code filled in by a previous call to
:ref:`llvm.init.trampoline <int_it>`.
Semantics:
""""""""""
On some architectures the address of the code to be executed needs to be
different than the address where the trampoline is actually stored. This
intrinsic returns the executable address corresponding to ``tramp``
after performing the required machine specific adjustments. The pointer
returned can then be :ref:`bitcast and executed <int_trampoline>`.
.. _int_vp:
Vector Predication Intrinsics
-----------------------------
VP intrinsics are intended for predicated SIMD/vector code. A typical VP
operation takes a vector mask and an explicit vector length parameter as in:
::
<W x T> llvm.vp.<opcode>.*(<W x T> %x, <W x T> %y, <W x i1> %mask, i32 %evl)
The vector mask parameter (%mask) always has a vector of `i1` type, for example
`<32 x i1>`. The explicit vector length parameter always has the type `i32` and
is an unsigned integer value. The explicit vector length parameter (%evl) is in
the range:
::
0 <= %evl <= W, where W is the number of vector elements
Note that for :ref:`scalable vector types <t_vector>` ``W`` is the runtime
length of the vector.
The VP intrinsic has undefined behavior if ``%evl > W``. The explicit vector
length (%evl) creates a mask, %EVLmask, with all elements ``0 <= i < %evl`` set
to True, and all other lanes ``%evl <= i < W`` to False. A new mask %M is
calculated with an element-wise AND from %mask and %EVLmask:
::
M = %mask AND %EVLmask
A vector operation ``<opcode>`` on vectors ``A`` and ``B`` calculates:
::
A <opcode> B = { A[i] <opcode> B[i] M[i] = True, and
{ undef otherwise
Optimization Hint
^^^^^^^^^^^^^^^^^
Some targets, such as AVX512, do not support the %evl parameter in hardware.
The use of an effective %evl is discouraged for those targets. The function
``TargetTransformInfo::hasActiveVectorLength()`` returns true when the target
has native support for %evl.
.. _int_vp_select:
'``llvm.vp.select.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.select.v16i32 (<16 x i1> <condition>, <16 x i32> <on_true>, <16 x i32> <on_false>, i32 <evl>)
declare <vscale x 4 x i64> @llvm.vp.select.nxv4i64 (<vscale x 4 x i1> <condition>, <vscale x 4 x i64> <on_true>, <vscale x 4 x i64> <on_false>, i32 <evl>)
Overview:
"""""""""
The '``llvm.vp.select``' intrinsic is used to choose one value based on a
condition vector, without IR-level branching.
Arguments:
""""""""""
The first operand is a vector of ``i1`` and indicates the condition. The
second operand is the value that is selected where the condition vector is
true. The third operand is the value that is selected where the condition
vector is false. The vectors must be of the same size. The fourth operand is
the explicit vector length.
#. The optional ``fast-math flags`` marker indicates that the select has one or
more :ref:`fast-math flags <fastmath>`. These are optimization hints to
enable otherwise unsafe floating-point optimizations. Fast-math flags are
only valid for selects that return a floating-point scalar or vector type,
or an array (nested to any depth) of floating-point scalar or vector types.
Semantics:
""""""""""
The intrinsic selects lanes from the second and third operand depending on a
condition vector.
All result lanes at positions greater or equal than ``%evl`` are undefined.
For all lanes below ``%evl`` where the condition vector is true the lane is
taken from the second operand. Otherwise, the lane is taken from the third
operand.
Example:
""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.select.v4i32(<4 x i1> %cond, <4 x i32> %on_true, <4 x i32> %on_false, i32 %evl)
;;; Expansion.
;; Any result is legal on lanes at and above %evl.
%also.r = select <4 x i1> %cond, <4 x i32> %on_true, <4 x i32> %on_false
.. _int_vp_merge:
'``llvm.vp.merge.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.merge.v16i32 (<16 x i1> <condition>, <16 x i32> <on_true>, <16 x i32> <on_false>, i32 <pivot>)
declare <vscale x 4 x i64> @llvm.vp.merge.nxv4i64 (<vscale x 4 x i1> <condition>, <vscale x 4 x i64> <on_true>, <vscale x 4 x i64> <on_false>, i32 <pivot>)
Overview:
"""""""""
The '``llvm.vp.merge``' intrinsic is used to choose one value based on a
condition vector and an index operand, without IR-level branching.
Arguments:
""""""""""
The first operand is a vector of ``i1`` and indicates the condition. The
second operand is the value that is merged where the condition vector is true.
The third operand is the value that is selected where the condition vector is
false or the lane position is greater equal than the pivot. The fourth operand
is the pivot.
#. The optional ``fast-math flags`` marker indicates that the merge has one or
more :ref:`fast-math flags <fastmath>`. These are optimization hints to
enable otherwise unsafe floating-point optimizations. Fast-math flags are
only valid for merges that return a floating-point scalar or vector type,
or an array (nested to any depth) of floating-point scalar or vector types.
Semantics:
""""""""""
The intrinsic selects lanes from the second and third operand depending on a
condition vector and pivot value.
For all lanes where the condition vector is true and the lane position is less
than ``%pivot`` the lane is taken from the second operand. Otherwise, the lane
is taken from the third operand.
Example:
""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.merge.v4i32(<4 x i1> %cond, <4 x i32> %on_true, <4 x i32> %on_false, i32 %pivot)
;;; Expansion.
;; Lanes at and above %pivot are taken from %on_false
%atfirst = insertelement <4 x i32> undef, i32 %pivot, i32 0
%splat = shufflevector <4 x i32> %atfirst, <4 x i32> poison, <4 x i32> zeroinitializer
%pivotmask = icmp ult <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> %splat
%mergemask = and <4 x i1> %cond, <4 x i1> %pivotmask
%also.r = select <4 x i1> %mergemask, <4 x i32> %on_true, <4 x i32> %on_false
.. _int_vp_add:
'``llvm.vp.add.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.add.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.add.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.add.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer addition of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.add``' intrinsic performs integer addition (:ref:`add <i_add>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = add <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_sub:
'``llvm.vp.sub.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.sub.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.sub.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.sub.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer subtraction of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.sub``' intrinsic performs integer subtraction
(:ref:`sub <i_sub>`) of the first and second vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.sub.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = sub <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_mul:
'``llvm.vp.mul.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.mul.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.mul.nxv46i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.mul.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer multiplication of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.mul``' intrinsic performs integer multiplication
(:ref:`mul <i_mul>`) of the first and second vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.mul.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = mul <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_sdiv:
'``llvm.vp.sdiv.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.sdiv.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.sdiv.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.sdiv.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated, signed division of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.sdiv``' intrinsic performs signed division (:ref:`sdiv <i_sdiv>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.sdiv.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = sdiv <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_udiv:
'``llvm.vp.udiv.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.udiv.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.udiv.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.udiv.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated, unsigned division of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The third operand is the vector mask and has the same number of elements as the result vector type. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.udiv``' intrinsic performs unsigned division
(:ref:`udiv <i_udiv>`) of the first and second vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.udiv.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = udiv <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_srem:
'``llvm.vp.srem.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.srem.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.srem.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.srem.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated computations of the signed remainder of two integer vectors.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.srem``' intrinsic computes the remainder of the signed division
(:ref:`srem <i_srem>`) of the first and second vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.srem.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = srem <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_urem:
'``llvm.vp.urem.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.urem.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.urem.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.urem.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated computation of the unsigned remainder of two integer vectors.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.urem``' intrinsic computes the remainder of the unsigned division
(:ref:`urem <i_urem>`) of the first and second vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.urem.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = urem <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_ashr:
'``llvm.vp.ashr.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.ashr.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.ashr.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.ashr.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated arithmetic right-shift.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.ashr``' intrinsic computes the arithmetic right shift
(:ref:`ashr <i_ashr>`) of the first operand by the second operand on each
enabled lane. The result on disabled lanes is a
:ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.ashr.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = ashr <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_lshr:
'``llvm.vp.lshr.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.lshr.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.lshr.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.lshr.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated logical right-shift.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.lshr``' intrinsic computes the logical right shift
(:ref:`lshr <i_lshr>`) of the first operand by the second operand on each
enabled lane. The result on disabled lanes is a
:ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.lshr.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = lshr <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_shl:
'``llvm.vp.shl.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.shl.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.shl.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.shl.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated left shift.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.shl``' intrinsic computes the left shift (:ref:`shl <i_shl>`) of
the first operand by the second operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.shl.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = shl <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_or:
'``llvm.vp.or.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.or.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.or.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.or.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated or.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.or``' intrinsic performs a bitwise or (:ref:`or <i_or>`) of the
first two operands on each enabled lane. The result on disabled lanes is
a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.or.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = or <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_and:
'``llvm.vp.and.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.and.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.and.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.and.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated and.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.and``' intrinsic performs a bitwise and (:ref:`and <i_or>`) of
the first two operands on each enabled lane. The result on disabled lanes is
a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = and <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_xor:
'``llvm.vp.xor.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.xor.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.xor.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.xor.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Vector-predicated, bitwise xor.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.xor``' intrinsic performs a bitwise xor (:ref:`xor <i_xor>`) of
the first two operands on each enabled lane.
The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.xor.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = xor <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_abs:
'``llvm.vp.abs.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.abs.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>, i1 <is_int_min_poison>)
declare <vscale x 4 x i32> @llvm.vp.abs.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>, i1 <is_int_min_poison>)
declare <256 x i64> @llvm.vp.abs.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>, i1 <is_int_min_poison>)
Overview:
"""""""""
Predicated abs of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation. The fourth argument must be a constant and is a flag to indicate
whether the result value of the '``llvm.vp.abs``' intrinsic is a
:ref:`poison value <poisonvalues>` if the argument is statically or dynamically
an ``INT_MIN`` value.
Semantics:
""""""""""
The '``llvm.vp.abs``' intrinsic performs abs (:ref:`abs <int_abs>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.abs.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl, i1 false)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.abs.v4i32(<4 x i32> %a, i1 false)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_smax:
'``llvm.vp.smax.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.smax.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.smax.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.smax.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer signed maximum of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.smax``' intrinsic performs integer signed maximum (:ref:`smax <int_smax>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.smax.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.smax.v4i32(<4 x i32> %a, <4 x i32> %b)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_smin:
'``llvm.vp.smin.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.smin.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.smin.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.smin.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer signed minimum of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.smin``' intrinsic performs integer signed minimum (:ref:`smin <int_smin>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.smin.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %a, <4 x i32> %b)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_umax:
'``llvm.vp.umax.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.umax.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.umax.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.umax.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer unsigned maximum of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.umax``' intrinsic performs integer unsigned maximum (:ref:`umax <int_umax>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.umax.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.umax.v4i32(<4 x i32> %a, <4 x i32> %b)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_umin:
'``llvm.vp.umin.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.umin.v16i32 (<16 x i32> <left_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.umin.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.umin.v256i64 (<256 x i64> <left_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer unsigned minimum of two vectors of integers.
Arguments:
""""""""""
The first two operands and the result have the same vector of integer type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.umin``' intrinsic performs integer unsigned minimum (:ref:`umin <int_umin>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.umin.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.umin.v4i32(<4 x i32> %a, <4 x i32> %b)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_copysign:
'``llvm.vp.copysign.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.copysign.v16f32 (<16 x float> <mag_op>, <16 x float> <sign_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.copysign.nxv4f32 (<vscale x 4 x float> <mag_op>, <vscale x 4 x float> <sign_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.copysign.v256f64 (<256 x double> <mag_op>, <256 x double> <sign_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point copysign of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.copysign``' intrinsic performs floating-point copysign (:ref:`copysign <int_copysign>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.copysign.v4f32(<4 x float> %mag, <4 x float> %sign, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.copysign.v4f32(<4 x float> %mag, <4 x float> %sign)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_minnum:
'``llvm.vp.minnum.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.minnum.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.minnum.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.minnum.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point IEEE-754 minNum of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.minnum``' intrinsic performs floating-point minimum (:ref:`minnum <i_minnum>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.minnum.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.minnum.v4f32(<4 x float> %a, <4 x float> %b)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_maxnum:
'``llvm.vp.maxnum.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.maxnum.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.maxnum.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.maxnum.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point IEEE-754 maxNum of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.maxnum``' intrinsic performs floating-point maximum (:ref:`maxnum <i_maxnum>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.maxnum.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fadd:
'``llvm.vp.fadd.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fadd.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fadd.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fadd.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point addition of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fadd``' intrinsic performs floating-point addition (:ref:`fadd <i_fadd>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fadd <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fsub:
'``llvm.vp.fsub.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fsub.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fsub.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fsub.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point subtraction of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fsub``' intrinsic performs floating-point subtraction (:ref:`fsub <i_fsub>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fsub.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fsub <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fmul:
'``llvm.vp.fmul.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fmul.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fmul.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fmul.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point multiplication of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fmul``' intrinsic performs floating-point multiplication (:ref:`fmul <i_fmul>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fmul.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fmul <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fdiv:
'``llvm.vp.fdiv.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fdiv.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fdiv.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fdiv.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point division of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fdiv``' intrinsic performs floating-point division (:ref:`fdiv <i_fdiv>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fdiv.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fdiv <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_frem:
'``llvm.vp.frem.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.frem.v16f32 (<16 x float> <left_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.frem.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.frem.v256f64 (<256 x double> <left_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point remainder of two vectors of floating-point values.
Arguments:
""""""""""
The first two operands and the result have the same vector of floating-point type. The
third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.frem``' intrinsic performs floating-point remainder (:ref:`frem <i_frem>`)
of the first and second vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.frem.v4f32(<4 x float> %a, <4 x float> %b, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = frem <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fneg:
'``llvm.vp.fneg.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fneg.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fneg.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fneg.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point negation of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fneg``' intrinsic performs floating-point negation (:ref:`fneg <i_fneg>`)
of the first vector operand on each enabled lane. The result on disabled lanes
is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fneg.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fneg <4 x float> %a
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fabs:
'``llvm.vp.fabs.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fabs.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fabs.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fabs.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point absolute value of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fabs``' intrinsic performs floating-point absolute value
(:ref:`fabs <int_fabs>`) of the first vector operand on each enabled lane. The
result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fabs.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_sqrt:
'``llvm.vp.sqrt.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.sqrt.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.sqrt.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.sqrt.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point square root of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.sqrt``' intrinsic performs floating-point square root (:ref:`sqrt <int_sqrt>`) of
the first vector operand on each enabled lane. The result on disabled lanes is
a :ref:`poison value <poisonvalues>`. The operation is performed in the default
floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.sqrt.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fma:
'``llvm.vp.fma.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fma.v16f32 (<16 x float> <left_op>, <16 x float> <middle_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fma.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <middle_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fma.v256f64 (<256 x double> <left_op>, <256 x double> <middle_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point fused multiply-add of two vectors of floating-point values.
Arguments:
""""""""""
The first three operands and the result have the same vector of floating-point type. The
fourth operand is the vector mask and has the same number of elements as the
result vector type. The fifth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fma``' intrinsic performs floating-point fused multiply-add (:ref:`llvm.fma <int_fma>`)
of the first, second, and third vector operand on each enabled lane. The result on
disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.fma(<4 x float> %a, <4 x float> %b, <4 x float> %c)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fmuladd:
'``llvm.vp.fmuladd.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fmuladd.v16f32 (<16 x float> <left_op>, <16 x float> <middle_op>, <16 x float> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.fmuladd.nxv4f32 (<vscale x 4 x float> <left_op>, <vscale x 4 x float> <middle_op>, <vscale x 4 x float> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.fmuladd.v256f64 (<256 x double> <left_op>, <256 x double> <middle_op>, <256 x double> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point multiply-add of two vectors of floating-point values
that can be fused if code generator determines that (a) the target instruction
set has support for a fused operation, and (b) that the fused operation is more
efficient than the equivalent, separate pair of mul and add instructions.
Arguments:
""""""""""
The first three operands and the result have the same vector of floating-point
type. The fourth operand is the vector mask and has the same number of elements
as the result vector type. The fifth operand is the explicit vector length of
the operation.
Semantics:
""""""""""
The '``llvm.vp.fmuladd``' intrinsic performs floating-point multiply-add (:ref:`llvm.fuladd <int_fmuladd>`)
of the first, second, and third vector operand on each enabled lane. The result
on disabled lanes is a :ref:`poison value <poisonvalues>`. The operation is
performed in the default floating-point environment.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fmuladd.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.fmuladd(<4 x float> %a, <4 x float> %b, <4 x float> %c)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_reduce_add:
'``llvm.vp.reduce.add.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.add.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.add.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer ``ADD`` reduction of a vector and a scalar starting value,
returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.add``' intrinsic performs the integer ``ADD`` reduction
(:ref:`llvm.vector.reduce.add <int_vector_reduce_add>`) of the vector operand
``val`` on each enabled lane, adding it to the scalar ``start_value``. Disabled
lanes are treated as containing the neutral value ``0`` (i.e. having no effect
on the reduction operation). If the vector length is zero, the result is equal
to ``start_value``.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.add.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> zeroinitializer
%reduction = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %masked.a)
%also.r = add i32 %reduction, %start
.. _int_vp_reduce_fadd:
'``llvm.vp.reduce.fadd.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vp.reduce.fadd.v4f32(float <start_value>, <4 x float> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare double @llvm.vp.reduce.fadd.nxv8f64(double <start_value>, <vscale x 8 x double> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point ``ADD`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
floating-point type equal to the result type. The second operand is the vector
on which the reduction is performed and must be a vector of floating-point
values whose element type is the result/start type. The third operand is the
vector mask and is a vector of boolean values with the same number of elements
as the vector operand. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.fadd``' intrinsic performs the floating-point ``ADD``
reduction (:ref:`llvm.vector.reduce.fadd <int_vector_reduce_fadd>`) of the
vector operand ``val`` on each enabled lane, adding it to the scalar
``start_value``. Disabled lanes are treated as containing the neutral value
``-0.0`` (i.e. having no effect on the reduction operation). If no lanes are
enabled, the resulting value will be equal to ``start_value``.
To ignore the start value, the neutral value can be used.
See the unpredicated version (:ref:`llvm.vector.reduce.fadd
<int_vector_reduce_fadd>`) for more detail on the semantics of the reduction.
Examples:
"""""""""
.. code-block:: llvm
%r = call float @llvm.vp.reduce.fadd.v4f32(float %start, <4 x float> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x float> %a, <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>
%also.r = call float @llvm.vector.reduce.fadd.v4f32(float %start, <4 x float> %masked.a)
.. _int_vp_reduce_mul:
'``llvm.vp.reduce.mul.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.mul.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.mul.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer ``MUL`` reduction of a vector and a scalar starting value,
returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.mul``' intrinsic performs the integer ``MUL`` reduction
(:ref:`llvm.vector.reduce.mul <int_vector_reduce_mul>`) of the vector operand ``val``
on each enabled lane, multiplying it by the scalar ``start_value``. Disabled
lanes are treated as containing the neutral value ``1`` (i.e. having no effect
on the reduction operation). If the vector length is zero, the result is the
start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.mul.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
%reduction = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> %masked.a)
%also.r = mul i32 %reduction, %start
.. _int_vp_reduce_fmul:
'``llvm.vp.reduce.fmul.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vp.reduce.fmul.v4f32(float <start_value>, <4 x float> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare double @llvm.vp.reduce.fmul.nxv8f64(double <start_value>, <vscale x 8 x double> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point ``MUL`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
floating-point type equal to the result type. The second operand is the vector
on which the reduction is performed and must be a vector of floating-point
values whose element type is the result/start type. The third operand is the
vector mask and is a vector of boolean values with the same number of elements
as the vector operand. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.fmul``' intrinsic performs the floating-point ``MUL``
reduction (:ref:`llvm.vector.reduce.fmul <int_vector_reduce_fmul>`) of the
vector operand ``val`` on each enabled lane, multiplying it by the scalar
`start_value``. Disabled lanes are treated as containing the neutral value
``1.0`` (i.e. having no effect on the reduction operation). If no lanes are
enabled, the resulting value will be equal to the starting value.
To ignore the start value, the neutral value can be used.
See the unpredicated version (:ref:`llvm.vector.reduce.fmul
<int_vector_reduce_fmul>`) for more detail on the semantics.
