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
|
@c Copyright (C) 1988-2023 Free Software Foundation, Inc.
@c This is part of the GCC manual.
@c For copying conditions, see the file gcc.texi.
@ifset INTERNALS
@node Machine Desc
@chapter Machine Descriptions
@cindex machine descriptions
A machine description has two parts: a file of instruction patterns
(@file{.md} file) and a C header file of macro definitions.
The @file{.md} file for a target machine contains a pattern for each
instruction that the target machine supports (or at least each instruction
that is worth telling the compiler about). It may also contain comments.
A semicolon causes the rest of the line to be a comment, unless the semicolon
is inside a quoted string.
See the next chapter for information on the C header file.
@menu
* Overview:: How the machine description is used.
* Patterns:: How to write instruction patterns.
* Example:: An explained example of a @code{define_insn} pattern.
* RTL Template:: The RTL template defines what insns match a pattern.
* Output Template:: The output template says how to make assembler code
from such an insn.
* Output Statement:: For more generality, write C code to output
the assembler code.
* Compact Syntax:: Compact syntax for writing machine descriptors.
* Predicates:: Controlling what kinds of operands can be used
for an insn.
* Constraints:: Fine-tuning operand selection.
* Standard Names:: Names mark patterns to use for code generation.
* Pattern Ordering:: When the order of patterns makes a difference.
* Dependent Patterns:: Having one pattern may make you need another.
* Jump Patterns:: Special considerations for patterns for jump insns.
* Looping Patterns:: How to define patterns for special looping insns.
* Insn Canonicalizations::Canonicalization of Instructions
* Expander Definitions::Generating a sequence of several RTL insns
for a standard operation.
* Insn Splitting:: Splitting Instructions into Multiple Instructions.
* Including Patterns:: Including Patterns in Machine Descriptions.
* Peephole Definitions::Defining machine-specific peephole optimizations.
* Insn Attributes:: Specifying the value of attributes for generated insns.
* Conditional Execution::Generating @code{define_insn} patterns for
predication.
* Define Subst:: Generating @code{define_insn} and @code{define_expand}
patterns from other patterns.
* Constant Definitions::Defining symbolic constants that can be used in the
md file.
* Iterators:: Using iterators to generate patterns from a template.
@end menu
@node Overview
@section Overview of How the Machine Description is Used
There are three main conversions that happen in the compiler:
@enumerate
@item
The front end reads the source code and builds a parse tree.
@item
The parse tree is used to generate an RTL insn list based on named
instruction patterns.
@item
The insn list is matched against the RTL templates to produce assembler
code.
@end enumerate
For the generate pass, only the names of the insns matter, from either a
named @code{define_insn} or a @code{define_expand}. The compiler will
choose the pattern with the right name and apply the operands according
to the documentation later in this chapter, without regard for the RTL
template or operand constraints. Note that the names the compiler looks
for are hard-coded in the compiler---it will ignore unnamed patterns and
patterns with names it doesn't know about, but if you don't provide a
named pattern it needs, it will abort.
If a @code{define_insn} is used, the template given is inserted into the
insn list. If a @code{define_expand} is used, one of three things
happens, based on the condition logic. The condition logic may manually
create new insns for the insn list, say via @code{emit_insn()}, and
invoke @code{DONE}. For certain named patterns, it may invoke @code{FAIL} to tell the
compiler to use an alternate way of performing that task. If it invokes
neither @code{DONE} nor @code{FAIL}, the template given in the pattern
is inserted, as if the @code{define_expand} were a @code{define_insn}.
Once the insn list is generated, various optimization passes convert,
replace, and rearrange the insns in the insn list. This is where the
@code{define_split} and @code{define_peephole} patterns get used, for
example.
Finally, the insn list's RTL is matched up with the RTL templates in the
@code{define_insn} patterns, and those patterns are used to emit the
final assembly code. For this purpose, each named @code{define_insn}
acts like it's unnamed, since the names are ignored.
@node Patterns
@section Everything about Instruction Patterns
@cindex patterns
@cindex instruction patterns
@findex define_insn
A @code{define_insn} expression is used to define instruction patterns
to which insns may be matched. A @code{define_insn} expression contains
an incomplete RTL expression, with pieces to be filled in later, operand
constraints that restrict how the pieces can be filled in, and an output
template or C code to generate the assembler output.
A @code{define_insn} is an RTL expression containing four or five operands:
@enumerate
@item
An optional name @var{n}. When a name is present, the compiler
automically generates a C++ function @samp{gen_@var{n}} that takes
the operands of the instruction as arguments and returns the instruction's
rtx pattern. The compiler also assigns the instruction a unique code
@samp{CODE_FOR_@var{n}}, with all such codes belonging to an enum
called @code{insn_code}.
These names serve one of two purposes. The first is to indicate that the
instruction performs a certain standard job for the RTL-generation
pass of the compiler, such as a move, an addition, or a conditional
jump. The second is to help the target generate certain target-specific
operations, such as when implementing target-specific intrinsic functions.
It is better to prefix target-specific names with the name of the
target, to avoid any clash with current or future standard names.
The absence of a name is indicated by writing an empty string
where the name should go. Nameless instruction patterns are never
used for generating RTL code, but they may permit several simpler insns
to be combined later on.
For the purpose of debugging the compiler, you may also specify a
name beginning with the @samp{*} character. Such a name is used only
for identifying the instruction in RTL dumps; it is equivalent to having
a nameless pattern for all other purposes. Names beginning with the
@samp{*} character are not required to be unique.
The name may also have the form @samp{@@@var{n}}. This has the same
effect as a name @samp{@var{n}}, but in addition tells the compiler to
generate further helper functions; see @ref{Parameterized Names} for details.
@item
The @dfn{RTL template}: This is a vector of incomplete RTL expressions
which describe the semantics of the instruction (@pxref{RTL Template}).
It is incomplete because it may contain @code{match_operand},
@code{match_operator}, and @code{match_dup} expressions that stand for
operands of the instruction.
If the vector has multiple elements, the RTL template is treated as a
@code{parallel} expression.
@cindex pattern conditions
@cindex conditions, in patterns
@item
The condition: This is a string which contains a C expression. When the
compiler attempts to match RTL against a pattern, the condition is
evaluated. If the condition evaluates to @code{true}, the match is
permitted. The condition may be an empty string, which is treated
as always @code{true}.
@cindex named patterns and conditions
For a named pattern, the condition may not depend on the data in the
insn being matched, but only the target-machine-type flags. The compiler
needs to test these conditions during initialization in order to learn
exactly which named instructions are available in a particular run.
@findex operands
For nameless patterns, the condition is applied only when matching an
individual insn, and only after the insn has matched the pattern's
recognition template. The insn's operands may be found in the vector
@code{operands}.
An instruction condition cannot become more restrictive as compilation
progresses. If the condition accepts a particular RTL instruction at
one stage of compilation, it must continue to accept that instruction
until the final pass. For example, @samp{!reload_completed} and
@samp{can_create_pseudo_p ()} are both invalid instruction conditions,
because they are true during the earlier RTL passes and false during
the later ones. For the same reason, if a condition accepts an
instruction before register allocation, it cannot later try to control
register allocation by excluding certain register or value combinations.
Although a condition cannot become more restrictive as compilation
progresses, the condition for a nameless pattern @emph{can} become
more permissive. For example, a nameless instruction can require
@samp{reload_completed} to be true, in which case it only matches
after register allocation.
@item
The @dfn{output template} or @dfn{output statement}: This is either
a string, or a fragment of C code which returns a string.
When simple substitution isn't general enough, you can specify a piece
of C code to compute the output. @xref{Output Statement}.
@item
The @dfn{insn attributes}: This is an optional vector containing the values of
attributes for insns matching this pattern (@pxref{Insn Attributes}).
@end enumerate
@node Example
@section Example of @code{define_insn}
@cindex @code{define_insn} example
Here is an example of an instruction pattern, taken from the machine
description for the 68000/68020.
@smallexample
(define_insn "tstsi"
[(set (cc0)
(match_operand:SI 0 "general_operand" "rm"))]
""
"*
@{
if (TARGET_68020 || ! ADDRESS_REG_P (operands[0]))
return \"tstl %0\";
return \"cmpl #0,%0\";
@}")
@end smallexample
@noindent
This can also be written using braced strings:
@smallexample
(define_insn "tstsi"
[(set (cc0)
(match_operand:SI 0 "general_operand" "rm"))]
""
@{
if (TARGET_68020 || ! ADDRESS_REG_P (operands[0]))
return "tstl %0";
return "cmpl #0,%0";
@})
@end smallexample
This describes an instruction which sets the condition codes based on the
value of a general operand. It has no condition, so any insn with an RTL
description of the form shown may be matched to this pattern. The name
@samp{tstsi} means ``test a @code{SImode} value'' and tells the RTL
generation pass that, when it is necessary to test such a value, an insn
to do so can be constructed using this pattern.
The output control string is a piece of C code which chooses which
output template to return based on the kind of operand and the specific
type of CPU for which code is being generated.
@samp{"rm"} is an operand constraint. Its meaning is explained below.
@node RTL Template
@section RTL Template
@cindex RTL insn template
@cindex generating insns
@cindex insns, generating
@cindex recognizing insns
@cindex insns, recognizing
The RTL template is used to define which insns match the particular pattern
and how to find their operands. For named patterns, the RTL template also
says how to construct an insn from specified operands.
Construction involves substituting specified operands into a copy of the
template. Matching involves determining the values that serve as the
operands in the insn being matched. Both of these activities are
controlled by special expression types that direct matching and
substitution of the operands.
@table @code
@findex match_operand
@item (match_operand:@var{m} @var{n} @var{predicate} @var{constraint})
This expression is a placeholder for operand number @var{n} of
the insn. When constructing an insn, operand number @var{n}
will be substituted at this point. When matching an insn, whatever
appears at this position in the insn will be taken as operand
number @var{n}; but it must satisfy @var{predicate} or this instruction
pattern will not match at all.
Operand numbers must be chosen consecutively counting from zero in
each instruction pattern. There may be only one @code{match_operand}
expression in the pattern for each operand number. Usually operands
are numbered in the order of appearance in @code{match_operand}
expressions. In the case of a @code{define_expand}, any operand numbers
used only in @code{match_dup} expressions have higher values than all
other operand numbers.
@var{predicate} is a string that is the name of a function that
accepts two arguments, an expression and a machine mode.
@xref{Predicates}. During matching, the function will be called with
the putative operand as the expression and @var{m} as the mode
argument (if @var{m} is not specified, @code{VOIDmode} will be used,
which normally causes @var{predicate} to accept any mode). If it
returns zero, this instruction pattern fails to match.
@var{predicate} may be an empty string; then it means no test is to be
done on the operand, so anything which occurs in this position is
valid.
Most of the time, @var{predicate} will reject modes other than @var{m}---but
not always. For example, the predicate @code{address_operand} uses
@var{m} as the mode of memory ref that the address should be valid for.
Many predicates accept @code{const_int} nodes even though their mode is
@code{VOIDmode}.
@var{constraint} controls reloading and the choice of the best register
class to use for a value, as explained later (@pxref{Constraints}).
If the constraint would be an empty string, it can be omitted.
People are often unclear on the difference between the constraint and the
predicate. The predicate helps decide whether a given insn matches the
pattern. The constraint plays no role in this decision; instead, it
controls various decisions in the case of an insn which does match.
@findex match_scratch
@item (match_scratch:@var{m} @var{n} @var{constraint})
This expression is also a placeholder for operand number @var{n}
and indicates that operand must be a @code{scratch} or @code{reg}
expression.
When matching patterns, this is equivalent to
@smallexample
(match_operand:@var{m} @var{n} "scratch_operand" @var{constraint})
@end smallexample
but, when generating RTL, it produces a (@code{scratch}:@var{m})
expression.
If the last few expressions in a @code{parallel} are @code{clobber}
expressions whose operands are either a hard register or
@code{match_scratch}, the combiner can add or delete them when
necessary. @xref{Side Effects}.
@findex match_dup
@item (match_dup @var{n})
This expression is also a placeholder for operand number @var{n}.
It is used when the operand needs to appear more than once in the
insn.
In construction, @code{match_dup} acts just like @code{match_operand}:
the operand is substituted into the insn being constructed. But in
matching, @code{match_dup} behaves differently. It assumes that operand
number @var{n} has already been determined by a @code{match_operand}
appearing earlier in the recognition template, and it matches only an
identical-looking expression.
Note that @code{match_dup} should not be used to tell the compiler that
a particular register is being used for two operands (example:
@code{add} that adds one register to another; the second register is
both an input operand and the output operand). Use a matching
constraint (@pxref{Simple Constraints}) for those. @code{match_dup} is for the cases where one
operand is used in two places in the template, such as an instruction
that computes both a quotient and a remainder, where the opcode takes
two input operands but the RTL template has to refer to each of those
twice; once for the quotient pattern and once for the remainder pattern.
@findex match_operator
@item (match_operator:@var{m} @var{n} @var{predicate} [@var{operands}@dots{}])
This pattern is a kind of placeholder for a variable RTL expression
code.
When constructing an insn, it stands for an RTL expression whose
expression code is taken from that of operand @var{n}, and whose
operands are constructed from the patterns @var{operands}.
When matching an expression, it matches an expression if the function
@var{predicate} returns nonzero on that expression @emph{and} the
patterns @var{operands} match the operands of the expression.
Suppose that the function @code{commutative_operator} is defined as
follows, to match any expression whose operator is one of the
commutative arithmetic operators of RTL and whose mode is @var{mode}:
@smallexample
int
commutative_operator (x, mode)
rtx x;
machine_mode mode;
@{
enum rtx_code code = GET_CODE (x);
if (GET_MODE (x) != mode)
return 0;
return (GET_RTX_CLASS (code) == RTX_COMM_ARITH
|| code == EQ || code == NE);
@}
@end smallexample
Then the following pattern will match any RTL expression consisting
of a commutative operator applied to two general operands:
@smallexample
(match_operator:SI 3 "commutative_operator"
[(match_operand:SI 1 "general_operand" "g")
(match_operand:SI 2 "general_operand" "g")])
@end smallexample
Here the vector @code{[@var{operands}@dots{}]} contains two patterns
because the expressions to be matched all contain two operands.
When this pattern does match, the two operands of the commutative
operator are recorded as operands 1 and 2 of the insn. (This is done
by the two instances of @code{match_operand}.) Operand 3 of the insn
will be the entire commutative expression: use @code{GET_CODE
(operands[3])} to see which commutative operator was used.
The machine mode @var{m} of @code{match_operator} works like that of
@code{match_operand}: it is passed as the second argument to the
predicate function, and that function is solely responsible for
deciding whether the expression to be matched ``has'' that mode.
When constructing an insn, argument 3 of the gen-function will specify
the operation (i.e.@: the expression code) for the expression to be
made. It should be an RTL expression, whose expression code is copied
into a new expression whose operands are arguments 1 and 2 of the
gen-function. The subexpressions of argument 3 are not used;
only its expression code matters.
When @code{match_operator} is used in a pattern for matching an insn,
it usually best if the operand number of the @code{match_operator}
is higher than that of the actual operands of the insn. This improves
register allocation because the register allocator often looks at
operands 1 and 2 of insns to see if it can do register tying.
There is no way to specify constraints in @code{match_operator}. The
operand of the insn which corresponds to the @code{match_operator}
never has any constraints because it is never reloaded as a whole.
However, if parts of its @var{operands} are matched by
@code{match_operand} patterns, those parts may have constraints of
their own.
@findex match_op_dup
@item (match_op_dup:@var{m} @var{n}[@var{operands}@dots{}])
Like @code{match_dup}, except that it applies to operators instead of
operands. When constructing an insn, operand number @var{n} will be
substituted at this point. But in matching, @code{match_op_dup} behaves
differently. It assumes that operand number @var{n} has already been
determined by a @code{match_operator} appearing earlier in the
recognition template, and it matches only an identical-looking
expression.
@findex match_parallel
@item (match_parallel @var{n} @var{predicate} [@var{subpat}@dots{}])
This pattern is a placeholder for an insn that consists of a
@code{parallel} expression with a variable number of elements. This
expression should only appear at the top level of an insn pattern.
When constructing an insn, operand number @var{n} will be substituted at
this point. When matching an insn, it matches if the body of the insn
is a @code{parallel} expression with at least as many elements as the
vector of @var{subpat} expressions in the @code{match_parallel}, if each
@var{subpat} matches the corresponding element of the @code{parallel},
@emph{and} the function @var{predicate} returns nonzero on the
@code{parallel} that is the body of the insn. It is the responsibility
of the predicate to validate elements of the @code{parallel} beyond
those listed in the @code{match_parallel}.
A typical use of @code{match_parallel} is to match load and store
multiple expressions, which can contain a variable number of elements
in a @code{parallel}. For example,
@smallexample
(define_insn ""
[(match_parallel 0 "load_multiple_operation"
[(set (match_operand:SI 1 "gpc_reg_operand" "=r")
(match_operand:SI 2 "memory_operand" "m"))
(use (reg:SI 179))
(clobber (reg:SI 179))])]
""
"loadm 0,0,%1,%2")
@end smallexample
This example comes from @file{a29k.md}. The function
@code{load_multiple_operation} is defined in @file{a29k.c} and checks
that subsequent elements in the @code{parallel} are the same as the
@code{set} in the pattern, except that they are referencing subsequent
registers and memory locations.
An insn that matches this pattern might look like:
@smallexample
(parallel
[(set (reg:SI 20) (mem:SI (reg:SI 100)))
(use (reg:SI 179))
(clobber (reg:SI 179))
(set (reg:SI 21)
(mem:SI (plus:SI (reg:SI 100)
(const_int 4))))
(set (reg:SI 22)
(mem:SI (plus:SI (reg:SI 100)
(const_int 8))))])
@end smallexample
@findex match_par_dup
@item (match_par_dup @var{n} [@var{subpat}@dots{}])
Like @code{match_op_dup}, but for @code{match_parallel} instead of
@code{match_operator}.
@end table
@node Output Template
@section Output Templates and Operand Substitution
@cindex output templates
@cindex operand substitution
@cindex @samp{%} in template
@cindex percent sign
The @dfn{output template} is a string which specifies how to output the
assembler code for an instruction pattern. Most of the template is a
fixed string which is output literally. The character @samp{%} is used
to specify where to substitute an operand; it can also be used to
identify places where different variants of the assembler require
different syntax.
In the simplest case, a @samp{%} followed by a digit @var{n} says to output
operand @var{n} at that point in the string.
@samp{%} followed by a letter and a digit says to output an operand in an
alternate fashion. Four letters have standard, built-in meanings described
below. The machine description macro @code{PRINT_OPERAND} can define
additional letters with nonstandard meanings.
@samp{%c@var{digit}} can be used to substitute an operand that is a
constant value without the syntax that normally indicates an immediate
operand.
@samp{%n@var{digit}} is like @samp{%c@var{digit}} except that the value of
the constant is negated before printing.
@samp{%a@var{digit}} can be used to substitute an operand as if it were a
memory reference, with the actual operand treated as the address. This may
be useful when outputting a ``load address'' instruction, because often the
assembler syntax for such an instruction requires you to write the operand
as if it were a memory reference.
@samp{%l@var{digit}} is used to substitute a @code{label_ref} into a jump
instruction.
@samp{%=} outputs a number which is unique to each instruction in the
entire compilation. This is useful for making local labels to be
referred to more than once in a single template that generates multiple
assembler instructions.
@samp{%} followed by a punctuation character specifies a substitution that
does not use an operand. Only one case is standard: @samp{%%} outputs a
@samp{%} into the assembler code. Other nonstandard cases can be
defined in the @code{PRINT_OPERAND} macro. You must also define
which punctuation characters are valid with the
@code{PRINT_OPERAND_PUNCT_VALID_P} macro.
@cindex \
@cindex backslash
The template may generate multiple assembler instructions. Write the text
for the instructions, with @samp{\;} between them.
@cindex matching operands
When the RTL contains two operands which are required by constraint to match
each other, the output template must refer only to the lower-numbered operand.
Matching operands are not always identical, and the rest of the compiler
arranges to put the proper RTL expression for printing into the lower-numbered
operand.
One use of nonstandard letters or punctuation following @samp{%} is to
distinguish between different assembler languages for the same machine; for
example, Motorola syntax versus MIT syntax for the 68000. Motorola syntax
requires periods in most opcode names, while MIT syntax does not. For
example, the opcode @samp{movel} in MIT syntax is @samp{move.l} in Motorola
syntax. The same file of patterns is used for both kinds of output syntax,
but the character sequence @samp{%.} is used in each place where Motorola
syntax wants a period. The @code{PRINT_OPERAND} macro for Motorola syntax
defines the sequence to output a period; the macro for MIT syntax defines
it to do nothing.
@cindex @code{#} in template
As a special case, a template consisting of the single character @code{#}
instructs the compiler to first split the insn, and then output the
resulting instructions separately. This helps eliminate redundancy in the
output templates. If you have a @code{define_insn} that needs to emit
multiple assembler instructions, and there is a matching @code{define_split}
already defined, then you can simply use @code{#} as the output template
instead of writing an output template that emits the multiple assembler
instructions.
Note that @code{#} only has an effect while generating assembly code;
it does not affect whether a split occurs earlier. An associated
@code{define_split} must exist and it must be suitable for use after
register allocation.
If the macro @code{ASSEMBLER_DIALECT} is defined, you can use construct
of the form @samp{@{option0|option1|option2@}} in the templates. These
describe multiple variants of assembler language syntax.
@xref{Instruction Output}.
@node Output Statement
@section C Statements for Assembler Output
@cindex output statements
@cindex C statements for assembler output
@cindex generating assembler output
Often a single fixed template string cannot produce correct and efficient
assembler code for all the cases that are recognized by a single
instruction pattern. For example, the opcodes may depend on the kinds of
operands; or some unfortunate combinations of operands may require extra
machine instructions.
If the output control string starts with a @samp{@@}, then it is actually
a series of templates, each on a separate line. (Blank lines and
leading spaces and tabs are ignored.) The templates correspond to the
pattern's constraint alternatives (@pxref{Multi-Alternative}). For example,
if a target machine has a two-address add instruction @samp{addr} to add
into a register and another @samp{addm} to add a register to memory, you
might write this pattern:
@smallexample
(define_insn "addsi3"
[(set (match_operand:SI 0 "general_operand" "=r,m")
(plus:SI (match_operand:SI 1 "general_operand" "0,0")
(match_operand:SI 2 "general_operand" "g,r")))]
""
"@@
addr %2,%0
addm %2,%0")
@end smallexample
@cindex @code{*} in template
@cindex asterisk in template
If the output control string starts with a @samp{*}, then it is not an
output template but rather a piece of C program that should compute a
template. It should execute a @code{return} statement to return the
template-string you want. Most such templates use C string literals, which
require doublequote characters to delimit them. To include these
doublequote characters in the string, prefix each one with @samp{\}.
If the output control string is written as a brace block instead of a
double-quoted string, it is automatically assumed to be C code. In that
case, it is not necessary to put in a leading asterisk, or to escape the
doublequotes surrounding C string literals.
The operands may be found in the array @code{operands}, whose C data type
is @code{rtx []}.
It is very common to select different ways of generating assembler code
based on whether an immediate operand is within a certain range. Be
careful when doing this, because the result of @code{INTVAL} is an
integer on the host machine. If the host machine has more bits in an
@code{int} than the target machine has in the mode in which the constant
will be used, then some of the bits you get from @code{INTVAL} will be
superfluous. For proper results, you must carefully disregard the
values of those bits.
@findex output_asm_insn
It is possible to output an assembler instruction and then go on to output
or compute more of them, using the subroutine @code{output_asm_insn}. This
receives two arguments: a template-string and a vector of operands. The
vector may be @code{operands}, or it may be another array of @code{rtx}
that you declare locally and initialize yourself.
@findex which_alternative
When an insn pattern has multiple alternatives in its constraints, often
the appearance of the assembler code is determined mostly by which alternative
was matched. When this is so, the C code can test the variable
@code{which_alternative}, which is the ordinal number of the alternative
that was actually satisfied (0 for the first, 1 for the second alternative,
etc.).
For example, suppose there are two opcodes for storing zero, @samp{clrreg}
for registers and @samp{clrmem} for memory locations. Here is how
a pattern could use @code{which_alternative} to choose between them:
@smallexample
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r,m")
(const_int 0))]
""
@{
return (which_alternative == 0
? "clrreg %0" : "clrmem %0");
@})
@end smallexample
The example above, where the assembler code to generate was
@emph{solely} determined by the alternative, could also have been specified
as follows, having the output control string start with a @samp{@@}:
@smallexample
@group
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r,m")
(const_int 0))]
""
"@@
clrreg %0
clrmem %0")
@end group
@end smallexample
If you just need a little bit of C code in one (or a few) alternatives,
you can use @samp{*} inside of a @samp{@@} multi-alternative template:
@smallexample
@group
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r,<,m")
(const_int 0))]
""
"@@
clrreg %0
* return stack_mem_p (operands[0]) ? \"push 0\" : \"clrmem %0\";
clrmem %0")
@end group
@end smallexample
@node Compact Syntax
@section Compact Syntax
@cindex compact syntax
When a @code{define_insn} or @code{define_insn_and_split} has multiple
alternatives it may be beneficial to use the compact syntax when specifying
alternatives.
This syntax puts the constraints and attributes on the same horizontal line as
the instruction assembly template.
As an example
@smallexample
@group
(define_insn_and_split ""
[(set (match_operand:SI 0 "nonimmediate_operand" "=r,k,r,r,r,r")
(match_operand:SI 1 "aarch64_mov_operand" " r,r,k,M,n,Usv"))]
""
"@@
mov\\t%w0, %w1
mov\\t%w0, %w1
mov\\t%w0, %w1
mov\\t%w0, %1
#
* return aarch64_output_sve_cnt_immediate ('cnt', '%x0', operands[1]);"
"&& true"
[(const_int 0)]
@{
aarch64_expand_mov_immediate (operands[0], operands[1]);
DONE;
@}
[(set_attr "type" "mov_reg,mov_reg,mov_reg,mov_imm,mov_imm,mov_imm")
(set_attr "arch" "*,*,*,*,*,sve")
(set_attr "length" "4,4,4,4,*, 4")
]
)
@end group
@end smallexample
can be better expressed as:
@smallexample
@group
(define_insn_and_split ""
[(set (match_operand:SI 0 "nonimmediate_operand")
(match_operand:SI 1 "aarch64_mov_operand"))]
""
@{@@ [cons: =0, 1; attrs: type, arch, length]
[r , r ; mov_reg , * , 4] mov\t%w0, %w1
[k , r ; mov_reg , * , 4] ^
[r , k ; mov_reg , * , 4] ^
[r , M ; mov_imm , * , 4] mov\t%w0, %1
[r , n ; mov_imm , * , *] #
[r , Usv; mov_imm , sve , 4] << aarch64_output_sve_cnt_immediate ("cnt", "%x0", operands[1]);
@}
"&& true"
[(const_int 0)]
@{
aarch64_expand_mov_immediate (operands[0], operands[1]);
DONE;
@}
)
@end group
@end smallexample
The syntax rules are as follows:
@itemize @bullet
@item
Templates must start with @samp{@{@@} to use the new syntax.
@item
@samp{@{@@} is followed by a layout in square brackets which is @samp{cons:}
followed by a comma-separated list of @code{match_operand}/@code{match_scratch}
operand numbers, then a semicolon, followed by the same for attributes
(@samp{attrs:}). Operand modifiers like @code{=} and @code{+} can be placed
before an operand number.
Both sections are optional (so you can use only @samp{cons}, or only
@samp{attrs}, or both), and @samp{cons} must come before @samp{attrs} if
present.
@item
Each alternative begins with any amount of whitespace.
@item
Following the whitespace is a comma-separated list of "constraints" and/or
"attributes" within brackets @code{[]}, with sections separated by a semicolon.
@item
Should you want to copy the previous asm line, the symbol @code{^} can be used.
This allows less copy pasting between alternative and reduces the number of
lines to update on changes.
@item
When using C functions for output, the idiom @samp{* return @var{function};}
can be replaced with the shorthand @samp{<< @var{function};}.
@item
Following the closing @samp{]} is any amount of whitespace, and then the actual
asm output.
@item
Spaces are allowed in the list (they will simply be removed).
@item
All constraint alternatives should be specified. For example, a list of
of three blank alternatives should be written @samp{[,,]} rather than
@samp{[]}.
@item
All attribute alternatives should be non-empty, with @samp{*}
representing the default attribute value. For example, a list of three
default attribute values should be written @samp{[*,*,*]} rather than
@samp{[]}.
@item
Within an @samp{@{@@} block both multiline and singleline C comments are
allowed, but when used outside of a C block they must be the only non-whitespace
blocks on the line.
@item
Within an @samp{@{@@} block, any iterators that do not get expanded will result
in an error. If for some reason it is required to have @code{<} or @code{>} in
the output then these must be escaped using @samp{\}.
@item
It is possible to use the @samp{attrs} list to specify some attributes and to
use the normal @code{set_attr} syntax to specify other attributes. There must
not be any overlap between the two lists.
In other words, the following is valid:
@smallexample
@group
(define_insn_and_split ""
[(set (match_operand:SI 0 "nonimmediate_operand")
(match_operand:SI 1 "aarch64_mov_operand"))]
""
@{@@ [cons: 0, 1; attrs: type, arch, length]@}
@dots{}
[(set_attr "foo" "mov_imm")]
)
@end group
@end smallexample
but this is not valid:
@smallexample
@group
(define_insn_and_split ""
[(set (match_operand:SI 0 "nonimmediate_operand")
(match_operand:SI 1 "aarch64_mov_operand"))]
""
@{@@ [cons: 0, 1; attrs: type, arch, length]@}
@dots{}
[(set_attr "arch" "bar")
(set_attr "foo" "mov_imm")]
)
@end group
@end smallexample
because it specifies @code{arch} twice.
@end itemize
@node Predicates
@section Predicates
@cindex predicates
@cindex operand predicates
@cindex operator predicates
A predicate determines whether a @code{match_operand} or
@code{match_operator} expression matches, and therefore whether the
surrounding instruction pattern will be used for that combination of
operands. GCC has a number of machine-independent predicates, and you
can define machine-specific predicates as needed. By convention,
predicates used with @code{match_operand} have names that end in
@samp{_operand}, and those used with @code{match_operator} have names
that end in @samp{_operator}.
All predicates are boolean functions (in the mathematical sense) of
two arguments: the RTL expression that is being considered at that
position in the instruction pattern, and the machine mode that the
@code{match_operand} or @code{match_operator} specifies. In this
section, the first argument is called @var{op} and the second argument
@var{mode}. Predicates can be called from C as ordinary two-argument
functions; this can be useful in output templates or other
machine-specific code.
Operand predicates can allow operands that are not actually acceptable
to the hardware, as long as the constraints give reload the ability to
fix them up (@pxref{Constraints}). However, GCC will usually generate
better code if the predicates specify the requirements of the machine
instructions as closely as possible. Reload cannot fix up operands
that must be constants (``immediate operands''); you must use a
predicate that allows only constants, or else enforce the requirement
in the extra condition.
@cindex predicates and machine modes
@cindex normal predicates
@cindex special predicates
Most predicates handle their @var{mode} argument in a uniform manner.
If @var{mode} is @code{VOIDmode} (unspecified), then @var{op} can have
any mode. If @var{mode} is anything else, then @var{op} must have the
same mode, unless @var{op} is a @code{CONST_INT} or integer
@code{CONST_DOUBLE}. These RTL expressions always have
@code{VOIDmode}, so it would be counterproductive to check that their
mode matches. Instead, predicates that accept @code{CONST_INT} and/or
integer @code{CONST_DOUBLE} check that the value stored in the
constant will fit in the requested mode.
Predicates with this behavior are called @dfn{normal}.
@command{genrecog} can optimize the instruction recognizer based on
knowledge of how normal predicates treat modes. It can also diagnose
certain kinds of common errors in the use of normal predicates; for
instance, it is almost always an error to use a normal predicate
without specifying a mode.
Predicates that do something different with their @var{mode} argument
are called @dfn{special}. The generic predicates
@code{address_operand} and @code{pmode_register_operand} are special
predicates. @command{genrecog} does not do any optimizations or
diagnosis when special predicates are used.
@menu
* Machine-Independent Predicates:: Predicates available to all back ends.
* Defining Predicates:: How to write machine-specific predicate
functions.
@end menu
@node Machine-Independent Predicates
@subsection Machine-Independent Predicates
@cindex machine-independent predicates
@cindex generic predicates
These are the generic predicates available to all back ends. They are
defined in @file{recog.cc}. The first category of predicates allow
only constant, or @dfn{immediate}, operands.
@defun immediate_operand
This predicate allows any sort of constant that fits in @var{mode}.
It is an appropriate choice for instructions that take operands that
must be constant.
@end defun
@defun const_int_operand
This predicate allows any @code{CONST_INT} expression that fits in
@var{mode}. It is an appropriate choice for an immediate operand that
does not allow a symbol or label.
@end defun
@defun const_double_operand
This predicate accepts any @code{CONST_DOUBLE} expression that has
exactly @var{mode}. If @var{mode} is @code{VOIDmode}, it will also
accept @code{CONST_INT}. It is intended for immediate floating point
constants.
@end defun
@noindent
The second category of predicates allow only some kind of machine
register.
@defun register_operand
This predicate allows any @code{REG} or @code{SUBREG} expression that
is valid for @var{mode}. It is often suitable for arithmetic
instruction operands on a RISC machine.
@end defun
@defun pmode_register_operand
This is a slight variant on @code{register_operand} which works around
a limitation in the machine-description reader.
@smallexample
(match_operand @var{n} "pmode_register_operand" @var{constraint})
@end smallexample
@noindent
means exactly what
@smallexample
(match_operand:P @var{n} "register_operand" @var{constraint})
@end smallexample
@noindent
would mean, if the machine-description reader accepted @samp{:P}
mode suffixes. Unfortunately, it cannot, because @code{Pmode} is an
alias for some other mode, and might vary with machine-specific
options. @xref{Misc}.
@end defun
@defun scratch_operand
This predicate allows hard registers and @code{SCRATCH} expressions,
but not pseudo-registers. It is used internally by @code{match_scratch};
it should not be used directly.
@end defun
@noindent
The third category of predicates allow only some kind of memory reference.
@defun memory_operand
This predicate allows any valid reference to a quantity of mode
@var{mode} in memory, as determined by the weak form of
@code{GO_IF_LEGITIMATE_ADDRESS} (@pxref{Addressing Modes}).
@end defun
@defun address_operand
This predicate is a little unusual; it allows any operand that is a
valid expression for the @emph{address} of a quantity of mode
@var{mode}, again determined by the weak form of
@code{GO_IF_LEGITIMATE_ADDRESS}. To first order, if
@samp{@w{(mem:@var{mode} (@var{exp}))}} is acceptable to
@code{memory_operand}, then @var{exp} is acceptable to
@code{address_operand}. Note that @var{exp} does not necessarily have
the mode @var{mode}.
@end defun
@defun indirect_operand
This is a stricter form of @code{memory_operand} which allows only
memory references with a @code{general_operand} as the address
expression. New uses of this predicate are discouraged, because
@code{general_operand} is very permissive, so it's hard to tell what
an @code{indirect_operand} does or does not allow. If a target has
different requirements for memory operands for different instructions,
it is better to define target-specific predicates which enforce the
hardware's requirements explicitly.
@end defun
@defun push_operand
This predicate allows a memory reference suitable for pushing a value
onto the stack. This will be a @code{MEM} which refers to
@code{stack_pointer_rtx}, with a side effect in its address expression
(@pxref{Incdec}); which one is determined by the
@code{STACK_PUSH_CODE} macro (@pxref{Frame Layout}).
@end defun
@defun pop_operand
This predicate allows a memory reference suitable for popping a value
off the stack. Again, this will be a @code{MEM} referring to
@code{stack_pointer_rtx}, with a side effect in its address
expression. However, this time @code{STACK_POP_CODE} is expected.
@end defun
@noindent
The fourth category of predicates allow some combination of the above
operands.
@defun nonmemory_operand
This predicate allows any immediate or register operand valid for @var{mode}.
@end defun
@defun nonimmediate_operand
This predicate allows any register or memory operand valid for @var{mode}.
@end defun
@defun general_operand
This predicate allows any immediate, register, or memory operand
valid for @var{mode}.
@end defun
@noindent
Finally, there are two generic operator predicates.
@defun comparison_operator
This predicate matches any expression which performs an arithmetic
comparison in @var{mode}; that is, @code{COMPARISON_P} is true for the
expression code.
@end defun
@defun ordered_comparison_operator
This predicate matches any expression which performs an arithmetic
comparison in @var{mode} and whose expression code is valid for integer
modes; that is, the expression code will be one of @code{eq}, @code{ne},
@code{lt}, @code{ltu}, @code{le}, @code{leu}, @code{gt}, @code{gtu},
@code{ge}, @code{geu}.
@end defun
@node Defining Predicates
@subsection Defining Machine-Specific Predicates
@cindex defining predicates
@findex define_predicate
@findex define_special_predicate
Many machines have requirements for their operands that cannot be
expressed precisely using the generic predicates. You can define
additional predicates using @code{define_predicate} and
@code{define_special_predicate} expressions. These expressions have
three operands:
@itemize @bullet
@item
The name of the predicate, as it will be referred to in
@code{match_operand} or @code{match_operator} expressions.
@item
An RTL expression which evaluates to true if the predicate allows the
operand @var{op}, false if it does not. This expression can only use
the following RTL codes:
@table @code
@item MATCH_OPERAND
When written inside a predicate expression, a @code{MATCH_OPERAND}
expression evaluates to true if the predicate it names would allow
@var{op}. The operand number and constraint are ignored. Due to
limitations in @command{genrecog}, you can only refer to generic
predicates and predicates that have already been defined.
@item MATCH_CODE
This expression evaluates to true if @var{op} or a specified
subexpression of @var{op} has one of a given list of RTX codes.
The first operand of this expression is a string constant containing a
comma-separated list of RTX code names (in lower case). These are the
codes for which the @code{MATCH_CODE} will be true.
The second operand is a string constant which indicates what
subexpression of @var{op} to examine. If it is absent or the empty
string, @var{op} itself is examined. Otherwise, the string constant
must be a sequence of digits and/or lowercase letters. Each character
indicates a subexpression to extract from the current expression; for
the first character this is @var{op}, for the second and subsequent
characters it is the result of the previous character. A digit
@var{n} extracts @samp{@w{XEXP (@var{e}, @var{n})}}; a letter @var{l}
extracts @samp{@w{XVECEXP (@var{e}, 0, @var{n})}} where @var{n} is the
alphabetic ordinal of @var{l} (0 for `a', 1 for 'b', and so on). The
@code{MATCH_CODE} then examines the RTX code of the subexpression
extracted by the complete string. It is not possible to extract
components of an @code{rtvec} that is not at position 0 within its RTX
object.
@item MATCH_TEST
This expression has one operand, a string constant containing a C
expression. The predicate's arguments, @var{op} and @var{mode}, are
available with those names in the C expression. The @code{MATCH_TEST}
evaluates to true if the C expression evaluates to a nonzero value.
@code{MATCH_TEST} expressions must not have side effects.
@item AND
@itemx IOR
@itemx NOT
@itemx IF_THEN_ELSE
The basic @samp{MATCH_} expressions can be combined using these
logical operators, which have the semantics of the C operators
@samp{&&}, @samp{||}, @samp{!}, and @samp{@w{? :}} respectively. As
in Common Lisp, you may give an @code{AND} or @code{IOR} expression an
arbitrary number of arguments; this has exactly the same effect as
writing a chain of two-argument @code{AND} or @code{IOR} expressions.
@end table
@item
An optional block of C code, which should execute
@samp{@w{return true}} if the predicate is found to match and
@samp{@w{return false}} if it does not. It must not have any side
effects. The predicate arguments, @var{op} and @var{mode}, are
available with those names.
If a code block is present in a predicate definition, then the RTL
expression must evaluate to true @emph{and} the code block must
execute @samp{@w{return true}} for the predicate to allow the operand.
The RTL expression is evaluated first; do not re-check anything in the
code block that was checked in the RTL expression.
@end itemize
The program @command{genrecog} scans @code{define_predicate} and
@code{define_special_predicate} expressions to determine which RTX
codes are possibly allowed. You should always make this explicit in
the RTL predicate expression, using @code{MATCH_OPERAND} and
@code{MATCH_CODE}.
Here is an example of a simple predicate definition, from the IA64
machine description:
@smallexample
@group
;; @r{True if @var{op} is a @code{SYMBOL_REF} which refers to the sdata section.}
(define_predicate "small_addr_symbolic_operand"
(and (match_code "symbol_ref")
(match_test "SYMBOL_REF_SMALL_ADDR_P (op)")))
@end group
@end smallexample
@noindent
And here is another, showing the use of the C block.
@smallexample
@group
;; @r{True if @var{op} is a register operand that is (or could be) a GR reg.}
(define_predicate "gr_register_operand"
(match_operand 0 "register_operand")
@{
unsigned int regno;
if (GET_CODE (op) == SUBREG)
op = SUBREG_REG (op);
regno = REGNO (op);
return (regno >= FIRST_PSEUDO_REGISTER || GENERAL_REGNO_P (regno));
@})
@end group
@end smallexample
Predicates written with @code{define_predicate} automatically include
a test that @var{mode} is @code{VOIDmode}, or @var{op} has the same
mode as @var{mode}, or @var{op} is a @code{CONST_INT} or
@code{CONST_DOUBLE}. They do @emph{not} check specifically for
integer @code{CONST_DOUBLE}, nor do they test that the value of either
kind of constant fits in the requested mode. This is because
target-specific predicates that take constants usually have to do more
stringent value checks anyway. If you need the exact same treatment
of @code{CONST_INT} or @code{CONST_DOUBLE} that the generic predicates
provide, use a @code{MATCH_OPERAND} subexpression to call
@code{const_int_operand}, @code{const_double_operand}, or
@code{immediate_operand}.
Predicates written with @code{define_special_predicate} do not get any
automatic mode checks, and are treated as having special mode handling
by @command{genrecog}.
The program @command{genpreds} is responsible for generating code to
test predicates. It also writes a header file containing function
declarations for all machine-specific predicates. It is not necessary
to declare these predicates in @file{@var{cpu}-protos.h}.
@end ifset
@c Most of this node appears by itself (in a different place) even
@c when the INTERNALS flag is clear. Passages that require the internals
@c manual's context are conditionalized to appear only in the internals manual.
@ifset INTERNALS
@node Constraints
@section Operand Constraints
@cindex operand constraints
@cindex constraints
Each @code{match_operand} in an instruction pattern can specify
constraints for the operands allowed. The constraints allow you to
fine-tune matching within the set of operands allowed by the
predicate.
@end ifset
@ifclear INTERNALS
@node Constraints
@section Constraints for @code{asm} Operands
@cindex operand constraints, @code{asm}
@cindex constraints, @code{asm}
@cindex @code{asm} constraints
Here are specific details on what constraint letters you can use with
@code{asm} operands.
@end ifclear
Constraints can say whether
an operand may be in a register, and which kinds of register; whether the
operand can be a memory reference, and which kinds of address; whether the
operand may be an immediate constant, and which possible values it may
have. Constraints can also require two operands to match.
Side-effects aren't allowed in operands of inline @code{asm}, unless
@samp{<} or @samp{>} constraints are used, because there is no guarantee
that the side effects will happen exactly once in an instruction that can update
the addressing register.
@ifset INTERNALS
@menu
* Simple Constraints:: Basic use of constraints.
* Multi-Alternative:: When an insn has two alternative constraint-patterns.
* Class Preferences:: Constraints guide which hard register to put things in.
* Modifiers:: More precise control over effects of constraints.
* Machine Constraints:: Existing constraints for some particular machines.
* Disable Insn Alternatives:: Disable insn alternatives using attributes.
* Define Constraints:: How to define machine-specific constraints.
* C Constraint Interface:: How to test constraints from C code.
@end menu
@end ifset
@ifclear INTERNALS
@menu
* Simple Constraints:: Basic use of constraints.
* Multi-Alternative:: When an insn has two alternative constraint-patterns.
* Modifiers:: More precise control over effects of constraints.
* Machine Constraints:: Special constraints for some particular machines.
@end menu
@end ifclear
@node Simple Constraints
@subsection Simple Constraints
@cindex simple constraints
The simplest kind of constraint is a string full of letters, each of
which describes one kind of operand that is permitted. Here are
the letters that are allowed:
@table @asis
@item whitespace
Whitespace characters are ignored and can be inserted at any position
except the first. This enables each alternative for different operands to
be visually aligned in the machine description even if they have different
number of constraints and modifiers.
@cindex @samp{m} in constraint
@cindex memory references in constraints
@item @samp{m}
A memory operand is allowed, with any kind of address that the machine
supports in general.
Note that the letter used for the general memory constraint can be
re-defined by a back end using the @code{TARGET_MEM_CONSTRAINT} macro.
@cindex offsettable address
@cindex @samp{o} in constraint
@item @samp{o}
A memory operand is allowed, but only if the address is
@dfn{offsettable}. This means that adding a small integer (actually,
the width in bytes of the operand, as determined by its machine mode)
may be added to the address and the result is also a valid memory
address.
@cindex autoincrement/decrement addressing
For example, an address which is constant is offsettable; so is an
address that is the sum of a register and a constant (as long as a
slightly larger constant is also within the range of address-offsets
supported by the machine); but an autoincrement or autodecrement
address is not offsettable. More complicated indirect/indexed
addresses may or may not be offsettable depending on the other
addressing modes that the machine supports.
Note that in an output operand which can be matched by another
operand, the constraint letter @samp{o} is valid only when accompanied
by both @samp{<} (if the target machine has predecrement addressing)
and @samp{>} (if the target machine has preincrement addressing).
@cindex @samp{V} in constraint
@item @samp{V}
A memory operand that is not offsettable. In other words, anything that
would fit the @samp{m} constraint but not the @samp{o} constraint.
@cindex @samp{<} in constraint
@item @samp{<}
A memory operand with autodecrement addressing (either predecrement or
postdecrement) is allowed. In inline @code{asm} this constraint is only
allowed if the operand is used exactly once in an instruction that can
handle the side effects. Not using an operand with @samp{<} in constraint
string in the inline @code{asm} pattern at all or using it in multiple
instructions isn't valid, because the side effects wouldn't be performed
or would be performed more than once. Furthermore, on some targets
the operand with @samp{<} in constraint string must be accompanied by
special instruction suffixes like @code{%U0} instruction suffix on PowerPC
or @code{%P0} on IA-64.
@cindex @samp{>} in constraint
@item @samp{>}
A memory operand with autoincrement addressing (either preincrement or
postincrement) is allowed. In inline @code{asm} the same restrictions
as for @samp{<} apply.
@cindex @samp{r} in constraint
@cindex registers in constraints
@item @samp{r}
A register operand is allowed provided that it is in a general
register.
@cindex constants in constraints
@cindex @samp{i} in constraint
@item @samp{i}
An immediate integer operand (one with constant value) is allowed.
This includes symbolic constants whose values will be known only at
assembly time or later.
@cindex @samp{n} in constraint
@item @samp{n}
An immediate integer operand with a known numeric value is allowed.
Many systems cannot support assembly-time constants for operands less
than a word wide. Constraints for these operands should use @samp{n}
rather than @samp{i}.
@cindex @samp{I} in constraint
@item @samp{I}, @samp{J}, @samp{K}, @dots{} @samp{P}
Other letters in the range @samp{I} through @samp{P} may be defined in
a machine-dependent fashion to permit immediate integer operands with
explicit integer values in specified ranges. For example, on the
68000, @samp{I} is defined to stand for the range of values 1 to 8.
This is the range permitted as a shift count in the shift
instructions.
@cindex @samp{E} in constraint
@item @samp{E}
An immediate floating operand (expression code @code{const_double}) is
allowed, but only if the target floating point format is the same as
that of the host machine (on which the compiler is running).
@cindex @samp{F} in constraint
@item @samp{F}
An immediate floating operand (expression code @code{const_double} or
@code{const_vector}) is allowed.
@cindex @samp{G} in constraint
@cindex @samp{H} in constraint
@item @samp{G}, @samp{H}
@samp{G} and @samp{H} may be defined in a machine-dependent fashion to
permit immediate floating operands in particular ranges of values.
@cindex @samp{s} in constraint
@item @samp{s}
An immediate integer operand whose value is not an explicit integer is
allowed.
This might appear strange; if an insn allows a constant operand with a
value not known at compile time, it certainly must allow any known
value. So why use @samp{s} instead of @samp{i}? Sometimes it allows
better code to be generated.
For example, on the 68000 in a fullword instruction it is possible to
use an immediate operand; but if the immediate value is between @minus{}128
and 127, better code results from loading the value into a register and
using the register. This is because the load into the register can be
done with a @samp{moveq} instruction. We arrange for this to happen
by defining the letter @samp{K} to mean ``any integer outside the
range @minus{}128 to 127'', and then specifying @samp{Ks} in the operand
constraints.
@cindex @samp{g} in constraint
@item @samp{g}
Any register, memory or immediate integer operand is allowed, except for
registers that are not general registers.
@cindex @samp{X} in constraint
@item @samp{X}
@ifset INTERNALS
Any operand whatsoever is allowed, even if it does not satisfy
@code{general_operand}. This is normally used in the constraint of
a @code{match_scratch} when certain alternatives will not actually
require a scratch register.
@end ifset
@ifclear INTERNALS
Any operand whatsoever is allowed.
@end ifclear
@cindex @samp{0} in constraint
@cindex digits in constraint
@item @samp{0}, @samp{1}, @samp{2}, @dots{} @samp{9}
An operand that matches the specified operand number is allowed. If a
digit is used together with letters within the same alternative, the
digit should come last.
This number is allowed to be more than a single digit. If multiple
digits are encountered consecutively, they are interpreted as a single
decimal integer. There is scant chance for ambiguity, since to-date
it has never been desirable that @samp{10} be interpreted as matching
either operand 1 @emph{or} operand 0. Should this be desired, one
can use multiple alternatives instead.
