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
|
/* Subroutines used to expand string and block move, clear,
compare and other operations for PowerPC.
Copyright (C) 1991-2023 Free Software Foundation, Inc.
This file is part of GCC.
GCC is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published
by the Free Software Foundation; either version 3, or (at your
option) any later version.
GCC is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
License for more details.
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
#define IN_TARGET_CODE 1
#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "backend.h"
#include "rtl.h"
#include "tree.h"
#include "memmodel.h"
#include "tm_p.h"
#include "ira.h"
#include "print-tree.h"
#include "varasm.h"
#include "explow.h"
#include "expr.h"
#include "output.h"
#include "target.h"
#include "profile-count.h"
#include "predict.h"
/* Expand a block clear operation, and return 1 if successful. Return 0
if we should let the compiler generate normal code.
operands[0] is the destination
operands[1] is the length
operands[3] is the alignment */
int
expand_block_clear (rtx operands[])
{
rtx orig_dest = operands[0];
rtx bytes_rtx = operands[1];
rtx align_rtx = operands[3];
bool constp = CONST_INT_P (bytes_rtx);
HOST_WIDE_INT align;
HOST_WIDE_INT bytes;
int offset;
int clear_bytes;
int clear_step;
/* If this is not a fixed size move, just call memcpy */
if (! constp)
return 0;
/* This must be a fixed size alignment */
gcc_assert (CONST_INT_P (align_rtx));
align = INTVAL (align_rtx) * BITS_PER_UNIT;
/* Anything to clear? */
bytes = INTVAL (bytes_rtx);
if (bytes <= 0)
return 1;
/* Use the builtin memset after a point, to avoid huge code bloat.
When optimize_size, avoid any significant code bloat; calling
memset is about 4 instructions, so allow for one instruction to
load zero and three to do clearing. */
if (TARGET_ALTIVEC && (align >= 128 || TARGET_EFFICIENT_UNALIGNED_VSX))
clear_step = 16;
else if (TARGET_POWERPC64 && (align >= 64 || !STRICT_ALIGNMENT))
clear_step = 8;
else
clear_step = 4;
if (optimize_size && bytes > 3 * clear_step)
return 0;
if (! optimize_size && bytes > 8 * clear_step)
return 0;
bool unaligned_vsx_ok = (bytes >= 32 && TARGET_EFFICIENT_UNALIGNED_VSX);
for (offset = 0; bytes > 0; offset += clear_bytes, bytes -= clear_bytes)
{
machine_mode mode = BLKmode;
rtx dest;
if (TARGET_ALTIVEC
&& (bytes >= 16 && (align >= 128 || unaligned_vsx_ok)))
{
clear_bytes = 16;
mode = V4SImode;
}
else if (bytes >= 8 && TARGET_POWERPC64
&& (align >= 64 || !STRICT_ALIGNMENT))
{
clear_bytes = 8;
mode = DImode;
if (offset == 0 && align < 64)
{
rtx addr;
/* If the address form is reg+offset with offset not a
multiple of four, reload into reg indirect form here
rather than waiting for reload. This way we get one
reload, not one per store. */
addr = XEXP (orig_dest, 0);
if ((GET_CODE (addr) == PLUS || GET_CODE (addr) == LO_SUM)
&& CONST_INT_P (XEXP (addr, 1))
&& (INTVAL (XEXP (addr, 1)) & 3) != 0)
{
addr = copy_addr_to_reg (addr);
orig_dest = replace_equiv_address (orig_dest, addr);
}
}
}
else if (bytes >= 4 && (align >= 32 || !STRICT_ALIGNMENT))
{ /* move 4 bytes */
clear_bytes = 4;
mode = SImode;
}
else if (bytes >= 2 && (align >= 16 || !STRICT_ALIGNMENT))
{ /* move 2 bytes */
clear_bytes = 2;
mode = HImode;
}
else /* move 1 byte at a time */
{
clear_bytes = 1;
mode = QImode;
}
dest = adjust_address (orig_dest, mode, offset);
emit_move_insn (dest, CONST0_RTX (mode));
}
return 1;
}
/* Figure out the correct instructions to generate to load data for
block compare. MODE is used for the read from memory, and
data is zero extended if REG is wider than MODE. If LE code
is being generated, bswap loads are used.
REG is the destination register to move the data into.
MEM is the memory block being read.
MODE is the mode of memory to use for the read. */
static void
do_load_for_compare (rtx reg, rtx mem, machine_mode mode)
{
switch (GET_MODE (reg))
{
case E_V16QImode:
switch (mode)
{
case E_V16QImode:
if (!BYTES_BIG_ENDIAN)
{
if (TARGET_P9_VECTOR)
emit_insn (gen_vsx_ld_elemrev_v16qi_internal (reg, mem));
else
{
rtx reg_v2di = simplify_gen_subreg (V2DImode, reg,
V16QImode, 0);
gcc_assert (MEM_P (mem));
rtx addr = XEXP (mem, 0);
rtx mem_v2di = gen_rtx_MEM (V2DImode, addr);
MEM_COPY_ATTRIBUTES (mem_v2di, mem);
set_mem_size (mem, GET_MODE_SIZE (V2DImode));
emit_insn (gen_vsx_ld_elemrev_v2di (reg_v2di, mem_v2di));
}
}
else
emit_insn (gen_vsx_movv2di_64bit (reg, mem));
break;
default:
gcc_unreachable ();
}
break;
case E_DImode:
switch (mode)
{
case E_QImode:
emit_insn (gen_zero_extendqidi2 (reg, mem));
break;
case E_HImode:
{
rtx src = mem;
if (!BYTES_BIG_ENDIAN)
{
src = gen_reg_rtx (HImode);
emit_insn (gen_bswaphi2 (src, mem));
}
emit_insn (gen_zero_extendhidi2 (reg, src));
break;
}
case E_SImode:
{
rtx src = mem;
if (!BYTES_BIG_ENDIAN)
{
src = gen_reg_rtx (SImode);
emit_insn (gen_bswapsi2 (src, mem));
}
emit_insn (gen_zero_extendsidi2 (reg, src));
}
break;
case E_DImode:
if (!BYTES_BIG_ENDIAN)
emit_insn (gen_bswapdi2 (reg, mem));
else
emit_insn (gen_movdi (reg, mem));
break;
default:
gcc_unreachable ();
}
break;
case E_SImode:
switch (mode)
{
case E_QImode:
emit_insn (gen_zero_extendqisi2 (reg, mem));
break;
case E_HImode:
{
rtx src = mem;
if (!BYTES_BIG_ENDIAN)
{
src = gen_reg_rtx (HImode);
emit_insn (gen_bswaphi2 (src, mem));
}
emit_insn (gen_zero_extendhisi2 (reg, src));
break;
}
case E_SImode:
if (!BYTES_BIG_ENDIAN)
emit_insn (gen_bswapsi2 (reg, mem));
else
emit_insn (gen_movsi (reg, mem));
break;
case E_DImode:
/* DImode is larger than the destination reg so is not expected. */
gcc_unreachable ();
break;
default:
gcc_unreachable ();
}
break;
case E_QImode:
gcc_assert (mode == E_QImode);
emit_move_insn (reg, mem);
break;
default:
gcc_unreachable ();
break;
}
}
/* Select the mode to be used for reading the next chunk of bytes
in the compare.
OFFSET is the current read offset from the beginning of the block.
BYTES is the number of bytes remaining to be read.
ALIGN is the minimum alignment of the memory blocks being compared in bytes. */
static machine_mode
select_block_compare_mode (unsigned HOST_WIDE_INT offset,
unsigned HOST_WIDE_INT bytes,
unsigned HOST_WIDE_INT align)
{
/* First see if we can do a whole load unit
as that will be more efficient than a larger load + shift. */
/* If big, use biggest chunk.
If exactly chunk size, use that size.
If remainder can be done in one piece with shifting, do that.
Do largest chunk possible without violating alignment rules. */
/* The most we can read without potential page crossing. */
unsigned HOST_WIDE_INT maxread = ROUND_UP (bytes, align);
/* If we have an LE target without ldbrx and word_mode is DImode,
then we must avoid using word_mode. */
int word_mode_ok = !(!BYTES_BIG_ENDIAN && !TARGET_LDBRX
&& word_mode == DImode);
if (word_mode_ok && bytes >= UNITS_PER_WORD)
return word_mode;
else if (bytes == GET_MODE_SIZE (SImode))
return SImode;
else if (bytes == GET_MODE_SIZE (HImode))
return HImode;
else if (bytes == GET_MODE_SIZE (QImode))
return QImode;
else if (bytes < GET_MODE_SIZE (SImode)
&& !targetm.slow_unaligned_access (SImode, align * BITS_PER_UNIT)
&& offset >= GET_MODE_SIZE (SImode) - bytes)
/* This matches the case were we have SImode and 3 bytes
and offset >= 1 and permits us to move back one and overlap
with the previous read, thus avoiding having to shift
unwanted bytes off of the input. */
return SImode;
else if (word_mode_ok && bytes < UNITS_PER_WORD
&& !targetm.slow_unaligned_access (word_mode, align * BITS_PER_UNIT)
&& offset >= UNITS_PER_WORD-bytes)
/* Similarly, if we can use DImode it will get matched here and
can do an overlapping read that ends at the end of the block. */
return word_mode;
else if (word_mode_ok && maxread >= UNITS_PER_WORD)
/* It is safe to do all remaining in one load of largest size,
possibly with a shift to get rid of unwanted bytes. */
return word_mode;
else if (maxread >= GET_MODE_SIZE (SImode))
/* It is safe to do all remaining in one SImode load,
possibly with a shift to get rid of unwanted bytes. */
return SImode;
else if (bytes > GET_MODE_SIZE (SImode))
return SImode;
else if (bytes > GET_MODE_SIZE (HImode))
return HImode;
/* final fallback is do one byte */
return QImode;
}
/* Compute the alignment of pointer+OFFSET where the original alignment
of pointer was BASE_ALIGN. */
static unsigned HOST_WIDE_INT
compute_current_alignment (unsigned HOST_WIDE_INT base_align,
unsigned HOST_WIDE_INT offset)
{
if (offset == 0)
return base_align;
return MIN (base_align, offset & -offset);
}
/* Prepare address and then do a load.
MODE is the mode to use for the load.
DEST is the destination register for the data.
ADDR is the address to be loaded.
ORIG_ADDR is the original address expression. */
static void
do_load_for_compare_from_addr (machine_mode mode, rtx dest, rtx addr,
rtx orig_addr)
{
rtx mem = gen_rtx_MEM (mode, addr);
MEM_COPY_ATTRIBUTES (mem, orig_addr);
set_mem_size (mem, GET_MODE_SIZE (mode));
do_load_for_compare (dest, mem, mode);
return;
}
/* Do a branch for an if/else decision.
CMPMODE is the mode to use for the comparison.
COMPARISON is the rtx code for the compare needed.
A is the first thing to be compared.
B is the second thing to be compared.
CR is the condition code reg input, or NULL_RTX.
TRUE_LABEL is the label to branch to if the condition is true.
P is the estimated branch probability for the branch.
The return value is the CR used for the comparison.
If CR is null_rtx, then a new register of CMPMODE is generated.
If A and B are both null_rtx, then CR must not be null, and the
compare is not generated so you can use this with a dot form insn. */
static void
do_ifelse (machine_mode cmpmode, rtx_code comparison,
rtx a, rtx b, rtx cr, rtx true_label, profile_probability br_prob)
{
gcc_assert ((a == NULL_RTX && b == NULL_RTX && cr != NULL_RTX)
|| (a != NULL_RTX && b != NULL_RTX));
if (cr != NULL_RTX)
gcc_assert (GET_MODE (cr) == cmpmode);
else
cr = gen_reg_rtx (cmpmode);
rtx label_ref = gen_rtx_LABEL_REF (VOIDmode, true_label);
if (a != NULL_RTX)
emit_move_insn (cr, gen_rtx_COMPARE (cmpmode, a, b));
rtx cmp_rtx = gen_rtx_fmt_ee (comparison, VOIDmode, cr, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx, label_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, br_prob);
JUMP_LABEL (j) = true_label;
LABEL_NUSES (true_label) += 1;
}
/* Emit an isel of the proper mode for DEST.
DEST is the isel destination register.
SRC1 is the isel source if CR is true.
SRC2 is the isel source if CR is false.
CR is the condition for the isel. */
static void
do_isel (rtx dest, rtx cmp, rtx src_t, rtx src_f, rtx cr)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_isel_cc_di (dest, cmp, src_t, src_f, cr));
else
emit_insn (gen_isel_cc_si (dest, cmp, src_t, src_f, cr));
}
/* Emit a subtract of the proper mode for DEST.
DEST is the destination register for the subtract.
SRC1 is the first subtract input.
SRC2 is the second subtract input.
Computes DEST = SRC1-SRC2. */
static void
do_sub3 (rtx dest, rtx src1, rtx src2)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_subdi3 (dest, src1, src2));
else
emit_insn (gen_subsi3 (dest, src1, src2));
}
/* Emit an add of the proper mode for DEST.