Examples:
"""""""""
.. code-block:: llvm
%r = call float @llvm.vp.reduce.fmul.v4f32(float %start, <4 x float> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x float> %a, <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>
%also.r = call float @llvm.vector.reduce.fmul.v4f32(float %start, <4 x float> %masked.a)
.. _int_vp_reduce_and:
'``llvm.vp.reduce.and.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.and.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.and.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer ``AND`` reduction of a vector and a scalar starting value,
returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.and``' intrinsic performs the integer ``AND`` reduction
(:ref:`llvm.vector.reduce.and <int_vector_reduce_and>`) of the vector operand
``val`` on each enabled lane, performing an '``and``' of that with with the
scalar ``start_value``. Disabled lanes are treated as containing the neutral
value ``UINT_MAX``, or ``-1`` (i.e. having no effect on the reduction
operation). If the vector length is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.and.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
%reduction = call i32 @llvm.vector.reduce.and.v4i32(<4 x i32> %masked.a)
%also.r = and i32 %reduction, %start
.. _int_vp_reduce_or:
'``llvm.vp.reduce.or.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.or.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.or.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer ``OR`` reduction of a vector and a scalar starting value,
returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.or``' intrinsic performs the integer ``OR`` reduction
(:ref:`llvm.vector.reduce.or <int_vector_reduce_or>`) of the vector operand
``val`` on each enabled lane, performing an '``or``' of that with the scalar
``start_value``. Disabled lanes are treated as containing the neutral value
``0`` (i.e. having no effect on the reduction operation). If the vector length
is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.or.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
%reduction = call i32 @llvm.vector.reduce.or.v4i32(<4 x i32> %masked.a)
%also.r = or i32 %reduction, %start
.. _int_vp_reduce_xor:
'``llvm.vp.reduce.xor.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.xor.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.xor.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated integer ``XOR`` reduction of a vector and a scalar starting value,
returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.xor``' intrinsic performs the integer ``XOR`` reduction
(:ref:`llvm.vector.reduce.xor <int_vector_reduce_xor>`) of the vector operand
``val`` on each enabled lane, performing an '``xor``' of that with the scalar
``start_value``. Disabled lanes are treated as containing the neutral value
``0`` (i.e. having no effect on the reduction operation). If the vector length
is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.xor.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
%reduction = call i32 @llvm.vector.reduce.xor.v4i32(<4 x i32> %masked.a)
%also.r = xor i32 %reduction, %start
.. _int_vp_reduce_smax:
'``llvm.vp.reduce.smax.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.smax.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.smax.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated signed-integer ``MAX`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.smax``' intrinsic performs the signed-integer ``MAX``
reduction (:ref:`llvm.vector.reduce.smax <int_vector_reduce_smax>`) of the
vector operand ``val`` on each enabled lane, and taking the maximum of that and
the scalar ``start_value``. Disabled lanes are treated as containing the
neutral value ``INT_MIN`` (i.e. having no effect on the reduction operation).
If the vector length is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i8 @llvm.vp.reduce.smax.v4i8(i8 %start, <4 x i8> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i8> %a, <4 x i8> <i8 -128, i8 -128, i8 -128, i8 -128>
%reduction = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> %masked.a)
%also.r = call i8 @llvm.smax.i8(i8 %reduction, i8 %start)
.. _int_vp_reduce_smin:
'``llvm.vp.reduce.smin.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.smin.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.smin.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated signed-integer ``MIN`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.smin``' intrinsic performs the signed-integer ``MIN``
reduction (:ref:`llvm.vector.reduce.smin <int_vector_reduce_smin>`) of the
vector operand ``val`` on each enabled lane, and taking the minimum of that and
the scalar ``start_value``. Disabled lanes are treated as containing the
neutral value ``INT_MAX`` (i.e. having no effect on the reduction operation).
If the vector length is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i8 @llvm.vp.reduce.smin.v4i8(i8 %start, <4 x i8> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i8> %a, <4 x i8> <i8 127, i8 127, i8 127, i8 127>
%reduction = call i8 @llvm.vector.reduce.smin.v4i8(<4 x i8> %masked.a)
%also.r = call i8 @llvm.smin.i8(i8 %reduction, i8 %start)
.. _int_vp_reduce_umax:
'``llvm.vp.reduce.umax.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.umax.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.umax.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated unsigned-integer ``MAX`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.umax``' intrinsic performs the unsigned-integer ``MAX``
reduction (:ref:`llvm.vector.reduce.umax <int_vector_reduce_umax>`) of the
vector operand ``val`` on each enabled lane, and taking the maximum of that and
the scalar ``start_value``. Disabled lanes are treated as containing the
neutral value ``0`` (i.e. having no effect on the reduction operation). If the
vector length is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.umax.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
%reduction = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %masked.a)
%also.r = call i32 @llvm.umax.i32(i32 %reduction, i32 %start)
.. _int_vp_reduce_umin:
'``llvm.vp.reduce.umin.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare i32 @llvm.vp.reduce.umin.v4i32(i32 <start_value>, <4 x i32> <val>, <4 x i1> <mask>, i32 <vector_length>)
declare i16 @llvm.vp.reduce.umin.nxv8i16(i16 <start_value>, <vscale x 8 x i16> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated unsigned-integer ``MIN`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
integer type equal to the result type. The second operand is the vector on
which the reduction is performed and must be a vector of integer values whose
element type is the result/start type. The third operand is the vector mask and
is a vector of boolean values with the same number of elements as the vector
operand. The fourth operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.umin``' intrinsic performs the unsigned-integer ``MIN``
reduction (:ref:`llvm.vector.reduce.umin <int_vector_reduce_umin>`) of the
vector operand ``val`` on each enabled lane, taking the minimum of that and the
scalar ``start_value``. Disabled lanes are treated as containing the neutral
value ``UINT_MAX``, or ``-1`` (i.e. having no effect on the reduction
operation). If the vector length is zero, the result is the start value.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call i32 @llvm.vp.reduce.umin.v4i32(i32 %start, <4 x i32> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x i32> %a, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
%reduction = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %masked.a)
%also.r = call i32 @llvm.umin.i32(i32 %reduction, i32 %start)
.. _int_vp_reduce_fmax:
'``llvm.vp.reduce.fmax.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vp.reduce.fmax.v4f32(float <start_value>, <4 x float> <val>, <4 x i1> <mask>, float <vector_length>)
declare double @llvm.vp.reduce.fmax.nxv8f64(double <start_value>, <vscale x 8 x double> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point ``MAX`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
floating-point type equal to the result type. The second operand is the vector
on which the reduction is performed and must be a vector of floating-point
values whose element type is the result/start type. The third operand is the
vector mask and is a vector of boolean values with the same number of elements
as the vector operand. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.fmax``' intrinsic performs the floating-point ``MAX``
reduction (:ref:`llvm.vector.reduce.fmax <int_vector_reduce_fmax>`) of the
vector operand ``val`` on each enabled lane, taking the maximum of that and the
scalar ``start_value``. Disabled lanes are treated as containing the neutral
value (i.e. having no effect on the reduction operation). If the vector length
is zero, the result is the start value.
The neutral value is dependent on the :ref:`fast-math flags <fastmath>`. If no
flags are set, the neutral value is ``-QNAN``. If ``nnan`` and ``ninf`` are
both set, then the neutral value is the smallest floating-point value for the
result type. If only ``nnan`` is set then the neutral value is ``-Infinity``.
This instruction has the same comparison semantics as the
:ref:`llvm.vector.reduce.fmax <int_vector_reduce_fmax>` intrinsic (and thus the
'``llvm.maxnum.*``' intrinsic). That is, the result will always be a number
unless all elements of the vector and the starting value are ``NaN``. For a
vector with maximum element magnitude ``0.0`` and containing both ``+0.0`` and
``-0.0`` elements, the sign of the result is unspecified.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call float @llvm.vp.reduce.fmax.v4f32(float %float, <4 x float> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x float> %a, <4 x float> <float QNAN, float QNAN, float QNAN, float QNAN>
%reduction = call float @llvm.vector.reduce.fmax.v4f32(<4 x float> %masked.a)
%also.r = call float @llvm.maxnum.f32(float %reduction, float %start)
.. _int_vp_reduce_fmin:
'``llvm.vp.reduce.fmin.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare float @llvm.vp.reduce.fmin.v4f32(float <start_value>, <4 x float> <val>, <4 x i1> <mask>, float <vector_length>)
declare double @llvm.vp.reduce.fmin.nxv8f64(double <start_value>, <vscale x 8 x double> <val>, <vscale x 8 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point ``MIN`` reduction of a vector and a scalar starting
value, returning the result as a scalar.
Arguments:
""""""""""
The first operand is the start value of the reduction, which must be a scalar
floating-point type equal to the result type. The second operand is the vector
on which the reduction is performed and must be a vector of floating-point
values whose element type is the result/start type. The third operand is the
vector mask and is a vector of boolean values with the same number of elements
as the vector operand. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.reduce.fmin``' intrinsic performs the floating-point ``MIN``
reduction (:ref:`llvm.vector.reduce.fmin <int_vector_reduce_fmin>`) of the
vector operand ``val`` on each enabled lane, taking the minimum of that and the
scalar ``start_value``. Disabled lanes are treated as containing the neutral
value (i.e. having no effect on the reduction operation). If the vector length
is zero, the result is the start value.
The neutral value is dependent on the :ref:`fast-math flags <fastmath>`. If no
flags are set, the neutral value is ``+QNAN``. If ``nnan`` and ``ninf`` are
both set, then the neutral value is the largest floating-point value for the
result type. If only ``nnan`` is set then the neutral value is ``+Infinity``.
This instruction has the same comparison semantics as the
:ref:`llvm.vector.reduce.fmin <int_vector_reduce_fmin>` intrinsic (and thus the
'``llvm.minnum.*``' intrinsic). That is, the result will always be a number
unless all elements of the vector and the starting value are ``NaN``. For a
vector with maximum element magnitude ``0.0`` and containing both ``+0.0`` and
``-0.0`` elements, the sign of the result is unspecified.
To ignore the start value, the neutral value can be used.
Examples:
"""""""""
.. code-block:: llvm
%r = call float @llvm.vp.reduce.fmin.v4f32(float %start, <4 x float> %a, <4 x i1> %mask, i32 %evl)
; %r is equivalent to %also.r, where lanes greater than or equal to %evl
; are treated as though %mask were false for those lanes.
%masked.a = select <4 x i1> %mask, <4 x float> %a, <4 x float> <float QNAN, float QNAN, float QNAN, float QNAN>
%reduction = call float @llvm.vector.reduce.fmin.v4f32(<4 x float> %masked.a)
%also.r = call float @llvm.minnum.f32(float %reduction, float %start)
.. _int_get_active_lane_mask:
'``llvm.get.active.lane.mask.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %base, i32 %n)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 %base, i64 %n)
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 %base, i64 %n)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 %base, i64 %n)
Overview:
"""""""""
Create a mask representing active and inactive vector lanes.
Arguments:
""""""""""
Both operands have the same scalar integer type. The result is a vector with
the i1 element type.
Semantics:
""""""""""
The '``llvm.get.active.lane.mask.*``' intrinsics are semantically equivalent
to:
::
%m[i] = icmp ult (%base + i), %n
where ``%m`` is a vector (mask) of active/inactive lanes with its elements
indexed by ``i``, and ``%base``, ``%n`` are the two arguments to
``llvm.get.active.lane.mask.*``, ``%icmp`` is an integer compare and ``ult``
the unsigned less-than comparison operator. Overflow cannot occur in
``(%base + i)`` and its comparison against ``%n`` as it is performed in integer
numbers and not in machine numbers. If ``%n`` is ``0``, then the result is a
poison value. The above is equivalent to:
::
%m = @llvm.get.active.lane.mask(%base, %n)
This can, for example, be emitted by the loop vectorizer in which case
``%base`` is the first element of the vector induction variable (VIV) and
``%n`` is the loop tripcount. Thus, these intrinsics perform an element-wise
less than comparison of VIV with the loop tripcount, producing a mask of
true/false values representing active/inactive vector lanes, except if the VIV
overflows in which case they return false in the lanes where the VIV overflows.
The arguments are scalar types to accommodate scalable vector types, for which
it is unknown what the type of the step vector needs to be that enumerate its
lanes without overflow.
This mask ``%m`` can e.g. be used in masked load/store instructions. These
intrinsics provide a hint to the backend. I.e., for a vector loop, the
back-edge taken count of the original scalar loop is explicit as the second
argument.
Examples:
"""""""""
.. code-block:: llvm
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 %elem0, i64 429)
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %3, i32 4, <4 x i1> %active.lane.mask, <4 x i32> poison)
.. _int_experimental_vp_splice:
'``llvm.experimental.vp.splice``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <2 x double> @llvm.experimental.vp.splice.v2f64(<2 x double> %vec1, <2 x double> %vec2, i32 %imm, <2 x i1> %mask, i32 %evl1, i32 %evl2)
declare <vscale x 4 x i32> @llvm.experimental.vp.splice.nxv4i32(<vscale x 4 x i32> %vec1, <vscale x 4 x i32> %vec2, i32 %imm, <vscale x 4 x i1> %mask, i32 %evl1, i32 %evl2)
Overview:
"""""""""
The '``llvm.experimental.vp.splice.*``' intrinsic is the vector length
predicated version of the '``llvm.experimental.vector.splice.*``' intrinsic.
Arguments:
""""""""""
The result and the first two arguments ``vec1`` and ``vec2`` are vectors with
the same type. The third argument ``imm`` is an immediate signed integer that
indicates the offset index. The fourth argument ``mask`` is a vector mask and
has the same number of elements as the result. The last two arguments ``evl1``
and ``evl2`` are unsigned integers indicating the explicit vector lengths of
``vec1`` and ``vec2`` respectively. ``imm``, ``evl1`` and ``evl2`` should
respect the following constraints: ``-evl1 <= imm < evl1``, ``0 <= evl1 <= VL``
and ``0 <= evl2 <= VL``, where ``VL`` is the runtime vector factor. If these
constraints are not satisfied the intrinsic has undefined behaviour.
Semantics:
""""""""""
Effectively, this intrinsic concatenates ``vec1[0..evl1-1]`` and
``vec2[0..evl2-1]`` and creates the result vector by selecting the elements in a
window of size ``evl2``, starting at index ``imm`` (for a positive immediate) of
the concatenated vector. Elements in the result vector beyond ``evl2`` are
``undef``. If ``imm`` is negative the starting index is ``evl1 + imm``. The result
vector of active vector length ``evl2`` contains ``evl1 - imm`` (``-imm`` for
negative ``imm``) elements from indices ``[imm..evl1 - 1]``
(``[evl1 + imm..evl1 -1]`` for negative ``imm``) of ``vec1`` followed by the
first ``evl2 - (evl1 - imm)`` (``evl2 + imm`` for negative ``imm``) elements of
``vec2``. If ``evl1 - imm`` (``-imm``) >= ``evl2``, only the first ``evl2``
elements are considered and the remaining are ``undef``. The lanes in the result
vector disabled by ``mask`` are ``poison``.
Examples:
"""""""""
.. code-block:: text
llvm.experimental.vp.splice(<A,B,C,D>, <E,F,G,H>, 1, 2, 3); ==> <B, E, F, poison> index
llvm.experimental.vp.splice(<A,B,C,D>, <E,F,G,H>, -2, 3, 2); ==> <B, C, poison, poison> trailing elements
.. _int_experimental_vp_reverse:
'``llvm.experimental.vp.reverse``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <2 x double> @llvm.experimental.vp.reverse.v2f64(<2 x double> %vec, <2 x i1> %mask, i32 %evl)
declare <vscale x 4 x i32> @llvm.experimental.vp.reverse.nxv4i32(<vscale x 4 x i32> %vec, <vscale x 4 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.experimental.vp.reverse.*``' intrinsic is the vector length
predicated version of the '``llvm.experimental.vector.reverse.*``' intrinsic.
Arguments:
""""""""""
The result and the first argument ``vec`` are vectors with the same type.
The second argument ``mask`` is a vector mask and has the same number of
elements as the result. The third argument is the explicit vector length of
the operation.
Semantics:
""""""""""
This intrinsic reverses the order of the first ``evl`` elements in a vector.
The lanes in the result vector disabled by ``mask`` are ``poison``. The
elements past ``evl`` are poison.
.. _int_vp_load:
'``llvm.vp.load``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <4 x float> @llvm.vp.load.v4f32.p0(ptr %ptr, <4 x i1> %mask, i32 %evl)
declare <vscale x 2 x i16> @llvm.vp.load.nxv2i16.p0(ptr %ptr, <vscale x 2 x i1> %mask, i32 %evl)
declare <8 x float> @llvm.vp.load.v8f32.p1(ptr addrspace(1) %ptr, <8 x i1> %mask, i32 %evl)
declare <vscale x 1 x i64> @llvm.vp.load.nxv1i64.p6(ptr addrspace(6) %ptr, <vscale x 1 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.vp.load.*``' intrinsic is the vector length predicated version of
the :ref:`llvm.masked.load <int_mload>` intrinsic.
Arguments:
""""""""""
The first operand is the base pointer for the load. The second operand is a
vector of boolean values with the same number of elements as the return type.
The third is the explicit vector length of the operation. The return type and
underlying type of the base pointer are the same vector types.
The :ref:`align <attr_align>` parameter attribute can be provided for the first
operand.
Semantics:
""""""""""
The '``llvm.vp.load``' intrinsic reads a vector from memory in the same way as
the '``llvm.masked.load``' intrinsic, where the mask is taken from the
combination of the '``mask``' and '``evl``' operands in the usual VP way.
Certain '``llvm.masked.load``' operands do not have corresponding operands in
'``llvm.vp.load``': the '``passthru``' operand is implicitly ``poison``; the
'``alignment``' operand is taken as the ``align`` parameter attribute, if
provided. The default alignment is taken as the ABI alignment of the return
type as specified by the :ref:`datalayout string<langref_datalayout>`.
Examples:
"""""""""
.. code-block:: text
%r = call <8 x i8> @llvm.vp.load.v8i8.p0(ptr align 2 %ptr, <8 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%also.r = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr %ptr, i32 2, <8 x i1> %mask, <8 x i8> poison)
.. _int_vp_store:
'``llvm.vp.store``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare void @llvm.vp.store.v4f32.p0(<4 x float> %val, ptr %ptr, <4 x i1> %mask, i32 %evl)
declare void @llvm.vp.store.nxv2i16.p0(<vscale x 2 x i16> %val, ptr %ptr, <vscale x 2 x i1> %mask, i32 %evl)
declare void @llvm.vp.store.v8f32.p1(<8 x float> %val, ptr addrspace(1) %ptr, <8 x i1> %mask, i32 %evl)
declare void @llvm.vp.store.nxv1i64.p6(<vscale x 1 x i64> %val, ptr addrspace(6) %ptr, <vscale x 1 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.vp.store.*``' intrinsic is the vector length predicated version of
the :ref:`llvm.masked.store <int_mstore>` intrinsic.
Arguments:
""""""""""
The first operand is the vector value to be written to memory. The second
operand is the base pointer for the store. It has the same underlying type as
the value operand. The third operand is a vector of boolean values with the
same number of elements as the return type. The fourth is the explicit vector
length of the operation.
The :ref:`align <attr_align>` parameter attribute can be provided for the
second operand.
Semantics:
""""""""""
The '``llvm.vp.store``' intrinsic reads a vector from memory in the same way as
the '``llvm.masked.store``' intrinsic, where the mask is taken from the
combination of the '``mask``' and '``evl``' operands in the usual VP way. The
alignment of the operation (corresponding to the '``alignment``' operand of
'``llvm.masked.store``') is specified by the ``align`` parameter attribute (see
above). If it is not provided then the ABI alignment of the type of the
'``value``' operand as specified by the :ref:`datalayout
string<langref_datalayout>` is used instead.
Examples:
"""""""""
.. code-block:: text
call void @llvm.vp.store.v8i8.p0(<8 x i8> %val, ptr align 4 %ptr, <8 x i1> %mask, i32 %evl)
;; For all lanes below %evl, the call above is lane-wise equivalent to the call below.
call void @llvm.masked.store.v8i8.p0(<8 x i8> %val, ptr %ptr, i32 4, <8 x i1> %mask)
.. _int_experimental_vp_strided_load:
'``llvm.experimental.vp.strided.load``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <4 x float> @llvm.experimental.vp.strided.load.v4f32.i64(ptr %ptr, i64 %stride, <4 x i1> %mask, i32 %evl)
declare <vscale x 2 x i16> @llvm.experimental.vp.strided.load.nxv2i16.i64(ptr %ptr, i64 %stride, <vscale x 2 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.experimental.vp.strided.load``' intrinsic loads, into a vector, scalar values from
memory locations evenly spaced apart by '``stride``' number of bytes, starting from '``ptr``'.
Arguments:
""""""""""
The first operand is the base pointer for the load. The second operand is the stride
value expressed in bytes. The third operand is a vector of boolean values
with the same number of elements as the return type. The fourth is the explicit
vector length of the operation. The base pointer underlying type matches the type of the scalar
elements of the return operand.
The :ref:`align <attr_align>` parameter attribute can be provided for the first
operand.
Semantics:
""""""""""
The '``llvm.experimental.vp.strided.load``' intrinsic loads, into a vector, multiple scalar
values from memory in the same way as the :ref:`llvm.vp.gather <int_vp_gather>` intrinsic,
where the vector of pointers is in the form:
``%ptrs = <%ptr, %ptr + %stride, %ptr + 2 * %stride, ... >``,
with '``ptr``' previously casted to a pointer '``i8``', '``stride``' always interpreted as a signed
integer and all arithmetic occurring in the pointer type.
Examples:
"""""""""
.. code-block:: text
%r = call <8 x i64> @llvm.experimental.vp.strided.load.v8i64.i64(i64* %ptr, i64 %stride, <8 x i64> %mask, i32 %evl)
;; The operation can also be expressed like this:
%addr = bitcast i64* %ptr to i8*
;; Create a vector of pointers %addrs in the form:
;; %addrs = <%addr, %addr + %stride, %addr + 2 * %stride, ...>
%ptrs = bitcast <8 x i8* > %addrs to <8 x i64* >
%also.r = call <8 x i64> @llvm.vp.gather.v8i64.v8p0i64(<8 x i64* > %ptrs, <8 x i64> %mask, i32 %evl)
.. _int_experimental_vp_strided_store:
'``llvm.experimental.vp.strided.store``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare void @llvm.experimental.vp.strided.store.v4f32.i64(<4 x float> %val, ptr %ptr, i64 %stride, <4 x i1> %mask, i32 %evl)
declare void @llvm.experimental.vp.strided.store.nxv2i16.i64(<vscale x 2 x i16> %val, ptr %ptr, i64 %stride, <vscale x 2 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``@llvm.experimental.vp.strided.store``' intrinsic stores the elements of
'``val``' into memory locations evenly spaced apart by '``stride``' number of
bytes, starting from '``ptr``'.