@cindex matching constraint
@cindex constraint, matching
This is called a @dfn{matching constraint} and what it really means is
that the assembler has only a single operand that fills two roles
@ifset INTERNALS
considered separate in the RTL insn. For example, an add insn has two
input operands and one output operand in the RTL, but on most CISC
@end ifset
@ifclear INTERNALS
which @code{asm} distinguishes. For example, an add instruction uses
two input operands and an output operand, but on most CISC
@end ifclear
machines an add instruction really has only two operands, one of them an
input-output operand:
@smallexample
addl #35,r12
@end smallexample
Matching constraints are used in these circumstances.
More precisely, the two operands that match must include one input-only
operand and one output-only operand. Moreover, the digit must be a
smaller number than the number of the operand that uses it in the
constraint.
@ifset INTERNALS
For operands to match in a particular case usually means that they
are identical-looking RTL expressions. But in a few special cases
specific kinds of dissimilarity are allowed. For example, @code{*x}
as an input operand will match @code{*x++} as an output operand.
For proper results in such cases, the output template should always
use the output-operand's number when printing the operand.
@end ifset
@cindex load address instruction
@cindex push address instruction
@cindex address constraints
@cindex @samp{p} in constraint
@item @samp{p}
An operand that is a valid memory address is allowed. This is
for ``load address'' and ``push address'' instructions.
@findex address_operand
@samp{p} in the constraint must be accompanied by @code{address_operand}
as the predicate in the @code{match_operand}. This predicate interprets
the mode specified in the @code{match_operand} as the mode of the memory
reference for which the address would be valid.
@cindex other register constraints
@cindex extensible constraints
@item @var{other-letters}
Other letters can be defined in machine-dependent fashion to stand for
particular classes of registers or other arbitrary operand types.
@samp{d}, @samp{a} and @samp{f} are defined on the 68000/68020 to stand
for data, address and floating point registers.
@end table
@ifset INTERNALS
In order to have valid assembler code, each operand must satisfy
its constraint. But a failure to do so does not prevent the pattern
from applying to an insn. Instead, it directs the compiler to modify
the code so that the constraint will be satisfied. Usually this is
done by copying an operand into a register.
Contrast, therefore, the two instruction patterns that follow:
@smallexample
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r")
(plus:SI (match_dup 0)
(match_operand:SI 1 "general_operand" "r")))]
""
"@dots{}")
@end smallexample
@noindent
which has two operands, one of which must appear in two places, and
@smallexample
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r")
(plus:SI (match_operand:SI 1 "general_operand" "0")
(match_operand:SI 2 "general_operand" "r")))]
""
"@dots{}")
@end smallexample
@noindent
which has three operands, two of which are required by a constraint to be
identical. If we are considering an insn of the form
@smallexample
(insn @var{n} @var{prev} @var{next}
(set (reg:SI 3)
(plus:SI (reg:SI 6) (reg:SI 109)))
@dots{})
@end smallexample
@noindent
the first pattern would not apply at all, because this insn does not
contain two identical subexpressions in the right place. The pattern would
say, ``That does not look like an add instruction; try other patterns''.
The second pattern would say, ``Yes, that's an add instruction, but there
is something wrong with it''. It would direct the reload pass of the
compiler to generate additional insns to make the constraint true. The
results might look like this:
@smallexample
(insn @var{n2} @var{prev} @var{n}
(set (reg:SI 3) (reg:SI 6))
@dots{})
(insn @var{n} @var{n2} @var{next}
(set (reg:SI 3)
(plus:SI (reg:SI 3) (reg:SI 109)))
@dots{})
@end smallexample
It is up to you to make sure that each operand, in each pattern, has
constraints that can handle any RTL expression that could be present for
that operand. (When multiple alternatives are in use, each pattern must,
for each possible combination of operand expressions, have at least one
alternative which can handle that combination of operands.) The
constraints don't need to @emph{allow} any possible operand---when this is
the case, they do not constrain---but they must at least point the way to
reloading any possible operand so that it will fit.
@itemize @bullet
@item
If the constraint accepts whatever operands the predicate permits,
there is no problem: reloading is never necessary for this operand.
For example, an operand whose constraints permit everything except
registers is safe provided its predicate rejects registers.
An operand whose predicate accepts only constant values is safe
provided its constraints include the letter @samp{i}. If any possible
constant value is accepted, then nothing less than @samp{i} will do;
if the predicate is more selective, then the constraints may also be
more selective.
@item
Any operand expression can be reloaded by copying it into a register.
So if an operand's constraints allow some kind of register, it is
certain to be safe. It need not permit all classes of registers; the
compiler knows how to copy a register into another register of the
proper class in order to make an instruction valid.
@cindex nonoffsettable memory reference
@cindex memory reference, nonoffsettable
@item
A nonoffsettable memory reference can be reloaded by copying the
address into a register. So if the constraint uses the letter
@samp{o}, all memory references are taken care of.
@item
A constant operand can be reloaded by allocating space in memory to
hold it as preinitialized data. Then the memory reference can be used
in place of the constant. So if the constraint uses the letters
@samp{o} or @samp{m}, constant operands are not a problem.
@item
If the constraint permits a constant and a pseudo register used in an insn
was not allocated to a hard register and is equivalent to a constant,
the register will be replaced with the constant. If the predicate does
not permit a constant and the insn is re-recognized for some reason, the
compiler will crash. Thus the predicate must always recognize any
objects allowed by the constraint.
@end itemize
If the operand's predicate can recognize registers, but the constraint does
not permit them, it can make the compiler crash. When this operand happens
to be a register, the reload pass will be stymied, because it does not know
how to copy a register temporarily into memory.
If the predicate accepts a unary operator, the constraint applies to the
operand. For example, the MIPS processor at ISA level 3 supports an
instruction which adds two registers in @code{SImode} to produce a
@code{DImode} result, but only if the registers are correctly sign
extended. This predicate for the input operands accepts a
@code{sign_extend} of an @code{SImode} register. Write the constraint
to indicate the type of register that is required for the operand of the
@code{sign_extend}.
@end ifset
@node Multi-Alternative
@subsection Multiple Alternative Constraints
@cindex multiple alternative constraints
Sometimes a single instruction has multiple alternative sets of possible
operands. For example, on the 68000, a logical-or instruction can combine
register or an immediate value into memory, or it can combine any kind of
operand into a register; but it cannot combine one memory location into
another.
These constraints are represented as multiple alternatives. An alternative
can be described by a series of letters for each operand. The overall
constraint for an operand is made from the letters for this operand
from the first alternative, a comma, the letters for this operand from
the second alternative, a comma, and so on until the last alternative.
All operands for a single instruction must have the same number of
alternatives.
@ifset INTERNALS
Here is how it is done for fullword logical-or on the 68000:
@smallexample
(define_insn "iorsi3"
[(set (match_operand:SI 0 "general_operand" "=m,d")
(ior:SI (match_operand:SI 1 "general_operand" "%0,0")
(match_operand:SI 2 "general_operand" "dKs,dmKs")))]
@dots{})
@end smallexample
The first alternative has @samp{m} (memory) for operand 0, @samp{0} for
operand 1 (meaning it must match operand 0), and @samp{dKs} for operand
2. The second alternative has @samp{d} (data register) for operand 0,
@samp{0} for operand 1, and @samp{dmKs} for operand 2. The @samp{=} and
@samp{%} in the constraints apply to all the alternatives; their
meaning is explained in a later section (@pxref{Modifiers}).
If all the operands fit any one alternative, the instruction is valid.
Otherwise, for each alternative, the compiler counts how many instructions
must be added to copy the operands so that that alternative applies.
The alternative requiring the least copying is chosen. If two alternatives
need the same amount of copying, the one that comes first is chosen.
These choices can be altered with the @samp{?} and @samp{!} characters:
@table @code
@cindex @samp{?} in constraint
@cindex question mark
@item ?
Disparage slightly the alternative that the @samp{?} appears in,
as a choice when no alternative applies exactly. The compiler regards
this alternative as one unit more costly for each @samp{?} that appears
in it.
@cindex @samp{!} in constraint
@cindex exclamation point
@item !
Disparage severely the alternative that the @samp{!} appears in.
This alternative can still be used if it fits without reloading,
but if reloading is needed, some other alternative will be used.
@cindex @samp{^} in constraint
@cindex caret
@item ^
This constraint is analogous to @samp{?} but it disparages slightly
the alternative only if the operand with the @samp{^} needs a reload.
@cindex @samp{$} in constraint
@cindex dollar sign
@item $
This constraint is analogous to @samp{!} but it disparages severely
the alternative only if the operand with the @samp{$} needs a reload.
@end table
When an insn pattern has multiple alternatives in its constraints, often
the appearance of the assembler code is determined mostly by which
alternative was matched. When this is so, the C code for writing the
assembler code can use the variable @code{which_alternative}, which is
the ordinal number of the alternative that was actually satisfied (0 for
the first, 1 for the second alternative, etc.). @xref{Output Statement}.
@end ifset
@ifclear INTERNALS
So the first alternative for the 68000's logical-or could be written as
@code{"+m" (output) : "ir" (input)}. The second could be @code{"+r"
(output): "irm" (input)}. However, the fact that two memory locations
cannot be used in a single instruction prevents simply using @code{"+rm"
(output) : "irm" (input)}. Using multi-alternatives, this might be
written as @code{"+m,r" (output) : "ir,irm" (input)}. This describes
all the available alternatives to the compiler, allowing it to choose
the most efficient one for the current conditions.
There is no way within the template to determine which alternative was
chosen. However you may be able to wrap your @code{asm} statements with
builtins such as @code{__builtin_constant_p} to achieve the desired results.
@end ifclear
@ifset INTERNALS
@node Class Preferences
@subsection Register Class Preferences
@cindex class preference constraints
@cindex register class preference constraints
@cindex voting between constraint alternatives
The operand constraints have another function: they enable the compiler
to decide which kind of hardware register a pseudo register is best
allocated to. The compiler examines the constraints that apply to the
insns that use the pseudo register, looking for the machine-dependent
letters such as @samp{d} and @samp{a} that specify classes of registers.
The pseudo register is put in whichever class gets the most ``votes''.
The constraint letters @samp{g} and @samp{r} also vote: they vote in
favor of a general register. The machine description says which registers
are considered general.
Of course, on some machines all registers are equivalent, and no register
classes are defined. Then none of this complexity is relevant.
@end ifset
@node Modifiers
@subsection Constraint Modifier Characters
@cindex modifiers in constraints
@cindex constraint modifier characters
@c prevent bad page break with this line
Here are constraint modifier characters.
@table @samp
@cindex @samp{=} in constraint
@item =
Means that this operand is written to by this instruction:
the previous value is discarded and replaced by new data.
@cindex @samp{+} in constraint
@item +
Means that this operand is both read and written by the instruction.
When the compiler fixes up the operands to satisfy the constraints,
it needs to know which operands are read by the instruction and
which are written by it. @samp{=} identifies an operand which is only
written; @samp{+} identifies an operand that is both read and written; all
other operands are assumed to only be read.
If you specify @samp{=} or @samp{+} in a constraint, you put it in the
first character of the constraint string.
@cindex @samp{&} in constraint
@cindex earlyclobber operand
@item &
Means (in a particular alternative) that this operand is an
@dfn{earlyclobber} operand, which is written before the instruction is
finished using the input operands. Therefore, this operand may not lie
in a register that is read by the instruction or as part of any memory
address.
@samp{&} applies only to the alternative in which it is written. In
constraints with multiple alternatives, sometimes one alternative
requires @samp{&} while others do not. See, for example, the
@samp{movdf} insn of the 68000.
An operand which is read by the instruction can be tied to an earlyclobber
operand if its only use as an input occurs before the early result is
written. Adding alternatives of this form often allows GCC to produce
better code when only some of the read operands can be affected by the
earlyclobber. See, for example, the @samp{mulsi3} insn of the ARM@.
Furthermore, if the @dfn{earlyclobber} operand is also a read/write
operand, then that operand is written only after it's used.
@samp{&} does not obviate the need to write @samp{=} or @samp{+}. As
@dfn{earlyclobber} operands are always written, a read-only
@dfn{earlyclobber} operand is ill-formed and will be rejected by the
compiler.
@cindex @samp{%} in constraint
@item %
Declares the instruction to be commutative for this operand and the
following operand. This means that the compiler may interchange the
two operands if that is the cheapest way to make all operands fit the
constraints. @samp{%} applies to all alternatives and must appear as
the first character in the constraint. Only read-only operands can use
@samp{%}.
@ifset INTERNALS
This is often used in patterns for addition instructions
that really have only two operands: the result must go in one of the
arguments. Here for example, is how the 68000 halfword-add
instruction is defined:
@smallexample
(define_insn "addhi3"
[(set (match_operand:HI 0 "general_operand" "=m,r")
(plus:HI (match_operand:HI 1 "general_operand" "%0,0")
(match_operand:HI 2 "general_operand" "di,g")))]
@dots{})
@end smallexample
@end ifset
GCC can only handle one commutative pair in an asm; if you use more,
the compiler may fail. Note that you need not use the modifier if
the two alternatives are strictly identical; this would only waste
time in the reload pass.
@ifset INTERNALS
The modifier is not operational after
register allocation, so the result of @code{define_peephole2}
and @code{define_split}s performed after reload cannot rely on
@samp{%} to make the intended insn match.
@cindex @samp{#} in constraint
@item #
Says that all following characters, up to the next comma, are to be
ignored as a constraint. They are significant only for choosing
register preferences.
@cindex @samp{*} in constraint
@item *
Says that the following character should be ignored when choosing
register preferences. @samp{*} has no effect on the meaning of the
constraint as a constraint, and no effect on reloading. For LRA
@samp{*} additionally disparages slightly the alternative if the
following character matches the operand.
Here is an example: the 68000 has an instruction to sign-extend a
halfword in a data register, and can also sign-extend a value by
copying it into an address register. While either kind of register is
acceptable, the constraints on an address-register destination are
less strict, so it is best if register allocation makes an address
register its goal. Therefore, @samp{*} is used so that the @samp{d}
constraint letter (for data register) is ignored when computing
register preferences.
@smallexample
(define_insn "extendhisi2"
[(set (match_operand:SI 0 "general_operand" "=*d,a")
(sign_extend:SI
(match_operand:HI 1 "general_operand" "0,g")))]
@dots{})
@end smallexample
@end ifset
@end table
@node Machine Constraints
@subsection Constraints for Particular Machines
@cindex machine specific constraints
@cindex constraints, machine specific
Whenever possible, you should use the general-purpose constraint letters
in @code{asm} arguments, since they will convey meaning more readily to
people reading your code. Failing that, use the constraint letters
that usually have very similar meanings across architectures. The most
commonly used constraints are @samp{m} and @samp{r} (for memory and
general-purpose registers respectively; @pxref{Simple Constraints}), and
@samp{I}, usually the letter indicating the most common
immediate-constant format.
Each architecture defines additional constraints. These constraints
are used by the compiler itself for instruction generation, as well as
for @code{asm} statements; therefore, some of the constraints are not
particularly useful for @code{asm}. Here is a summary of some of the
machine-dependent constraints available on some particular machines;
it includes both constraints that are useful for @code{asm} and
constraints that aren't. The compiler source file mentioned in the
table heading for each architecture is the definitive reference for
the meanings of that architecture's constraints.
@c Please keep this table alphabetized by target!
@table @emph
@item AArch64 family---@file{config/aarch64/constraints.md}
@table @code
@item k
The stack pointer register (@code{SP})
@item w
Floating point register, Advanced SIMD vector register or SVE vector register
@item x
Like @code{w}, but restricted to registers 0 to 15 inclusive.
@item y
Like @code{w}, but restricted to registers 0 to 7 inclusive.
@item Upl
One of the low eight SVE predicate registers (@code{P0} to @code{P7})
@item Upa
Any of the SVE predicate registers (@code{P0} to @code{P15})
@item I
Integer constant that is valid as an immediate operand in an @code{ADD}
instruction
@item J
Integer constant that is valid as an immediate operand in a @code{SUB}
instruction (once negated)
@item K
Integer constant that can be used with a 32-bit logical instruction
@item L
Integer constant that can be used with a 64-bit logical instruction
@item M
Integer constant that is valid as an immediate operand in a 32-bit @code{MOV}
pseudo instruction. The @code{MOV} may be assembled to one of several different
machine instructions depending on the value
@item N
Integer constant that is valid as an immediate operand in a 64-bit @code{MOV}
pseudo instruction
@item S
An absolute symbolic address or a label reference
@item Y
Floating point constant zero
@item Z
Integer constant zero
@item Ush
The high part (bits 12 and upwards) of the pc-relative address of a symbol
within 4GB of the instruction
@item Q
A memory address which uses a single base register with no offset
@item Ump
A memory address suitable for a load/store pair instruction in SI, DI, SF and
DF modes
@end table
@item AMD GCN ---@file{config/gcn/constraints.md}
@table @code
@item I
Immediate integer in the range @minus{}16 to 64
@item J
Immediate 16-bit signed integer
@item Kf
Immediate constant @minus{}1
@item L
Immediate 15-bit unsigned integer
@item A
Immediate constant that can be inlined in an instruction encoding: integer
@minus{}16..64, or float 0.0, +/@minus{}0.5, +/@minus{}1.0, +/@minus{}2.0,
+/@minus{}4.0, 1.0/(2.0*PI)
@item B
Immediate 32-bit signed integer that can be attached to an instruction encoding
@item C
Immediate 32-bit integer in range @minus{}16..4294967295 (i.e. 32-bit unsigned
integer or @samp{A} constraint)
@item DA
Immediate 64-bit constant that can be split into two @samp{A} constants
@item DB
Immediate 64-bit constant that can be split into two @samp{B} constants
@item U
Any @code{unspec}
@item Y
Any @code{symbol_ref} or @code{label_ref}
@item v
VGPR register
@item Sg
SGPR register
@item SD
SGPR registers valid for instruction destinations, including VCC, M0 and EXEC
@item SS
SGPR registers valid for instruction sources, including VCC, M0, EXEC and SCC
@item Sm
SGPR registers valid as a source for scalar memory instructions (excludes M0
and EXEC)
@item Sv
SGPR registers valid as a source or destination for vector instructions
(excludes EXEC)
@item ca
All condition registers: SCC, VCCZ, EXECZ
@item cs
Scalar condition register: SCC
@item cV
Vector condition register: VCC, VCC_LO, VCC_HI
@item e
EXEC register (EXEC_LO and EXEC_HI)
@item RB
Memory operand with address space suitable for @code{buffer_*} instructions
@item RF
Memory operand with address space suitable for @code{flat_*} instructions
@item RS
Memory operand with address space suitable for @code{s_*} instructions
@item RL
Memory operand with address space suitable for @code{ds_*} LDS instructions
@item RG
Memory operand with address space suitable for @code{ds_*} GDS instructions
@item RD
Memory operand with address space suitable for any @code{ds_*} instructions
@item RM
Memory operand with address space suitable for @code{global_*} instructions
@end table
@item ARC ---@file{config/arc/constraints.md}
@table @code
@item q
Registers usable in ARCompact 16-bit instructions: @code{r0}-@code{r3},
@code{r12}-@code{r15}. This constraint can only match when the @option{-mq}
option is in effect.
@item e
Registers usable as base-regs of memory addresses in ARCompact 16-bit memory
instructions: @code{r0}-@code{r3}, @code{r12}-@code{r15}, @code{sp}.
This constraint can only match when the @option{-mq}
option is in effect.
@item D
ARC FPX (dpfp) 64-bit registers. @code{D0}, @code{D1}.
@item I
A signed 12-bit integer constant.
@item Cal
constant for arithmetic/logical operations. This might be any constant
that can be put into a long immediate by the assmbler or linker without
involving a PIC relocation.
@item K
A 3-bit unsigned integer constant.
@item L
A 6-bit unsigned integer constant.
@item CnL
One's complement of a 6-bit unsigned integer constant.
@item CmL
Two's complement of a 6-bit unsigned integer constant.
@item M
A 5-bit unsigned integer constant.
@item O
A 7-bit unsigned integer constant.
@item P
A 8-bit unsigned integer constant.
@item H
Any const_double value.
@end table
@item ARM family---@file{config/arm/constraints.md}
@table @code
@item h
In Thumb state, the core registers @code{r8}-@code{r15}.
@item k
The stack pointer register.
@item l
In Thumb State the core registers @code{r0}-@code{r7}. In ARM state this
is an alias for the @code{r} constraint.
@item t
VFP floating-point registers @code{s0}-@code{s31}. Used for 32 bit values.
@item w
VFP floating-point registers @code{d0}-@code{d31} and the appropriate
subset @code{d0}-@code{d15} based on command line options.
Used for 64 bit values only. Not valid for Thumb1.
@item y
The iWMMX co-processor registers.
@item z
The iWMMX GR registers.
@item G
The floating-point constant 0.0
@item I
Integer that is valid as an immediate operand in a data processing
instruction. That is, an integer in the range 0 to 255 rotated by a
multiple of 2
@item J
Integer in the range @minus{}4095 to 4095
@item K
Integer that satisfies constraint @samp{I} when inverted (ones complement)
@item L
Integer that satisfies constraint @samp{I} when negated (twos complement)
@item M
Integer in the range 0 to 32
@item Q
A memory reference where the exact address is in a single register
(`@samp{m}' is preferable for @code{asm} statements)
@item R
An item in the constant pool
@item S
A symbol in the text segment of the current file
@item Uv
A memory reference suitable for VFP load/store insns (reg+constant offset)
@item Uy
A memory reference suitable for iWMMXt load/store instructions.
@item Uq
A memory reference suitable for the ARMv4 ldrsb instruction.
@end table
@item AVR family---@file{config/avr/constraints.md}
@table @code
@item l
Registers from r0 to r15
@item a
Registers from r16 to r23
@item d
Registers from r16 to r31
@item w
Registers from r24 to r31. These registers can be used in @samp{adiw} command
@item e
Pointer register (r26--r31)
@item b
Base pointer register (r28--r31)
@item q
Stack pointer register (SPH:SPL)
@item t
Temporary register r0
@item x
Register pair X (r27:r26)
@item y
Register pair Y (r29:r28)
@item z
Register pair Z (r31:r30)
@item I
Constant greater than @minus{}1, less than 64
@item J
Constant greater than @minus{}64, less than 1
@item K
Constant integer 2
@item L
Constant integer 0
@item M
Constant that fits in 8 bits
@item N
Constant integer @minus{}1
@item O
Constant integer 8, 16, or 24
@item P
Constant integer 1
@item G
A floating point constant 0.0
@item Q
A memory address based on Y or Z pointer with displacement.
@end table
@item Blackfin family---@file{config/bfin/constraints.md}
@table @code
@item a
P register
@item d
D register
@item z
A call clobbered P register.
@item q@var{n}
A single register. If @var{n} is in the range 0 to 7, the corresponding D
register. If it is @code{A}, then the register P0.
@item D
Even-numbered D register
@item W
Odd-numbered D register
@item e
Accumulator register.
@item A
Even-numbered accumulator register.
@item B
Odd-numbered accumulator register.
@item b
I register
@item v
B register
@item f
M register
@item c
Registers used for circular buffering, i.e.@: I, B, or L registers.
@item C
The CC register.
@item t
LT0 or LT1.
@item k
LC0 or LC1.
@item u
LB0 or LB1.
@item x
Any D, P, B, M, I or L register.
@item y
Additional registers typically used only in prologues and epilogues: RETS,
RETN, RETI, RETX, RETE, ASTAT, SEQSTAT and USP.
@item w
Any register except accumulators or CC.
@item Ksh
Signed 16 bit integer (in the range @minus{}32768 to 32767)
@item Kuh
Unsigned 16 bit integer (in the range 0 to 65535)
@item Ks7
Signed 7 bit integer (in the range @minus{}64 to 63)
@item Ku7
Unsigned 7 bit integer (in the range 0 to 127)
@item Ku5
Unsigned 5 bit integer (in the range 0 to 31)
@item Ks4
Signed 4 bit integer (in the range @minus{}8 to 7)
@item Ks3
Signed 3 bit integer (in the range @minus{}3 to 4)
@item Ku3
Unsigned 3 bit integer (in the range 0 to 7)
@item P@var{n}
Constant @var{n}, where @var{n} is a single-digit constant in the range 0 to 4.
@item PA
An integer equal to one of the MACFLAG_XXX constants that is suitable for
use with either accumulator.
@item PB
An integer equal to one of the MACFLAG_XXX constants that is suitable for
use only with accumulator A1.
@item M1
Constant 255.
@item M2
Constant 65535.
@item J
An integer constant with exactly a single bit set.
@item L
An integer constant with all bits set except exactly one.
@item H
@itemx Q
Any SYMBOL_REF.
@end table
@item C-SKY---@file{config/csky/constraints.md}
@table @code
@item a
The mini registers r0 - r7.
@item b
The low registers r0 - r15.
@item c
C register.
@item y
HI and LO registers.
@item l
LO register.
@item h
HI register.
@item v
Vector registers.
@item z
Stack pointer register (SP).
@item Q
A memory address which uses a base register with a short offset
or with a index register with its scale.
@item W
A memory address which uses a base register with a index register
with its scale.
@end table
@ifset INTERNALS
The C-SKY back end supports a large set of additional constraints
that are only useful for instruction selection or splitting rather
than inline asm, such as constraints representing constant integer
ranges accepted by particular instruction encodings.
Refer to the source code for details.
@end ifset
@item Epiphany---@file{config/epiphany/constraints.md}
@table @code
@item U16
An unsigned 16-bit constant.
@item K
An unsigned 5-bit constant.
@item L
A signed 11-bit constant.
@item Cm1
A signed 11-bit constant added to @minus{}1.
Can only match when the @option{-m1reg-@var{reg}} option is active.
@item Cl1
Left-shift of @minus{}1, i.e., a bit mask with a block of leading ones, the rest
being a block of trailing zeroes.
Can only match when the @option{-m1reg-@var{reg}} option is active.
@item Cr1
Right-shift of @minus{}1, i.e., a bit mask with a trailing block of ones, the
rest being zeroes. Or to put it another way, one less than a power of two.
Can only match when the @option{-m1reg-@var{reg}} option is active.
@item Cal
Constant for arithmetic/logical operations.
This is like @code{i}, except that for position independent code,
no symbols / expressions needing relocations are allowed.
@item Csy
Symbolic constant for call/jump instruction.
@item Rcs
The register class usable in short insns. This is a register class
constraint, and can thus drive register allocation.
This constraint won't match unless @option{-mprefer-short-insn-regs} is
in effect.
@item Rsc
The register class of registers that can be used to hold a
sibcall call address. I.e., a caller-saved register.
@item Rct
Core control register class.
@item Rgs
The register group usable in short insns.
This constraint does not use a register class, so that it only
passively matches suitable registers, and doesn't drive register allocation.
@ifset INTERNALS
@item Car
Constant suitable for the addsi3_r pattern. This is a valid offset
For byte, halfword, or word addressing.
@end ifset
@item Rra
Matches the return address if it can be replaced with the link register.
@item Rcc
Matches the integer condition code register.
@item Sra
Matches the return address if it is in a stack slot.
@item Cfm
Matches control register values to switch fp mode, which are encapsulated in
@code{UNSPEC_FP_MODE}.
@end table
@item FRV---@file{config/frv/frv.h}
@table @code
@item a
Register in the class @code{ACC_REGS} (@code{acc0} to @code{acc7}).
@item b
Register in the class @code{EVEN_ACC_REGS} (@code{acc0} to @code{acc7}).
@item c
Register in the class @code{CC_REGS} (@code{fcc0} to @code{fcc3} and
@code{icc0} to @code{icc3}).
@item d
Register in the class @code{GPR_REGS} (@code{gr0} to @code{gr63}).
@item e
Register in the class @code{EVEN_REGS} (@code{gr0} to @code{gr63}).
Odd registers are excluded not in the class but through the use of a machine
mode larger than 4 bytes.
@item f
Register in the class @code{FPR_REGS} (@code{fr0} to @code{fr63}).
@item h
Register in the class @code{FEVEN_REGS} (@code{fr0} to @code{fr63}).
Odd registers are excluded not in the class but through the use of a machine
mode larger than 4 bytes.
@item l
Register in the class @code{LR_REG} (the @code{lr} register).
@item q
Register in the class @code{QUAD_REGS} (@code{gr2} to @code{gr63}).
Register numbers not divisible by 4 are excluded not in the class but through
the use of a machine mode larger than 8 bytes.
@item t
Register in the class @code{ICC_REGS} (@code{icc0} to @code{icc3}).
@item u
Register in the class @code{FCC_REGS} (@code{fcc0} to @code{fcc3}).
@item v
Register in the class @code{ICR_REGS} (@code{cc4} to @code{cc7}).
@item w
Register in the class @code{FCR_REGS} (@code{cc0} to @code{cc3}).
@item x
Register in the class @code{QUAD_FPR_REGS} (@code{fr0} to @code{fr63}).
Register numbers not divisible by 4 are excluded not in the class but through
the use of a machine mode larger than 8 bytes.
@item z
Register in the class @code{SPR_REGS} (@code{lcr} and @code{lr}).
@item A
Register in the class @code{QUAD_ACC_REGS} (@code{acc0} to @code{acc7}).
@item B
Register in the class @code{ACCG_REGS} (@code{accg0} to @code{accg7}).
@item C
Register in the class @code{CR_REGS} (@code{cc0} to @code{cc7}).
@item G
Floating point constant zero
@item I
6-bit signed integer constant
@item J
10-bit signed integer constant
@item L
16-bit signed integer constant
@item M
16-bit unsigned integer constant
@item N
12-bit signed integer constant that is negative---i.e.@: in the
range of @minus{}2048 to @minus{}1
@item O
Constant zero
@item P
12-bit signed integer constant that is greater than zero---i.e.@: in the
range of 1 to 2047.
@end table
@item FT32---@file{config/ft32/constraints.md}
@table @code
@item A
An absolute address
@item B
An offset address
@item W
A register indirect memory operand
@item e
An offset address.
@item f
An offset address.
@item O
The constant zero or one
@item I
A 16-bit signed constant (@minus{}32768 @dots{} 32767)
@item w
A bitfield mask suitable for bext or bins
@item x
An inverted bitfield mask suitable for bext or bins
@item L
A 16-bit unsigned constant, multiple of 4 (0 @dots{} 65532)
@item S
A 20-bit signed constant (@minus{}524288 @dots{} 524287)
@item b
A constant for a bitfield width (1 @dots{} 16)
@item KA
A 10-bit signed constant (@minus{}512 @dots{} 511)
@end table
@item Hewlett-Packard PA-RISC---@file{config/pa/pa.h}
@table @code
@item a
General register 1
@item f
Floating point register
@item q
Shift amount register
@item x
Floating point register (deprecated)
@item y
Upper floating point register (32-bit), floating point register (64-bit)
@item Z
Any register
@item I
Signed 11-bit integer constant
@item J
Signed 14-bit integer constant
@item K
Integer constant that can be deposited with a @code{zdepi} instruction
@item L
Signed 5-bit integer constant
@item M
Integer constant 0
@item N
Integer constant that can be loaded with a @code{ldil} instruction
@item O
Integer constant whose value plus one is a power of 2
@item P
Integer constant that can be used for @code{and} operations in @code{depi}
and @code{extru} instructions
@item S
Integer constant 31
@item U
Integer constant 63
@item G
Floating-point constant 0.0
@item A
A @code{lo_sum} data-linkage-table memory operand
@item Q
A memory operand that can be used as the destination operand of an
integer store instruction
@item R
A scaled or unscaled indexed memory operand
@item T
A memory operand for floating-point loads and stores
@item W
A register indirect memory operand
@end table
@item Intel IA-64---@file{config/ia64/ia64.h}
@table @code
@item a
General register @code{r0} to @code{r3} for @code{addl} instruction
@item b
Branch register
@item c
Predicate register (@samp{c} as in ``conditional'')
@item d
Application register residing in M-unit
@item e
Application register residing in I-unit
@item f
Floating-point register
@item m
Memory operand. If used together with @samp{<} or @samp{>},
the operand can have postincrement and postdecrement which
require printing with @samp{%Pn} on IA-64.
@item G
Floating-point constant 0.0 or 1.0
@item I
14-bit signed integer constant
@item J
22-bit signed integer constant
@item K
8-bit signed integer constant for logical instructions
@item L
8-bit adjusted signed integer constant for compare pseudo-ops
@item M
6-bit unsigned integer constant for shift counts
@item N
9-bit signed integer constant for load and store postincrements
@item O
The constant zero
@item P
0 or @minus{}1 for @code{dep} instruction
@item Q
Non-volatile memory for floating-point loads and stores
@item R
Integer constant in the range 1 to 4 for @code{shladd} instruction
@item S
Memory operand except postincrement and postdecrement. This is
now roughly the same as @samp{m} when not used together with @samp{<}
or @samp{>}.
@end table
@item M32C---@file{config/m32c/m32c.cc}
@table @code
@item Rsp
@itemx Rfb
@itemx Rsb
@samp{$sp}, @samp{$fb}, @samp{$sb}.
@item Rcr
Any control register, when they're 16 bits wide (nothing if control
registers are 24 bits wide)
@item Rcl
Any control register, when they're 24 bits wide.
@item R0w
@itemx R1w
@itemx R2w
@itemx R3w
$r0, $r1, $r2, $r3.
@item R02
$r0 or $r2, or $r2r0 for 32 bit values.
@item R13
$r1 or $r3, or $r3r1 for 32 bit values.
@item Rdi
A register that can hold a 64 bit value.
@item Rhl
$r0 or $r1 (registers with addressable high/low bytes)
@item R23
$r2 or $r3
@item Raa
Address registers
@item Raw
Address registers when they're 16 bits wide.
@item Ral
Address registers when they're 24 bits wide.
@item Rqi
Registers that can hold QI values.
@item Rad
Registers that can be used with displacements ($a0, $a1, $sb).
@item Rsi
Registers that can hold 32 bit values.
@item Rhi
Registers that can hold 16 bit values.
@item Rhc
Registers chat can hold 16 bit values, including all control
registers.
@item Rra
$r0 through R1, plus $a0 and $a1.
@item Rfl
The flags register.
@item Rmm
The memory-based pseudo-registers $mem0 through $mem15.
@item Rpi
Registers that can hold pointers (16 bit registers for r8c, m16c; 24
bit registers for m32cm, m32c).
@item Rpa
Matches multiple registers in a PARALLEL to form a larger register.
Used to match function return values.
@item Is3
@minus{}8 @dots{} 7
@item IS1
@minus{}128 @dots{} 127
@item IS2
@minus{}32768 @dots{} 32767
@item IU2
0 @dots{} 65535
@item In4
@minus{}8 @dots{} @minus{}1 or 1 @dots{} 8
@item In5
@minus{}16 @dots{} @minus{}1 or 1 @dots{} 16
@item In6
@minus{}32 @dots{} @minus{}1 or 1 @dots{} 32
@item IM2
@minus{}65536 @dots{} @minus{}1
@item Ilb
An 8 bit value with exactly one bit set.
@item Ilw
A 16 bit value with exactly one bit set.
@item Sd
The common src/dest memory addressing modes.
@item Sa
Memory addressed using $a0 or $a1.
@item Si
Memory addressed with immediate addresses.
@item Ss
Memory addressed using the stack pointer ($sp).
@item Sf
Memory addressed using the frame base register ($fb).
@item Ss
Memory addressed using the small base register ($sb).
@item S1
$r1h
@end table
@item LoongArch---@file{config/loongarch/constraints.md}
@table @code
@item f
A floating-point register (if available).
@item k
A memory operand whose address is formed by a base register and
(optionally scaled) index register.
@item l
A signed 16-bit constant.
@item m
A memory operand whose address is formed by a base register and offset
that is suitable for use in instructions with the same addressing mode
as @code{st.w} and @code{ld.w}.
@item I
A signed 12-bit constant (for arithmetic instructions).
@item K
An unsigned 12-bit constant (for logic instructions).
@item ZB
An address that is held in a general-purpose register.
The offset is zero.
@item ZC
A memory operand whose address is formed by a base register and offset
that is suitable for use in instructions with the same addressing mode
as @code{ll.w} and @code{sc.w}.
@end table
@item MicroBlaze---@file{config/microblaze/constraints.md}
@table @code
@item d
A general register (@code{r0} to @code{r31}).
@item z
A status register (@code{rmsr}, @code{$fcc1} to @code{$fcc7}).
@end table
@item MIPS---@file{config/mips/constraints.md}
@table @code
@item d
A general-purpose register. This is equivalent to @code{r} unless
generating MIPS16 code, in which case the MIPS16 register set is used.
@item f
A floating-point register (if available).
@item h
Formerly the @code{hi} register. This constraint is no longer supported.
@item l
The @code{lo} register. Use this register to store values that are
no bigger than a word.
@item x
The concatenated @code{hi} and @code{lo} registers. Use this register
to store doubleword values.
@item c
A register suitable for use in an indirect jump. This will always be
@code{$25} for @option{-mabicalls}.
@item v
Register @code{$3}. Do not use this constraint in new code;
it is retained only for compatibility with glibc.
@item y
Equivalent to @code{r}; retained for backwards compatibility.
@item z
A floating-point condition code register.
@item I
A signed 16-bit constant (for arithmetic instructions).
@item J
Integer zero.
@item K
An unsigned 16-bit constant (for logic instructions).
@item L
A signed 32-bit constant in which the lower 16 bits are zero.
Such constants can be loaded using @code{lui}.
@item M
A constant that cannot be loaded using @code{lui}, @code{addiu}
or @code{ori}.
@item N
A constant in the range @minus{}65535 to @minus{}1 (inclusive).
@item O
A signed 15-bit constant.
@item P
A constant in the range 1 to 65535 (inclusive).
@item G
Floating-point zero.
@item R
An address that can be used in a non-macro load or store.
@item 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 @code{ll} and @code{sc}.
@item ZD
An address suitable for a @code{prefetch} instruction, or for any other
instruction with the same addressing mode as @code{prefetch}.
@end table
@item Motorola 680x0---@file{config/m68k/constraints.md}
@table @code
@item a
Address register
@item d
Data register
@item f
68881 floating-point register, if available
@item I
Integer in the range 1 to 8
@item J
16-bit signed number
@item K
Signed number whose magnitude is greater than 0x80
@item L
Integer in the range @minus{}8 to @minus{}1
@item M
Signed number whose magnitude is greater than 0x100
@item N
Range 24 to 31, rotatert:SI 8 to 1 expressed as rotate
@item O
16 (for rotate using swap)
@item P
Range 8 to 15, rotatert:HI 8 to 1 expressed as rotate
@item R
Numbers that mov3q can handle
@item G
Floating point constant that is not a 68881 constant
@item S
Operands that satisfy 'm' when -mpcrel is in effect
@item T
Operands that satisfy 's' when -mpcrel is not in effect
@item Q
Address register indirect addressing mode
@item U
Register offset addressing
@item W
const_call_operand
@item Cs
symbol_ref or const
@item Ci
const_int
@item C0
const_int 0
@item Cj
Range of signed numbers that don't fit in 16 bits
@item Cmvq
Integers valid for mvq
@item Capsw
Integers valid for a moveq followed by a swap
@item Cmvz
Integers valid for mvz
@item Cmvs
Integers valid for mvs
@item Ap
push_operand
@item Ac
Non-register operands allowed in clr
@end table
@item Moxie---@file{config/moxie/constraints.md}
@table @code
@item A
An absolute address
@item B
An offset address
@item W
A register indirect memory operand
@item I
A constant in the range of 0 to 255.
@item N
A constant in the range of 0 to @minus{}255.
@end table
@item MSP430--@file{config/msp430/constraints.md}
@table @code
@item R12
Register R12.
@item R13
Register R13.
@item K
Integer constant 1.
@item L
Integer constant -1^20..1^19.
@item M
Integer constant 1-4.
@item Ya
Memory references which do not require an extended MOVX instruction.
@item Yl
Memory reference, labels only.
@item Ys
Memory reference, stack only.
@end table
@item NDS32---@file{config/nds32/constraints.md}
@table @code
@item w
LOW register class $r0 to $r7 constraint for V3/V3M ISA.
@item l
LOW register class $r0 to $r7.
@item d
MIDDLE register class $r0 to $r11, $r16 to $r19.
@item h
HIGH register class $r12 to $r14, $r20 to $r31.
@item t
Temporary assist register $ta (i.e.@: $r15).
@item k
Stack register $sp.
@item Iu03
Unsigned immediate 3-bit value.
@item In03
Negative immediate 3-bit value in the range of @minus{}7--0.
@item Iu04
Unsigned immediate 4-bit value.
@item Is05
Signed immediate 5-bit value.
@item Iu05
Unsigned immediate 5-bit value.
@item In05
Negative immediate 5-bit value in the range of @minus{}31--0.
@item Ip05
Unsigned immediate 5-bit value for movpi45 instruction with range 16--47.
@item Iu06
Unsigned immediate 6-bit value constraint for addri36.sp instruction.
@item Iu08
Unsigned immediate 8-bit value.
@item Iu09
Unsigned immediate 9-bit value.
@item Is10
Signed immediate 10-bit value.
@item Is11
Signed immediate 11-bit value.
@item Is15
Signed immediate 15-bit value.
@item Iu15
Unsigned immediate 15-bit value.
@item Ic15
A constant which is not in the range of imm15u but ok for bclr instruction.
@item Ie15
A constant which is not in the range of imm15u but ok for bset instruction.
@item It15
A constant which is not in the range of imm15u but ok for btgl instruction.
@item Ii15
A constant whose compliment value is in the range of imm15u
and ok for bitci instruction.
@item Is16
Signed immediate 16-bit value.
@item Is17
Signed immediate 17-bit value.
@item Is19
Signed immediate 19-bit value.
@item Is20
Signed immediate 20-bit value.
@item Ihig
The immediate value that can be simply set high 20-bit.
@item Izeb
The immediate value 0xff.
@item Izeh
The immediate value 0xffff.
@item Ixls
The immediate value 0x01.
@item Ix11
The immediate value 0x7ff.
@item Ibms
The immediate value with power of 2.
@item Ifex
The immediate value with power of 2 minus 1.
@item U33
Memory constraint for 333 format.
@item U45
Memory constraint for 45 format.
@item U37
Memory constraint for 37 format.
@end table
@item Nios II family---@file{config/nios2/constraints.md}
@table @code
@item I
Integer that is valid as an immediate operand in an
instruction taking a signed 16-bit number. Range
@minus{}32768 to 32767.
@item J
Integer that is valid as an immediate operand in an
instruction taking an unsigned 16-bit number. Range
0 to 65535.
@item K
Integer that is valid as an immediate operand in an
instruction taking only the upper 16-bits of a
32-bit number. Range 32-bit numbers with the lower
16-bits being 0.
@item L
Integer that is valid as an immediate operand for a
shift instruction. Range 0 to 31.
@item M
Integer that is valid as an immediate operand for
only the value 0. Can be used in conjunction with
the format modifier @code{z} to use @code{r0}
instead of @code{0} in the assembly output.
@item N
Integer that is valid as an immediate operand for
a custom instruction opcode. Range 0 to 255.
@item P
An immediate operand for R2 andchi/andci instructions.
@item S
Matches immediates which are addresses in the small
data section and therefore can be added to @code{gp}
as a 16-bit immediate to re-create their 32-bit value.
@item U
Matches constants suitable as an operand for the rdprs and
cache instructions.
@item v
A memory operand suitable for Nios II R2 load/store
exclusive instructions.
@item w
A memory operand suitable for load/store IO and cache
instructions.
@ifset INTERNALS
@item T
A @code{const} wrapped @code{UNSPEC} expression,
representing a supported PIC or TLS relocation.
@end ifset
@end table
@item OpenRISC---@file{config/or1k/constraints.md}
@table @code
@item I
Integer that is valid as an immediate operand in an
instruction taking a signed 16-bit number. Range
@minus{}32768 to 32767.
@item K
Integer that is valid as an immediate operand in an
instruction taking an unsigned 16-bit number. Range
0 to 65535.
@item M
Signed 16-bit constant shifted left 16 bits. (Used with @code{l.movhi})
@item O
Zero
@ifset INTERNALS
@item c
Register usable for sibcalls.
@end ifset
@end table
@item PDP-11---@file{config/pdp11/constraints.md}
@table @code
@item a
Floating point registers AC0 through AC3. These can be loaded from/to
memory with a single instruction.
@item d
Odd numbered general registers (R1, R3, R5). These are used for
16-bit multiply operations.
@item D
A memory reference that is encoded within the opcode, but not
auto-increment or auto-decrement.
@item f
Any of the floating point registers (AC0 through AC5).
@item G
Floating point constant 0.
@item h
Floating point registers AC4 and AC5. These cannot be loaded from/to
memory with a single instruction.
@item I
An integer constant that fits in 16 bits.
@item J
An integer constant whose low order 16 bits are zero.
@item K
An integer constant that does not meet the constraints for codes
@samp{I} or @samp{J}.
@item L
The integer constant 1.
@item M
The integer constant @minus{}1.
@item N
The integer constant 0.
@item O
Integer constants 0 through 3; shifts by these
amounts are handled as multiple single-bit shifts rather than a single
variable-length shift.
@item Q
A memory reference which requires an additional word (address or
offset) after the opcode.
@item R
A memory reference that is encoded within the opcode.
@end table
@item PowerPC and IBM RS6000---@file{config/rs6000/constraints.md}
@table @code
@item r
A general purpose register (GPR), @code{r0}@dots{}@code{r31}.
@item b
A base register. Like @code{r}, but @code{r0} is not allowed, so
@code{r1}@dots{}@code{r31}.
@item f
A floating point register (FPR), @code{f0}@dots{}@code{f31}.
@item d
A floating point register. This is the same as @code{f} nowadays;
historically @code{f} was for single-precision and @code{d} was for
double-precision floating point.
@item v
An Altivec vector register (VR), @code{v0}@dots{}@code{v31}.
@item wa
A VSX register (VSR), @code{vs0}@dots{}@code{vs63}. This is either an
FPR (@code{vs0}@dots{}@code{vs31} are @code{f0}@dots{}@code{f31}) or a VR
(@code{vs32}@dots{}@code{vs63} are @code{v0}@dots{}@code{v31}).
When using @code{wa}, you should use the @code{%x} output modifier, so that
the correct register number is printed. For example:
@smallexample
asm ("xvadddp %x0,%x1,%x2"
: "=wa" (v1)
: "wa" (v2), "wa" (v3));
@end smallexample
You should not use @code{%x} for @code{v} operands:
@smallexample
asm ("xsaddqp %0,%1,%2"
: "=v" (v1)
: "v" (v2), "v" (v3));
@end smallexample
@ifset INTERNALS
@item h
A special register (@code{vrsave}, @code{ctr}, or @code{lr}).
@end ifset
@item c
The count register, @code{ctr}.
@item l
The link register, @code{lr}.
@item x
Condition register field 0, @code{cr0}.
@item y
Any condition register field, @code{cr0}@dots{}@code{cr7}.
@ifset INTERNALS
@item z
The carry bit, @code{XER[CA]}.
@item we
Like @code{wa}, if @option{-mpower9-vector} and @option{-m64} are used;
otherwise, @code{NO_REGS}.
@item wn
No register (@code{NO_REGS}).
@item wr
Like @code{r}, if @option{-mpowerpc64} is used; otherwise, @code{NO_REGS}.
@item wx
Like @code{d}, if @option{-mpowerpc-gfxopt} is used; otherwise, @code{NO_REGS}.
@item wA
Like @code{b}, if @option{-mpowerpc64} is used; otherwise, @code{NO_REGS}.
@item wB
Signed 5-bit constant integer that can be loaded into an Altivec register.
@item wE
Vector constant that can be loaded with the XXSPLTIB instruction.
@item wF
Memory operand suitable for power8 GPR load fusion.
@item wL
Int constant that is the element number mfvsrld accesses in a vector.
@item wM
Match vector constant with all 1's if the XXLORC instruction is available.
@item wO
Memory operand suitable for the ISA 3.0 vector d-form instructions.
@item wQ
Memory operand suitable for the load/store quad instructions.
@item wS
Vector constant that can be loaded with XXSPLTIB & sign extension.
@item wY
A memory operand for a DS-form instruction.
@item wZ
An indexed or indirect memory operand, ignoring the bottom 4 bits.
@end ifset
@item I
A signed 16-bit constant.
@item J
An unsigned 16-bit constant shifted left 16 bits (use @code{L} instead
for @code{SImode} constants).
@item K
An unsigned 16-bit constant.
@item L
A signed 16-bit constant shifted left 16 bits.
@ifset INTERNALS
@item M
An integer constant greater than 31.
@item N
An exact power of 2.
@item O
The integer constant zero.
@item P
A constant whose negation is a signed 16-bit constant.
@end ifset
@item eI
A signed 34-bit integer constant if prefixed instructions are supported.
@item eP
A scalar floating point constant or a vector constant that can be
loaded to a VSX register with one prefixed instruction.
@item eQ
An IEEE 128-bit constant that can be loaded into a VSX register with
the @code{lxvkq} instruction.
@ifset INTERNALS
@item G
A floating point constant that can be loaded into a register with one
instruction per word.
@item H
A floating point constant that can be loaded into a register using
three instructions.
@end ifset
@item m
A memory operand.
Normally, @code{m} does not allow addresses that update the base register.
If the @code{<} or @code{>} constraint is also used, they are allowed and
therefore on PowerPC targets in that case it is only safe
to use @code{m<>} in an @code{asm} statement if that @code{asm} statement
accesses the operand exactly once. The @code{asm} statement must also
use @code{%U@var{<opno>}} as a placeholder for the ``update'' flag in the
corresponding load or store instruction. For example:
@smallexample
asm ("st%U0 %1,%0" : "=m<>" (mem) : "r" (val));
@end smallexample
is correct but:
@smallexample
asm ("st %1,%0" : "=m<>" (mem) : "r" (val));
@end smallexample
is not.
@ifset INTERNALS
@item es
A ``stable'' memory operand; that is, one which does not include any
automodification of the base register. This used to be useful when
@code{m} allowed automodification of the base register, but as those
are now only allowed when @code{<} or @code{>} is used, @code{es} is
basically the same as @code{m} without @code{<} and @code{>}.
@end ifset
@item Q
A memory operand addressed by just a base register.
@ifset INTERNALS
@item Y
A memory operand for a DQ-form instruction.
@end ifset
@item Z
A memory operand accessed with indexed or indirect addressing.
@ifset INTERNALS
@item R
An AIX TOC entry.
@end ifset
@item a
An indexed or indirect address.