DEST is the destination register for the add.
SRC1 is the first add input.
SRC2 is the second add input.
Computes DEST = SRC1+SRC2. */
static void
do_add3 (rtx dest, rtx src1, rtx src2)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_adddi3 (dest, src1, src2));
else
emit_insn (gen_addsi3 (dest, src1, src2));
}
/* Emit an and of the proper mode for DEST.
DEST is the destination register for the and.
SRC1 is the first and input.
SRC2 is the second and input.
Computes DEST = SRC1&SRC2. */
static void
do_and3 (rtx dest, rtx src1, rtx src2)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_anddi3 (dest, src1, src2));
else
emit_insn (gen_andsi3 (dest, src1, src2));
}
/* Emit an cmpb of the proper mode for DEST.
DEST is the destination register for the cmpb.
SRC1 is the first input.
SRC2 is the second input.
Computes cmpb of SRC1, SRC2. */
static void
do_cmpb3 (rtx dest, rtx src1, rtx src2)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_cmpbdi3 (dest, src1, src2));
else
emit_insn (gen_cmpbsi3 (dest, src1, src2));
}
/* Emit a rotl of the proper mode for DEST.
DEST is the destination register for the and.
SRC1 is the first and input.
SRC2 is the second and input.
Computes DEST = SRC1 rotated left by SRC2. */
static void
do_rotl3 (rtx dest, rtx src1, rtx src2)
{
if (GET_MODE (dest) == DImode)
emit_insn (gen_rotldi3 (dest, src1, src2));
else
emit_insn (gen_rotlsi3 (dest, src1, src2));
}
/* Generate rtl for a load, shift, and compare of less than a full word.
LOAD_MODE is the machine mode for the loads.
DIFF is the reg for the difference.
CMP_REM is the reg containing the remaining bytes to compare.
DCOND is the CCUNS reg for the compare if we are doing P9 code with setb.
SRC1_ADDR is the first source address.
SRC2_ADDR is the second source address.
ORIG_SRC1 is the original first source block's address rtx.
ORIG_SRC2 is the original second source block's address rtx. */
static void
do_load_mask_compare (const machine_mode load_mode, rtx diff, rtx cmp_rem, rtx dcond,
rtx src1_addr, rtx src2_addr, rtx orig_src1, rtx orig_src2)
{
HOST_WIDE_INT load_mode_size = GET_MODE_SIZE (load_mode);
rtx shift_amount = gen_reg_rtx (word_mode);
rtx d1 = gen_reg_rtx (word_mode);
rtx d2 = gen_reg_rtx (word_mode);
do_load_for_compare_from_addr (load_mode, d1, src1_addr, orig_src1);
do_load_for_compare_from_addr (load_mode, d2, src2_addr, orig_src2);
do_sub3 (shift_amount, GEN_INT (load_mode_size), cmp_rem);
if (word_mode == DImode)
{
emit_insn (gen_ashldi3 (shift_amount, shift_amount,
GEN_INT (LOG2_BITS_PER_UNIT)));
emit_insn (gen_lshrdi3 (d1, d1,
gen_lowpart (SImode, shift_amount)));
emit_insn (gen_lshrdi3 (d2, d2,
gen_lowpart (SImode, shift_amount)));
}
else
{
emit_insn (gen_ashlsi3 (shift_amount, shift_amount,
GEN_INT (LOG2_BITS_PER_UNIT)));
emit_insn (gen_lshrsi3 (d1, d1, shift_amount));
emit_insn (gen_lshrsi3 (d2, d2, shift_amount));
}
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, d1, d2);
emit_insn (gen_rtx_SET (dcond, cmp));
}
else
{
if (word_mode == DImode)
emit_insn (gen_subfdi3_carry (diff, d2, d1));
else
emit_insn (gen_subfsi3_carry (diff, d2, d1));
}
}
/* Generate rtl for an overlapping load and compare of less than a
full load_mode. This assumes that the previous word is part of the
block being compared so it's ok to back up part of a word so we can
compare the last unaligned full word that ends at the end of the block.
LOAD_MODE is the machine mode for the loads.
ISCONST tells whether the remaining length is a constant or in a register.
BYTES_REM is the remaining length if ISCONST is true.
DIFF is the reg for the difference.
CMP_REM is the reg containing the remaining bytes to compare if !ISCONST.
DCOND is the CCUNS reg for the compare if we are doing P9 code with setb.
SRC1_ADDR is the first source address.
SRC2_ADDR is the second source address.
ORIG_SRC1 is the original first source block's address rtx.
ORIG_SRC2 is the original second source block's address rtx. */
static void
do_overlap_load_compare (machine_mode load_mode, bool isConst,
HOST_WIDE_INT bytes_rem, rtx diff,
rtx cmp_rem, rtx dcond, rtx src1_addr, rtx src2_addr,
rtx orig_src1, rtx orig_src2)
{
HOST_WIDE_INT load_mode_size = GET_MODE_SIZE (load_mode);
HOST_WIDE_INT addr_adj = load_mode_size - bytes_rem;
rtx d1 = gen_reg_rtx (word_mode);
rtx d2 = gen_reg_rtx (word_mode);
rtx addr1, addr2;
if (!isConst || addr_adj)
{
rtx adj_reg = gen_reg_rtx (word_mode);
if (isConst)
emit_move_insn (adj_reg, GEN_INT (-addr_adj));
else
{
rtx reg_lms = gen_reg_rtx (word_mode);
emit_move_insn (reg_lms, GEN_INT (load_mode_size));
do_sub3 (adj_reg, cmp_rem, reg_lms);
}
addr1 = gen_rtx_PLUS (word_mode, src1_addr, adj_reg);
addr2 = gen_rtx_PLUS (word_mode, src2_addr, adj_reg);
}
else
{
addr1 = src1_addr;
addr2 = src2_addr;
}
do_load_for_compare_from_addr (load_mode, d1, addr1, orig_src1);
do_load_for_compare_from_addr (load_mode, d2, addr2, orig_src2);
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, d1, d2);
emit_insn (gen_rtx_SET (dcond, cmp));
}
else
{
if (word_mode == DImode)
emit_insn (gen_subfdi3_carry (diff, d2, d1));
else
emit_insn (gen_subfsi3_carry (diff, d2, d1));
}
}
/* Generate the sequence of compares for strcmp/strncmp using vec/vsx
instructions.
BYTES_TO_COMPARE is the number of bytes to be compared.
ORIG_SRC1 is the unmodified rtx for the first string.
ORIG_SRC2 is the unmodified rtx for the second string.
S1ADDR is the register to use for the base address of the first string.
S2ADDR is the register to use for the base address of the second string.
OFF_REG is the register to use for the string offset for loads.
S1DATA is the register for loading the first string.
S2DATA is the register for loading the second string.
VEC_RESULT is the rtx for the vector result indicating the byte difference.
EQUALITY_COMPARE_REST is a flag to indicate we need to make a cleanup call
to strcmp/strncmp if we have equality at the end of the inline comparison.
P_CLEANUP_LABEL is a pointer to rtx for a label we generate if we need code
to clean up and generate the final comparison result.
FINAL_MOVE_LABEL is rtx for a label we can branch to when we can just
set the final result.
CHECKZERO indicates whether the sequence should check for zero bytes
for use doing strncmp, or not (for use doing memcmp). */
static void
expand_cmp_vec_sequence (unsigned HOST_WIDE_INT bytes_to_compare,
rtx orig_src1, rtx orig_src2,
rtx s1addr, rtx s2addr, rtx off_reg,
rtx s1data, rtx s2data, rtx vec_result,
bool equality_compare_rest, rtx *p_cleanup_label,
rtx final_move_label, bool checkzero)
{
machine_mode load_mode;
unsigned int load_mode_size;
unsigned HOST_WIDE_INT cmp_bytes = 0;
unsigned HOST_WIDE_INT offset = 0;
rtx zero_reg = NULL;
gcc_assert (p_cleanup_label != NULL);
rtx cleanup_label = *p_cleanup_label;
emit_move_insn (s1addr, force_reg (Pmode, XEXP (orig_src1, 0)));
emit_move_insn (s2addr, force_reg (Pmode, XEXP (orig_src2, 0)));
if (checkzero && !TARGET_P9_VECTOR)
{
zero_reg = gen_reg_rtx (V16QImode);
emit_move_insn (zero_reg, CONST0_RTX (V16QImode));
}
while (bytes_to_compare > 0)
{
/* VEC/VSX compare sequence for P8:
check each 16B with:
lxvd2x 32,28,8
lxvd2x 33,29,8
vcmpequb 2,0,1 # compare strings
vcmpequb 4,0,3 # compare w/ 0
xxlorc 37,36,34 # first FF byte is either mismatch or end of string
vcmpequb. 7,5,3 # reg 7 contains 0
bnl 6,.Lmismatch
For the P8 LE case, we use lxvd2x and compare full 16 bytes
but then use vgbbd and a shift to get two bytes with the
information we need in the correct order.
VEC/VSX compare sequence if TARGET_P9_VECTOR:
lxvb16x/lxvb16x # load 16B of each string
vcmpnezb. # produces difference location or zero byte location
bne 6,.Lmismatch
Use the overlapping compare trick for the last block if it is
less than 16 bytes.
*/
load_mode = V16QImode;
load_mode_size = GET_MODE_SIZE (load_mode);
if (bytes_to_compare >= load_mode_size)
cmp_bytes = load_mode_size;
else
{
/* Move this load back so it doesn't go past the end. P8/P9
can do this efficiently. This is never called with less
than 16 bytes so we should always be able to do this. */
unsigned int extra_bytes = load_mode_size - bytes_to_compare;
cmp_bytes = bytes_to_compare;
gcc_assert (offset > extra_bytes);
offset -= extra_bytes;
cmp_bytes = load_mode_size;
bytes_to_compare = cmp_bytes;
}
/* The offset currently used is always kept in off_reg so that the
cleanup code on P8 can use it to extract the differing byte. */
emit_move_insn (off_reg, GEN_INT (offset));
rtx addr1 = gen_rtx_PLUS (Pmode, s1addr, off_reg);
do_load_for_compare_from_addr (load_mode, s1data, addr1, orig_src1);
rtx addr2 = gen_rtx_PLUS (Pmode, s2addr, off_reg);
do_load_for_compare_from_addr (load_mode, s2data, addr2, orig_src2);
/* Cases to handle. A and B are chunks of the two strings.
1: Not end of comparison:
A != B: branch to cleanup code to compute result.
A == B: next block
2: End of the inline comparison:
A != B: branch to cleanup code to compute result.
A == B: call strcmp/strncmp
3: compared requested N bytes:
A == B: branch to result 0.
A != B: cleanup code to compute result. */
unsigned HOST_WIDE_INT remain = bytes_to_compare - cmp_bytes;
if (checkzero)
{
if (TARGET_P9_VECTOR)
emit_insn (gen_vcmpnezb_p (vec_result, s1data, s2data));
else
{
/* Emit instructions to do comparison and zero check. */
rtx cmp_res = gen_reg_rtx (load_mode);
rtx cmp_zero = gen_reg_rtx (load_mode);
rtx cmp_combined = gen_reg_rtx (load_mode);
emit_insn (gen_altivec_eqv16qi (cmp_res, s1data, s2data));
emit_insn (gen_altivec_eqv16qi (cmp_zero, s1data, zero_reg));
emit_insn (gen_orcv16qi3 (vec_result, cmp_zero, cmp_res));
emit_insn (gen_altivec_vcmpequb_p (cmp_combined, vec_result, zero_reg));
}
}
else
emit_insn (gen_altivec_vcmpequb_p (vec_result, s1data, s2data));
bool branch_to_cleanup = (remain > 0 || equality_compare_rest);
rtx cr6 = gen_rtx_REG (CCmode, CR6_REGNO);
rtx dst_label;
rtx cmp_rtx;
if (branch_to_cleanup)
{
/* Branch to cleanup code, otherwise fall through to do more
compares. P8 and P9 use different CR bits because on P8
we are looking at the result of a comparsion vs a
register of zeroes so the all-true condition means no
difference or zero was found. On P9, vcmpnezb sets a byte
to 0xff if there is a mismatch or zero, so the all-false
condition indicates we found no difference or zero. */
if (!cleanup_label)
cleanup_label = gen_label_rtx ();
dst_label = cleanup_label;
if (TARGET_P9_VECTOR && checkzero)
cmp_rtx = gen_rtx_NE (VOIDmode, cr6, const0_rtx);
else
cmp_rtx = gen_rtx_GE (VOIDmode, cr6, const0_rtx);
}
else
{
/* Branch to final return or fall through to cleanup,
result is already set to 0. */
dst_label = final_move_label;
if (TARGET_P9_VECTOR && checkzero)
cmp_rtx = gen_rtx_EQ (VOIDmode, cr6, const0_rtx);
else
cmp_rtx = gen_rtx_LT (VOIDmode, cr6, const0_rtx);
}
rtx lab_ref = gen_rtx_LABEL_REF (VOIDmode, dst_label);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx,
lab_ref, pc_rtx);
rtx_insn *j2 = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j2, profile_probability::likely ());
JUMP_LABEL (j2) = dst_label;
LABEL_NUSES (dst_label) += 1;
offset += cmp_bytes;
bytes_to_compare -= cmp_bytes;
}
*p_cleanup_label = cleanup_label;
return;
}
/* Generate the final sequence that identifies the differing
byte and generates the final result, taking into account
zero bytes:
P8:
vgbbd 0,0
vsldoi 0,0,0,9
mfvsrd 9,32
addi 10,9,-1 # count trailing zero bits
andc 9,10,9
popcntd 9,9
lbzx 10,28,9 # use that offset to load differing byte
lbzx 3,29,9
subf 3,3,10 # subtract for final result
P9:
vclzlsbb # counts trailing bytes with lsb=0
vextublx # extract differing byte
STR1 is the reg rtx for data from string 1.