Arguments:
""""""""""
The first operand is the vector value to be written to memory. The second
operand is the base pointer for the store. Its underlying type matches the
scalar element type of the value operand. The third operand is the stride value
expressed in bytes. The fourth operand is a vector of boolean values with the
same number of elements as the return type. The fifth is the explicit vector
length of the operation.
The :ref:`align <attr_align>` parameter attribute can be provided for the
second operand.
Semantics:
""""""""""
The '``llvm.experimental.vp.strided.store``' intrinsic stores the elements of
'``val``' in the same way as the :ref:`llvm.vp.scatter <int_vp_scatter>` intrinsic,
where the vector of pointers is in the form:
``%ptrs = <%ptr, %ptr + %stride, %ptr + 2 * %stride, ... >``,
with '``ptr``' previously casted to a pointer '``i8``', '``stride``' always interpreted as a signed
integer and all arithmetic occurring in the pointer type.
Examples:
"""""""""
.. code-block:: text
call void @llvm.experimental.vp.strided.store.v8i64.i64(<8 x i64> %val, i64* %ptr, i64 %stride, <8 x i1> %mask, i32 %evl)
;; The operation can also be expressed like this:
%addr = bitcast i64* %ptr to i8*
;; Create a vector of pointers %addrs in the form:
;; %addrs = <%addr, %addr + %stride, %addr + 2 * %stride, ...>
%ptrs = bitcast <8 x i8* > %addrs to <8 x i64* >
call void @llvm.vp.scatter.v8i64.v8p0i64(<8 x i64> %val, <8 x i64*> %ptrs, <8 x i1> %mask, i32 %evl)
.. _int_vp_gather:
'``llvm.vp.gather``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <4 x double> @llvm.vp.gather.v4f64.v4p0(<4 x ptr> %ptrs, <4 x i1> %mask, i32 %evl)
declare <vscale x 2 x i8> @llvm.vp.gather.nxv2i8.nxv2p0(<vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %mask, i32 %evl)
declare <2 x float> @llvm.vp.gather.v2f32.v2p2(<2 x ptr addrspace(2)> %ptrs, <2 x i1> %mask, i32 %evl)
declare <vscale x 4 x i32> @llvm.vp.gather.nxv4i32.nxv4p4(<vscale x 4 x ptr addrspace(4)> %ptrs, <vscale x 4 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.vp.gather.*``' intrinsic is the vector length predicated version of
the :ref:`llvm.masked.gather <int_mgather>` intrinsic.
Arguments:
""""""""""
The first operand is a vector of pointers which holds all memory addresses to
read. The second operand is a vector of boolean values with the same number of
elements as the return type. The third is the explicit vector length of the
operation. The return type and underlying type of the vector of pointers are
the same vector types.
The :ref:`align <attr_align>` parameter attribute can be provided for the first
operand.
Semantics:
""""""""""
The '``llvm.vp.gather``' intrinsic reads multiple scalar values from memory in
the same way as the '``llvm.masked.gather``' intrinsic, where the mask is taken
from the combination of the '``mask``' and '``evl``' operands in the usual VP
way. Certain '``llvm.masked.gather``' operands do not have corresponding
operands in '``llvm.vp.gather``': the '``passthru``' operand is implicitly
``poison``; the '``alignment``' operand is taken as the ``align`` parameter, if
provided. The default alignment is taken as the ABI alignment of the source
addresses as specified by the :ref:`datalayout string<langref_datalayout>`.
Examples:
"""""""""
.. code-block:: text
%r = call <8 x i8> @llvm.vp.gather.v8i8.v8p0(<8 x ptr> align 8 %ptrs, <8 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%also.r = call <8 x i8> @llvm.masked.gather.v8i8.v8p0(<8 x ptr> %ptrs, i32 8, <8 x i1> %mask, <8 x i8> poison)
.. _int_vp_scatter:
'``llvm.vp.scatter``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare void @llvm.vp.scatter.v4f64.v4p0(<4 x double> %val, <4 x ptr> %ptrs, <4 x i1> %mask, i32 %evl)
declare void @llvm.vp.scatter.nxv2i8.nxv2p0(<vscale x 2 x i8> %val, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %mask, i32 %evl)
declare void @llvm.vp.scatter.v2f32.v2p2(<2 x float> %val, <2 x ptr addrspace(2)> %ptrs, <2 x i1> %mask, i32 %evl)
declare void @llvm.vp.scatter.nxv4i32.nxv4p4(<vscale x 4 x i32> %val, <vscale x 4 x ptr addrspace(4)> %ptrs, <vscale x 4 x i1> %mask, i32 %evl)
Overview:
"""""""""
The '``llvm.vp.scatter.*``' intrinsic is the vector length predicated version of
the :ref:`llvm.masked.scatter <int_mscatter>` intrinsic.
Arguments:
""""""""""
The first operand is a vector value to be written to memory. The second operand
is a vector of pointers, pointing to where the value elements should be stored.
The third operand is a vector of boolean values with the same number of
elements as the return type. The fourth is the explicit vector length of the
operation.
The :ref:`align <attr_align>` parameter attribute can be provided for the
second operand.
Semantics:
""""""""""
The '``llvm.vp.scatter``' intrinsic writes multiple scalar values to memory in
the same way as the '``llvm.masked.scatter``' intrinsic, where the mask is
taken from the combination of the '``mask``' and '``evl``' operands in the
usual VP way. The '``alignment``' operand of the '``llvm.masked.scatter``' does
not have a corresponding operand in '``llvm.vp.scatter``': it is instead
provided via the optional ``align`` parameter attribute on the
vector-of-pointers operand. Otherwise it is taken as the ABI alignment of the
destination addresses as specified by the :ref:`datalayout
string<langref_datalayout>`.
Examples:
"""""""""
.. code-block:: text
call void @llvm.vp.scatter.v8i8.v8p0(<8 x i8> %val, <8 x ptr> align 1 %ptrs, <8 x i1> %mask, i32 %evl)
;; For all lanes below %evl, the call above is lane-wise equivalent to the call below.
call void @llvm.masked.scatter.v8i8.v8p0(<8 x i8> %val, <8 x ptr> %ptrs, i32 1, <8 x i1> %mask)
.. _int_vp_trunc:
'``llvm.vp.trunc.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i16> @llvm.vp.trunc.v16i16.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i16> @llvm.vp.trunc.nxv4i16.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.trunc``' intrinsic truncates its first operand to the return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.trunc``' intrinsic takes a value to cast as its first operand.
The return type is the type to cast the value to. Both types must be vector of
:ref:`integer <t_integer>` type. The bit size of the value must be larger than
the bit size of the return type. The second operand is the vector mask. The
return type, the value to cast, and the vector mask have the same number of
elements. The third operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.trunc``' intrinsic truncates the high order bits in value and
converts the remaining bits to return type. Since the source size must be larger
than the destination size, '``llvm.vp.trunc``' cannot be a *no-op cast*. It will
always truncate bits. The conversion is performed on lane positions below the
explicit vector length and where the vector mask is true. Masked-off lanes are
``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i16> @llvm.vp.trunc.v4i16.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = trunc <4 x i32> %a to <4 x i16>
%also.r = select <4 x i1> %mask, <4 x i16> %t, <4 x i16> poison
.. _int_vp_zext:
'``llvm.vp.zext.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.zext.v16i32.v16i16 (<16 x i16> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.zext.nxv4i32.nxv4i16 (<vscale x 4 x i16> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.zext``' intrinsic zero extends its first operand to the return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.zext``' intrinsic takes a value to cast as its first operand.
The return type is the type to cast the value to. Both types must be vectors of
:ref:`integer <t_integer>` type. The bit size of the value must be smaller than
the bit size of the return type. The second operand is the vector mask. The
return type, the value to cast, and the vector mask have the same number of
elements. The third operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.zext``' intrinsic fill the high order bits of the value with zero
bits until it reaches the size of the return type. When zero extending from i1,
the result will always be either 0 or 1. The conversion is performed on lane
positions below the explicit vector length and where the vector mask is true.
Masked-off lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.zext.v4i32.v4i16(<4 x i16> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = zext <4 x i16> %a to <4 x i32>
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_sext:
'``llvm.vp.sext.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.sext.v16i32.v16i16 (<16 x i16> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.sext.nxv4i32.nxv4i16 (<vscale x 4 x i16> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.sext``' intrinsic sign extends its first operand to the return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.sext``' intrinsic takes a value to cast as its first operand.
The return type is the type to cast the value to. Both types must be vectors of
:ref:`integer <t_integer>` type. The bit size of the value must be smaller than
the bit size of the return type. The second operand is the vector mask. The
return type, the value to cast, and the vector mask have the same number of
elements. The third operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.sext``' intrinsic performs a sign extension by copying the sign
bit (highest order bit) of the value until it reaches the size of the return
type. When sign extending from i1, the result will always be either -1 or 0.
The conversion is performed on lane positions below the explicit vector length
and where the vector mask is true. Masked-off lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.sext.v4i32.v4i16(<4 x i16> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = sext <4 x i16> %a to <4 x i32>
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_fptrunc:
'``llvm.vp.fptrunc.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.fptrunc.v16f32.v16f64 (<16 x double> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.trunc.nxv4f32.nxv4f64 (<vscale x 4 x double> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.fptrunc``' intrinsic truncates its first operand to the return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.fptrunc``' intrinsic takes a value to cast as its first operand.
The return type is the type to cast the value to. Both types must be vector of
:ref:`floating-point <t_floating>` type. The bit size of the value must be
larger than the bit size of the return type. This implies that
'``llvm.vp.fptrunc``' cannot be used to make a *no-op cast*. The second operand
is the vector mask. The return type, the value to cast, and the vector mask have
the same number of elements. The third operand is the explicit vector length of
the operation.
Semantics:
""""""""""
The '``llvm.vp.fptrunc``' intrinsic casts a ``value`` from a larger
:ref:`floating-point <t_floating>` type to a smaller :ref:`floating-point
<t_floating>` type.
This instruction is assumed to execute in the default :ref:`floating-point
environment <floatenv>`. The conversion is performed on lane positions below the
explicit vector length and where the vector mask is true. Masked-off lanes are
``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.fptrunc.v4f32.v4f64(<4 x double> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fptrunc <4 x double> %a to <4 x float>
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_fpext:
'``llvm.vp.fpext.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x double> @llvm.vp.fpext.v16f64.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x double> @llvm.vp.fpext.nxv4f64.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.fpext``' intrinsic extends its first operand to the return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.fpext``' intrinsic takes a value to cast as its first operand.
The return type is the type to cast the value to. Both types must be vector of
:ref:`floating-point <t_floating>` type. The bit size of the value must be
smaller than the bit size of the return type. This implies that
'``llvm.vp.fpext``' cannot be used to make a *no-op cast*. The second operand
is the vector mask. The return type, the value to cast, and the vector mask have
the same number of elements. The third operand is the explicit vector length of
the operation.
Semantics:
""""""""""
The '``llvm.vp.fpext``' intrinsic extends the ``value`` from a smaller
:ref:`floating-point <t_floating>` type to a larger :ref:`floating-point
<t_floating>` type. The '``llvm.vp.fpext``' cannot be used to make a
*no-op cast* because it always changes bits. Use ``bitcast`` to make a
*no-op cast* for a floating-point cast.
The conversion is performed on lane positions below the explicit vector length
and where the vector mask is true. Masked-off lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x double> @llvm.vp.fpext.v4f64.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fpext <4 x float> %a to <4 x double>
%also.r = select <4 x i1> %mask, <4 x double> %t, <4 x double> poison
.. _int_vp_fptoui:
'``llvm.vp.fptoui.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.fptoui.v16i32.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.fptoui.nxv4i32.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.fptoui.v256i64.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.fptoui``' intrinsic converts the :ref:`floating-point
<t_floating>` operand to the unsigned integer return type.
The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.fptoui``' intrinsic takes a value to cast as its first operand.
The value to cast must be a vector of :ref:`floating-point <t_floating>` type.
The return type is the type to cast the value to. The return type must be
vector of :ref:`integer <t_integer>` type. The second operand is the vector
mask. The return type, the value to cast, and the vector mask have the same
number of elements. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fptoui``' intrinsic converts its :ref:`floating-point
<t_floating>` operand into the nearest (rounding towards zero) unsigned integer
value where the lane position is below the explicit vector length and the
vector mask is true. Masked-off lanes are ``poison``. On enabled lanes where
conversion takes place and the value cannot fit in the return type, the result
on that lane is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.fptoui.v4i32.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fptoui <4 x float> %a to <4 x i32>
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_fptosi:
'``llvm.vp.fptosi.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.fptosi.v16i32.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.fptosi.nxv4i32.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.fptosi.v256i64.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.fptosi``' intrinsic converts the :ref:`floating-point
<t_floating>` operand to the signed integer return type.
The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.fptosi``' intrinsic takes a value to cast as its first operand.
The value to cast must be a vector of :ref:`floating-point <t_floating>` type.
The return type is the type to cast the value to. The return type must be
vector of :ref:`integer <t_integer>` type. The second operand is the vector
mask. The return type, the value to cast, and the vector mask have the same
number of elements. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fptosi``' intrinsic converts its :ref:`floating-point
<t_floating>` operand into the nearest (rounding towards zero) signed integer
value where the lane position is below the explicit vector length and the
vector mask is true. Masked-off lanes are ``poison``. On enabled lanes where
conversion takes place and the value cannot fit in the return type, the result
on that lane is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.fptosi.v4i32.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fptosi <4 x float> %a to <4 x i32>
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_uitofp:
'``llvm.vp.uitofp.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.uitofp.v16f32.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.uitofp.nxv4f32.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.uitofp.v256f64.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.uitofp``' intrinsic converts its unsigned integer operand to the
:ref:`floating-point <t_floating>` return type. The operation has a mask and
an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.uitofp``' intrinsic takes a value to cast as its first operand.
The value to cast must be vector of :ref:`integer <t_integer>` type. The
return type is the type to cast the value to. The return type must be a vector
of :ref:`floating-point <t_floating>` type. The second operand is the vector
mask. The return type, the value to cast, and the vector mask have the same
number of elements. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.uitofp``' intrinsic interprets its first operand as an unsigned
integer quantity and converts it to the corresponding floating-point value. If
the value cannot be exactly represented, it is rounded using the default
rounding mode. The conversion is performed on lane positions below the
explicit vector length and where the vector mask is true. Masked-off lanes are
``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.uitofp.v4f32.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = uitofp <4 x i32> %a to <4 x float>
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_sitofp:
'``llvm.vp.sitofp.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.sitofp.v16f32.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.sitofp.nxv4f32.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.sitofp.v256f64.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.sitofp``' intrinsic converts its signed integer operand to the
:ref:`floating-point <t_floating>` return type. The operation has a mask and
an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.sitofp``' intrinsic takes a value to cast as its first operand.
The value to cast must be vector of :ref:`integer <t_integer>` type. The
return type is the type to cast the value to. The return type must be a vector
of :ref:`floating-point <t_floating>` type. The second operand is the vector
mask. The return type, the value to cast, and the vector mask have the same
number of elements. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.sitofp``' intrinsic interprets its first operand as a signed
integer quantity and converts it to the corresponding floating-point value. If
the value cannot be exactly represented, it is rounded using the default
rounding mode. The conversion is performed on lane positions below the
explicit vector length and where the vector mask is true. Masked-off lanes are
``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.sitofp.v4f32.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = sitofp <4 x i32> %a to <4 x float>
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_ptrtoint:
'``llvm.vp.ptrtoint.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i8> @llvm.vp.ptrtoint.v16i8.v16p0(<16 x ptr> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i8> @llvm.vp.ptrtoint.nxv4i8.nxv4p0(<vscale x 4 x ptr> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.ptrtoint.v16i64.v16p0(<256 x ptr> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.ptrtoint``' intrinsic converts its pointer to the integer return
type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.ptrtoint``' intrinsic takes a value to cast as its first operand
, which must be a vector of pointers, and a type to cast it to return type,
which must be a vector of :ref:`integer <t_integer>` type.
The second operand is the vector mask. The return type, the value to cast, and
the vector mask have the same number of elements.
The third operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.ptrtoint``' intrinsic converts value to return type by
interpreting the pointer value as an integer and either truncating or zero
extending that value to the size of the integer type.
If ``value`` is smaller than return type, then a zero extension is done. If
``value`` is larger than return type, then a truncation is done. If they are
the same size, then nothing is done (*no-op cast*) other than a type
change.
The conversion is performed on lane positions below the explicit vector length
and where the vector mask is true. Masked-off lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i8> @llvm.vp.ptrtoint.v4i8.v4p0i32(<4 x ptr> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = ptrtoint <4 x ptr> %a to <4 x i8>
%also.r = select <4 x i1> %mask, <4 x i8> %t, <4 x i8> poison
.. _int_vp_inttoptr:
'``llvm.vp.inttoptr.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x ptr> @llvm.vp.inttoptr.v16p0.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x ptr> @llvm.vp.inttoptr.nxv4p0.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x ptr> @llvm.vp.inttoptr.v256p0.v256i32 (<256 x i32> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.inttoptr``' intrinsic converts its integer value to the point
return type. The operation has a mask and an explicit vector length parameter.
Arguments:
""""""""""
The '``llvm.vp.inttoptr``' intrinsic takes a value to cast as its first operand
, which must be a vector of :ref:`integer <t_integer>` type, and a type to cast
it to return type, which must be a vector of pointers type.
The second operand is the vector mask. The return type, the value to cast, and
the vector mask have the same number of elements.
The third operand is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.inttoptr``' intrinsic converts ``value`` to return type by
applying either a zero extension or a truncation depending on the size of the
integer ``value``. If ``value`` is larger than the size of a pointer, then a
truncation is done. If ``value`` is smaller than the size of a pointer, then a
zero extension is done. If they are the same size, nothing is done (*no-op cast*).
The conversion is performed on lane positions below the explicit vector length
and where the vector mask is true. Masked-off lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x ptr> @llvm.vp.inttoptr.v4p0i32.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = inttoptr <4 x i32> %a to <4 x ptr>
%also.r = select <4 x i1> %mask, <4 x ptr> %t, <4 x ptr> poison
.. _int_vp_fcmp:
'``llvm.vp.fcmp.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i1> @llvm.vp.fcmp.v16f32(<16 x float> <left_op>, <16 x float> <right_op>, metadata <condition code>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i1> @llvm.vp.fcmp.nxv4f32(<vscale x 4 x float> <left_op>, <vscale x 4 x float> <right_op>, metadata <condition code>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i1> @llvm.vp.fcmp.v256f64(<256 x double> <left_op>, <256 x double> <right_op>, metadata <condition code>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.fcmp``' intrinsic returns a vector of boolean values based on
the comparison of its operands. The operation has a mask and an explicit vector
length parameter.
Arguments:
""""""""""
The '``llvm.vp.fcmp``' intrinsic takes the two values to compare as its first
and second operands. These two values must be vectors of :ref:`floating-point
<t_floating>` types.
The return type is the result of the comparison. The return type must be a
vector of :ref:`i1 <t_integer>` type. The fourth operand is the vector mask.
The return type, the values to compare, and the vector mask have the same
number of elements. The third operand is the condition code indicating the kind
of comparison to perform. It must be a metadata string with :ref:`one of the
supported floating-point condition code values <fcmp_md_cc>`. The fifth operand
is the explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.fcmp``' compares its first two operands according to the
condition code given as the third operand. The operands are compared element by
element on each enabled lane, where the semantics of the comparison are
defined :ref:`according to the condition code <fcmp_md_cc_sem>`. Masked-off
lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i1> @llvm.vp.fcmp.v4f32(<4 x float> %a, <4 x float> %b, metadata !"oeq", <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = fcmp oeq <4 x float> %a, %b
%also.r = select <4 x i1> %mask, <4 x i1> %t, <4 x i1> poison
.. _int_vp_icmp:
'``llvm.vp.icmp.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <32 x i1> @llvm.vp.icmp.v32i32(<32 x i32> <left_op>, <32 x i32> <right_op>, metadata <condition code>, <32 x i1> <mask>, i32 <vector_length>)
declare <vscale x 2 x i1> @llvm.vp.icmp.nxv2i32(<vscale x 2 x i32> <left_op>, <vscale x 2 x i32> <right_op>, metadata <condition code>, <vscale x 2 x i1> <mask>, i32 <vector_length>)
declare <128 x i1> @llvm.vp.icmp.v128i8(<128 x i8> <left_op>, <128 x i8> <right_op>, metadata <condition code>, <128 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
The '``llvm.vp.icmp``' intrinsic returns a vector of boolean values based on
the comparison of its operands. The operation has a mask and an explicit vector
length parameter.
Arguments:
""""""""""
The '``llvm.vp.icmp``' intrinsic takes the two values to compare as its first
and second operands. These two values must be vectors of :ref:`integer
<t_integer>` types.
The return type is the result of the comparison. The return type must be a
vector of :ref:`i1 <t_integer>` type. The fourth operand is the vector mask.
The return type, the values to compare, and the vector mask have the same
number of elements. The third operand is the condition code indicating the kind
of comparison to perform. It must be a metadata string with :ref:`one of the
supported integer condition code values <icmp_md_cc>`. The fifth operand is the
explicit vector length of the operation.