@ifset INTERNALS
@item U
A V.4 small data reference.
@item W
A vector constant that does not require memory.
@item j
The zero vector constant.
@end ifset
@end table
@item PRU---@file{config/pru/constraints.md}
@table @code
@item I
An unsigned 8-bit integer constant.
@item J
An unsigned 16-bit integer constant.
@item L
An unsigned 5-bit integer constant (for shift counts).
@item T
A text segment (program memory) constant label.
@item Z
Integer constant zero.
@end table
@item RL78---@file{config/rl78/constraints.md}
@table @code
@item Int3
An integer constant in the range 1 @dots{} 7.
@item Int8
An integer constant in the range 0 @dots{} 255.
@item J
An integer constant in the range @minus{}255 @dots{} 0
@item K
The integer constant 1.
@item L
The integer constant -1.
@item M
The integer constant 0.
@item N
The integer constant 2.
@item O
The integer constant -2.
@item P
An integer constant in the range 1 @dots{} 15.
@item Qbi
The built-in compare types--eq, ne, gtu, ltu, geu, and leu.
@item Qsc
The synthetic compare types--gt, lt, ge, and le.
@item Wab
A memory reference with an absolute address.
@item Wbc
A memory reference using @code{BC} as a base register, with an optional offset.
@item Wca
A memory reference using @code{AX}, @code{BC}, @code{DE}, or @code{HL} for the address, for calls.
@item Wcv
A memory reference using any 16-bit register pair for the address, for calls.
@item Wd2
A memory reference using @code{DE} as a base register, with an optional offset.
@item Wde
A memory reference using @code{DE} as a base register, without any offset.
@item Wfr
Any memory reference to an address in the far address space.
@item Wh1
A memory reference using @code{HL} as a base register, with an optional one-byte offset.
@item Whb
A memory reference using @code{HL} as a base register, with @code{B} or @code{C} as the index register.
@item Whl
A memory reference using @code{HL} as a base register, without any offset.
@item Ws1
A memory reference using @code{SP} as a base register, with an optional one-byte offset.
@item Y
Any memory reference to an address in the near address space.
@item A
The @code{AX} register.
@item B
The @code{BC} register.
@item D
The @code{DE} register.
@item R
@code{A} through @code{L} registers.
@item S
The @code{SP} register.
@item T
The @code{HL} register.
@item Z08W
The 16-bit @code{R8} register.
@item Z10W
The 16-bit @code{R10} register.
@item Zint
The registers reserved for interrupts (@code{R24} to @code{R31}).
@item a
The @code{A} register.
@item b
The @code{B} register.
@item c
The @code{C} register.
@item d
The @code{D} register.
@item e
The @code{E} register.
@item h
The @code{H} register.
@item l
The @code{L} register.
@item v
The virtual registers.
@item w
The @code{PSW} register.
@item x
The @code{X} register.
@end table
@item RISC-V---@file{config/riscv/constraints.md}
@table @code
@item f
A floating-point register (if available).
@item I
An I-type 12-bit signed immediate.
@item J
Integer zero.
@item K
A 5-bit unsigned immediate for CSR access instructions.
@item A
An address that is held in a general-purpose register.
@item S
A constraint that matches an absolute symbolic address.
@item vr
A vector register (if available)..
@item vd
A vector register, excluding v0 (if available).
@item vm
A vector register, only v0 (if available).
@end table
@item RX---@file{config/rx/constraints.md}
@table @code
@item Q
An address which does not involve register indirect addressing or
pre/post increment/decrement addressing.
@item Symbol
A symbol reference.
@item Int08
A constant in the range @minus{}256 to 255, inclusive.
@item Sint08
A constant in the range @minus{}128 to 127, inclusive.
@item Sint16
A constant in the range @minus{}32768 to 32767, inclusive.
@item Sint24
A constant in the range @minus{}8388608 to 8388607, inclusive.
@item Uint04
A constant in the range 0 to 15, inclusive.
@end table
@item S/390 and zSeries---@file{config/s390/s390.h}
@table @code
@item a
Address register (general purpose register except r0)
@item c
Condition code register
@item d
Data register (arbitrary general purpose register)
@item f
Floating-point register
@item I
Unsigned 8-bit constant (0--255)
@item J
Unsigned 12-bit constant (0--4095)
@item K
Signed 16-bit constant (@minus{}32768--32767)
@item L
Value appropriate as displacement.
@table @code
@item (0..4095)
for short displacement
@item (@minus{}524288..524287)
for long displacement
@end table
@item M
Constant integer with a value of 0x7fffffff.
@item N
Multiple letter constraint followed by 4 parameter letters.
@table @code
@item 0..9:
number of the part counting from most to least significant
@item H,Q:
mode of the part
@item D,S,H:
mode of the containing operand
@item 0,F:
value of the other parts (F---all bits set)
@end table
The constraint matches if the specified part of a constant
has a value different from its other parts.
@item Q
Memory reference without index register and with short displacement.
@item R
Memory reference with index register and short displacement.
@item S
Memory reference without index register but with long displacement.
@item T
Memory reference with index register and long displacement.
@item U
Pointer with short displacement.
@item W
Pointer with long displacement.
@item Y
Shift count operand.
@end table
@need 1000
@item SPARC---@file{config/sparc/sparc.h}
@table @code
@item f
Floating-point register on the SPARC-V8 architecture and
lower floating-point register on the SPARC-V9 architecture.
@item e
Floating-point register. It is equivalent to @samp{f} on the
SPARC-V8 architecture and contains both lower and upper
floating-point registers on the SPARC-V9 architecture.
@item c
Floating-point condition code register.
@item d
Lower floating-point register. It is only valid on the SPARC-V9
architecture when the Visual Instruction Set is available.
@item b
Floating-point register. It is only valid on the SPARC-V9 architecture
when the Visual Instruction Set is available.
@item h
64-bit global or out register for the SPARC-V8+ architecture.
@item C
The constant all-ones, for floating-point.
@item A
Signed 5-bit constant
@item D
A vector constant
@item I
Signed 13-bit constant
@item J
Zero
@item K
32-bit constant with the low 12 bits clear (a constant that can be
loaded with the @code{sethi} instruction)
@item L
A constant in the range supported by @code{movcc} instructions (11-bit
signed immediate)
@item M
A constant in the range supported by @code{movrcc} instructions (10-bit
signed immediate)
@item N
Same as @samp{K}, except that it verifies that bits that are not in the
lower 32-bit range are all zero. Must be used instead of @samp{K} for
modes wider than @code{SImode}
@item O
The constant 4096
@item G
Floating-point zero
@item H
Signed 13-bit constant, sign-extended to 32 or 64 bits
@item P
The constant -1
@item Q
Floating-point constant whose integral representation can
be moved into an integer register using a single sethi
instruction
@item R
Floating-point constant whose integral representation can
be moved into an integer register using a single mov
instruction
@item S
Floating-point constant whose integral representation can
be moved into an integer register using a high/lo_sum
instruction sequence
@item T
Memory address aligned to an 8-byte boundary
@item U
Even register
@item W
Memory address for @samp{e} constraint registers
@item w
Memory address with only a base register
@item Y
Vector zero
@end table
@item TI C6X family---@file{config/c6x/constraints.md}
@table @code
@item a
Register file A (A0--A31).
@item b
Register file B (B0--B31).
@item A
Predicate registers in register file A (A0--A2 on C64X and
higher, A1 and A2 otherwise).
@item B
Predicate registers in register file B (B0--B2).
@item C
A call-used register in register file B (B0--B9, B16--B31).
@item Da
Register file A, excluding predicate registers (A3--A31,
plus A0 if not C64X or higher).
@item Db
Register file B, excluding predicate registers (B3--B31).
@item Iu4
Integer constant in the range 0 @dots{} 15.
@item Iu5
Integer constant in the range 0 @dots{} 31.
@item In5
Integer constant in the range @minus{}31 @dots{} 0.
@item Is5
Integer constant in the range @minus{}16 @dots{} 15.
@item I5x
Integer constant that can be the operand of an ADDA or a SUBA insn.
@item IuB
Integer constant in the range 0 @dots{} 65535.
@item IsB
Integer constant in the range @minus{}32768 @dots{} 32767.
@item IsC
Integer constant in the range @math{-2^{20}} @dots{} @math{2^{20} - 1}.
@item Jc
Integer constant that is a valid mask for the clr instruction.
@item Js
Integer constant that is a valid mask for the set instruction.
@item Q
Memory location with A base register.
@item R
Memory location with B base register.
@ifset INTERNALS
@item S0
On C64x+ targets, a GP-relative small data reference.
@item S1
Any kind of @code{SYMBOL_REF}, for use in a call address.
@item Si
Any kind of immediate operand, unless it matches the S0 constraint.
@item T
Memory location with B base register, but not using a long offset.
@item W
A memory operand with an address that cannot be used in an unaligned access.
@end ifset
@item Z
Register B14 (aka DP).
@end table
@item Visium---@file{config/visium/constraints.md}
@table @code
@item b
EAM register @code{mdb}
@item c
EAM register @code{mdc}
@item f
Floating point register
@ifset INTERNALS
@item k
Register for sibcall optimization
@end ifset
@item l
General register, but not @code{r29}, @code{r30} and @code{r31}
@item t
Register @code{r1}
@item u
Register @code{r2}
@item v
Register @code{r3}
@item G
Floating-point constant 0.0
@item J
Integer constant in the range 0 .. 65535 (16-bit immediate)
@item K
Integer constant in the range 1 .. 31 (5-bit immediate)
@item L
Integer constant in the range @minus{}65535 .. @minus{}1 (16-bit negative immediate)
@item M
Integer constant @minus{}1
@item O
Integer constant 0
@item P
Integer constant 32
@end table
@item x86 family---@file{config/i386/constraints.md}
@table @code
@item R
Legacy register---the eight integer registers available on all
i386 processors (@code{a}, @code{b}, @code{c}, @code{d},
@code{si}, @code{di}, @code{bp}, @code{sp}).
@item q
Any register accessible as @code{@var{r}l}. In 32-bit mode, @code{a},
@code{b}, @code{c}, and @code{d}; in 64-bit mode, any integer register.
@item Q
Any register accessible as @code{@var{r}h}: @code{a}, @code{b},
@code{c}, and @code{d}.
@ifset INTERNALS
@item l
Any register that can be used as the index in a base+index memory
access: that is, any general register except the stack pointer.
@end ifset
@item a
The @code{a} register.
@item b
The @code{b} register.
@item c
The @code{c} register.
@item d
The @code{d} register.
@item S
The @code{si} register.
@item D
The @code{di} register.
@item A
The @code{a} and @code{d} registers. This class is used for instructions
that return double word results in the @code{ax:dx} register pair. Single
word values will be allocated either in @code{ax} or @code{dx}.
For example on i386 the following implements @code{rdtsc}:
@smallexample
unsigned long long rdtsc (void)
@{
unsigned long long tick;
__asm__ __volatile__("rdtsc":"=A"(tick));
return tick;
@}
@end smallexample
This is not correct on x86-64 as it would allocate tick in either @code{ax}
or @code{dx}. You have to use the following variant instead:
@smallexample
unsigned long long rdtsc (void)
@{
unsigned int tickl, tickh;
__asm__ __volatile__("rdtsc":"=a"(tickl),"=d"(tickh));
return ((unsigned long long)tickh << 32)|tickl;
@}
@end smallexample
@item U
The call-clobbered integer registers.
@item f
Any 80387 floating-point (stack) register.
@item t
Top of 80387 floating-point stack (@code{%st(0)}).
@item u
Second from top of 80387 floating-point stack (@code{%st(1)}).
@ifset INTERNALS
@item Yk
Any mask register that can be used as a predicate, i.e.@: @code{k1-k7}.
@item k
Any mask register.
@end ifset
@item y
Any MMX register.
@item x
Any SSE register.
@item v
Any EVEX encodable SSE register (@code{%xmm0-%xmm31}).
@ifset INTERNALS
@item w
Any bound register.
@end ifset
@item Yz
First SSE register (@code{%xmm0}).
@ifset INTERNALS
@item Yi
Any SSE register, when SSE2 and inter-unit moves are enabled.
@item Yj
Any SSE register, when SSE2 and inter-unit moves from vector registers are enabled.
@item Ym
Any MMX register, when inter-unit moves are enabled.
@item Yn
Any MMX register, when inter-unit moves from vector registers are enabled.
@item Yp
Any integer register when @code{TARGET_PARTIAL_REG_STALL} is disabled.
@item Ya
Any integer register when zero extensions with @code{AND} are disabled.
@item Yb
Any register that can be used as the GOT base when calling@*
@code{___tls_get_addr}: that is, any general register except @code{a}
and @code{sp} registers, for @option{-fno-plt} if linker supports it.
Otherwise, @code{b} register.
@item Yf
Any x87 register when 80387 floating-point arithmetic is enabled.
@item Yr
Lower SSE register when avoiding REX prefix and all SSE registers otherwise.
@item Yv
For AVX512VL, any EVEX-encodable SSE register (@code{%xmm0-%xmm31}),
otherwise any SSE register.
@item Yh
Any EVEX-encodable SSE register, that has number factor of four.
@item Bf
Flags register operand.
@item Bg
GOT memory operand.
@item Bm
Vector memory operand.
@item Bc
Constant memory operand.
@item Bn
Memory operand without REX prefix.
@item Bs
Sibcall memory operand.
@item Bw
Call memory operand.
@item Bz
Constant call address operand.
@item BC
SSE constant -1 operand.
@end ifset
@item I
Integer constant in the range 0 @dots{} 31, for 32-bit shifts.
@item J
Integer constant in the range 0 @dots{} 63, for 64-bit shifts.
@item K
Signed 8-bit integer constant.
@item L
@code{0xFF} or @code{0xFFFF}, for andsi as a zero-extending move.
@item M
0, 1, 2, or 3 (shifts for the @code{lea} instruction).
@item N
Unsigned 8-bit integer constant (for @code{in} and @code{out}
instructions).
@ifset INTERNALS
@item O
Integer constant in the range 0 @dots{} 127, for 128-bit shifts.
@end ifset
@item G
Standard 80387 floating point constant.
@item C
SSE constant zero operand.
@item e
32-bit signed integer constant, or a symbolic reference known
to fit that range (for immediate operands in sign-extending x86-64
instructions).
@item We
32-bit signed integer constant, or a symbolic reference known
to fit that range (for sign-extending conversion operations that
require non-@code{VOIDmode} immediate operands).
@item Wz
32-bit unsigned integer constant, or a symbolic reference known
to fit that range (for zero-extending conversion operations that
require non-@code{VOIDmode} immediate operands).
@item Wd
128-bit integer constant where both the high and low 64-bit word
satisfy the @code{e} constraint.
@item Z
32-bit unsigned integer constant, or a symbolic reference known
to fit that range (for immediate operands in zero-extending x86-64
instructions).
@item Tv
VSIB address operand.
@item Ts
Address operand without segment register.
@end table
@item Xstormy16---@file{config/stormy16/stormy16.h}
@table @code
@item a
Register r0.
@item b
Register r1.
@item c
Register r2.
@item d
Register r8.
@item e
Registers r0 through r7.
@item t
Registers r0 and r1.
@item y
The carry register.
@item z
Registers r8 and r9.
@item I
A constant between 0 and 3 inclusive.
@item J
A constant that has exactly one bit set.
@item K
A constant that has exactly one bit clear.
@item L
A constant between 0 and 255 inclusive.
@item M
A constant between @minus{}255 and 0 inclusive.
@item N
A constant between @minus{}3 and 0 inclusive.
@item O
A constant between 1 and 4 inclusive.
@item P
A constant between @minus{}4 and @minus{}1 inclusive.
@item Q
A memory reference that is a stack push.
@item R
A memory reference that is a stack pop.
@item S
A memory reference that refers to a constant address of known value.
@item T
The register indicated by Rx (not implemented yet).
@item U
A constant that is not between 2 and 15 inclusive.
@item Z
The constant 0.
@end table
@item Xtensa---@file{config/xtensa/constraints.md}
@table @code
@item a
General-purpose 32-bit register
@item b
One-bit boolean register
@item A
MAC16 40-bit accumulator register
@item I
Signed 12-bit integer constant, for use in MOVI instructions
@item J
Signed 8-bit integer constant, for use in ADDI instructions
@item K
Integer constant valid for BccI instructions
@item L
Unsigned constant valid for BccUI instructions
@end table
@end table
@ifset INTERNALS
@node Disable Insn Alternatives
@subsection Disable insn alternatives using the @code{enabled} attribute
@cindex enabled
There are three insn attributes that may be used to selectively disable
instruction alternatives:
@table @code
@item enabled
Says whether an alternative is available on the current subtarget.
@item preferred_for_size
Says whether an enabled alternative should be used in code that is
optimized for size.
@item preferred_for_speed
Says whether an enabled alternative should be used in code that is
optimized for speed.
@end table
All these attributes should use @code{(const_int 1)} to allow an alternative
or @code{(const_int 0)} to disallow it. The attributes must be a static
property of the subtarget; they cannot for example depend on the
current operands, on the current optimization level, on the location
of the insn within the body of a loop, on whether register allocation
has finished, or on the current compiler pass.
The @code{enabled} attribute is a correctness property. It tells GCC to act
as though the disabled alternatives were never defined in the first place.
This is useful when adding new instructions to an existing pattern in
cases where the new instructions are only available for certain cpu
architecture levels (typically mapped to the @code{-march=} command-line
option).
In contrast, the @code{preferred_for_size} and @code{preferred_for_speed}
attributes are strong optimization hints rather than correctness properties.
@code{preferred_for_size} tells GCC which alternatives to consider when
adding or modifying an instruction that GCC wants to optimize for size.
@code{preferred_for_speed} does the same thing for speed. Note that things
like code motion can lead to cases where code optimized for size uses
alternatives that are not preferred for size, and similarly for speed.
Although @code{define_insn}s can in principle specify the @code{enabled}
attribute directly, it is often clearer to have subsiduary attributes
for each architectural feature of interest. The @code{define_insn}s
can then use these subsiduary attributes to say which alternatives
require which features. The example below does this for @code{cpu_facility}.
E.g. the following two patterns could easily be merged using the @code{enabled}
attribute:
@smallexample
(define_insn "*movdi_old"
[(set (match_operand:DI 0 "register_operand" "=d")
(match_operand:DI 1 "register_operand" " d"))]
"!TARGET_NEW"
"lgr %0,%1")
(define_insn "*movdi_new"
[(set (match_operand:DI 0 "register_operand" "=d,f,d")
(match_operand:DI 1 "register_operand" " d,d,f"))]
"TARGET_NEW"
"@@
lgr %0,%1
ldgr %0,%1
lgdr %0,%1")
@end smallexample
to:
@smallexample
(define_insn "*movdi_combined"
[(set (match_operand:DI 0 "register_operand" "=d,f,d")
(match_operand:DI 1 "register_operand" " d,d,f"))]
""
"@@
lgr %0,%1
ldgr %0,%1
lgdr %0,%1"
[(set_attr "cpu_facility" "*,new,new")])
@end smallexample
with the @code{enabled} attribute defined like this:
@smallexample
(define_attr "cpu_facility" "standard,new" (const_string "standard"))
(define_attr "enabled" ""
(cond [(eq_attr "cpu_facility" "standard") (const_int 1)
(and (eq_attr "cpu_facility" "new")
(ne (symbol_ref "TARGET_NEW") (const_int 0)))
(const_int 1)]
(const_int 0)))
@end smallexample
@end ifset
@ifset INTERNALS
@node Define Constraints
@subsection Defining Machine-Specific Constraints
@cindex defining constraints
@cindex constraints, defining
Machine-specific constraints fall into two categories: register and
non-register constraints. Within the latter category, constraints
which allow subsets of all possible memory or address operands should
be specially marked, to give @code{reload} more information.
Machine-specific constraints can be given names of arbitrary length,
but they must be entirely composed of letters, digits, underscores
(@samp{_}), and angle brackets (@samp{< >}). Like C identifiers, they
must begin with a letter or underscore.
In order to avoid ambiguity in operand constraint strings, no
constraint can have a name that begins with any other constraint's
name. For example, if @code{x} is defined as a constraint name,
@code{xy} may not be, and vice versa. As a consequence of this rule,
no constraint may begin with one of the generic constraint letters:
@samp{E F V X g i m n o p r s}.
Register constraints correspond directly to register classes.
@xref{Register Classes}. There is thus not much flexibility in their
definitions.
@deffn {MD Expression} define_register_constraint name regclass docstring
All three arguments are string constants.
@var{name} is the name of the constraint, as it will appear in
@code{match_operand} expressions. If @var{name} is a multi-letter
constraint its length shall be the same for all constraints starting
with the same letter. @var{regclass} can be either the
name of the corresponding register class (@pxref{Register Classes}),
or a C expression which evaluates to the appropriate register class.
If it is an expression, it must have no side effects, and it cannot
look at the operand. The usual use of expressions is to map some
register constraints to @code{NO_REGS} when the register class
is not available on a given subarchitecture.
@var{docstring} is a sentence documenting the meaning of the
constraint. Docstrings are explained further below.
@end deffn
Non-register constraints are more like predicates: the constraint
definition gives a boolean expression which indicates whether the
constraint matches.
@deffn {MD Expression} define_constraint name docstring exp
The @var{name} and @var{docstring} arguments are the same as for
@code{define_register_constraint}, but note that the docstring comes
immediately after the name for these expressions. @var{exp} is an RTL
expression, obeying the same rules as the RTL expressions in predicate
definitions. @xref{Defining Predicates}, for details. If it
evaluates true, the constraint matches; if it evaluates false, it
doesn't. Constraint expressions should indicate which RTL codes they
might match, just like predicate expressions.
@code{match_test} C expressions have access to the
following variables:
@table @var
@item op
The RTL object defining the operand.
@item mode
The machine mode of @var{op}.
@item ival
@samp{INTVAL (@var{op})}, if @var{op} is a @code{const_int}.
@item hval
@samp{CONST_DOUBLE_HIGH (@var{op})}, if @var{op} is an integer
@code{const_double}.
@item lval
@samp{CONST_DOUBLE_LOW (@var{op})}, if @var{op} is an integer
@code{const_double}.
@item rval
@samp{CONST_DOUBLE_REAL_VALUE (@var{op})}, if @var{op} is a floating-point
@code{const_double}.
@end table
The @var{*val} variables should only be used once another piece of the
expression has verified that @var{op} is the appropriate kind of RTL
object.
@end deffn
Most non-register constraints should be defined with
@code{define_constraint}. The remaining two definition expressions
are only appropriate for constraints that should be handled specially
by @code{reload} if they fail to match.
@deffn {MD Expression} define_memory_constraint name docstring exp
Use this expression for constraints that match a subset of all memory
operands: that is, @code{reload} can make them match by converting the
operand to the form @samp{@w{(mem (reg @var{X}))}}, where @var{X} is a
base register (from the register class specified by
@code{BASE_REG_CLASS}, @pxref{Register Classes}).
For example, on the S/390, some instructions do not accept arbitrary
memory references, but only those that do not make use of an index
register. The constraint letter @samp{Q} is defined to represent a
memory address of this type. If @samp{Q} is defined with
@code{define_memory_constraint}, a @samp{Q} constraint can handle any
memory operand, because @code{reload} knows it can simply copy the
memory address into a base register if required. This is analogous to
the way an @samp{o} constraint can handle any memory operand.
The syntax and semantics are otherwise identical to
@code{define_constraint}.
@end deffn
@deffn {MD Expression} define_special_memory_constraint name docstring exp
Use this expression for constraints that match a subset of all memory
operands: that is, @code{reload} cannot make them match by reloading
the address as it is described for @code{define_memory_constraint} or
such address reload is undesirable with the performance point of view.
For example, @code{define_special_memory_constraint} can be useful if
specifically aligned memory is necessary or desirable for some insn
operand.
The syntax and semantics are otherwise identical to
@code{define_memory_constraint}.
@end deffn
@deffn {MD Expression} define_relaxed_memory_constraint name docstring exp
The test expression in a @code{define_memory_constraint} can assume
that @code{TARGET_LEGITIMATE_ADDRESS_P} holds for the address inside
a @code{mem} rtx and so it does not need to test this condition itself.
In other words, a @code{define_memory_constraint} test of the form:
@smallexample
(match_test "mem")
@end smallexample
is enough to test whether an rtx is a @code{mem} @emph{and} whether
its address satisfies @code{TARGET_MEM_CONSTRAINT} (which is usually
@samp{'m'}). Thus the conditions imposed by a @code{define_memory_constraint}
always apply on top of the conditions imposed by @code{TARGET_MEM_CONSTRAINT}.
However, it is sometimes useful to define memory constraints that allow
addresses beyond those accepted by @code{TARGET_LEGITIMATE_ADDRESS_P}.
@code{define_relaxed_memory_constraint} exists for this case.
The test expression in a @code{define_relaxed_memory_constraint} is
applied with no preconditions, so that the expression can determine
``from scratch'' exactly which addresses are valid and which are not.
The syntax and semantics are otherwise identical to
@code{define_memory_constraint}.
@end deffn
@deffn {MD Expression} define_address_constraint name docstring exp
Use this expression for constraints that match a subset of all address
operands: that is, @code{reload} can make the constraint match by
converting the operand to the form @samp{@w{(reg @var{X})}}, again
with @var{X} a base register.
Constraints defined with @code{define_address_constraint} can only be
used with the @code{address_operand} predicate, or machine-specific
predicates that work the same way. They are treated analogously to
the generic @samp{p} constraint.
The syntax and semantics are otherwise identical to
@code{define_constraint}.
@end deffn
For historical reasons, names beginning with the letters @samp{G H}
are reserved for constraints that match only @code{const_double}s, and
names beginning with the letters @samp{I J K L M N O P} are reserved
for constraints that match only @code{const_int}s. This may change in
the future. For the time being, constraints with these names must be
written in a stylized form, so that @code{genpreds} can tell you did
it correctly:
@smallexample
@group
(define_constraint "[@var{GHIJKLMNOP}]@dots{}"
"@var{doc}@dots{}"
(and (match_code "const_int") ; @r{@code{const_double} for G/H}
@var{condition}@dots{})) ; @r{usually a @code{match_test}}
@end group
@end smallexample
@c the semicolons line up in the formatted manual
It is fine to use names beginning with other letters for constraints
that match @code{const_double}s or @code{const_int}s.
Each docstring in a constraint definition should be one or more complete
sentences, marked up in Texinfo format. @emph{They are currently unused.}
In the future they will be copied into the GCC manual, in @ref{Machine
Constraints}, replacing the hand-maintained tables currently found in
that section. Also, in the future the compiler may use this to give
more helpful diagnostics when poor choice of @code{asm} constraints
causes a reload failure.
If you put the pseudo-Texinfo directive @samp{@@internal} at the
beginning of a docstring, then (in the future) it will appear only in
the internals manual's version of the machine-specific constraint tables.
Use this for constraints that should not appear in @code{asm} statements.
@node C Constraint Interface
@subsection Testing constraints from C
@cindex testing constraints
@cindex constraints, testing
It is occasionally useful to test a constraint from C code rather than
implicitly via the constraint string in a @code{match_operand}. The
generated file @file{tm_p.h} declares a few interfaces for working
with constraints. At present these are defined for all constraints
except @code{g} (which is equivalent to @code{general_operand}).
Some valid constraint names are not valid C identifiers, so there is a
mangling scheme for referring to them from C@. Constraint names that
do not contain angle brackets or underscores are left unchanged.
Underscores are doubled, each @samp{<} is replaced with @samp{_l}, and
each @samp{>} with @samp{_g}. Here are some examples:
@c the @c's prevent double blank lines in the printed manual.
@example
@multitable {Original} {Mangled}
@item @strong{Original} @tab @strong{Mangled} @c
@item @code{x} @tab @code{x} @c
@item @code{P42x} @tab @code{P42x} @c
@item @code{P4_x} @tab @code{P4__x} @c
@item @code{P4>x} @tab @code{P4_gx} @c
@item @code{P4>>} @tab @code{P4_g_g} @c
@item @code{P4_g>} @tab @code{P4__g_g} @c
@end multitable
@end example
Throughout this section, the variable @var{c} is either a constraint
in the abstract sense, or a constant from @code{enum constraint_num};
the variable @var{m} is a mangled constraint name (usually as part of
a larger identifier).
@deftp Enum constraint_num
For each constraint except @code{g}, there is a corresponding
enumeration constant: @samp{CONSTRAINT_} plus the mangled name of the
constraint. Functions that take an @code{enum constraint_num} as an
argument expect one of these constants.
@end deftp
@deftypefun {inline bool} satisfies_constraint_@var{m} (rtx @var{exp})
For each non-register constraint @var{m} except @code{g}, there is
one of these functions; it returns @code{true} if @var{exp} satisfies the
constraint. These functions are only visible if @file{rtl.h} was included
before @file{tm_p.h}.
@end deftypefun
@deftypefun bool constraint_satisfied_p (rtx @var{exp}, enum constraint_num @var{c})
Like the @code{satisfies_constraint_@var{m}} functions, but the
constraint to test is given as an argument, @var{c}. If @var{c}
specifies a register constraint, this function will always return
@code{false}.
@end deftypefun
@deftypefun {enum reg_class} reg_class_for_constraint (enum constraint_num @var{c})
Returns the register class associated with @var{c}. If @var{c} is not
a register constraint, or those registers are not available for the
currently selected subtarget, returns @code{NO_REGS}.
@end deftypefun
Here is an example use of @code{satisfies_constraint_@var{m}}. In
peephole optimizations (@pxref{Peephole Definitions}), operand
constraint strings are ignored, so if there are relevant constraints,
they must be tested in the C condition. In the example, the
optimization is applied if operand 2 does @emph{not} satisfy the
@samp{K} constraint. (This is a simplified version of a peephole
definition from the i386 machine description.)
@smallexample
(define_peephole2
[(match_scratch:SI 3 "r")
(set (match_operand:SI 0 "register_operand" "")
(mult:SI (match_operand:SI 1 "memory_operand" "")
(match_operand:SI 2 "immediate_operand" "")))]
"!satisfies_constraint_K (operands[2])"
[(set (match_dup 3) (match_dup 1))
(set (match_dup 0) (mult:SI (match_dup 3) (match_dup 2)))]
"")
@end smallexample
@node Standard Names
@section Standard Pattern Names For Generation
@cindex standard pattern names
@cindex pattern names
@cindex names, pattern
Here is a table of the instruction names that are meaningful in the RTL
generation pass of the compiler. Giving one of these names to an
instruction pattern tells the RTL generation pass that it can use the
pattern to accomplish a certain task.
@table @asis
@cindex @code{mov@var{m}} instruction pattern
@item @samp{mov@var{m}}
Here @var{m} stands for a two-letter machine mode name, in lowercase.
This instruction pattern moves data with that machine mode from operand
1 to operand 0. For example, @samp{movsi} moves full-word data.
If operand 0 is a @code{subreg} with mode @var{m} of a register whose
own mode is wider than @var{m}, the effect of this instruction is
to store the specified value in the part of the register that corresponds
to mode @var{m}. Bits outside of @var{m}, but which are within the
same target word as the @code{subreg} are undefined. Bits which are
outside the target word are left unchanged.
This class of patterns is special in several ways. First of all, each
of these names up to and including full word size @emph{must} be defined,
because there is no other way to copy a datum from one place to another.
If there are patterns accepting operands in larger modes,
@samp{mov@var{m}} must be defined for integer modes of those sizes.
Second, these patterns are not used solely in the RTL generation pass.
Even the reload pass can generate move insns to copy values from stack
slots into temporary registers. When it does so, one of the operands is
a hard register and the other is an operand that can need to be reloaded
into a register.
@findex force_reg
Therefore, when given such a pair of operands, the pattern must generate
RTL which needs no reloading and needs no temporary registers---no
registers other than the operands. For example, if you support the
pattern with a @code{define_expand}, then in such a case the
@code{define_expand} mustn't call @code{force_reg} or any other such
function which might generate new pseudo registers.
This requirement exists even for subword modes on a RISC machine where
fetching those modes from memory normally requires several insns and
some temporary registers.
@findex change_address
During reload a memory reference with an invalid address may be passed
as an operand. Such an address will be replaced with a valid address
later in the reload pass. In this case, nothing may be done with the
address except to use it as it stands. If it is copied, it will not be
replaced with a valid address. No attempt should be made to make such
an address into a valid address and no routine (such as
@code{change_address}) that will do so may be called. Note that
@code{general_operand} will fail when applied to such an address.
@findex reload_in_progress
The global variable @code{reload_in_progress} (which must be explicitly
declared if required) can be used to determine whether such special
handling is required.
The variety of operands that have reloads depends on the rest of the
machine description, but typically on a RISC machine these can only be
pseudo registers that did not get hard registers, while on other
machines explicit memory references will get optional reloads.
If a scratch register is required to move an object to or from memory,
it can be allocated using @code{gen_reg_rtx} prior to life analysis.
If there are cases which need scratch registers during or after reload,
you must provide an appropriate secondary_reload target hook.
@findex can_create_pseudo_p
The macro @code{can_create_pseudo_p} can be used to determine if it
is unsafe to create new pseudo registers. If this variable is nonzero, then
it is unsafe to call @code{gen_reg_rtx} to allocate a new pseudo.
The constraints on a @samp{mov@var{m}} must permit moving any hard
register to any other hard register provided that
@code{TARGET_HARD_REGNO_MODE_OK} permits mode @var{m} in both registers and
@code{TARGET_REGISTER_MOVE_COST} applied to their classes returns a value
of 2.
It is obligatory to support floating point @samp{mov@var{m}}
instructions into and out of any registers that can hold fixed point
values, because unions and structures (which have modes @code{SImode} or
@code{DImode}) can be in those registers and they may have floating
point members.
There may also be a need to support fixed point @samp{mov@var{m}}
instructions in and out of floating point registers. Unfortunately, I
have forgotten why this was so, and I don't know whether it is still
true. If @code{TARGET_HARD_REGNO_MODE_OK} rejects fixed point values in
floating point registers, then the constraints of the fixed point
@samp{mov@var{m}} instructions must be designed to avoid ever trying to
reload into a floating point register.
@cindex @code{reload_in} instruction pattern
@cindex @code{reload_out} instruction pattern
@item @samp{reload_in@var{m}}
@itemx @samp{reload_out@var{m}}
These named patterns have been obsoleted by the target hook
@code{secondary_reload}.
Like @samp{mov@var{m}}, but used when a scratch register is required to
move between operand 0 and operand 1. Operand 2 describes the scratch
register. See the discussion of the @code{SECONDARY_RELOAD_CLASS}
macro in @pxref{Register Classes}.
There are special restrictions on the form of the @code{match_operand}s
used in these patterns. First, only the predicate for the reload
operand is examined, i.e., @code{reload_in} examines operand 1, but not
the predicates for operand 0 or 2. Second, there may be only one
alternative in the constraints. Third, only a single register class
letter may be used for the constraint; subsequent constraint letters
are ignored. As a special exception, an empty constraint string
matches the @code{ALL_REGS} register class. This may relieve ports
of the burden of defining an @code{ALL_REGS} constraint letter just
for these patterns.
@cindex @code{movstrict@var{m}} instruction pattern
@item @samp{movstrict@var{m}}
Like @samp{mov@var{m}} except that if operand 0 is a @code{subreg}
with mode @var{m} of a register whose natural mode is wider,
the @samp{movstrict@var{m}} instruction is guaranteed not to alter
any of the register except the part which belongs to mode @var{m}.
@cindex @code{movmisalign@var{m}} instruction pattern
@item @samp{movmisalign@var{m}}
This variant of a move pattern is designed to load or store a value
from a memory address that is not naturally aligned for its mode.
For a store, the memory will be in operand 0; for a load, the memory
will be in operand 1. The other operand is guaranteed not to be a
memory, so that it's easy to tell whether this is a load or store.
This pattern is used by the autovectorizer, and when expanding a
@code{MISALIGNED_INDIRECT_REF} expression.
@cindex @code{load_multiple} instruction pattern
@item @samp{load_multiple}
Load several consecutive memory locations into consecutive registers.
Operand 0 is the first of the consecutive registers, operand 1
is the first memory location, and operand 2 is a constant: the
number of consecutive registers.
Define this only if the target machine really has such an instruction;
do not define this if the most efficient way of loading consecutive
registers from memory is to do them one at a time.
On some machines, there are restrictions as to which consecutive
registers can be stored into memory, such as particular starting or
ending register numbers or only a range of valid counts. For those
machines, use a @code{define_expand} (@pxref{Expander Definitions})
and make the pattern fail if the restrictions are not met.
Write the generated insn as a @code{parallel} with elements being a
@code{set} of one register from the appropriate memory location (you may
also need @code{use} or @code{clobber} elements). Use a
@code{match_parallel} (@pxref{RTL Template}) to recognize the insn. See
@file{rs6000.md} for examples of the use of this insn pattern.
@cindex @samp{store_multiple} instruction pattern
@item @samp{store_multiple}
Similar to @samp{load_multiple}, but store several consecutive registers
into consecutive memory locations. Operand 0 is the first of the
consecutive memory locations, operand 1 is the first register, and
operand 2 is a constant: the number of consecutive registers.
@cindex @code{vec_load_lanes@var{m}@var{n}} instruction pattern
@item @samp{vec_load_lanes@var{m}@var{n}}
Perform an interleaved load of several vectors from memory operand 1
into register operand 0. Both operands have mode @var{m}. The register
operand is viewed as holding consecutive vectors of mode @var{n},
while the memory operand is a flat array that contains the same number
of elements. The operation is equivalent to:
@smallexample
int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
for (i = 0; i < c; i++)
operand0[i][j] = operand1[j * c + i];
@end smallexample
For example, @samp{vec_load_lanestiv4hi} loads 8 16-bit values
from memory into a register of mode @samp{TI}@. The register
contains two consecutive vectors of mode @samp{V4HI}@.
This pattern can only be used if:
@smallexample
TARGET_ARRAY_MODE_SUPPORTED_P (@var{n}, @var{c})
@end smallexample
is true. GCC assumes that, if a target supports this kind of
instruction for some mode @var{n}, it also supports unaligned
loads for vectors of mode @var{n}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{vec_mask_load_lanes@var{m}@var{n}} instruction pattern
@item @samp{vec_mask_load_lanes@var{m}@var{n}}
Like @samp{vec_load_lanes@var{m}@var{n}}, but takes an additional
mask operand (operand 2) that specifies which elements of the destination
vectors should be loaded. Other elements of the destination
vectors are set to zero. The operation is equivalent to:
@smallexample
int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
if (operand2[j])
for (i = 0; i < c; i++)
operand0[i][j] = operand1[j * c + i];
else
for (i = 0; i < c; i++)
operand0[i][j] = 0;
@end smallexample
This pattern is not allowed to @code{FAIL}.
@cindex @code{vec_store_lanes@var{m}@var{n}} instruction pattern
@item @samp{vec_store_lanes@var{m}@var{n}}
Equivalent to @samp{vec_load_lanes@var{m}@var{n}}, with the memory
and register operands reversed. That is, the instruction is
equivalent to:
@smallexample
int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
for (i = 0; i < c; i++)
operand0[j * c + i] = operand1[i][j];
@end smallexample
for a memory operand 0 and register operand 1.
This pattern is not allowed to @code{FAIL}.
@cindex @code{vec_mask_store_lanes@var{m}@var{n}} instruction pattern
@item @samp{vec_mask_store_lanes@var{m}@var{n}}
Like @samp{vec_store_lanes@var{m}@var{n}}, but takes an additional
mask operand (operand 2) that specifies which elements of the source
vectors should be stored. The operation is equivalent to:
@smallexample
int c = GET_MODE_SIZE (@var{m}) / GET_MODE_SIZE (@var{n});
for (j = 0; j < GET_MODE_NUNITS (@var{n}); j++)
if (operand2[j])
for (i = 0; i < c; i++)
operand0[j * c + i] = operand1[i][j];
@end smallexample
This pattern is not allowed to @code{FAIL}.
@cindex @code{gather_load@var{m}@var{n}} instruction pattern
@item @samp{gather_load@var{m}@var{n}}
Load several separate memory locations into a vector of mode @var{m}.
Operand 1 is a scalar base address and operand 2 is a vector of mode @var{n}
containing offsets from that base. Operand 0 is a destination vector with
the same number of elements as @var{n}. For each element index @var{i}:
@itemize @bullet
@item
extend the offset element @var{i} to address width, using zero
extension if operand 3 is 1 and sign extension if operand 3 is zero;
@item
multiply the extended offset by operand 4;
@item
add the result to the base; and
@item
load the value at that address into element @var{i} of operand 0.
@end itemize
The value of operand 3 does not matter if the offsets are already
address width.
@cindex @code{mask_gather_load@var{m}@var{n}} instruction pattern
@item @samp{mask_gather_load@var{m}@var{n}}
Like @samp{gather_load@var{m}@var{n}}, but takes an extra mask operand as
operand 5. Bit @var{i} of the mask is set if element @var{i}
of the result should be loaded from memory and clear if element @var{i}
of the result should be set to zero.
@cindex @code{len_mask_gather_load@var{m}@var{n}} instruction pattern
@item @samp{len_mask_gather_load@var{m}@var{n}}
Like @samp{gather_load@var{m}@var{n}}, but takes an extra length operand (operand 5),
a bias operand (operand 6) as well as a mask operand (operand 7). Similar to len_maskload,
the instruction loads at most (operand 5 + operand 6) elements from memory.
Bit @var{i} of the mask is set if element @var{i} of the result should
be loaded from memory and clear if element @var{i} of the result should be undefined.
Mask elements @var{i} with @var{i} > (operand 5 + operand 6) are ignored.
@cindex @code{scatter_store@var{m}@var{n}} instruction pattern
@item @samp{scatter_store@var{m}@var{n}}
Store a vector of mode @var{m} into several distinct memory locations.
Operand 0 is a scalar base address and operand 1 is a vector of mode
@var{n} containing offsets from that base. Operand 4 is the vector of
values that should be stored, which has the same number of elements as
@var{n}. For each element index @var{i}:
@itemize @bullet
@item
extend the offset element @var{i} to address width, using zero
extension if operand 2 is 1 and sign extension if operand 2 is zero;
@item
multiply the extended offset by operand 3;
@item
add the result to the base; and
@item
store element @var{i} of operand 4 to that address.
@end itemize
The value of operand 2 does not matter if the offsets are already
address width.
@cindex @code{mask_scatter_store@var{m}@var{n}} instruction pattern
@item @samp{mask_scatter_store@var{m}@var{n}}
Like @samp{scatter_store@var{m}@var{n}}, but takes an extra mask operand as
operand 5. Bit @var{i} of the mask is set if element @var{i}
of the result should be stored to memory.
@cindex @code{len_mask_scatter_store@var{m}@var{n}} instruction pattern
@item @samp{len_mask_scatter_store@var{m}@var{n}}
Like @samp{scatter_store@var{m}@var{n}}, but takes an extra length operand (operand 5),
a bias operand (operand 6) as well as a mask operand (operand 7). The instruction stores
at most (operand 5 + operand 6) elements of (operand 4) to memory.
Bit @var{i} of the mask is set if element @var{i} of (operand 4) should be stored.
Mask elements @var{i} with @var{i} > (operand 5 + operand 6) are ignored.
@cindex @code{vec_set@var{m}} instruction pattern
@item @samp{vec_set@var{m}}
Set given field in the vector value. Operand 0 is the vector to modify,
operand 1 is new value of field and operand 2 specify the field index.
@cindex @code{vec_extract@var{m}@var{n}} instruction pattern
@item @samp{vec_extract@var{m}@var{n}}
Extract given field from the vector value. Operand 1 is the vector, operand 2
specify field index and operand 0 place to store value into. The
@var{n} mode is the mode of the field or vector of fields that should be
extracted, should be either element mode of the vector mode @var{m}, or
a vector mode with the same element mode and smaller number of elements.
If @var{n} is a vector mode, the index is counted in units of that mode.
@cindex @code{vec_init@var{m}@var{n}} instruction pattern
@item @samp{vec_init@var{m}@var{n}}
Initialize the vector to given values. Operand 0 is the vector to initialize
and operand 1 is parallel containing values for individual fields. The
@var{n} mode is the mode of the elements, should be either element mode of
the vector mode @var{m}, or a vector mode with the same element mode and
smaller number of elements.
@cindex @code{vec_duplicate@var{m}} instruction pattern
@item @samp{vec_duplicate@var{m}}
Initialize vector output operand 0 so that each element has the value given
by scalar input operand 1. The vector has mode @var{m} and the scalar has
the mode appropriate for one element of @var{m}.
This pattern only handles duplicates of non-constant inputs. Constant
vectors go through the @code{mov@var{m}} pattern instead.
This pattern is not allowed to @code{FAIL}.
@cindex @code{vec_series@var{m}} instruction pattern
@item @samp{vec_series@var{m}}
Initialize vector output operand 0 so that element @var{i} is equal to
operand 1 plus @var{i} times operand 2. In other words, create a linear
series whose base value is operand 1 and whose step is operand 2.
The vector output has mode @var{m} and the scalar inputs have the mode
appropriate for one element of @var{m}. This pattern is not used for
floating-point vectors, in order to avoid having to specify the
rounding behavior for @var{i} > 1.
This pattern is not allowed to @code{FAIL}.
@cindex @code{while_ult@var{m}@var{n}} instruction pattern
@item @code{while_ult@var{m}@var{n}}
Set operand 0 to a mask that is true while incrementing operand 1
gives a value that is less than operand 2, for a vector length up to operand 3.
Operand 0 has mode @var{n} and operands 1 and 2 are scalar integers of mode
@var{m}. Operand 3 should be omitted when @var{n} is a vector mode, and
a @code{CONST_INT} otherwise. The operation for vector modes is equivalent to:
@smallexample
operand0[0] = operand1 < operand2;
for (i = 1; i < GET_MODE_NUNITS (@var{n}); i++)
operand0[i] = operand0[i - 1] && (operand1 + i < operand2);
@end smallexample
And for non-vector modes the operation is equivalent to:
@smallexample
operand0[0] = operand1 < operand2;
for (i = 1; i < operand3; i++)
operand0[i] = operand0[i - 1] && (operand1 + i < operand2);
@end smallexample
@cindex @code{select_vl@var{m}} instruction pattern
@item @code{select_vl@var{m}}
Set operand 0 to the number of scalar iterations that should be handled
by one iteration of a vector loop. Operand 1 is the total number of
scalar iterations that the loop needs to process and operand 2 is a
maximum bound on the result (also known as the maximum ``vectorization
factor'').
The maximum value of operand 0 is given by:
@smallexample
operand0 = MIN (operand1, operand2)
@end smallexample
However, targets might choose a lower value than this, based on
target-specific criteria. Each iteration of the vector loop might
therefore process a different number of scalar iterations, which in turn
means that induction variables will have a variable step. Because of
this, it is generally not useful to define this instruction if it will
always calculate the maximum value.
This optab is only useful on targets that implement @samp{len_load_@var{m}}
and/or @samp{len_store_@var{m}}.
@cindex @code{check_raw_ptrs@var{m}} instruction pattern
@item @samp{check_raw_ptrs@var{m}}
Check whether, given two pointers @var{a} and @var{b} and a length @var{len},
a write of @var{len} bytes at @var{a} followed by a read of @var{len} bytes
at @var{b} can be split into interleaved byte accesses
@samp{@var{a}[0], @var{b}[0], @var{a}[1], @var{b}[1], @dots{}}
without affecting the dependencies between the bytes. Set operand 0
to true if the split is possible and false otherwise.
Operands 1, 2 and 3 provide the values of @var{a}, @var{b} and @var{len}
respectively. Operand 4 is a constant integer that provides the known
common alignment of @var{a} and @var{b}. All inputs have mode @var{m}.
This split is possible if:
@smallexample
@var{a} == @var{b} || @var{a} + @var{len} <= @var{b} || @var{b} + @var{len} <= @var{a}
@end smallexample
You should only define this pattern if the target has a way of accelerating
the test without having to do the individual comparisons.
@cindex @code{check_war_ptrs@var{m}} instruction pattern
@item @samp{check_war_ptrs@var{m}}
Like @samp{check_raw_ptrs@var{m}}, but with the read and write swapped round.
The split is possible in this case if:
@smallexample
@var{b} <= @var{a} || @var{a} + @var{len} <= @var{b}
@end smallexample
@cindex @code{vec_cmp@var{m}@var{n}} instruction pattern
@item @samp{vec_cmp@var{m}@var{n}}
Output a vector comparison. Operand 0 of mode @var{n} is the destination for
predicate in operand 1 which is a signed vector comparison with operands of
mode @var{m} in operands 2 and 3. Predicate is computed by element-wise
evaluation of the vector comparison with a truth value of all-ones and a false
value of all-zeros.
@cindex @code{vec_cmpu@var{m}@var{n}} instruction pattern
@item @samp{vec_cmpu@var{m}@var{n}}
Similar to @code{vec_cmp@var{m}@var{n}} but perform unsigned vector comparison.
@cindex @code{vec_cmpeq@var{m}@var{n}} instruction pattern
@item @samp{vec_cmpeq@var{m}@var{n}}
Similar to @code{vec_cmp@var{m}@var{n}} but perform equality or non-equality
vector comparison only. If @code{vec_cmp@var{m}@var{n}}
or @code{vec_cmpu@var{m}@var{n}} instruction pattern is supported,
it will be preferred over @code{vec_cmpeq@var{m}@var{n}}, so there is
no need to define this instruction pattern if the others are supported.
@cindex @code{vcond@var{m}@var{n}} instruction pattern
@item @samp{vcond@var{m}@var{n}}
Output a conditional vector move. Operand 0 is the destination to
receive a combination of operand 1 and operand 2, which are of mode @var{m},
dependent on the outcome of the predicate in operand 3 which is a signed
vector comparison with operands of mode @var{n} in operands 4 and 5. The
modes @var{m} and @var{n} should have the same size. Operand 0
will be set to the value @var{op1} & @var{msk} | @var{op2} & ~@var{msk}
where @var{msk} is computed by element-wise evaluation of the vector
comparison with a truth value of all-ones and a false value of all-zeros.
@cindex @code{vcondu@var{m}@var{n}} instruction pattern
@item @samp{vcondu@var{m}@var{n}}
Similar to @code{vcond@var{m}@var{n}} but performs unsigned vector
comparison.