STR2 is the reg rtx for data from string 2.
RESULT is the reg rtx for the comparison result.
S1ADDR is the register to use for the base address of the first string.
S2ADDR is the register to use for the base address of the second string.
ORIG_SRC1 is the unmodified rtx for the first string.
ORIG_SRC2 is the unmodified rtx for the second string.
OFF_REG is the register to use for the string offset for loads.
VEC_RESULT is the rtx for the vector result indicating the byte difference. */
static void
emit_final_compare_vec (rtx str1, rtx str2, rtx result,
rtx s1addr, rtx s2addr,
rtx orig_src1, rtx orig_src2,
rtx off_reg, rtx vec_result)
{
if (TARGET_P9_VECTOR)
{
rtx diffix = gen_reg_rtx (SImode);
rtx chr1 = gen_reg_rtx (SImode);
rtx chr2 = gen_reg_rtx (SImode);
rtx chr1_di = simplify_gen_subreg (DImode, chr1, SImode, 0);
rtx chr2_di = simplify_gen_subreg (DImode, chr2, SImode, 0);
emit_insn (gen_vclzlsbb_v16qi (diffix, vec_result));
emit_insn (gen_vextublx (chr1, diffix, str1));
emit_insn (gen_vextublx (chr2, diffix, str2));
do_sub3 (result, chr1_di, chr2_di);
}
else
{
gcc_assert (TARGET_P8_VECTOR);
rtx diffix = gen_reg_rtx (DImode);
rtx result_gbbd = gen_reg_rtx (V16QImode);
/* Since each byte of the input is either 00 or FF, the bytes in
dw0 and dw1 after vgbbd are all identical to each other. */
emit_insn (gen_p8v_vgbbd (result_gbbd, vec_result));
/* For LE, we shift by 9 and get BA in the low two bytes then CTZ.
For BE, we shift by 7 and get AB in the high two bytes then CLZ. */
rtx result_shifted = gen_reg_rtx (V16QImode);
int shift_amt = (BYTES_BIG_ENDIAN) ? 7 : 9;
emit_insn (gen_altivec_vsldoi_v16qi (result_shifted, result_gbbd,
result_gbbd, GEN_INT (shift_amt)));
rtx diffix_df = simplify_gen_subreg (DFmode, diffix, DImode, 0);
emit_insn (gen_p8_mfvsrd_3_v16qi (diffix_df, result_shifted));
rtx count = gen_reg_rtx (DImode);
if (BYTES_BIG_ENDIAN)
emit_insn (gen_clzdi2 (count, diffix));
else
emit_insn (gen_ctzdi2 (count, diffix));
/* P8 doesn't have a good solution for extracting one byte from
a vsx reg like vextublx on P9 so we just compute the offset
of the differing byte and load it from each string. */
do_add3 (off_reg, off_reg, count);
rtx chr1 = gen_reg_rtx (QImode);
rtx chr2 = gen_reg_rtx (QImode);
rtx addr1 = gen_rtx_PLUS (Pmode, s1addr, off_reg);
do_load_for_compare_from_addr (QImode, chr1, addr1, orig_src1);
rtx addr2 = gen_rtx_PLUS (Pmode, s2addr, off_reg);
do_load_for_compare_from_addr (QImode, chr2, addr2, orig_src2);
machine_mode rmode = GET_MODE (result);
rtx chr1_rm = simplify_gen_subreg (rmode, chr1, QImode, 0);
rtx chr2_rm = simplify_gen_subreg (rmode, chr2, QImode, 0);
do_sub3 (result, chr1_rm, chr2_rm);
}
return;
}
/* Expand a block compare operation using loop code, and return true
if successful. Return false if we should let the compiler generate
normal code, probably a memcmp call.
OPERANDS[0] is the target (result).
OPERANDS[1] is the first source.
OPERANDS[2] is the second source.
OPERANDS[3] is the length.
OPERANDS[4] is the alignment. */
bool
expand_compare_loop (rtx operands[])
{
rtx target = operands[0];
rtx orig_src1 = operands[1];
rtx orig_src2 = operands[2];
rtx bytes_rtx = operands[3];
rtx align_rtx = operands[4];
/* This case is complicated to handle because the subtract
with carry instructions do not generate the 64-bit
carry and so we must emit code to calculate it ourselves.
We choose not to implement this yet. */
if (TARGET_32BIT && TARGET_POWERPC64)
return false;
/* Allow non-const length. */
int bytes_is_const = CONST_INT_P (bytes_rtx);
/* This must be a fixed size alignment. */
if (!CONST_INT_P (align_rtx))
return false;
HOST_WIDE_INT align1 = MEM_ALIGN (orig_src1) / BITS_PER_UNIT;
HOST_WIDE_INT align2 = MEM_ALIGN (orig_src2) / BITS_PER_UNIT;
HOST_WIDE_INT minalign = MIN (align1, align2);
bool isP7 = (rs6000_tune == PROCESSOR_POWER7);
gcc_assert (GET_MODE (target) == SImode);
/* Anything to move? */
HOST_WIDE_INT bytes = 0;
if (bytes_is_const)
bytes = INTVAL (bytes_rtx);
if (bytes_is_const && bytes == 0)
return true;
/* Limit the amount we compare, if known statically. */
HOST_WIDE_INT max_bytes;
switch (rs6000_tune)
{
case PROCESSOR_POWER7:
if (!bytes_is_const)
if (minalign < 8)
max_bytes = 0;
else
max_bytes = 128;
else
if (minalign < 8)
max_bytes = 32;
else
max_bytes = 128;
break;
case PROCESSOR_POWER8:
if (!bytes_is_const)
max_bytes = 0;
else
if (minalign < 8)
max_bytes = 128;
else
max_bytes = 64;
break;
case PROCESSOR_POWER9:
case PROCESSOR_POWER10:
if (bytes_is_const)
max_bytes = 191;
else
max_bytes = 0;
break;
default:
max_bytes = 128;
}
/* Allow the option to override the default. */
if (rs6000_block_compare_inline_loop_limit >= 0)
max_bytes = (unsigned HOST_WIDE_INT) rs6000_block_compare_inline_loop_limit;
if (max_bytes == 0)
return false;
rtx cmp_rem = gen_reg_rtx (word_mode); /* Remainder for library call. */
rtx loop_cmp = gen_reg_rtx (word_mode); /* Actual amount compared by loop. */
HOST_WIDE_INT niter;
rtx iter = gen_reg_rtx (word_mode);
rtx iv1 = gen_reg_rtx (word_mode);
rtx iv2 = gen_reg_rtx (word_mode);
rtx d1_1 = gen_reg_rtx (word_mode); /* Addr expression src1+iv1 */
rtx d1_2 = gen_reg_rtx (word_mode); /* Addr expression src1+iv2 */
rtx d2_1 = gen_reg_rtx (word_mode); /* Addr expression src2+iv1 */
rtx d2_2 = gen_reg_rtx (word_mode); /* Addr expression src2+iv2 */
/* Strip unneeded subreg from length if there is one. */
if (SUBREG_P (bytes_rtx) && subreg_lowpart_p (bytes_rtx))
bytes_rtx = SUBREG_REG (bytes_rtx);
/* Extend bytes_rtx to word_mode if needed. But, we expect only to
maybe have to deal with the case were bytes_rtx is SImode and
word_mode is DImode. */
if (!bytes_is_const)
{
if (GET_MODE_SIZE (GET_MODE (bytes_rtx)) > GET_MODE_SIZE (word_mode))
/* Do not expect length longer than word_mode. */
return false;
else if (GET_MODE_SIZE (GET_MODE (bytes_rtx)) < GET_MODE_SIZE (word_mode))
{
bytes_rtx = force_reg (GET_MODE (bytes_rtx), bytes_rtx);
bytes_rtx = force_reg (word_mode,
gen_rtx_fmt_e (ZERO_EXTEND, word_mode,
bytes_rtx));
}
else
/* Make sure it's in a register before we get started. */
bytes_rtx = force_reg (GET_MODE (bytes_rtx), bytes_rtx);
}
machine_mode load_mode = word_mode;
HOST_WIDE_INT load_mode_size = GET_MODE_SIZE (load_mode);
/* Number of bytes per iteration of the unrolled loop. */
HOST_WIDE_INT loop_bytes = 2 * load_mode_size;
/* max iters and bytes compared in the loop. */
HOST_WIDE_INT max_loop_iter = max_bytes / loop_bytes;
HOST_WIDE_INT max_loop_bytes = max_loop_iter * loop_bytes;
int l2lb = floor_log2 (loop_bytes);
if (bytes_is_const && (max_bytes < load_mode_size
|| !IN_RANGE (bytes, load_mode_size, max_bytes)))
return false;
bool no_remainder_code = false;
rtx final_label = gen_label_rtx ();
rtx final_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
rtx diff_label = gen_label_rtx ();
rtx library_call_label = NULL;
rtx cleanup_label = gen_label_rtx ();
rtx cr;
rtx src1_addr = copy_addr_to_reg (XEXP (orig_src1, 0));
rtx src2_addr = copy_addr_to_reg (XEXP (orig_src2, 0));
/* Difference found is stored here before jump to diff_label. */
rtx diff = gen_reg_rtx (word_mode);
rtx_insn *j;
/* Example of generated code for 35 bytes aligned 1 byte.
mtctr 8
li 6,0
li 5,8
.L13:
ldbrx 7,3,6
ldbrx 9,10,6
ldbrx 0,3,5
ldbrx 4,10,5
addi 6,6,16
addi 5,5,16
subfc. 9,9,7
bne 0,.L10
subfc. 9,4,0
bdnzt 2,.L13
bne 0,.L10
add 3,3,6
add 10,10,6
addi 9,3,-5
ldbrx 7,0,9
addi 9,10,-5
ldbrx 9,0,9
subfc 9,9,7
.p2align 4,,15
.L10:
popcntd 9,9
subfe 10,10,10
or 9,9,10
Compiled with -fno-reorder-blocks for clarity. */
/* Structure of what we're going to do:
Two separate lengths: what we will compare before bailing to library
call (max_bytes), and the total length to be checked.