Semantics:
""""""""""
The '``llvm.vp.icmp``' compares its first two operands according to the
condition code given as the third operand. The operands are compared element by
element on each enabled lane, where the semantics of the comparison are
defined :ref:`according to the condition code <icmp_md_cc_sem>`. Masked-off
lanes are ``poison``.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i1> @llvm.vp.icmp.v4i32(<4 x i32> %a, <4 x i32> %b, metadata !"ne", <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = icmp ne <4 x i32> %a, %b
%also.r = select <4 x i1> %mask, <4 x i1> %t, <4 x i1> poison
.. _int_vp_ceil:
'``llvm.vp.ceil.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.ceil.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.ceil.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.ceil.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point ceiling of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.ceil``' intrinsic performs floating-point ceiling
(:ref:`ceil <int_ceil>`) of the first vector operand on each enabled lane. The
result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.ceil.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.ceil.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_floor:
'``llvm.vp.floor.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.floor.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.floor.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.floor.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point floor of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.floor``' intrinsic performs floating-point floor
(:ref:`floor <int_floor>`) of the first vector operand on each enabled lane.
The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.floor.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.floor.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_rint:
'``llvm.vp.rint.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.rint.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.rint.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.rint.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point rint of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.rint``' intrinsic performs floating-point rint
(:ref:`rint <int_rint>`) of the first vector operand on each enabled lane.
The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.rint.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.rint.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_nearbyint:
'``llvm.vp.nearbyint.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.nearbyint.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.nearbyint.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.nearbyint.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point nearbyint of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.nearbyint``' intrinsic performs floating-point nearbyint
(:ref:`nearbyint <int_nearbyint>`) of the first vector operand on each enabled lane.
The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.nearbyint.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_round:
'``llvm.vp.round.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.round.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.round.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.round.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point round of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.round``' intrinsic performs floating-point round
(:ref:`round <int_round>`) of the first vector operand on each enabled lane.
The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.round.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.round.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_roundeven:
'``llvm.vp.roundeven.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.roundeven.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.roundeven.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.roundeven.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point roundeven of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.roundeven``' intrinsic performs floating-point roundeven
(:ref:`roundeven <int_roundeven>`) of the first vector operand on each enabled
lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.roundeven.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.roundeven.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_roundtozero:
'``llvm.vp.roundtozero.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x float> @llvm.vp.roundtozero.v16f32 (<16 x float> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x float> @llvm.vp.roundtozero.nxv4f32 (<vscale x 4 x float> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x double> @llvm.vp.roundtozero.v256f64 (<256 x double> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated floating-point round-to-zero of a vector of floating-point values.
Arguments:
""""""""""
The first operand and the result have the same vector of floating-point type.
The second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.roundtozero``' intrinsic performs floating-point roundeven
(:ref:`llvm.trunc <int_llvm_trunc>`) of the first vector operand on each enabled lane. The
result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x float> @llvm.vp.roundtozero.v4f32(<4 x float> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x float> @llvm.trunc.v4f32(<4 x float> %a)
%also.r = select <4 x i1> %mask, <4 x float> %t, <4 x float> poison
.. _int_vp_bitreverse:
'``llvm.vp.bitreverse.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.bitreverse.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.bitreverse.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.bitreverse.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated bitreverse of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.bitreverse``' intrinsic performs bitreverse (:ref:`bitreverse <int_bitreverse>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.bitreverse.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> %a)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_bswap:
'``llvm.vp.bswap.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.bswap.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.bswap.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.bswap.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated bswap of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.bswap``' intrinsic performs bswap (:ref:`bswap <int_bswap>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.bswap.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.bswap.v4i32(<4 x i32> %a)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_ctpop:
'``llvm.vp.ctpop.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.ctpop.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.ctpop.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.ctpop.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated ctpop of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.ctpop``' intrinsic performs ctpop (:ref:`ctpop <int_ctpop>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.ctpop.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %a)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_ctlz:
'``llvm.vp.ctlz.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.ctlz.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
declare <vscale x 4 x i32> @llvm.vp.ctlz.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
declare <256 x i64> @llvm.vp.ctlz.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
Overview:
"""""""""
Predicated ctlz of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.ctlz``' intrinsic performs ctlz (:ref:`ctlz <int_ctlz>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.ctlz.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl, i1 false)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.ctlz.v4i32(<4 x i32> %a, i1 false)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_cttz:
'``llvm.vp.cttz.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.cttz.v16i32 (<16 x i32> <op>, <16 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
declare <vscale x 4 x i32> @llvm.vp.cttz.nxv4i32 (<vscale x 4 x i32> <op>, <vscale x 4 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
declare <256 x i64> @llvm.vp.cttz.v256i64 (<256 x i64> <op>, <256 x i1> <mask>, i32 <vector_length>, i1 <is_zero_poison>)
Overview:
"""""""""
Predicated cttz of a vector of integers.
Arguments:
""""""""""
The first operand and the result have the same vector of integer type. The
second operand is the vector mask and has the same number of elements as the
result vector type. The third operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.cttz``' intrinsic performs cttz (:ref:`cttz <int_cttz>`) of the first operand on each
enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.cttz.v4i32(<4 x i32> %a, <4 x i1> %mask, i32 %evl, i1 false)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.cttz.v4i32(<4 x i32> %a, i1 false)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
.. _int_vp_fshl:
'``llvm.vp.fshl.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.fshl.v16i32 (<16 x i32> <left_op>, <16 x i32> <middle_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.fshl.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <middle_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.fshl.v256i64 (<256 x i64> <left_op>, <256 x i64> <middle_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated fshl of three vectors of integers.
Arguments:
""""""""""
The first three operand and the result have the same vector of integer type. The
fourth operand is the vector mask and has the same number of elements as the
result vector type. The fifth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fshl``' intrinsic performs fshl (:ref:`fshl <int_fshl>`) of the first, second, and third
vector operand on each enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
'``llvm.vp.fshr.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <16 x i32> @llvm.vp.fshr.v16i32 (<16 x i32> <left_op>, <16 x i32> <middle_op>, <16 x i32> <right_op>, <16 x i1> <mask>, i32 <vector_length>)
declare <vscale x 4 x i32> @llvm.vp.fshr.nxv4i32 (<vscale x 4 x i32> <left_op>, <vscale x 4 x i32> <middle_op>, <vscale x 4 x i32> <right_op>, <vscale x 4 x i1> <mask>, i32 <vector_length>)
declare <256 x i64> @llvm.vp.fshr.v256i64 (<256 x i64> <left_op>, <256 x i64> <middle_op>, <256 x i64> <right_op>, <256 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated fshr of three vectors of integers.
Arguments:
""""""""""
The first three operand and the result have the same vector of integer type. The
fourth operand is the vector mask and has the same number of elements as the
result vector type. The fifth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.fshr``' intrinsic performs fshr (:ref:`fshr <int_fshr>`) of the first, second, and third
vector operand on each enabled lane. The result on disabled lanes is a :ref:`poison value <poisonvalues>`.
Examples:
"""""""""
.. code-block:: llvm
%r = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c, <4 x i1> %mask, i32 %evl)
;; For all lanes below %evl, %r is lane-wise equivalent to %also.r
%t = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c)
%also.r = select <4 x i1> %mask, <4 x i32> %t, <4 x i32> poison
'``llvm.vp.is.fpclass.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic.
::
declare <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f32(<vscale x 2 x float> <op>, i32 <test>, <vscale x 2 x i1> <mask>, i32 <vector_length>)
declare <2 x i1> @llvm.vp.is.fpclass.v2f16(<2 x half> <op>, i32 <test>, <2 x i1> <mask>, i32 <vector_length>)
Overview:
"""""""""
Predicated llvm.is.fpclass :ref:`llvm.is.fpclass <llvm.is.fpclass>`
Arguments:
""""""""""
The first operand is a floating-point vector, the result type is a vector of
boolean with the same number of elements as the first argument. The second
operand specifies, which tests to perform :ref:`llvm.is.fpclass <llvm.is.fpclass>`.
The third operand is the vector mask and has the same number of elements as the
result vector type. The fourth operand is the explicit vector length of the
operation.
Semantics:
""""""""""
The '``llvm.vp.is.fpclass``' intrinsic performs llvm.is.fpclass (:ref:`llvm.is.fpclass <llvm.is.fpclass>`).
Examples:
"""""""""
.. code-block:: llvm
%r = call <2 x i1> @llvm.vp.is.fpclass.v2f16(<2 x half> %x, i32 3, <2 x i1> %m, i32 %evl)
%t = call <vscale x 2 x i1> @llvm.vp.is.fpclass.nxv2f16(<vscale x 2 x half> %x, i32 3, <vscale x 2 x i1> %m, i32 %evl)
.. _int_mload_mstore:
Masked Vector Load and Store Intrinsics
---------------------------------------
LLVM provides intrinsics for predicated vector load and store operations. The predicate is specified by a mask operand, which holds one bit per vector element, switching the associated vector lane on or off. The memory addresses corresponding to the "off" lanes are not accessed. When all bits of the mask are on, the intrinsic is identical to a regular vector load or store. When all bits are off, no memory is accessed.
.. _int_mload:
'``llvm.masked.load.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The loaded data is a vector of any integer, floating-point or pointer data type.
::
declare <16 x float> @llvm.masked.load.v16f32.p0(ptr <ptr>, i32 <alignment>, <16 x i1> <mask>, <16 x float> <passthru>)
declare <2 x double> @llvm.masked.load.v2f64.p0(ptr <ptr>, i32 <alignment>, <2 x i1> <mask>, <2 x double> <passthru>)
;; The data is a vector of pointers
declare <8 x ptr> @llvm.masked.load.v8p0.p0(ptr <ptr>, i32 <alignment>, <8 x i1> <mask>, <8 x ptr> <passthru>)
Overview:
"""""""""
Reads a vector from memory according to the provided mask. The mask holds a bit for each vector lane, and is used to prevent memory accesses to the masked-off lanes. The masked-off lanes in the result vector are taken from the corresponding lanes of the '``passthru``' operand.
Arguments:
""""""""""
The first operand is the base pointer for the load. The second operand is the alignment of the source location. It must be a power of two constant integer value. The third operand, mask, is a vector of boolean values with the same number of elements as the return type. The fourth is a pass-through value that is used to fill the masked-off lanes of the result. The return type, underlying type of the base pointer and the type of the '``passthru``' operand are the same vector types.
Semantics:
""""""""""
The '``llvm.masked.load``' intrinsic is designed for conditional reading of selected vector elements in a single IR operation. It is useful for targets that support vector masked loads and allows vectorizing predicated basic blocks on these targets. Other targets may support this intrinsic differently, for example by lowering it into a sequence of branches that guard scalar load operations.
The result of this operation is equivalent to a regular vector load instruction followed by a 'select' between the loaded and the passthru values, predicated on the same mask. However, using this intrinsic prevents exceptions on memory access to masked-off lanes.
::
%res = call <16 x float> @llvm.masked.load.v16f32.p0(ptr %ptr, i32 4, <16 x i1>%mask, <16 x float> %passthru)
;; The result of the two following instructions is identical aside from potential memory access exception
%loadlal = load <16 x float>, ptr %ptr, align 4
%res = select <16 x i1> %mask, <16 x float> %loadlal, <16 x float> %passthru
.. _int_mstore:
'``llvm.masked.store.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The data stored in memory is a vector of any integer, floating-point or pointer data type.
::
declare void @llvm.masked.store.v8i32.p0 (<8 x i32> <value>, ptr <ptr>, i32 <alignment>, <8 x i1> <mask>)
declare void @llvm.masked.store.v16f32.p0(<16 x float> <value>, ptr <ptr>, i32 <alignment>, <16 x i1> <mask>)
;; The data is a vector of pointers
declare void @llvm.masked.store.v8p0.p0 (<8 x ptr> <value>, ptr <ptr>, i32 <alignment>, <8 x i1> <mask>)
Overview:
"""""""""
Writes a vector to memory according to the provided mask. The mask holds a bit for each vector lane, and is used to prevent memory accesses to the masked-off lanes.
Arguments:
""""""""""
The first operand is the vector value to be written to memory. The second operand is the base pointer for the store, it has the same underlying type as the value operand. The third operand is the alignment of the destination location. It must be a power of two constant integer value. The fourth operand, mask, is a vector of boolean values. The types of the mask and the value operand must have the same number of vector elements.
Semantics:
""""""""""
The '``llvm.masked.store``' intrinsics is designed for conditional writing of selected vector elements in a single IR operation. It is useful for targets that support vector masked store and allows vectorizing predicated basic blocks on these targets. Other targets may support this intrinsic differently, for example by lowering it into a sequence of branches that guard scalar store operations.
The result of this operation is equivalent to a load-modify-store sequence. However, using this intrinsic prevents exceptions and data races on memory access to masked-off lanes.
::
call void @llvm.masked.store.v16f32.p0(<16 x float> %value, ptr %ptr, i32 4, <16 x i1> %mask)
;; The result of the following instructions is identical aside from potential data races and memory access exceptions
%oldval = load <16 x float>, ptr %ptr, align 4
%res = select <16 x i1> %mask, <16 x float> %value, <16 x float> %oldval
store <16 x float> %res, ptr %ptr, align 4
Masked Vector Gather and Scatter Intrinsics
-------------------------------------------
LLVM provides intrinsics for vector gather and scatter operations. They are similar to :ref:`Masked Vector Load and Store <int_mload_mstore>`, except they are designed for arbitrary memory accesses, rather than sequential memory accesses. Gather and scatter also employ a mask operand, which holds one bit per vector element, switching the associated vector lane on or off. The memory addresses corresponding to the "off" lanes are not accessed. When all bits are off, no memory is accessed.
.. _int_mgather:
'``llvm.masked.gather.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The loaded data are multiple scalar values of any integer, floating-point or pointer data type gathered together into one vector.
::
declare <16 x float> @llvm.masked.gather.v16f32.v16p0(<16 x ptr> <ptrs>, i32 <alignment>, <16 x i1> <mask>, <16 x float> <passthru>)
declare <2 x double> @llvm.masked.gather.v2f64.v2p1(<2 x ptr addrspace(1)> <ptrs>, i32 <alignment>, <2 x i1> <mask>, <2 x double> <passthru>)
declare <8 x ptr> @llvm.masked.gather.v8p0.v8p0(<8 x ptr> <ptrs>, i32 <alignment>, <8 x i1> <mask>, <8 x ptr> <passthru>)
Overview:
"""""""""
Reads scalar values from arbitrary memory locations and gathers them into one vector. The memory locations are provided in the vector of pointers '``ptrs``'. The memory is accessed according to the provided mask. The mask holds a bit for each vector lane, and is used to prevent memory accesses to the masked-off lanes. The masked-off lanes in the result vector are taken from the corresponding lanes of the '``passthru``' operand.
Arguments:
""""""""""
The first operand is a vector of pointers which holds all memory addresses to read. The second operand is an alignment of the source addresses. It must be 0 or a power of two constant integer value. The third operand, mask, is a vector of boolean values with the same number of elements as the return type. The fourth is a pass-through value that is used to fill the masked-off lanes of the result. The return type, underlying type of the vector of pointers and the type of the '``passthru``' operand are the same vector types.
Semantics:
""""""""""
The '``llvm.masked.gather``' intrinsic is designed for conditional reading of multiple scalar values from arbitrary memory locations in a single IR operation. It is useful for targets that support vector masked gathers and allows vectorizing basic blocks with data and control divergence. Other targets may support this intrinsic differently, for example by lowering it into a sequence of scalar load operations.
The semantics of this operation are equivalent to a sequence of conditional scalar loads with subsequent gathering all loaded values into a single vector. The mask restricts memory access to certain lanes and facilitates vectorization of predicated basic blocks.
::
%res = call <4 x double> @llvm.masked.gather.v4f64.v4p0(<4 x ptr> %ptrs, i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x double> poison)
;; The gather with all-true mask is equivalent to the following instruction sequence
%ptr0 = extractelement <4 x ptr> %ptrs, i32 0
%ptr1 = extractelement <4 x ptr> %ptrs, i32 1
%ptr2 = extractelement <4 x ptr> %ptrs, i32 2
%ptr3 = extractelement <4 x ptr> %ptrs, i32 3
%val0 = load double, ptr %ptr0, align 8
%val1 = load double, ptr %ptr1, align 8
%val2 = load double, ptr %ptr2, align 8
%val3 = load double, ptr %ptr3, align 8
%vec0 = insertelement <4 x double> poison, %val0, 0
%vec01 = insertelement <4 x double> %vec0, %val1, 1
%vec012 = insertelement <4 x double> %vec01, %val2, 2
%vec0123 = insertelement <4 x double> %vec012, %val3, 3
.. _int_mscatter:
'``llvm.masked.scatter.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The data stored in memory is a vector of any integer, floating-point or pointer data type. Each vector element is stored in an arbitrary memory address. Scatter with overlapping addresses is guaranteed to be ordered from least-significant to most-significant element.
::
declare void @llvm.masked.scatter.v8i32.v8p0 (<8 x i32> <value>, <8 x ptr> <ptrs>, i32 <alignment>, <8 x i1> <mask>)
declare void @llvm.masked.scatter.v16f32.v16p1(<16 x float> <value>, <16 x ptr addrspace(1)> <ptrs>, i32 <alignment>, <16 x i1> <mask>)
declare void @llvm.masked.scatter.v4p0.v4p0 (<4 x ptr> <value>, <4 x ptr> <ptrs>, i32 <alignment>, <4 x i1> <mask>)
Overview:
"""""""""
Writes each element from the value vector to the corresponding memory address. The memory addresses are represented as a vector of pointers. Writing is done according to the provided mask. The mask holds a bit for each vector lane, and is used to prevent memory accesses to the masked-off lanes.
Arguments:
""""""""""
The first operand is a vector value to be written to memory. The second operand is a vector of pointers, pointing to where the value elements should be stored. It has the same underlying type as the value operand. The third operand is an alignment of the destination addresses. It must be 0 or a power of two constant integer value. The fourth operand, mask, is a vector of boolean values. The types of the mask and the value operand must have the same number of vector elements.
Semantics:
""""""""""
The '``llvm.masked.scatter``' intrinsics is designed for writing selected vector elements to arbitrary memory addresses in a single IR operation. The operation may be conditional, when not all bits in the mask are switched on. It is useful for targets that support vector masked scatter and allows vectorizing basic blocks with data and control divergence. Other targets may support this intrinsic differently, for example by lowering it into a sequence of branches that guard scalar store operations.
::
;; This instruction unconditionally stores data vector in multiple addresses
call @llvm.masked.scatter.v8i32.v8p0(<8 x i32> %value, <8 x ptr> %ptrs, i32 4, <8 x i1> <true, true, .. true>)
;; It is equivalent to a list of scalar stores
%val0 = extractelement <8 x i32> %value, i32 0
%val1 = extractelement <8 x i32> %value, i32 1
..
%val7 = extractelement <8 x i32> %value, i32 7
%ptr0 = extractelement <8 x ptr> %ptrs, i32 0
%ptr1 = extractelement <8 x ptr> %ptrs, i32 1
..
%ptr7 = extractelement <8 x ptr> %ptrs, i32 7
;; Note: the order of the following stores is important when they overlap:
store i32 %val0, ptr %ptr0, align 4
store i32 %val1, ptr %ptr1, align 4
..
store i32 %val7, ptr %ptr7, align 4
Masked Vector Expanding Load and Compressing Store Intrinsics
-------------------------------------------------------------
LLVM provides intrinsics for expanding load and compressing store operations. Data selected from a vector according to a mask is stored in consecutive memory addresses (compressed store), and vice-versa (expanding load). These operations effective map to "if (cond.i) a[j++] = v.i" and "if (cond.i) v.i = a[j++]" patterns, respectively. Note that when the mask starts with '1' bits followed by '0' bits, these operations are identical to :ref:`llvm.masked.store <int_mstore>` and :ref:`llvm.masked.load <int_mload>`.
.. _int_expandload:
'``llvm.masked.expandload.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. Several values of integer, floating point or pointer data type are loaded from consecutive memory addresses and stored into the elements of a vector according to the mask.
::
declare <16 x float> @llvm.masked.expandload.v16f32 (ptr <ptr>, <16 x i1> <mask>, <16 x float> <passthru>)
declare <2 x i64> @llvm.masked.expandload.v2i64 (ptr <ptr>, <2 x i1> <mask>, <2 x i64> <passthru>)
Overview:
"""""""""
Reads a number of scalar values sequentially from memory location provided in '``ptr``' and spreads them in a vector. The '``mask``' holds a bit for each vector lane. The number of elements read from memory is equal to the number of '1' bits in the mask. The loaded elements are positioned in the destination vector according to the sequence of '1' and '0' bits in the mask. E.g., if the mask vector is '10010001', "expandload" reads 3 values from memory addresses ptr, ptr+1, ptr+2 and places them in lanes 0, 3 and 7 accordingly. The masked-off lanes are filled by elements from the corresponding lanes of the '``passthru``' operand.
Arguments:
""""""""""
The first operand is the base pointer for the load. It has the same underlying type as the element of the returned vector. The second operand, mask, is a vector of boolean values with the same number of elements as the return type. The third is a pass-through value that is used to fill the masked-off lanes of the result. The return type and the type of the '``passthru``' operand have the same vector type.
Semantics:
""""""""""
The '``llvm.masked.expandload``' intrinsic is designed for reading multiple scalar values from adjacent memory addresses into possibly non-adjacent vector lanes. It is useful for targets that support vector expanding loads and allows vectorizing loop with cross-iteration dependency like in the following example:
.. code-block:: c
// In this loop we load from B and spread the elements into array A.
double *A, B; int *C;
for (int i = 0; i < size; ++i) {
if (C[i] != 0)
A[i] = B[j++];
}
.. code-block:: llvm
; Load several elements from array B and expand them in a vector.