@cindex @code{vcondeq@var{m}@var{n}} instruction pattern
@item @samp{vcondeq@var{m}@var{n}}
Similar to @code{vcond@var{m}@var{n}} but performs equality or
non-equality vector comparison only. If @code{vcond@var{m}@var{n}}
or @code{vcondu@var{m}@var{n}} instruction pattern is supported,
it will be preferred over @code{vcondeq@var{m}@var{n}}, so there is
no need to define this instruction pattern if the others are supported.
@cindex @code{vcond_mask_@var{m}@var{n}} instruction pattern
@item @samp{vcond_mask_@var{m}@var{n}}
Similar to @code{vcond@var{m}@var{n}} but operand 3 holds a pre-computed
result of vector comparison.
@cindex @code{maskload@var{m}@var{n}} instruction pattern
@item @samp{maskload@var{m}@var{n}}
Perform a masked load of vector from memory operand 1 of mode @var{m}
into register operand 0. Mask is provided in register operand 2 of
mode @var{n}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{maskstore@var{m}@var{n}} instruction pattern
@item @samp{maskstore@var{m}@var{n}}
Perform a masked store of vector from register operand 1 of mode @var{m}
into memory operand 0. Mask is provided in register operand 2 of
mode @var{n}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{len_load_@var{m}} instruction pattern
@item @samp{len_load_@var{m}}
Load (operand 2 + operand 3) elements from memory operand 1
into vector register operand 0, setting the other elements of
operand 0 to undefined values. Operands 0 and 1 have mode @var{m},
which must be a vector mode. Operand 2 has whichever integer mode the
target prefers. Operand 3 conceptually has mode @code{QI}.
Operand 2 can be a variable or a constant amount. Operand 3 specifies a
constant bias: it is either a constant 0 or a constant -1. The predicate on
operand 3 must only accept the bias values that the target actually supports.
GCC handles a bias of 0 more efficiently than a bias of -1.
If (operand 2 + operand 3) exceeds the number of elements in mode
@var{m}, the behavior is undefined.
If the target prefers the length to be measured in bytes rather than
elements, it should only implement this pattern for vectors of @code{QI}
elements.
This pattern is not allowed to @code{FAIL}.
@cindex @code{len_store_@var{m}} instruction pattern
@item @samp{len_store_@var{m}}
Store (operand 2 + operand 3) vector elements from vector register operand 1
into memory operand 0, leaving the other elements of
operand 0 unchanged. Operands 0 and 1 have mode @var{m}, which must be
a vector mode. Operand 2 has whichever integer mode the target prefers.
Operand 3 conceptually has mode @code{QI}.
Operand 2 can be a variable or a constant amount. Operand 3 specifies a
constant bias: it is either a constant 0 or a constant -1. The predicate on
operand 3 must only accept the bias values that the target actually supports.
GCC handles a bias of 0 more efficiently than a bias of -1.
If (operand 2 + operand 3) exceeds the number of elements in mode
@var{m}, the behavior is undefined.
If the target prefers the length to be measured in bytes
rather than elements, it should only implement this pattern for vectors
of @code{QI} elements.
This pattern is not allowed to @code{FAIL}.
@cindex @code{len_maskload@var{m}@var{n}} instruction pattern
@item @samp{len_maskload@var{m}@var{n}}
Perform a masked load from the memory location pointed to by operand 1
into register operand 0. (operand 2 + operand 3) elements are loaded from
memory and other elements in operand 0 are set to undefined values.
This is a combination of len_load and maskload.
Operands 0 and 1 have mode @var{m}, which must be a vector mode. Operand 2
has whichever integer mode the target prefers. A mask is specified in
operand 4 which must be of type @var{n}. The mask has lower precedence than
the length and is itself subject to length masking,
i.e. only mask indices < (operand 2 + operand 3) are used.
Operand 3 conceptually has mode @code{QI}.
Operand 2 can be a variable or a constant amount. Operand 4 specifies a
constant bias: it is either a constant 0 or a constant -1. The predicate on
operand 4 must only accept the bias values that the target actually supports.
GCC handles a bias of 0 more efficiently than a bias of -1.
If (operand 2 + operand 4) exceeds the number of elements in mode
@var{m}, the behavior is undefined.
If the target prefers the length to be measured in bytes
rather than elements, it should only implement this pattern for vectors
of @code{QI} elements.
This pattern is not allowed to @code{FAIL}.
@cindex @code{len_maskstore@var{m}@var{n}} instruction pattern
@item @samp{len_maskstore@var{m}@var{n}}
Perform a masked store from vector register operand 1 into memory operand 0.
(operand 2 + operand 3) elements are stored to memory
and leave the other elements of operand 0 unchanged.
This is a combination of len_store and maskstore.
Operands 0 and 1 have mode @var{m}, which must be a vector mode. Operand 2 has whichever
integer mode the target prefers. A mask is specified in operand 4 which must be
of type @var{n}. The mask has lower precedence than the length and is itself subject to
length masking, i.e. only mask indices < (operand 2 + operand 3) are used.
Operand 3 conceptually has mode @code{QI}.
Operand 2 can be a variable or a constant amount. Operand 3 specifies a
constant bias: it is either a constant 0 or a constant -1. The predicate on
operand 4 must only accept the bias values that the target actually supports.
GCC handles a bias of 0 more efficiently than a bias of -1.
If (operand 2 + operand 4) exceeds the number of elements in mode
@var{m}, the behavior is undefined.
If the target prefers the length to be measured in bytes
rather than elements, it should only implement this pattern for vectors
of @code{QI} elements.
This pattern is not allowed to @code{FAIL}.
@cindex @code{vec_perm@var{m}} instruction pattern
@item @samp{vec_perm@var{m}}
Output a (variable) vector permutation. Operand 0 is the destination
to receive elements from operand 1 and operand 2, which are of mode
@var{m}. Operand 3 is the @dfn{selector}. It is an integral mode
vector of the same width and number of elements as mode @var{m}.
The input elements are numbered from 0 in operand 1 through
@math{2*@var{N}-1} in operand 2. The elements of the selector must
be computed modulo @math{2*@var{N}}. Note that if
@code{rtx_equal_p(operand1, operand2)}, this can be implemented
with just operand 1 and selector elements modulo @var{N}.
In order to make things easy for a number of targets, if there is no
@samp{vec_perm} pattern for mode @var{m}, but there is for mode @var{q}
where @var{q} is a vector of @code{QImode} of the same width as @var{m},
the middle-end will lower the mode @var{m} @code{VEC_PERM_EXPR} to
mode @var{q}.
See also @code{TARGET_VECTORIZER_VEC_PERM_CONST}, which performs
the analogous operation for constant selectors.
@cindex @code{push@var{m}1} instruction pattern
@item @samp{push@var{m}1}
Output a push instruction. Operand 0 is value to push. Used only when
@code{PUSH_ROUNDING} is defined. For historical reason, this pattern may be
missing and in such case an @code{mov} expander is used instead, with a
@code{MEM} expression forming the push operation. The @code{mov} expander
method is deprecated.
@cindex @code{add@var{m}3} instruction pattern
@item @samp{add@var{m}3}
Add operand 2 and operand 1, storing the result in operand 0. All operands
must have mode @var{m}. This can be used even on two-address machines, by
means of constraints requiring operands 1 and 0 to be the same location.
@cindex @code{ssadd@var{m}3} instruction pattern
@cindex @code{usadd@var{m}3} instruction pattern
@cindex @code{sub@var{m}3} instruction pattern
@cindex @code{sssub@var{m}3} instruction pattern
@cindex @code{ussub@var{m}3} instruction pattern
@cindex @code{mul@var{m}3} instruction pattern
@cindex @code{ssmul@var{m}3} instruction pattern
@cindex @code{usmul@var{m}3} instruction pattern
@cindex @code{div@var{m}3} instruction pattern
@cindex @code{ssdiv@var{m}3} instruction pattern
@cindex @code{udiv@var{m}3} instruction pattern
@cindex @code{usdiv@var{m}3} instruction pattern
@cindex @code{mod@var{m}3} instruction pattern
@cindex @code{umod@var{m}3} instruction pattern
@cindex @code{umin@var{m}3} instruction pattern
@cindex @code{umax@var{m}3} instruction pattern
@cindex @code{and@var{m}3} instruction pattern
@cindex @code{ior@var{m}3} instruction pattern
@cindex @code{xor@var{m}3} instruction pattern
@item @samp{ssadd@var{m}3}, @samp{usadd@var{m}3}
@itemx @samp{sub@var{m}3}, @samp{sssub@var{m}3}, @samp{ussub@var{m}3}
@itemx @samp{mul@var{m}3}, @samp{ssmul@var{m}3}, @samp{usmul@var{m}3}
@itemx @samp{div@var{m}3}, @samp{ssdiv@var{m}3}
@itemx @samp{udiv@var{m}3}, @samp{usdiv@var{m}3}
@itemx @samp{mod@var{m}3}, @samp{umod@var{m}3}
@itemx @samp{umin@var{m}3}, @samp{umax@var{m}3}
@itemx @samp{and@var{m}3}, @samp{ior@var{m}3}, @samp{xor@var{m}3}
Similar, for other arithmetic operations.
@cindex @code{addv@var{m}4} instruction pattern
@item @samp{addv@var{m}4}
Like @code{add@var{m}3} but takes a @code{code_label} as operand 3 and
emits code to jump to it if signed overflow occurs during the addition.
This pattern is used to implement the built-in functions performing
signed integer addition with overflow checking.
@cindex @code{subv@var{m}4} instruction pattern
@cindex @code{mulv@var{m}4} instruction pattern
@item @samp{subv@var{m}4}, @samp{mulv@var{m}4}
Similar, for other signed arithmetic operations.
@cindex @code{uaddv@var{m}4} instruction pattern
@item @samp{uaddv@var{m}4}
Like @code{addv@var{m}4} but for unsigned addition. That is to
say, the operation is the same as signed addition but the jump
is taken only on unsigned overflow.
@cindex @code{usubv@var{m}4} instruction pattern
@cindex @code{umulv@var{m}4} instruction pattern
@item @samp{usubv@var{m}4}, @samp{umulv@var{m}4}
Similar, for other unsigned arithmetic operations.
@cindex @code{uaddc@var{m}5} instruction pattern
@item @samp{uaddc@var{m}5}
Adds unsigned operands 2, 3 and 4 (where the last operand is guaranteed to
have only values 0 or 1) together, sets operand 0 to the result of the
addition of the 3 operands and sets operand 1 to 1 iff there was
overflow on the unsigned additions, and to 0 otherwise. So, it is
an addition with carry in (operand 4) and carry out (operand 1).
All operands have the same mode.
@cindex @code{usubc@var{m}5} instruction pattern
@item @samp{usubc@var{m}5}
Similarly to @samp{uaddc@var{m}5}, except subtracts unsigned operands 3
and 4 from operand 2 instead of adding them. So, it is
a subtraction with carry/borrow in (operand 4) and carry/borrow out
(operand 1). All operands have the same mode.
@cindex @code{addptr@var{m}3} instruction pattern
@item @samp{addptr@var{m}3}
Like @code{add@var{m}3} but is guaranteed to only be used for address
calculations. The expanded code is not allowed to clobber the
condition code. It only needs to be defined if @code{add@var{m}3}
sets the condition code. If adds used for address calculations and
normal adds are not compatible it is required to expand a distinct
pattern (e.g.@: using an unspec). The pattern is used by LRA to emit
address calculations. @code{add@var{m}3} is used if
@code{addptr@var{m}3} is not defined.
@cindex @code{fma@var{m}4} instruction pattern
@item @samp{fma@var{m}4}
Multiply operand 2 and operand 1, then add operand 3, storing the
result in operand 0 without doing an intermediate rounding step. All
operands must have mode @var{m}. This pattern is used to implement
the @code{fma}, @code{fmaf}, and @code{fmal} builtin functions from
the ISO C99 standard.
@cindex @code{fms@var{m}4} instruction pattern
@item @samp{fms@var{m}4}
Like @code{fma@var{m}4}, except operand 3 subtracted from the
product instead of added to the product. This is represented
in the rtl as
@smallexample
(fma:@var{m} @var{op1} @var{op2} (neg:@var{m} @var{op3}))
@end smallexample
@cindex @code{fnma@var{m}4} instruction pattern
@item @samp{fnma@var{m}4}
Like @code{fma@var{m}4} except that the intermediate product
is negated before being added to operand 3. This is represented
in the rtl as
@smallexample
(fma:@var{m} (neg:@var{m} @var{op1}) @var{op2} @var{op3})
@end smallexample
@cindex @code{fnms@var{m}4} instruction pattern
@item @samp{fnms@var{m}4}
Like @code{fms@var{m}4} except that the intermediate product
is negated before subtracting operand 3. This is represented
in the rtl as
@smallexample
(fma:@var{m} (neg:@var{m} @var{op1}) @var{op2} (neg:@var{m} @var{op3}))
@end smallexample
@cindex @code{min@var{m}3} instruction pattern
@cindex @code{max@var{m}3} instruction pattern
@item @samp{smin@var{m}3}, @samp{smax@var{m}3}
Signed minimum and maximum operations. When used with floating point,
if both operands are zeros, or if either operand is @code{NaN}, then
it is unspecified which of the two operands is returned as the result.
@cindex @code{fmin@var{m}3} instruction pattern
@cindex @code{fmax@var{m}3} instruction pattern
@item @samp{fmin@var{m}3}, @samp{fmax@var{m}3}
IEEE-conformant minimum and maximum operations. If one operand is a quiet
@code{NaN}, then the other operand is returned. If both operands are quiet
@code{NaN}, then a quiet @code{NaN} is returned. In the case when gcc supports
signaling @code{NaN} (-fsignaling-nans) an invalid floating point exception is
raised and a quiet @code{NaN} is returned.
All operands have mode @var{m}, which is a scalar or vector
floating-point mode. These patterns are not allowed to @code{FAIL}.
@cindex @code{reduc_smin_scal_@var{m}} instruction pattern
@cindex @code{reduc_smax_scal_@var{m}} instruction pattern
@item @samp{reduc_smin_scal_@var{m}}, @samp{reduc_smax_scal_@var{m}}
Find the signed minimum/maximum of the elements of a vector. The vector is
operand 1, and operand 0 is the scalar result, with mode equal to the mode of
the elements of the input vector.
@cindex @code{reduc_umin_scal_@var{m}} instruction pattern
@cindex @code{reduc_umax_scal_@var{m}} instruction pattern
@item @samp{reduc_umin_scal_@var{m}}, @samp{reduc_umax_scal_@var{m}}
Find the unsigned minimum/maximum of the elements of a vector. The vector is
operand 1, and operand 0 is the scalar result, with mode equal to the mode of
the elements of the input vector.
@cindex @code{reduc_fmin_scal_@var{m}} instruction pattern
@cindex @code{reduc_fmax_scal_@var{m}} instruction pattern
@item @samp{reduc_fmin_scal_@var{m}}, @samp{reduc_fmax_scal_@var{m}}
Find the floating-point minimum/maximum of the elements of a vector,
using the same rules as @code{fmin@var{m}3} and @code{fmax@var{m}3}.
Operand 1 is a vector of mode @var{m} and operand 0 is the scalar
result, which has mode @code{GET_MODE_INNER (@var{m})}.
@cindex @code{reduc_plus_scal_@var{m}} instruction pattern
@item @samp{reduc_plus_scal_@var{m}}
Compute the sum of the elements of a vector. The vector is operand 1, and
operand 0 is the scalar result, with mode equal to the mode of the elements of
the input vector.
@cindex @code{reduc_and_scal_@var{m}} instruction pattern
@cindex @code{reduc_ior_scal_@var{m}} instruction pattern
@cindex @code{reduc_xor_scal_@var{m}} instruction pattern
@item @samp{reduc_and_scal_@var{m}}
@itemx @samp{reduc_ior_scal_@var{m}}
@itemx @samp{reduc_xor_scal_@var{m}}
Compute the bitwise @code{AND}/@code{IOR}/@code{XOR} reduction of the elements
of a vector of mode @var{m}. Operand 1 is the vector input and operand 0
is the scalar result. The mode of the scalar result is the same as one
element of @var{m}.
@cindex @code{extract_last_@var{m}} instruction pattern
@item @code{extract_last_@var{m}}
Find the last set bit in mask operand 1 and extract the associated element
of vector operand 2. Store the result in scalar operand 0. Operand 2
has vector mode @var{m} while operand 0 has the mode appropriate for one
element of @var{m}. Operand 1 has the usual mask mode for vectors of mode
@var{m}; see @code{TARGET_VECTORIZE_GET_MASK_MODE}.
@cindex @code{fold_extract_last_@var{m}} instruction pattern
@item @code{fold_extract_last_@var{m}}
If any bits of mask operand 2 are set, find the last set bit, extract
the associated element from vector operand 3, and store the result
in operand 0. Store operand 1 in operand 0 otherwise. Operand 3
has mode @var{m} and operands 0 and 1 have the mode appropriate for
one element of @var{m}. Operand 2 has the usual mask mode for vectors
of mode @var{m}; see @code{TARGET_VECTORIZE_GET_MASK_MODE}.
@cindex @code{fold_left_plus_@var{m}} instruction pattern
@item @code{fold_left_plus_@var{m}}
Take scalar operand 1 and successively add each element from vector
operand 2. Store the result in scalar operand 0. The vector has
mode @var{m} and the scalars have the mode appropriate for one
element of @var{m}. The operation is strictly in-order: there is
no reassociation.
@cindex @code{mask_fold_left_plus_@var{m}} instruction pattern
@item @code{mask_fold_left_plus_@var{m}}
Like @samp{fold_left_plus_@var{m}}, but takes an additional mask operand
(operand 3) that specifies which elements of the source vector should be added.
@cindex @code{sdot_prod@var{m}} instruction pattern
@item @samp{sdot_prod@var{m}}
Compute the sum of the products of two signed elements.
Operand 1 and operand 2 are of the same mode. Their
product, which is of a wider mode, is computed and added to operand 3.
Operand 3 is of a mode equal or wider than the mode of the product. The
result is placed in operand 0, which is of the same mode as operand 3.
Semantically the expressions perform the multiplication in the following signs
@smallexample
sdot<signed op0, signed op1, signed op2, signed op3> ==
op0 = sign-ext (op1) * sign-ext (op2) + op3
@dots{}
@end smallexample
@cindex @code{udot_prod@var{m}} instruction pattern
@item @samp{udot_prod@var{m}}
Compute the sum of the products of two unsigned elements.
Operand 1 and operand 2 are of the same mode. Their
product, which is of a wider mode, is computed and added to operand 3.
Operand 3 is of a mode equal or wider than the mode of the product. The
result is placed in operand 0, which is of the same mode as operand 3.
Semantically the expressions perform the multiplication in the following signs
@smallexample
udot<unsigned op0, unsigned op1, unsigned op2, unsigned op3> ==
op0 = zero-ext (op1) * zero-ext (op2) + op3
@dots{}
@end smallexample
@cindex @code{usdot_prod@var{m}} instruction pattern
@item @samp{usdot_prod@var{m}}
Compute the sum of the products of elements of different signs.
Operand 1 must be unsigned and operand 2 signed. Their
product, which is of a wider mode, is computed and added to operand 3.
Operand 3 is of a mode equal or wider than the mode of the product. The
result is placed in operand 0, which is of the same mode as operand 3.
Semantically the expressions perform the multiplication in the following signs
@smallexample
usdot<signed op0, unsigned op1, signed op2, signed op3> ==
op0 = ((signed-conv) zero-ext (op1)) * sign-ext (op2) + op3
@dots{}
@end smallexample
@cindex @code{ssad@var{m}} instruction pattern
@cindex @code{usad@var{m}} instruction pattern
@item @samp{ssad@var{m}}
@item @samp{usad@var{m}}
Compute the sum of absolute differences of two signed/unsigned elements.
Operand 1 and operand 2 are of the same mode. Their absolute difference, which
is of a wider mode, is computed and added to operand 3. Operand 3 is of a mode
equal or wider than the mode of the absolute difference. The result is placed
in operand 0, which is of the same mode as operand 3.
@cindex @code{widen_ssum@var{m3}} instruction pattern
@cindex @code{widen_usum@var{m3}} instruction pattern
@item @samp{widen_ssum@var{m3}}
@itemx @samp{widen_usum@var{m3}}
Operands 0 and 2 are of the same mode, which is wider than the mode of
operand 1. Add operand 1 to operand 2 and place the widened result in
operand 0. (This is used express accumulation of elements into an accumulator
of a wider mode.)
@cindex @code{smulhs@var{m3}} instruction pattern
@cindex @code{umulhs@var{m3}} instruction pattern
@item @samp{smulhs@var{m3}}
@itemx @samp{umulhs@var{m3}}
Signed/unsigned multiply high with scale. This is equivalent to the C code:
@smallexample
narrow op0, op1, op2;
@dots{}
op0 = (narrow) (((wide) op1 * (wide) op2) >> (N / 2 - 1));
@end smallexample
where the sign of @samp{narrow} determines whether this is a signed
or unsigned operation, and @var{N} is the size of @samp{wide} in bits.
@cindex @code{smulhrs@var{m3}} instruction pattern
@cindex @code{umulhrs@var{m3}} instruction pattern
@item @samp{smulhrs@var{m3}}
@itemx @samp{umulhrs@var{m3}}
Signed/unsigned multiply high with round and scale. This is
equivalent to the C code:
@smallexample
narrow op0, op1, op2;
@dots{}
op0 = (narrow) (((((wide) op1 * (wide) op2) >> (N / 2 - 2)) + 1) >> 1);
@end smallexample
where the sign of @samp{narrow} determines whether this is a signed
or unsigned operation, and @var{N} is the size of @samp{wide} in bits.
@cindex @code{sdiv_pow2@var{m3}} instruction pattern
@cindex @code{sdiv_pow2@var{m3}} instruction pattern
@item @samp{sdiv_pow2@var{m3}}
@itemx @samp{sdiv_pow2@var{m3}}
Signed division by power-of-2 immediate. Equivalent to:
@smallexample
signed op0, op1;
@dots{}
op0 = op1 / (1 << imm);
@end smallexample
@cindex @code{vec_shl_insert_@var{m}} instruction pattern
@item @samp{vec_shl_insert_@var{m}}
Shift the elements in vector input operand 1 left one element (i.e.@:
away from element 0) and fill the vacated element 0 with the scalar
in operand 2. Store the result in vector output operand 0. Operands
0 and 1 have mode @var{m} and operand 2 has the mode appropriate for
one element of @var{m}.
@cindex @code{vec_shl_@var{m}} instruction pattern
@item @samp{vec_shl_@var{m}}
Whole vector left shift in bits, i.e.@: away from element 0.
Operand 1 is a vector to be shifted.
Operand 2 is an integer shift amount in bits.
Operand 0 is where the resulting shifted vector is stored.
The output and input vectors should have the same modes.
@cindex @code{vec_shr_@var{m}} instruction pattern
@item @samp{vec_shr_@var{m}}
Whole vector right shift in bits, i.e.@: towards element 0.
Operand 1 is a vector to be shifted.
Operand 2 is an integer shift amount in bits.
Operand 0 is where the resulting shifted vector is stored.
The output and input vectors should have the same modes.
@cindex @code{vec_pack_trunc_@var{m}} instruction pattern
@item @samp{vec_pack_trunc_@var{m}}
Narrow (demote) and merge the elements of two vectors. Operands 1 and 2
are vectors of the same mode having N integral or floating point elements
of size S@. Operand 0 is the resulting vector in which 2*N elements of
size S/2 are concatenated after narrowing them down using truncation.
@cindex @code{vec_pack_sbool_trunc_@var{m}} instruction pattern
@item @samp{vec_pack_sbool_trunc_@var{m}}
Narrow and merge the elements of two vectors. Operands 1 and 2 are vectors
of the same type having N boolean elements. Operand 0 is the resulting
vector in which 2*N elements are concatenated. The last operand (operand 3)
is the number of elements in the output vector 2*N as a @code{CONST_INT}.
This instruction pattern is used when all the vector input and output
operands have the same scalar mode @var{m} and thus using
@code{vec_pack_trunc_@var{m}} would be ambiguous.
@cindex @code{vec_pack_ssat_@var{m}} instruction pattern
@cindex @code{vec_pack_usat_@var{m}} instruction pattern
@item @samp{vec_pack_ssat_@var{m}}, @samp{vec_pack_usat_@var{m}}
Narrow (demote) and merge the elements of two vectors. Operands 1 and 2
are vectors of the same mode having N integral elements of size S.
Operand 0 is the resulting vector in which the elements of the two input
vectors are concatenated after narrowing them down using signed/unsigned
saturating arithmetic.
@cindex @code{vec_pack_sfix_trunc_@var{m}} instruction pattern
@cindex @code{vec_pack_ufix_trunc_@var{m}} instruction pattern
@item @samp{vec_pack_sfix_trunc_@var{m}}, @samp{vec_pack_ufix_trunc_@var{m}}
Narrow, convert to signed/unsigned integral type and merge the elements
of two vectors. Operands 1 and 2 are vectors of the same mode having N
floating point elements of size S@. Operand 0 is the resulting vector
in which 2*N elements of size S/2 are concatenated.
@cindex @code{vec_packs_float_@var{m}} instruction pattern
@cindex @code{vec_packu_float_@var{m}} instruction pattern
@item @samp{vec_packs_float_@var{m}}, @samp{vec_packu_float_@var{m}}
Narrow, convert to floating point type and merge the elements
of two vectors. Operands 1 and 2 are vectors of the same mode having N
signed/unsigned integral elements of size S@. Operand 0 is the resulting vector
in which 2*N elements of size S/2 are concatenated.
@cindex @code{vec_unpacks_hi_@var{m}} instruction pattern
@cindex @code{vec_unpacks_lo_@var{m}} instruction pattern
@item @samp{vec_unpacks_hi_@var{m}}, @samp{vec_unpacks_lo_@var{m}}
Extract and widen (promote) the high/low part of a vector of signed
integral or floating point elements. The input vector (operand 1) has N
elements of size S@. Widen (promote) the high/low elements of the vector
using signed or floating point extension and place the resulting N/2
values of size 2*S in the output vector (operand 0).
@cindex @code{vec_unpacku_hi_@var{m}} instruction pattern
@cindex @code{vec_unpacku_lo_@var{m}} instruction pattern
@item @samp{vec_unpacku_hi_@var{m}}, @samp{vec_unpacku_lo_@var{m}}
Extract and widen (promote) the high/low part of a vector of unsigned
integral elements. The input vector (operand 1) has N elements of size S.
Widen (promote) the high/low elements of the vector using zero extension and
place the resulting N/2 values of size 2*S in the output vector (operand 0).
@cindex @code{vec_unpacks_sbool_hi_@var{m}} instruction pattern
@cindex @code{vec_unpacks_sbool_lo_@var{m}} instruction pattern
@item @samp{vec_unpacks_sbool_hi_@var{m}}, @samp{vec_unpacks_sbool_lo_@var{m}}
Extract the high/low part of a vector of boolean elements that have scalar
mode @var{m}. The input vector (operand 1) has N elements, the output
vector (operand 0) has N/2 elements. The last operand (operand 2) is the
number of elements of the input vector N as a @code{CONST_INT}. These
patterns are used if both the input and output vectors have the same scalar
mode @var{m} and thus using @code{vec_unpacks_hi_@var{m}} or
@code{vec_unpacks_lo_@var{m}} would be ambiguous.
@cindex @code{vec_unpacks_float_hi_@var{m}} instruction pattern
@cindex @code{vec_unpacks_float_lo_@var{m}} instruction pattern
@cindex @code{vec_unpacku_float_hi_@var{m}} instruction pattern
@cindex @code{vec_unpacku_float_lo_@var{m}} instruction pattern
@item @samp{vec_unpacks_float_hi_@var{m}}, @samp{vec_unpacks_float_lo_@var{m}}
@itemx @samp{vec_unpacku_float_hi_@var{m}}, @samp{vec_unpacku_float_lo_@var{m}}
Extract, convert to floating point type and widen the high/low part of a
vector of signed/unsigned integral elements. The input vector (operand 1)
has N elements of size S@. Convert the high/low elements of the vector using
floating point conversion and place the resulting N/2 values of size 2*S in
the output vector (operand 0).
@cindex @code{vec_unpack_sfix_trunc_hi_@var{m}} instruction pattern
@cindex @code{vec_unpack_sfix_trunc_lo_@var{m}} instruction pattern
@cindex @code{vec_unpack_ufix_trunc_hi_@var{m}} instruction pattern
@cindex @code{vec_unpack_ufix_trunc_lo_@var{m}} instruction pattern
@item @samp{vec_unpack_sfix_trunc_hi_@var{m}},
@itemx @samp{vec_unpack_sfix_trunc_lo_@var{m}}
@itemx @samp{vec_unpack_ufix_trunc_hi_@var{m}}
@itemx @samp{vec_unpack_ufix_trunc_lo_@var{m}}
Extract, convert to signed/unsigned integer type and widen the high/low part of a
vector of floating point elements. The input vector (operand 1)
has N elements of size S@. Convert the high/low elements of the vector
to integers and place the resulting N/2 values of size 2*S in
the output vector (operand 0).
@cindex @code{vec_widen_umult_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_umult_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_smult_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_smult_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_umult_even_@var{m}} instruction pattern
@cindex @code{vec_widen_umult_odd_@var{m}} instruction pattern
@cindex @code{vec_widen_smult_even_@var{m}} instruction pattern
@cindex @code{vec_widen_smult_odd_@var{m}} instruction pattern
@item @samp{vec_widen_umult_hi_@var{m}}, @samp{vec_widen_umult_lo_@var{m}}
@itemx @samp{vec_widen_smult_hi_@var{m}}, @samp{vec_widen_smult_lo_@var{m}}
@itemx @samp{vec_widen_umult_even_@var{m}}, @samp{vec_widen_umult_odd_@var{m}}
@itemx @samp{vec_widen_smult_even_@var{m}}, @samp{vec_widen_smult_odd_@var{m}}
Signed/Unsigned widening multiplication. The two inputs (operands 1 and 2)
are vectors with N signed/unsigned elements of size S@. Multiply the high/low
or even/odd elements of the two vectors, and put the N/2 products of size 2*S
in the output vector (operand 0). A target shouldn't implement even/odd pattern
pair if it is less efficient than lo/hi one.
@cindex @code{vec_widen_ushiftl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_ushiftl_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_sshiftl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_sshiftl_lo_@var{m}} instruction pattern
@item @samp{vec_widen_ushiftl_hi_@var{m}}, @samp{vec_widen_ushiftl_lo_@var{m}}
@itemx @samp{vec_widen_sshiftl_hi_@var{m}}, @samp{vec_widen_sshiftl_lo_@var{m}}
Signed/Unsigned widening shift left. The first input (operand 1) is a vector
with N signed/unsigned elements of size S@. Operand 2 is a constant. Shift
the high/low elements of operand 1, and put the N/2 results of size 2*S in the
output vector (operand 0).
@cindex @code{vec_widen_saddl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_saddl_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_uaddl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_uaddl_lo_@var{m}} instruction pattern
@item @samp{vec_widen_uaddl_hi_@var{m}}, @samp{vec_widen_uaddl_lo_@var{m}}
@itemx @samp{vec_widen_saddl_hi_@var{m}}, @samp{vec_widen_saddl_lo_@var{m}}
Signed/Unsigned widening add long. Operands 1 and 2 are vectors with N
signed/unsigned elements of size S@. Add the high/low elements of 1 and 2
together, widen the resulting elements and put the N/2 results of size 2*S in
the output vector (operand 0).
@cindex @code{vec_widen_ssubl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_ssubl_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_usubl_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_usubl_lo_@var{m}} instruction pattern
@item @samp{vec_widen_usubl_hi_@var{m}}, @samp{vec_widen_usubl_lo_@var{m}}
@itemx @samp{vec_widen_ssubl_hi_@var{m}}, @samp{vec_widen_ssubl_lo_@var{m}}
Signed/Unsigned widening subtract long. Operands 1 and 2 are vectors with N
signed/unsigned elements of size S@. Subtract the high/low elements of 2 from
1 and widen the resulting elements. Put the N/2 results of size 2*S in the
output vector (operand 0).
@cindex @code{vec_widen_sabd_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_sabd_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_sabd_odd_@var{m}} instruction pattern
@cindex @code{vec_widen_sabd_even_@var{m}} instruction pattern
@cindex @code{vec_widen_uabd_hi_@var{m}} instruction pattern
@cindex @code{vec_widen_uabd_lo_@var{m}} instruction pattern
@cindex @code{vec_widen_uabd_odd_@var{m}} instruction pattern
@cindex @code{vec_widen_uabd_even_@var{m}} instruction pattern
@item @samp{vec_widen_uabd_hi_@var{m}}, @samp{vec_widen_uabd_lo_@var{m}}
@itemx @samp{vec_widen_uabd_odd_@var{m}}, @samp{vec_widen_uabd_even_@var{m}}
@itemx @samp{vec_widen_sabd_hi_@var{m}}, @samp{vec_widen_sabd_lo_@var{m}}
@itemx @samp{vec_widen_sabd_odd_@var{m}}, @samp{vec_widen_sabd_even_@var{m}}
Signed/Unsigned widening absolute difference. Operands 1 and 2 are
vectors with N signed/unsigned elements of size S@. Find the absolute
difference between operands 1 and 2 and widen the resulting elements.
Put the N/2 results of size 2*S in the output vector (operand 0).
@cindex @code{vec_addsub@var{m}3} instruction pattern
@item @samp{vec_addsub@var{m}3}
Alternating subtract, add with even lanes doing subtract and odd
lanes doing addition. Operands 1 and 2 and the outout operand are vectors
with mode @var{m}.
@cindex @code{vec_fmaddsub@var{m}4} instruction pattern
@item @samp{vec_fmaddsub@var{m}4}
Alternating multiply subtract, add with even lanes doing subtract and odd
lanes doing addition of the third operand to the multiplication result
of the first two operands. Operands 1, 2 and 3 and the outout operand are vectors
with mode @var{m}.
@cindex @code{vec_fmsubadd@var{m}4} instruction pattern
@item @samp{vec_fmsubadd@var{m}4}
Alternating multiply add, subtract with even lanes doing addition and odd
lanes doing subtraction of the third operand to the multiplication result
of the first two operands. Operands 1, 2 and 3 and the outout operand are vectors
with mode @var{m}.
These instructions are not allowed to @code{FAIL}.
@cindex @code{mulhisi3} instruction pattern
@item @samp{mulhisi3}
Multiply operands 1 and 2, which have mode @code{HImode}, and store
a @code{SImode} product in operand 0.
@cindex @code{mulqihi3} instruction pattern
@cindex @code{mulsidi3} instruction pattern
@item @samp{mulqihi3}, @samp{mulsidi3}
Similar widening-multiplication instructions of other widths.
@cindex @code{umulqihi3} instruction pattern
@cindex @code{umulhisi3} instruction pattern
@cindex @code{umulsidi3} instruction pattern
@item @samp{umulqihi3}, @samp{umulhisi3}, @samp{umulsidi3}
Similar widening-multiplication instructions that do unsigned
multiplication.
@cindex @code{usmulqihi3} instruction pattern
@cindex @code{usmulhisi3} instruction pattern
@cindex @code{usmulsidi3} instruction pattern
@item @samp{usmulqihi3}, @samp{usmulhisi3}, @samp{usmulsidi3}
Similar widening-multiplication instructions that interpret the first
operand as unsigned and the second operand as signed, then do a signed
multiplication.
@cindex @code{smul@var{m}3_highpart} instruction pattern
@item @samp{smul@var{m}3_highpart}
Perform a signed multiplication of operands 1 and 2, which have mode
@var{m}, and store the most significant half of the product in operand 0.
The least significant half of the product is discarded. This may be
represented in RTL using a @code{smul_highpart} RTX expression.
@cindex @code{umul@var{m}3_highpart} instruction pattern
@item @samp{umul@var{m}3_highpart}
Similar, but the multiplication is unsigned. This may be represented
in RTL using an @code{umul_highpart} RTX expression.
@cindex @code{madd@var{m}@var{n}4} instruction pattern
@item @samp{madd@var{m}@var{n}4}
Multiply operands 1 and 2, sign-extend them to mode @var{n}, add
operand 3, and store the result in operand 0. Operands 1 and 2
have mode @var{m} and operands 0 and 3 have mode @var{n}.
Both modes must be integer or fixed-point modes and @var{n} must be twice
the size of @var{m}.
In other words, @code{madd@var{m}@var{n}4} is like
@code{mul@var{m}@var{n}3} except that it also adds operand 3.
These instructions are not allowed to @code{FAIL}.
@cindex @code{umadd@var{m}@var{n}4} instruction pattern
@item @samp{umadd@var{m}@var{n}4}
Like @code{madd@var{m}@var{n}4}, but zero-extend the multiplication
operands instead of sign-extending them.
@cindex @code{ssmadd@var{m}@var{n}4} instruction pattern
@item @samp{ssmadd@var{m}@var{n}4}
Like @code{madd@var{m}@var{n}4}, but all involved operations must be
signed-saturating.
@cindex @code{usmadd@var{m}@var{n}4} instruction pattern
@item @samp{usmadd@var{m}@var{n}4}
Like @code{umadd@var{m}@var{n}4}, but all involved operations must be
unsigned-saturating.
@cindex @code{msub@var{m}@var{n}4} instruction pattern
@item @samp{msub@var{m}@var{n}4}
Multiply operands 1 and 2, sign-extend them to mode @var{n}, subtract the
result from operand 3, and store the result in operand 0. Operands 1 and 2
have mode @var{m} and operands 0 and 3 have mode @var{n}.
Both modes must be integer or fixed-point modes and @var{n} must be twice
the size of @var{m}.
In other words, @code{msub@var{m}@var{n}4} is like
@code{mul@var{m}@var{n}3} except that it also subtracts the result
from operand 3.
These instructions are not allowed to @code{FAIL}.
@cindex @code{umsub@var{m}@var{n}4} instruction pattern
@item @samp{umsub@var{m}@var{n}4}
Like @code{msub@var{m}@var{n}4}, but zero-extend the multiplication
operands instead of sign-extending them.
@cindex @code{ssmsub@var{m}@var{n}4} instruction pattern
@item @samp{ssmsub@var{m}@var{n}4}
Like @code{msub@var{m}@var{n}4}, but all involved operations must be
signed-saturating.
@cindex @code{usmsub@var{m}@var{n}4} instruction pattern
@item @samp{usmsub@var{m}@var{n}4}
Like @code{umsub@var{m}@var{n}4}, but all involved operations must be
unsigned-saturating.
@cindex @code{divmod@var{m}4} instruction pattern
@item @samp{divmod@var{m}4}
Signed division that produces both a quotient and a remainder.
Operand 1 is divided by operand 2 to produce a quotient stored
in operand 0 and a remainder stored in operand 3.
For machines with an instruction that produces both a quotient and a
remainder, provide a pattern for @samp{divmod@var{m}4} but do not
provide patterns for @samp{div@var{m}3} and @samp{mod@var{m}3}. This
allows optimization in the relatively common case when both the quotient
and remainder are computed.
If an instruction that just produces a quotient or just a remainder
exists and is more efficient than the instruction that produces both,
write the output routine of @samp{divmod@var{m}4} to call
@code{find_reg_note} and look for a @code{REG_UNUSED} note on the
quotient or remainder and generate the appropriate instruction.
@cindex @code{udivmod@var{m}4} instruction pattern
@item @samp{udivmod@var{m}4}
Similar, but does unsigned division.
@anchor{shift patterns}
@cindex @code{ashl@var{m}3} instruction pattern
@cindex @code{ssashl@var{m}3} instruction pattern
@cindex @code{usashl@var{m}3} instruction pattern
@item @samp{ashl@var{m}3}, @samp{ssashl@var{m}3}, @samp{usashl@var{m}3}
Arithmetic-shift operand 1 left by a number of bits specified by operand
2, and store the result in operand 0. Here @var{m} is the mode of
operand 0 and operand 1; operand 2's mode is specified by the
instruction pattern, and the compiler will convert the operand to that
mode before generating the instruction. The shift or rotate expander
or instruction pattern should explicitly specify the mode of the operand 2,
it should never be @code{VOIDmode}. The meaning of out-of-range shift
counts can optionally be specified by @code{TARGET_SHIFT_TRUNCATION_MASK}.
@xref{TARGET_SHIFT_TRUNCATION_MASK}. Operand 2 is always a scalar type.
@cindex @code{ashr@var{m}3} instruction pattern
@cindex @code{lshr@var{m}3} instruction pattern
@cindex @code{rotl@var{m}3} instruction pattern
@cindex @code{rotr@var{m}3} instruction pattern
@item @samp{ashr@var{m}3}, @samp{lshr@var{m}3}, @samp{rotl@var{m}3}, @samp{rotr@var{m}3}
Other shift and rotate instructions, analogous to the
@code{ashl@var{m}3} instructions. Operand 2 is always a scalar type.
@cindex @code{vashl@var{m}3} instruction pattern
@cindex @code{vashr@var{m}3} instruction pattern
@cindex @code{vlshr@var{m}3} instruction pattern
@cindex @code{vrotl@var{m}3} instruction pattern
@cindex @code{vrotr@var{m}3} instruction pattern
@item @samp{vashl@var{m}3}, @samp{vashr@var{m}3}, @samp{vlshr@var{m}3}, @samp{vrotl@var{m}3}, @samp{vrotr@var{m}3}
Vector shift and rotate instructions that take vectors as operand 2
instead of a scalar type.
@cindex @code{uabd@var{m}} instruction pattern
@cindex @code{sabd@var{m}} instruction pattern
@item @samp{uabd@var{m}}, @samp{sabd@var{m}}
Signed and unsigned absolute difference instructions. These
instructions find the difference between operands 1 and 2
then return the absolute value. A C code equivalent would be:
@smallexample
op0 = op1 > op2 ? op1 - op2 : op2 - op1;
@end smallexample
@cindex @code{avg@var{m}3_floor} instruction pattern
@cindex @code{uavg@var{m}3_floor} instruction pattern
@item @samp{avg@var{m}3_floor}
@itemx @samp{uavg@var{m}3_floor}
Signed and unsigned average instructions. These instructions add
operands 1 and 2 without truncation, divide the result by 2,
round towards -Inf, and store the result in operand 0. This is
equivalent to the C code:
@smallexample
narrow op0, op1, op2;
@dots{}
op0 = (narrow) (((wide) op1 + (wide) op2) >> 1);
@end smallexample
where the sign of @samp{narrow} determines whether this is a signed
or unsigned operation.
@cindex @code{avg@var{m}3_ceil} instruction pattern
@cindex @code{uavg@var{m}3_ceil} instruction pattern
@item @samp{avg@var{m}3_ceil}
@itemx @samp{uavg@var{m}3_ceil}
Like @samp{avg@var{m}3_floor} and @samp{uavg@var{m}3_floor}, but round
towards +Inf. This is equivalent to the C code:
@smallexample
narrow op0, op1, op2;
@dots{}
op0 = (narrow) (((wide) op1 + (wide) op2 + 1) >> 1);
@end smallexample
@cindex @code{bswap@var{m}2} instruction pattern
@item @samp{bswap@var{m}2}
Reverse the order of bytes of operand 1 and store the result in operand 0.
@cindex @code{neg@var{m}2} instruction pattern
@cindex @code{ssneg@var{m}2} instruction pattern
@cindex @code{usneg@var{m}2} instruction pattern
@item @samp{neg@var{m}2}, @samp{ssneg@var{m}2}, @samp{usneg@var{m}2}
Negate operand 1 and store the result in operand 0.
@cindex @code{negv@var{m}3} instruction pattern
@item @samp{negv@var{m}3}
Like @code{neg@var{m}2} but takes a @code{code_label} as operand 2 and
emits code to jump to it if signed overflow occurs during the negation.
@cindex @code{abs@var{m}2} instruction pattern
@item @samp{abs@var{m}2}
Store the absolute value of operand 1 into operand 0.
@cindex @code{sqrt@var{m}2} instruction pattern
@item @samp{sqrt@var{m}2}
Store the square root of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{rsqrt@var{m}2} instruction pattern
@item @samp{rsqrt@var{m}2}
Store the reciprocal of the square root of operand 1 into operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode.
On most architectures this pattern is only approximate, so either
its C condition or the @code{TARGET_OPTAB_SUPPORTED_P} hook should
check for the appropriate math flags. (Using the C condition is
more direct, but using @code{TARGET_OPTAB_SUPPORTED_P} can be useful
if a target-specific built-in also uses the @samp{rsqrt@var{m}2}
pattern.)
This pattern is not allowed to @code{FAIL}.
@cindex @code{fmod@var{m}3} instruction pattern
@item @samp{fmod@var{m}3}
Store the remainder of dividing operand 1 by operand 2 into
operand 0, rounded towards zero to an integer. All operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{remainder@var{m}3} instruction pattern
@item @samp{remainder@var{m}3}
Store the remainder of dividing operand 1 by operand 2 into
operand 0, rounded to the nearest integer. All operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{scalb@var{m}3} instruction pattern
@item @samp{scalb@var{m}3}
Raise @code{FLT_RADIX} to the power of operand 2, multiply it by
operand 1, and store the result in operand 0. All operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{ldexp@var{m}3} instruction pattern
@item @samp{ldexp@var{m}3}
Raise 2 to the power of operand 2, multiply it by operand 1, and store
the result in operand 0. Operands 0 and 1 have mode @var{m}, which is
a scalar or vector floating-point mode. Operand 2's mode has
the same number of elements as @var{m} and each element is wide
enough to store an @code{int}. The integers are signed.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cos@var{m}2} instruction pattern
@item @samp{cos@var{m}2}
Store the cosine of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{sin@var{m}2} instruction pattern
@item @samp{sin@var{m}2}
Store the sine of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{sincos@var{m}3} instruction pattern
@item @samp{sincos@var{m}3}
Store the cosine of operand 2 into operand 0 and the sine of
operand 2 into operand 1. All operands have mode @var{m},
which is a scalar or vector floating-point mode.
Targets that can calculate the sine and cosine simultaneously can
implement this pattern as opposed to implementing individual
@code{sin@var{m}2} and @code{cos@var{m}2} patterns. The @code{sin}
and @code{cos} built-in functions will then be expanded to the
@code{sincos@var{m}3} pattern, with one of the output values
left unused.
@cindex @code{tan@var{m}2} instruction pattern
@item @samp{tan@var{m}2}
Store the tangent of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{asin@var{m}2} instruction pattern
@item @samp{asin@var{m}2}
Store the arc sine of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{acos@var{m}2} instruction pattern
@item @samp{acos@var{m}2}
Store the arc cosine of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{atan@var{m}2} instruction pattern
@item @samp{atan@var{m}2}
Store the arc tangent of operand 1 into operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{fegetround@var{m}} instruction pattern
@item @samp{fegetround@var{m}}
Store the current machine floating-point rounding mode into operand 0.
Operand 0 has mode @var{m}, which is scalar. This pattern is used to
implement the @code{fegetround} function from the ISO C99 standard.
@cindex @code{feclearexcept@var{m}} instruction pattern
@cindex @code{feraiseexcept@var{m}} instruction pattern
@item @samp{feclearexcept@var{m}}
@item @samp{feraiseexcept@var{m}}
Clears or raises the supported machine floating-point exceptions
represented by the bits in operand 1. Error status is stored as
nonzero value in operand 0. Both operands have mode @var{m}, which is
a scalar. These patterns are used to implement the
@code{feclearexcept} and @code{feraiseexcept} functions from the ISO
C99 standard.
@cindex @code{exp@var{m}2} instruction pattern
@item @samp{exp@var{m}2}
Raise e (the base of natural logarithms) to the power of operand 1
and store the result in operand 0. Both operands have mode @var{m},
which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{expm1@var{m}2} instruction pattern
@item @samp{expm1@var{m}2}
Raise e (the base of natural logarithms) to the power of operand 1,
subtract 1, and store the result in operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode.
For inputs close to zero, the pattern is expected to be more
accurate than a separate @code{exp@var{m}2} and @code{sub@var{m}3}
would be.
This pattern is not allowed to @code{FAIL}.
@cindex @code{exp10@var{m}2} instruction pattern
@item @samp{exp10@var{m}2}
Raise 10 to the power of operand 1 and store the result in operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{exp2@var{m}2} instruction pattern
@item @samp{exp2@var{m}2}
Raise 2 to the power of operand 1 and store the result in operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{log@var{m}2} instruction pattern
@item @samp{log@var{m}2}
Store the natural logarithm of operand 1 into operand 0. Both operands
have mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{log1p@var{m}2} instruction pattern
@item @samp{log1p@var{m}2}
Add 1 to operand 1, compute the natural logarithm, and store
the result in operand 0. Both operands have mode @var{m}, which is
a scalar or vector floating-point mode.
For inputs close to zero, the pattern is expected to be more
accurate than a separate @code{add@var{m}3} and @code{log@var{m}2}
would be.
This pattern is not allowed to @code{FAIL}.
@cindex @code{log10@var{m}2} instruction pattern
@item @samp{log10@var{m}2}
Store the base-10 logarithm of operand 1 into operand 0. Both operands
have mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{log2@var{m}2} instruction pattern
@item @samp{log2@var{m}2}
Store the base-2 logarithm of operand 1 into operand 0. Both operands
have mode @var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{logb@var{m}2} instruction pattern
@item @samp{logb@var{m}2}
Store the base-@code{FLT_RADIX} logarithm of operand 1 into operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{signbit@var{m}2} instruction pattern
@item @samp{signbit@var{m}2}
Store the sign bit of floating-point operand 1 in operand 0.
@var{m} is either a scalar or vector mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 must have mode @code{SImode}.
When @var{m} is a vector, operand 1 has the mode @var{m}.
operand 0's mode should be an vector integer mode which has
the same number of elements and the same size as mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{significand@var{m}2} instruction pattern
@item @samp{significand@var{m}2}
Store the significand of floating-point operand 1 in operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{pow@var{m}3} instruction pattern
@item @samp{pow@var{m}3}
Store the value of operand 1 raised to the exponent operand 2
into operand 0. All operands have mode @var{m}, which is a scalar
or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{atan2@var{m}3} instruction pattern
@item @samp{atan2@var{m}3}
Store the arc tangent (inverse tangent) of operand 1 divided by
operand 2 into operand 0, using the signs of both arguments to
determine the quadrant of the result. All operands have mode
@var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{floor@var{m}2} instruction pattern
@item @samp{floor@var{m}2}
Store the largest integral value not greater than operand 1 in operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode. If @option{-ffp-int-builtin-inexact} is in
effect, the ``inexact'' exception may be raised for noninteger
operands; otherwise, it may not.
