summaryrefslogtreecommitdiff
path: root/gcc/tree-vect-data-refs.c
blob: 9c6ca77e3ce68f74d8e2937eaa13fad6d2d7883e (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
/* Data References Analysis and Manipulation Utilities for Vectorization.
   Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
   Free Software Foundation, Inc.
   Contributed by Dorit Naishlos <dorit@il.ibm.com>
   and Ira Rosen <irar@il.ibm.com>

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/>.  */

#include "config.h"
#include "system.h"
#include "coretypes.h"
#include "tm.h"
#include "ggc.h"
#include "tree.h"
#include "tm_p.h"
#include "target.h"
#include "basic-block.h"
#include "tree-pretty-print.h"
#include "gimple-pretty-print.h"
#include "tree-flow.h"
#include "tree-dump.h"
#include "cfgloop.h"
#include "tree-chrec.h"
#include "tree-scalar-evolution.h"
#include "tree-vectorizer.h"
#include "diagnostic-core.h"

/* Need to include rtl.h, expr.h, etc. for optabs.  */
#include "expr.h"
#include "optabs.h"

/* Return the smallest scalar part of STMT.
   This is used to determine the vectype of the stmt.  We generally set the
   vectype according to the type of the result (lhs).  For stmts whose
   result-type is different than the type of the arguments (e.g., demotion,
   promotion), vectype will be reset appropriately (later).  Note that we have
   to visit the smallest datatype in this function, because that determines the
   VF.  If the smallest datatype in the loop is present only as the rhs of a
   promotion operation - we'd miss it.
   Such a case, where a variable of this datatype does not appear in the lhs
   anywhere in the loop, can only occur if it's an invariant: e.g.:
   'int_x = (int) short_inv', which we'd expect to have been optimized away by
   invariant motion.  However, we cannot rely on invariant motion to always
   take invariants out of the loop, and so in the case of promotion we also
   have to check the rhs.
   LHS_SIZE_UNIT and RHS_SIZE_UNIT contain the sizes of the corresponding
   types.  */

tree
vect_get_smallest_scalar_type (gimple stmt, HOST_WIDE_INT *lhs_size_unit,
                               HOST_WIDE_INT *rhs_size_unit)
{
  tree scalar_type = gimple_expr_type (stmt);
  HOST_WIDE_INT lhs, rhs;

  lhs = rhs = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (scalar_type));

  if (is_gimple_assign (stmt)
      && (gimple_assign_cast_p (stmt)
          || gimple_assign_rhs_code (stmt) == WIDEN_MULT_EXPR
          || gimple_assign_rhs_code (stmt) == FLOAT_EXPR))
    {
      tree rhs_type = TREE_TYPE (gimple_assign_rhs1 (stmt));

      rhs = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (rhs_type));
      if (rhs < lhs)
        scalar_type = rhs_type;
    }

  *lhs_size_unit = lhs;
  *rhs_size_unit = rhs;
  return scalar_type;
}


/* Find the place of the data-ref in STMT in the interleaving chain that starts
   from FIRST_STMT.  Return -1 if the data-ref is not a part of the chain.  */

int
vect_get_place_in_interleaving_chain (gimple stmt, gimple first_stmt)
{
  gimple next_stmt = first_stmt;
  int result = 0;

  if (first_stmt != DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)))
    return -1;

  while (next_stmt && next_stmt != stmt)
    {
      result++;
      next_stmt = DR_GROUP_NEXT_DR (vinfo_for_stmt (next_stmt));
    }

  if (next_stmt)
    return result;
  else
    return -1;
}


/* Function vect_insert_into_interleaving_chain.