; The number of loaded elements is equal to the number of '1' elements in the Mask.
%Tmp = call <8 x double> @llvm.masked.expandload.v8f64(ptr %Bptr, <8 x i1> %Mask, <8 x double> poison)
; Store the result in A
call void @llvm.masked.store.v8f64.p0(<8 x double> %Tmp, ptr %Aptr, i32 8, <8 x i1> %Mask)
; %Bptr should be increased on each iteration according to the number of '1' elements in the Mask.
%MaskI = bitcast <8 x i1> %Mask to i8
%MaskIPopcnt = call i8 @llvm.ctpop.i8(i8 %MaskI)
%MaskI64 = zext i8 %MaskIPopcnt to i64
%BNextInd = add i64 %BInd, %MaskI64
Other targets may support this intrinsic differently, for example, by lowering it into a sequence of conditional scalar load operations and shuffles.
If all mask elements are '1', the intrinsic behavior is equivalent to the regular unmasked vector load.
.. _int_compressstore:
'``llvm.masked.compressstore.*``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. A number of scalar values of integer, floating point or pointer data type are collected from an input vector and stored into adjacent memory addresses. A mask defines which elements to collect from the vector.
::
declare void @llvm.masked.compressstore.v8i32 (<8 x i32> <value>, ptr <ptr>, <8 x i1> <mask>)
declare void @llvm.masked.compressstore.v16f32 (<16 x float> <value>, ptr <ptr>, <16 x i1> <mask>)
Overview:
"""""""""
Selects elements from input vector '``value``' according to the '``mask``'. All selected elements are written into adjacent memory addresses starting at address '`ptr`', from lower to higher. The mask holds a bit for each vector lane, and is used to select elements to be stored. The number of elements to be stored is equal to the number of active bits in the mask.
Arguments:
""""""""""
The first operand is the input vector, from which elements are collected and written to memory. The second operand is the base pointer for the store, it has the same underlying type as the element of the input vector operand. The third operand is the mask, a vector of boolean values. The mask and the input vector must have the same number of vector elements.
Semantics:
""""""""""
The '``llvm.masked.compressstore``' intrinsic is designed for compressing data in memory. It allows to collect elements from possibly non-adjacent lanes of a vector and store them contiguously in memory in one IR operation. It is useful for targets that support compressing store operations and allows vectorizing loops with cross-iteration dependences like in the following example:
.. code-block:: c
// In this loop we load elements from A and store them consecutively in B
double *A, B; int *C;
for (int i = 0; i < size; ++i) {
if (C[i] != 0)
B[j++] = A[i]
}
.. code-block:: llvm
; Load elements from A.
%Tmp = call <8 x double> @llvm.masked.load.v8f64.p0(ptr %Aptr, i32 8, <8 x i1> %Mask, <8 x double> poison)
; Store all selected elements consecutively in array B
call <void> @llvm.masked.compressstore.v8f64(<8 x double> %Tmp, ptr %Bptr, <8 x i1> %Mask)
; %Bptr should be increased on each iteration according to the number of '1' elements in the Mask.
%MaskI = bitcast <8 x i1> %Mask to i8
%MaskIPopcnt = call i8 @llvm.ctpop.i8(i8 %MaskI)
%MaskI64 = zext i8 %MaskIPopcnt to i64
%BNextInd = add i64 %BInd, %MaskI64
Other targets may support this intrinsic differently, for example, by lowering it into a sequence of branches that guard scalar store operations.
Memory Use Markers
------------------
This class of intrinsics provides information about the
:ref:`lifetime of memory objects <objectlifetime>` and ranges where variables
are immutable.
.. _int_lifestart:
'``llvm.lifetime.start``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.lifetime.start(i64 <size>, ptr nocapture <ptr>)
Overview:
"""""""""
The '``llvm.lifetime.start``' intrinsic specifies the start of a memory
object's lifetime.
Arguments:
""""""""""
The first argument is a constant integer representing the size of the
object, or -1 if it is variable sized. The second argument is a pointer
to the object.
Semantics:
""""""""""
If ``ptr`` is a stack-allocated object and it points to the first byte of
the object, the object is initially marked as dead.
``ptr`` is conservatively considered as a non-stack-allocated object if
the stack coloring algorithm that is used in the optimization pipeline cannot
conclude that ``ptr`` is a stack-allocated object.
After '``llvm.lifetime.start``', the stack object that ``ptr`` points is marked
as alive and has an uninitialized value.
The stack object is marked as dead when either
:ref:`llvm.lifetime.end <int_lifeend>` to the alloca is executed or the
function returns.
After :ref:`llvm.lifetime.end <int_lifeend>` is called,
'``llvm.lifetime.start``' on the stack object can be called again.
The second '``llvm.lifetime.start``' call marks the object as alive, but it
does not change the address of the object.
If ``ptr`` is a non-stack-allocated object, it does not point to the first
byte of the object or it is a stack object that is already alive, it simply
fills all bytes of the object with ``poison``.
.. _int_lifeend:
'``llvm.lifetime.end``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.lifetime.end(i64 <size>, ptr nocapture <ptr>)
Overview:
"""""""""
The '``llvm.lifetime.end``' intrinsic specifies the end of a memory object's
lifetime.
Arguments:
""""""""""
The first argument is a constant integer representing the size of the
object, or -1 if it is variable sized. The second argument is a pointer
to the object.
Semantics:
""""""""""
If ``ptr`` is a stack-allocated object and it points to the first byte of the
object, the object is dead.
``ptr`` is conservatively considered as a non-stack-allocated object if
the stack coloring algorithm that is used in the optimization pipeline cannot
conclude that ``ptr`` is a stack-allocated object.
Calling ``llvm.lifetime.end`` on an already dead alloca is no-op.
If ``ptr`` is a non-stack-allocated object or it does not point to the first
byte of the object, it is equivalent to simply filling all bytes of the object
with ``poison``.
'``llvm.invariant.start``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The memory object can belong to any address space.
::
declare ptr @llvm.invariant.start.p0(i64 <size>, ptr nocapture <ptr>)
Overview:
"""""""""
The '``llvm.invariant.start``' intrinsic specifies that the contents of
a memory object will not change.
Arguments:
""""""""""
The first argument is a constant integer representing the size of the
object, or -1 if it is variable sized. The second argument is a pointer
to the object.
Semantics:
""""""""""
This intrinsic indicates that until an ``llvm.invariant.end`` that uses
the return value, the referenced memory location is constant and
unchanging.
'``llvm.invariant.end``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The memory object can belong to any address space.
::
declare void @llvm.invariant.end.p0(ptr <start>, i64 <size>, ptr nocapture <ptr>)
Overview:
"""""""""
The '``llvm.invariant.end``' intrinsic specifies that the contents of a
memory object are mutable.
Arguments:
""""""""""
The first argument is the matching ``llvm.invariant.start`` intrinsic.
The second argument is a constant integer representing the size of the
object, or -1 if it is variable sized and the third argument is a
pointer to the object.
Semantics:
""""""""""
This intrinsic indicates that the memory is mutable again.
'``llvm.launder.invariant.group``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The memory object can belong to any address
space. The returned pointer must belong to the same address space as the
argument.
::
declare ptr @llvm.launder.invariant.group.p0(ptr <ptr>)
Overview:
"""""""""
The '``llvm.launder.invariant.group``' intrinsic can be used when an invariant
established by ``invariant.group`` metadata no longer holds, to obtain a new
pointer value that carries fresh invariant group information. It is an
experimental intrinsic, which means that its semantics might change in the
future.
Arguments:
""""""""""
The ``llvm.launder.invariant.group`` takes only one argument, which is a pointer
to the memory.
Semantics:
""""""""""
Returns another pointer that aliases its argument but which is considered different
for the purposes of ``load``/``store`` ``invariant.group`` metadata.
It does not read any accessible memory and the execution can be speculated.
'``llvm.strip.invariant.group``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. The memory object can belong to any address
space. The returned pointer must belong to the same address space as the
argument.
::
declare ptr @llvm.strip.invariant.group.p0(ptr <ptr>)
Overview:
"""""""""
The '``llvm.strip.invariant.group``' intrinsic can be used when an invariant
established by ``invariant.group`` metadata no longer holds, to obtain a new pointer
value that does not carry the invariant information. It is an experimental
intrinsic, which means that its semantics might change in the future.
Arguments:
""""""""""
The ``llvm.strip.invariant.group`` takes only one argument, which is a pointer
to the memory.
Semantics:
""""""""""
Returns another pointer that aliases its argument but which has no associated
``invariant.group`` metadata.
It does not read any memory and can be speculated.
.. _constrainedfp:
Constrained Floating-Point Intrinsics
-------------------------------------
These intrinsics are used to provide special handling of floating-point
operations when specific rounding mode or floating-point exception behavior is
required. By default, LLVM optimization passes assume that the rounding mode is
round-to-nearest and that floating-point exceptions will not be monitored.
Constrained FP intrinsics are used to support non-default rounding modes and
accurately preserve exception behavior without compromising LLVM's ability to
optimize FP code when the default behavior is used.
If any FP operation in a function is constrained then they all must be
constrained. This is required for correct LLVM IR. Optimizations that
move code around can create miscompiles if mixing of constrained and normal
operations is done. The correct way to mix constrained and less constrained
operations is to use the rounding mode and exception handling metadata to
mark constrained intrinsics as having LLVM's default behavior.
Each of these intrinsics corresponds to a normal floating-point operation. The
data arguments and the return value are the same as the corresponding FP
operation.
The rounding mode argument is a metadata string specifying what
assumptions, if any, the optimizer can make when transforming constant
values. Some constrained FP intrinsics omit this argument. If required
by the intrinsic, this argument must be one of the following strings:
::
"round.dynamic"
"round.tonearest"
"round.downward"
"round.upward"
"round.towardzero"
"round.tonearestaway"
If this argument is "round.dynamic" optimization passes must assume that the
rounding mode is unknown and may change at runtime. No transformations that
depend on rounding mode may be performed in this case.
The other possible values for the rounding mode argument correspond to the
similarly named IEEE rounding modes. If the argument is any of these values
optimization passes may perform transformations as long as they are consistent
with the specified rounding mode.
For example, 'x-0'->'x' is not a valid transformation if the rounding mode is
"round.downward" or "round.dynamic" because if the value of 'x' is +0 then
'x-0' should evaluate to '-0' when rounding downward. However, this
transformation is legal for all other rounding modes.
For values other than "round.dynamic" optimization passes may assume that the
actual runtime rounding mode (as defined in a target-specific manner) matches
the specified rounding mode, but this is not guaranteed. Using a specific
non-dynamic rounding mode which does not match the actual rounding mode at
runtime results in undefined behavior.
The exception behavior argument is a metadata string describing the floating
point exception semantics that required for the intrinsic. This argument
must be one of the following strings:
::
"fpexcept.ignore"
"fpexcept.maytrap"
"fpexcept.strict"
If this argument is "fpexcept.ignore" optimization passes may assume that the
exception status flags will not be read and that floating-point exceptions will
be masked. This allows transformations to be performed that may change the
exception semantics of the original code. For example, FP operations may be
speculatively executed in this case whereas they must not be for either of the
other possible values of this argument.
If the exception behavior argument is "fpexcept.maytrap" optimization passes
must avoid transformations that may raise exceptions that would not have been
raised by the original code (such as speculatively executing FP operations), but
passes are not required to preserve all exceptions that are implied by the
original code. For example, exceptions may be potentially hidden by constant
folding.
If the exception behavior argument is "fpexcept.strict" all transformations must
strictly preserve the floating-point exception semantics of the original code.
Any FP exception that would have been raised by the original code must be raised
by the transformed code, and the transformed code must not raise any FP
exceptions that would not have been raised by the original code. This is the
exception behavior argument that will be used if the code being compiled reads
the FP exception status flags, but this mode can also be used with code that
unmasks FP exceptions.
The number and order of floating-point exceptions is NOT guaranteed. For
example, a series of FP operations that each may raise exceptions may be
vectorized into a single instruction that raises each unique exception a single
time.
Proper :ref:`function attributes <fnattrs>` usage is required for the
constrained intrinsics to function correctly.
All function *calls* done in a function that uses constrained floating
point intrinsics must have the ``strictfp`` attribute either on the
calling instruction or on the declaration or definition of the function
being called.
All function *definitions* that use constrained floating point intrinsics
must have the ``strictfp`` attribute.
'``llvm.experimental.constrained.fadd``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fadd(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fadd``' intrinsic returns the sum of its
two operands.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.fadd``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
The value produced is the floating-point sum of the two value operands and has
the same type as the operands.
'``llvm.experimental.constrained.fsub``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fsub(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fsub``' intrinsic returns the difference
of its two operands.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.fsub``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
The value produced is the floating-point difference of the two value operands
and has the same type as the operands.
'``llvm.experimental.constrained.fmul``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fmul(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fmul``' intrinsic returns the product of
its two operands.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.fmul``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
The value produced is the floating-point product of the two value operands and
has the same type as the operands.
'``llvm.experimental.constrained.fdiv``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fdiv(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fdiv``' intrinsic returns the quotient of
its two operands.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.fdiv``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
The value produced is the floating-point quotient of the two value operands and
has the same type as the operands.
'``llvm.experimental.constrained.frem``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.frem(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.frem``' intrinsic returns the remainder
from the division of its two operands.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.frem``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third and fourth arguments specify the rounding mode and exception
behavior as described above. The rounding mode argument has no effect, since
the result of frem is never rounded, but the argument is included for
consistency with the other constrained floating-point intrinsics.
Semantics:
""""""""""
The value produced is the floating-point remainder from the division of the two
value operands and has the same type as the operands. The remainder has the
same sign as the dividend.
'``llvm.experimental.constrained.fma``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fma(<type> <op1>, <type> <op2>, <type> <op3>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fma``' intrinsic returns the result of a
fused-multiply-add operation on its operands.
Arguments:
""""""""""
The first three arguments to the '``llvm.experimental.constrained.fma``'
intrinsic must be :ref:`floating-point <t_floating>` or :ref:`vector
<t_vector>` of floating-point values. All arguments must have identical types.
The fourth and fifth arguments specify the rounding mode and exception behavior
as described above.
Semantics:
""""""""""
The result produced is the product of the first two operands added to the third
operand computed with infinite precision, and then rounded to the target
precision.
'``llvm.experimental.constrained.fptoui``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.fptoui(<type> <value>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fptoui``' intrinsic converts a
floating-point ``value`` to its unsigned integer equivalent of type ``ty2``.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.fptoui``'
intrinsic must be :ref:`floating point <t_floating>` or :ref:`vector
<t_vector>` of floating point values.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
The result produced is an unsigned integer converted from the floating
point operand. The value is truncated, so it is rounded towards zero.
'``llvm.experimental.constrained.fptosi``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.fptosi(<type> <value>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fptosi``' intrinsic converts
:ref:`floating-point <t_floating>` ``value`` to type ``ty2``.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.fptosi``'
intrinsic must be :ref:`floating point <t_floating>` or :ref:`vector
<t_vector>` of floating point values.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
The result produced is a signed integer converted from the floating
point operand. The value is truncated, so it is rounded towards zero.
'``llvm.experimental.constrained.uitofp``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.uitofp(<type> <value>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.uitofp``' intrinsic converts an
unsigned integer ``value`` to a floating-point of type ``ty2``.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.uitofp``'
intrinsic must be an :ref:`integer <t_integer>` or :ref:`vector
<t_vector>` of integer values.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
An inexact floating-point exception will be raised if rounding is required.
Any result produced is a floating point value converted from the input
integer operand.
'``llvm.experimental.constrained.sitofp``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.sitofp(<type> <value>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.sitofp``' intrinsic converts a
signed integer ``value`` to a floating-point of type ``ty2``.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.sitofp``'
intrinsic must be an :ref:`integer <t_integer>` or :ref:`vector
<t_vector>` of integer values.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
An inexact floating-point exception will be raised if rounding is required.
Any result produced is a floating point value converted from the input
integer operand.
'``llvm.experimental.constrained.fptrunc``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.fptrunc(<type> <value>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fptrunc``' intrinsic truncates ``value``
to type ``ty2``.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.fptrunc``'
intrinsic must be :ref:`floating point <t_floating>` or :ref:`vector
<t_vector>` of floating point values. This argument must be larger in size
than the result.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
The result produced is a floating point value truncated to be smaller in size
than the operand.
'``llvm.experimental.constrained.fpext``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.fpext(<type> <value>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fpext``' intrinsic extends a
floating-point ``value`` to a larger floating-point value.
Arguments:
""""""""""
The first argument to the '``llvm.experimental.constrained.fpext``'
intrinsic must be :ref:`floating point <t_floating>` or :ref:`vector
<t_vector>` of floating point values. This argument must be smaller in size
than the result.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
The result produced is a floating point value extended to be larger in size
than the operand. All restrictions that apply to the fpext instruction also
apply to this intrinsic.
'``llvm.experimental.constrained.fcmp``' and '``llvm.experimental.constrained.fcmps``' Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.experimental.constrained.fcmp(<type> <op1>, <type> <op2>,
metadata <condition code>,
metadata <exception behavior>)
declare <ty2>
@llvm.experimental.constrained.fcmps(<type> <op1>, <type> <op2>,
metadata <condition code>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fcmp``' and
'``llvm.experimental.constrained.fcmps``' intrinsics return a boolean
value or vector of boolean values based on comparison of its operands.
If the operands are floating-point scalars, then the result type is a
boolean (:ref:`i1 <t_integer>`).
If the operands are floating-point vectors, then the result type is a
vector of boolean with the same number of elements as the operands being
compared.
The '``llvm.experimental.constrained.fcmp``' intrinsic performs a quiet
comparison operation while the '``llvm.experimental.constrained.fcmps``'
intrinsic performs a signaling comparison operation.
Arguments:
""""""""""
The first two arguments to the '``llvm.experimental.constrained.fcmp``'
and '``llvm.experimental.constrained.fcmps``' intrinsics must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values. Both arguments must have identical types.
The third argument is the condition code indicating the kind of comparison
to perform. It must be a metadata string with one of the following values:
.. _fcmp_md_cc:
- "``oeq``": ordered and equal
- "``ogt``": ordered and greater than
- "``oge``": ordered and greater than or equal
- "``olt``": ordered and less than
- "``ole``": ordered and less than or equal
- "``one``": ordered and not equal
- "``ord``": ordered (no nans)
- "``ueq``": unordered or equal
- "``ugt``": unordered or greater than
- "``uge``": unordered or greater than or equal
- "``ult``": unordered or less than
- "``ule``": unordered or less than or equal
- "``une``": unordered or not equal
- "``uno``": unordered (either nans)
*Ordered* means that neither operand is a NAN while *unordered* means
that either operand may be a NAN.
The fourth argument specifies the exception behavior as described above.
Semantics:
""""""""""
``op1`` and ``op2`` are compared according to the condition code given
as the third argument. If the operands are vectors, then the
vectors are compared element by element. Each comparison performed
always yields an :ref:`i1 <t_integer>` result, as follows:
.. _fcmp_md_cc_sem:
- "``oeq``": yields ``true`` if both operands are not a NAN and ``op1``
is equal to ``op2``.
- "``ogt``": yields ``true`` if both operands are not a NAN and ``op1``
is greater than ``op2``.
- "``oge``": yields ``true`` if both operands are not a NAN and ``op1``
is greater than or equal to ``op2``.
- "``olt``": yields ``true`` if both operands are not a NAN and ``op1``
is less than ``op2``.
- "``ole``": yields ``true`` if both operands are not a NAN and ``op1``
is less than or equal to ``op2``.
- "``one``": yields ``true`` if both operands are not a NAN and ``op1``
is not equal to ``op2``.
- "``ord``": yields ``true`` if both operands are not a NAN.
- "``ueq``": yields ``true`` if either operand is a NAN or ``op1`` is
equal to ``op2``.
- "``ugt``": yields ``true`` if either operand is a NAN or ``op1`` is
greater than ``op2``.
- "``uge``": yields ``true`` if either operand is a NAN or ``op1`` is
greater than or equal to ``op2``.
- "``ult``": yields ``true`` if either operand is a NAN or ``op1`` is
less than ``op2``.
- "``ule``": yields ``true`` if either operand is a NAN or ``op1`` is
less than or equal to ``op2``.
- "``une``": yields ``true`` if either operand is a NAN or ``op1`` is
not equal to ``op2``.
- "``uno``": yields ``true`` if either operand is a NAN.
The quiet comparison operation performed by
'``llvm.experimental.constrained.fcmp``' will only raise an exception
if either operand is a SNAN. The signaling comparison operation
performed by '``llvm.experimental.constrained.fcmps``' will raise an
exception if either operand is a NAN (QNAN or SNAN). Such an exception
does not preclude a result being produced (e.g. exception might only
set a flag), therefore the distinction between ordered and unordered
comparisons is also relevant for the
'``llvm.experimental.constrained.fcmps``' intrinsic.
'``llvm.experimental.constrained.fmuladd``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.fmuladd(<type> <op1>, <type> <op2>,
<type> <op3>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.fmuladd``' intrinsic represents
multiply-add expressions that can be fused if the code generator determines
that (a) the target instruction set has support for a fused operation,
and (b) that the fused operation is more efficient than the equivalent,
separate pair of mul and add instructions.
Arguments:
""""""""""
The first three arguments to the '``llvm.experimental.constrained.fmuladd``'
intrinsic must be floating-point or vector of floating-point values.
All three arguments must have identical types.