This pattern is not allowed to @code{FAIL}.
@cindex @code{btrunc@var{m}2} instruction pattern
@item @samp{btrunc@var{m}2}
Round operand 1 to an integer, towards zero, and store the result in
operand 0. Both operands have mode @var{m}, which is a scalar or
vector floating-point mode. If @option{-ffp-int-builtin-inexact} is
in effect, the ``inexact'' exception may be raised for noninteger
operands; otherwise, it may not.
This pattern is not allowed to @code{FAIL}.
@cindex @code{round@var{m}2} instruction pattern
@item @samp{round@var{m}2}
Round operand 1 to the nearest integer, rounding away from zero in the
event of a tie, and store the result in operand 0. Both operands have
mode @var{m}, which is a scalar or vector floating-point mode. If
@option{-ffp-int-builtin-inexact} is in effect, the ``inexact''
exception may be raised for noninteger operands; otherwise, it may
not.
This pattern is not allowed to @code{FAIL}.
@cindex @code{ceil@var{m}2} instruction pattern
@item @samp{ceil@var{m}2}
Store the smallest integral value not less than operand 1 in operand 0.
Both operands have mode @var{m}, which is a scalar or vector
floating-point mode. If @option{-ffp-int-builtin-inexact} is in
effect, the ``inexact'' exception may be raised for noninteger
operands; otherwise, it may not.
This pattern is not allowed to @code{FAIL}.
@cindex @code{nearbyint@var{m}2} instruction pattern
@item @samp{nearbyint@var{m}2}
Round operand 1 to an integer, using the current rounding mode, and
store the result in operand 0. Do not raise an inexact condition when
the result is different from the argument. Both operands have mode
@var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{rint@var{m}2} instruction pattern
@item @samp{rint@var{m}2}
Round operand 1 to an integer, using the current rounding mode, and
store the result in operand 0. Raise an inexact condition when
the result is different from the argument. Both operands have mode
@var{m}, which is a scalar or vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{lrint@var{m}@var{n}2}
@item @samp{lrint@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as a signed number according to the current
rounding mode and store in operand 0 (which has mode @var{n}).
@cindex @code{lround@var{m}@var{n}2}
@item @samp{lround@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as a signed number rounding to nearest and away
from zero and store in operand 0 (which has mode @var{n}).
@cindex @code{lfloor@var{m}@var{n}2}
@item @samp{lfloor@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as a signed number rounding down and store in
operand 0 (which has mode @var{n}).
@cindex @code{lceil@var{m}@var{n}2}
@item @samp{lceil@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as a signed number rounding up and store in
operand 0 (which has mode @var{n}).
@cindex @code{copysign@var{m}3} instruction pattern
@item @samp{copysign@var{m}3}
Store a value with the magnitude of operand 1 and the sign of operand
2 into operand 0. All operands have mode @var{m}, which is a scalar or
vector floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{xorsign@var{m}3} instruction pattern
@item @samp{xorsign@var{m}3}
Equivalent to @samp{op0 = op1 * copysign (1.0, op2)}: store a value with
the magnitude of operand 1 and the sign of operand 2 into operand 0.
All operands have mode @var{m}, which is a scalar or vector
floating-point mode.
This pattern is not allowed to @code{FAIL}.
@cindex @code{issignaling@var{m}2} instruction pattern
@item @samp{issignaling@var{m}2}
Set operand 0 to 1 if operand 1 is a signaling NaN and to 0 otherwise.
@cindex @code{cadd90@var{m}3} instruction pattern
@item @samp{cadd90@var{m}3}
Perform vector add and subtract on even/odd number pairs. The operation being
matched is semantically described as
@smallexample
for (int i = 0; i < N; i += 2)
@{
c[i] = a[i] - b[i+1];
c[i+1] = a[i+1] + b[i];
@}
@end smallexample
This operation is semantically equivalent to performing a vector addition of
complex numbers in operand 1 with operand 2 rotated by 90 degrees around
the argand plane and storing the result in operand 0.
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cadd270@var{m}3} instruction pattern
@item @samp{cadd270@var{m}3}
Perform vector add and subtract on even/odd number pairs. The operation being
matched is semantically described as
@smallexample
for (int i = 0; i < N; i += 2)
@{
c[i] = a[i] + b[i+1];
c[i+1] = a[i+1] - b[i];
@}
@end smallexample
This operation is semantically equivalent to performing a vector addition of
complex numbers in operand 1 with operand 2 rotated by 270 degrees around
the argand plane and storing the result in operand 0.
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmla@var{m}4} instruction pattern
@item @samp{cmla@var{m}4}
Perform a vector multiply and accumulate that is semantically the same as
a multiply and accumulate of complex numbers.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * op2[i] + op3[i];
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmla_conj@var{m}4} instruction pattern
@item @samp{cmla_conj@var{m}4}
Perform a vector multiply by conjugate and accumulate that is semantically
the same as a multiply and accumulate of complex numbers where the second
multiply arguments is conjugated.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * conj (op2[i]) + op3[i];
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmls@var{m}4} instruction pattern
@item @samp{cmls@var{m}4}
Perform a vector multiply and subtract that is semantically the same as
a multiply and subtract of complex numbers.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * op2[i] - op3[i];
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmls_conj@var{m}4} instruction pattern
@item @samp{cmls_conj@var{m}4}
Perform a vector multiply by conjugate and subtract that is semantically
the same as a multiply and subtract of complex numbers where the second
multiply arguments is conjugated.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
complex TYPE op3[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * conj (op2[i]) - op3[i];
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmul@var{m}4} instruction pattern
@item @samp{cmul@var{m}4}
Perform a vector multiply that is semantically the same as multiply of
complex numbers.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * op2[i];
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{cmul_conj@var{m}4} instruction pattern
@item @samp{cmul_conj@var{m}4}
Perform a vector multiply by conjugate that is semantically the same as a
multiply of complex numbers where the second multiply arguments is conjugated.
@smallexample
complex TYPE op0[N];
complex TYPE op1[N];
complex TYPE op2[N];
for (int i = 0; i < N; i += 1)
@{
op0[i] = op1[i] * conj (op2[i]);
@}
@end smallexample
In GCC lane ordering the real part of the number must be in the even lanes with
the imaginary part in the odd lanes.
The operation is only supported for vector modes @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{ffs@var{m}2} instruction pattern
@item @samp{ffs@var{m}2}
Store into operand 0 one plus the index of the least significant 1-bit
of operand 1. If operand 1 is zero, store zero.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{clrsb@var{m}2} instruction pattern
@item @samp{clrsb@var{m}2}
Count leading redundant sign bits.
Store into operand 0 the number of redundant sign bits in operand 1, starting
at the most significant bit position.
A redundant sign bit is defined as any sign bit after the first. As such,
this count will be one less than the count of leading sign bits.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{clz@var{m}2} instruction pattern
@item @samp{clz@var{m}2}
Store into operand 0 the number of leading 0-bits in operand 1, starting
at the most significant bit position. If operand 1 is 0, the
@code{CLZ_DEFINED_VALUE_AT_ZERO} (@pxref{Misc}) macro defines if
the result is undefined or has a useful value.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{ctz@var{m}2} instruction pattern
@item @samp{ctz@var{m}2}
Store into operand 0 the number of trailing 0-bits in operand 1, starting
at the least significant bit position. If operand 1 is 0, the
@code{CTZ_DEFINED_VALUE_AT_ZERO} (@pxref{Misc}) macro defines if
the result is undefined or has a useful value.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{popcount@var{m}2} instruction pattern
@item @samp{popcount@var{m}2}
Store into operand 0 the number of 1-bits in operand 1.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{parity@var{m}2} instruction pattern
@item @samp{parity@var{m}2}
Store into operand 0 the parity of operand 1, i.e.@: the number of 1-bits
in operand 1 modulo 2.
@var{m} is either a scalar or vector integer mode. When it is a scalar,
operand 1 has mode @var{m} but operand 0 can have whatever scalar
integer mode is suitable for the target. The compiler will insert
conversion instructions as necessary (typically to convert the result
to the same width as @code{int}). When @var{m} is a vector, both
operands must have mode @var{m}.
This pattern is not allowed to @code{FAIL}.
@cindex @code{one_cmpl@var{m}2} instruction pattern
@item @samp{one_cmpl@var{m}2}
Store the bitwise-complement of operand 1 into operand 0.
@cindex @code{cpymem@var{m}} instruction pattern
@item @samp{cpymem@var{m}}
Block copy instruction. The destination and source blocks of memory
are the first two operands, and both are @code{mem:BLK}s with an
address in mode @code{Pmode}.
The number of bytes to copy is the third operand, in mode @var{m}.
Usually, you specify @code{Pmode} for @var{m}. However, if you can
generate better code knowing the range of valid lengths is smaller than
those representable in a full Pmode pointer, you should provide
a pattern with a
mode corresponding to the range of values you can handle efficiently
(e.g., @code{QImode} for values in the range 0--127; note we avoid numbers
that appear negative) and also a pattern with @code{Pmode}.
The fourth operand is the known shared alignment of the source and
destination, in the form of a @code{const_int} rtx. Thus, if the
compiler knows that both source and destination are word-aligned,
it may provide the value 4 for this operand.
Optional operands 5 and 6 specify expected alignment and size of block
respectively. The expected alignment differs from alignment in operand 4
in a way that the blocks are not required to be aligned according to it in
all cases. This expected alignment is also in bytes, just like operand 4.
Expected size, when unknown, is set to @code{(const_int -1)}.
Descriptions of multiple @code{cpymem@var{m}} patterns can only be
beneficial if the patterns for smaller modes have fewer restrictions
on their first, second and fourth operands. Note that the mode @var{m}
in @code{cpymem@var{m}} does not impose any restriction on the mode of
individually copied data units in the block.
The @code{cpymem@var{m}} patterns need not give special consideration
to the possibility that the source and destination strings might
overlap. These patterns are used to do inline expansion of
@code{__builtin_memcpy}.
@cindex @code{movmem@var{m}} instruction pattern
@item @samp{movmem@var{m}}
Block move instruction. The destination and source blocks of memory
are the first two operands, and both are @code{mem:BLK}s with an
address in mode @code{Pmode}.
The number of bytes to copy is the third operand, in mode @var{m}.
Usually, you specify @code{Pmode} for @var{m}. However, if you can
generate better code knowing the range of valid lengths is smaller than
those representable in a full Pmode pointer, you should provide
a pattern with a
mode corresponding to the range of values you can handle efficiently
(e.g., @code{QImode} for values in the range 0--127; note we avoid numbers
that appear negative) and also a pattern with @code{Pmode}.
The fourth operand is the known shared alignment of the source and
destination, in the form of a @code{const_int} rtx. Thus, if the
compiler knows that both source and destination are word-aligned,
it may provide the value 4 for this operand.
Optional operands 5 and 6 specify expected alignment and size of block
respectively. The expected alignment differs from alignment in operand 4
in a way that the blocks are not required to be aligned according to it in
all cases. This expected alignment is also in bytes, just like operand 4.
Expected size, when unknown, is set to @code{(const_int -1)}.
Descriptions of multiple @code{movmem@var{m}} patterns can only be
beneficial if the patterns for smaller modes have fewer restrictions
on their first, second and fourth operands. Note that the mode @var{m}
in @code{movmem@var{m}} does not impose any restriction on the mode of
individually copied data units in the block.
The @code{movmem@var{m}} patterns must correctly handle the case where
the source and destination strings overlap. These patterns are used to
do inline expansion of @code{__builtin_memmove}.
@cindex @code{movstr} instruction pattern
@item @samp{movstr}
String copy instruction, with @code{stpcpy} semantics. Operand 0 is
an output operand in mode @code{Pmode}. The addresses of the
destination and source strings are operands 1 and 2, and both are
@code{mem:BLK}s with addresses in mode @code{Pmode}. The execution of
the expansion of this pattern should store in operand 0 the address in
which the @code{NUL} terminator was stored in the destination string.
This pattern has also several optional operands that are same as in
@code{setmem}.
@cindex @code{setmem@var{m}} instruction pattern
@item @samp{setmem@var{m}}
Block set instruction. The destination string is the first operand,
given as a @code{mem:BLK} whose address is in mode @code{Pmode}. The
number of bytes to set is the second operand, in mode @var{m}. The value to
initialize the memory with is the third operand. Targets that only support the
clearing of memory should reject any value that is not the constant 0. See
@samp{cpymem@var{m}} for a discussion of the choice of mode.
The fourth operand is the known alignment of the destination, in the form
of a @code{const_int} rtx. Thus, if the compiler knows that the
destination is word-aligned, it may provide the value 4 for this
operand.
Optional operands 5 and 6 specify expected alignment and size of block
respectively. The expected alignment differs from alignment in operand 4
in a way that the blocks are not required to be aligned according to it in
all cases. This expected alignment is also in bytes, just like operand 4.
Expected size, when unknown, is set to @code{(const_int -1)}.
Operand 7 is the minimal size of the block and operand 8 is the
maximal size of the block (NULL if it cannot be represented as CONST_INT).
Operand 9 is the probable maximal size (i.e.@: we cannot rely on it for
correctness, but it can be used for choosing proper code sequence for a
given size).
The use for multiple @code{setmem@var{m}} is as for @code{cpymem@var{m}}.
@cindex @code{cmpstrn@var{m}} instruction pattern
@item @samp{cmpstrn@var{m}}
String compare instruction, with five operands. Operand 0 is the output;
it has mode @var{m}. The remaining four operands are like the operands
of @samp{cpymem@var{m}}. The two memory blocks specified are compared
byte by byte in lexicographic order starting at the beginning of each
string. The instruction is not allowed to prefetch more than one byte
at a time since either string may end in the first byte and reading past
that may access an invalid page or segment and cause a fault. The
comparison terminates early if the fetched bytes are different or if
they are equal to zero. The effect of the instruction is to store a
value in operand 0 whose sign indicates the result of the comparison.
@cindex @code{cmpstr@var{m}} instruction pattern
@item @samp{cmpstr@var{m}}
String compare instruction, without known maximum length. Operand 0 is the
output; it has mode @var{m}. The second and third operand are the blocks of
memory to be compared; both are @code{mem:BLK} with an address in mode
@code{Pmode}.
The fourth operand is the known shared alignment of the source and
destination, in the form of a @code{const_int} rtx. Thus, if the
compiler knows that both source and destination are word-aligned,
it may provide the value 4 for this operand.
The two memory blocks specified are compared byte by byte in lexicographic
order starting at the beginning of each string. The instruction is not allowed
to prefetch more than one byte at a time since either string may end in the
first byte and reading past that may access an invalid page or segment and
cause a fault. The comparison will terminate when the fetched bytes
are different or if they are equal to zero. The effect of the
instruction is to store a value in operand 0 whose sign indicates the
result of the comparison.
@cindex @code{cmpmem@var{m}} instruction pattern
@item @samp{cmpmem@var{m}}
Block compare instruction, with five operands like the operands
of @samp{cmpstr@var{m}}. The two memory blocks specified are compared
byte by byte in lexicographic order starting at the beginning of each
block. Unlike @samp{cmpstr@var{m}} the instruction can prefetch
any bytes in the two memory blocks. Also unlike @samp{cmpstr@var{m}}
the comparison will not stop if both bytes are zero. The effect of
the instruction is to store a value in operand 0 whose sign indicates
the result of the comparison.
@cindex @code{strlen@var{m}} instruction pattern
@item @samp{strlen@var{m}}
Compute the length of a string, with three operands.
Operand 0 is the result (of mode @var{m}), operand 1 is
a @code{mem} referring to the first character of the string,
operand 2 is the character to search for (normally zero),
and operand 3 is a constant describing the known alignment
of the beginning of the string.
@cindex @code{rawmemchr@var{m}} instruction pattern
@item @samp{rawmemchr@var{m}}
Scan memory referred to by operand 1 for the first occurrence of operand 2.
Operand 1 is a @code{mem} and operand 2 a @code{const_int} of mode @var{m}.
Operand 0 is the result, i.e., a pointer to the first occurrence of operand 2
in the memory block given by operand 1.
@cindex @code{float@var{m}@var{n}2} instruction pattern
@item @samp{float@var{m}@var{n}2}
Convert signed integer operand 1 (valid for fixed point mode @var{m}) to
floating point mode @var{n} and store in operand 0 (which has mode
@var{n}).
@cindex @code{floatuns@var{m}@var{n}2} instruction pattern
@item @samp{floatuns@var{m}@var{n}2}
Convert unsigned integer operand 1 (valid for fixed point mode @var{m})
to floating point mode @var{n} and store in operand 0 (which has mode
@var{n}).
@cindex @code{fix@var{m}@var{n}2} instruction pattern
@item @samp{fix@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as a signed number and store in operand 0 (which
has mode @var{n}). This instruction's result is defined only when
the value of operand 1 is an integer.
If the machine description defines this pattern, it also needs to
define the @code{ftrunc} pattern.
@cindex @code{fixuns@var{m}@var{n}2} instruction pattern
@item @samp{fixuns@var{m}@var{n}2}
Convert operand 1 (valid for floating point mode @var{m}) to fixed
point mode @var{n} as an unsigned number and store in operand 0 (which
has mode @var{n}). This instruction's result is defined only when the
value of operand 1 is an integer.
@cindex @code{ftrunc@var{m}2} instruction pattern
@item @samp{ftrunc@var{m}2}
Convert operand 1 (valid for floating point mode @var{m}) to an
integer value, still represented in floating point mode @var{m}, and
store it in operand 0 (valid for floating point mode @var{m}).
@cindex @code{fix_trunc@var{m}@var{n}2} instruction pattern
@item @samp{fix_trunc@var{m}@var{n}2}
Like @samp{fix@var{m}@var{n}2} but works for any floating point value
of mode @var{m} by converting the value to an integer.
@cindex @code{fixuns_trunc@var{m}@var{n}2} instruction pattern
@item @samp{fixuns_trunc@var{m}@var{n}2}
Like @samp{fixuns@var{m}@var{n}2} but works for any floating point
value of mode @var{m} by converting the value to an integer.
@cindex @code{trunc@var{m}@var{n}2} instruction pattern
@item @samp{trunc@var{m}@var{n}2}
Truncate operand 1 (valid for mode @var{m}) to mode @var{n} and
store in operand 0 (which has mode @var{n}). Both modes must be fixed
point or both floating point.
@cindex @code{extend@var{m}@var{n}2} instruction pattern
@item @samp{extend@var{m}@var{n}2}
Sign-extend operand 1 (valid for mode @var{m}) to mode @var{n} and
store in operand 0 (which has mode @var{n}). Both modes must be fixed
point or both floating point.
@cindex @code{zero_extend@var{m}@var{n}2} instruction pattern
@item @samp{zero_extend@var{m}@var{n}2}
Zero-extend operand 1 (valid for mode @var{m}) to mode @var{n} and
store in operand 0 (which has mode @var{n}). Both modes must be fixed
point.
@cindex @code{fract@var{m}@var{n}2} instruction pattern
@item @samp{fract@var{m}@var{n}2}
Convert operand 1 of mode @var{m} to mode @var{n} and store in
operand 0 (which has mode @var{n}). Mode @var{m} and mode @var{n}
could be fixed-point to fixed-point, signed integer to fixed-point,
fixed-point to signed integer, floating-point to fixed-point,
or fixed-point to floating-point.
When overflows or underflows happen, the results are undefined.
@cindex @code{satfract@var{m}@var{n}2} instruction pattern
@item @samp{satfract@var{m}@var{n}2}
Convert operand 1 of mode @var{m} to mode @var{n} and store in
operand 0 (which has mode @var{n}). Mode @var{m} and mode @var{n}
could be fixed-point to fixed-point, signed integer to fixed-point,
or floating-point to fixed-point.
When overflows or underflows happen, the instruction saturates the
results to the maximum or the minimum.
@cindex @code{fractuns@var{m}@var{n}2} instruction pattern
@item @samp{fractuns@var{m}@var{n}2}
Convert operand 1 of mode @var{m} to mode @var{n} and store in
operand 0 (which has mode @var{n}). Mode @var{m} and mode @var{n}
could be unsigned integer to fixed-point, or
fixed-point to unsigned integer.
When overflows or underflows happen, the results are undefined.
@cindex @code{satfractuns@var{m}@var{n}2} instruction pattern
@item @samp{satfractuns@var{m}@var{n}2}
Convert unsigned integer operand 1 of mode @var{m} to fixed-point mode
@var{n} and store in operand 0 (which has mode @var{n}).
When overflows or underflows happen, the instruction saturates the
results to the maximum or the minimum.
@cindex @code{extv@var{m}} instruction pattern
@item @samp{extv@var{m}}
Extract a bit-field from register operand 1, sign-extend it, and store
it in operand 0. Operand 2 specifies the width of the field in bits
and operand 3 the starting bit, which counts from the most significant
bit if @samp{BITS_BIG_ENDIAN} is true and from the least significant bit
otherwise.
Operands 0 and 1 both have mode @var{m}. Operands 2 and 3 have a
target-specific mode.
@cindex @code{extvmisalign@var{m}} instruction pattern
@item @samp{extvmisalign@var{m}}
Extract a bit-field from memory operand 1, sign extend it, and store
it in operand 0. Operand 2 specifies the width in bits and operand 3
the starting bit. The starting bit is always somewhere in the first byte of
operand 1; it counts from the most significant bit if @samp{BITS_BIG_ENDIAN}
is true and from the least significant bit otherwise.
Operand 0 has mode @var{m} while operand 1 has @code{BLK} mode.
Operands 2 and 3 have a target-specific mode.
The instruction must not read beyond the last byte of the bit-field.
@cindex @code{extzv@var{m}} instruction pattern
@item @samp{extzv@var{m}}
Like @samp{extv@var{m}} except that the bit-field value is zero-extended.
@cindex @code{extzvmisalign@var{m}} instruction pattern
@item @samp{extzvmisalign@var{m}}
Like @samp{extvmisalign@var{m}} except that the bit-field value is
zero-extended.
@cindex @code{insv@var{m}} instruction pattern
@item @samp{insv@var{m}}
Insert operand 3 into a bit-field of register operand 0. Operand 1
specifies the width of the field in bits and operand 2 the starting bit,
which counts from the most significant bit if @samp{BITS_BIG_ENDIAN}
is true and from the least significant bit otherwise.
Operands 0 and 3 both have mode @var{m}. Operands 1 and 2 have a
target-specific mode.
@cindex @code{insvmisalign@var{m}} instruction pattern
@item @samp{insvmisalign@var{m}}
Insert operand 3 into a bit-field of memory operand 0. Operand 1
specifies the width of the field in bits and operand 2 the starting bit.
The starting bit is always somewhere in the first byte of operand 0;
it counts from the most significant bit if @samp{BITS_BIG_ENDIAN}
is true and from the least significant bit otherwise.
Operand 3 has mode @var{m} while operand 0 has @code{BLK} mode.
Operands 1 and 2 have a target-specific mode.
The instruction must not read or write beyond the last byte of the bit-field.
@cindex @code{extv} instruction pattern
@item @samp{extv}
Extract a bit-field from operand 1 (a register or memory operand), where
operand 2 specifies the width in bits and operand 3 the starting bit,
and store it in operand 0. Operand 0 must have mode @code{word_mode}.
Operand 1 may have mode @code{byte_mode} or @code{word_mode}; often
@code{word_mode} is allowed only for registers. Operands 2 and 3 must
be valid for @code{word_mode}.
The RTL generation pass generates this instruction only with constants
for operands 2 and 3 and the constant is never zero for operand 2.
The bit-field value is sign-extended to a full word integer
before it is stored in operand 0.
This pattern is deprecated; please use @samp{extv@var{m}} and
@code{extvmisalign@var{m}} instead.
@cindex @code{extzv} instruction pattern
@item @samp{extzv}
Like @samp{extv} except that the bit-field value is zero-extended.
This pattern is deprecated; please use @samp{extzv@var{m}} and
@code{extzvmisalign@var{m}} instead.
@cindex @code{insv} instruction pattern
@item @samp{insv}
Store operand 3 (which must be valid for @code{word_mode}) into a
bit-field in operand 0, where operand 1 specifies the width in bits and
operand 2 the starting bit. Operand 0 may have mode @code{byte_mode} or
@code{word_mode}; often @code{word_mode} is allowed only for registers.
Operands 1 and 2 must be valid for @code{word_mode}.
The RTL generation pass generates this instruction only with constants
for operands 1 and 2 and the constant is never zero for operand 1.
This pattern is deprecated; please use @samp{insv@var{m}} and
@code{insvmisalign@var{m}} instead.
@cindex @code{mov@var{mode}cc} instruction pattern
@item @samp{mov@var{mode}cc}
Conditionally move operand 2 or operand 3 into operand 0 according to the
comparison in operand 1. If the comparison is true, operand 2 is moved
into operand 0, otherwise operand 3 is moved.
The mode of the operands being compared need not be the same as the operands
being moved. Some machines, sparc64 for example, have instructions that
conditionally move an integer value based on the floating point condition
codes and vice versa.
If the machine does not have conditional move instructions, do not
define these patterns.
@cindex @code{add@var{mode}cc} instruction pattern
@item @samp{add@var{mode}cc}
Similar to @samp{mov@var{mode}cc} but for conditional addition. Conditionally
move operand 2 or (operands 2 + operand 3) into operand 0 according to the
comparison in operand 1. If the comparison is false, operand 2 is moved into
operand 0, otherwise (operand 2 + operand 3) is moved.
@cindex @code{cond_add@var{mode}} instruction pattern
@cindex @code{cond_sub@var{mode}} instruction pattern
@cindex @code{cond_mul@var{mode}} instruction pattern
@cindex @code{cond_div@var{mode}} instruction pattern
@cindex @code{cond_udiv@var{mode}} instruction pattern
@cindex @code{cond_mod@var{mode}} instruction pattern
@cindex @code{cond_umod@var{mode}} instruction pattern
@cindex @code{cond_and@var{mode}} instruction pattern
@cindex @code{cond_ior@var{mode}} instruction pattern
@cindex @code{cond_xor@var{mode}} instruction pattern
@cindex @code{cond_smin@var{mode}} instruction pattern
@cindex @code{cond_smax@var{mode}} instruction pattern
@cindex @code{cond_umin@var{mode}} instruction pattern
@cindex @code{cond_umax@var{mode}} instruction pattern
@cindex @code{cond_fmin@var{mode}} instruction pattern
@cindex @code{cond_fmax@var{mode}} instruction pattern
@cindex @code{cond_ashl@var{mode}} instruction pattern
@cindex @code{cond_ashr@var{mode}} instruction pattern
@cindex @code{cond_lshr@var{mode}} instruction pattern
@item @samp{cond_add@var{mode}}
@itemx @samp{cond_sub@var{mode}}
@itemx @samp{cond_mul@var{mode}}
@itemx @samp{cond_div@var{mode}}
@itemx @samp{cond_udiv@var{mode}}
@itemx @samp{cond_mod@var{mode}}
@itemx @samp{cond_umod@var{mode}}
@itemx @samp{cond_and@var{mode}}
@itemx @samp{cond_ior@var{mode}}
@itemx @samp{cond_xor@var{mode}}
@itemx @samp{cond_smin@var{mode}}
@itemx @samp{cond_smax@var{mode}}
@itemx @samp{cond_umin@var{mode}}
@itemx @samp{cond_umax@var{mode}}
@itemx @samp{cond_fmin@var{mode}}
@itemx @samp{cond_fmax@var{mode}}
@itemx @samp{cond_ashl@var{mode}}
@itemx @samp{cond_ashr@var{mode}}
@itemx @samp{cond_lshr@var{mode}}
When operand 1 is true, perform an operation on operands 2 and 3 and
store the result in operand 0, otherwise store operand 4 in operand 0.
The operation works elementwise if the operands are vectors.
The scalar case is equivalent to:
@smallexample
op0 = op1 ? op2 @var{op} op3 : op4;
@end smallexample
while the vector case is equivalent to:
@smallexample
for (i = 0; i < GET_MODE_NUNITS (@var{m}); i++)
op0[i] = op1[i] ? op2[i] @var{op} op3[i] : op4[i];
@end smallexample
where, for example, @var{op} is @code{+} for @samp{cond_add@var{mode}}.
When defined for floating-point modes, the contents of @samp{op3[i]}
are not interpreted if @samp{op1[i]} is false, just like they would not
be in a normal C @samp{?:} condition.
Operands 0, 2, 3 and 4 all have mode @var{m}. Operand 1 is a scalar
integer if @var{m} is scalar, otherwise it has the mode returned by
@code{TARGET_VECTORIZE_GET_MASK_MODE}.
@samp{cond_@var{op}@var{mode}} generally corresponds to a conditional
form of @samp{@var{op}@var{mode}3}. As an exception, the vector forms
of shifts correspond to patterns like @code{vashl@var{mode}3} rather
than patterns like @code{ashl@var{mode}3}.
@cindex @code{cond_fma@var{mode}} instruction pattern
@cindex @code{cond_fms@var{mode}} instruction pattern
@cindex @code{cond_fnma@var{mode}} instruction pattern
@cindex @code{cond_fnms@var{mode}} instruction pattern
@item @samp{cond_fma@var{mode}}
@itemx @samp{cond_fms@var{mode}}
@itemx @samp{cond_fnma@var{mode}}
@itemx @samp{cond_fnms@var{mode}}
Like @samp{cond_add@var{m}}, except that the conditional operation
takes 3 operands rather than two. For example, the vector form of
@samp{cond_fma@var{mode}} is equivalent to:
@smallexample
for (i = 0; i < GET_MODE_NUNITS (@var{m}); i++)
op0[i] = op1[i] ? fma (op2[i], op3[i], op4[i]) : op5[i];
@end smallexample
@cindex @code{neg@var{mode}cc} instruction pattern
@item @samp{neg@var{mode}cc}
Similar to @samp{mov@var{mode}cc} but for conditional negation. Conditionally
move the negation of operand 2 or the unchanged operand 3 into operand 0
according to the comparison in operand 1. If the comparison is true, the negation
of operand 2 is moved into operand 0, otherwise operand 3 is moved.
@cindex @code{not@var{mode}cc} instruction pattern
@item @samp{not@var{mode}cc}
Similar to @samp{neg@var{mode}cc} but for conditional complement.
Conditionally move the bitwise complement of operand 2 or the unchanged
operand 3 into operand 0 according to the comparison in operand 1.
If the comparison is true, the complement of operand 2 is moved into
operand 0, otherwise operand 3 is moved.
@cindex @code{cstore@var{mode}4} instruction pattern
@item @samp{cstore@var{mode}4}
Store zero or nonzero in operand 0 according to whether a comparison
is true. Operand 1 is a comparison operator. Operand 2 and operand 3
are the first and second operand of the comparison, respectively.
You specify the mode that operand 0 must have when you write the
@code{match_operand} expression. The compiler automatically sees which
mode you have used and supplies an operand of that mode.
The value stored for a true condition must have 1 as its low bit, or
else must be negative. Otherwise the instruction is not suitable and
you should omit it from the machine description. You describe to the
compiler exactly which value is stored by defining the macro
@code{STORE_FLAG_VALUE} (@pxref{Misc}). If a description cannot be
found that can be used for all the possible comparison operators, you
should pick one and use a @code{define_expand} to map all results
onto the one you chose.
These operations may @code{FAIL}, but should do so only in relatively
uncommon cases; if they would @code{FAIL} for common cases involving
integer comparisons, it is best to restrict the predicates to not
allow these operands. Likewise if a given comparison operator will
always fail, independent of the operands (for floating-point modes, the
@code{ordered_comparison_operator} predicate is often useful in this case).
If this pattern is omitted, the compiler will generate a conditional
branch---for example, it may copy a constant one to the target and branching
around an assignment of zero to the target---or a libcall. If the predicate
for operand 1 only rejects some operators, it will also try reordering the
operands and/or inverting the result value (e.g.@: by an exclusive OR).
These possibilities could be cheaper or equivalent to the instructions
used for the @samp{cstore@var{mode}4} pattern followed by those required
to convert a positive result from @code{STORE_FLAG_VALUE} to 1; in this
case, you can and should make operand 1's predicate reject some operators
in the @samp{cstore@var{mode}4} pattern, or remove the pattern altogether
from the machine description.
@cindex @code{tbranch_@var{op}@var{mode}3} instruction pattern
@item @samp{tbranch_@var{op}@var{mode}3}
Conditional branch instruction combined with a bit test-and-compare
instruction. Operand 0 is the operand of the comparison. Operand 1 is the bit
position of Operand 1 to test. Operand 3 is the @code{code_label} to jump to.
@var{op} is one of @var{eq} or @var{ne}.
@cindex @code{cbranch@var{mode}4} instruction pattern
@item @samp{cbranch@var{mode}4}
Conditional branch instruction combined with a compare instruction.
Operand 0 is a comparison operator. Operand 1 and operand 2 are the
first and second operands of the comparison, respectively. Operand 3
is the @code{code_label} to jump to.
@cindex @code{jump} instruction pattern
@item @samp{jump}
A jump inside a function; an unconditional branch. Operand 0 is the
@code{code_label} to jump to. This pattern name is mandatory on all
machines.
@cindex @code{call} instruction pattern
@item @samp{call}
Subroutine call instruction returning no value. Operand 0 is the
function to call; operand 1 is the number of bytes of arguments pushed
as a @code{const_int}. Operand 2 is the result of calling the target
hook @code{TARGET_FUNCTION_ARG} with the second argument @code{arg}
yielding true for @code{arg.end_marker_p ()}, in a call after all
parameters have been passed to that hook. By default this is the first
register beyond those used for arguments in the call, or @code{NULL} if
all the argument-registers are used in the call.
On most machines, operand 2 is not actually stored into the RTL
pattern. It is supplied for the sake of some RISC machines which need
to put this information into the assembler code; they can put it in
the RTL instead of operand 1.
Operand 0 should be a @code{mem} RTX whose address is the address of the
function. Note, however, that this address can be a @code{symbol_ref}
expression even if it would not be a legitimate memory address on the
target machine. If it is also not a valid argument for a call
instruction, the pattern for this operation should be a
@code{define_expand} (@pxref{Expander Definitions}) that places the
address into a register and uses that register in the call instruction.
@cindex @code{call_value} instruction pattern
@item @samp{call_value}
Subroutine call instruction returning a value. Operand 0 is the hard
register in which the value is returned. There are three more
operands, the same as the three operands of the @samp{call}
instruction (but with numbers increased by one).
Subroutines that return @code{BLKmode} objects use the @samp{call}
insn.
@cindex @code{call_pop} instruction pattern
@cindex @code{call_value_pop} instruction pattern
@item @samp{call_pop}, @samp{call_value_pop}
Similar to @samp{call} and @samp{call_value}, except used if defined and
if @code{RETURN_POPS_ARGS} is nonzero. They should emit a @code{parallel}
that contains both the function call and a @code{set} to indicate the
adjustment made to the frame pointer.
For machines where @code{RETURN_POPS_ARGS} can be nonzero, the use of these
patterns increases the number of functions for which the frame pointer
can be eliminated, if desired.
@cindex @code{untyped_call} instruction pattern
@item @samp{untyped_call}
Subroutine call instruction returning a value of any type. Operand 0 is
the function to call; operand 1 is a memory location where the result of
calling the function is to be stored; operand 2 is a @code{parallel}
expression where each element is a @code{set} expression that indicates
the saving of a function return value into the result block.
This instruction pattern should be defined to support
@code{__builtin_apply} on machines where special instructions are needed
to call a subroutine with arbitrary arguments or to save the value
returned. This instruction pattern is required on machines that have
multiple registers that can hold a return value
(i.e.@: @code{FUNCTION_VALUE_REGNO_P} is true for more than one register).
@cindex @code{return} instruction pattern
@item @samp{return}
Subroutine return instruction. This instruction pattern name should be
defined only if a single instruction can do all the work of returning
from a function.
Like the @samp{mov@var{m}} patterns, this pattern is also used after the
RTL generation phase. In this case it is to support machines where
multiple instructions are usually needed to return from a function, but
some class of functions only requires one instruction to implement a
return. Normally, the applicable functions are those which do not need
to save any registers or allocate stack space.
It is valid for this pattern to expand to an instruction using
@code{simple_return} if no epilogue is required.
@cindex @code{simple_return} instruction pattern
@item @samp{simple_return}
Subroutine return instruction. This instruction pattern name should be
defined only if a single instruction can do all the work of returning
from a function on a path where no epilogue is required. This pattern
is very similar to the @code{return} instruction pattern, but it is emitted
only by the shrink-wrapping optimization on paths where the function
prologue has not been executed, and a function return should occur without
any of the effects of the epilogue. Additional uses may be introduced on
paths where both the prologue and the epilogue have executed.
@findex reload_completed
@findex leaf_function_p
For such machines, the condition specified in this pattern should only
be true when @code{reload_completed} is nonzero and the function's
epilogue would only be a single instruction. For machines with register
windows, the routine @code{leaf_function_p} may be used to determine if
a register window push is required.
Machines that have conditional return instructions should define patterns
such as
@smallexample
(define_insn ""
[(set (pc)
(if_then_else (match_operator
0 "comparison_operator"
[(reg:CC CC_REG) (const_int 0)])
(return)
(pc)))]
"@var{condition}"
"@dots{}")
@end smallexample
where @var{condition} would normally be the same condition specified on the
named @samp{return} pattern.
@cindex @code{untyped_return} instruction pattern
@item @samp{untyped_return}
Untyped subroutine return instruction. This instruction pattern should
be defined to support @code{__builtin_return} on machines where special
instructions are needed to return a value of any type.
Operand 0 is a memory location where the result of calling a function
with @code{__builtin_apply} is stored; operand 1 is a @code{parallel}
expression where each element is a @code{set} expression that indicates
the restoring of a function return value from the result block.
@cindex @code{nop} instruction pattern
@item @samp{nop}
No-op instruction. This instruction pattern name should always be defined
to output a no-op in assembler code. @code{(const_int 0)} will do as an
RTL pattern.
@cindex @code{indirect_jump} instruction pattern
@item @samp{indirect_jump}
An instruction to jump to an address which is operand zero.
This pattern name is mandatory on all machines.
@cindex @code{casesi} instruction pattern
@item @samp{casesi}
Instruction to jump through a dispatch table, including bounds checking.
This instruction takes five operands:
@enumerate
@item
The index to dispatch on, which has mode @code{SImode}.
@item
The lower bound for indices in the table, an integer constant.
@item
The total range of indices in the table---the largest index
minus the smallest one (both inclusive).
@item
A label that precedes the table itself.
@item
A label to jump to if the index has a value outside the bounds.
@end enumerate
The table is an @code{addr_vec} or @code{addr_diff_vec} inside of a
@code{jump_table_data}. The number of elements in the table is one plus the
difference between the upper bound and the lower bound.
@cindex @code{tablejump} instruction pattern
@item @samp{tablejump}
Instruction to jump to a variable address. This is a low-level
capability which can be used to implement a dispatch table when there
is no @samp{casesi} pattern.
This pattern requires two operands: the address or offset, and a label
which should immediately precede the jump table. If the macro
@code{CASE_VECTOR_PC_RELATIVE} evaluates to a nonzero value then the first
operand is an offset which counts from the address of the table; otherwise,
it is an absolute address to jump to. In either case, the first operand has
mode @code{Pmode}.
The @samp{tablejump} insn is always the last insn before the jump
table it uses. Its assembler code normally has no need to use the
second operand, but you should incorporate it in the RTL pattern so
that the jump optimizer will not delete the table as unreachable code.
@cindex @code{doloop_end} instruction pattern
@item @samp{doloop_end}
Conditional branch instruction that decrements a register and
jumps if the register is nonzero. Operand 0 is the register to
decrement and test; operand 1 is the label to jump to if the
register is nonzero.
@xref{Looping Patterns}.
This optional instruction pattern should be defined for machines with
low-overhead looping instructions as the loop optimizer will try to
modify suitable loops to utilize it. The target hook
@code{TARGET_CAN_USE_DOLOOP_P} controls the conditions under which
low-overhead loops can be used.
@cindex @code{doloop_begin} instruction pattern
@item @samp{doloop_begin}
Companion instruction to @code{doloop_end} required for machines that
need to perform some initialization, such as loading a special counter
register. Operand 1 is the associated @code{doloop_end} pattern and
operand 0 is the register that it decrements.
If initialization insns do not always need to be emitted, use a
@code{define_expand} (@pxref{Expander Definitions}) and make it fail.
@cindex @code{canonicalize_funcptr_for_compare} instruction pattern
@item @samp{canonicalize_funcptr_for_compare}
Canonicalize the function pointer in operand 1 and store the result
into operand 0.
Operand 0 is always a @code{reg} and has mode @code{Pmode}; operand 1
may be a @code{reg}, @code{mem}, @code{symbol_ref}, @code{const_int}, etc
and also has mode @code{Pmode}.
Canonicalization of a function pointer usually involves computing
the address of the function which would be called if the function
pointer were used in an indirect call.
Only define this pattern if function pointers on the target machine
can have different values but still call the same function when
used in an indirect call.
@cindex @code{save_stack_block} instruction pattern
@cindex @code{save_stack_function} instruction pattern
@cindex @code{save_stack_nonlocal} instruction pattern
@cindex @code{restore_stack_block} instruction pattern
@cindex @code{restore_stack_function} instruction pattern
@cindex @code{restore_stack_nonlocal} instruction pattern
@item @samp{save_stack_block}
@itemx @samp{save_stack_function}
@itemx @samp{save_stack_nonlocal}
@itemx @samp{restore_stack_block}
@itemx @samp{restore_stack_function}
@itemx @samp{restore_stack_nonlocal}
Most machines save and restore the stack pointer by copying it to or
from an object of mode @code{Pmode}. Do not define these patterns on
such machines.
Some machines require special handling for stack pointer saves and
restores. On those machines, define the patterns corresponding to the
non-standard cases by using a @code{define_expand} (@pxref{Expander
Definitions}) that produces the required insns. The three types of
saves and restores are:
@enumerate
@item
@samp{save_stack_block} saves the stack pointer at the start of a block
that allocates a variable-sized object, and @samp{restore_stack_block}
restores the stack pointer when the block is exited.
@item
@samp{save_stack_function} and @samp{restore_stack_function} do a
similar job for the outermost block of a function and are used when the
function allocates variable-sized objects or calls @code{alloca}. Only
the epilogue uses the restored stack pointer, allowing a simpler save or
restore sequence on some machines.
@item
@samp{save_stack_nonlocal} is used in functions that contain labels
branched to by nested functions. It saves the stack pointer in such a
way that the inner function can use @samp{restore_stack_nonlocal} to
restore the stack pointer. The compiler generates code to restore the
frame and argument pointer registers, but some machines require saving
and restoring additional data such as register window information or
stack backchains. Place insns in these patterns to save and restore any
such required data.
@end enumerate
When saving the stack pointer, operand 0 is the save area and operand 1
is the stack pointer. The mode used to allocate the save area defaults
to @code{Pmode} but you can override that choice by defining the
@code{STACK_SAVEAREA_MODE} macro (@pxref{Storage Layout}). You must
specify an integral mode, or @code{VOIDmode} if no save area is needed
for a particular type of save (either because no save is needed or
because a machine-specific save area can be used). Operand 0 is the
stack pointer and operand 1 is the save area for restore operations. If
@samp{save_stack_block} is defined, operand 0 must not be
@code{VOIDmode} since these saves can be arbitrarily nested.
A save area is a @code{mem} that is at a constant offset from
@code{virtual_stack_vars_rtx} when the stack pointer is saved for use by
nonlocal gotos and a @code{reg} in the other two cases.
@cindex @code{allocate_stack} instruction pattern
@item @samp{allocate_stack}
Subtract (or add if @code{STACK_GROWS_DOWNWARD} is undefined) operand 1 from
the stack pointer to create space for dynamically allocated data.
Store the resultant pointer to this space into operand 0. If you
are allocating space from the main stack, do this by emitting a
move insn to copy @code{virtual_stack_dynamic_rtx} to operand 0.
If you are allocating the space elsewhere, generate code to copy the
location of the space to operand 0. In the latter case, you must
ensure this space gets freed when the corresponding space on the main
stack is free.
Do not define this pattern if all that must be done is the subtraction.
Some machines require other operations such as stack probes or
maintaining the back chain. Define this pattern to emit those
operations in addition to updating the stack pointer.
@cindex @code{check_stack} instruction pattern
@item @samp{check_stack}
If stack checking (@pxref{Stack Checking}) cannot be done on your system by
probing the stack, define this pattern to perform the needed check and signal
an error if the stack has overflowed. The single operand is the address in
the stack farthest from the current stack pointer that you need to validate.
Normally, on platforms where this pattern is needed, you would obtain the
stack limit from a global or thread-specific variable or register.
@cindex @code{probe_stack_address} instruction pattern
@item @samp{probe_stack_address}
If stack checking (@pxref{Stack Checking}) can be done on your system by
probing the stack but without the need to actually access it, define this
pattern and signal an error if the stack has overflowed. The single operand
is the memory address in the stack that needs to be probed.
@cindex @code{probe_stack} instruction pattern
@item @samp{probe_stack}
If stack checking (@pxref{Stack Checking}) can be done on your system by
probing the stack but doing it with a ``store zero'' instruction is not valid
or optimal, define this pattern to do the probing differently and signal an
error if the stack has overflowed. The single operand is the memory reference
in the stack that needs to be probed.
@cindex @code{nonlocal_goto} instruction pattern
@item @samp{nonlocal_goto}
Emit code to generate a non-local goto, e.g., a jump from one function
to a label in an outer function. This pattern has four arguments,
each representing a value to be used in the jump. The first
argument is to be loaded into the frame pointer, the second is
the address to branch to (code to dispatch to the actual label),
the third is the address of a location where the stack is saved,
and the last is the address of the label, to be placed in the
location for the incoming static chain.
On most machines you need not define this pattern, since GCC will
already generate the correct code, which is to load the frame pointer
and static chain, restore the stack (using the
@samp{restore_stack_nonlocal} pattern, if defined), and jump indirectly
to the dispatcher. You need only define this pattern if this code will
not work on your machine.
@cindex @code{nonlocal_goto_receiver} instruction pattern
@item @samp{nonlocal_goto_receiver}
This pattern, if defined, contains code needed at the target of a
nonlocal goto after the code already generated by GCC@. You will not
normally need to define this pattern. A typical reason why you might
need this pattern is if some value, such as a pointer to a global table,
must be restored when the frame pointer is restored. Note that a nonlocal
goto only occurs within a unit-of-translation, so a global table pointer
that is shared by all functions of a given module need not be restored.
There are no arguments.
@cindex @code{exception_receiver} instruction pattern
@item @samp{exception_receiver}
This pattern, if defined, contains code needed at the site of an
exception handler that isn't needed at the site of a nonlocal goto. You
will not normally need to define this pattern. A typical reason why you
might need this pattern is if some value, such as a pointer to a global
table, must be restored after control flow is branched to the handler of
an exception. There are no arguments.
@cindex @code{builtin_setjmp_setup} instruction pattern
@item @samp{builtin_setjmp_setup}
This pattern, if defined, contains additional code needed to initialize
the @code{jmp_buf}. You will not normally need to define this pattern.
A typical reason why you might need this pattern is if some value, such
as a pointer to a global table, must be restored. Though it is
preferred that the pointer value be recalculated if possible (given the
address of a label for instance). The single argument is a pointer to
the @code{jmp_buf}. Note that the buffer is five words long and that
the first three are normally used by the generic mechanism.
@cindex @code{builtin_setjmp_receiver} instruction pattern
@item @samp{builtin_setjmp_receiver}
This pattern, if defined, contains code needed at the site of a
built-in setjmp that isn't needed at the site of a nonlocal goto. You
will not normally need to define this pattern. A typical reason why you
might need this pattern is if some value, such as a pointer to a global
table, must be restored. It takes one argument, which is the label
to which builtin_longjmp transferred control; this pattern may be emitted
at a small offset from that label.
@cindex @code{builtin_longjmp} instruction pattern
@item @samp{builtin_longjmp}
This pattern, if defined, performs the entire action of the longjmp.
You will not normally need to define this pattern unless you also define
@code{builtin_setjmp_setup}. The single argument is a pointer to the
@code{jmp_buf}.
@cindex @code{eh_return} instruction pattern
@item @samp{eh_return}
This pattern, if defined, affects the way @code{__builtin_eh_return},
and thence the call frame exception handling library routines, are
built. It is intended to handle non-trivial actions needed along
the abnormal return path.
The address of the exception handler to which the function should return
is passed as operand to this pattern. It will normally need to copied by
the pattern to some special register or memory location.
If the pattern needs to determine the location of the target call
frame in order to do so, it may use @code{EH_RETURN_STACKADJ_RTX},
if defined; it will have already been assigned.
If this pattern is not defined, the default action will be to simply
copy the return address to @code{EH_RETURN_HANDLER_RTX}. Either
that macro or this pattern needs to be defined if call frame exception
handling is to be used.
@cindex @code{prologue} instruction pattern
@anchor{prologue instruction pattern}
@item @samp{prologue}
This pattern, if defined, emits RTL for entry to a function. The function
entry is responsible for setting up the stack frame, initializing the frame
pointer register, saving callee saved registers, etc.
Using a prologue pattern is generally preferred over defining
@code{TARGET_ASM_FUNCTION_PROLOGUE} to emit assembly code for the prologue.
The @code{prologue} pattern is particularly useful for targets which perform
instruction scheduling.
@cindex @code{window_save} instruction pattern
@anchor{window_save instruction pattern}
@item @samp{window_save}
This pattern, if defined, emits RTL for a register window save. It should
be defined if the target machine has register windows but the window events
are decoupled from calls to subroutines. The canonical example is the SPARC
architecture.
@cindex @code{epilogue} instruction pattern
@anchor{epilogue instruction pattern}
@item @samp{epilogue}
This pattern emits RTL for exit from a function. The function
exit is responsible for deallocating the stack frame, restoring callee saved
registers and emitting the return instruction.