if length <= 16, branch to linear cleanup code starting with
remainder length check (length not known at compile time)
set up 2 iv's and load count reg, compute remainder length
unrollx2 compare loop
if loop exit due to a difference, branch to difference handling code
if remainder length < 8, branch to final cleanup compare
load and compare 8B
final cleanup comparison (depends on alignment and length)
load 8B, shift off bytes past length, compare
load 8B ending at last byte and compare
load/compare 1 byte at a time (short block abutting 4k boundary)
difference handling, 64->32 conversion
final result
branch around memcmp call
memcmp library call
*/
/* If bytes is not const, compare length and branch directly
to the cleanup code that can handle 0-16 bytes if length
is >= 16. Stash away bytes-max_bytes for the library call. */
if (bytes_is_const)
{
/* These need to be set for some of the places we may jump to. */
if (bytes > max_bytes)
{
no_remainder_code = true;
niter = max_loop_iter;
library_call_label = gen_label_rtx ();
}
else
{
niter = bytes / loop_bytes;
}
emit_move_insn (iter, GEN_INT (niter));
emit_move_insn (loop_cmp, GEN_INT (niter * loop_bytes));
emit_move_insn (cmp_rem, GEN_INT (bytes - niter * loop_bytes));
}
else
{
library_call_label = gen_label_rtx ();
/* If we go to the cleanup code, it expects length to be in cmp_rem. */
emit_move_insn (cmp_rem, bytes_rtx);
/* Check for > max_bytes bytes. We want to bail out as quickly as
possible if we have to go over to memcmp. */
do_ifelse (CCmode, GT, bytes_rtx, GEN_INT (max_bytes),
NULL_RTX, library_call_label, profile_probability::even ());
/* Check for < loop_bytes bytes. */
do_ifelse (CCmode, LT, bytes_rtx, GEN_INT (loop_bytes),
NULL_RTX, cleanup_label, profile_probability::even ());
/* Loop compare bytes and iterations if bytes>max_bytes. */
rtx mb_reg = gen_reg_rtx (word_mode);
emit_move_insn (mb_reg, GEN_INT (max_loop_bytes));
rtx mi_reg = gen_reg_rtx (word_mode);
emit_move_insn (mi_reg, GEN_INT (max_loop_iter));
/* Compute number of loop iterations if bytes <= max_bytes. */
if (word_mode == DImode)
emit_insn (gen_lshrdi3 (iter, bytes_rtx, GEN_INT (l2lb)));
else
emit_insn (gen_lshrsi3 (iter, bytes_rtx, GEN_INT (l2lb)));
/* Compute bytes to compare in loop if bytes <= max_bytes. */
rtx mask = GEN_INT (HOST_WIDE_INT_M1U << l2lb);
if (word_mode == DImode)
{
emit_insn (gen_anddi3 (loop_cmp, bytes_rtx, mask));
}
else
{
emit_insn (gen_andsi3 (loop_cmp, bytes_rtx, mask));
}
/* Check for bytes <= max_bytes. */
if (TARGET_ISEL)
{
/* P9 has fast isel so we use one compare and two isel. */
cr = gen_reg_rtx (CCmode);
rtx compare_rtx = gen_rtx_COMPARE (CCmode, bytes_rtx,
GEN_INT (max_bytes));
emit_move_insn (cr, compare_rtx);
rtx cmp_rtx = gen_rtx_LE (VOIDmode, cr, const0_rtx);
do_isel (loop_cmp, cmp_rtx, loop_cmp, mb_reg, cr);
do_isel (iter, cmp_rtx, iter, mi_reg, cr);
}
else
{
rtx lab_after = gen_label_rtx ();
do_ifelse (CCmode, LE, bytes_rtx, GEN_INT (max_bytes),
NULL_RTX, lab_after, profile_probability::even ());
emit_move_insn (loop_cmp, mb_reg);
emit_move_insn (iter, mi_reg);
emit_label (lab_after);
}
/* Now compute remainder bytes which isn't used until after the loop. */
do_sub3 (cmp_rem, bytes_rtx, loop_cmp);
}
rtx dcond = NULL_RTX; /* Used for when we jump to diff_label. */
/* For p9 we need to have just one of these as multiple places define
it and it gets used by the setb at the end. */
if (TARGET_P9_MISC)
dcond = gen_reg_rtx (CCUNSmode);
if (!bytes_is_const || bytes >= loop_bytes)
{
/* It should not be possible to come here if remaining bytes is
< 16 in the runtime case either. Compute number of loop
iterations. We compare 2*word_mode per iteration so 16B for
64-bit code and 8B for 32-bit. Set up two induction
variables and load count register. */
/* HACK ALERT: create hard reg for CTR here. If we just use a
pseudo, cse will get rid of it and then the allocator will
see it used in the lshr above and won't give us ctr. */
rtx ctr = gen_rtx_REG (Pmode, CTR_REGNO);
emit_move_insn (ctr, iter);
emit_move_insn (diff, GEN_INT (0));
emit_move_insn (iv1, GEN_INT (0));
emit_move_insn (iv2, GEN_INT (load_mode_size));
/* inner loop to compare 2*word_mode */
rtx loop_top_label = gen_label_rtx ();
emit_label (loop_top_label);
rtx src1_ix1 = gen_rtx_PLUS (word_mode, src1_addr, iv1);
rtx src2_ix1 = gen_rtx_PLUS (word_mode, src2_addr, iv1);
do_load_for_compare_from_addr (load_mode, d1_1,
src1_ix1, orig_src1);
do_load_for_compare_from_addr (load_mode, d2_1,
src2_ix1, orig_src2);
do_add3 (iv1, iv1, GEN_INT (loop_bytes));
rtx src1_ix2 = gen_rtx_PLUS (word_mode, src1_addr, iv2);
rtx src2_ix2 = gen_rtx_PLUS (word_mode, src2_addr, iv2);
do_load_for_compare_from_addr (load_mode, d1_2,
src1_ix2, orig_src1);
do_load_for_compare_from_addr (load_mode, d2_2,
src2_ix2, orig_src2);
do_add3 (iv2, iv2, GEN_INT (loop_bytes));
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, d1_1, d2_1);
emit_insn (gen_rtx_SET (dcond, cmp));
}
else
{
dcond = gen_reg_rtx (CCmode);
if (word_mode == DImode)
emit_insn (gen_subfdi3_carry_dot2 (diff, d2_1, d1_1, dcond));
else
emit_insn (gen_subfsi3_carry_dot2 (diff, d2_1, d1_1, dcond));
}
do_ifelse (GET_MODE (dcond), NE, NULL_RTX, NULL_RTX,
dcond, diff_label, profile_probability::unlikely ());
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, d1_2, d2_2);
emit_insn (gen_rtx_SET (dcond, cmp));
}
else
{
dcond = gen_reg_rtx (CCmode);
if (word_mode == DImode)
emit_insn (gen_subfdi3_carry_dot2 (diff, d2_2, d1_2, dcond));
else
emit_insn (gen_subfsi3_carry_dot2 (diff, d2_2, d1_2, dcond));
}
rtx eqrtx = gen_rtx_EQ (VOIDmode, d1_2, d2_2);
if (TARGET_64BIT)
j = emit_jump_insn (gen_bdnztf_di (loop_top_label, ctr, ctr,
eqrtx, dcond));
else
j = emit_jump_insn (gen_bdnztf_si (loop_top_label, ctr, ctr,
eqrtx, dcond));
add_reg_br_prob_note (j, profile_probability::likely ());
JUMP_LABEL (j) = loop_top_label;
LABEL_NUSES (loop_top_label) += 1;
}
HOST_WIDE_INT bytes_remaining = 0;
if (bytes_is_const)
bytes_remaining = (bytes % loop_bytes);
/* If diff is nonzero, branch to difference handling
code. If we exit here with a nonzero diff, it is
because the second word differed. */
if (TARGET_P9_MISC)
do_ifelse (CCUNSmode, NE, NULL_RTX, NULL_RTX, dcond,
diff_label, profile_probability::unlikely ());
else
do_ifelse (CCmode, NE, diff, const0_rtx, NULL_RTX,
diff_label, profile_probability::unlikely ());
if (library_call_label != NULL && bytes_is_const && bytes > max_bytes)
{
/* If the length is known at compile time, then we will always
have a remainder to go to the library call with. */
rtx library_call_ref = gen_rtx_LABEL_REF (VOIDmode, library_call_label);
j = emit_jump_insn (gen_rtx_SET (pc_rtx, library_call_ref));
JUMP_LABEL (j) = library_call_label;
LABEL_NUSES (library_call_label) += 1;
emit_barrier ();
}
if (bytes_is_const && bytes_remaining == 0)
{
/* No remainder and if we are here then diff is 0 so just return 0 */
if (TARGET_64BIT)
emit_insn (gen_movsi (target, gen_lowpart (SImode, diff)));
else
emit_move_insn (target, diff);
j = emit_jump_insn (gen_rtx_SET (pc_rtx, final_ref));
JUMP_LABEL (j) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
}
else if (!no_remainder_code)
{
/* Update addresses to point to the next word to examine. */
do_add3 (src1_addr, src1_addr, iv1);
do_add3 (src2_addr, src2_addr, iv1);
emit_label (cleanup_label);
if (!bytes_is_const)
{
/* If we're dealing with runtime length, we have to check if
it's zero after the loop. When length is known at compile
time the no-remainder condition is dealt with above. By
doing this after cleanup_label, we also deal with the
case where length is 0 at the start and we bypass the
loop with a branch to cleanup_label. */
emit_move_insn (target, const0_rtx);
do_ifelse (CCmode, EQ, cmp_rem, const0_rtx,
NULL_RTX, final_label, profile_probability::unlikely ());
}
rtx final_cleanup = gen_label_rtx ();
rtx cmp_rem_before = gen_reg_rtx (word_mode);
/* Compare one more word_mode chunk if needed. */
if (!bytes_is_const || bytes_remaining >= load_mode_size)
{
/* If remainder length < word length, branch to final
cleanup compare. */
if (!bytes_is_const)
{
do_ifelse (CCmode, LT, cmp_rem, GEN_INT (load_mode_size),
NULL_RTX, final_cleanup, profile_probability::even ());
}
/* load and compare 8B */
do_load_for_compare_from_addr (load_mode, d1_1,
src1_addr, orig_src1);
do_load_for_compare_from_addr (load_mode, d2_1,
src2_addr, orig_src2);
/* Compare the word, see if we need to do the last partial. */
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, d1_1, d2_1);
emit_insn (gen_rtx_SET (dcond, cmp));
}
else
{
dcond = gen_reg_rtx (CCmode);
if (word_mode == DImode)
emit_insn (gen_subfdi3_carry_dot2 (diff, d2_1, d1_1, dcond));
else
emit_insn (gen_subfsi3_carry_dot2 (diff, d2_1, d1_1, dcond));
}
do_ifelse (GET_MODE (dcond), NE, NULL_RTX, NULL_RTX,
dcond, diff_label, profile_probability::even ());
do_add3 (src1_addr, src1_addr, GEN_INT (load_mode_size));
do_add3 (src2_addr, src2_addr, GEN_INT (load_mode_size));
emit_move_insn (cmp_rem_before, cmp_rem);
do_add3 (cmp_rem, cmp_rem, GEN_INT (-load_mode_size));
if (bytes_is_const)
bytes_remaining -= load_mode_size;
else
/* See if remaining length is now zero. We previously set
target to 0 so we can just jump to the end. */
do_ifelse (CCmode, EQ, cmp_rem, const0_rtx, NULL_RTX,
final_label, profile_probability::unlikely ());
}
/* Cases:
bytes_is_const
We can always shift back to do an overlapping compare
of the last chunk because we know length >= 8.
!bytes_is_const
align>=load_mode_size
Read word_mode and mask
align<load_mode_size
avoid stepping past end
Three strategies:
* decrement address and do overlapping compare
* read word_mode and mask
* carefully avoid crossing 4k boundary
*/
if ((!bytes_is_const || (bytes_is_const && bytes_remaining && isP7))
&& align1 >= load_mode_size && align2 >= load_mode_size)
{
/* Alignment is larger than word_mode so we do not need to be
concerned with extra page crossings. But, we do not know
that the length is larger than load_mode_size so we might
end up compareing against data before the block if we try
an overlapping compare. Also we use this on P7 for fixed length
remainder because P7 doesn't like overlapping unaligned.
Strategy: load 8B, shift off bytes past length, and compare. */
emit_label (final_cleanup);
do_load_mask_compare (load_mode, diff, cmp_rem, dcond,
src1_addr, src2_addr, orig_src1, orig_src2);
}
else if (bytes_remaining && bytes_is_const)
{
/* We do not do loop expand if length < 32 so we know at the
end we can do an overlapping compare.