   Insert DRA into the interleaving chain of DRB according to DRA's INIT.  */

static void
vect_insert_into_interleaving_chain (struct data_reference *dra,
				     struct data_reference *drb)
{
  gimple prev, next;
  tree next_init;
  stmt_vec_info stmtinfo_a = vinfo_for_stmt (DR_STMT (dra));
  stmt_vec_info stmtinfo_b = vinfo_for_stmt (DR_STMT (drb));

  prev = DR_GROUP_FIRST_DR (stmtinfo_b);
  next = DR_GROUP_NEXT_DR (vinfo_for_stmt (prev));
  while (next)
    {
      next_init = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (next)));
      if (tree_int_cst_compare (next_init, DR_INIT (dra)) > 0)
	{
	  /* Insert here.  */
	  DR_GROUP_NEXT_DR (vinfo_for_stmt (prev)) = DR_STMT (dra);
	  DR_GROUP_NEXT_DR (stmtinfo_a) = next;
	  return;
	}
      prev = next;
      next = DR_GROUP_NEXT_DR (vinfo_for_stmt (prev));
    }

  /* We got to the end of the list. Insert here.  */
  DR_GROUP_NEXT_DR (vinfo_for_stmt (prev)) = DR_STMT (dra);
  DR_GROUP_NEXT_DR (stmtinfo_a) = NULL;
}


/* Function vect_update_interleaving_chain.

   For two data-refs DRA and DRB that are a part of a chain interleaved data
   accesses, update the interleaving chain.  DRB's INIT is smaller than DRA's.

   There are four possible cases:
   1. New stmts - both DRA and DRB are not a part of any chain:
      FIRST_DR = DRB
      NEXT_DR (DRB) = DRA
   2. DRB is a part of a chain and DRA is not:
      no need to update FIRST_DR
      no need to insert DRB
      insert DRA according to init
   3. DRA is a part of a chain and DRB is not:
      if (init of FIRST_DR > init of DRB)
          FIRST_DR = DRB
	  NEXT(FIRST_DR) = previous FIRST_DR
      else
          insert DRB according to its init
   4. both DRA and DRB are in some interleaving chains:
      choose the chain with the smallest init of FIRST_DR
      insert the nodes of the second chain into the first one.  */

static void
vect_update_interleaving_chain (struct data_reference *drb,
				struct data_reference *dra)
{
  stmt_vec_info stmtinfo_a = vinfo_for_stmt (DR_STMT (dra));
  stmt_vec_info stmtinfo_b = vinfo_for_stmt (DR_STMT (drb));
  tree next_init, init_dra_chain, init_drb_chain;
  gimple first_a, first_b;
  tree node_init;
  gimple node, prev, next, first_stmt;

  /* 1. New stmts - both DRA and DRB are not a part of any chain.   */
  if (!DR_GROUP_FIRST_DR (stmtinfo_a) && !DR_GROUP_FIRST_DR (stmtinfo_b))
    {
      DR_GROUP_FIRST_DR (stmtinfo_a) = DR_STMT (drb);
      DR_GROUP_FIRST_DR (stmtinfo_b) = DR_STMT (drb);
      DR_GROUP_NEXT_DR (stmtinfo_b) = DR_STMT (dra);
      return;
    }

  /* 2. DRB is a part of a chain and DRA is not.  */
  if (!DR_GROUP_FIRST_DR (stmtinfo_a) && DR_GROUP_FIRST_DR (stmtinfo_b))
    {
      DR_GROUP_FIRST_DR (stmtinfo_a) = DR_GROUP_FIRST_DR (stmtinfo_b);
      /* Insert DRA into the chain of DRB.  */
      vect_insert_into_interleaving_chain (dra, drb);
      return;
    }

  /* 3. DRA is a part of a chain and DRB is not.  */
  if (DR_GROUP_FIRST_DR (stmtinfo_a) && !DR_GROUP_FIRST_DR (stmtinfo_b))
    {
      gimple old_first_stmt = DR_GROUP_FIRST_DR (stmtinfo_a);
      tree init_old = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (
							      old_first_stmt)));
      gimple tmp;

      if (tree_int_cst_compare (init_old, DR_INIT (drb)) > 0)
	{
	  /* DRB's init is smaller than the init of the stmt previously marked
	     as the first stmt of the interleaving chain of DRA.  Therefore, we
	     update FIRST_STMT and put DRB in the head of the list.  */
	  DR_GROUP_FIRST_DR (stmtinfo_b) = DR_STMT (drb);
	  DR_GROUP_NEXT_DR (stmtinfo_b) = old_first_stmt;