Using an epilogue pattern is generally preferred over defining
@code{TARGET_ASM_FUNCTION_EPILOGUE} to emit assembly code for the epilogue.
The @code{epilogue} pattern is particularly useful for targets which perform
instruction scheduling or which have delay slots for their return instruction.
@cindex @code{sibcall_epilogue} instruction pattern
@item @samp{sibcall_epilogue}
This pattern, if defined, emits RTL for exit from a function without the final
branch back to the calling function. This pattern will be emitted before any
sibling call (aka tail call) sites.
The @code{sibcall_epilogue} pattern must not clobber any arguments used for
parameter passing or any stack slots for arguments passed to the current
function.
@cindex @code{trap} instruction pattern
@item @samp{trap}
This pattern, if defined, signals an error, typically by causing some
kind of signal to be raised.
@cindex @code{ctrap@var{MM}4} instruction pattern
@item @samp{ctrap@var{MM}4}
Conditional trap instruction. Operand 0 is a piece of RTL which
performs a comparison, and operands 1 and 2 are the arms of the
comparison. Operand 3 is the trap code, an integer.
A typical @code{ctrap} pattern looks like
@smallexample
(define_insn "ctrapsi4"
[(trap_if (match_operator 0 "trap_operator"
[(match_operand 1 "register_operand")
(match_operand 2 "immediate_operand")])
(match_operand 3 "const_int_operand" "i"))]
""
"@dots{}")
@end smallexample
@cindex @code{prefetch} instruction pattern
@item @samp{prefetch}
This pattern, if defined, emits code for a non-faulting data prefetch
instruction. Operand 0 is the address of the memory to prefetch. Operand 1
is a constant 1 if the prefetch is preparing for a write to the memory
address, or a constant 0 otherwise. Operand 2 is the expected degree of
temporal locality of the data and is a value between 0 and 3, inclusive; 0
means that the data has no temporal locality, so it need not be left in the
cache after the access; 3 means that the data has a high degree of temporal
locality and should be left in all levels of cache possible; 1 and 2 mean,
respectively, a low or moderate degree of temporal locality.
Targets that do not support write prefetches or locality hints can ignore
the values of operands 1 and 2.
@cindex @code{blockage} instruction pattern
@item @samp{blockage}
This pattern defines a pseudo insn that prevents the instruction
scheduler and other passes from moving instructions and using register
equivalences across the boundary defined by the blockage insn.
This needs to be an UNSPEC_VOLATILE pattern or a volatile ASM.
@cindex @code{memory_blockage} instruction pattern
@item @samp{memory_blockage}
This pattern, if defined, represents a compiler memory barrier, and will be
placed at points across which RTL passes may not propagate memory accesses.
This instruction needs to read and write volatile BLKmode memory. It does
not need to generate any machine instruction. If this pattern is not defined,
the compiler falls back to emitting an instruction corresponding
to @code{asm volatile ("" ::: "memory")}.
@cindex @code{memory_barrier} instruction pattern
@item @samp{memory_barrier}
If the target memory model is not fully synchronous, then this pattern
should be defined to an instruction that orders both loads and stores
before the instruction with respect to loads and stores after the instruction.
This pattern has no operands.
@cindex @code{speculation_barrier} instruction pattern
@item @samp{speculation_barrier}
If the target can support speculative execution, then this pattern should
be defined to an instruction that will block subsequent execution until
any prior speculation conditions has been resolved. The pattern must also
ensure that the compiler cannot move memory operations past the barrier,
so it needs to be an UNSPEC_VOLATILE pattern. The pattern has no
operands.
If this pattern is not defined then the default expansion of
@code{__builtin_speculation_safe_value} will emit a warning. You can
suppress this warning by defining this pattern with a final condition
of @code{0} (zero), which tells the compiler that a speculation
barrier is not needed for this target.
@cindex @code{sync_compare_and_swap@var{mode}} instruction pattern
@item @samp{sync_compare_and_swap@var{mode}}
This pattern, if defined, emits code for an atomic compare-and-swap
operation. Operand 1 is the memory on which the atomic operation is
performed. Operand 2 is the ``old'' value to be compared against the
current contents of the memory location. Operand 3 is the ``new'' value
to store in the memory if the compare succeeds. Operand 0 is the result
of the operation; it should contain the contents of the memory
before the operation. If the compare succeeds, this should obviously be
a copy of operand 2.
This pattern must show that both operand 0 and operand 1 are modified.
This pattern must issue any memory barrier instructions such that all
memory operations before the atomic operation occur before the atomic
operation and all memory operations after the atomic operation occur
after the atomic operation.
For targets where the success or failure of the compare-and-swap
operation is available via the status flags, it is possible to
avoid a separate compare operation and issue the subsequent
branch or store-flag operation immediately after the compare-and-swap.
To this end, GCC will look for a @code{MODE_CC} set in the
output of @code{sync_compare_and_swap@var{mode}}; if the machine
description includes such a set, the target should also define special
@code{cbranchcc4} and/or @code{cstorecc4} instructions. GCC will then
be able to take the destination of the @code{MODE_CC} set and pass it
to the @code{cbranchcc4} or @code{cstorecc4} pattern as the first
operand of the comparison (the second will be @code{(const_int 0)}).
For targets where the operating system may provide support for this
operation via library calls, the @code{sync_compare_and_swap_optab}
may be initialized to a function with the same interface as the
@code{__sync_val_compare_and_swap_@var{n}} built-in. If the entire
set of @var{__sync} builtins are supported via library calls, the
target can initialize all of the optabs at once with
@code{init_sync_libfuncs}.
For the purposes of C++11 @code{std::atomic::is_lock_free}, it is
assumed that these library calls do @emph{not} use any kind of
interruptable locking.
@cindex @code{sync_add@var{mode}} instruction pattern
@cindex @code{sync_sub@var{mode}} instruction pattern
@cindex @code{sync_ior@var{mode}} instruction pattern
@cindex @code{sync_and@var{mode}} instruction pattern
@cindex @code{sync_xor@var{mode}} instruction pattern
@cindex @code{sync_nand@var{mode}} instruction pattern
@item @samp{sync_add@var{mode}}, @samp{sync_sub@var{mode}}
@itemx @samp{sync_ior@var{mode}}, @samp{sync_and@var{mode}}
@itemx @samp{sync_xor@var{mode}}, @samp{sync_nand@var{mode}}
These patterns emit code for an atomic operation on memory.
Operand 0 is the memory on which the atomic operation is performed.
Operand 1 is the second operand to the binary operator.
This pattern must issue any memory barrier instructions such that all
memory operations before the atomic operation occur before the atomic
operation and all memory operations after the atomic operation occur
after the atomic operation.
If these patterns are not defined, the operation will be constructed
from a compare-and-swap operation, if defined.
@cindex @code{sync_old_add@var{mode}} instruction pattern
@cindex @code{sync_old_sub@var{mode}} instruction pattern
@cindex @code{sync_old_ior@var{mode}} instruction pattern
@cindex @code{sync_old_and@var{mode}} instruction pattern
@cindex @code{sync_old_xor@var{mode}} instruction pattern
@cindex @code{sync_old_nand@var{mode}} instruction pattern
@item @samp{sync_old_add@var{mode}}, @samp{sync_old_sub@var{mode}}
@itemx @samp{sync_old_ior@var{mode}}, @samp{sync_old_and@var{mode}}
@itemx @samp{sync_old_xor@var{mode}}, @samp{sync_old_nand@var{mode}}
These patterns emit code for an atomic operation on memory,
and return the value that the memory contained before the operation.
Operand 0 is the result value, operand 1 is the memory on which the
atomic operation is performed, and operand 2 is the second operand
to the binary operator.
This pattern must issue any memory barrier instructions such that all
memory operations before the atomic operation occur before the atomic
operation and all memory operations after the atomic operation occur
after the atomic operation.
If these patterns are not defined, the operation will be constructed
from a compare-and-swap operation, if defined.
@cindex @code{sync_new_add@var{mode}} instruction pattern
@cindex @code{sync_new_sub@var{mode}} instruction pattern
@cindex @code{sync_new_ior@var{mode}} instruction pattern
@cindex @code{sync_new_and@var{mode}} instruction pattern
@cindex @code{sync_new_xor@var{mode}} instruction pattern
@cindex @code{sync_new_nand@var{mode}} instruction pattern
@item @samp{sync_new_add@var{mode}}, @samp{sync_new_sub@var{mode}}
@itemx @samp{sync_new_ior@var{mode}}, @samp{sync_new_and@var{mode}}
@itemx @samp{sync_new_xor@var{mode}}, @samp{sync_new_nand@var{mode}}
These patterns are like their @code{sync_old_@var{op}} counterparts,
except that they return the value that exists in the memory location
after the operation, rather than before the operation.
@cindex @code{sync_lock_test_and_set@var{mode}} instruction pattern
@item @samp{sync_lock_test_and_set@var{mode}}
This pattern takes two forms, based on the capabilities of the target.
In either case, operand 0 is the result of the operand, operand 1 is
the memory on which the atomic operation is performed, and operand 2
is the value to set in the lock.
In the ideal case, this operation is an atomic exchange operation, in
which the previous value in memory operand is copied into the result
operand, and the value operand is stored in the memory operand.
For less capable targets, any value operand that is not the constant 1
should be rejected with @code{FAIL}. In this case the target may use
an atomic test-and-set bit operation. The result operand should contain
1 if the bit was previously set and 0 if the bit was previously clear.
The true contents of the memory operand are implementation defined.
This pattern must issue any memory barrier instructions such that the
pattern as a whole acts as an acquire barrier, that is all memory
operations after the pattern do not occur until the lock is acquired.
If this pattern is not defined, the operation will be constructed from
a compare-and-swap operation, if defined.
@cindex @code{sync_lock_release@var{mode}} instruction pattern
@item @samp{sync_lock_release@var{mode}}
This pattern, if defined, releases a lock set by
@code{sync_lock_test_and_set@var{mode}}. Operand 0 is the memory
that contains the lock; operand 1 is the value to store in the lock.
If the target doesn't implement full semantics for
@code{sync_lock_test_and_set@var{mode}}, any value operand which is not
the constant 0 should be rejected with @code{FAIL}, and the true contents
of the memory operand are implementation defined.
This pattern must issue any memory barrier instructions such that the
pattern as a whole acts as a release barrier, that is the lock is
released only after all previous memory operations have completed.
If this pattern is not defined, then a @code{memory_barrier} pattern
will be emitted, followed by a store of the value to the memory operand.
@cindex @code{atomic_compare_and_swap@var{mode}} instruction pattern
@item @samp{atomic_compare_and_swap@var{mode}}
This pattern, if defined, emits code for an atomic compare-and-swap
operation with memory model semantics. Operand 2 is the memory on which
the atomic operation is performed. Operand 0 is an output operand which
is set to true or false based on whether the operation succeeded. Operand
1 is an output operand which is set to the contents of the memory before
the operation was attempted. Operand 3 is the value that is expected to
be in memory. Operand 4 is the value to put in memory if the expected
value is found there. Operand 5 is set to 1 if this compare and swap is to
be treated as a weak operation. Operand 6 is the memory model to be used
if the operation is a success. Operand 7 is the memory model to be used
if the operation fails.
If memory referred to in operand 2 contains the value in operand 3, then
operand 4 is stored in memory pointed to by operand 2 and fencing based on
the memory model in operand 6 is issued.
If memory referred to in operand 2 does not contain the value in operand 3,
then fencing based on the memory model in operand 7 is issued.
If a target does not support weak compare-and-swap operations, or the port
elects not to implement weak operations, the argument in operand 5 can be
ignored. Note a strong implementation must be provided.
If this pattern is not provided, the @code{__atomic_compare_exchange}
built-in functions will utilize the legacy @code{sync_compare_and_swap}
pattern with an @code{__ATOMIC_SEQ_CST} memory model.
@cindex @code{atomic_load@var{mode}} instruction pattern
@item @samp{atomic_load@var{mode}}
This pattern implements an atomic load operation with memory model
semantics. Operand 1 is the memory address being loaded from. Operand 0
is the result of the load. Operand 2 is the memory model to be used for
the load operation.
If not present, the @code{__atomic_load} built-in function will either
resort to a normal load with memory barriers, or a compare-and-swap
operation if a normal load would not be atomic.
@cindex @code{atomic_store@var{mode}} instruction pattern
@item @samp{atomic_store@var{mode}}
This pattern implements an atomic store operation with memory model
semantics. Operand 0 is the memory address being stored to. Operand 1
is the value to be written. Operand 2 is the memory model to be used for
the operation.
If not present, the @code{__atomic_store} built-in function will attempt to
perform a normal store and surround it with any required memory fences. If
the store would not be atomic, then an @code{__atomic_exchange} is
attempted with the result being ignored.
@cindex @code{atomic_exchange@var{mode}} instruction pattern
@item @samp{atomic_exchange@var{mode}}
This pattern implements an atomic exchange operation with memory model
semantics. Operand 1 is the memory location the operation is performed on.
Operand 0 is an output operand which is set to the original value contained
in the memory pointed to by operand 1. Operand 2 is the value to be
stored. Operand 3 is the memory model to be used.
If this pattern is not present, the built-in function
@code{__atomic_exchange} will attempt to preform the operation with a
compare and swap loop.
@cindex @code{atomic_add@var{mode}} instruction pattern
@cindex @code{atomic_sub@var{mode}} instruction pattern
@cindex @code{atomic_or@var{mode}} instruction pattern
@cindex @code{atomic_and@var{mode}} instruction pattern
@cindex @code{atomic_xor@var{mode}} instruction pattern
@cindex @code{atomic_nand@var{mode}} instruction pattern
@item @samp{atomic_add@var{mode}}, @samp{atomic_sub@var{mode}}
@itemx @samp{atomic_or@var{mode}}, @samp{atomic_and@var{mode}}
@itemx @samp{atomic_xor@var{mode}}, @samp{atomic_nand@var{mode}}
These patterns emit code for an atomic operation on memory with memory
model semantics. Operand 0 is the memory on which the atomic operation is
performed. Operand 1 is the second operand to the binary operator.
Operand 2 is the memory model to be used by the operation.
If these patterns are not defined, attempts will be made to use legacy
@code{sync} patterns, or equivalent patterns which return a result. If
none of these are available a compare-and-swap loop will be used.
@cindex @code{atomic_fetch_add@var{mode}} instruction pattern
@cindex @code{atomic_fetch_sub@var{mode}} instruction pattern
@cindex @code{atomic_fetch_or@var{mode}} instruction pattern
@cindex @code{atomic_fetch_and@var{mode}} instruction pattern
@cindex @code{atomic_fetch_xor@var{mode}} instruction pattern
@cindex @code{atomic_fetch_nand@var{mode}} instruction pattern
@item @samp{atomic_fetch_add@var{mode}}, @samp{atomic_fetch_sub@var{mode}}
@itemx @samp{atomic_fetch_or@var{mode}}, @samp{atomic_fetch_and@var{mode}}
@itemx @samp{atomic_fetch_xor@var{mode}}, @samp{atomic_fetch_nand@var{mode}}
These patterns emit code for an atomic operation on memory with memory
model semantics, and return the original value. Operand 0 is an output
operand which contains the value of the memory location before the
operation was performed. Operand 1 is the memory on which the atomic
operation is performed. Operand 2 is the second operand to the binary
operator. Operand 3 is the memory model to be used by the operation.
If these patterns are not defined, attempts will be made to use legacy
@code{sync} patterns. If none of these are available a compare-and-swap
loop will be used.
@cindex @code{atomic_add_fetch@var{mode}} instruction pattern
@cindex @code{atomic_sub_fetch@var{mode}} instruction pattern
@cindex @code{atomic_or_fetch@var{mode}} instruction pattern
@cindex @code{atomic_and_fetch@var{mode}} instruction pattern
@cindex @code{atomic_xor_fetch@var{mode}} instruction pattern
@cindex @code{atomic_nand_fetch@var{mode}} instruction pattern
@item @samp{atomic_add_fetch@var{mode}}, @samp{atomic_sub_fetch@var{mode}}
@itemx @samp{atomic_or_fetch@var{mode}}, @samp{atomic_and_fetch@var{mode}}
@itemx @samp{atomic_xor_fetch@var{mode}}, @samp{atomic_nand_fetch@var{mode}}
These patterns emit code for an atomic operation on memory with memory
model semantics and return the result after the operation is performed.
Operand 0 is an output operand which contains the value after the
operation. Operand 1 is the memory on which the atomic operation is
performed. Operand 2 is the second operand to the binary operator.
Operand 3 is the memory model to be used by the operation.
If these patterns are not defined, attempts will be made to use legacy
@code{sync} patterns, or equivalent patterns which return the result before
the operation followed by the arithmetic operation required to produce the
result. If none of these are available a compare-and-swap loop will be
used.
@cindex @code{atomic_test_and_set} instruction pattern
@item @samp{atomic_test_and_set}
This pattern emits code for @code{__builtin_atomic_test_and_set}.
Operand 0 is an output operand which is set to true if the previous
previous contents of the byte was "set", and false otherwise. Operand 1
is the @code{QImode} memory to be modified. Operand 2 is the memory
model to be used.
The specific value that defines "set" is implementation defined, and
is normally based on what is performed by the native atomic test and set
instruction.
@cindex @code{atomic_bit_test_and_set@var{mode}} instruction pattern
@cindex @code{atomic_bit_test_and_complement@var{mode}} instruction pattern
@cindex @code{atomic_bit_test_and_reset@var{mode}} instruction pattern
@item @samp{atomic_bit_test_and_set@var{mode}}
@itemx @samp{atomic_bit_test_and_complement@var{mode}}
@itemx @samp{atomic_bit_test_and_reset@var{mode}}
These patterns emit code for an atomic bitwise operation on memory with memory
model semantics, and return the original value of the specified bit.
Operand 0 is an output operand which contains the value of the specified bit
from the memory location before the operation was performed. Operand 1 is the
memory on which the atomic operation is performed. Operand 2 is the bit within
the operand, starting with least significant bit. Operand 3 is the memory model
to be used by the operation. Operand 4 is a flag - it is @code{const1_rtx}
if operand 0 should contain the original value of the specified bit in the
least significant bit of the operand, and @code{const0_rtx} if the bit should
be in its original position in the operand.
@code{atomic_bit_test_and_set@var{mode}} atomically sets the specified bit after
remembering its original value, @code{atomic_bit_test_and_complement@var{mode}}
inverts the specified bit and @code{atomic_bit_test_and_reset@var{mode}} clears
the specified bit.
If these patterns are not defined, attempts will be made to use
@code{atomic_fetch_or@var{mode}}, @code{atomic_fetch_xor@var{mode}} or
@code{atomic_fetch_and@var{mode}} instruction patterns, or their @code{sync}
counterparts. If none of these are available a compare-and-swap
loop will be used.
@cindex @code{atomic_add_fetch_cmp_0@var{mode}} instruction pattern
@cindex @code{atomic_sub_fetch_cmp_0@var{mode}} instruction pattern
@cindex @code{atomic_and_fetch_cmp_0@var{mode}} instruction pattern
@cindex @code{atomic_or_fetch_cmp_0@var{mode}} instruction pattern
@cindex @code{atomic_xor_fetch_cmp_0@var{mode}} instruction pattern
@item @samp{atomic_add_fetch_cmp_0@var{mode}}
@itemx @samp{atomic_sub_fetch_cmp_0@var{mode}}
@itemx @samp{atomic_and_fetch_cmp_0@var{mode}}
@itemx @samp{atomic_or_fetch_cmp_0@var{mode}}
@itemx @samp{atomic_xor_fetch_cmp_0@var{mode}}
These patterns emit code for an atomic operation on memory with memory
model semantics if the fetch result is used only in a comparison against
zero.
Operand 0 is an output operand which contains a boolean result of comparison
of the value after the operation against zero. Operand 1 is the memory on
which the atomic operation is performed. Operand 2 is the second operand
to the binary operator. Operand 3 is the memory model to be used by the
operation. Operand 4 is an integer holding the comparison code, one of
@code{EQ}, @code{NE}, @code{LT}, @code{GT}, @code{LE} or @code{GE}.
If these patterns are not defined, attempts will be made to use separate
atomic operation and fetch pattern followed by comparison of the result
against zero.
@cindex @code{mem_thread_fence} instruction pattern
@item @samp{mem_thread_fence}
This pattern emits code required to implement a thread fence with
memory model semantics. Operand 0 is the memory model to be used.
For the @code{__ATOMIC_RELAXED} model no instructions need to be issued
and this expansion is not invoked.
The compiler always emits a compiler memory barrier regardless of what
expanding this pattern produced.
If this pattern is not defined, the compiler falls back to expanding the
@code{memory_barrier} pattern, then to emitting @code{__sync_synchronize}
library call, and finally to just placing a compiler memory barrier.
@cindex @code{get_thread_pointer@var{mode}} instruction pattern
@cindex @code{set_thread_pointer@var{mode}} instruction pattern
@item @samp{get_thread_pointer@var{mode}}
@itemx @samp{set_thread_pointer@var{mode}}
These patterns emit code that reads/sets the TLS thread pointer. Currently,
these are only needed if the target needs to support the
@code{__builtin_thread_pointer} and @code{__builtin_set_thread_pointer}
builtins.
The get/set patterns have a single output/input operand respectively,
with @var{mode} intended to be @code{Pmode}.
@cindex @code{stack_protect_combined_set} instruction pattern
@item @samp{stack_protect_combined_set}
This pattern, if defined, moves a @code{ptr_mode} value from an address
whose declaration RTX is given in operand 1 to the memory in operand 0
without leaving the value in a register afterward. If several
instructions are needed by the target to perform the operation (eg. to
load the address from a GOT entry then load the @code{ptr_mode} value
and finally store it), it is the backend's responsibility to ensure no
intermediate result gets spilled. This is to avoid leaking the value
some place that an attacker might use to rewrite the stack guard slot
after having clobbered it.
If this pattern is not defined, then the address declaration is
expanded first in the standard way and a @code{stack_protect_set}
pattern is then generated to move the value from that address to the
address in operand 0.
@cindex @code{stack_protect_set} instruction pattern
@item @samp{stack_protect_set}
This pattern, if defined, moves a @code{ptr_mode} value from the valid
memory location in operand 1 to the memory in operand 0 without leaving
the value in a register afterward. This is to avoid leaking the value
some place that an attacker might use to rewrite the stack guard slot
after having clobbered it.
Note: on targets where the addressing modes do not allow to load
directly from stack guard address, the address is expanded in a standard
way first which could cause some spills.
If this pattern is not defined, then a plain move pattern is generated.
@cindex @code{stack_protect_combined_test} instruction pattern
@item @samp{stack_protect_combined_test}
This pattern, if defined, compares a @code{ptr_mode} value from an
address whose declaration RTX is given in operand 1 with the memory in
operand 0 without leaving the value in a register afterward and
branches to operand 2 if the values were equal. If several
instructions are needed by the target to perform the operation (eg. to
load the address from a GOT entry then load the @code{ptr_mode} value
and finally store it), it is the backend's responsibility to ensure no
intermediate result gets spilled. This is to avoid leaking the value
some place that an attacker might use to rewrite the stack guard slot
after having clobbered it.
If this pattern is not defined, then the address declaration is
expanded first in the standard way and a @code{stack_protect_test}
pattern is then generated to compare the value from that address to the
value at the memory in operand 0.
@cindex @code{stack_protect_test} instruction pattern
@item @samp{stack_protect_test}
This pattern, if defined, compares a @code{ptr_mode} value from the
valid memory location in operand 1 with the memory in operand 0 without
leaving the value in a register afterward and branches to operand 2 if
the values were equal.
If this pattern is not defined, then a plain compare pattern and
conditional branch pattern is used.
@cindex @code{clear_cache} instruction pattern
@item @samp{clear_cache}
This pattern, if defined, flushes the instruction cache for a region of
memory. The region is bounded to by the Pmode pointers in operand 0
inclusive and operand 1 exclusive.
If this pattern is not defined, a call to the library function
@code{__clear_cache} is used.
@cindex @code{spaceship@var{m}3} instruction pattern
@item @samp{spaceship@var{m}3}
Initialize output operand 0 with mode of integer type to -1, 0, 1 or 2
if operand 1 with mode @var{m} compares less than operand 2, equal to
operand 2, greater than operand 2 or is unordered with operand 2.
@var{m} should be a scalar floating point mode.
This pattern is not allowed to @code{FAIL}.
@end table
@end ifset
@c Each of the following nodes are wrapped in separate
@c "@ifset INTERNALS" to work around memory limits for the default
@c configuration in older tetex distributions. Known to not work:
@c tetex-1.0.7, known to work: tetex-2.0.2.
@ifset INTERNALS
@node Pattern Ordering
@section When the Order of Patterns Matters
@cindex Pattern Ordering
@cindex Ordering of Patterns
Sometimes an insn can match more than one instruction pattern. Then the
pattern that appears first in the machine description is the one used.
Therefore, more specific patterns (patterns that will match fewer things)
and faster instructions (those that will produce better code when they
do match) should usually go first in the description.
In some cases the effect of ordering the patterns can be used to hide
a pattern when it is not valid. For example, the 68000 has an
instruction for converting a fullword to floating point and another
for converting a byte to floating point. An instruction converting
an integer to floating point could match either one. We put the
pattern to convert the fullword first to make sure that one will
be used rather than the other. (Otherwise a large integer might
be generated as a single-byte immediate quantity, which would not work.)
Instead of using this pattern ordering it would be possible to make the
pattern for convert-a-byte smart enough to deal properly with any
constant value.
@end ifset
@ifset INTERNALS
@node Dependent Patterns
@section Interdependence of Patterns
@cindex Dependent Patterns
@cindex Interdependence of Patterns
In some cases machines support instructions identical except for the
machine mode of one or more operands. For example, there may be
``sign-extend halfword'' and ``sign-extend byte'' instructions whose
patterns are
@smallexample
(set (match_operand:SI 0 @dots{})
(extend:SI (match_operand:HI 1 @dots{})))
(set (match_operand:SI 0 @dots{})
(extend:SI (match_operand:QI 1 @dots{})))
@end smallexample
@noindent
Constant integers do not specify a machine mode, so an instruction to
extend a constant value could match either pattern. The pattern it
actually will match is the one that appears first in the file. For correct
results, this must be the one for the widest possible mode (@code{HImode},
here). If the pattern matches the @code{QImode} instruction, the results
will be incorrect if the constant value does not actually fit that mode.
Such instructions to extend constants are rarely generated because they are
optimized away, but they do occasionally happen in nonoptimized
compilations.
If a constraint in a pattern allows a constant, the reload pass may
replace a register with a constant permitted by the constraint in some
cases. Similarly for memory references. Because of this substitution,
you should not provide separate patterns for increment and decrement
instructions. Instead, they should be generated from the same pattern
that supports register-register add insns by examining the operands and
generating the appropriate machine instruction.
@end ifset
@ifset INTERNALS
@node Jump Patterns
@section Defining Jump Instruction Patterns
@cindex jump instruction patterns
@cindex defining jump instruction patterns
GCC does not assume anything about how the machine realizes jumps.
The machine description should define a single pattern, usually
a @code{define_expand}, which expands to all the required insns.
Usually, this would be a comparison insn to set the condition code
and a separate branch insn testing the condition code and branching
or not according to its value. For many machines, however,
separating compares and branches is limiting, which is why the
more flexible approach with one @code{define_expand} is used in GCC.
The machine description becomes clearer for architectures that
have compare-and-branch instructions but no condition code. It also
works better when different sets of comparison operators are supported
by different kinds of conditional branches (e.g.@: integer vs.@:
floating-point), or by conditional branches with respect to conditional stores.
Two separate insns are always used on most machines that use a separate
condition code register (@pxref{Condition Code}).
Even in this case having a single entry point for conditional branches
is advantageous, because it handles equally well the case where a single
comparison instruction records the results of both signed and unsigned
comparison of the given operands (with the branch insns coming in distinct
signed and unsigned flavors) as in the x86 or SPARC, and the case where
there are distinct signed and unsigned compare instructions and only
one set of conditional branch instructions as in the PowerPC.
@end ifset
@ifset INTERNALS
@node Looping Patterns
@section Defining Looping Instruction Patterns
@cindex looping instruction patterns
@cindex defining looping instruction patterns
Some machines have special jump instructions that can be utilized to
make loops more efficient. A common example is the 68000 @samp{dbra}
instruction which performs a decrement of a register and a branch if the
result was greater than zero. Other machines, in particular digital
signal processors (DSPs), have special block repeat instructions to
provide low-overhead loop support. For example, the TI TMS320C3x/C4x
DSPs have a block repeat instruction that loads special registers to
mark the top and end of a loop and to count the number of loop
iterations. This avoids the need for fetching and executing a
@samp{dbra}-like instruction and avoids pipeline stalls associated with
the jump.
GCC has two special named patterns to support low overhead looping.
They are @samp{doloop_begin} and @samp{doloop_end}. These are emitted
by the loop optimizer for certain well-behaved loops with a finite
number of loop iterations using information collected during strength
reduction.
The @samp{doloop_end} pattern describes the actual looping instruction
(or the implicit looping operation) and the @samp{doloop_begin} pattern
is an optional companion pattern that can be used for initialization
needed for some low-overhead looping instructions.
Note that some machines require the actual looping instruction to be
emitted at the top of the loop (e.g., the TMS320C3x/C4x DSPs). Emitting
the true RTL for a looping instruction at the top of the loop can cause
problems with flow analysis. So instead, a dummy @code{doloop} insn is
emitted at the end of the loop. The machine dependent reorg pass checks
for the presence of this @code{doloop} insn and then searches back to
the top of the loop, where it inserts the true looping insn (provided
there are no instructions in the loop which would cause problems). Any
additional labels can be emitted at this point. In addition, if the
desired special iteration counter register was not allocated, this
machine dependent reorg pass could emit a traditional compare and jump
instruction pair.
For the @samp{doloop_end} pattern, the loop optimizer allocates an
additional pseudo register as an iteration counter. This pseudo
register cannot be used within the loop (i.e., general induction
variables cannot be derived from it), however, in many cases the loop
induction variable may become redundant and removed by the flow pass.
The @samp{doloop_end} pattern must have a specific structure to be
handled correctly by GCC. The example below is taken (slightly
simplified) from the PDP-11 target:
@smallexample
@group
(define_expand "doloop_end"
[(parallel [(set (pc)
(if_then_else
(ne (match_operand:HI 0 "nonimmediate_operand" "+r,!m")
(const_int 1))
(label_ref (match_operand 1 "" ""))
(pc)))
(set (match_dup 0)
(plus:HI (match_dup 0)
(const_int -1)))])]
""
"@{
if (GET_MODE (operands[0]) != HImode)
FAIL;
@}")
(define_insn "doloop_end_insn"
[(set (pc)
(if_then_else
(ne (match_operand:HI 0 "nonimmediate_operand" "+r,!m")
(const_int 1))
(label_ref (match_operand 1 "" ""))
(pc)))
(set (match_dup 0)
(plus:HI (match_dup 0)
(const_int -1)))]
""
@{
if (which_alternative == 0)
return "sob %0,%l1";
/* emulate sob */
output_asm_insn ("dec %0", operands);
return "bne %l1";
@})
@end group
@end smallexample
The first part of the pattern describes the branch condition. GCC
supports three cases for the way the target machine handles the loop
counter:
@itemize @bullet
@item Loop terminates when the loop register decrements to zero. This
is represented by a @code{ne} comparison of the register (its old value)
with constant 1 (as in the example above).
@item Loop terminates when the loop register decrements to @minus{}1.
This is represented by a @code{ne} comparison of the register with
constant zero.
@item Loop terminates when the loop register decrements to a negative
value. This is represented by a @code{ge} comparison of the register
with constant zero. For this case, GCC will attach a @code{REG_NONNEG}
note to the @code{doloop_end} insn if it can determine that the register
will be non-negative.
@end itemize
Since the @code{doloop_end} insn is a jump insn that also has an output,
the reload pass does not handle the output operand. Therefore, the
constraint must allow for that operand to be in memory rather than a
register. In the example shown above, that is handled (in the
@code{doloop_end_insn} pattern) by using a loop instruction sequence
that can handle memory operands when the memory alternative appears.
GCC does not check the mode of the loop register operand when generating
the @code{doloop_end} pattern. If the pattern is only valid for some
modes but not others, the pattern should be a @code{define_expand}
pattern that checks the operand mode in the preparation code, and issues
@code{FAIL} if an unsupported mode is found. The example above does
this, since the machine instruction to be used only exists for
@code{HImode}.
If the @code{doloop_end} pattern is a @code{define_expand}, there must
also be a @code{define_insn} or @code{define_insn_and_split} matching
the generated pattern. Otherwise, the compiler will fail during loop
optimization.
@end ifset
@ifset INTERNALS
@node Insn Canonicalizations
@section Canonicalization of Instructions
@cindex canonicalization of instructions
@cindex insn canonicalization
There are often cases where multiple RTL expressions could represent an
operation performed by a single machine instruction. This situation is
most commonly encountered with logical, branch, and multiply-accumulate
instructions. In such cases, the compiler attempts to convert these
multiple RTL expressions into a single canonical form to reduce the
number of insn patterns required.
In addition to algebraic simplifications, following canonicalizations
are performed:
@itemize @bullet
@item
For commutative and comparison operators, a constant is always made the
second operand. If a machine only supports a constant as the second
operand, only patterns that match a constant in the second operand need
be supplied.
@cindex @code{vec_merge}, canonicalization of
@item
For the @code{vec_merge} with constant mask(the third operand), the first
and the second operand can be exchanged by inverting the mask. In such cases,
a constant is always made the second operand, otherwise the least significant
bit of the mask is always set(select the first operand first).
@item
For associative operators, a sequence of operators will always chain
to the left; for instance, only the left operand of an integer @code{plus}
can itself be a @code{plus}. @code{and}, @code{ior}, @code{xor},
@code{plus}, @code{mult}, @code{smin}, @code{smax}, @code{umin}, and
@code{umax} are associative when applied to integers, and sometimes to
floating-point.
@cindex @code{neg}, canonicalization of
@cindex @code{not}, canonicalization of
@cindex @code{mult}, canonicalization of
@cindex @code{plus}, canonicalization of
@cindex @code{minus}, canonicalization of
@item
For these operators, if only one operand is a @code{neg}, @code{not},
@code{mult}, @code{plus}, or @code{minus} expression, it will be the
first operand.
@item
In combinations of @code{neg}, @code{mult}, @code{plus}, and
@code{minus}, the @code{neg} operations (if any) will be moved inside
the operations as far as possible. For instance,
@code{(neg (mult A B))} is canonicalized as @code{(mult (neg A) B)}, but
@code{(plus (mult (neg B) C) A)} is canonicalized as
@code{(minus A (mult B C))}.
@cindex @code{compare}, canonicalization of
@item
For the @code{compare} operator, a constant is always the second operand
if the first argument is a condition code register.
@item
For instructions that inherently set a condition code register, the
@code{compare} operator is always written as the first RTL expression of
the @code{parallel} instruction pattern. For example,
@smallexample
(define_insn ""
[(set (reg:CCZ FLAGS_REG)
(compare:CCZ
(plus:SI
(match_operand:SI 1 "register_operand" "%r")
(match_operand:SI 2 "register_operand" "r"))
(const_int 0)))
(set (match_operand:SI 0 "register_operand" "=r")
(plus:SI (match_dup 1) (match_dup 2)))]
""
"addl %0, %1, %2")
@end smallexample
@item
An operand of @code{neg}, @code{not}, @code{mult}, @code{plus}, or
@code{minus} is made the first operand under the same conditions as
above.
@item
@code{(ltu (plus @var{a} @var{b}) @var{b})} is converted to
@code{(ltu (plus @var{a} @var{b}) @var{a})}. Likewise with @code{geu} instead
of @code{ltu}.
@item
@code{(minus @var{x} (const_int @var{n}))} is converted to
@code{(plus @var{x} (const_int @var{-n}))}.
@item
Within address computations (i.e., inside @code{mem}), a left shift is
converted into the appropriate multiplication by a power of two.
@cindex @code{ior}, canonicalization of
@cindex @code{and}, canonicalization of
@cindex De Morgan's law
@item
De Morgan's Law is used to move bitwise negation inside a bitwise
logical-and or logical-or operation. If this results in only one
operand being a @code{not} expression, it will be the first one.
A machine that has an instruction that performs a bitwise logical-and of one
operand with the bitwise negation of the other should specify the pattern
for that instruction as
@smallexample
(define_insn ""
[(set (match_operand:@var{m} 0 @dots{})
(and:@var{m} (not:@var{m} (match_operand:@var{m} 1 @dots{}))
(match_operand:@var{m} 2 @dots{})))]
"@dots{}"
"@dots{}")
@end smallexample
@noindent
Similarly, a pattern for a ``NAND'' instruction should be written
@smallexample
(define_insn ""
[(set (match_operand:@var{m} 0 @dots{})
(ior:@var{m} (not:@var{m} (match_operand:@var{m} 1 @dots{}))
(not:@var{m} (match_operand:@var{m} 2 @dots{}))))]
"@dots{}"
"@dots{}")
@end smallexample
In both cases, it is not necessary to include patterns for the many
logically equivalent RTL expressions.
@cindex @code{xor}, canonicalization of
@item
The only possible RTL expressions involving both bitwise exclusive-or
and bitwise negation are @code{(xor:@var{m} @var{x} @var{y})}
and @code{(not:@var{m} (xor:@var{m} @var{x} @var{y}))}.
@item
The sum of three items, one of which is a constant, will only appear in
the form
@smallexample
(plus:@var{m} (plus:@var{m} @var{x} @var{y}) @var{constant})
@end smallexample
@cindex @code{zero_extract}, canonicalization of
@cindex @code{sign_extract}, canonicalization of
@item
Equality comparisons of a group of bits (usually a single bit) with zero
will be written using @code{zero_extract} rather than the equivalent
@code{and} or @code{sign_extract} operations.
@cindex @code{mult}, canonicalization of
@item
@code{(sign_extend:@var{m1} (mult:@var{m2} (sign_extend:@var{m2} @var{x})
(sign_extend:@var{m2} @var{y})))} is converted to @code{(mult:@var{m1}
(sign_extend:@var{m1} @var{x}) (sign_extend:@var{m1} @var{y}))}, and likewise
for @code{zero_extend}.
@item
@code{(sign_extend:@var{m1} (mult:@var{m2} (ashiftrt:@var{m2}
@var{x} @var{s}) (sign_extend:@var{m2} @var{y})))} is converted
to @code{(mult:@var{m1} (sign_extend:@var{m1} (ashiftrt:@var{m2}
@var{x} @var{s})) (sign_extend:@var{m1} @var{y}))}, and likewise for
patterns using @code{zero_extend} and @code{lshiftrt}. If the second
operand of @code{mult} is also a shift, then that is extended also.
This transformation is only applied when it can be proven that the
original operation had sufficient precision to prevent overflow.
@end itemize
Further canonicalization rules are defined in the function
@code{commutative_operand_precedence} in @file{gcc/rtlanal.cc}.
@end ifset
@ifset INTERNALS
@node Expander Definitions
@section Defining RTL Sequences for Code Generation
@cindex expander definitions
@cindex code generation RTL sequences
@cindex defining RTL sequences for code generation
On some target machines, some standard pattern names for RTL generation
cannot be handled with single insn, but a sequence of RTL insns can
represent them. For these target machines, you can write a
@code{define_expand} to specify how to generate the sequence of RTL@.
@findex define_expand
A @code{define_expand} is an RTL expression that looks almost like a
@code{define_insn}; but, unlike the latter, a @code{define_expand} is used
only for RTL generation and it can produce more than one RTL insn.
A @code{define_expand} RTX has four operands:
@itemize @bullet
@item
The name. Each @code{define_expand} must have a name, since the only
use for it is to refer to it by name.
@item
The RTL template. This is a vector of RTL expressions representing
a sequence of separate instructions. Unlike @code{define_insn}, there
is no implicit surrounding @code{PARALLEL}.
@item
The condition, a string containing a C expression. This expression is
used to express how the availability of this pattern depends on
subclasses of target machine, selected by command-line options when GCC
is run. This is just like the condition of a @code{define_insn} that
has a standard name. Therefore, the condition (if present) may not
depend on the data in the insn being matched, but only the
target-machine-type flags. The compiler needs to test these conditions
during initialization in order to learn exactly which named instructions
are available in a particular run.
@item
The preparation statements, a string containing zero or more C
statements which are to be executed before RTL code is generated from
the RTL template.
Usually these statements prepare temporary registers for use as
internal operands in the RTL template, but they can also generate RTL
insns directly by calling routines such as @code{emit_insn}, etc.
Any such insns precede the ones that come from the RTL template.
@item
Optionally, a vector containing the values of attributes. @xref{Insn
Attributes}.
@end itemize
Every RTL insn emitted by a @code{define_expand} must match some
@code{define_insn} in the machine description. Otherwise, the compiler
will crash when trying to generate code for the insn or trying to optimize
it.
The RTL template, in addition to controlling generation of RTL insns,
also describes the operands that need to be specified when this pattern
is used. In particular, it gives a predicate for each operand.
A true operand, which needs to be specified in order to generate RTL from
the pattern, should be described with a @code{match_operand} in its first
occurrence in the RTL template. This enters information on the operand's
predicate into the tables that record such things. GCC uses the
information to preload the operand into a register if that is required for
valid RTL code. If the operand is referred to more than once, subsequent
references should use @code{match_dup}.
The RTL template may also refer to internal ``operands'' which are
temporary registers or labels used only within the sequence made by the
@code{define_expand}. Internal operands are substituted into the RTL
template with @code{match_dup}, never with @code{match_operand}. The
values of the internal operands are not passed in as arguments by the
compiler when it requests use of this pattern. Instead, they are computed
within the pattern, in the preparation statements. These statements
compute the values and store them into the appropriate elements of
@code{operands} so that @code{match_dup} can find them.
There are two special macros defined for use in the preparation statements:
@code{DONE} and @code{FAIL}. Use them with a following semicolon,
as a statement.
@table @code
@findex DONE
@item DONE
Use the @code{DONE} macro to end RTL generation for the pattern. The
only RTL insns resulting from the pattern on this occasion will be
those already emitted by explicit calls to @code{emit_insn} within the
preparation statements; the RTL template will not be generated.
@findex FAIL
@item FAIL
Make the pattern fail on this occasion. When a pattern fails, it means
that the pattern was not truly available. The calling routines in the
compiler will try other strategies for code generation using other patterns.
Failure is currently supported only for binary (addition, multiplication,
shifting, etc.) and bit-field (@code{extv}, @code{extzv}, and @code{insv})
operations.
@end table
If the preparation falls through (invokes neither @code{DONE} nor
@code{FAIL}), then the @code{define_expand} acts like a
@code{define_insn} in that the RTL template is used to generate the
insn.
The RTL template is not used for matching, only for generating the
initial insn list. If the preparation statement always invokes
@code{DONE} or @code{FAIL}, the RTL template may be reduced to a simple
list of operands, such as this example:
@smallexample
@group
(define_expand "addsi3"
[(match_operand:SI 0 "register_operand" "")
(match_operand:SI 1 "register_operand" "")
(match_operand:SI 2 "register_operand" "")]
""
"
@{
handle_add (operands[0], operands[1], operands[2]);
DONE;
@}")
@end group
@end smallexample
Here is an example, the definition of left-shift for the SPUR chip:
@smallexample
@group
(define_expand "ashlsi3"
[(set (match_operand:SI 0 "register_operand" "")
(ashift:SI
(match_operand:SI 1 "register_operand" "")
(match_operand:SI 2 "nonmemory_operand" "")))]
""
"
@{
if (GET_CODE (operands[2]) != CONST_INT
|| (unsigned) INTVAL (operands[2]) > 3)
FAIL;
@}")
@end group
@end smallexample
@noindent
This example uses @code{define_expand} so that it can generate an RTL insn
for shifting when the shift-count is in the supported range of 0 to 3 but
fail in other cases where machine insns aren't available. When it fails,
the compiler tries another strategy using different patterns (such as, a
library call).
If the compiler were able to handle nontrivial condition-strings in
patterns with names, then it would be possible to use a
@code{define_insn} in that case. Here is another case (zero-extension
on the 68000) which makes more use of the power of @code{define_expand}:
@smallexample
(define_expand "zero_extendhisi2"
[(set (match_operand:SI 0 "general_operand" "")
(const_int 0))
(set (strict_low_part
(subreg:HI
(match_dup 0)
0))
(match_operand:HI 1 "general_operand" ""))]
""
"operands[1] = make_safe_from (operands[1], operands[0]);")
@end smallexample
@noindent
@findex make_safe_from
Here two RTL insns are generated, one to clear the entire output operand
and the other to copy the input operand into its low half. This sequence
is incorrect if the input operand refers to [the old value of] the output
operand, so the preparation statement makes sure this isn't so. The
function @code{make_safe_from} copies the @code{operands[1]} into a
temporary register if it refers to @code{operands[0]}. It does this
by emitting another RTL insn.
Finally, a third example shows the use of an internal operand.
Zero-extension on the SPUR chip is done by @code{and}-ing the result
against a halfword mask. But this mask cannot be represented by a
@code{const_int} because the constant value is too large to be legitimate
on this machine. So it must be copied into a register with
@code{force_reg} and then the register used in the @code{and}.
@smallexample
(define_expand "zero_extendhisi2"
[(set (match_operand:SI 0 "register_operand" "")
(and:SI (subreg:SI
(match_operand:HI 1 "register_operand" "")
0)
(match_dup 2)))]
""
"operands[2]
= force_reg (SImode, GEN_INT (65535)); ")
@end smallexample
@emph{Note:} If the @code{define_expand} is used to serve a
standard binary or unary arithmetic operation or a bit-field operation,
then the last insn it generates must not be a @code{code_label},
@code{barrier} or @code{note}. It must be an @code{insn},
@code{jump_insn} or @code{call_insn}. If you don't need a real insn
at the end, emit an insn to copy the result of the operation into
itself. Such an insn will generate no code, but it can avoid problems
in the compiler.
@end ifset
@ifset INTERNALS
@node Insn Splitting
@section Defining How to Split Instructions
@cindex insn splitting
@cindex instruction splitting
@cindex splitting instructions
There are two cases where you should specify how to split a pattern
into multiple insns. On machines that have instructions requiring
delay slots (@pxref{Delay Slots}) or that have instructions whose
output is not available for multiple cycles (@pxref{Processor pipeline
description}), the compiler phases that optimize these cases need to
be able to move insns into one-instruction delay slots. However, some
insns may generate more than one machine instruction. These insns
cannot be placed into a delay slot.
Often you can rewrite the single insn as a list of individual insns,
each corresponding to one machine instruction. The disadvantage of
doing so is that it will cause the compilation to be slower and require
more space. If the resulting insns are too complex, it may also
suppress some optimizations. The compiler splits the insn if there is a
reason to believe that it might improve instruction or delay slot
scheduling.
The insn combiner phase also splits putative insns. If three insns are
merged into one insn with a complex expression that cannot be matched by
some @code{define_insn} pattern, the combiner phase attempts to split
the complex pattern into two insns that are recognized. Usually it can
break the complex pattern into two patterns by splitting out some
subexpression. However, in some other cases, such as performing an
addition of a large constant in two insns on a RISC machine, the way to
split the addition into two insns is machine-dependent.
@findex define_split
The @code{define_split} definition tells the compiler how to split a
complex insn into several simpler insns. It looks like this:
@smallexample
(define_split
[@var{insn-pattern}]
"@var{condition}"
[@var{new-insn-pattern-1}
@var{new-insn-pattern-2}
@dots{}]
"@var{preparation-statements}")
@end smallexample
@var{insn-pattern} is a pattern that needs to be split and
@var{condition} is the final condition to be tested, as in a
@code{define_insn}. When an insn matching @var{insn-pattern} and
satisfying @var{condition} is found, it is replaced in the insn list
with the insns given by @var{new-insn-pattern-1},
@var{new-insn-pattern-2}, etc.
The @var{preparation-statements} are similar to those statements that
are specified for @code{define_expand} (@pxref{Expander Definitions})
and are executed before the new RTL is generated to prepare for the
generated code or emit some insns whose pattern is not fixed. Unlike
those in @code{define_expand}, however, these statements must not
generate any new pseudo-registers. Once reload has completed, they also
must not allocate any space in the stack frame.
There are two special macros defined for use in the preparation statements:
@code{DONE} and @code{FAIL}. Use them with a following semicolon,
as a statement.
@table @code
@findex DONE
@item DONE
Use the @code{DONE} macro to end RTL generation for the splitter. The
only RTL insns generated as replacement for the matched input insn will
be those already emitted by explicit calls to @code{emit_insn} within
the preparation statements; the replacement pattern is not used.
@findex FAIL
@item FAIL
Make the @code{define_split} fail on this occasion. When a @code{define_split}
fails, it means that the splitter was not truly available for the inputs
it was given, and the input insn will not be split.
@end table
If the preparation falls through (invokes neither @code{DONE} nor
@code{FAIL}), then the @code{define_split} uses the replacement
template.
Patterns are matched against @var{insn-pattern} in two different
circumstances. If an insn needs to be split for delay slot scheduling
or insn scheduling, the insn is already known to be valid, which means
that it must have been matched by some @code{define_insn} and, if
@code{reload_completed} is nonzero, is known to satisfy the constraints
of that @code{define_insn}. In that case, the new insn patterns must
also be insns that are matched by some @code{define_insn} and, if
@code{reload_completed} is nonzero, must also satisfy the constraints
of those definitions.
As an example of this usage of @code{define_split}, consider the following
example from @file{a29k.md}, which splits a @code{sign_extend} from
@code{HImode} to @code{SImode} into a pair of shift insns:
@smallexample
(define_split
[(set (match_operand:SI 0 "gen_reg_operand" "")
(sign_extend:SI (match_operand:HI 1 "gen_reg_operand" "")))]
""
[(set (match_dup 0)
(ashift:SI (match_dup 1)
(const_int 16)))
(set (match_dup 0)
(ashiftrt:SI (match_dup 0)
(const_int 16)))]
"
@{ operands[1] = gen_lowpart (SImode, operands[1]); @}")
@end smallexample
When the combiner phase tries to split an insn pattern, it is always the
case that the pattern is @emph{not} matched by any @code{define_insn}.