Strategy: shift address back and do word_mode load that
ends at the end of the block. */
emit_label (final_cleanup);
do_overlap_load_compare (load_mode, true, bytes_remaining, diff,
cmp_rem, dcond, src1_addr, src2_addr,
orig_src1, orig_src2);
}
else if (!bytes_is_const)
{
rtx handle4k_label = gen_label_rtx ();
rtx nonconst_overlap = gen_label_rtx ();
emit_label (nonconst_overlap);
/* Here we have to handle the case where whe have runtime
length which may be too short for overlap compare, and
alignment is not at least load_mode_size so we have to
tread carefully to avoid stepping across 4k boundaries. */
/* If the length after the loop was larger than word_mode
size, we can just do an overlapping compare and we're
done. We fall through to this code from the word_mode
compare that preceeds this. */
do_overlap_load_compare (load_mode, false, 0, diff,
cmp_rem, dcond, src1_addr, src2_addr,
orig_src1, orig_src2);
rtx diff_ref = gen_rtx_LABEL_REF (VOIDmode, diff_label);
j = emit_jump_insn (gen_rtx_SET (pc_rtx, diff_ref));
JUMP_LABEL (j) = diff_label;
LABEL_NUSES (diff_label) += 1;
emit_barrier ();
/* If we couldn't do the overlap compare we have to be more
careful of the 4k boundary. Test to see if either
address is less than word_mode_size away from a 4k
boundary. If not, then we can do a load/shift/compare
and we are done. We come to this code if length was less
than word_mode_size. */
emit_label (final_cleanup);
/* We can still avoid the slow case if the length was larger
than one loop iteration, in which case go do the overlap
load compare path. */
do_ifelse (CCmode, GT, bytes_rtx, GEN_INT (loop_bytes),
NULL_RTX, nonconst_overlap, profile_probability::even ());
rtx rem4k = gen_reg_rtx (word_mode);
rtx dist1 = gen_reg_rtx (word_mode);
rtx dist2 = gen_reg_rtx (word_mode);
do_sub3 (rem4k, GEN_INT (4096), cmp_rem);
if (word_mode == SImode)
emit_insn (gen_andsi3 (dist1, src1_addr, GEN_INT (0xfff)));
else
emit_insn (gen_anddi3 (dist1, src1_addr, GEN_INT (0xfff)));
do_ifelse (CCmode, LE, dist1, rem4k, NULL_RTX,
handle4k_label, profile_probability::very_unlikely ());
if (word_mode == SImode)
emit_insn (gen_andsi3 (dist2, src2_addr, GEN_INT (0xfff)));
else
emit_insn (gen_anddi3 (dist2, src2_addr, GEN_INT (0xfff)));
do_ifelse (CCmode, LE, dist2, rem4k, NULL_RTX,
handle4k_label, profile_probability::very_unlikely ());
/* We don't have a 4k boundary to deal with, so do
a load/shift/compare and jump to diff. */
do_load_mask_compare (load_mode, diff, cmp_rem, dcond,
src1_addr, src2_addr, orig_src1, orig_src2);
j = emit_jump_insn (gen_rtx_SET (pc_rtx, diff_ref));
JUMP_LABEL (j) = diff_label;
LABEL_NUSES (diff_label) += 1;
emit_barrier ();
/* Finally in the unlikely case we are inching up to a
4k boundary we use a compact lbzx/compare loop to do
it a byte at a time. */
emit_label (handle4k_label);
rtx ctr = gen_rtx_REG (Pmode, CTR_REGNO);
emit_move_insn (ctr, cmp_rem);
rtx ixreg = gen_reg_rtx (Pmode);
emit_move_insn (ixreg, const0_rtx);
rtx src1_ix = gen_rtx_PLUS (word_mode, src1_addr, ixreg);
rtx src2_ix = gen_rtx_PLUS (word_mode, src2_addr, ixreg);
rtx d1 = gen_reg_rtx (word_mode);
rtx d2 = gen_reg_rtx (word_mode);
rtx fc_loop = gen_label_rtx ();
emit_label (fc_loop);
do_load_for_compare_from_addr (QImode, d1, src1_ix, orig_src1);
do_load_for_compare_from_addr (QImode, d2, src2_ix, orig_src2);
do_add3 (ixreg, ixreg, const1_rtx);
rtx cond = gen_reg_rtx (CCmode);
rtx subexpr = gen_rtx_MINUS (word_mode, d1, d2);
rs6000_emit_dot_insn (diff, subexpr, 2, cond);
rtx eqrtx = gen_rtx_EQ (VOIDmode, d1, d2);
if (TARGET_64BIT)
j = emit_jump_insn (gen_bdnztf_di (fc_loop, ctr, ctr,
eqrtx, cond));
else
j = emit_jump_insn (gen_bdnztf_si (fc_loop, ctr, ctr,
eqrtx, cond));
add_reg_br_prob_note (j, profile_probability::likely ());
JUMP_LABEL (j) = fc_loop;
LABEL_NUSES (fc_loop) += 1;
if (TARGET_64BIT)
emit_insn (gen_movsi (target, gen_lowpart (SImode, diff)));
else
emit_move_insn (target, diff);
/* Since we are comparing bytes, the difference can be used
as the final result and we are done here. */
j = emit_jump_insn (gen_rtx_SET (pc_rtx, final_ref));
JUMP_LABEL (j) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
}
}
emit_label (diff_label);
/* difference handling, 64->32 conversion */
/* We need to produce DI result from sub, then convert to target SI
while maintaining <0 / ==0 / >0 properties. This sequence works:
subfc L,A,B
subfe H,H,H
popcntd L,L
rldimi L,H,6,0
This is an alternate one Segher cooked up if somebody
wants to expand this for something that doesn't have popcntd:
subfc L,a,b
subfe H,x,x
addic t,L,-1
subfe v,t,L
or z,v,H
And finally, p9 can just do this:
cmpld A,B
setb r */
if (TARGET_P9_MISC)
emit_insn (gen_setb_unsigned (target, dcond));
else
{
if (TARGET_64BIT)
{
rtx tmp_reg_ca = gen_reg_rtx (DImode);
emit_insn (gen_subfdi3_carry_in_xx (tmp_reg_ca));
emit_insn (gen_popcntddi2 (diff, diff));
emit_insn (gen_iordi3 (diff, diff, tmp_reg_ca));
emit_insn (gen_movsi (target, gen_lowpart (SImode, diff)));
}
else
{
rtx tmp_reg_ca = gen_reg_rtx (SImode);
emit_insn (gen_subfsi3_carry_in_xx (tmp_reg_ca));
emit_insn (gen_popcntdsi2 (diff, diff));
emit_insn (gen_iorsi3 (target, diff, tmp_reg_ca));
}
}
if (library_call_label != NULL)
{
/* Branch around memcmp call. */
j = emit_jump_insn (gen_rtx_SET (pc_rtx, final_ref));
JUMP_LABEL (j) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
/* Make memcmp library call. cmp_rem is the remaining bytes that
were compared and cmp_rem is the expected amount to be compared
by memcmp. If we don't find a difference in the loop compare, do
the library call directly instead of doing a small compare just
to get to an arbitrary boundary before calling it anyway.
Also, update addresses to point to the next word to examine. */
emit_label (library_call_label);
rtx len_rtx = gen_reg_rtx (word_mode);
if (bytes_is_const)
{
emit_move_insn (len_rtx, cmp_rem);
do_add3 (src1_addr, src1_addr, iv1);
do_add3 (src2_addr, src2_addr, iv1);
}
else
emit_move_insn (len_rtx, bytes_rtx);
tree fun = builtin_decl_explicit (BUILT_IN_MEMCMP);
emit_library_call_value (XEXP (DECL_RTL (fun), 0),
target, LCT_NORMAL, GET_MODE (target),
src1_addr, Pmode,
src2_addr, Pmode,
len_rtx, GET_MODE (len_rtx));
}
/* emit final_label */
emit_label (final_label);
return true;
}
/* Generate code to convert a DImode-plus-carry subtract result into
a SImode result that has the same <0 / ==0 / >0 properties to
produce the final result from memcmp.
TARGET is the rtx for the register to receive the memcmp result.
SUB_RESULT is the rtx for the register contining the subtract result. */
void
generate_6432_conversion(rtx target, rtx sub_result)
{
/* We need to produce DI result from sub, then convert to target SI
while maintaining <0 / ==0 / >0 properties. This sequence works:
subfc L,A,B
subfe H,H,H
popcntd L,L
rldimi L,H,6,0
This is an alternate one Segher cooked up if somebody
wants to expand this for something that doesn't have popcntd:
subfc L,a,b
subfe H,x,x
addic t,L,-1
subfe v,t,L
or z,v,H
And finally, p9 can just do this:
cmpld A,B
setb r */
if (TARGET_64BIT)
{
rtx tmp_reg_ca = gen_reg_rtx (DImode);
emit_insn (gen_subfdi3_carry_in_xx (tmp_reg_ca));
rtx popcnt = gen_reg_rtx (DImode);
emit_insn (gen_popcntddi2 (popcnt, sub_result));
rtx tmp2 = gen_reg_rtx (DImode);
emit_insn (gen_iordi3 (tmp2, popcnt, tmp_reg_ca));
emit_insn (gen_movsi (target, gen_lowpart (SImode, tmp2)));
}
else
{
rtx tmp_reg_ca = gen_reg_rtx (SImode);
emit_insn (gen_subfsi3_carry_in_xx (tmp_reg_ca));
rtx popcnt = gen_reg_rtx (SImode);
emit_insn (gen_popcntdsi2 (popcnt, sub_result));
emit_insn (gen_iorsi3 (target, popcnt, tmp_reg_ca));
}
}
/* Generate memcmp expansion using in-line non-loop GPR instructions.
The bool return indicates whether code for a 64->32 conversion
should be generated.
BYTES is the number of bytes to be compared.
BASE_ALIGN is the minimum alignment for both blocks to compare.
ORIG_SRC1 is the original pointer to the first block to compare.
ORIG_SRC2 is the original pointer to the second block to compare.
SUB_RESULT is the reg rtx for the result from the final subtract.
COND is rtx for a condition register that will be used for the final
compare on power9 or better.
FINAL_RESULT is the reg rtx for the final memcmp result.
P_CONVERT_LABEL is a pointer to rtx that will be used to store the
label generated for a branch to the 64->32 code, if such a branch
is needed.
P_FINAL_LABEL is a pointer to rtx that will be used to store the label
for the end of the memcmp if a branch there is needed.
*/
bool
expand_block_compare_gpr(unsigned HOST_WIDE_INT bytes, unsigned int base_align,
rtx orig_src1, rtx orig_src2,
rtx sub_result, rtx cond, rtx final_result,
rtx *p_convert_label, rtx *p_final_label)
{
/* Example of generated code for 18 bytes aligned 1 byte.
Compiled with -fno-reorder-blocks for clarity.
ldbrx 10,31,8
ldbrx 9,7,8
subfc. 9,9,10
bne 0,.L6487
addi 9,12,8
addi 5,11,8
ldbrx 10,0,9
ldbrx 9,0,5
subfc. 9,9,10
bne 0,.L6487
addi 9,12,16
lhbrx 10,0,9
addi 9,11,16
lhbrx 9,0,9
subf 9,9,10
b .L6488
.p2align 4,,15
.L6487: #convert_label
popcntd 9,9
subfe 10,10,10
or 9,9,10
.L6488: #final_label
extsw 10,9
We start off with DImode for two blocks that jump to the DI->SI conversion
if the difference is found there, then a final block of HImode that skips
the DI->SI conversion. */
unsigned HOST_WIDE_INT offset = 0;
unsigned int load_mode_size;
HOST_WIDE_INT cmp_bytes = 0;
rtx src1 = orig_src1;
rtx src2 = orig_src2;
rtx tmp_reg_src1 = gen_reg_rtx (word_mode);
rtx tmp_reg_src2 = gen_reg_rtx (word_mode);
bool need_6432_conv = false;
rtx convert_label = NULL;
rtx final_label = NULL;
machine_mode load_mode;
while (bytes > 0)
{
unsigned int align = compute_current_alignment (base_align, offset);
load_mode = select_block_compare_mode (offset, bytes, align);
load_mode_size = GET_MODE_SIZE (load_mode);
if (bytes >= load_mode_size)
cmp_bytes = load_mode_size;
else if (!targetm.slow_unaligned_access (load_mode,
align * BITS_PER_UNIT))
{
/* Move this load back so it doesn't go past the end.
P8/P9 can do this efficiently. */
unsigned int extra_bytes = load_mode_size - bytes;
cmp_bytes = bytes;
if (extra_bytes < offset)
{
offset -= extra_bytes;
cmp_bytes = load_mode_size;
bytes = cmp_bytes;
}
}
else
/* P7 and earlier can't do the overlapping load trick fast,
so this forces a non-overlapping load and a shift to get
rid of the extra bytes. */
cmp_bytes = bytes;
src1 = adjust_address (orig_src1, load_mode, offset);
src2 = adjust_address (orig_src2, load_mode, offset);
if (!REG_P (XEXP (src1, 0)))
{
rtx src1_reg = copy_addr_to_reg (XEXP (src1, 0));
src1 = replace_equiv_address (src1, src1_reg);
}
set_mem_size (src1, load_mode_size);
if (!REG_P (XEXP (src2, 0)))
{
rtx src2_reg = copy_addr_to_reg (XEXP (src2, 0));
src2 = replace_equiv_address (src2, src2_reg);
}
set_mem_size (src2, load_mode_size);
do_load_for_compare (tmp_reg_src1, src1, load_mode);
do_load_for_compare (tmp_reg_src2, src2, load_mode);
if (cmp_bytes < load_mode_size)
{
/* Shift unneeded bytes off. */
rtx sh = GEN_INT (BITS_PER_UNIT * (load_mode_size - cmp_bytes));
if (word_mode == DImode)
{
emit_insn (gen_lshrdi3 (tmp_reg_src1, tmp_reg_src1, sh));
emit_insn (gen_lshrdi3 (tmp_reg_src2, tmp_reg_src2, sh));
}
else
{
emit_insn (gen_lshrsi3 (tmp_reg_src1, tmp_reg_src1, sh));
emit_insn (gen_lshrsi3 (tmp_reg_src2, tmp_reg_src2, sh));
}
}
int remain = bytes - cmp_bytes;
if (GET_MODE_SIZE (GET_MODE (final_result)) > GET_MODE_SIZE (load_mode))
{
/* Final_result is larger than load size so we don't need to
reduce result size. */
/* We previously did a block that need 64->32 conversion but
the current block does not, so a label is needed to jump
to the end. */
if (need_6432_conv && !final_label)
final_label = gen_label_rtx ();
if (remain > 0)
{
/* This is not the last block, branch to the end if the result
of this subtract is not zero. */
if (!final_label)
final_label = gen_label_rtx ();
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
rtx tmp = gen_rtx_MINUS (word_mode, tmp_reg_src1, tmp_reg_src2);
rtx cr = gen_reg_rtx (CCmode);
rs6000_emit_dot_insn (tmp_reg_src2, tmp, 2, cr);
emit_insn (gen_movsi (final_result,
gen_lowpart (SImode, tmp_reg_src2)));
rtx ne_rtx = gen_rtx_NE (VOIDmode, cr, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, ne_rtx,
fin_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, profile_probability::unlikely ());
JUMP_LABEL (j) = final_label;
LABEL_NUSES (final_label) += 1;
}
else
{
if (word_mode == DImode)
{
emit_insn (gen_subdi3 (tmp_reg_src2, tmp_reg_src1,
tmp_reg_src2));
emit_insn (gen_movsi (final_result,
gen_lowpart (SImode, tmp_reg_src2)));
}
else
emit_insn (gen_subsi3 (final_result, tmp_reg_src1, tmp_reg_src2));
if (final_label)
{
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
rtx j = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
JUMP_LABEL (j) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
}
}
}
else
{
/* Do we need a 64->32 conversion block? We need the 64->32
conversion even if final_result size == load_mode size because
the subtract generates one extra bit. */
need_6432_conv = true;
if (remain > 0)
{
if (!convert_label)
convert_label = gen_label_rtx ();
/* Compare to zero and branch to convert_label if not zero. */
rtx cvt_ref = gen_rtx_LABEL_REF (VOIDmode, convert_label);
if (TARGET_P9_MISC)
{
/* Generate a compare, and convert with a setb later.