	  /* Update all the stmts in the list to point to the new FIRST_STMT.  */
	  tmp = old_first_stmt;
	  while (tmp)
	    {
	      DR_GROUP_FIRST_DR (vinfo_for_stmt (tmp)) = DR_STMT (drb);
	      tmp = DR_GROUP_NEXT_DR (vinfo_for_stmt (tmp));
	    }
	}
      else
	{
	  /* Insert DRB in the list of DRA.  */
	  vect_insert_into_interleaving_chain (drb, dra);
	  DR_GROUP_FIRST_DR (stmtinfo_b) = DR_GROUP_FIRST_DR (stmtinfo_a);
	}
      return;
    }

  /* 4. both DRA and DRB are in some interleaving chains.  */
  first_a = DR_GROUP_FIRST_DR (stmtinfo_a);
  first_b = DR_GROUP_FIRST_DR (stmtinfo_b);
  if (first_a == first_b)
    return;
  init_dra_chain = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (first_a)));
  init_drb_chain = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (first_b)));

  if (tree_int_cst_compare (init_dra_chain, init_drb_chain) > 0)
    {
      /* Insert the nodes of DRA chain into the DRB chain.
	 After inserting a node, continue from this node of the DRB chain (don't
         start from the beginning.  */
      node = DR_GROUP_FIRST_DR (stmtinfo_a);
      prev = DR_GROUP_FIRST_DR (stmtinfo_b);
      first_stmt = first_b;
    }
  else
    {
      /* Insert the nodes of DRB chain into the DRA chain.
	 After inserting a node, continue from this node of the DRA chain (don't
         start from the beginning.  */
      node = DR_GROUP_FIRST_DR (stmtinfo_b);
      prev = DR_GROUP_FIRST_DR (stmtinfo_a);
      first_stmt = first_a;
    }

  while (node)
    {
      node_init = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (node)));
      next = DR_GROUP_NEXT_DR (vinfo_for_stmt (prev));
      while (next)
	{
	  next_init = DR_INIT (STMT_VINFO_DATA_REF (vinfo_for_stmt (next)));
	  if (tree_int_cst_compare (next_init, node_init) > 0)
	    {
	      /* Insert here.  */
	      DR_GROUP_NEXT_DR (vinfo_for_stmt (prev)) = node;
	      DR_GROUP_NEXT_DR (vinfo_for_stmt (node)) = next;
	      prev = node;
	      break;
	    }
	  prev = next;
	  next = DR_GROUP_NEXT_DR (vinfo_for_stmt (prev));
	}
      if (!next)
	{
	  /* We got to the end of the list. Insert here.  */
	  DR_GROUP_NEXT_DR (vinfo_for_stmt (prev)) = node;
	  DR_GROUP_NEXT_DR (vinfo_for_stmt (node)) = NULL;
	  prev = node;
	}
      DR_GROUP_FIRST_DR (vinfo_for_stmt (node)) = first_stmt;
      node = DR_GROUP_NEXT_DR (vinfo_for_stmt (node));
    }
}


/* Function vect_equal_offsets.

   Check if OFFSET1 and OFFSET2 are identical expressions.  */

static bool
vect_equal_offsets (tree offset1, tree offset2)
{
  bool res;