The fourth and fifth arguments specify the rounding mode and exception behavior
as described above.
Semantics:
""""""""""
The expression:
::
%0 = call float @llvm.experimental.constrained.fmuladd.f32(%a, %b, %c,
metadata <rounding mode>,
metadata <exception behavior>)
is equivalent to the expression:
::
%0 = call float @llvm.experimental.constrained.fmul.f32(%a, %b,
metadata <rounding mode>,
metadata <exception behavior>)
%1 = call float @llvm.experimental.constrained.fadd.f32(%0, %c,
metadata <rounding mode>,
metadata <exception behavior>)
except that it is unspecified whether rounding will be performed between the
multiplication and addition steps. Fusion is not guaranteed, even if the target
platform supports it.
If a fused multiply-add is required, the corresponding
:ref:`llvm.experimental.constrained.fma <int_fma>` intrinsic function should be
used instead.
This never sets errno, just as '``llvm.experimental.constrained.fma.*``'.
Constrained libm-equivalent Intrinsics
--------------------------------------
In addition to the basic floating-point operations for which constrained
intrinsics are described above, there are constrained versions of various
operations which provide equivalent behavior to a corresponding libm function.
These intrinsics allow the precise behavior of these operations with respect to
rounding mode and exception behavior to be controlled.
As with the basic constrained floating-point intrinsics, the rounding mode
and exception behavior arguments only control the behavior of the optimizer.
They do not change the runtime floating-point environment.
'``llvm.experimental.constrained.sqrt``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.sqrt(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.sqrt``' intrinsic returns the square root
of the specified value, returning the same value as the libm '``sqrt``'
functions would, but without setting ``errno``.
Arguments:
""""""""""
The first argument and the return type are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the nonnegative square root of the specified value.
If the value is less than negative zero, a floating-point exception occurs
and the return value is architecture specific.
'``llvm.experimental.constrained.pow``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.pow(<type> <op1>, <type> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.pow``' intrinsic returns the first operand
raised to the (positive or negative) power specified by the second operand.
Arguments:
""""""""""
The first two arguments and the return value are floating-point numbers of the
same type. The second argument specifies the power to which the first argument
should be raised.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the first value raised to the second power,
returning the same values as the libm ``pow`` functions would, and
handles error conditions in the same way.
'``llvm.experimental.constrained.powi``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.powi(<type> <op1>, i32 <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.powi``' intrinsic returns the first operand
raised to the (positive or negative) power specified by the second operand. The
order of evaluation of multiplications is not defined. When a vector of
floating-point type is used, the second argument remains a scalar integer value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type. The second argument is a 32-bit signed integer specifying the power to
which the first argument should be raised.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the first value raised to the second power with an
unspecified sequence of rounding operations.
'``llvm.experimental.constrained.ldexp``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type0>
@llvm.experimental.constrained.ldexp(<type0> <op1>, <type1> <op2>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.ldexp``' performs the ldexp function.
Arguments:
""""""""""
The first argument and the return value are :ref:`floating-point
<t_floating>` or :ref:`vector <t_vector>` of floating-point values of
the same type. The second argument is an integer with the same number
of elements.
The third and fourth arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function multiplies the first argument by 2 raised to the second
argument's power. If the first argument is NaN or infinite, the same
value is returned. If the result underflows a zero with the same sign
is returned. If the result overflows, the result is an infinity with
the same sign.
'``llvm.experimental.constrained.sin``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.sin(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.sin``' intrinsic returns the sine of the
first operand.
Arguments:
""""""""""
The first argument and the return type are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the sine of the specified operand, returning the
same values as the libm ``sin`` functions would, and handles error
conditions in the same way.
'``llvm.experimental.constrained.cos``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.cos(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.cos``' intrinsic returns the cosine of the
first operand.
Arguments:
""""""""""
The first argument and the return type are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the cosine of the specified operand, returning the
same values as the libm ``cos`` functions would, and handles error
conditions in the same way.
'``llvm.experimental.constrained.exp``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.exp(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.exp``' intrinsic computes the base-e
exponential of the specified value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``exp`` functions
would, and handles error conditions in the same way.
'``llvm.experimental.constrained.exp2``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.exp2(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.exp2``' intrinsic computes the base-2
exponential of the specified value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``exp2`` functions
would, and handles error conditions in the same way.
'``llvm.experimental.constrained.log``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.log(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.log``' intrinsic computes the base-e
logarithm of the specified value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``log`` functions
would, and handles error conditions in the same way.
'``llvm.experimental.constrained.log10``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.log10(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.log10``' intrinsic computes the base-10
logarithm of the specified value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``log10`` functions
would, and handles error conditions in the same way.
'``llvm.experimental.constrained.log2``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.log2(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.log2``' intrinsic computes the base-2
logarithm of the specified value.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``log2`` functions
would, and handles error conditions in the same way.
'``llvm.experimental.constrained.rint``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.rint(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.rint``' intrinsic returns the first
operand rounded to the nearest integer. It may raise an inexact floating-point
exception if the operand is not an integer.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``rint`` functions
would, and handles error conditions in the same way. The rounding mode is
described, not determined, by the rounding mode argument. The actual rounding
mode is determined by the runtime floating-point environment. The rounding
mode argument is only intended as information to the compiler.
'``llvm.experimental.constrained.lrint``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <inttype>
@llvm.experimental.constrained.lrint(<fptype> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.lrint``' intrinsic returns the first
operand rounded to the nearest integer. An inexact floating-point exception
will be raised if the operand is not an integer. An invalid exception is
raised if the result is too large to fit into a supported integer type,
and in this case the result is undefined.
Arguments:
""""""""""
The first argument is a floating-point number. The return value is an
integer type. Not all types are supported on all targets. The supported
types are the same as the ``llvm.lrint`` intrinsic and the ``lrint``
libm functions.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``lrint`` functions
would, and handles error conditions in the same way.
The rounding mode is described, not determined, by the rounding mode
argument. The actual rounding mode is determined by the runtime floating-point
environment. The rounding mode argument is only intended as information
to the compiler.
If the runtime floating-point environment is using the default rounding mode
then the results will be the same as the llvm.lrint intrinsic.
'``llvm.experimental.constrained.llrint``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <inttype>
@llvm.experimental.constrained.llrint(<fptype> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.llrint``' intrinsic returns the first
operand rounded to the nearest integer. An inexact floating-point exception
will be raised if the operand is not an integer. An invalid exception is
raised if the result is too large to fit into a supported integer type,
and in this case the result is undefined.
Arguments:
""""""""""
The first argument is a floating-point number. The return value is an
integer type. Not all types are supported on all targets. The supported
types are the same as the ``llvm.llrint`` intrinsic and the ``llrint``
libm functions.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``llrint`` functions
would, and handles error conditions in the same way.
The rounding mode is described, not determined, by the rounding mode
argument. The actual rounding mode is determined by the runtime floating-point
environment. The rounding mode argument is only intended as information
to the compiler.
If the runtime floating-point environment is using the default rounding mode
then the results will be the same as the llvm.llrint intrinsic.
'``llvm.experimental.constrained.nearbyint``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.nearbyint(<type> <op1>,
metadata <rounding mode>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.nearbyint``' intrinsic returns the first
operand rounded to the nearest integer. It will not raise an inexact
floating-point exception if the operand is not an integer.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second and third arguments specify the rounding mode and exception
behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``nearbyint`` functions
would, and handles error conditions in the same way. The rounding mode is
described, not determined, by the rounding mode argument. The actual rounding
mode is determined by the runtime floating-point environment. The rounding
mode argument is only intended as information to the compiler.
'``llvm.experimental.constrained.maxnum``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.maxnum(<type> <op1>, <type> <op2>
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.maxnum``' intrinsic returns the maximum
of the two arguments.
Arguments:
""""""""""
The first two arguments and the return value are floating-point numbers
of the same type.
The third argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function follows the IEEE-754 semantics for maxNum.
'``llvm.experimental.constrained.minnum``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.minnum(<type> <op1>, <type> <op2>
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.minnum``' intrinsic returns the minimum
of the two arguments.
Arguments:
""""""""""
The first two arguments and the return value are floating-point numbers
of the same type.
The third argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function follows the IEEE-754 semantics for minNum.
'``llvm.experimental.constrained.maximum``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.maximum(<type> <op1>, <type> <op2>
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.maximum``' intrinsic returns the maximum
of the two arguments, propagating NaNs and treating -0.0 as less than +0.0.
Arguments:
""""""""""
The first two arguments and the return value are floating-point numbers
of the same type.
The third argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function follows semantics specified in the draft of IEEE 754-2018.
'``llvm.experimental.constrained.minimum``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.minimum(<type> <op1>, <type> <op2>
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.minimum``' intrinsic returns the minimum
of the two arguments, propagating NaNs and treating -0.0 as less than +0.0.
Arguments:
""""""""""
The first two arguments and the return value are floating-point numbers
of the same type.
The third argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function follows semantics specified in the draft of IEEE 754-2018.
'``llvm.experimental.constrained.ceil``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.ceil(<type> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.ceil``' intrinsic returns the ceiling of the
first operand.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``ceil`` functions
would and handles error conditions in the same way.
'``llvm.experimental.constrained.floor``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.floor(<type> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.floor``' intrinsic returns the floor of the
first operand.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``floor`` functions
would and handles error conditions in the same way.
'``llvm.experimental.constrained.round``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.round(<type> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.round``' intrinsic returns the first
operand rounded to the nearest integer.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``round`` functions
would and handles error conditions in the same way.
'``llvm.experimental.constrained.roundeven``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.roundeven(<type> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.roundeven``' intrinsic returns the first
operand rounded to the nearest integer in floating-point format, rounding
halfway cases to even (that is, to the nearest value that is an even integer),
regardless of the current rounding direction.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function implements IEEE-754 operation ``roundToIntegralTiesToEven``. It
also behaves in the same way as C standard function ``roundeven`` and can signal
the invalid operation exception for a SNAN operand.
'``llvm.experimental.constrained.lround``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <inttype>
@llvm.experimental.constrained.lround(<fptype> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.lround``' intrinsic returns the first
operand rounded to the nearest integer with ties away from zero. It will
raise an inexact floating-point exception if the operand is not an integer.
An invalid exception is raised if the result is too large to fit into a
supported integer type, and in this case the result is undefined.
Arguments:
""""""""""
The first argument is a floating-point number. The return value is an
integer type. Not all types are supported on all targets. The supported
types are the same as the ``llvm.lround`` intrinsic and the ``lround``
libm functions.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``lround`` functions
would and handles error conditions in the same way.
'``llvm.experimental.constrained.llround``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <inttype>
@llvm.experimental.constrained.llround(<fptype> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.llround``' intrinsic returns the first
operand rounded to the nearest integer with ties away from zero. It will
raise an inexact floating-point exception if the operand is not an integer.
An invalid exception is raised if the result is too large to fit into a
supported integer type, and in this case the result is undefined.
Arguments:
""""""""""
The first argument is a floating-point number. The return value is an
integer type. Not all types are supported on all targets. The supported
types are the same as the ``llvm.llround`` intrinsic and the ``llround``
libm functions.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``llround`` functions
would and handles error conditions in the same way.
'``llvm.experimental.constrained.trunc``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.experimental.constrained.trunc(<type> <op1>,
metadata <exception behavior>)
Overview:
"""""""""
The '``llvm.experimental.constrained.trunc``' intrinsic returns the first
operand rounded to the nearest integer not larger in magnitude than the
operand.
Arguments:
""""""""""
The first argument and the return value are floating-point numbers of the same
type.
The second argument specifies the exception behavior as described above.
Semantics:
""""""""""
This function returns the same values as the libm ``trunc`` functions
would and handles error conditions in the same way.
.. _int_experimental_noalias_scope_decl:
'``llvm.experimental.noalias.scope.decl``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.experimental.noalias.scope.decl(metadata !id.scope.list)
Overview:
"""""""""
The ``llvm.experimental.noalias.scope.decl`` intrinsic identifies where a
noalias scope is declared. When the intrinsic is duplicated, a decision must
also be made about the scope: depending on the reason of the duplication,
the scope might need to be duplicated as well.
Arguments:
""""""""""
The ``!id.scope.list`` argument is metadata that is a list of ``noalias``
metadata references. The format is identical to that required for ``noalias``
metadata. This list must have exactly one element.
Semantics:
""""""""""
The ``llvm.experimental.noalias.scope.decl`` intrinsic identifies where a
noalias scope is declared. When the intrinsic is duplicated, a decision must
also be made about the scope: depending on the reason of the duplication,
the scope might need to be duplicated as well.
For example, when the intrinsic is used inside a loop body, and that loop is
unrolled, the associated noalias scope must also be duplicated. Otherwise, the
noalias property it signifies would spill across loop iterations, whereas it
was only valid within a single iteration.
.. code-block:: llvm
; This examples shows two possible positions for noalias.decl and how they impact the semantics:
; If it is outside the loop (Version 1), then %a and %b are noalias across *all* iterations.
; If it is inside the loop (Version 2), then %a and %b are noalias only within *one* iteration.
declare void @decl_in_loop(ptr %a.base, ptr %b.base) {
entry:
; call void @llvm.experimental.noalias.scope.decl(metadata !2) ; Version 1: noalias decl outside loop
br label %loop
loop:
%a = phi ptr [ %a.base, %entry ], [ %a.inc, %loop ]
%b = phi ptr [ %b.base, %entry ], [ %b.inc, %loop ]
; call void @llvm.experimental.noalias.scope.decl(metadata !2) ; Version 2: noalias decl inside loop
%val = load i8, ptr %a, !alias.scope !2
store i8 %val, ptr %b, !noalias !2
%a.inc = getelementptr inbounds i8, ptr %a, i64 1
%b.inc = getelementptr inbounds i8, ptr %b, i64 1
%cond = call i1 @cond()
br i1 %cond, label %loop, label %exit
exit:
ret void
}
!0 = !{!0} ; domain
!1 = !{!1, !0} ; scope
!2 = !{!1} ; scope list
Multiple calls to `@llvm.experimental.noalias.scope.decl` for the same scope
are possible, but one should never dominate another. Violations are pointed out
by the verifier as they indicate a problem in either a transformation pass or
the input.
Floating Point Environment Manipulation intrinsics
--------------------------------------------------
These functions read or write floating point environment, such as rounding
mode or state of floating point exceptions. Altering the floating point
environment requires special care. See :ref:`Floating Point Environment <floatenv>`.
.. _int_get_rounding:
'``llvm.get.rounding``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.get.rounding()
Overview:
"""""""""
The '``llvm.get.rounding``' intrinsic reads the current rounding mode.
Semantics:
""""""""""
The '``llvm.get.rounding``' intrinsic returns the current rounding mode.
Encoding of the returned values is same as the result of ``FLT_ROUNDS``,
specified by C standard:
::
0 - toward zero
1 - to nearest, ties to even
2 - toward positive infinity
3 - toward negative infinity
4 - to nearest, ties away from zero
Other values may be used to represent additional rounding modes, supported by a
target. These values are target-specific.
'``llvm.set.rounding``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.set.rounding(i32 <val>)
Overview:
"""""""""
The '``llvm.set.rounding``' intrinsic sets current rounding mode.
Arguments:
""""""""""
The argument is the required rounding mode. Encoding of rounding mode is
the same as used by '``llvm.get.rounding``'.
Semantics:
""""""""""
The '``llvm.set.rounding``' intrinsic sets the current rounding mode. It is
similar to C library function 'fesetround', however this intrinsic does not
return any value and uses platform-independent representation of IEEE rounding
modes.
'``llvm.get.fpenv``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <integer_type> @llvm.get.fpenv()
Overview:
"""""""""
The '``llvm.get.fpenv``' intrinsic returns bits of the current floating-point
environment. The return value type is platform-specific.
Semantics:
""""""""""
The '``llvm.get.fpenv``' intrinsic reads the current floating-point environment
and returns it as an integer value.
'``llvm.set.fpenv``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.set.fpenv(<integer_type> <val>)
Overview:
"""""""""
The '``llvm.set.fpenv``' intrinsic sets the current floating-point environment.
Arguments:
""""""""""
The argument is an integer representing the new floating-point environment. The
integer type is platform-specific.
Semantics:
""""""""""
The '``llvm.set.fpenv``' intrinsic sets the current floating-point environment
to the state specified by the argument. The state may be previously obtained by a
call to '``llvm.get.fpenv``' or synthesised in a platform-dependent way.
'``llvm.reset.fpenv``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.reset.fpenv()
Overview:
"""""""""
The '``llvm.reset.fpenv``' intrinsic sets the default floating-point environment.
Semantics:
""""""""""
The '``llvm.reset.fpenv``' intrinsic sets the current floating-point environment
to default state. It is similar to the call 'fesetenv(FE_DFL_ENV)', except it
does not return any value.
.. _int_get_fpmode:
'``llvm.get.fpmode``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
The '``llvm.get.fpmode``' intrinsic returns bits of the current floating-point
control modes. The return value type is platform-specific.
::
declare <integer_type> @llvm.get.fpmode()
Overview:
"""""""""
The '``llvm.get.fpmode``' intrinsic reads the current dynamic floating-point
control modes and returns it as an integer value.
Arguments:
""""""""""
None.
Semantics:
""""""""""
The '``llvm.get.fpmode``' intrinsic reads the current dynamic floating-point
control modes, such as rounding direction, precision, treatment of denormals and
so on. It is similar to the C library function 'fegetmode', however this
function does not store the set of control modes into memory but returns it as
an integer value. Interpretation of the bits in this value is target-dependent.
'``llvm.set.fpmode``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
The '``llvm.set.fpmode``' intrinsic sets the current floating-point control modes.
::
declare void @llvm.set.fpmode(<integer_type> <val>)
Overview:
"""""""""
The '``llvm.set.fpmode``' intrinsic sets the current dynamic floating-point
control modes.
Arguments:
""""""""""
The argument is a set of floating-point control modes, represented as an integer
value in a target-dependent way.
Semantics:
""""""""""
The '``llvm.set.fpmode``' intrinsic sets the current dynamic floating-point
control modes to the state specified by the argument, which must be obtained by
a call to '``llvm.get.fpmode``' or constructed in a target-specific way. It is
similar to the C library function 'fesetmode', however this function does not
read the set of control modes from memory but gets it as integer value.
'``llvm.reset.fpmode``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.reset.fpmode()
Overview:
"""""""""
The '``llvm.reset.fpmode``' intrinsic sets the default dynamic floating-point
control modes.
Arguments:
""""""""""
None.
Semantics:
""""""""""
The '``llvm.reset.fpmode``' intrinsic sets the current dynamic floating-point
environment to default state. It is similar to the C library function call
'fesetmode(FE_DFL_MODE)', however this function does not return any value.
Floating-Point Test Intrinsics
------------------------------
These functions get properties of floating-point values.
.. _llvm.is.fpclass:
'``llvm.is.fpclass``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i1 @llvm.is.fpclass(<fptype> <op>, i32 <test>)
declare <N x i1> @llvm.is.fpclass(<vector-fptype> <op>, i32 <test>)
Overview:
"""""""""
The '``llvm.is.fpclass``' intrinsic returns a boolean value or vector of boolean
values depending on whether the first argument satisfies the test specified by
the second argument.
If the first argument is a floating-point scalar, then the result type is a
boolean (:ref:`i1 <t_integer>`).
If the first argument is a floating-point vector, then the result type is a
vector of boolean with the same number of elements as the first argument.
Arguments:
""""""""""
The first argument to the '``llvm.is.fpclass``' intrinsic must be
:ref:`floating-point <t_floating>` or :ref:`vector <t_vector>`
of floating-point values.
The second argument specifies, which tests to perform. It must be a compile-time
integer constant, each bit in which specifies floating-point class:
+-------+----------------------+
| Bit # | floating-point class |
+=======+======================+
| 0 | Signaling NaN |
+-------+----------------------+
| 1 | Quiet NaN |
+-------+----------------------+
| 2 | Negative infinity |
+-------+----------------------+
| 3 | Negative normal |
+-------+----------------------+
| 4 | Negative subnormal |
+-------+----------------------+
| 5 | Negative zero |
+-------+----------------------+
| 6 | Positive zero |
+-------+----------------------+
| 7 | Positive subnormal |
+-------+----------------------+
| 8 | Positive normal |
+-------+----------------------+
| 9 | Positive infinity |
+-------+----------------------+
Semantics:
""""""""""
The function checks if ``op`` belongs to any of the floating-point classes
specified by ``test``. If ``op`` is a vector, then the check is made element by
element. Each check yields an :ref:`i1 <t_integer>` result, which is ``true``,
if the element value satisfies the specified test. The argument ``test`` is a
bit mask where each bit specifies floating-point class to test. For example, the
value 0x108 makes test for normal value, - bits 3 and 8 in it are set, which
means that the function returns ``true`` if ``op`` is a positive or negative
normal value. The function never raises floating-point exceptions. The
function does not canonicalize its input value and does not depend
on the floating-point environment. If the floating-point environment
has a zeroing treatment of subnormal input values (such as indicated
by the ``"denormal-fp-math"`` attribute), a subnormal value will be
observed (will not be implicitly treated as zero).
General Intrinsics
------------------
This class of intrinsics is designed to be generic and has no specific
purpose.
'``llvm.var.annotation``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.var.annotation(ptr <val>, ptr <str>, ptr <str>, i32 <int>)
Overview:
"""""""""
The '``llvm.var.annotation``' intrinsic.
Arguments:
""""""""""
The first argument is a pointer to a value, the second is a pointer to a
global string, the third is a pointer to a global string which is the
source file name, and the last argument is the line number.