Use cond that is passed in because the caller needs
to use it for the 64->32 conversion later. */
rtx cmp = gen_rtx_COMPARE (CCUNSmode, tmp_reg_src1,
tmp_reg_src2);
emit_insn (gen_rtx_SET (cond, cmp));
}
else
{
/* Generate a subfc. and use the longer sequence for
conversion. Cond is not used outside this
function in this case. */
cond = gen_reg_rtx (CCmode);
if (TARGET_64BIT)
emit_insn (gen_subfdi3_carry_dot2 (sub_result, tmp_reg_src2,
tmp_reg_src1, cond));
else
emit_insn (gen_subfsi3_carry_dot2 (sub_result, tmp_reg_src2,
tmp_reg_src1, cond));
}
rtx ne_rtx = gen_rtx_NE (VOIDmode, cond, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, ne_rtx,
cvt_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, profile_probability::likely ());
JUMP_LABEL (j) = convert_label;
LABEL_NUSES (convert_label) += 1;
}
else
{
/* Just do the subtract/compare. Since this is the last block
the convert code will be generated immediately following. */
if (TARGET_P9_MISC)
{
rtx cmp = gen_rtx_COMPARE (CCUNSmode, tmp_reg_src1,
tmp_reg_src2);
emit_insn (gen_rtx_SET (cond, cmp));
}
else
if (TARGET_64BIT)
emit_insn (gen_subfdi3_carry (sub_result, tmp_reg_src2,
tmp_reg_src1));
else
emit_insn (gen_subfsi3_carry (sub_result, tmp_reg_src2,
tmp_reg_src1));
}
}
offset += cmp_bytes;
bytes -= cmp_bytes;
}
if (convert_label)
*p_convert_label = convert_label;
if (final_label)
*p_final_label = final_label;
return need_6432_conv;
}
/* Expand a block compare operation, and return true if successful.
Return false if we should let the compiler generate normal code,
probably a memcmp call.
OPERANDS[0] is the target (result).
OPERANDS[1] is the first source.
OPERANDS[2] is the second source.
OPERANDS[3] is the length.
OPERANDS[4] is the alignment. */
bool
expand_block_compare (rtx operands[])
{
rtx target = operands[0];
rtx orig_src1 = operands[1];
rtx orig_src2 = operands[2];
rtx bytes_rtx = operands[3];
rtx align_rtx = operands[4];
/* This case is complicated to handle because the subtract
with carry instructions do not generate the 64-bit
carry and so we must emit code to calculate it ourselves.
We choose not to implement this yet. */
if (TARGET_32BIT && TARGET_POWERPC64)
return false;
bool isP7 = (rs6000_tune == PROCESSOR_POWER7);
/* Allow this param to shut off all expansion. */
if (rs6000_block_compare_inline_limit == 0)
return false;
/* targetm.slow_unaligned_access -- don't do unaligned stuff.
However slow_unaligned_access returns true on P7 even though the
performance of this code is good there. */
if (!isP7
&& (targetm.slow_unaligned_access (word_mode, MEM_ALIGN (orig_src1))
|| targetm.slow_unaligned_access (word_mode, MEM_ALIGN (orig_src2))))
return false;
/* Unaligned l*brx traps on P7 so don't do this. However this should
not affect much because LE isn't really supported on P7 anyway. */
if (isP7 && !BYTES_BIG_ENDIAN)
return false;
/* If this is not a fixed size compare, try generating loop code and
if that fails just call memcmp. */
if (!CONST_INT_P (bytes_rtx))
return expand_compare_loop (operands);
/* This must be a fixed size alignment. */
if (!CONST_INT_P (align_rtx))
return false;
unsigned int align_by_bits = UINTVAL (align_rtx);
unsigned int base_align = align_by_bits / BITS_PER_UNIT;
gcc_assert (GET_MODE (target) == SImode);
/* Anything to move? */
unsigned HOST_WIDE_INT bytes = UINTVAL (bytes_rtx);
if (bytes == 0)
return true;
/* P7/P8 code uses cond for subfc. but P9 uses
it for cmpld which needs CCUNSmode. */
rtx cond = NULL;
if (TARGET_P9_MISC)
cond = gen_reg_rtx (CCUNSmode);
/* Is it OK to use vec/vsx for this. TARGET_VSX means we have at
least POWER7 but we use TARGET_EFFICIENT_UNALIGNED_VSX which is
at least POWER8. That way we can rely on overlapping compares to
do the final comparison of less than 16 bytes. Also I do not
want to deal with making this work for 32 bits. In addition, we
have to make sure that we have at least P8_VECTOR (we don't allow
P9_VECTOR without P8_VECTOR). */
int use_vec = (bytes >= 33 && !TARGET_32BIT
&& TARGET_EFFICIENT_UNALIGNED_VSX && TARGET_P8_VECTOR);
/* We don't want to generate too much code. The loop code can take
over for lengths greater than 31 bytes. */
unsigned HOST_WIDE_INT max_bytes = rs6000_block_compare_inline_limit;
/* Don't generate too much code if vsx was disabled. */
if (!use_vec && max_bytes > 1)
max_bytes = ((max_bytes + 1) / 2) - 1;
if (!IN_RANGE (bytes, 1, max_bytes))
return expand_compare_loop (operands);
/* The code generated for p7 and older is not faster than glibc
memcmp if alignment is small and length is not short, so bail
out to avoid those conditions. */
if (targetm.slow_unaligned_access (word_mode, align_by_bits)
&& ((base_align == 1 && bytes > 16)
|| (base_align == 2 && bytes > 32)))
return false;
rtx final_label = NULL;
if (use_vec)
{
rtx final_move_label = gen_label_rtx ();
rtx s1addr = gen_reg_rtx (Pmode);
rtx s2addr = gen_reg_rtx (Pmode);
rtx off_reg = gen_reg_rtx (Pmode);
rtx cleanup_label = NULL;
rtx vec_result = gen_reg_rtx (V16QImode);
rtx s1data = gen_reg_rtx (V16QImode);
rtx s2data = gen_reg_rtx (V16QImode);
rtx result_reg = gen_reg_rtx (word_mode);
emit_move_insn (result_reg, GEN_INT (0));
expand_cmp_vec_sequence (bytes, orig_src1, orig_src2,
s1addr, s2addr, off_reg, s1data, s2data,
vec_result, false,
&cleanup_label, final_move_label, false);
if (cleanup_label)
emit_label (cleanup_label);
emit_insn (gen_one_cmplv16qi2 (vec_result, vec_result));
emit_final_compare_vec (s1data, s2data, result_reg,
s1addr, s2addr, orig_src1, orig_src2,
off_reg, vec_result);
emit_label (final_move_label);
emit_insn (gen_movsi (target,
gen_lowpart (SImode, result_reg)));
}
else
{ /* generate GPR code */
rtx convert_label = NULL;
rtx sub_result = gen_reg_rtx (word_mode);
bool need_6432_conversion =
expand_block_compare_gpr(bytes, base_align,
orig_src1, orig_src2,
sub_result, cond, target,
&convert_label, &final_label);
if (need_6432_conversion)
{
if (convert_label)
emit_label (convert_label);
if (TARGET_P9_MISC)
emit_insn (gen_setb_unsigned (target, cond));
else
generate_6432_conversion(target, sub_result);
}
}
if (final_label)
emit_label (final_label);
return true;
}
/* Generate page crossing check and branch code to set up for
strncmp when we don't have DI alignment.
STRNCMP_LABEL is the label to branch if there is a page crossing.
SRC_ADDR is the string address to be examined.
BYTES is the max number of bytes to compare. */
static void
expand_strncmp_align_check (rtx strncmp_label, rtx src_addr, HOST_WIDE_INT bytes)
{
rtx lab_ref = gen_rtx_LABEL_REF (VOIDmode, strncmp_label);
rtx src_pgoff = gen_reg_rtx (GET_MODE (src_addr));
do_and3 (src_pgoff, src_addr, GEN_INT (0xfff));
rtx cond = gen_reg_rtx (CCmode);
emit_move_insn (cond, gen_rtx_COMPARE (CCmode, src_pgoff,
GEN_INT (4096 - bytes)));
rtx cmp_rtx = gen_rtx_GE (VOIDmode, cond, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx,
lab_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, profile_probability::unlikely ());
JUMP_LABEL (j) = strncmp_label;
LABEL_NUSES (strncmp_label) += 1;
}
/* Generate the sequence of compares for strcmp/strncmp using gpr instructions.
BYTES_TO_COMPARE is the number of bytes to be compared.
BASE_ALIGN is the smaller of the alignment of the two strings.
ORIG_SRC1 is the unmodified rtx for the first string.
ORIG_SRC2 is the unmodified rtx for the second string.
TMP_REG_SRC1 is the register for loading the first string.
TMP_REG_SRC2 is the register for loading the second string.
RESULT_REG is the rtx for the result register.
EQUALITY_COMPARE_REST is a flag to indicate we need to make a cleanup call
to strcmp/strncmp if we have equality at the end of the inline comparison.
P_CLEANUP_LABEL is a pointer to rtx for a label we generate if we need code
to clean up and generate the final comparison result.
FINAL_MOVE_LABEL is rtx for a label we can branch to when we can just
set the final result. */
static void
expand_strncmp_gpr_sequence (unsigned HOST_WIDE_INT bytes_to_compare,
unsigned int base_align,
rtx orig_src1, rtx orig_src2,
rtx tmp_reg_src1, rtx tmp_reg_src2, rtx result_reg,
bool equality_compare_rest, rtx *p_cleanup_label,
rtx final_move_label)
{
unsigned int word_mode_size = GET_MODE_SIZE (word_mode);
machine_mode load_mode;
unsigned int load_mode_size;
unsigned HOST_WIDE_INT cmp_bytes = 0;
unsigned HOST_WIDE_INT offset = 0;
rtx src1_addr = force_reg (Pmode, XEXP (orig_src1, 0));
rtx src2_addr = force_reg (Pmode, XEXP (orig_src2, 0));
gcc_assert (p_cleanup_label != NULL);
rtx cleanup_label = *p_cleanup_label;
while (bytes_to_compare > 0)
{
/* GPR compare sequence:
check each 8B with: ld/ld/cmpb/cmpb/orc./bne
cleanup code at end:
cntlzd get bit of first zero/diff byte
subfic convert for rldcl use
rldcl rldcl extract diff/zero byte
subf subtract for final result
The last compare can branch around the cleanup code if the
result is zero because the strings are exactly equal. */
unsigned int align = compute_current_alignment (base_align, offset);
load_mode = select_block_compare_mode (offset, bytes_to_compare, align);
load_mode_size = GET_MODE_SIZE (load_mode);
if (bytes_to_compare >= load_mode_size)
cmp_bytes = load_mode_size;
else if (!targetm.slow_unaligned_access (load_mode,
align * BITS_PER_UNIT))
{
/* Move this load back so it doesn't go past the end.
P8/P9 can do this efficiently. */
unsigned int extra_bytes = load_mode_size - bytes_to_compare;
cmp_bytes = bytes_to_compare;
if (extra_bytes < offset)
{
offset -= extra_bytes;
cmp_bytes = load_mode_size;
bytes_to_compare = cmp_bytes;
}
}
else
/* P7 and earlier can't do the overlapping load trick fast,
so this forces a non-overlapping load and a shift to get
rid of the extra bytes. */
cmp_bytes = bytes_to_compare;
rtx offset_rtx;
if (BYTES_BIG_ENDIAN || TARGET_AVOID_XFORM)
offset_rtx = GEN_INT (offset);
else
{
offset_rtx = gen_reg_rtx (Pmode);
emit_move_insn (offset_rtx, GEN_INT (offset));
}
rtx addr1 = gen_rtx_PLUS (Pmode, src1_addr, offset_rtx);
rtx addr2 = gen_rtx_PLUS (Pmode, src2_addr, offset_rtx);
do_load_for_compare_from_addr (load_mode, tmp_reg_src1, addr1, orig_src1);
do_load_for_compare_from_addr (load_mode, tmp_reg_src2, addr2, orig_src2);
/* We must always left-align the data we read, and
clear any bytes to the right that are beyond the string.