The combiner pass first tries to split a single @code{set} expression
and then the same @code{set} expression inside a @code{parallel}, but
followed by a @code{clobber} of a pseudo-reg to use as a scratch
register. In these cases, the combiner expects exactly one or two new insn
patterns to be generated. It will verify that these patterns match some
@code{define_insn} definitions, so you need not do this test in the
@code{define_split} (of course, there is no point in writing a
@code{define_split} that will never produce insns that match).
Here is an example of this use of @code{define_split}, taken from
@file{rs6000.md}:
@smallexample
(define_split
[(set (match_operand:SI 0 "gen_reg_operand" "")
(plus:SI (match_operand:SI 1 "gen_reg_operand" "")
(match_operand:SI 2 "non_add_cint_operand" "")))]
""
[(set (match_dup 0) (plus:SI (match_dup 1) (match_dup 3)))
(set (match_dup 0) (plus:SI (match_dup 0) (match_dup 4)))]
"
@{
int low = INTVAL (operands[2]) & 0xffff;
int high = (unsigned) INTVAL (operands[2]) >> 16;
if (low & 0x8000)
high++, low |= 0xffff0000;
operands[3] = GEN_INT (high << 16);
operands[4] = GEN_INT (low);
@}")
@end smallexample
Here the predicate @code{non_add_cint_operand} matches any
@code{const_int} that is @emph{not} a valid operand of a single add
insn. The add with the smaller displacement is written so that it
can be substituted into the address of a subsequent operation.
An example that uses a scratch register, from the same file, generates
an equality comparison of a register and a large constant:
@smallexample
(define_split
[(set (match_operand:CC 0 "cc_reg_operand" "")
(compare:CC (match_operand:SI 1 "gen_reg_operand" "")
(match_operand:SI 2 "non_short_cint_operand" "")))
(clobber (match_operand:SI 3 "gen_reg_operand" ""))]
"find_single_use (operands[0], insn, 0)
&& (GET_CODE (*find_single_use (operands[0], insn, 0)) == EQ
|| GET_CODE (*find_single_use (operands[0], insn, 0)) == NE)"
[(set (match_dup 3) (xor:SI (match_dup 1) (match_dup 4)))
(set (match_dup 0) (compare:CC (match_dup 3) (match_dup 5)))]
"
@{
/* @r{Get the constant we are comparing against, C, and see what it
looks like sign-extended to 16 bits. Then see what constant
could be XOR'ed with C to get the sign-extended value.} */
int c = INTVAL (operands[2]);
int sextc = (c << 16) >> 16;
int xorv = c ^ sextc;
operands[4] = GEN_INT (xorv);
operands[5] = GEN_INT (sextc);
@}")
@end smallexample
To avoid confusion, don't write a single @code{define_split} that
accepts some insns that match some @code{define_insn} as well as some
insns that don't. Instead, write two separate @code{define_split}
definitions, one for the insns that are valid and one for the insns that
are not valid.
The splitter is allowed to split jump instructions into a sequence of jumps or
create new jumps while splitting non-jump instructions. As the control flow
graph and branch prediction information needs to be updated after the splitter
runs, several restrictions apply.
Splitting of a jump instruction into a sequence that has another jump
instruction to the same label is always valid, as the compiler expects
identical behavior of the new jump. When the new sequence contains multiple
jump instructions or new labels, more assistance is needed. The splitter is
permitted to create only unconditional jumps, or simple conditional jump
instructions. Additionally it must attach a @code{REG_BR_PROB} note to each
conditional jump. A global variable @code{split_branch_probability} holds the
probability of the original branch in case it was a simple conditional jump,
@minus{}1 otherwise. To simplify recomputing of edge frequencies, the new
sequence is permitted to have only forward jumps to the newly-created labels.
@findex define_insn_and_split
For the common case where the pattern of a define_split exactly matches the
pattern of a define_insn, use @code{define_insn_and_split}. It looks like
this:
@smallexample
(define_insn_and_split
[@var{insn-pattern}]
"@var{condition}"
"@var{output-template}"
"@var{split-condition}"
[@var{new-insn-pattern-1}
@var{new-insn-pattern-2}
@dots{}]
"@var{preparation-statements}"
[@var{insn-attributes}])
@end smallexample
@var{insn-pattern}, @var{condition}, @var{output-template}, and
@var{insn-attributes} are used as in @code{define_insn}. The
@var{new-insn-pattern} vector and the @var{preparation-statements} are used as
in a @code{define_split}. The @var{split-condition} is also used as in
@code{define_split}, with the additional behavior that if the condition starts
with @samp{&&}, the condition used for the split will be the constructed as a
logical ``and'' of the split condition with the insn condition. For example,
from i386.md:
@smallexample
(define_insn_and_split "zero_extendhisi2_and"
[(set (match_operand:SI 0 "register_operand" "=r")
(zero_extend:SI (match_operand:HI 1 "register_operand" "0")))
(clobber (reg:CC 17))]
"TARGET_ZERO_EXTEND_WITH_AND && !optimize_size"
"#"
"&& reload_completed"
[(parallel [(set (match_dup 0)
(and:SI (match_dup 0) (const_int 65535)))
(clobber (reg:CC 17))])]
""
[(set_attr "type" "alu1")])
@end smallexample
In this case, the actual split condition will be
@samp{TARGET_ZERO_EXTEND_WITH_AND && !optimize_size && reload_completed}.
The @code{define_insn_and_split} construction provides exactly the same
functionality as two separate @code{define_insn} and @code{define_split}
patterns. It exists for compactness, and as a maintenance tool to prevent
having to ensure the two patterns' templates match.
@findex define_insn_and_rewrite
It is sometimes useful to have a @code{define_insn_and_split}
that replaces specific operands of an instruction but leaves the
rest of the instruction pattern unchanged. You can do this directly
with a @code{define_insn_and_split}, but it requires a
@var{new-insn-pattern-1} that repeats most of the original @var{insn-pattern}.
There is also the complication that an implicit @code{parallel} in
@var{insn-pattern} must become an explicit @code{parallel} in
@var{new-insn-pattern-1}, which is easy to overlook.
A simpler alternative is to use @code{define_insn_and_rewrite}, which
is a form of @code{define_insn_and_split} that automatically generates
@var{new-insn-pattern-1} by replacing each @code{match_operand}
in @var{insn-pattern} with a corresponding @code{match_dup}, and each
@code{match_operator} in the pattern with a corresponding @code{match_op_dup}.
The arguments are otherwise identical to @code{define_insn_and_split}:
@smallexample
(define_insn_and_rewrite
[@var{insn-pattern}]
"@var{condition}"
"@var{output-template}"
"@var{split-condition}"
"@var{preparation-statements}"
[@var{insn-attributes}])
@end smallexample
The @code{match_dup}s and @code{match_op_dup}s in the new
instruction pattern use any new operand values that the
@var{preparation-statements} store in the @code{operands} array,
as for a normal @code{define_insn_and_split}. @var{preparation-statements}
can also emit additional instructions before the new instruction.
They can even emit an entirely different sequence of instructions and
use @code{DONE} to avoid emitting a new form of the original
instruction.
The split in a @code{define_insn_and_rewrite} is only intended
to apply to existing instructions that match @var{insn-pattern}.
@var{split-condition} must therefore start with @code{&&},
so that the split condition applies on top of @var{condition}.
Here is an example from the AArch64 SVE port, in which operand 1 is
known to be equivalent to an all-true constant and isn't used by the
output template:
@smallexample
(define_insn_and_rewrite "*while_ult<GPI:mode><PRED_ALL:mode>_cc"
[(set (reg:CC CC_REGNUM)
(compare:CC
(unspec:SI [(match_operand:PRED_ALL 1)
(unspec:PRED_ALL
[(match_operand:GPI 2 "aarch64_reg_or_zero" "rZ")
(match_operand:GPI 3 "aarch64_reg_or_zero" "rZ")]
UNSPEC_WHILE_LO)]
UNSPEC_PTEST_PTRUE)
(const_int 0)))
(set (match_operand:PRED_ALL 0 "register_operand" "=Upa")
(unspec:PRED_ALL [(match_dup 2)
(match_dup 3)]
UNSPEC_WHILE_LO))]
"TARGET_SVE"
"whilelo\t%0.<PRED_ALL:Vetype>, %<w>2, %<w>3"
;; Force the compiler to drop the unused predicate operand, so that we
;; don't have an unnecessary PTRUE.
"&& !CONSTANT_P (operands[1])"
@{
operands[1] = CONSTM1_RTX (<MODE>mode);
@}
)
@end smallexample
The splitter in this case simply replaces operand 1 with the constant
value that it is known to have. The equivalent @code{define_insn_and_split}
would be:
@smallexample
(define_insn_and_split "*while_ult<GPI:mode><PRED_ALL:mode>_cc"
[(set (reg:CC CC_REGNUM)
(compare:CC
(unspec:SI [(match_operand:PRED_ALL 1)
(unspec:PRED_ALL
[(match_operand:GPI 2 "aarch64_reg_or_zero" "rZ")
(match_operand:GPI 3 "aarch64_reg_or_zero" "rZ")]
UNSPEC_WHILE_LO)]
UNSPEC_PTEST_PTRUE)
(const_int 0)))
(set (match_operand:PRED_ALL 0 "register_operand" "=Upa")
(unspec:PRED_ALL [(match_dup 2)
(match_dup 3)]
UNSPEC_WHILE_LO))]
"TARGET_SVE"
"whilelo\t%0.<PRED_ALL:Vetype>, %<w>2, %<w>3"
;; Force the compiler to drop the unused predicate operand, so that we
;; don't have an unnecessary PTRUE.
"&& !CONSTANT_P (operands[1])"
[(parallel
[(set (reg:CC CC_REGNUM)
(compare:CC
(unspec:SI [(match_dup 1)
(unspec:PRED_ALL [(match_dup 2)
(match_dup 3)]
UNSPEC_WHILE_LO)]
UNSPEC_PTEST_PTRUE)
(const_int 0)))
(set (match_dup 0)
(unspec:PRED_ALL [(match_dup 2)
(match_dup 3)]
UNSPEC_WHILE_LO))])]
@{
operands[1] = CONSTM1_RTX (<MODE>mode);
@}
)
@end smallexample
@end ifset
@ifset INTERNALS
@node Including Patterns
@section Including Patterns in Machine Descriptions.
@cindex insn includes
@findex include
The @code{include} pattern tells the compiler tools where to
look for patterns that are in files other than in the file
@file{.md}. This is used only at build time and there is no preprocessing allowed.
It looks like:
@smallexample
(include @var{pathname})
@end smallexample
For example:
@smallexample
(include "filestuff")
@end smallexample
Where @var{pathname} is a string that specifies the location of the file,
specifies the include file to be in @file{gcc/config/target/filestuff}. The
directory @file{gcc/config/target} is regarded as the default directory.
Machine descriptions may be split up into smaller more manageable subsections
and placed into subdirectories.
By specifying:
@smallexample
(include "BOGUS/filestuff")
@end smallexample
the include file is specified to be in @file{gcc/config/@var{target}/BOGUS/filestuff}.
Specifying an absolute path for the include file such as;
@smallexample
(include "/u2/BOGUS/filestuff")
@end smallexample
is permitted but is not encouraged.
@subsection RTL Generation Tool Options for Directory Search
@cindex directory options .md
@cindex options, directory search
@cindex search options
The @option{-I@var{dir}} option specifies directories to search for machine descriptions.
For example:
@smallexample
genrecog -I/p1/abc/proc1 -I/p2/abcd/pro2 target.md
@end smallexample
Add the directory @var{dir} to the head of the list of directories to be
searched for header files. This can be used to override a system machine definition
file, substituting your own version, since these directories are
searched before the default machine description file directories. If you use more than
one @option{-I} option, the directories are scanned in left-to-right
order; the standard default directory come after.
@end ifset
@ifset INTERNALS
@node Peephole Definitions
@section Machine-Specific Peephole Optimizers
@cindex peephole optimizer definitions
@cindex defining peephole optimizers
In addition to instruction patterns the @file{md} file may contain
definitions of machine-specific peephole optimizations.
The combiner does not notice certain peephole optimizations when the data
flow in the program does not suggest that it should try them. For example,
sometimes two consecutive insns related in purpose can be combined even
though the second one does not appear to use a register computed in the
first one. A machine-specific peephole optimizer can detect such
opportunities.
There are two forms of peephole definitions that may be used. The
original @code{define_peephole} is run at assembly output time to
match insns and substitute assembly text. Use of @code{define_peephole}
is deprecated.
A newer @code{define_peephole2} matches insns and substitutes new
insns. The @code{peephole2} pass is run after register allocation
but before scheduling, which may result in much better code for
targets that do scheduling.
@menu
* define_peephole:: RTL to Text Peephole Optimizers
* define_peephole2:: RTL to RTL Peephole Optimizers
@end menu
@end ifset
@ifset INTERNALS
@node define_peephole
@subsection RTL to Text Peephole Optimizers
@findex define_peephole
@need 1000
A definition looks like this:
@smallexample
(define_peephole
[@var{insn-pattern-1}
@var{insn-pattern-2}
@dots{}]
"@var{condition}"
"@var{template}"
"@var{optional-insn-attributes}")
@end smallexample
@noindent
The last string operand may be omitted if you are not using any
machine-specific information in this machine description. If present,
it must obey the same rules as in a @code{define_insn}.
In this skeleton, @var{insn-pattern-1} and so on are patterns to match
consecutive insns. The optimization applies to a sequence of insns when
@var{insn-pattern-1} matches the first one, @var{insn-pattern-2} matches
the next, and so on.
Each of the insns matched by a peephole must also match a
@code{define_insn}. Peepholes are checked only at the last stage just
before code generation, and only optionally. Therefore, any insn which
would match a peephole but no @code{define_insn} will cause a crash in code
generation in an unoptimized compilation, or at various optimization
stages.
The operands of the insns are matched with @code{match_operands},
@code{match_operator}, and @code{match_dup}, as usual. What is not
usual is that the operand numbers apply to all the insn patterns in the
definition. So, you can check for identical operands in two insns by
using @code{match_operand} in one insn and @code{match_dup} in the
other.
The operand constraints used in @code{match_operand} patterns do not have
any direct effect on the applicability of the peephole, but they will
be validated afterward, so make sure your constraints are general enough
to apply whenever the peephole matches. If the peephole matches
but the constraints are not satisfied, the compiler will crash.
It is safe to omit constraints in all the operands of the peephole; or
you can write constraints which serve as a double-check on the criteria
previously tested.
Once a sequence of insns matches the patterns, the @var{condition} is
checked. This is a C expression which makes the final decision whether to
perform the optimization (we do so if the expression is nonzero). If
@var{condition} is omitted (in other words, the string is empty) then the
optimization is applied to every sequence of insns that matches the
patterns.
The defined peephole optimizations are applied after register allocation
is complete. Therefore, the peephole definition can check which
operands have ended up in which kinds of registers, just by looking at
the operands.
@findex prev_active_insn
The way to refer to the operands in @var{condition} is to write
@code{operands[@var{i}]} for operand number @var{i} (as matched by
@code{(match_operand @var{i} @dots{})}). Use the variable @code{insn}
to refer to the last of the insns being matched; use
@code{prev_active_insn} to find the preceding insns.
@findex dead_or_set_p
When optimizing computations with intermediate results, you can use
@var{condition} to match only when the intermediate results are not used
elsewhere. Use the C expression @code{dead_or_set_p (@var{insn},
@var{op})}, where @var{insn} is the insn in which you expect the value
to be used for the last time (from the value of @code{insn}, together
with use of @code{prev_nonnote_insn}), and @var{op} is the intermediate
value (from @code{operands[@var{i}]}).
Applying the optimization means replacing the sequence of insns with one
new insn. The @var{template} controls ultimate output of assembler code
for this combined insn. It works exactly like the template of a
@code{define_insn}. Operand numbers in this template are the same ones
used in matching the original sequence of insns.
The result of a defined peephole optimizer does not need to match any of
the insn patterns in the machine description; it does not even have an
opportunity to match them. The peephole optimizer definition itself serves
as the insn pattern to control how the insn is output.
Defined peephole optimizers are run as assembler code is being output,
so the insns they produce are never combined or rearranged in any way.
Here is an example, taken from the 68000 machine description:
@smallexample
(define_peephole
[(set (reg:SI 15) (plus:SI (reg:SI 15) (const_int 4)))
(set (match_operand:DF 0 "register_operand" "=f")
(match_operand:DF 1 "register_operand" "ad"))]
"FP_REG_P (operands[0]) && ! FP_REG_P (operands[1])"
@{
rtx xoperands[2];
xoperands[1] = gen_rtx_REG (SImode, REGNO (operands[1]) + 1);
#ifdef MOTOROLA
output_asm_insn ("move.l %1,(sp)", xoperands);
output_asm_insn ("move.l %1,-(sp)", operands);
return "fmove.d (sp)+,%0";
#else
output_asm_insn ("movel %1,sp@@", xoperands);
output_asm_insn ("movel %1,sp@@-", operands);
return "fmoved sp@@+,%0";
#endif
@})
@end smallexample
@need 1000
The effect of this optimization is to change
@smallexample
@group
jbsr _foobar
addql #4,sp
movel d1,sp@@-
movel d0,sp@@-
fmoved sp@@+,fp0
@end group
@end smallexample
@noindent
into
@smallexample
@group
jbsr _foobar
movel d1,sp@@
movel d0,sp@@-
fmoved sp@@+,fp0
@end group
@end smallexample
@ignore
@findex CC_REVERSED
If a peephole matches a sequence including one or more jump insns, you must
take account of the flags such as @code{CC_REVERSED} which specify that the
condition codes are represented in an unusual manner. The compiler
automatically alters any ordinary conditional jumps which occur in such
situations, but the compiler cannot alter jumps which have been replaced by
peephole optimizations. So it is up to you to alter the assembler code
that the peephole produces. Supply C code to write the assembler output,
and in this C code check the condition code status flags and change the
assembler code as appropriate.
@end ignore
@var{insn-pattern-1} and so on look @emph{almost} like the second
operand of @code{define_insn}. There is one important difference: the
second operand of @code{define_insn} consists of one or more RTX's
enclosed in square brackets. Usually, there is only one: then the same
action can be written as an element of a @code{define_peephole}. But
when there are multiple actions in a @code{define_insn}, they are
implicitly enclosed in a @code{parallel}. Then you must explicitly
write the @code{parallel}, and the square brackets within it, in the
@code{define_peephole}. Thus, if an insn pattern looks like this,
@smallexample
(define_insn "divmodsi4"
[(set (match_operand:SI 0 "general_operand" "=d")
(div:SI (match_operand:SI 1 "general_operand" "0")
(match_operand:SI 2 "general_operand" "dmsK")))
(set (match_operand:SI 3 "general_operand" "=d")
(mod:SI (match_dup 1) (match_dup 2)))]
"TARGET_68020"
"divsl%.l %2,%3:%0")
@end smallexample
@noindent
then the way to mention this insn in a peephole is as follows:
@smallexample
(define_peephole
[@dots{}
(parallel
[(set (match_operand:SI 0 "general_operand" "=d")
(div:SI (match_operand:SI 1 "general_operand" "0")
(match_operand:SI 2 "general_operand" "dmsK")))
(set (match_operand:SI 3 "general_operand" "=d")
(mod:SI (match_dup 1) (match_dup 2)))])
@dots{}]
@dots{})
@end smallexample
@end ifset
@ifset INTERNALS
@node define_peephole2
@subsection RTL to RTL Peephole Optimizers
@findex define_peephole2
The @code{define_peephole2} definition tells the compiler how to
substitute one sequence of instructions for another sequence,
what additional scratch registers may be needed and what their
lifetimes must be.
@smallexample
(define_peephole2
[@var{insn-pattern-1}
@var{insn-pattern-2}
@dots{}]
"@var{condition}"
[@var{new-insn-pattern-1}
@var{new-insn-pattern-2}
@dots{}]
"@var{preparation-statements}")
@end smallexample
The definition is almost identical to @code{define_split}
(@pxref{Insn Splitting}) except that the pattern to match is not a
single instruction, but a sequence of instructions.
It is possible to request additional scratch registers for use in the
output template. If appropriate registers are not free, the pattern
will simply not match.
@findex match_scratch
@findex match_dup
Scratch registers are requested with a @code{match_scratch} pattern at
the top level of the input pattern. The allocated register (initially) will
be dead at the point requested within the original sequence. If the scratch
is used at more than a single point, a @code{match_dup} pattern at the
top level of the input pattern marks the last position in the input sequence
at which the register must be available.
Here is an example from the IA-32 machine description:
@smallexample
(define_peephole2
[(match_scratch:SI 2 "r")
(parallel [(set (match_operand:SI 0 "register_operand" "")
(match_operator:SI 3 "arith_or_logical_operator"
[(match_dup 0)
(match_operand:SI 1 "memory_operand" "")]))
(clobber (reg:CC 17))])]
"! optimize_size && ! TARGET_READ_MODIFY"
[(set (match_dup 2) (match_dup 1))
(parallel [(set (match_dup 0)
(match_op_dup 3 [(match_dup 0) (match_dup 2)]))
(clobber (reg:CC 17))])]
"")
@end smallexample
@noindent
This pattern tries to split a load from its use in the hopes that we'll be
able to schedule around the memory load latency. It allocates a single
@code{SImode} register of class @code{GENERAL_REGS} (@code{"r"}) that needs
to be live only at the point just before the arithmetic.
A real example requiring extended scratch lifetimes is harder to come by,
so here's a silly made-up example:
@smallexample
(define_peephole2
[(match_scratch:SI 4 "r")
(set (match_operand:SI 0 "" "") (match_operand:SI 1 "" ""))
(set (match_operand:SI 2 "" "") (match_dup 1))
(match_dup 4)
(set (match_operand:SI 3 "" "") (match_dup 1))]
"/* @r{determine 1 does not overlap 0 and 2} */"
[(set (match_dup 4) (match_dup 1))
(set (match_dup 0) (match_dup 4))
(set (match_dup 2) (match_dup 4))
(set (match_dup 3) (match_dup 4))]
"")
@end smallexample
@noindent
If we had not added the @code{(match_dup 4)} in the middle of the input
sequence, it might have been the case that the register we chose at the
beginning of the sequence is killed by the first or second @code{set}.
There are two special macros defined for use in the preparation statements:
@code{DONE} and @code{FAIL}. Use them with a following semicolon,
as a statement.
@table @code
@findex DONE
@item DONE
Use the @code{DONE} macro to end RTL generation for the peephole. The
only RTL insns generated as replacement for the matched input insn will
be those already emitted by explicit calls to @code{emit_insn} within
the preparation statements; the replacement pattern is not used.
@findex FAIL
@item FAIL
Make the @code{define_peephole2} fail on this occasion. When a @code{define_peephole2}
fails, it means that the replacement was not truly available for the
particular inputs it was given. In that case, GCC may still apply a
later @code{define_peephole2} that also matches the given insn pattern.
(Note that this is different from @code{define_split}, where @code{FAIL}
prevents the input insn from being split at all.)
@end table
If the preparation falls through (invokes neither @code{DONE} nor
@code{FAIL}), then the @code{define_peephole2} uses the replacement
template.
Insns are scanned in forward order from beginning to end for each basic
block. Matches are attempted in order of @code{define_peephole2}
appearance in the @file{md} file. After a successful replacement,
scanning for further opportunities for @code{define_peephole2}, resumes
with the first generated replacement insn as the first insn to be
matched against all @code{define_peephole2}. For the example above,
after its successful replacement, the first insn that can be matched by
a @code{define_peephole2} is @code{(set (match_dup 4) (match_dup 1))}.
@end ifset
@ifset INTERNALS
@node Insn Attributes
@section Instruction Attributes
@cindex insn attributes
@cindex instruction attributes
In addition to describing the instruction supported by the target machine,
the @file{md} file also defines a group of @dfn{attributes} and a set of
values for each. Every generated insn is assigned a value for each attribute.
One possible attribute would be the effect that the insn has on the machine's
condition code.
@menu
* Defining Attributes:: Specifying attributes and their values.
* Expressions:: Valid expressions for attribute values.
* Tagging Insns:: Assigning attribute values to insns.
* Attr Example:: An example of assigning attributes.
* Insn Lengths:: Computing the length of insns.
* Constant Attributes:: Defining attributes that are constant.
* Mnemonic Attribute:: Obtain the instruction mnemonic as attribute value.
* Delay Slots:: Defining delay slots required for a machine.
* Processor pipeline description:: Specifying information for insn scheduling.
@end menu
@end ifset
@ifset INTERNALS
@node Defining Attributes
@subsection Defining Attributes and their Values
@cindex defining attributes and their values
@cindex attributes, defining
@findex define_attr
The @code{define_attr} expression is used to define each attribute required
by the target machine. It looks like:
@smallexample
(define_attr @var{name} @var{list-of-values} @var{default})
@end smallexample
@var{name} is a string specifying the name of the attribute being
defined. Some attributes are used in a special way by the rest of the
compiler. The @code{enabled} attribute can be used to conditionally
enable or disable insn alternatives (@pxref{Disable Insn
Alternatives}). The @code{predicable} attribute, together with a
suitable @code{define_cond_exec} (@pxref{Conditional Execution}), can
be used to automatically generate conditional variants of instruction
patterns. The @code{mnemonic} attribute can be used to check for the
instruction mnemonic (@pxref{Mnemonic Attribute}). The compiler
internally uses the names @code{ce_enabled} and @code{nonce_enabled},
so they should not be used elsewhere as alternative names.
@var{list-of-values} is either a string that specifies a comma-separated
list of values that can be assigned to the attribute, or a null string to
indicate that the attribute takes numeric values.
@var{default} is an attribute expression that gives the value of this
attribute for insns that match patterns whose definition does not include
an explicit value for this attribute. @xref{Attr Example}, for more
information on the handling of defaults. @xref{Constant Attributes},
for information on attributes that do not depend on any particular insn.
@findex insn-attr.h
For each defined attribute, a number of definitions are written to the
@file{insn-attr.h} file. For cases where an explicit set of values is
specified for an attribute, the following are defined:
@itemize @bullet
@item
A @samp{#define} is written for the symbol @samp{HAVE_ATTR_@var{name}}.
@item
An enumerated class is defined for @samp{attr_@var{name}} with
elements of the form @samp{@var{upper-name}_@var{upper-value}} where
the attribute name and value are first converted to uppercase.
@item
A function @samp{get_attr_@var{name}} is defined that is passed an insn and
returns the attribute value for that insn.
@end itemize
For example, if the following is present in the @file{md} file:
@smallexample
(define_attr "type" "branch,fp,load,store,arith" @dots{})
@end smallexample
@noindent
the following lines will be written to the file @file{insn-attr.h}.
@smallexample
#define HAVE_ATTR_type 1
enum attr_type @{TYPE_BRANCH, TYPE_FP, TYPE_LOAD,
TYPE_STORE, TYPE_ARITH@};
extern enum attr_type get_attr_type ();
@end smallexample
If the attribute takes numeric values, no @code{enum} type will be
defined and the function to obtain the attribute's value will return
@code{int}.
There are attributes which are tied to a specific meaning. These
attributes are not free to use for other purposes:
@table @code
@item length
The @code{length} attribute is used to calculate the length of emitted
code chunks. This is especially important when verifying branch
distances. @xref{Insn Lengths}.
@item enabled
The @code{enabled} attribute can be defined to prevent certain
alternatives of an insn definition from being used during code
generation. @xref{Disable Insn Alternatives}.
@item mnemonic
The @code{mnemonic} attribute can be defined to implement instruction
specific checks in e.g.@: the pipeline description.
@xref{Mnemonic Attribute}.
@end table
For each of these special attributes, the corresponding
@samp{HAVE_ATTR_@var{name}} @samp{#define} is also written when the
attribute is not defined; in that case, it is defined as @samp{0}.
@findex define_enum_attr
@anchor{define_enum_attr}
Another way of defining an attribute is to use:
@smallexample
(define_enum_attr "@var{attr}" "@var{enum}" @var{default})
@end smallexample
This works in just the same way as @code{define_attr}, except that
the list of values is taken from a separate enumeration called
@var{enum} (@pxref{define_enum}). This form allows you to use
the same list of values for several attributes without having to
repeat the list each time. For example:
@smallexample
(define_enum "processor" [
model_a
model_b
@dots{}
])
(define_enum_attr "arch" "processor"
(const (symbol_ref "target_arch")))
(define_enum_attr "tune" "processor"
(const (symbol_ref "target_tune")))
@end smallexample
defines the same attributes as:
@smallexample
(define_attr "arch" "model_a,model_b,@dots{}"
(const (symbol_ref "target_arch")))
(define_attr "tune" "model_a,model_b,@dots{}"
(const (symbol_ref "target_tune")))
@end smallexample
but without duplicating the processor list. The second example defines two
separate C enums (@code{attr_arch} and @code{attr_tune}) whereas the first
defines a single C enum (@code{processor}).
@end ifset
@ifset INTERNALS
@node Expressions
@subsection Attribute Expressions
@cindex attribute expressions
RTL expressions used to define attributes use the codes described above
plus a few specific to attribute definitions, to be discussed below.
Attribute value expressions must have one of the following forms:
@table @code
@cindex @code{const_int} and attributes
@item (const_int @var{i})
The integer @var{i} specifies the value of a numeric attribute. @var{i}
must be non-negative.
The value of a numeric attribute can be specified either with a
@code{const_int}, or as an integer represented as a string in
@code{const_string}, @code{eq_attr} (see below), @code{attr},
@code{symbol_ref}, simple arithmetic expressions, and @code{set_attr}
overrides on specific instructions (@pxref{Tagging Insns}).
@cindex @code{const_string} and attributes
@item (const_string @var{value})
The string @var{value} specifies a constant attribute value.
If @var{value} is specified as @samp{"*"}, it means that the default value of
the attribute is to be used for the insn containing this expression.
@samp{"*"} obviously cannot be used in the @var{default} expression
of a @code{define_attr}.
If the attribute whose value is being specified is numeric, @var{value}
must be a string containing a non-negative integer (normally
@code{const_int} would be used in this case). Otherwise, it must
contain one of the valid values for the attribute.
@cindex @code{if_then_else} and attributes
@item (if_then_else @var{test} @var{true-value} @var{false-value})
@var{test} specifies an attribute test, whose format is defined below.
The value of this expression is @var{true-value} if @var{test} is true,
otherwise it is @var{false-value}.
@cindex @code{cond} and attributes
@item (cond [@var{test1} @var{value1} @dots{}] @var{default})
The first operand of this expression is a vector containing an even
number of expressions and consisting of pairs of @var{test} and @var{value}
expressions. The value of the @code{cond} expression is that of the
@var{value} corresponding to the first true @var{test} expression. If
none of the @var{test} expressions are true, the value of the @code{cond}
expression is that of the @var{default} expression.
@end table
@var{test} expressions can have one of the following forms:
@table @code
@cindex @code{const_int} and attribute tests
@item (const_int @var{i})
This test is true if @var{i} is nonzero and false otherwise.
@cindex @code{not} and attributes
@cindex @code{ior} and attributes
@cindex @code{and} and attributes
@item (not @var{test})
@itemx (ior @var{test1} @var{test2})
@itemx (and @var{test1} @var{test2})
These tests are true if the indicated logical function is true.
@cindex @code{match_operand} and attributes
@item (match_operand:@var{m} @var{n} @var{pred} @var{constraints})
This test is true if operand @var{n} of the insn whose attribute value
is being determined has mode @var{m} (this part of the test is ignored
if @var{m} is @code{VOIDmode}) and the function specified by the string
@var{pred} returns a nonzero value when passed operand @var{n} and mode
@var{m} (this part of the test is ignored if @var{pred} is the null
string).
The @var{constraints} operand is ignored and should be the null string.
@cindex @code{match_test} and attributes
@item (match_test @var{c-expr})
The test is true if C expression @var{c-expr} is true. In non-constant
attributes, @var{c-expr} has access to the following variables:
@table @var
@item insn
The rtl instruction under test.
@item which_alternative
The @code{define_insn} alternative that @var{insn} matches.
@xref{Output Statement}.
@item operands
An array of @var{insn}'s rtl operands.
@end table
@var{c-expr} behaves like the condition in a C @code{if} statement,
so there is no need to explicitly convert the expression into a boolean
0 or 1 value. For example, the following two tests are equivalent:
@smallexample
(match_test "x & 2")
(match_test "(x & 2) != 0")
@end smallexample
@cindex @code{le} and attributes
@cindex @code{leu} and attributes
@cindex @code{lt} and attributes
@cindex @code{gt} and attributes
@cindex @code{gtu} and attributes
@cindex @code{ge} and attributes
@cindex @code{geu} and attributes
@cindex @code{ne} and attributes
@cindex @code{eq} and attributes
@cindex @code{plus} and attributes
@cindex @code{minus} and attributes
@cindex @code{mult} and attributes
@cindex @code{div} and attributes
@cindex @code{mod} and attributes
@cindex @code{abs} and attributes
@cindex @code{neg} and attributes
@cindex @code{ashift} and attributes
@cindex @code{lshiftrt} and attributes
@cindex @code{ashiftrt} and attributes
@item (le @var{arith1} @var{arith2})
@itemx (leu @var{arith1} @var{arith2})
@itemx (lt @var{arith1} @var{arith2})
@itemx (ltu @var{arith1} @var{arith2})
@itemx (gt @var{arith1} @var{arith2})
@itemx (gtu @var{arith1} @var{arith2})
@itemx (ge @var{arith1} @var{arith2})
@itemx (geu @var{arith1} @var{arith2})
@itemx (ne @var{arith1} @var{arith2})
@itemx (eq @var{arith1} @var{arith2})
These tests are true if the indicated comparison of the two arithmetic
expressions is true. Arithmetic expressions are formed with
@code{plus}, @code{minus}, @code{mult}, @code{div}, @code{mod},
@code{abs}, @code{neg}, @code{and}, @code{ior}, @code{xor}, @code{not},
@code{ashift}, @code{lshiftrt}, and @code{ashiftrt} expressions.
@findex get_attr
@code{const_int} and @code{symbol_ref} are always valid terms (@pxref{Insn
Lengths},for additional forms). @code{symbol_ref} is a string
denoting a C expression that yields an @code{int} when evaluated by the
@samp{get_attr_@dots{}} routine. It should normally be a global
variable.
@findex eq_attr
@item (eq_attr @var{name} @var{value})
@var{name} is a string specifying the name of an attribute.
@var{value} is a string that is either a valid value for attribute
@var{name}, a comma-separated list of values, or @samp{!} followed by a
value or list. If @var{value} does not begin with a @samp{!}, this
test is true if the value of the @var{name} attribute of the current
insn is in the list specified by @var{value}. If @var{value} begins
with a @samp{!}, this test is true if the attribute's value is
@emph{not} in the specified list.
For example,
@smallexample
(eq_attr "type" "load,store")
@end smallexample
@noindent
is equivalent to
@smallexample
(ior (eq_attr "type" "load") (eq_attr "type" "store"))
@end smallexample
If @var{name} specifies an attribute of @samp{alternative}, it refers to the
value of the compiler variable @code{which_alternative}
(@pxref{Output Statement}) and the values must be small integers. For
example,
@smallexample
(eq_attr "alternative" "2,3")
@end smallexample
@noindent
is equivalent to
@smallexample
(ior (eq (symbol_ref "which_alternative") (const_int 2))
(eq (symbol_ref "which_alternative") (const_int 3)))
@end smallexample
Note that, for most attributes, an @code{eq_attr} test is simplified in cases
where the value of the attribute being tested is known for all insns matching
a particular pattern. This is by far the most common case.
@findex attr_flag
@item (attr_flag @var{name})
The value of an @code{attr_flag} expression is true if the flag
specified by @var{name} is true for the @code{insn} currently being
scheduled.
@var{name} is a string specifying one of a fixed set of flags to test.
Test the flags @code{forward} and @code{backward} to determine the
direction of a conditional branch.
This example describes a conditional branch delay slot which
can be nullified for forward branches that are taken (annul-true) or
for backward branches which are not taken (annul-false).
@smallexample
(define_delay (eq_attr "type" "cbranch")
[(eq_attr "in_branch_delay" "true")
(and (eq_attr "in_branch_delay" "true")
(attr_flag "forward"))
(and (eq_attr "in_branch_delay" "true")
(attr_flag "backward"))])
@end smallexample
The @code{forward} and @code{backward} flags are false if the current
@code{insn} being scheduled is not a conditional branch.
@code{attr_flag} is only used during delay slot scheduling and has no
meaning to other passes of the compiler.
@findex attr
@item (attr @var{name})
The value of another attribute is returned. This is most useful
for numeric attributes, as @code{eq_attr} and @code{attr_flag}
produce more efficient code for non-numeric attributes.
@end table
@end ifset
@ifset INTERNALS
@node Tagging Insns
@subsection Assigning Attribute Values to Insns
@cindex tagging insns
@cindex assigning attribute values to insns
The value assigned to an attribute of an insn is primarily determined by
which pattern is matched by that insn (or which @code{define_peephole}
generated it). Every @code{define_insn} and @code{define_peephole} can
have an optional last argument to specify the values of attributes for
matching insns. The value of any attribute not specified in a particular
insn is set to the default value for that attribute, as specified in its
@code{define_attr}. Extensive use of default values for attributes
permits the specification of the values for only one or two attributes
in the definition of most insn patterns, as seen in the example in the
next section.
The optional last argument of @code{define_insn} and
@code{define_peephole} is a vector of expressions, each of which defines
the value for a single attribute. The most general way of assigning an
attribute's value is to use a @code{set} expression whose first operand is an
@code{attr} expression giving the name of the attribute being set. The
second operand of the @code{set} is an attribute expression
(@pxref{Expressions}) giving the value of the attribute.
When the attribute value depends on the @samp{alternative} attribute
(i.e., which is the applicable alternative in the constraint of the
insn), the @code{set_attr_alternative} expression can be used. It
allows the specification of a vector of attribute expressions, one for
each alternative.
@findex set_attr
When the generality of arbitrary attribute expressions is not required,
the simpler @code{set_attr} expression can be used, which allows
specifying a string giving either a single attribute value or a list
of attribute values, one for each alternative.
The form of each of the above specifications is shown below. In each case,
@var{name} is a string specifying the attribute to be set.
@table @code
@item (set_attr @var{name} @var{value-string})
@var{value-string} is either a string giving the desired attribute value,
or a string containing a comma-separated list giving the values for
succeeding alternatives. The number of elements must match the number
of alternatives in the constraint of the insn pattern.
Note that it may be useful to specify @samp{*} for some alternative, in
which case the attribute will assume its default value for insns matching
that alternative.
@findex set_attr_alternative
@item (set_attr_alternative @var{name} [@var{value1} @var{value2} @dots{}])
Depending on the alternative of the insn, the value will be one of the
specified values. This is a shorthand for using a @code{cond} with
tests on the @samp{alternative} attribute.
@findex attr
@item (set (attr @var{name}) @var{value})
The first operand of this @code{set} must be the special RTL expression
@code{attr}, whose sole operand is a string giving the name of the
attribute being set. @var{value} is the value of the attribute.
@end table
The following shows three different ways of representing the same
attribute value specification:
@smallexample
(set_attr "type" "load,store,arith")
(set_attr_alternative "type"
[(const_string "load") (const_string "store")
(const_string "arith")])
(set (attr "type")
(cond [(eq_attr "alternative" "1") (const_string "load")
(eq_attr "alternative" "2") (const_string "store")]
(const_string "arith")))
@end smallexample
@need 1000
@findex define_asm_attributes
The @code{define_asm_attributes} expression provides a mechanism to
specify the attributes assigned to insns produced from an @code{asm}
statement. It has the form:
@smallexample
(define_asm_attributes [@var{attr-sets}])
@end smallexample
@noindent
where @var{attr-sets} is specified the same as for both the
@code{define_insn} and the @code{define_peephole} expressions.
These values will typically be the ``worst case'' attribute values. For
example, they might indicate that the condition code will be clobbered.
A specification for a @code{length} attribute is handled specially. The
way to compute the length of an @code{asm} insn is to multiply the
length specified in the expression @code{define_asm_attributes} by the
number of machine instructions specified in the @code{asm} statement,
determined by counting the number of semicolons and newlines in the
string. Therefore, the value of the @code{length} attribute specified
in a @code{define_asm_attributes} should be the maximum possible length
of a single machine instruction.
@end ifset
@ifset INTERNALS
@node Attr Example
@subsection Example of Attribute Specifications
@cindex attribute specifications example
@cindex attribute specifications
The judicious use of defaulting is important in the efficient use of
insn attributes. Typically, insns are divided into @dfn{types} and an
attribute, customarily called @code{type}, is used to represent this
value. This attribute is normally used only to define the default value
for other attributes. An example will clarify this usage.
Assume we have a RISC machine with a condition code and in which only
full-word operations are performed in registers. Let us assume that we
can divide all insns into loads, stores, (integer) arithmetic
operations, floating point operations, and branches.
Here we will concern ourselves with determining the effect of an insn on
the condition code and will limit ourselves to the following possible
effects: The condition code can be set unpredictably (clobbered), not
be changed, be set to agree with the results of the operation, or only
changed if the item previously set into the condition code has been
modified.
Here is part of a sample @file{md} file for such a machine:
@smallexample
(define_attr "type" "load,store,arith,fp,branch" (const_string "arith"))
(define_attr "cc" "clobber,unchanged,set,change0"
(cond [(eq_attr "type" "load")
(const_string "change0")
(eq_attr "type" "store,branch")
(const_string "unchanged")
(eq_attr "type" "arith")
(if_then_else (match_operand:SI 0 "" "")
(const_string "set")
(const_string "clobber"))]
(const_string "clobber")))
(define_insn ""
[(set (match_operand:SI 0 "general_operand" "=r,r,m")
(match_operand:SI 1 "general_operand" "r,m,r"))]
""
"@@
move %0,%1
load %0,%1
store %0,%1"
[(set_attr "type" "arith,load,store")])
@end smallexample
Note that we assume in the above example that arithmetic operations
performed on quantities smaller than a machine word clobber the condition
code since they will set the condition code to a value corresponding to the
full-word result.
@end ifset
@ifset INTERNALS
@node Insn Lengths
@subsection Computing the Length of an Insn
@cindex insn lengths, computing
@cindex computing the length of an insn
For many machines, multiple types of branch instructions are provided, each
for different length branch displacements. In most cases, the assembler
will choose the correct instruction to use. However, when the assembler
cannot do so, GCC can when a special attribute, the @code{length}
attribute, is defined. This attribute must be defined to have numeric
values by specifying a null string in its @code{define_attr}.
In the case of the @code{length} attribute, two additional forms of
arithmetic terms are allowed in test expressions:
@table @code
@cindex @code{match_dup} and attributes
@item (match_dup @var{n})
This refers to the address of operand @var{n} of the current insn, which
must be a @code{label_ref}.
@cindex @code{pc} and attributes
@item (pc)
For non-branch instructions and backward branch instructions, this refers
to the address of the current insn. But for forward branch instructions,
this refers to the address of the next insn, because the length of the
current insn is to be computed.
@end table
@cindex @code{addr_vec}, length of
@cindex @code{addr_diff_vec}, length of
For normal insns, the length will be determined by value of the
@code{length} attribute. In the case of @code{addr_vec} and
@code{addr_diff_vec} insn patterns, the length is computed as
the number of vectors multiplied by the size of each vector.
Lengths are measured in addressable storage units (bytes).
Note that it is possible to call functions via the @code{symbol_ref}
mechanism to compute the length of an insn. However, if you use this
mechanism you must provide dummy clauses to express the maximum length
without using the function call. You can see an example of this in the
@code{pa} machine description for the @code{call_symref} pattern.
The following macros can be used to refine the length computation:
@table @code
@findex ADJUST_INSN_LENGTH
@item ADJUST_INSN_LENGTH (@var{insn}, @var{length})
If defined, modifies the length assigned to instruction @var{insn} as a
function of the context in which it is used. @var{length} is an lvalue
that contains the initially computed length of the insn and should be
updated with the correct length of the insn.
This macro will normally not be required. A case in which it is
required is the ROMP@. On this machine, the size of an @code{addr_vec}
insn must be increased by two to compensate for the fact that alignment
may be required.
@end table
@findex get_attr_length
The routine that returns @code{get_attr_length} (the value of the
@code{length} attribute) can be used by the output routine to
determine the form of the branch instruction to be written, as the
example below illustrates.
As an example of the specification of variable-length branches, consider
the IBM 360. If we adopt the convention that a register will be set to
the starting address of a function, we can jump to labels within 4k of
the start using a four-byte instruction. Otherwise, we need a six-byte
sequence to load the address from memory and then branch to it.
On such a machine, a pattern for a branch instruction might be specified
as follows:
@smallexample
(define_insn "jump"
[(set (pc)
(label_ref (match_operand 0 "" "")))]
""
@{
return (get_attr_length (insn) == 4
? "b %l0" : "l r15,=a(%l0); br r15");
@}
[(set (attr "length")
(if_then_else (lt (match_dup 0) (const_int 4096))
(const_int 4)
(const_int 6)))])
@end smallexample
@end ifset
@ifset INTERNALS
@node Constant Attributes
@subsection Constant Attributes
@cindex constant attributes
A special form of @code{define_attr}, where the expression for the
default value is a @code{const} expression, indicates an attribute that
is constant for a given run of the compiler. Constant attributes may be
used to specify which variety of processor is used. For example,
@smallexample
(define_attr "cpu" "m88100,m88110,m88000"
(const
(cond [(symbol_ref "TARGET_88100") (const_string "m88100")
(symbol_ref "TARGET_88110") (const_string "m88110")]
(const_string "m88000"))))
(define_attr "memory" "fast,slow"
(const
(if_then_else (symbol_ref "TARGET_FAST_MEM")
(const_string "fast")
(const_string "slow"))))
@end smallexample
The routine generated for constant attributes has no parameters as it
does not depend on any particular insn. RTL expressions used to define
the value of a constant attribute may use the @code{symbol_ref} form,
but may not use either the @code{match_operand} form or @code{eq_attr}
forms involving insn attributes.
@end ifset
@ifset INTERNALS
@node Mnemonic Attribute
@subsection Mnemonic Attribute
@cindex mnemonic attribute
The @code{mnemonic} attribute is a string type attribute holding the
instruction mnemonic for an insn alternative. The attribute values
will automatically be generated by the machine description parser if
there is an attribute definition in the md file:
@smallexample
(define_attr "mnemonic" "unknown" (const_string "unknown"))
@end smallexample
The default value can be freely chosen as long as it does not collide
with any of the instruction mnemonics. This value will be used
whenever the machine description parser is not able to determine the
mnemonic string. This might be the case for output templates
containing more than a single instruction as in
@code{"mvcle\t%0,%1,0\;jo\t.-4"}.
The @code{mnemonic} attribute set is not generated automatically if the
instruction string is generated via C code.
An existing @code{mnemonic} attribute set in an insn definition will not
be overriden by the md file parser. That way it is possible to
manually set the instruction mnemonics for the cases where the md file
parser fails to determine it automatically.
The @code{mnemonic} attribute is useful for dealing with instruction
specific properties in the pipeline description without defining
additional insn attributes.
@smallexample
(define_attr "ooo_expanded" ""
(cond [(eq_attr "mnemonic" "dlr,dsgr,d,dsgf,stam,dsgfr,dlgr")
(const_int 1)]
(const_int 0)))
@end smallexample
@end ifset
@ifset INTERNALS
@node Delay Slots
@subsection Delay Slot Scheduling
@cindex delay slots, defining
The insn attribute mechanism can be used to specify the requirements for
delay slots, if any, on a target machine. An instruction is said to
require a @dfn{delay slot} if some instructions that are physically
after the instruction are executed as if they were located before it.
Classic examples are branch and call instructions, which often execute
the following instruction before the branch or call is performed.
On some machines, conditional branch instructions can optionally
@dfn{annul} instructions in the delay slot. This means that the
instruction will not be executed for certain branch outcomes. Both
instructions that annul if the branch is true and instructions that
annul if the branch is false are supported.
Delay slot scheduling differs from instruction scheduling in that
determining whether an instruction needs a delay slot is dependent only
on the type of instruction being generated, not on data flow between the
instructions. See the next section for a discussion of data-dependent
instruction scheduling.
@findex define_delay
The requirement of an insn needing one or more delay slots is indicated
via the @code{define_delay} expression. It has the following form:
@smallexample
(define_delay @var{test}
[@var{delay-1} @var{annul-true-1} @var{annul-false-1}
@var{delay-2} @var{annul-true-2} @var{annul-false-2}
@dots{}])
@end smallexample
@var{test} is an attribute test that indicates whether this
@code{define_delay} applies to a particular insn. If so, the number of
required delay slots is determined by the length of the vector specified
as the second argument. An insn placed in delay slot @var{n} must
satisfy attribute test @var{delay-n}. @var{annul-true-n} is an
attribute test that specifies which insns may be annulled if the branch
is true. Similarly, @var{annul-false-n} specifies which insns in the
delay slot may be annulled if the branch is false. If annulling is not
supported for that delay slot, @code{(nil)} should be coded.
For example, in the common case where branch and call insns require
a single delay slot, which may contain any insn other than a branch or
call, the following would be placed in the @file{md} file:
@smallexample
(define_delay (eq_attr "type" "branch,call")
[(eq_attr "type" "!branch,call") (nil) (nil)])
@end smallexample
Multiple @code{define_delay} expressions may be specified. In this
case, each such expression specifies different delay slot requirements
and there must be no insn for which tests in two @code{define_delay}
expressions are both true.
For example, if we have a machine that requires one delay slot for branches
but two for calls, no delay slot can contain a branch or call insn,
and any valid insn in the delay slot for the branch can be annulled if the
branch is true, we might represent this as follows:
@smallexample
(define_delay (eq_attr "type" "branch")
[(eq_attr "type" "!branch,call")
(eq_attr "type" "!branch,call")
(nil)])
(define_delay (eq_attr "type" "call")
[(eq_attr "type" "!branch,call") (nil) (nil)
(eq_attr "type" "!branch,call") (nil) (nil)])
@end smallexample
@c the above is *still* too long. --mew 4feb93
@end ifset
@ifset INTERNALS
@node Processor pipeline description
@subsection Specifying processor pipeline description
@cindex processor pipeline description
@cindex processor functional units
@cindex instruction latency time
@cindex interlock delays
@cindex data dependence delays
@cindex reservation delays
@cindex pipeline hazard recognizer
@cindex automaton based pipeline description
@cindex regular expressions
@cindex deterministic finite state automaton
@cindex automaton based scheduler
@cindex RISC
@cindex VLIW
To achieve better performance, most modern processors
(super-pipelined, superscalar @acronym{RISC}, and @acronym{VLIW}
processors) have many @dfn{functional units} on which several
instructions can be executed simultaneously. An instruction starts
execution if its issue conditions are satisfied. If not, the
instruction is stalled until its conditions are satisfied. Such
@dfn{interlock (pipeline) delay} causes interruption of the fetching
of successor instructions (or demands nop instructions, e.g.@: for some
MIPS processors).