Semantics:
""""""""""
This intrinsic allows annotation of local variables with arbitrary
strings. This can be useful for special purpose optimizations that want
to look for these annotations. These have no other defined use; they are
ignored by code generation and optimization.
'``llvm.ptr.annotation.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use '``llvm.ptr.annotation``' on a
pointer to an integer of any width. *NOTE* you must specify an address space for
the pointer. The identifier for the default address space is the integer
'``0``'.
::
declare ptr @llvm.ptr.annotation.p0(ptr <val>, ptr <str>, ptr <str>, i32 <int>)
declare ptr @llvm.ptr.annotation.p1(ptr addrspace(1) <val>, ptr <str>, ptr <str>, i32 <int>)
Overview:
"""""""""
The '``llvm.ptr.annotation``' intrinsic.
Arguments:
""""""""""
The first argument is a pointer to an integer value of arbitrary bitwidth
(result of some expression), the second is a pointer to a global string, the
third is a pointer to a global string which is the source file name, and the
last argument is the line number. It returns the value of the first argument.
Semantics:
""""""""""
This intrinsic allows annotation of a pointer to an integer with arbitrary
strings. This can be useful for special purpose optimizations that want to look
for these annotations. These have no other defined use; transformations preserve
annotations on a best-effort basis but are allowed to replace the intrinsic with
its first argument without breaking semantics and the intrinsic is completely
dropped during instruction selection.
'``llvm.annotation.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use '``llvm.annotation``' on
any integer bit width.
::
declare i8 @llvm.annotation.i8(i8 <val>, ptr <str>, ptr <str>, i32 <int>)
declare i16 @llvm.annotation.i16(i16 <val>, ptr <str>, ptr <str>, i32 <int>)
declare i32 @llvm.annotation.i32(i32 <val>, ptr <str>, ptr <str>, i32 <int>)
declare i64 @llvm.annotation.i64(i64 <val>, ptr <str>, ptr <str>, i32 <int>)
declare i256 @llvm.annotation.i256(i256 <val>, ptr <str>, ptr <str>, i32 <int>)
Overview:
"""""""""
The '``llvm.annotation``' intrinsic.
Arguments:
""""""""""
The first argument is an integer value (result of some expression), the
second is a pointer to a global string, the third is a pointer to a
global string which is the source file name, and the last argument is
the line number. It returns the value of the first argument.
Semantics:
""""""""""
This intrinsic allows annotations to be put on arbitrary expressions with
arbitrary strings. This can be useful for special purpose optimizations that
want to look for these annotations. These have no other defined use;
transformations preserve annotations on a best-effort basis but are allowed to
replace the intrinsic with its first argument without breaking semantics and the
intrinsic is completely dropped during instruction selection.
'``llvm.codeview.annotation``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This annotation emits a label at its program point and an associated
``S_ANNOTATION`` codeview record with some additional string metadata. This is
used to implement MSVC's ``__annotation`` intrinsic. It is marked
``noduplicate``, so calls to this intrinsic prevent inlining and should be
considered expensive.
::
declare void @llvm.codeview.annotation(metadata)
Arguments:
""""""""""
The argument should be an MDTuple containing any number of MDStrings.
'``llvm.trap``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.trap() cold noreturn nounwind
Overview:
"""""""""
The '``llvm.trap``' intrinsic.
Arguments:
""""""""""
None.
Semantics:
""""""""""
This intrinsic is lowered to the target dependent trap instruction. If
the target does not have a trap instruction, this intrinsic will be
lowered to a call of the ``abort()`` function.
'``llvm.debugtrap``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.debugtrap() nounwind
Overview:
"""""""""
The '``llvm.debugtrap``' intrinsic.
Arguments:
""""""""""
None.
Semantics:
""""""""""
This intrinsic is lowered to code which is intended to cause an
execution trap with the intention of requesting the attention of a
debugger.
'``llvm.ubsantrap``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.ubsantrap(i8 immarg) cold noreturn nounwind
Overview:
"""""""""
The '``llvm.ubsantrap``' intrinsic.
Arguments:
""""""""""
An integer describing the kind of failure detected.
Semantics:
""""""""""
This intrinsic is lowered to code which is intended to cause an execution trap,
embedding the argument into encoding of that trap somehow to discriminate
crashes if possible.
Equivalent to ``@llvm.trap`` for targets that do not support this behaviour.
'``llvm.stackprotector``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.stackprotector(ptr <guard>, ptr <slot>)
Overview:
"""""""""
The ``llvm.stackprotector`` intrinsic takes the ``guard`` and stores it
onto the stack at ``slot``. The stack slot is adjusted to ensure that it
is placed on the stack before local variables.
Arguments:
""""""""""
The ``llvm.stackprotector`` intrinsic requires two pointer arguments.
The first argument is the value loaded from the stack guard
``@__stack_chk_guard``. The second variable is an ``alloca`` that has
enough space to hold the value of the guard.
Semantics:
""""""""""
This intrinsic causes the prologue/epilogue inserter to force the position of
the ``AllocaInst`` stack slot to be before local variables on the stack. This is
to ensure that if a local variable on the stack is overwritten, it will destroy
the value of the guard. When the function exits, the guard on the stack is
checked against the original guard by ``llvm.stackprotectorcheck``. If they are
different, then ``llvm.stackprotectorcheck`` causes the program to abort by
calling the ``__stack_chk_fail()`` function.
'``llvm.stackguard``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.stackguard()
Overview:
"""""""""
The ``llvm.stackguard`` intrinsic returns the system stack guard value.
It should not be generated by frontends, since it is only for internal usage.
The reason why we create this intrinsic is that we still support IR form Stack
Protector in FastISel.
Arguments:
""""""""""
None.
Semantics:
""""""""""
On some platforms, the value returned by this intrinsic remains unchanged
between loads in the same thread. On other platforms, it returns the same
global variable value, if any, e.g. ``@__stack_chk_guard``.
Currently some platforms have IR-level customized stack guard loading (e.g.
X86 Linux) that is not handled by ``llvm.stackguard()``, while they should be
in the future.
'``llvm.objectsize``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 @llvm.objectsize.i32(ptr <object>, i1 <min>, i1 <nullunknown>, i1 <dynamic>)
declare i64 @llvm.objectsize.i64(ptr <object>, i1 <min>, i1 <nullunknown>, i1 <dynamic>)
Overview:
"""""""""
The ``llvm.objectsize`` intrinsic is designed to provide information to the
optimizer to determine whether a) an operation (like memcpy) will overflow a
buffer that corresponds to an object, or b) that a runtime check for overflow
isn't necessary. An object in this context means an allocation of a specific
class, structure, array, or other object.
Arguments:
""""""""""
The ``llvm.objectsize`` intrinsic takes four arguments. The first argument is a
pointer to or into the ``object``. The second argument determines whether
``llvm.objectsize`` returns 0 (if true) or -1 (if false) when the object size is
unknown. The third argument controls how ``llvm.objectsize`` acts when ``null``
in address space 0 is used as its pointer argument. If it's ``false``,
``llvm.objectsize`` reports 0 bytes available when given ``null``. Otherwise, if
the ``null`` is in a non-zero address space or if ``true`` is given for the
third argument of ``llvm.objectsize``, we assume its size is unknown. The fourth
argument to ``llvm.objectsize`` determines if the value should be evaluated at
runtime.
The second, third, and fourth arguments only accept constants.
Semantics:
""""""""""
The ``llvm.objectsize`` intrinsic is lowered to a value representing the size of
the object concerned. If the size cannot be determined, ``llvm.objectsize``
returns ``i32/i64 -1 or 0`` (depending on the ``min`` argument).
'``llvm.expect``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.expect`` on any
integer bit width.
::
declare i1 @llvm.expect.i1(i1 <val>, i1 <expected_val>)
declare i32 @llvm.expect.i32(i32 <val>, i32 <expected_val>)
declare i64 @llvm.expect.i64(i64 <val>, i64 <expected_val>)
Overview:
"""""""""
The ``llvm.expect`` intrinsic provides information about expected (the
most probable) value of ``val``, which can be used by optimizers.
Arguments:
""""""""""
The ``llvm.expect`` intrinsic takes two arguments. The first argument is
a value. The second argument is an expected value.
Semantics:
""""""""""
This intrinsic is lowered to the ``val``.
'``llvm.expect.with.probability``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This intrinsic is similar to ``llvm.expect``. This is an overloaded intrinsic.
You can use ``llvm.expect.with.probability`` on any integer bit width.
::
declare i1 @llvm.expect.with.probability.i1(i1 <val>, i1 <expected_val>, double <prob>)
declare i32 @llvm.expect.with.probability.i32(i32 <val>, i32 <expected_val>, double <prob>)
declare i64 @llvm.expect.with.probability.i64(i64 <val>, i64 <expected_val>, double <prob>)
Overview:
"""""""""
The ``llvm.expect.with.probability`` intrinsic provides information about
expected value of ``val`` with probability(or confidence) ``prob``, which can
be used by optimizers.
Arguments:
""""""""""
The ``llvm.expect.with.probability`` intrinsic takes three arguments. The first
argument is a value. The second argument is an expected value. The third
argument is a probability.
Semantics:
""""""""""
This intrinsic is lowered to the ``val``.
.. _int_assume:
'``llvm.assume``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.assume(i1 %cond)
Overview:
"""""""""
The ``llvm.assume`` allows the optimizer to assume that the provided
condition is true. This information can then be used in simplifying other parts
of the code.
More complex assumptions can be encoded as
:ref:`assume operand bundles <assume_opbundles>`.
Arguments:
""""""""""
The argument of the call is the condition which the optimizer may assume is
always true.
Semantics:
""""""""""
The intrinsic allows the optimizer to assume that the provided condition is
always true whenever the control flow reaches the intrinsic call. No code is
generated for this intrinsic, and instructions that contribute only to the
provided condition are not used for code generation. If the condition is
violated during execution, the behavior is undefined.
Note that the optimizer might limit the transformations performed on values
used by the ``llvm.assume`` intrinsic in order to preserve the instructions
only used to form the intrinsic's input argument. This might prove undesirable
if the extra information provided by the ``llvm.assume`` intrinsic does not cause
sufficient overall improvement in code quality. For this reason,
``llvm.assume`` should not be used to document basic mathematical invariants
that the optimizer can otherwise deduce or facts that are of little use to the
optimizer.
.. _int_ssa_copy:
'``llvm.ssa.copy``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare type @llvm.ssa.copy(type returned %operand) memory(none)
Arguments:
""""""""""
The first argument is an operand which is used as the returned value.
Overview:
""""""""""
The ``llvm.ssa.copy`` intrinsic can be used to attach information to
operations by copying them and giving them new names. For example,
the PredicateInfo utility uses it to build Extended SSA form, and
attach various forms of information to operands that dominate specific
uses. It is not meant for general use, only for building temporary
renaming forms that require value splits at certain points.
.. _type.test:
'``llvm.type.test``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i1 @llvm.type.test(ptr %ptr, metadata %type) nounwind memory(none)
Arguments:
""""""""""
The first argument is a pointer to be tested. The second argument is a
metadata object representing a :doc:`type identifier <TypeMetadata>`.
Overview:
"""""""""
The ``llvm.type.test`` intrinsic tests whether the given pointer is associated
with the given type identifier.
.. _type.checked.load:
'``llvm.type.checked.load``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare {ptr, i1} @llvm.type.checked.load(ptr %ptr, i32 %offset, metadata %type) nounwind memory(argmem: read)
Arguments:
""""""""""
The first argument is a pointer from which to load a function pointer. The
second argument is the byte offset from which to load the function pointer. The
third argument is a metadata object representing a :doc:`type identifier
<TypeMetadata>`.
Overview:
"""""""""
The ``llvm.type.checked.load`` intrinsic safely loads a function pointer from a
virtual table pointer using type metadata. This intrinsic is used to implement
control flow integrity in conjunction with virtual call optimization. The
virtual call optimization pass will optimize away ``llvm.type.checked.load``
intrinsics associated with devirtualized calls, thereby removing the type
check in cases where it is not needed to enforce the control flow integrity
constraint.
If the given pointer is associated with a type metadata identifier, this
function returns true as the second element of its return value. (Note that
the function may also return true if the given pointer is not associated
with a type metadata identifier.) If the function's return value's second
element is true, the following rules apply to the first element:
- If the given pointer is associated with the given type metadata identifier,
it is the function pointer loaded from the given byte offset from the given
pointer.
- If the given pointer is not associated with the given type metadata
identifier, it is one of the following (the choice of which is unspecified):
1. The function pointer that would have been loaded from an arbitrarily chosen
(through an unspecified mechanism) pointer associated with the type
metadata.
2. If the function has a non-void return type, a pointer to a function that
returns an unspecified value without causing side effects.
If the function's return value's second element is false, the value of the
first element is undefined.
.. _type.checked.load.relative:
'``llvm.type.checked.load.relative``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare {ptr, i1} @llvm.type.checked.load.relative(ptr %ptr, i32 %offset, metadata %type) argmemonly nounwind readonly
Overview:
"""""""""
The ``llvm.type.checked.load.relative`` intrinsic loads a relative pointer to a
function from a virtual table pointer using metadata. Otherwise, its semantic is
identical to the ``llvm.type.checked.load`` intrinsic.
A relative pointer is a pointer to an offset to the pointed to value. The
address of the underlying pointer of the relative pointer is obtained by adding
the offset to the address of the offset value.
'``llvm.arithmetic.fence``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.arithmetic.fence(<type> <op>)
Overview:
"""""""""
The purpose of the ``llvm.arithmetic.fence`` intrinsic
is to prevent the optimizer from performing fast-math optimizations,
particularly reassociation,
between the argument and the expression that contains the argument.
It can be used to preserve the parentheses in the source language.
Arguments:
""""""""""
The ``llvm.arithmetic.fence`` intrinsic takes only one argument.
The argument and the return value are floating-point numbers,
or vector floating-point numbers, of the same type.
Semantics:
""""""""""
This intrinsic returns the value of its operand. The optimizer can optimize
the argument, but the optimizer cannot hoist any component of the operand
to the containing context, and the optimizer cannot move the calculation of
any expression in the containing context into the operand.
'``llvm.donothing``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.donothing() nounwind memory(none)
Overview:
"""""""""
The ``llvm.donothing`` intrinsic doesn't perform any operation. It's one of only
three intrinsics (besides ``llvm.experimental.patchpoint`` and
``llvm.experimental.gc.statepoint``) that can be called with an invoke
instruction.
Arguments:
""""""""""
None.
Semantics:
""""""""""
This intrinsic does nothing, and it's removed by optimizers and ignored
by codegen.
'``llvm.experimental.deoptimize``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare type @llvm.experimental.deoptimize(...) [ "deopt"(...) ]
Overview:
"""""""""
This intrinsic, together with :ref:`deoptimization operand bundles
<deopt_opbundles>`, allow frontends to express transfer of control and
frame-local state from the currently executing (typically more specialized,
hence faster) version of a function into another (typically more generic, hence
slower) version.
In languages with a fully integrated managed runtime like Java and JavaScript
this intrinsic can be used to implement "uncommon trap" or "side exit" like
functionality. In unmanaged languages like C and C++, this intrinsic can be
used to represent the slow paths of specialized functions.
Arguments:
""""""""""
The intrinsic takes an arbitrary number of arguments, whose meaning is
decided by the :ref:`lowering strategy<deoptimize_lowering>`.
Semantics:
""""""""""
The ``@llvm.experimental.deoptimize`` intrinsic executes an attached
deoptimization continuation (denoted using a :ref:`deoptimization
operand bundle <deopt_opbundles>`) and returns the value returned by
the deoptimization continuation. Defining the semantic properties of
the continuation itself is out of scope of the language reference --
as far as LLVM is concerned, the deoptimization continuation can
invoke arbitrary side effects, including reading from and writing to
the entire heap.
Deoptimization continuations expressed using ``"deopt"`` operand bundles always
continue execution to the end of the physical frame containing them, so all
calls to ``@llvm.experimental.deoptimize`` must be in "tail position":
- ``@llvm.experimental.deoptimize`` cannot be invoked.
- The call must immediately precede a :ref:`ret <i_ret>` instruction.
- The ``ret`` instruction must return the value produced by the
``@llvm.experimental.deoptimize`` call if there is one, or void.
Note that the above restrictions imply that the return type for a call to
``@llvm.experimental.deoptimize`` will match the return type of its immediate
caller.
The inliner composes the ``"deopt"`` continuations of the caller into the
``"deopt"`` continuations present in the inlinee, and also updates calls to this
intrinsic to return directly from the frame of the function it inlined into.
All declarations of ``@llvm.experimental.deoptimize`` must share the
same calling convention.
.. _deoptimize_lowering:
Lowering:
"""""""""
Calls to ``@llvm.experimental.deoptimize`` are lowered to calls to the
symbol ``__llvm_deoptimize`` (it is the frontend's responsibility to
ensure that this symbol is defined). The call arguments to
``@llvm.experimental.deoptimize`` are lowered as if they were formal
arguments of the specified types, and not as varargs.
'``llvm.experimental.guard``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.experimental.guard(i1, ...) [ "deopt"(...) ]
Overview:
"""""""""
This intrinsic, together with :ref:`deoptimization operand bundles
<deopt_opbundles>`, allows frontends to express guards or checks on
optimistic assumptions made during compilation. The semantics of
``@llvm.experimental.guard`` is defined in terms of
``@llvm.experimental.deoptimize`` -- its body is defined to be
equivalent to:
.. code-block:: text
define void @llvm.experimental.guard(i1 %pred, <args...>) {
%realPred = and i1 %pred, undef
br i1 %realPred, label %continue, label %leave [, !make.implicit !{}]
leave:
call void @llvm.experimental.deoptimize(<args...>) [ "deopt"() ]
ret void
continue:
ret void
}
with the optional ``[, !make.implicit !{}]`` present if and only if it
is present on the call site. For more details on ``!make.implicit``,
see :doc:`FaultMaps`.
In words, ``@llvm.experimental.guard`` executes the attached
``"deopt"`` continuation if (but **not** only if) its first argument
is ``false``. Since the optimizer is allowed to replace the ``undef``
with an arbitrary value, it can optimize guard to fail "spuriously",
i.e. without the original condition being false (hence the "not only
if"); and this allows for "check widening" type optimizations.
``@llvm.experimental.guard`` cannot be invoked.
After ``@llvm.experimental.guard`` was first added, a more general
formulation was found in ``@llvm.experimental.widenable.condition``.
Support for ``@llvm.experimental.guard`` is slowly being rephrased in
terms of this alternate.
'``llvm.experimental.widenable.condition``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i1 @llvm.experimental.widenable.condition()
Overview:
"""""""""
This intrinsic represents a "widenable condition" which is
boolean expressions with the following property: whether this
expression is `true` or `false`, the program is correct and
well-defined.
Together with :ref:`deoptimization operand bundles <deopt_opbundles>`,
``@llvm.experimental.widenable.condition`` allows frontends to
express guards or checks on optimistic assumptions made during
compilation and represent them as branch instructions on special
conditions.
While this may appear similar in semantics to `undef`, it is very
different in that an invocation produces a particular, singular
value. It is also intended to be lowered late, and remain available
for specific optimizations and transforms that can benefit from its
special properties.
Arguments:
""""""""""
None.
Semantics:
""""""""""
The intrinsic ``@llvm.experimental.widenable.condition()``
returns either `true` or `false`. For each evaluation of a call
to this intrinsic, the program must be valid and correct both if
it returns `true` and if it returns `false`. This allows
transformation passes to replace evaluations of this intrinsic
with either value whenever one is beneficial.
When used in a branch condition, it allows us to choose between
two alternative correct solutions for the same problem, like
in example below:
.. code-block:: text
%cond = call i1 @llvm.experimental.widenable.condition()
br i1 %cond, label %solution_1, label %solution_2
label %fast_path:
; Apply memory-consuming but fast solution for a task.
label %slow_path:
; Cheap in memory but slow solution.
Whether the result of intrinsic's call is `true` or `false`,
it should be correct to pick either solution. We can switch
between them by replacing the result of
``@llvm.experimental.widenable.condition`` with different
`i1` expressions.
This is how it can be used to represent guards as widenable branches:
.. code-block:: text
block:
; Unguarded instructions
call void @llvm.experimental.guard(i1 %cond, <args...>) ["deopt"(<deopt_args...>)]
; Guarded instructions
Can be expressed in an alternative equivalent form of explicit branch using
``@llvm.experimental.widenable.condition``:
.. code-block:: text
block:
; Unguarded instructions
%widenable_condition = call i1 @llvm.experimental.widenable.condition()
%guard_condition = and i1 %cond, %widenable_condition
br i1 %guard_condition, label %guarded, label %deopt
guarded:
; Guarded instructions
deopt:
call type @llvm.experimental.deoptimize(<args...>) [ "deopt"(<deopt_args...>) ]
So the block `guarded` is only reachable when `%cond` is `true`,
and it should be valid to go to the block `deopt` whenever `%cond`
is `true` or `false`.
``@llvm.experimental.widenable.condition`` will never throw, thus
it cannot be invoked.
Guard widening:
"""""""""""""""
When ``@llvm.experimental.widenable.condition()`` is used in
condition of a guard represented as explicit branch, it is
legal to widen the guard's condition with any additional
conditions.