Otherwise the cmpb sequence won't produce the correct
results. However if there is only one byte left, we
can just subtract to get the final result so the shifts
and clears are not needed. */
unsigned HOST_WIDE_INT remain = bytes_to_compare - cmp_bytes;
/* Loading just a single byte is a special case. If we are
loading more than that, we have to check whether we are
looking at the entire chunk of data. If not, rotate left and
clear right so that bytes we aren't supposed to look at are
zeroed, and the first byte we are supposed to compare is
leftmost. */
if (load_mode_size != 1)
{
if (load_mode_size < word_mode_size)
{
/* Rotate left first. */
rtx sh = GEN_INT (BITS_PER_UNIT
* (word_mode_size - load_mode_size));
do_rotl3 (tmp_reg_src1, tmp_reg_src1, sh);
do_rotl3 (tmp_reg_src2, tmp_reg_src2, sh);
}
if (cmp_bytes < word_mode_size)
{
/* Now clear right. This plus the rotate can be
turned into a rldicr instruction. */
HOST_WIDE_INT mb = BITS_PER_UNIT * (word_mode_size - cmp_bytes);
rtx mask = GEN_INT (HOST_WIDE_INT_M1U << mb);
do_and3 (tmp_reg_src1, tmp_reg_src1, mask);
do_and3 (tmp_reg_src2, tmp_reg_src2, mask);
}
}
/* Cases to handle. A and B are chunks of the two strings.
1: Not end of comparison:
A != B: branch to cleanup code to compute result.
A == B: check for 0 byte, next block if not found.
2: End of the inline comparison:
A != B: branch to cleanup code to compute result.
A == B: check for 0 byte, call strcmp/strncmp
3: compared requested N bytes:
A == B: branch to result 0.
A != B: cleanup code to compute result. */
rtx dst_label;
if (remain > 0 || equality_compare_rest)
{
/* Branch to cleanup code, otherwise fall through to do
more compares. */
if (!cleanup_label)
cleanup_label = gen_label_rtx ();
dst_label = cleanup_label;
}
else
/* Branch to end and produce result of 0. */
dst_label = final_move_label;
if (load_mode_size == 1)
{
/* Special case for comparing just single byte. */
if (equality_compare_rest)
{
/* Use subf./bne to branch to final_move_label if the
byte differs, otherwise fall through to the strncmp
call. We must also check for a zero byte here as we
must not make the library call if this is the end of
the string. */
rtx lab_ref = gen_rtx_LABEL_REF (VOIDmode, final_move_label);
rtx cond = gen_reg_rtx (CCmode);
rtx diff_rtx = gen_rtx_MINUS (word_mode,
tmp_reg_src1, tmp_reg_src2);
rs6000_emit_dot_insn (result_reg, diff_rtx, 2, cond);
rtx cmp_rtx = gen_rtx_NE (VOIDmode, cond, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx,
lab_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, profile_probability::unlikely ());
JUMP_LABEL (j) = final_move_label;
LABEL_NUSES (final_move_label) += 1;
/* Check for zero byte here before fall through to
library call. This catches the case where the
strings are equal and end in a zero byte at this
position. */
rtx cond0 = gen_reg_rtx (CCmode);
emit_move_insn (cond0, gen_rtx_COMPARE (CCmode, tmp_reg_src1,
const0_rtx));
rtx cmp0eq_rtx = gen_rtx_EQ (VOIDmode, cond0, const0_rtx);
rtx ifelse0 = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp0eq_rtx,
lab_ref, pc_rtx);
rtx_insn *j0 = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse0));
add_reg_br_prob_note (j0, profile_probability::unlikely ());
JUMP_LABEL (j0) = final_move_label;
LABEL_NUSES (final_move_label) += 1;
}
else
{
/* This is the last byte to be compared so we can use
subf to compute the final result and branch
unconditionally to final_move_label. */
do_sub3 (result_reg, tmp_reg_src1, tmp_reg_src2);
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_move_label);
rtx j = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
JUMP_LABEL (j) = final_move_label;
LABEL_NUSES (final_move_label) += 1;
emit_barrier ();
}
}
else
{
rtx cmpb_zero = gen_reg_rtx (word_mode);
rtx cmpb_diff = gen_reg_rtx (word_mode);
rtx zero_reg = gen_reg_rtx (word_mode);
rtx lab_ref = gen_rtx_LABEL_REF (VOIDmode, dst_label);
rtx cond = gen_reg_rtx (CCmode);
emit_move_insn (zero_reg, GEN_INT (0));
do_cmpb3 (cmpb_diff, tmp_reg_src1, tmp_reg_src2);
do_cmpb3 (cmpb_zero, tmp_reg_src1, zero_reg);
rtx not_diff = gen_rtx_NOT (word_mode, cmpb_diff);
rtx orc_rtx = gen_rtx_IOR (word_mode, not_diff, cmpb_zero);
rs6000_emit_dot_insn (result_reg, orc_rtx, 2, cond);
rtx cmp_rtx;
if (remain == 0 && !equality_compare_rest)
cmp_rtx = gen_rtx_EQ (VOIDmode, cond, const0_rtx);
else
cmp_rtx = gen_rtx_NE (VOIDmode, cond, const0_rtx);
rtx ifelse = gen_rtx_IF_THEN_ELSE (VOIDmode, cmp_rtx,
lab_ref, pc_rtx);
rtx_insn *j = emit_jump_insn (gen_rtx_SET (pc_rtx, ifelse));
add_reg_br_prob_note (j, profile_probability::unlikely ());
JUMP_LABEL (j) = dst_label;
LABEL_NUSES (dst_label) += 1;
}
offset += cmp_bytes;
bytes_to_compare -= cmp_bytes;
}
*p_cleanup_label = cleanup_label;
return;
}
/* Generate the final sequence that identifies the differing
byte and generates the final result, taking into account
zero bytes:
cntlzd get bit of first zero/diff byte
addi convert for rldcl use
rldcl rldcl extract diff/zero byte
subf subtract for final result
STR1 is the reg rtx for data from string 1.
STR2 is the reg rtx for data from string 2.
RESULT is the reg rtx for the comparison result. */
static void
emit_final_str_compare_gpr (rtx str1, rtx str2, rtx result)
{
machine_mode m = GET_MODE (str1);
rtx rot_amt = gen_reg_rtx (m);
rtx rot1_1 = gen_reg_rtx (m);
rtx rot1_2 = gen_reg_rtx (m);
rtx rot2_1 = gen_reg_rtx (m);
rtx rot2_2 = gen_reg_rtx (m);
if (m == SImode)
{
emit_insn (gen_clzsi2 (rot_amt, result));
emit_insn (gen_addsi3 (rot_amt, rot_amt, GEN_INT (8)));
emit_insn (gen_rotlsi3 (rot1_1, str1,
gen_lowpart (SImode, rot_amt)));
emit_insn (gen_andsi3_mask (rot1_2, rot1_1, GEN_INT (0xff)));
emit_insn (gen_rotlsi3 (rot2_1, str2,
gen_lowpart (SImode, rot_amt)));
emit_insn (gen_andsi3_mask (rot2_2, rot2_1, GEN_INT (0xff)));
emit_insn (gen_subsi3 (result, rot1_2, rot2_2));
}
else if (m == DImode)
{
emit_insn (gen_clzdi2 (rot_amt, result));
emit_insn (gen_adddi3 (rot_amt, rot_amt, GEN_INT (8)));
emit_insn (gen_rotldi3 (rot1_1, str1,
gen_lowpart (SImode, rot_amt)));
emit_insn (gen_anddi3_mask (rot1_2, rot1_1, GEN_INT (0xff)));
emit_insn (gen_rotldi3 (rot2_1, str2,
gen_lowpart (SImode, rot_amt)));
emit_insn (gen_anddi3_mask (rot2_2, rot2_1, GEN_INT (0xff)));
emit_insn (gen_subdi3 (result, rot1_2, rot2_2));
}
else
gcc_unreachable ();
return;
}
/* Expand a string compare operation with length, and return
true if successful. Return false if we should let the
compiler generate normal code, probably a strncmp call.
OPERANDS[0] is the target (result).
OPERANDS[1] is the first source.
OPERANDS[2] is the second source.
If NO_LENGTH is zero, then:
OPERANDS[3] is the length.
OPERANDS[4] is the alignment in bytes.
If NO_LENGTH is nonzero, then:
OPERANDS[3] is the alignment in bytes. */
bool
expand_strn_compare (rtx operands[], int no_length)
{
rtx target = operands[0];
rtx orig_src1 = operands[1];
rtx orig_src2 = operands[2];
rtx bytes_rtx, align_rtx;
if (no_length)
{
bytes_rtx = NULL;
align_rtx = operands[3];
}
else
{
bytes_rtx = operands[3];
align_rtx = operands[4];
}
rtx src1_addr = force_reg (Pmode, XEXP (orig_src1, 0));
rtx src2_addr = force_reg (Pmode, XEXP (orig_src2, 0));
/* If we have a length, it must be constant. This simplifies things
a bit as we don't have to generate code to check if we've exceeded
the length. Later this could be expanded to handle this case. */
if (!no_length && !CONST_INT_P (bytes_rtx))
return false;
/* This must be a fixed size alignment. */
if (!CONST_INT_P (align_rtx))
return false;
unsigned int base_align = UINTVAL (align_rtx);
unsigned int align1 = MEM_ALIGN (orig_src1) / BITS_PER_UNIT;
unsigned int align2 = MEM_ALIGN (orig_src2) / BITS_PER_UNIT;
/* targetm.slow_unaligned_access -- don't do unaligned stuff. */
if (targetm.slow_unaligned_access (word_mode, align1)
|| targetm.slow_unaligned_access (word_mode, align2))
return false;
gcc_assert (GET_MODE (target) == SImode);
unsigned int required_align = 8;
unsigned HOST_WIDE_INT offset = 0;
unsigned HOST_WIDE_INT bytes; /* N from the strncmp args if available. */
unsigned HOST_WIDE_INT compare_length; /* How much to compare inline. */
if (no_length)
bytes = rs6000_string_compare_inline_limit;
else
bytes = UINTVAL (bytes_rtx);
/* Is it OK to use vec/vsx for this. TARGET_VSX means we have at
least POWER7 but we use TARGET_EFFICIENT_UNALIGNED_VSX which is
at least POWER8. That way we can rely on overlapping compares to
do the final comparison of less than 16 bytes. Also I do not
want to deal with making this work for 32 bits. In addition, we
have to make sure that we have at least P8_VECTOR (we don't allow
P9_VECTOR without P8_VECTOR). */
int use_vec = (bytes >= 16 && !TARGET_32BIT
&& TARGET_EFFICIENT_UNALIGNED_VSX && TARGET_P8_VECTOR);
if (use_vec)
required_align = 16;
machine_mode load_mode;
rtx tmp_reg_src1, tmp_reg_src2;
if (use_vec)
{
load_mode = V16QImode;
tmp_reg_src1 = gen_reg_rtx (V16QImode);
tmp_reg_src2 = gen_reg_rtx (V16QImode);
}
else
{
load_mode = select_block_compare_mode (0, bytes, base_align);
tmp_reg_src1 = gen_reg_rtx (word_mode);
tmp_reg_src2 = gen_reg_rtx (word_mode);
}
compare_length = rs6000_string_compare_inline_limit;
/* If we have equality at the end of the last compare and we have not
found the end of the string, we need to call strcmp/strncmp to
compare the remainder. */
bool equality_compare_rest = false;
if (no_length)
{
bytes = compare_length;
equality_compare_rest = true;
}
else
{
if (bytes <= compare_length)
compare_length = bytes;
else
equality_compare_rest = true;
}
rtx result_reg = gen_reg_rtx (word_mode);
rtx final_move_label = gen_label_rtx ();
rtx final_label = gen_label_rtx ();
rtx begin_compare_label = NULL;
if (base_align < required_align)
{
/* Generate code that checks distance to 4k boundary for this case. */
begin_compare_label = gen_label_rtx ();
rtx strncmp_label = gen_label_rtx ();
rtx jmp;
/* Strncmp for power8 in glibc does this:
rldicl r8,r3,0,52
cmpldi cr7,r8,4096-16
bgt cr7,L(pagecross) */
/* Make sure that the length we use for the alignment test and
the subsequent code generation are in agreement so we do not