  STRIP_NOPS (offset1);
  STRIP_NOPS (offset2);

  if (offset1 == offset2)
    return true;

  if (TREE_CODE (offset1) != TREE_CODE (offset2)
      || (!BINARY_CLASS_P (offset1) && !UNARY_CLASS_P (offset1)))
    return false;

  res = vect_equal_offsets (TREE_OPERAND (offset1, 0),
			    TREE_OPERAND (offset2, 0));

  if (!res || !BINARY_CLASS_P (offset1))
    return res;

  res = vect_equal_offsets (TREE_OPERAND (offset1, 1),
			    TREE_OPERAND (offset2, 1));

  return res;
}


/* Check dependence between DRA and DRB for basic block vectorization.
   If the accesses share same bases and offsets, we can compare their initial
   constant offsets to decide whether they differ or not.  In case of a read-
   write dependence we check that the load is before the store to ensure that
   vectorization will not change the order of the accesses.  */

static bool
vect_drs_dependent_in_basic_block (struct data_reference *dra,
                                   struct data_reference *drb)
{
  HOST_WIDE_INT type_size_a, type_size_b, init_a, init_b;
  gimple earlier_stmt;

  /* We only call this function for pairs of loads and stores, but we verify
     it here.  */
  if (DR_IS_READ (dra) == DR_IS_READ (drb))
    {
      if (DR_IS_READ (dra))
        return false;
      else
        return true;
    }

  /* Check that the data-refs have same bases and offsets.  If not, we can't
     determine if they are dependent.  */
  if ((DR_BASE_ADDRESS (dra) != DR_BASE_ADDRESS (drb)
       && (TREE_CODE (DR_BASE_ADDRESS (dra)) != ADDR_EXPR
           || TREE_CODE (DR_BASE_ADDRESS (drb)) != ADDR_EXPR
           || TREE_OPERAND (DR_BASE_ADDRESS (dra), 0)
           != TREE_OPERAND (DR_BASE_ADDRESS (drb),0)))
      || !vect_equal_offsets (DR_OFFSET (dra), DR_OFFSET (drb)))
    return true;

  /* Check the types.  */
  type_size_a = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dra))));
  type_size_b = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (drb))));

  if (type_size_a != type_size_b
      || !types_compatible_p (TREE_TYPE (DR_REF (dra)),
                              TREE_TYPE (DR_REF (drb))))
    return true;

  init_a = TREE_INT_CST_LOW (DR_INIT (dra));
  init_b = TREE_INT_CST_LOW (DR_INIT (drb));

  /* Two different locations - no dependence.  */
  if (init_a != init_b)
    return false;

  /* We have a read-write dependence.  Check that the load is before the store.
     When we vectorize basic blocks, vector load can be only before 
     corresponding scalar load, and vector store can be only after its
     corresponding scalar store.  So the order of the acceses is preserved in
     case the load is before the store.  */
  earlier_stmt = get_earlier_stmt (DR_STMT (dra), DR_STMT (drb));   
  if (DR_IS_READ (STMT_VINFO_DATA_REF (vinfo_for_stmt (earlier_stmt))))
    return false;

  return true;
}


/* Function vect_check_interleaving.

   Check if DRA and DRB are a part of interleaving.  In case they are, insert
   DRA and DRB in an interleaving chain.  */

static bool
vect_check_interleaving (struct data_reference *dra,
			 struct data_reference *drb)
{
  HOST_WIDE_INT type_size_a, type_size_b, diff_mod_size, step, init_a, init_b;

  /* Check that the data-refs have same first location (except init) and they
     are both either store or load (not load and store).  */
  if ((DR_BASE_ADDRESS (dra) != DR_BASE_ADDRESS (drb)
       && (TREE_CODE (DR_BASE_ADDRESS (dra)) != ADDR_EXPR
	   || TREE_CODE (DR_BASE_ADDRESS (drb)) != ADDR_EXPR
	   || TREE_OPERAND (DR_BASE_ADDRESS (dra), 0)
	   != TREE_OPERAND (DR_BASE_ADDRESS (drb),0)))
      || !vect_equal_offsets (DR_OFFSET (dra), DR_OFFSET (drb))
      || !tree_int_cst_compare (DR_INIT (dra), DR_INIT (drb))
      || DR_IS_READ (dra) != DR_IS_READ (drb))
    return false;