There are two major kinds of interlock delays in modern processors.
The first one is a data dependence delay determining @dfn{instruction
latency time}. The instruction execution is not started until all
source data have been evaluated by prior instructions (there are more
complex cases when the instruction execution starts even when the data
are not available but will be ready in given time after the
instruction execution start). Taking the data dependence delays into
account is simple. The data dependence (true, output, and
anti-dependence) delay between two instructions is given by a
constant. In most cases this approach is adequate. The second kind
of interlock delays is a reservation delay. The reservation delay
means that two instructions under execution will be in need of shared
processors resources, i.e.@: buses, internal registers, and/or
functional units, which are reserved for some time. Taking this kind
of delay into account is complex especially for modern @acronym{RISC}
processors.
The task of exploiting more processor parallelism is solved by an
instruction scheduler. For a better solution to this problem, the
instruction scheduler has to have an adequate description of the
processor parallelism (or @dfn{pipeline description}). GCC
machine descriptions describe processor parallelism and functional
unit reservations for groups of instructions with the aid of
@dfn{regular expressions}.
The GCC instruction scheduler uses a @dfn{pipeline hazard recognizer} to
figure out the possibility of the instruction issue by the processor
on a given simulated processor cycle. The pipeline hazard recognizer is
automatically generated from the processor pipeline description. The
pipeline hazard recognizer generated from the machine description
is based on a deterministic finite state automaton (@acronym{DFA}):
the instruction issue is possible if there is a transition from one
automaton state to another one. This algorithm is very fast, and
furthermore, its speed is not dependent on processor
complexity@footnote{However, the size of the automaton depends on
processor complexity. To limit this effect, machine descriptions
can split orthogonal parts of the machine description among several
automata: but then, since each of these must be stepped independently,
this does cause a small decrease in the algorithm's performance.}.
@cindex automaton based pipeline description
The rest of this section describes the directives that constitute
an automaton-based processor pipeline description. The order of
these constructions within the machine description file is not
important.
@findex define_automaton
@cindex pipeline hazard recognizer
The following optional construction describes names of automata
generated and used for the pipeline hazards recognition. Sometimes
the generated finite state automaton used by the pipeline hazard
recognizer is large. If we use more than one automaton and bind functional
units to the automata, the total size of the automata is usually
less than the size of the single automaton. If there is no one such
construction, only one finite state automaton is generated.
@smallexample
(define_automaton @var{automata-names})
@end smallexample
@var{automata-names} is a string giving names of the automata. The
names are separated by commas. All the automata should have unique names.
The automaton name is used in the constructions @code{define_cpu_unit} and
@code{define_query_cpu_unit}.
@findex define_cpu_unit
@cindex processor functional units
Each processor functional unit used in the description of instruction
reservations should be described by the following construction.
@smallexample
(define_cpu_unit @var{unit-names} [@var{automaton-name}])
@end smallexample
@var{unit-names} is a string giving the names of the functional units
separated by commas. Don't use name @samp{nothing}, it is reserved
for other goals.
@var{automaton-name} is a string giving the name of the automaton with
which the unit is bound. The automaton should be described in
construction @code{define_automaton}. You should give
@dfn{automaton-name}, if there is a defined automaton.
The assignment of units to automata are constrained by the uses of the
units in insn reservations. The most important constraint is: if a
unit reservation is present on a particular cycle of an alternative
for an insn reservation, then some unit from the same automaton must
be present on the same cycle for the other alternatives of the insn
reservation. The rest of the constraints are mentioned in the
description of the subsequent constructions.
@findex define_query_cpu_unit
@cindex querying function unit reservations
The following construction describes CPU functional units analogously
to @code{define_cpu_unit}. The reservation of such units can be
queried for an automaton state. The instruction scheduler never
queries reservation of functional units for given automaton state. So
as a rule, you don't need this construction. This construction could
be used for future code generation goals (e.g.@: to generate
@acronym{VLIW} insn templates).
@smallexample
(define_query_cpu_unit @var{unit-names} [@var{automaton-name}])
@end smallexample
@var{unit-names} is a string giving names of the functional units
separated by commas.
@var{automaton-name} is a string giving the name of the automaton with
which the unit is bound.
@findex define_insn_reservation
@cindex instruction latency time
@cindex regular expressions
@cindex data bypass
The following construction is the major one to describe pipeline
characteristics of an instruction.
@smallexample
(define_insn_reservation @var{insn-name} @var{default_latency}
@var{condition} @var{regexp})
@end smallexample
@var{default_latency} is a number giving latency time of the
instruction. There is an important difference between the old
description and the automaton based pipeline description. The latency
time is used for all dependencies when we use the old description. In
the automaton based pipeline description, the given latency time is only
used for true dependencies. The cost of anti-dependencies is always
zero and the cost of output dependencies is the difference between
latency times of the producing and consuming insns (if the difference
is negative, the cost is considered to be zero). You can always
change the default costs for any description by using the target hook
@code{TARGET_SCHED_ADJUST_COST} (@pxref{Scheduling}).
@var{insn-name} is a string giving the internal name of the insn. The
internal names are used in constructions @code{define_bypass} and in
the automaton description file generated for debugging. The internal
name has nothing in common with the names in @code{define_insn}. It is a
good practice to use insn classes described in the processor manual.
@var{condition} defines what RTL insns are described by this
construction. You should remember that you will be in trouble if
@var{condition} for two or more different
@code{define_insn_reservation} constructions is TRUE for an insn. In
this case what reservation will be used for the insn is not defined.
Such cases are not checked during generation of the pipeline hazards
recognizer because in general recognizing that two conditions may have
the same value is quite difficult (especially if the conditions
contain @code{symbol_ref}). It is also not checked during the
pipeline hazard recognizer work because it would slow down the
recognizer considerably.
@var{regexp} is a string describing the reservation of the cpu's functional
units by the instruction. The reservations are described by a regular
expression according to the following syntax:
@smallexample
regexp = regexp "," oneof
| oneof
oneof = oneof "|" allof
| allof
allof = allof "+" repeat
| repeat
repeat = element "*" number
| element
element = cpu_function_unit_name
| reservation_name
| result_name
| "nothing"
| "(" regexp ")"
@end smallexample
@itemize @bullet
@item
@samp{,} is used for describing the start of the next cycle in
the reservation.
@item
@samp{|} is used for describing a reservation described by the first
regular expression @strong{or} a reservation described by the second
regular expression @strong{or} etc.
@item
@samp{+} is used for describing a reservation described by the first
regular expression @strong{and} a reservation described by the
second regular expression @strong{and} etc.
@item
@samp{*} is used for convenience and simply means a sequence in which
the regular expression are repeated @var{number} times with cycle
advancing (see @samp{,}).
@item
@samp{cpu_function_unit_name} denotes reservation of the named
functional unit.
@item
@samp{reservation_name} --- see description of construction
@samp{define_reservation}.
@item
@samp{nothing} denotes no unit reservations.
@end itemize
@findex define_reservation
Sometimes unit reservations for different insns contain common parts.
In such case, you can simplify the pipeline description by describing
the common part by the following construction
@smallexample
(define_reservation @var{reservation-name} @var{regexp})
@end smallexample
@var{reservation-name} is a string giving name of @var{regexp}.
Functional unit names and reservation names are in the same name
space. So the reservation names should be different from the
functional unit names and cannot be the reserved name @samp{nothing}.
@findex define_bypass
@cindex instruction latency time
@cindex data bypass
The following construction is used to describe exceptions in the
latency time for given instruction pair. This is so called bypasses.
@smallexample
(define_bypass @var{number} @var{out_insn_names} @var{in_insn_names}
[@var{guard}])
@end smallexample
@var{number} defines when the result generated by the instructions
given in string @var{out_insn_names} will be ready for the
instructions given in string @var{in_insn_names}. Each of these
strings is a comma-separated list of filename-style globs and
they refer to the names of @code{define_insn_reservation}s.
For example:
@smallexample
(define_bypass 1 "cpu1_load_*, cpu1_store_*" "cpu1_load_*")
@end smallexample
defines a bypass between instructions that start with
@samp{cpu1_load_} or @samp{cpu1_store_} and those that start with
@samp{cpu1_load_}.
@var{guard} is an optional string giving the name of a C function which
defines an additional guard for the bypass. The function will get the
two insns as parameters. If the function returns zero the bypass will
be ignored for this case. The additional guard is necessary to
recognize complicated bypasses, e.g.@: when the consumer is only an address
of insn @samp{store} (not a stored value).
If there are more one bypass with the same output and input insns, the
chosen bypass is the first bypass with a guard in description whose
guard function returns nonzero. If there is no such bypass, then
bypass without the guard function is chosen.
@findex exclusion_set
@findex presence_set
@findex final_presence_set
@findex absence_set
@findex final_absence_set
@cindex VLIW
@cindex RISC
The following five constructions are usually used to describe
@acronym{VLIW} processors, or more precisely, to describe a placement
of small instructions into @acronym{VLIW} instruction slots. They
can be used for @acronym{RISC} processors, too.
@smallexample
(exclusion_set @var{unit-names} @var{unit-names})
(presence_set @var{unit-names} @var{patterns})
(final_presence_set @var{unit-names} @var{patterns})
(absence_set @var{unit-names} @var{patterns})
(final_absence_set @var{unit-names} @var{patterns})
@end smallexample
@var{unit-names} is a string giving names of functional units
separated by commas.
@var{patterns} is a string giving patterns of functional units
separated by comma. Currently pattern is one unit or units
separated by white-spaces.
The first construction (@samp{exclusion_set}) means that each
functional unit in the first string cannot be reserved simultaneously
with a unit whose name is in the second string and vice versa. For
example, the construction is useful for describing processors
(e.g.@: some SPARC processors) with a fully pipelined floating point
functional unit which can execute simultaneously only single floating
point insns or only double floating point insns.
The second construction (@samp{presence_set}) means that each
functional unit in the first string cannot be reserved unless at
least one of pattern of units whose names are in the second string is
reserved. This is an asymmetric relation. For example, it is useful
for description that @acronym{VLIW} @samp{slot1} is reserved after
@samp{slot0} reservation. We could describe it by the following
construction
@smallexample
(presence_set "slot1" "slot0")
@end smallexample
Or @samp{slot1} is reserved only after @samp{slot0} and unit @samp{b0}
reservation. In this case we could write
@smallexample
(presence_set "slot1" "slot0 b0")
@end smallexample
The third construction (@samp{final_presence_set}) is analogous to
@samp{presence_set}. The difference between them is when checking is
done. When an instruction is issued in given automaton state
reflecting all current and planned unit reservations, the automaton
state is changed. The first state is a source state, the second one
is a result state. Checking for @samp{presence_set} is done on the
source state reservation, checking for @samp{final_presence_set} is
done on the result reservation. This construction is useful to
describe a reservation which is actually two subsequent reservations.
For example, if we use
@smallexample
(presence_set "slot1" "slot0")
@end smallexample
the following insn will be never issued (because @samp{slot1} requires
@samp{slot0} which is absent in the source state).
@smallexample
(define_reservation "insn_and_nop" "slot0 + slot1")
@end smallexample
but it can be issued if we use analogous @samp{final_presence_set}.
The forth construction (@samp{absence_set}) means that each functional
unit in the first string can be reserved only if each pattern of units
whose names are in the second string is not reserved. This is an
asymmetric relation (actually @samp{exclusion_set} is analogous to
this one but it is symmetric). For example it might be useful in a
@acronym{VLIW} description to say that @samp{slot0} cannot be reserved
after either @samp{slot1} or @samp{slot2} have been reserved. This
can be described as:
@smallexample
(absence_set "slot0" "slot1, slot2")
@end smallexample
Or @samp{slot2} cannot be reserved if @samp{slot0} and unit @samp{b0}
are reserved or @samp{slot1} and unit @samp{b1} are reserved. In
this case we could write
@smallexample
(absence_set "slot2" "slot0 b0, slot1 b1")
@end smallexample
All functional units mentioned in a set should belong to the same
automaton.
The last construction (@samp{final_absence_set}) is analogous to
@samp{absence_set} but checking is done on the result (state)
reservation. See comments for @samp{final_presence_set}.
@findex automata_option
@cindex deterministic finite state automaton
@cindex nondeterministic finite state automaton
@cindex finite state automaton minimization
You can control the generator of the pipeline hazard recognizer with
the following construction.
@smallexample
(automata_option @var{options})
@end smallexample
@var{options} is a string giving options which affect the generated
code. Currently there are the following options:
@itemize @bullet
@item
@dfn{no-minimization} makes no minimization of the automaton. This is
only worth to do when we are debugging the description and need to
look more accurately at reservations of states.
@item
@dfn{time} means printing time statistics about the generation of
automata.
@item
@dfn{stats} means printing statistics about the generated automata
such as the number of DFA states, NDFA states and arcs.
@item
@dfn{v} means a generation of the file describing the result automata.
The file has suffix @samp{.dfa} and can be used for the description
verification and debugging.
@item
@dfn{w} means a generation of warning instead of error for
non-critical errors.
@item
@dfn{no-comb-vect} prevents the automaton generator from generating
two data structures and comparing them for space efficiency. Using
a comb vector to represent transitions may be better, but it can be
very expensive to construct. This option is useful if the build
process spends an unacceptably long time in genautomata.
@item
@dfn{ndfa} makes nondeterministic finite state automata. This affects
the treatment of operator @samp{|} in the regular expressions. The
usual treatment of the operator is to try the first alternative and,
if the reservation is not possible, the second alternative. The
nondeterministic treatment means trying all alternatives, some of them
may be rejected by reservations in the subsequent insns.
@item
@dfn{collapse-ndfa} modifies the behavior of the generator when
producing an automaton. An additional state transition to collapse a
nondeterministic @acronym{NDFA} state to a deterministic @acronym{DFA}
state is generated. It can be triggered by passing @code{const0_rtx} to
state_transition. In such an automaton, cycle advance transitions are
available only for these collapsed states. This option is useful for
ports that want to use the @code{ndfa} option, but also want to use
@code{define_query_cpu_unit} to assign units to insns issued in a cycle.
@item
@dfn{progress} means output of a progress bar showing how many states
were generated so far for automaton being processed. This is useful
during debugging a @acronym{DFA} description. If you see too many
generated states, you could interrupt the generator of the pipeline
hazard recognizer and try to figure out a reason for generation of the
huge automaton.
@end itemize
As an example, consider a superscalar @acronym{RISC} machine which can
issue three insns (two integer insns and one floating point insn) on
the cycle but can finish only two insns. To describe this, we define
the following functional units.
@smallexample
(define_cpu_unit "i0_pipeline, i1_pipeline, f_pipeline")
(define_cpu_unit "port0, port1")
@end smallexample
All simple integer insns can be executed in any integer pipeline and
their result is ready in two cycles. The simple integer insns are
issued into the first pipeline unless it is reserved, otherwise they
are issued into the second pipeline. Integer division and
multiplication insns can be executed only in the second integer
pipeline and their results are ready correspondingly in 9 and 4
cycles. The integer division is not pipelined, i.e.@: the subsequent
integer division insn cannot be issued until the current division
insn finished. Floating point insns are fully pipelined and their
results are ready in 3 cycles. Where the result of a floating point
insn is used by an integer insn, an additional delay of one cycle is
incurred. To describe all of this we could specify
@smallexample
(define_cpu_unit "div")
(define_insn_reservation "simple" 2 (eq_attr "type" "int")
"(i0_pipeline | i1_pipeline), (port0 | port1)")
(define_insn_reservation "mult" 4 (eq_attr "type" "mult")
"i1_pipeline, nothing*2, (port0 | port1)")
(define_insn_reservation "div" 9 (eq_attr "type" "div")
"i1_pipeline, div*7, div + (port0 | port1)")
(define_insn_reservation "float" 3 (eq_attr "type" "float")
"f_pipeline, nothing, (port0 | port1))
(define_bypass 4 "float" "simple,mult,div")
@end smallexample
To simplify the description we could describe the following reservation
@smallexample
(define_reservation "finish" "port0|port1")
@end smallexample
and use it in all @code{define_insn_reservation} as in the following
construction
@smallexample
(define_insn_reservation "simple" 2 (eq_attr "type" "int")
"(i0_pipeline | i1_pipeline), finish")
@end smallexample
@end ifset
@ifset INTERNALS
@node Conditional Execution
@section Conditional Execution
@cindex conditional execution
@cindex predication
A number of architectures provide for some form of conditional
execution, or predication. The hallmark of this feature is the
ability to nullify most of the instructions in the instruction set.
When the instruction set is large and not entirely symmetric, it
can be quite tedious to describe these forms directly in the
@file{.md} file. An alternative is the @code{define_cond_exec} template.
@findex define_cond_exec
@smallexample
(define_cond_exec
[@var{predicate-pattern}]
"@var{condition}"
"@var{output-template}"
"@var{optional-insn-attribues}")
@end smallexample
@var{predicate-pattern} is the condition that must be true for the
insn to be executed at runtime and should match a relational operator.
One can use @code{match_operator} to match several relational operators
at once. Any @code{match_operand} operands must have no more than one
alternative.
@var{condition} is a C expression that must be true for the generated
pattern to match.
@findex current_insn_predicate
@var{output-template} is a string similar to the @code{define_insn}
output template (@pxref{Output Template}), except that the @samp{*}
and @samp{@@} special cases do not apply. This is only useful if the
assembly text for the predicate is a simple prefix to the main insn.
In order to handle the general case, there is a global variable
@code{current_insn_predicate} that will contain the entire predicate
if the current insn is predicated, and will otherwise be @code{NULL}.
@var{optional-insn-attributes} is an optional vector of attributes that gets
appended to the insn attributes of the produced cond_exec rtx. It can
be used to add some distinguishing attribute to cond_exec rtxs produced
that way. An example usage would be to use this attribute in conjunction
with attributes on the main pattern to disable particular alternatives under
certain conditions.
When @code{define_cond_exec} is used, an implicit reference to
the @code{predicable} instruction attribute is made.
@xref{Insn Attributes}. This attribute must be a boolean (i.e.@: have
exactly two elements in its @var{list-of-values}), with the possible
values being @code{no} and @code{yes}. The default and all uses in
the insns must be a simple constant, not a complex expressions. It
may, however, depend on the alternative, by using a comma-separated
list of values. If that is the case, the port should also define an
@code{enabled} attribute (@pxref{Disable Insn Alternatives}), which
should also allow only @code{no} and @code{yes} as its values.
For each @code{define_insn} for which the @code{predicable}
attribute is true, a new @code{define_insn} pattern will be
generated that matches a predicated version of the instruction.
For example,
@smallexample
(define_insn "addsi"
[(set (match_operand:SI 0 "register_operand" "r")
(plus:SI (match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r")))]
"@var{test1}"
"add %2,%1,%0")
(define_cond_exec
[(ne (match_operand:CC 0 "register_operand" "c")
(const_int 0))]
"@var{test2}"
"(%0)")
@end smallexample
@noindent
generates a new pattern
@smallexample
(define_insn ""
[(cond_exec
(ne (match_operand:CC 3 "register_operand" "c") (const_int 0))
(set (match_operand:SI 0 "register_operand" "r")
(plus:SI (match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r"))))]
"(@var{test2}) && (@var{test1})"
"(%3) add %2,%1,%0")
@end smallexample
@end ifset
@ifset INTERNALS
@node Define Subst
@section RTL Templates Transformations
@cindex define_subst
For some hardware architectures there are common cases when the RTL
templates for the instructions can be derived from the other RTL
templates using simple transformations. E.g., @file{i386.md} contains
an RTL template for the ordinary @code{sub} instruction---
@code{*subsi_1}, and for the @code{sub} instruction with subsequent
zero-extension---@code{*subsi_1_zext}. Such cases can be easily
implemented by a single meta-template capable of generating a modified
case based on the initial one:
@findex define_subst
@smallexample
(define_subst "@var{name}"
[@var{input-template}]
"@var{condition}"
[@var{output-template}])
@end smallexample
@var{input-template} is a pattern describing the source RTL template,
which will be transformed.
@var{condition} is a C expression that is conjunct with the condition
from the input-template to generate a condition to be used in the
output-template.
@var{output-template} is a pattern that will be used in the resulting
template.
@code{define_subst} mechanism is tightly coupled with the notion of the
subst attribute (@pxref{Subst Iterators}). The use of
@code{define_subst} is triggered by a reference to a subst attribute in
the transforming RTL template. This reference initiates duplication of
the source RTL template and substitution of the attributes with their
values. The source RTL template is left unchanged, while the copy is
transformed by @code{define_subst}. This transformation can fail in the
case when the source RTL template is not matched against the
input-template of the @code{define_subst}. In such case the copy is
deleted.
@code{define_subst} can be used only in @code{define_insn} and
@code{define_expand}, it cannot be used in other expressions (e.g.@: in
@code{define_insn_and_split}).
@menu
* Define Subst Example:: Example of @code{define_subst} work.
* Define Subst Pattern Matching:: Process of template comparison.
* Define Subst Output Template:: Generation of output template.
@end menu
@node Define Subst Example
@subsection @code{define_subst} Example
@cindex define_subst
To illustrate how @code{define_subst} works, let us examine a simple
template transformation.
Suppose there are two kinds of instructions: one that touches flags and
the other that does not. The instructions of the second type could be
generated with the following @code{define_subst}:
@smallexample
(define_subst "add_clobber_subst"
[(set (match_operand:SI 0 "" "")
(match_operand:SI 1 "" ""))]
""
[(set (match_dup 0)
(match_dup 1))
(clobber (reg:CC FLAGS_REG))])
@end smallexample
This @code{define_subst} can be applied to any RTL pattern containing
@code{set} of mode SI and generates a copy with clobber when it is
applied.
Assume there is an RTL template for a @code{max} instruction to be used
in @code{define_subst} mentioned above:
@smallexample
(define_insn "maxsi"
[(set (match_operand:SI 0 "register_operand" "=r")
(max:SI
(match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r")))]
""
"max\t@{%2, %1, %0|%0, %1, %2@}"
[@dots{}])
@end smallexample
To mark the RTL template for @code{define_subst} application,
subst-attributes are used. They should be declared in advance:
@smallexample
(define_subst_attr "add_clobber_name" "add_clobber_subst" "_noclobber" "_clobber")
@end smallexample
Here @samp{add_clobber_name} is the attribute name,
@samp{add_clobber_subst} is the name of the corresponding
@code{define_subst}, the third argument (@samp{_noclobber}) is the
attribute value that would be substituted into the unchanged version of
the source RTL template, and the last argument (@samp{_clobber}) is the
value that would be substituted into the second, transformed,
version of the RTL template.
Once the subst-attribute has been defined, it should be used in RTL
templates which need to be processed by the @code{define_subst}. So,
the original RTL template should be changed:
@smallexample
(define_insn "maxsi<add_clobber_name>"
[(set (match_operand:SI 0 "register_operand" "=r")
(max:SI
(match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r")))]
""
"max\t@{%2, %1, %0|%0, %1, %2@}"
[@dots{}])
@end smallexample
The result of the @code{define_subst} usage would look like the following:
@smallexample
(define_insn "maxsi_noclobber"
[(set (match_operand:SI 0 "register_operand" "=r")
(max:SI
(match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r")))]
""
"max\t@{%2, %1, %0|%0, %1, %2@}"
[@dots{}])
(define_insn "maxsi_clobber"
[(set (match_operand:SI 0 "register_operand" "=r")
(max:SI
(match_operand:SI 1 "register_operand" "r")
(match_operand:SI 2 "register_operand" "r")))
(clobber (reg:CC FLAGS_REG))]
""
"max\t@{%2, %1, %0|%0, %1, %2@}"
[@dots{}])
@end smallexample
@node Define Subst Pattern Matching
@subsection Pattern Matching in @code{define_subst}
@cindex define_subst
All expressions, allowed in @code{define_insn} or @code{define_expand},
are allowed in the input-template of @code{define_subst}, except
@code{match_par_dup}, @code{match_scratch}, @code{match_parallel}. The
meanings of expressions in the input-template were changed:
@code{match_operand} matches any expression (possibly, a subtree in
RTL-template), if modes of the @code{match_operand} and this expression
are the same, or mode of the @code{match_operand} is @code{VOIDmode}, or
this expression is @code{match_dup}, @code{match_op_dup}. If the
expression is @code{match_operand} too, and predicate of
@code{match_operand} from the input pattern is not empty, then the
predicates are compared. That can be used for more accurate filtering
of accepted RTL-templates.
@code{match_operator} matches common operators (like @code{plus},
@code{minus}), @code{unspec}, @code{unspec_volatile} operators and
@code{match_operator}s from the original pattern if the modes match and
@code{match_operator} from the input pattern has the same number of
operands as the operator from the original pattern.
@node Define Subst Output Template
@subsection Generation of output template in @code{define_subst}
@cindex define_subst
If all necessary checks for @code{define_subst} application pass, a new
RTL-pattern, based on the output-template, is created to replace the old
template. Like in input-patterns, meanings of some RTL expressions are
changed when they are used in output-patterns of a @code{define_subst}.
Thus, @code{match_dup} is used for copying the whole expression from the
original pattern, which matched corresponding @code{match_operand} from
the input pattern.
@code{match_dup N} is used in the output template to be replaced with
the expression from the original pattern, which matched
@code{match_operand N} from the input pattern. As a consequence,
@code{match_dup} cannot be used to point to @code{match_operand}s from
the output pattern, it should always refer to a @code{match_operand}
from the input pattern. If a @code{match_dup N} occurs more than once
in the output template, its first occurrence is replaced with the
expression from the original pattern, and the subsequent expressions
are replaced with @code{match_dup N}, i.e., a reference to the first
expression.
In the output template one can refer to the expressions from the
original pattern and create new ones. For instance, some operands could
be added by means of standard @code{match_operand}.
After replacing @code{match_dup} with some RTL-subtree from the original
pattern, it could happen that several @code{match_operand}s in the
output pattern have the same indexes. It is unknown, how many and what
indexes would be used in the expression which would replace
@code{match_dup}, so such conflicts in indexes are inevitable. To
overcome this issue, @code{match_operands} and @code{match_operators},
which were introduced into the output pattern, are renumerated when all
@code{match_dup}s are replaced.
Number of alternatives in @code{match_operand}s introduced into the
output template @code{M} could differ from the number of alternatives in
the original pattern @code{N}, so in the resultant pattern there would
be @code{N*M} alternatives. Thus, constraints from the original pattern
would be duplicated @code{N} times, constraints from the output pattern
would be duplicated @code{M} times, producing all possible combinations.
@end ifset
@ifset INTERNALS
@node Constant Definitions
@section Constant Definitions
@cindex constant definitions
@findex define_constants
Using literal constants inside instruction patterns reduces legibility and
can be a maintenance problem.
To overcome this problem, you may use the @code{define_constants}
expression. It contains a vector of name-value pairs. From that
point on, wherever any of the names appears in the MD file, it is as
if the corresponding value had been written instead. You may use
@code{define_constants} multiple times; each appearance adds more
constants to the table. It is an error to redefine a constant with
a different value.
To come back to the a29k load multiple example, instead of
@smallexample
(define_insn ""
[(match_parallel 0 "load_multiple_operation"
[(set (match_operand:SI 1 "gpc_reg_operand" "=r")
(match_operand:SI 2 "memory_operand" "m"))
(use (reg:SI 179))
(clobber (reg:SI 179))])]
""
"loadm 0,0,%1,%2")
@end smallexample
You could write:
@smallexample
(define_constants [
(R_BP 177)
(R_FC 178)
(R_CR 179)
(R_Q 180)
])
(define_insn ""
[(match_parallel 0 "load_multiple_operation"
[(set (match_operand:SI 1 "gpc_reg_operand" "=r")
(match_operand:SI 2 "memory_operand" "m"))
(use (reg:SI R_CR))
(clobber (reg:SI R_CR))])]
""
"loadm 0,0,%1,%2")
@end smallexample
The constants that are defined with a define_constant are also output
in the insn-codes.h header file as #defines.
@cindex enumerations
@findex define_c_enum
You can also use the machine description file to define enumerations.
Like the constants defined by @code{define_constant}, these enumerations
are visible to both the machine description file and the main C code.
The syntax is as follows:
@smallexample
(define_c_enum "@var{name}" [
@var{value0}
@var{value1}
(@var{value32} 32)
@var{value33}
@dots{}
@var{valuen}
])
@end smallexample
This definition causes the equivalent of the following C code to appear
in @file{insn-constants.h}:
@smallexample
enum @var{name} @{
@var{value0} = 0,
@var{value1} = 1,
@var{value32} = 32,
@var{value33} = 33,
@dots{}
@var{valuen} = @var{n}
@};
#define NUM_@var{cname}_VALUES (@var{n} + 1)
@end smallexample
where @var{cname} is the capitalized form of @var{name}.
It also makes each @var{valuei} available in the machine description
file, just as if it had been declared with:
@smallexample
(define_constants [(@var{valuei} @var{i})])
@end smallexample
Each @var{valuei} is usually an upper-case identifier and usually
begins with @var{cname}.
You can split the enumeration definition into as many statements as
you like. The above example is directly equivalent to:
@smallexample
(define_c_enum "@var{name}" [@var{value0}])
(define_c_enum "@var{name}" [@var{value1}])
@dots{}
(define_c_enum "@var{name}" [@var{valuen}])
@end smallexample
Splitting the enumeration helps to improve the modularity of each
individual @code{.md} file. For example, if a port defines its
synchronization instructions in a separate @file{sync.md} file,
it is convenient to define all synchronization-specific enumeration
values in @file{sync.md} rather than in the main @file{.md} file.
Some enumeration names have special significance to GCC:
@table @code
@findex unspec_volatile
@item unspecv
If an enumeration called @code{unspecv} is defined, GCC will use it
when printing out @code{unspec_volatile} expressions. For example:
@smallexample
(define_c_enum "unspecv" [
UNSPECV_BLOCKAGE
])
@end smallexample
causes GCC to print @samp{(unspec_volatile @dots{} 0)} as:
@smallexample
(unspec_volatile ... UNSPECV_BLOCKAGE)
@end smallexample
@findex unspec
@item unspec
If an enumeration called @code{unspec} is defined, GCC will use
it when printing out @code{unspec} expressions. GCC will also use
it when printing out @code{unspec_volatile} expressions unless an
@code{unspecv} enumeration is also defined. You can therefore
decide whether to keep separate enumerations for volatile and
non-volatile expressions or whether to use the same enumeration
for both.
@end table
@findex define_enum
@anchor{define_enum}
Another way of defining an enumeration is to use @code{define_enum}:
@smallexample
(define_enum "@var{name}" [
@var{value0}
@var{value1}
@dots{}
@var{valuen}
])
@end smallexample
This directive implies:
@smallexample
(define_c_enum "@var{name}" [
@var{cname}_@var{cvalue0}
@var{cname}_@var{cvalue1}
@dots{}
@var{cname}_@var{cvaluen}
])
@end smallexample
@findex define_enum_attr
where @var{cvaluei} is the capitalized form of @var{valuei}.
However, unlike @code{define_c_enum}, the enumerations defined
by @code{define_enum} can be used in attribute specifications
(@pxref{define_enum_attr}).
@end ifset
@ifset INTERNALS
@node Iterators
@section Iterators
@cindex iterators in @file{.md} files
Ports often need to define similar patterns for more than one machine
mode or for more than one rtx code. GCC provides some simple iterator
facilities to make this process easier.
@menu
* Mode Iterators:: Generating variations of patterns for different modes.
* Code Iterators:: Doing the same for codes.
* Int Iterators:: Doing the same for integers.
* Subst Iterators:: Generating variations of patterns for define_subst.
* Parameterized Names:: Specifying iterator values in C++ code.
@end menu
@node Mode Iterators
@subsection Mode Iterators
@cindex mode iterators in @file{.md} files
Ports often need to define similar patterns for two or more different modes.
For example:
@itemize @bullet
@item
If a processor has hardware support for both single and double
floating-point arithmetic, the @code{SFmode} patterns tend to be
very similar to the @code{DFmode} ones.
@item
If a port uses @code{SImode} pointers in one configuration and
@code{DImode} pointers in another, it will usually have very similar
@code{SImode} and @code{DImode} patterns for manipulating pointers.
@end itemize
Mode iterators allow several patterns to be instantiated from one
@file{.md} file template. They can be used with any type of
rtx-based construct, such as a @code{define_insn},
@code{define_split}, or @code{define_peephole2}.
@menu
* Defining Mode Iterators:: Defining a new mode iterator.
* Substitutions:: Combining mode iterators with substitutions
* Examples:: Examples
@end menu
@node Defining Mode Iterators
@subsubsection Defining Mode Iterators
@findex define_mode_iterator
The syntax for defining a mode iterator is:
@smallexample
(define_mode_iterator @var{name} [(@var{mode1} "@var{cond1}") @dots{} (@var{moden} "@var{condn}")])
@end smallexample
This allows subsequent @file{.md} file constructs to use the mode suffix
@code{:@var{name}}. Every construct that does so will be expanded
@var{n} times, once with every use of @code{:@var{name}} replaced by
@code{:@var{mode1}}, once with every use replaced by @code{:@var{mode2}},
and so on. In the expansion for a particular @var{modei}, every
C condition will also require that @var{condi} be true.
For example:
@smallexample
(define_mode_iterator P [(SI "Pmode == SImode") (DI "Pmode == DImode")])
@end smallexample
defines a new mode suffix @code{:P}. Every construct that uses
@code{:P} will be expanded twice, once with every @code{:P} replaced
by @code{:SI} and once with every @code{:P} replaced by @code{:DI}.
The @code{:SI} version will only apply if @code{Pmode == SImode} and
the @code{:DI} version will only apply if @code{Pmode == DImode}.
As with other @file{.md} conditions, an empty string is treated
as ``always true''. @code{(@var{mode} "")} can also be abbreviated
to @code{@var{mode}}. For example:
@smallexample
(define_mode_iterator GPR [SI (DI "TARGET_64BIT")])
@end smallexample
means that the @code{:DI} expansion only applies if @code{TARGET_64BIT}
but that the @code{:SI} expansion has no such constraint.
Iterators are applied in the order they are defined. This can be
significant if two iterators are used in a construct that requires
substitutions. @xref{Substitutions}.
@node Substitutions
@subsubsection Substitution in Mode Iterators
@findex define_mode_attr
If an @file{.md} file construct uses mode iterators, each version of the
construct will often need slightly different strings or modes. For
example:
@itemize @bullet
@item
When a @code{define_expand} defines several @code{add@var{m}3} patterns
(@pxref{Standard Names}), each expander will need to use the
appropriate mode name for @var{m}.
@item
When a @code{define_insn} defines several instruction patterns,
each instruction will often use a different assembler mnemonic.
@item
When a @code{define_insn} requires operands with different modes,
using an iterator for one of the operand modes usually requires a specific
mode for the other operand(s).
@end itemize
GCC supports such variations through a system of ``mode attributes''.
There are two standard attributes: @code{mode}, which is the name of
the mode in lower case, and @code{MODE}, which is the same thing in
upper case. You can define other attributes using:
@smallexample
(define_mode_attr @var{name} [(@var{mode1} "@var{value1}") @dots{} (@var{moden} "@var{valuen}")])
@end smallexample
where @var{name} is the name of the attribute and @var{valuei}
is the value associated with @var{modei}.
When GCC replaces some @var{:iterator} with @var{:mode}, it will scan
each string and mode in the pattern for sequences of the form
@code{<@var{iterator}:@var{attr}>}, where @var{attr} is the name of a
mode attribute. If the attribute is defined for @var{mode}, the whole
@code{<@dots{}>} sequence will be replaced by the appropriate attribute
value.
For example, suppose an @file{.md} file has:
@smallexample
(define_mode_iterator P [(SI "Pmode == SImode") (DI "Pmode == DImode")])
(define_mode_attr load [(SI "lw") (DI "ld")])
@end smallexample
If one of the patterns that uses @code{:P} contains the string
@code{"<P:load>\t%0,%1"}, the @code{SI} version of that pattern
will use @code{"lw\t%0,%1"} and the @code{DI} version will use
@code{"ld\t%0,%1"}.
Here is an example of using an attribute for a mode:
@smallexample
(define_mode_iterator LONG [SI DI])
(define_mode_attr SHORT [(SI "HI") (DI "SI")])
(define_insn @dots{}
(sign_extend:LONG (match_operand:<LONG:SHORT> @dots{})) @dots{})
@end smallexample
The @code{@var{iterator}:} prefix may be omitted, in which case the
substitution will be attempted for every iterator expansion.
@node Examples
@subsubsection Mode Iterator Examples
Here is an example from the MIPS port. It defines the following
modes and attributes (among others):
@smallexample
(define_mode_iterator GPR [SI (DI "TARGET_64BIT")])
(define_mode_attr d [(SI "") (DI "d")])
@end smallexample
and uses the following template to define both @code{subsi3}
and @code{subdi3}:
@smallexample
(define_insn "sub<mode>3"
[(set (match_operand:GPR 0 "register_operand" "=d")
(minus:GPR (match_operand:GPR 1 "register_operand" "d")
(match_operand:GPR 2 "register_operand" "d")))]
""
"<d>subu\t%0,%1,%2"
[(set_attr "type" "arith")
(set_attr "mode" "<MODE>")])
@end smallexample
This is exactly equivalent to:
@smallexample
(define_insn "subsi3"
[(set (match_operand:SI 0 "register_operand" "=d")
(minus:SI (match_operand:SI 1 "register_operand" "d")
(match_operand:SI 2 "register_operand" "d")))]
""
"subu\t%0,%1,%2"
[(set_attr "type" "arith")
(set_attr "mode" "SI")])
(define_insn "subdi3"
[(set (match_operand:DI 0 "register_operand" "=d")
(minus:DI (match_operand:DI 1 "register_operand" "d")
(match_operand:DI 2 "register_operand" "d")))]
"TARGET_64BIT"
"dsubu\t%0,%1,%2"
[(set_attr "type" "arith")
(set_attr "mode" "DI")])
@end smallexample
@node Code Iterators
@subsection Code Iterators
@cindex code iterators in @file{.md} files
@findex define_code_iterator
@findex define_code_attr
Code iterators operate in a similar way to mode iterators. @xref{Mode Iterators}.
The construct:
@smallexample
(define_code_iterator @var{name} [(@var{code1} "@var{cond1}") @dots{} (@var{coden} "@var{condn}")])
@end smallexample
defines a pseudo rtx code @var{name} that can be instantiated as
@var{codei} if condition @var{condi} is true. Each @var{codei}
must have the same rtx format. @xref{RTL Classes}.
As with mode iterators, each pattern that uses @var{name} will be
expanded @var{n} times, once with all uses of @var{name} replaced by
@var{code1}, once with all uses replaced by @var{code2}, and so on.
@xref{Defining Mode Iterators}.
It is possible to define attributes for codes as well as for modes.
There are two standard code attributes: @code{code}, the name of the
code in lower case, and @code{CODE}, the name of the code in upper case.
Other attributes are defined using:
@smallexample
(define_code_attr @var{name} [(@var{code1} "@var{value1}") @dots{} (@var{coden} "@var{valuen}")])
@end smallexample
Instruction patterns can use code attributes as rtx codes, which can be
useful if two sets of codes act in tandem. For example, the following
@code{define_insn} defines two patterns, one calculating a signed absolute
difference and another calculating an unsigned absolute difference:
@smallexample
(define_code_iterator any_max [smax umax])
(define_code_attr paired_min [(smax "smin") (umax "umin")])
(define_insn @dots{}
[(set (match_operand:SI 0 @dots{})
(minus:SI (any_max:SI (match_operand:SI 1 @dots{})
(match_operand:SI 2 @dots{}))
(<paired_min>:SI (match_dup 1) (match_dup 2))))]
@dots{})
@end smallexample
The signed version of the instruction uses @code{smax} and @code{smin}
while the unsigned version uses @code{umax} and @code{umin}. There
are no versions that pair @code{smax} with @code{umin} or @code{umax}
with @code{smin}.
Here's an example of code iterators in action, taken from the MIPS port:
@smallexample
(define_code_iterator any_cond [unordered ordered unlt unge uneq ltgt unle ungt
eq ne gt ge lt le gtu geu ltu leu])
(define_expand "b<code>"
[(set (pc)
(if_then_else (any_cond:CC (cc0)
(const_int 0))
(label_ref (match_operand 0 ""))
(pc)))]
""
@{
gen_conditional_branch (operands, <CODE>);
DONE;
@})
@end smallexample
This is equivalent to:
@smallexample
(define_expand "bunordered"
[(set (pc)
(if_then_else (unordered:CC (cc0)
(const_int 0))
(label_ref (match_operand 0 ""))
(pc)))]
""
@{
gen_conditional_branch (operands, UNORDERED);
DONE;
@})
(define_expand "bordered"
[(set (pc)
(if_then_else (ordered:CC (cc0)
(const_int 0))
(label_ref (match_operand 0 ""))
(pc)))]
""
@{
gen_conditional_branch (operands, ORDERED);
DONE;
@})
@dots{}
@end smallexample
@node Int Iterators
@subsection Int Iterators
@cindex int iterators in @file{.md} files
@findex define_int_iterator
@findex define_int_attr
Int iterators operate in a similar way to code iterators. @xref{Code Iterators}.
The construct:
@smallexample
(define_int_iterator @var{name} [(@var{int1} "@var{cond1}") @dots{} (@var{intn} "@var{condn}")])
@end smallexample
defines a pseudo integer constant @var{name} that can be instantiated as
@var{inti} if condition @var{condi} is true. Int iterators can appear in
only those rtx fields that have `i', `n', `w', or `p' as the specifier.
This means that each @var{int} has to be a constant defined using
@samp{define_constant} or @samp{define_c_enum}.
As with mode and code iterators, each pattern that uses @var{name} will be
expanded @var{n} times, once with all uses of @var{name} replaced by
@var{int1}, once with all uses replaced by @var{int2}, and so on.
@xref{Defining Mode Iterators}.
It is possible to define attributes for ints as well as for codes and modes.
Attributes are defined using:
@smallexample
(define_int_attr @var{attr_name} [(@var{int1} "@var{value1}") @dots{} (@var{intn} "@var{valuen}")])
@end smallexample
In additon to these user-defined attributes, it is possible to use
@samp{<@var{name}>} to refer to the current expansion of iterator
@var{name} (such as @var{int1}, @var{int2}, and so on).
Here's an example of int iterators in action, taken from the ARM port:
@smallexample
(define_int_iterator QABSNEG [UNSPEC_VQABS UNSPEC_VQNEG])
(define_int_attr absneg [(UNSPEC_VQABS "abs") (UNSPEC_VQNEG "neg")])
(define_insn "neon_vq<absneg><mode>"
[(set (match_operand:VDQIW 0 "s_register_operand" "=w")
(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w")
(match_operand:SI 2 "immediate_operand" "i")]
QABSNEG))]
"TARGET_NEON"
"vq<absneg>.<V_s_elem>\t%<V_reg>0, %<V_reg>1"
[(set_attr "type" "neon_vqneg_vqabs")]
)
@end smallexample
This is equivalent to:
@smallexample
(define_insn "neon_vqabs<mode>"
[(set (match_operand:VDQIW 0 "s_register_operand" "=w")
(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w")
(match_operand:SI 2 "immediate_operand" "i")]
UNSPEC_VQABS))]
"TARGET_NEON"
"vqabs.<V_s_elem>\t%<V_reg>0, %<V_reg>1"
[(set_attr "type" "neon_vqneg_vqabs")]
)
(define_insn "neon_vqneg<mode>"
[(set (match_operand:VDQIW 0 "s_register_operand" "=w")
(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w")
(match_operand:SI 2 "immediate_operand" "i")]
UNSPEC_VQNEG))]
"TARGET_NEON"
"vqneg.<V_s_elem>\t%<V_reg>0, %<V_reg>1"
[(set_attr "type" "neon_vqneg_vqabs")]
)
@end smallexample
@node Subst Iterators
@subsection Subst Iterators
@cindex subst iterators in @file{.md} files
@findex define_subst
@findex define_subst_attr
Subst iterators are special type of iterators with the following
restrictions: they could not be declared explicitly, they always have
only two values, and they do not have explicit dedicated name.
Subst-iterators are triggered only when corresponding subst-attribute is
used in RTL-pattern.
Subst iterators transform templates in the following way: the templates
are duplicated, the subst-attributes in these templates are replaced
with the corresponding values, and a new attribute is implicitly added
to the given @code{define_insn}/@code{define_expand}. The name of the
added attribute matches the name of @code{define_subst}. Such
attributes are declared implicitly, and it is not allowed to have a
@code{define_attr} named as a @code{define_subst}.
Each subst iterator is linked to a @code{define_subst}. It is declared
implicitly by the first appearance of the corresponding
@code{define_subst_attr}, and it is not allowed to define it explicitly.
Declarations of subst-attributes have the following syntax:
@findex define_subst_attr
@smallexample
(define_subst_attr "@var{name}"
"@var{subst-name}"
"@var{no-subst-value}"
"@var{subst-applied-value}")
@end smallexample
@var{name} is a string with which the given subst-attribute could be
referred to.
@var{subst-name} shows which @code{define_subst} should be applied to an
RTL-template if the given subst-attribute is present in the
RTL-template.
@var{no-subst-value} is a value with which subst-attribute would be
replaced in the first copy of the original RTL-template.
@var{subst-applied-value} is a value with which subst-attribute would be
replaced in the second copy of the original RTL-template.
@node Parameterized Names
@subsection Parameterized Names
@cindex @samp{@@} in instruction pattern names
Ports sometimes need to apply iterators using C++ code, in order to
get the code or RTL pattern for a specific instruction. For example,
suppose we have the @samp{neon_vq<absneg><mode>} pattern given above:
@smallexample
(define_int_iterator QABSNEG [UNSPEC_VQABS UNSPEC_VQNEG])
(define_int_attr absneg [(UNSPEC_VQABS "abs") (UNSPEC_VQNEG "neg")])
(define_insn "neon_vq<absneg><mode>"
[(set (match_operand:VDQIW 0 "s_register_operand" "=w")
(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w")
(match_operand:SI 2 "immediate_operand" "i")]
QABSNEG))]
@dots{}
)
@end smallexample
A port might need to generate this pattern for a variable
@samp{QABSNEG} value and a variable @samp{VDQIW} mode. There are two
ways of doing this. The first is to build the rtx for the pattern
directly from C++ code; this is a valid technique and avoids any risk
of combinatorial explosion. The second is to prefix the instruction
name with the special character @samp{@@}, which tells GCC to generate
the four additional functions below. In each case, @var{name} is the
name of the instruction without the leading @samp{@@} character,
without the @samp{<@dots{}>} placeholders, and with any underscore
before a @samp{<@dots{}>} placeholder removed if keeping it would
lead to a double or trailing underscore.
@table @samp
@item insn_code maybe_code_for_@var{name} (@var{i1}, @var{i2}, @dots{})
See whether replacing the first @samp{<@dots{}>} placeholder with
iterator value @var{i1}, the second with iterator value @var{i2}, and
so on, gives a valid instruction. Return its code if so, otherwise
return @code{CODE_FOR_nothing}.
@item insn_code code_for_@var{name} (@var{i1}, @var{i2}, @dots{})
Same, but abort the compiler if the requested instruction does not exist.
@item rtx maybe_gen_@var{name} (@var{i1}, @var{i2}, @dots{}, @var{op0}, @var{op1}, @dots{})
Check for a valid instruction in the same way as
@code{maybe_code_for_@var{name}}. If the instruction exists,
generate an instance of it using the operand values given by @var{op0},
@var{op1}, and so on, otherwise return null.
@item rtx gen_@var{name} (@var{i1}, @var{i2}, @dots{}, @var{op0}, @var{op1}, @dots{})
Same, but abort the compiler if the requested instruction does not exist,
or if the instruction generator invoked the @code{FAIL} macro.
@end table
For example, changing the pattern above to:
@smallexample
(define_insn "@@neon_vq<absneg><mode>"
[(set (match_operand:VDQIW 0 "s_register_operand" "=w")
(unspec:VDQIW [(match_operand:VDQIW 1 "s_register_operand" "w")
(match_operand:SI 2 "immediate_operand" "i")]
QABSNEG))]
@dots{}
)
@end smallexample
would define the same patterns as before, but in addition would generate
the four functions below:
@smallexample
insn_code maybe_code_for_neon_vq (int, machine_mode);
insn_code code_for_neon_vq (int, machine_mode);
rtx maybe_gen_neon_vq (int, machine_mode, rtx, rtx, rtx);
rtx gen_neon_vq (int, machine_mode, rtx, rtx, rtx);
@end smallexample
Calling @samp{code_for_neon_vq (UNSPEC_VQABS, V8QImode)}
would then give @code{CODE_FOR_neon_vqabsv8qi}.
It is possible to have multiple @samp{@@} patterns with the same
name and same types of iterator. For example:
@smallexample
(define_insn "@@some_arithmetic_op<mode>"
[(set (match_operand:INTEGER_MODES 0 "register_operand") @dots{})]
@dots{}
)
(define_insn "@@some_arithmetic_op<mode>"
[(set (match_operand:FLOAT_MODES 0 "register_operand") @dots{})]
@dots{}
)
@end smallexample
would produce a single set of functions that handles both
@code{INTEGER_MODES} and @code{FLOAT_MODES}.
It is also possible for these @samp{@@} patterns to have different
numbers of operands from each other. For example, patterns with
a binary rtl code might take three operands (one output and two inputs)
while patterns with a ternary rtl code might take four operands (one
output and three inputs). This combination would produce separate
@samp{maybe_gen_@var{name}} and @samp{gen_@var{name}} functions for
each operand count, but it would still produce a single
@samp{maybe_code_for_@var{name}} and a single @samp{code_for_@var{name}}.
@end ifset
|