Guard widening looks like replacement of
.. code-block:: text
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%guard_cond = and i1 %cond, %widenable_cond
br i1 %guard_cond, label %guarded, label %deopt
with
.. code-block:: text
%widenable_cond = call i1 @llvm.experimental.widenable.condition()
%new_cond = and i1 %any_other_cond, %widenable_cond
%new_guard_cond = and i1 %cond, %new_cond
br i1 %new_guard_cond, label %guarded, label %deopt
for this branch. Here `%any_other_cond` is an arbitrarily chosen
well-defined `i1` value. By making guard widening, we may
impose stricter conditions on `guarded` block and bail to the
deopt when the new condition is not met.
Lowering:
"""""""""
Default lowering strategy is replacing the result of
call of ``@llvm.experimental.widenable.condition`` with
constant `true`. However it is always correct to replace
it with any other `i1` value. Any pass can
freely do it if it can benefit from non-default lowering.
'``llvm.load.relative``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.load.relative.iN(ptr %ptr, iN %offset) nounwind memory(argmem: read)
Overview:
"""""""""
This intrinsic loads a 32-bit value from the address ``%ptr + %offset``,
adds ``%ptr`` to that value and returns it. The constant folder specifically
recognizes the form of this intrinsic and the constant initializers it may
load from; if a loaded constant initializer is known to have the form
``i32 trunc(x - %ptr)``, the intrinsic call is folded to ``x``.
LLVM provides that the calculation of such a constant initializer will
not overflow at link time under the medium code model if ``x`` is an
``unnamed_addr`` function. However, it does not provide this guarantee for
a constant initializer folded into a function body. This intrinsic can be
used to avoid the possibility of overflows when loading from such a constant.
.. _llvm_sideeffect:
'``llvm.sideeffect``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.sideeffect() inaccessiblememonly nounwind willreturn
Overview:
"""""""""
The ``llvm.sideeffect`` intrinsic doesn't perform any operation. Optimizers
treat it as having side effects, so it can be inserted into a loop to
indicate that the loop shouldn't be assumed to terminate (which could
potentially lead to the loop being optimized away entirely), even if it's
an infinite loop with no other side effects.
Arguments:
""""""""""
None.
Semantics:
""""""""""
This intrinsic actually does nothing, but optimizers must assume that it
has externally observable side effects.
'``llvm.is.constant.*``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use llvm.is.constant with any argument type.
::
declare i1 @llvm.is.constant.i32(i32 %operand) nounwind memory(none)
declare i1 @llvm.is.constant.f32(float %operand) nounwind memory(none)
declare i1 @llvm.is.constant.TYPENAME(TYPE %operand) nounwind memory(none)
Overview:
"""""""""
The '``llvm.is.constant``' intrinsic will return true if the argument
is known to be a manifest compile-time constant. It is guaranteed to
fold to either true or false before generating machine code.
Semantics:
""""""""""
This intrinsic generates no code. If its argument is known to be a
manifest compile-time constant value, then the intrinsic will be
converted to a constant true value. Otherwise, it will be converted to
a constant false value.
In particular, note that if the argument is a constant expression
which refers to a global (the address of which _is_ a constant, but
not manifest during the compile), then the intrinsic evaluates to
false.
The result also intentionally depends on the result of optimization
passes -- e.g., the result can change depending on whether a
function gets inlined or not. A function's parameters are
obviously not constant. However, a call like
``llvm.is.constant.i32(i32 %param)`` *can* return true after the
function is inlined, if the value passed to the function parameter was
a constant.
On the other hand, if constant folding is not run, it will never
evaluate to true, even in simple cases.
.. _int_ptrmask:
'``llvm.ptrmask``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptrty llvm.ptrmask(ptrty %ptr, intty %mask) speculatable memory(none)
Arguments:
""""""""""
The first argument is a pointer or vector of pointers. The second argument is
an integer or vector of integers with the same bit width as the index type
size of the first argument.
Overview:
""""""""""
The ``llvm.ptrmask`` intrinsic masks out bits of the pointer according to a mask.
This allows stripping data from tagged pointers without converting them to an
integer (ptrtoint/inttoptr). As a consequence, we can preserve more information
to facilitate alias analysis and underlying-object detection.
Semantics:
""""""""""
The result of ``ptrmask(%ptr, %mask)`` is equivalent to the following expansion,
where ``iPtrIdx`` is the index type size of the pointer::
%intptr = ptrtoint ptr %ptr to iPtrIdx ; this may truncate
%masked = and iPtrIdx %intptr, %mask
%diff = sub iPtrIdx %masked, %intptr
%result = getelementptr i8, ptr %ptr, iPtrIdx %diff
If the pointer index type size is smaller than the pointer type size, this
implies that pointer bits beyond the index size are not affected by this
intrinsic. For integral pointers, it behaves as if the mask were extended with
1 bits to the pointer type size.
Both the returned pointer(s) and the first argument are based on the same
underlying object (for more information on the *based on* terminology see
:ref:`the pointer aliasing rules <pointeraliasing>`).
The intrinsic only captures the pointer argument through the return value.
.. _int_threadlocal_address:
'``llvm.threadlocal.address``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.threadlocal.address(ptr) nounwind willreturn memory(none)
Arguments:
""""""""""
The first argument is a pointer, which refers to a thread local global.
Semantics:
""""""""""
The address of a thread local global is not a constant, since it depends on
the calling thread. The `llvm.threadlocal.address` intrinsic returns the
address of the given thread local global in the calling thread.
.. _int_vscale:
'``llvm.vscale``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare i32 llvm.vscale.i32()
declare i64 llvm.vscale.i64()
Overview:
"""""""""
The ``llvm.vscale`` intrinsic returns the value for ``vscale`` in scalable
vectors such as ``<vscale x 16 x i8>``.
Semantics:
""""""""""
``vscale`` is a positive value that is constant throughout program
execution, but is unknown at compile time.
If the result value does not fit in the result type, then the result is
a :ref:`poison value <poisonvalues>`.
Stack Map Intrinsics
--------------------
LLVM provides experimental intrinsics to support runtime patching
mechanisms commonly desired in dynamic language JITs. These intrinsics
are described in :doc:`StackMaps`.
Element Wise Atomic Memory Intrinsics
-------------------------------------
These intrinsics are similar to the standard library memory intrinsics except
that they perform memory transfer as a sequence of atomic memory accesses.
.. _int_memcpy_element_unordered_atomic:
'``llvm.memcpy.element.unordered.atomic``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.memcpy.element.unordered.atomic`` on
any integer bit width and for different address spaces. Not all targets
support all bit widths however.
::
declare void @llvm.memcpy.element.unordered.atomic.p0.p0.i32(ptr <dest>,
ptr <src>,
i32 <len>,
i32 <element_size>)
declare void @llvm.memcpy.element.unordered.atomic.p0.p0.i64(ptr <dest>,
ptr <src>,
i64 <len>,
i32 <element_size>)
Overview:
"""""""""
The '``llvm.memcpy.element.unordered.atomic.*``' intrinsic is a specialization of the
'``llvm.memcpy.*``' intrinsic. It differs in that the ``dest`` and ``src`` are treated
as arrays with elements that are exactly ``element_size`` bytes, and the copy between
buffers uses a sequence of :ref:`unordered atomic <ordering>` load/store operations
that are a positive integer multiple of the ``element_size`` in size.
Arguments:
""""""""""
The first three arguments are the same as they are in the :ref:`@llvm.memcpy <int_memcpy>`
intrinsic, with the added constraint that ``len`` is required to be a positive integer
multiple of the ``element_size``. If ``len`` is not a positive integer multiple of
``element_size``, then the behaviour of the intrinsic is undefined.
``element_size`` must be a compile-time constant positive power of two no greater than
target-specific atomic access size limit.
For each of the input pointers ``align`` parameter attribute must be specified. It
must be a power of two no less than the ``element_size``. Caller guarantees that
both the source and destination pointers are aligned to that boundary.
Semantics:
""""""""""
The '``llvm.memcpy.element.unordered.atomic.*``' intrinsic copies ``len`` bytes of
memory from the source location to the destination location. These locations are not
allowed to overlap. The memory copy is performed as a sequence of load/store operations
where each access is guaranteed to be a multiple of ``element_size`` bytes wide and
aligned at an ``element_size`` boundary.
The order of the copy is unspecified. The same value may be read from the source
buffer many times, but only one write is issued to the destination buffer per
element. It is well defined to have concurrent reads and writes to both source and
destination provided those reads and writes are unordered atomic when specified.
This intrinsic does not provide any additional ordering guarantees over those
provided by a set of unordered loads from the source location and stores to the
destination.
Lowering:
"""""""""
In the most general case call to the '``llvm.memcpy.element.unordered.atomic.*``' is
lowered to a call to the symbol ``__llvm_memcpy_element_unordered_atomic_*``. Where '*'
is replaced with an actual element size. See :ref:`RewriteStatepointsForGC intrinsic
lowering <RewriteStatepointsForGC_intrinsic_lowering>` for details on GC specific
lowering.
Optimizer is allowed to inline memory copy when it's profitable to do so.
'``llvm.memmove.element.unordered.atomic``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use
``llvm.memmove.element.unordered.atomic`` on any integer bit width and for
different address spaces. Not all targets support all bit widths however.
::
declare void @llvm.memmove.element.unordered.atomic.p0.p0.i32(ptr <dest>,
ptr <src>,
i32 <len>,
i32 <element_size>)
declare void @llvm.memmove.element.unordered.atomic.p0.p0.i64(ptr <dest>,
ptr <src>,
i64 <len>,
i32 <element_size>)
Overview:
"""""""""
The '``llvm.memmove.element.unordered.atomic.*``' intrinsic is a specialization
of the '``llvm.memmove.*``' intrinsic. It differs in that the ``dest`` and
``src`` are treated as arrays with elements that are exactly ``element_size``
bytes, and the copy between buffers uses a sequence of
:ref:`unordered atomic <ordering>` load/store operations that are a positive
integer multiple of the ``element_size`` in size.
Arguments:
""""""""""
The first three arguments are the same as they are in the
:ref:`@llvm.memmove <int_memmove>` intrinsic, with the added constraint that
``len`` is required to be a positive integer multiple of the ``element_size``.
If ``len`` is not a positive integer multiple of ``element_size``, then the
behaviour of the intrinsic is undefined.
``element_size`` must be a compile-time constant positive power of two no
greater than a target-specific atomic access size limit.
For each of the input pointers the ``align`` parameter attribute must be
specified. It must be a power of two no less than the ``element_size``. Caller
guarantees that both the source and destination pointers are aligned to that
boundary.
Semantics:
""""""""""
The '``llvm.memmove.element.unordered.atomic.*``' intrinsic copies ``len`` bytes
of memory from the source location to the destination location. These locations
are allowed to overlap. The memory copy is performed as a sequence of load/store
operations where each access is guaranteed to be a multiple of ``element_size``
bytes wide and aligned at an ``element_size`` boundary.
The order of the copy is unspecified. The same value may be read from the source
buffer many times, but only one write is issued to the destination buffer per
element. It is well defined to have concurrent reads and writes to both source
and destination provided those reads and writes are unordered atomic when
specified.
This intrinsic does not provide any additional ordering guarantees over those
provided by a set of unordered loads from the source location and stores to the
destination.
Lowering:
"""""""""
In the most general case call to the
'``llvm.memmove.element.unordered.atomic.*``' is lowered to a call to the symbol
``__llvm_memmove_element_unordered_atomic_*``. Where '*' is replaced with an
actual element size. See :ref:`RewriteStatepointsForGC intrinsic lowering
<RewriteStatepointsForGC_intrinsic_lowering>` for details on GC specific
lowering.
The optimizer is allowed to inline the memory copy when it's profitable to do so.
.. _int_memset_element_unordered_atomic:
'``llvm.memset.element.unordered.atomic``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
This is an overloaded intrinsic. You can use ``llvm.memset.element.unordered.atomic`` on
any integer bit width and for different address spaces. Not all targets
support all bit widths however.
::
declare void @llvm.memset.element.unordered.atomic.p0.i32(ptr <dest>,
i8 <value>,
i32 <len>,
i32 <element_size>)
declare void @llvm.memset.element.unordered.atomic.p0.i64(ptr <dest>,
i8 <value>,
i64 <len>,
i32 <element_size>)
Overview:
"""""""""
The '``llvm.memset.element.unordered.atomic.*``' intrinsic is a specialization of the
'``llvm.memset.*``' intrinsic. It differs in that the ``dest`` is treated as an array
with elements that are exactly ``element_size`` bytes, and the assignment to that array
uses uses a sequence of :ref:`unordered atomic <ordering>` store operations
that are a positive integer multiple of the ``element_size`` in size.
Arguments:
""""""""""
The first three arguments are the same as they are in the :ref:`@llvm.memset <int_memset>`
intrinsic, with the added constraint that ``len`` is required to be a positive integer
multiple of the ``element_size``. If ``len`` is not a positive integer multiple of
``element_size``, then the behaviour of the intrinsic is undefined.
``element_size`` must be a compile-time constant positive power of two no greater than
target-specific atomic access size limit.
The ``dest`` input pointer must have the ``align`` parameter attribute specified. It
must be a power of two no less than the ``element_size``. Caller guarantees that
the destination pointer is aligned to that boundary.
Semantics:
""""""""""
The '``llvm.memset.element.unordered.atomic.*``' intrinsic sets the ``len`` bytes of
memory starting at the destination location to the given ``value``. The memory is
set with a sequence of store operations where each access is guaranteed to be a
multiple of ``element_size`` bytes wide and aligned at an ``element_size`` boundary.
The order of the assignment is unspecified. Only one write is issued to the
destination buffer per element. It is well defined to have concurrent reads and
writes to the destination provided those reads and writes are unordered atomic
when specified.
This intrinsic does not provide any additional ordering guarantees over those
provided by a set of unordered stores to the destination.
Lowering:
"""""""""
In the most general case call to the '``llvm.memset.element.unordered.atomic.*``' is
lowered to a call to the symbol ``__llvm_memset_element_unordered_atomic_*``. Where '*'
is replaced with an actual element size.
The optimizer is allowed to inline the memory assignment when it's profitable to do so.
Objective-C ARC Runtime Intrinsics
----------------------------------
LLVM provides intrinsics that lower to Objective-C ARC runtime entry points.
LLVM is aware of the semantics of these functions, and optimizes based on that
knowledge. You can read more about the details of Objective-C ARC `here
<https://clang.llvm.org/docs/AutomaticReferenceCounting.html>`_.
'``llvm.objc.autorelease``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.autorelease(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_autorelease <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-autorelease>`_.
'``llvm.objc.autoreleasePoolPop``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.autoreleasePoolPop(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_autoreleasePoolPop <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-autoreleasepoolpop-void-pool>`_.
'``llvm.objc.autoreleasePoolPush``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.autoreleasePoolPush()
Lowering:
"""""""""
Lowers to a call to `objc_autoreleasePoolPush <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-autoreleasepoolpush-void>`_.
'``llvm.objc.autoreleaseReturnValue``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.autoreleaseReturnValue(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_autoreleaseReturnValue <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-autoreleasereturnvalue>`_.
'``llvm.objc.copyWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.copyWeak(ptr, ptr)
Lowering:
"""""""""
Lowers to a call to `objc_copyWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-copyweak-id-dest-id-src>`_.
'``llvm.objc.destroyWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.destroyWeak(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_destroyWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-destroyweak-id-object>`_.
'``llvm.objc.initWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.initWeak(ptr, ptr)
Lowering:
"""""""""
Lowers to a call to `objc_initWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-initweak>`_.
'``llvm.objc.loadWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.loadWeak(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_loadWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-loadweak>`_.
'``llvm.objc.loadWeakRetained``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.loadWeakRetained(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_loadWeakRetained <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-loadweakretained>`_.
'``llvm.objc.moveWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.moveWeak(ptr, ptr)
Lowering:
"""""""""
Lowers to a call to `objc_moveWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-moveweak-id-dest-id-src>`_.
'``llvm.objc.release``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.release(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_release <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-release-id-value>`_.
'``llvm.objc.retain``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.retain(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_retain <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-retain>`_.
'``llvm.objc.retainAutorelease``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.retainAutorelease(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_retainAutorelease <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-retainautorelease>`_.
'``llvm.objc.retainAutoreleaseReturnValue``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.retainAutoreleaseReturnValue(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_retainAutoreleaseReturnValue <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-retainautoreleasereturnvalue>`_.
'``llvm.objc.retainAutoreleasedReturnValue``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.retainAutoreleasedReturnValue(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_retainAutoreleasedReturnValue <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-retainautoreleasedreturnvalue>`_.
'``llvm.objc.retainBlock``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.retainBlock(ptr)
Lowering:
"""""""""
Lowers to a call to `objc_retainBlock <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-retainblock>`_.
'``llvm.objc.storeStrong``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare void @llvm.objc.storeStrong(ptr, ptr)
Lowering:
"""""""""
Lowers to a call to `objc_storeStrong <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#void-objc-storestrong-id-object-id-value>`_.
'``llvm.objc.storeWeak``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare ptr @llvm.objc.storeWeak(ptr, ptr)
Lowering:
"""""""""
Lowers to a call to `objc_storeWeak <https://clang.llvm.org/docs/AutomaticReferenceCounting.html#arc-runtime-objc-storeweak>`_.
Preserving Debug Information Intrinsics
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
These intrinsics are used to carry certain debuginfo together with
IR-level operations. For example, it may be desirable to
know the structure/union name and the original user-level field
indices. Such information got lost in IR GetElementPtr instruction
since the IR types are different from debugInfo types and unions
are converted to structs in IR.
'``llvm.preserve.array.access.index``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ret_type>
@llvm.preserve.array.access.index.p0s_union.anons.p0a10s_union.anons(<type> base,
i32 dim,
i32 index)
Overview:
"""""""""
The '``llvm.preserve.array.access.index``' intrinsic returns the getelementptr address
based on array base ``base``, array dimension ``dim`` and the last access index ``index``
into the array. The return type ``ret_type`` is a pointer type to the array element.
The array ``dim`` and ``index`` are preserved which is more robust than
getelementptr instruction which may be subject to compiler transformation.
The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
to provide array or pointer debuginfo type.
The metadata is a ``DICompositeType`` or ``DIDerivedType`` representing the
debuginfo version of ``type``.
Arguments:
""""""""""
The ``base`` is the array base address. The ``dim`` is the array dimension.
The ``base`` is a pointer if ``dim`` equals 0.
The ``index`` is the last access index into the array or pointer.
The ``base`` argument must be annotated with an :ref:`elementtype
<attr_elementtype>` attribute at the call-site. This attribute specifies the
getelementptr element type.
Semantics:
""""""""""
The '``llvm.preserve.array.access.index``' intrinsic produces the same result
as a getelementptr with base ``base`` and access operands ``{dim's 0's, index}``.
'``llvm.preserve.union.access.index``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <type>
@llvm.preserve.union.access.index.p0s_union.anons.p0s_union.anons(<type> base,
i32 di_index)
Overview:
"""""""""
The '``llvm.preserve.union.access.index``' intrinsic carries the debuginfo field index
``di_index`` and returns the ``base`` address.
The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
to provide union debuginfo type.
The metadata is a ``DICompositeType`` representing the debuginfo version of ``type``.
The return type ``type`` is the same as the ``base`` type.
Arguments:
""""""""""
The ``base`` is the union base address. The ``di_index`` is the field index in debuginfo.
Semantics:
""""""""""
The '``llvm.preserve.union.access.index``' intrinsic returns the ``base`` address.
'``llvm.preserve.struct.access.index``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ret_type>
@llvm.preserve.struct.access.index.p0i8.p0s_struct.anon.0s(<type> base,
i32 gep_index,
i32 di_index)
Overview:
"""""""""
The '``llvm.preserve.struct.access.index``' intrinsic returns the getelementptr address
based on struct base ``base`` and IR struct member index ``gep_index``.
The ``llvm.preserve.access.index`` type of metadata is attached to this call instruction
to provide struct debuginfo type.
The metadata is a ``DICompositeType`` representing the debuginfo version of ``type``.
The return type ``ret_type`` is a pointer type to the structure member.
Arguments:
""""""""""
The ``base`` is the structure base address. The ``gep_index`` is the struct member index
based on IR structures. The ``di_index`` is the struct member index based on debuginfo.
The ``base`` argument must be annotated with an :ref:`elementtype
<attr_elementtype>` attribute at the call-site. This attribute specifies the
getelementptr element type.
Semantics:
""""""""""
The '``llvm.preserve.struct.access.index``' intrinsic produces the same result
as a getelementptr with base ``base`` and access operands ``{0, gep_index}``.
'``llvm.fptrunc.round``' Intrinsic
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Syntax:
"""""""
::
declare <ty2>
@llvm.fptrunc.round(<type> <value>, metadata <rounding mode>)
Overview:
"""""""""
The '``llvm.fptrunc.round``' intrinsic truncates
:ref:`floating-point <t_floating>` ``value`` to type ``ty2``
with a specified rounding mode.
Arguments:
""""""""""
The '``llvm.fptrunc.round``' intrinsic takes a :ref:`floating-point
<t_floating>` value to cast and a :ref:`floating-point <t_floating>` type
to cast it to. This argument must be larger in size than the result.
The second argument specifies the rounding mode as described in the constrained
intrinsics section.
For this intrinsic, the "round.dynamic" mode is not supported.
Semantics:
""""""""""
The '``llvm.fptrunc.round``' intrinsic casts a ``value`` from a larger
:ref:`floating-point <t_floating>` type to a smaller :ref:`floating-point
<t_floating>` type.
This intrinsic is assumed to execute in the default :ref:`floating-point
environment <floatenv>` *except* for the rounding mode.
This intrinsic is not supported on all targets. Some targets may not support
all rounding modes.
|