go past the length we tested for a 4k boundary crossing. */
unsigned HOST_WIDE_INT align_test = compare_length;
if (align_test < required_align)
{
align_test = HOST_WIDE_INT_1U << ceil_log2 (align_test);
base_align = align_test;
}
else
{
align_test = ROUND_UP (align_test, required_align);
base_align = required_align;
}
if (align1 < required_align)
expand_strncmp_align_check (strncmp_label, src1_addr, align_test);
if (align2 < required_align)
expand_strncmp_align_check (strncmp_label, src2_addr, align_test);
/* Now generate the following sequence:
- branch to begin_compare
- strncmp_label
- call to strncmp
- branch to final_label
- begin_compare_label */
rtx cmp_ref = gen_rtx_LABEL_REF (VOIDmode, begin_compare_label);
jmp = emit_jump_insn (gen_rtx_SET (pc_rtx, cmp_ref));
JUMP_LABEL (jmp) = begin_compare_label;
LABEL_NUSES (begin_compare_label) += 1;
emit_barrier ();
emit_label (strncmp_label);
if (no_length)
{
tree fun = builtin_decl_explicit (BUILT_IN_STRCMP);
emit_library_call_value (XEXP (DECL_RTL (fun), 0),
target, LCT_NORMAL, GET_MODE (target),
force_reg (Pmode, src1_addr), Pmode,
force_reg (Pmode, src2_addr), Pmode);
}
else
{
/* -m32 -mpowerpc64 results in word_mode being DImode even
though otherwise it is 32-bit. The length arg to strncmp
is a size_t which will be the same size as pointers. */
rtx len_rtx = gen_reg_rtx (Pmode);
emit_move_insn (len_rtx, gen_int_mode (bytes, Pmode));
tree fun = builtin_decl_explicit (BUILT_IN_STRNCMP);
emit_library_call_value (XEXP (DECL_RTL (fun), 0),
target, LCT_NORMAL, GET_MODE (target),
force_reg (Pmode, src1_addr), Pmode,
force_reg (Pmode, src2_addr), Pmode,
len_rtx, Pmode);
}
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
jmp = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
JUMP_LABEL (jmp) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
emit_label (begin_compare_label);
}
rtx cleanup_label = NULL;
rtx s1addr = NULL, s2addr = NULL, off_reg = NULL, vec_result = NULL;
/* Generate a sequence of GPR or VEC/VSX instructions to compare out
to the length specified. */
if (use_vec)
{
s1addr = gen_reg_rtx (Pmode);
s2addr = gen_reg_rtx (Pmode);
off_reg = gen_reg_rtx (Pmode);
vec_result = gen_reg_rtx (load_mode);
emit_move_insn (result_reg, GEN_INT (0));
expand_cmp_vec_sequence (compare_length,
orig_src1, orig_src2,
s1addr, s2addr, off_reg,
tmp_reg_src1, tmp_reg_src2,
vec_result,
equality_compare_rest,
&cleanup_label, final_move_label, true);
}
else
expand_strncmp_gpr_sequence (compare_length, base_align,
orig_src1, orig_src2,
tmp_reg_src1, tmp_reg_src2,
result_reg,
equality_compare_rest,
&cleanup_label, final_move_label);
offset = compare_length;
if (equality_compare_rest)
{
/* Update pointers past what has been compared already. */
rtx src1 = force_reg (Pmode,
gen_rtx_PLUS (Pmode, src1_addr, GEN_INT (offset)));
rtx src2 = force_reg (Pmode,
gen_rtx_PLUS (Pmode, src2_addr, GEN_INT (offset)));
/* Construct call to strcmp/strncmp to compare the rest of the string. */
if (no_length)
{
tree fun = builtin_decl_explicit (BUILT_IN_STRCMP);
emit_library_call_value (XEXP (DECL_RTL (fun), 0),
target, LCT_NORMAL, GET_MODE (target),
src1, Pmode, src2, Pmode);
}
else
{
rtx len_rtx = gen_reg_rtx (Pmode);
emit_move_insn (len_rtx, gen_int_mode (bytes - compare_length, Pmode));
tree fun = builtin_decl_explicit (BUILT_IN_STRNCMP);
emit_library_call_value (XEXP (DECL_RTL (fun), 0),
target, LCT_NORMAL, GET_MODE (target),
src1, Pmode, src2, Pmode, len_rtx, Pmode);
}
rtx fin_ref = gen_rtx_LABEL_REF (VOIDmode, final_label);
rtx jmp = emit_jump_insn (gen_rtx_SET (pc_rtx, fin_ref));
JUMP_LABEL (jmp) = final_label;
LABEL_NUSES (final_label) += 1;
emit_barrier ();
}
if (cleanup_label)
emit_label (cleanup_label);
if (use_vec)
emit_final_compare_vec (tmp_reg_src1, tmp_reg_src2, result_reg,
s1addr, s2addr, orig_src1, orig_src2,
off_reg, vec_result);
else
emit_final_str_compare_gpr (tmp_reg_src1, tmp_reg_src2, result_reg);
emit_label (final_move_label);
emit_insn (gen_movsi (target,
gen_lowpart (SImode, result_reg)));
emit_label (final_label);
return true;
}
/* Generate loads and stores for a move of v4si mode using lvx/stvx.
This uses altivec_{l,st}vx_<mode>_internal which use unspecs to
keep combine from changing what instruction gets used.
DEST is the destination for the data.
SRC is the source of the data for the move. */
static rtx
gen_lvx_v4si_move (rtx dest, rtx src)
{
gcc_assert (MEM_P (dest) ^ MEM_P (src));
gcc_assert (GET_MODE (dest) == V4SImode && GET_MODE (src) == V4SImode);
if (MEM_P (dest))
return gen_altivec_stvx_v4si_internal (dest, src);
else
return gen_altivec_lvx_v4si_internal (dest, src);
}
static rtx
gen_lxvl_stxvl_move (rtx dest, rtx src, int length)
{
gcc_assert (MEM_P (dest) ^ MEM_P (src));
gcc_assert (GET_MODE (dest) == V16QImode && GET_MODE (src) == V16QImode);
gcc_assert (length <= 16);
bool is_store = MEM_P (dest);
rtx addr;
/* If the address form is not a simple register, make it so. */
if (is_store)
addr = XEXP (dest, 0);
else
addr = XEXP (src, 0);
if (!REG_P (addr))
addr = force_reg (Pmode, addr);
rtx len = force_reg (DImode, gen_int_mode (length, DImode));
if (is_store)
return gen_stxvl (src, addr, len);
else
return gen_lxvl (dest, addr, len);
}
/* Expand a block move operation, and return 1 if successful. Return 0
if we should let the compiler generate normal code.
operands[0] is the destination
operands[1] is the source
operands[2] is the length
operands[3] is the alignment */
#define MAX_MOVE_REG 4
int
expand_block_move (rtx operands[], bool might_overlap)
{
rtx orig_dest = operands[0];
rtx orig_src = operands[1];
rtx bytes_rtx = operands[2];
rtx align_rtx = operands[3];
int constp = CONST_INT_P (bytes_rtx);
int align;
int bytes;
int offset;
int move_bytes;
rtx loads[MAX_MOVE_REG];
rtx stores[MAX_MOVE_REG];
int num_reg = 0;
/* If this is not a fixed size move, just call memcpy */
if (! constp)
return 0;
/* This must be a fixed size alignment */
gcc_assert (CONST_INT_P (align_rtx));
align = INTVAL (align_rtx) * BITS_PER_UNIT;
/* Anything to move? */
bytes = INTVAL (bytes_rtx);
if (bytes <= 0)
return 1;
if (bytes > rs6000_block_move_inline_limit)
return 0;
int orig_bytes = bytes;
for (offset = 0; bytes > 0; offset += move_bytes, bytes -= move_bytes)
{
union {
rtx (*mov) (rtx, rtx);
rtx (*movlen) (rtx, rtx, int);
} gen_func;
machine_mode mode = BLKmode;
rtx src, dest;
bool move_with_length = false;
/* Use OOmode for paired vsx load/store. Use V2DI for single
unaligned vsx load/store, for consistency with what other
expansions (compare) already do, and so we can use lxvd2x on
p8. Order is VSX pair unaligned, VSX unaligned, Altivec, VSX
with length < 16 (if allowed), then gpr load/store. */
if (TARGET_MMA && TARGET_BLOCK_OPS_UNALIGNED_VSX
&& TARGET_BLOCK_OPS_VECTOR_PAIR
&& bytes >= 32
&& (align >= 256 || !STRICT_ALIGNMENT))
{
move_bytes = 32;
mode = OOmode;
gen_func.mov = gen_movoo;
}
else if (TARGET_POWERPC64 && TARGET_BLOCK_OPS_UNALIGNED_VSX
&& VECTOR_MEM_VSX_P (V2DImode)
&& bytes >= 16 && (align >= 128 || !STRICT_ALIGNMENT))
{
move_bytes = 16;
mode = V2DImode;
gen_func.mov = gen_vsx_movv2di_64bit;
}
else if (TARGET_BLOCK_OPS_UNALIGNED_VSX
/* Only use lxvl/stxvl on 64bit POWER10. */
&& TARGET_POWER10
&& TARGET_64BIT
&& bytes < 16
&& orig_bytes > 16
&& !(bytes == 1
|| bytes == 2
|| bytes == 4
|| bytes == 8)
&& (align >= 128
|| !STRICT_ALIGNMENT))
{
/* Only use lxvl/stxvl if it could replace multiple ordinary
loads+stores. Also don't use it unless we likely already
did one vsx copy so we aren't mixing gpr and vsx. */
move_bytes = bytes;
mode = V16QImode;
gen_func.movlen = gen_lxvl_stxvl_move;
move_with_length = true;
}
else if (TARGET_ALTIVEC && bytes >= 16 && align >= 128)
{
move_bytes = 16;
mode = V4SImode;
gen_func.mov = gen_lvx_v4si_move;
}
else if (bytes >= 8 && TARGET_POWERPC64
&& (align >= 64 || !STRICT_ALIGNMENT))
{
move_bytes = 8;
mode = DImode;
gen_func.mov = gen_movdi;
if (offset == 0 && align < 64)
{
rtx addr;
/* If the address form is reg+offset with offset not a
multiple of four, reload into reg indirect form here
rather than waiting for reload. This way we get one
reload, not one per load and/or store. */
addr = XEXP (orig_dest, 0);
if ((GET_CODE (addr) == PLUS || GET_CODE (addr) == LO_SUM)
&& CONST_INT_P (XEXP (addr, 1))
&& (INTVAL (XEXP (addr, 1)) & 3) != 0)
{
addr = copy_addr_to_reg (addr);
orig_dest = replace_equiv_address (orig_dest, addr);
}
addr = XEXP (orig_src, 0);
if ((GET_CODE (addr) == PLUS || GET_CODE (addr) == LO_SUM)
&& CONST_INT_P (XEXP (addr, 1))
&& (INTVAL (XEXP (addr, 1)) & 3) != 0)
{
addr = copy_addr_to_reg (addr);
orig_src = replace_equiv_address (orig_src, addr);
}
}
}
else if (bytes >= 4 && (align >= 32 || !STRICT_ALIGNMENT))
{ /* move 4 bytes */
move_bytes = 4;
mode = SImode;
gen_func.mov = gen_movsi;
}
else if (bytes >= 2 && (align >= 16 || !STRICT_ALIGNMENT))
{ /* move 2 bytes */
move_bytes = 2;
mode = HImode;
gen_func.mov = gen_movhi;
}
else /* move 1 byte at a time */
{
move_bytes = 1;
mode = QImode;
gen_func.mov = gen_movqi;
}
/* If we can't succeed in doing the move in one pass, we can't
do it in the might_overlap case. Bail out and return
failure. We test num_reg + 1 >= MAX_MOVE_REG here to check
the same condition as the test of num_reg >= MAX_MOVE_REG
that is done below after the increment of num_reg. */
if (might_overlap && num_reg + 1 >= MAX_MOVE_REG
&& bytes > move_bytes)
return 0;
/* Mode is always set to something other than BLKmode by one of the
cases of the if statement above. */
gcc_assert (mode != BLKmode);
src = adjust_address (orig_src, mode, offset);
dest = adjust_address (orig_dest, mode, offset);
rtx tmp_reg = gen_reg_rtx (mode);
if (move_with_length)
{
loads[num_reg] = (*gen_func.movlen) (tmp_reg, src, move_bytes);
stores[num_reg++] = (*gen_func.movlen) (dest, tmp_reg, move_bytes);
}
else
{
loads[num_reg] = (*gen_func.mov) (tmp_reg, src);
stores[num_reg++] = (*gen_func.mov) (dest, tmp_reg);
}
/* Emit loads and stores saved up. */
if (num_reg >= MAX_MOVE_REG || bytes == move_bytes)
{
int i;
for (i = 0; i < num_reg; i++)
emit_insn (loads[i]);
for (i = 0; i < num_reg; i++)
emit_insn (stores[i]);
num_reg = 0;
}
}
return 1;
}
|