  /* Check:
     1. data-refs are of the same type
     2. their steps are equal
     3. the step (if greater than zero) is greater than the difference between
        data-refs' inits.  */
  type_size_a = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dra))));
  type_size_b = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (drb))));

  if (type_size_a != type_size_b
      || tree_int_cst_compare (DR_STEP (dra), DR_STEP (drb))
      || !types_compatible_p (TREE_TYPE (DR_REF (dra)),
                              TREE_TYPE (DR_REF (drb))))
    return false;

  init_a = TREE_INT_CST_LOW (DR_INIT (dra));
  init_b = TREE_INT_CST_LOW (DR_INIT (drb));
  step = TREE_INT_CST_LOW (DR_STEP (dra));

  if (init_a > init_b)
    {
      /* If init_a == init_b + the size of the type * k, we have an interleaving,
	 and DRB is accessed before DRA.  */
      diff_mod_size = (init_a - init_b) % type_size_a;

      if (step && (init_a - init_b) > step)
         return false;

      if (diff_mod_size == 0)
	{
	  vect_update_interleaving_chain (drb, dra);
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    {
	      fprintf (vect_dump, "Detected interleaving ");
	      print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
	      fprintf (vect_dump, " and ");
	      print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
	    }
	  return true;
	}
    }
  else
    {
      /* If init_b == init_a + the size of the type * k, we have an
	 interleaving, and DRA is accessed before DRB.  */
      diff_mod_size = (init_b - init_a) % type_size_a;

      if (step && (init_b - init_a) > step)
         return false;

      if (diff_mod_size == 0)
	{
	  vect_update_interleaving_chain (dra, drb);
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    {
	      fprintf (vect_dump, "Detected interleaving ");
	      print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
	      fprintf (vect_dump, " and ");
	      print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
	    }
	  return true;
	}
    }

  return false;
}

/* Check if data references pointed by DR_I and DR_J are same or
   belong to same interleaving group.  Return FALSE if drs are
   different, otherwise return TRUE.  */

static bool
vect_same_range_drs (data_reference_p dr_i, data_reference_p dr_j)
{
  gimple stmt_i = DR_STMT (dr_i);
  gimple stmt_j = DR_STMT (dr_j);

  if (operand_equal_p (DR_REF (dr_i), DR_REF (dr_j), 0)
      || (DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt_i))
	    && DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt_j))
	    && (DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt_i))
		== DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt_j)))))
    return true;
  else
    return false;
}

/* If address ranges represented by DDR_I and DDR_J are equal,
   return TRUE, otherwise return FALSE.  */

static bool
vect_vfa_range_equal (ddr_p ddr_i, ddr_p ddr_j)
{
  if ((vect_same_range_drs (DDR_A (ddr_i), DDR_A (ddr_j))
       && vect_same_range_drs (DDR_B (ddr_i), DDR_B (ddr_j)))
      || (vect_same_range_drs (DDR_A (ddr_i), DDR_B (ddr_j))
	  && vect_same_range_drs (DDR_B (ddr_i), DDR_A (ddr_j))))
    return true;
  else
    return false;
}

/* Insert DDR into LOOP_VINFO list of ddrs that may alias and need to be
   tested at run-time.  Return TRUE if DDR was successfully inserted.
   Return false if versioning is not supported.  */

static bool
vect_mark_for_runtime_alias_test (ddr_p ddr, loop_vec_info loop_vinfo)
{
  struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);

  if ((unsigned) PARAM_VALUE (PARAM_VECT_MAX_VERSION_FOR_ALIAS_CHECKS) == 0)
    return false;

  if (vect_print_dump_info (REPORT_DR_DETAILS))
    {
      fprintf (vect_dump, "mark for run-time aliasing test between ");
      print_generic_expr (vect_dump, DR_REF (DDR_A (ddr)), TDF_SLIM);
      fprintf (vect_dump, " and ");
      print_generic_expr (vect_dump, DR_REF (DDR_B (ddr)), TDF_SLIM);
    }

  if (optimize_loop_nest_for_size_p (loop))
    {
      if (vect_print_dump_info (REPORT_DR_DETAILS))
	fprintf (vect_dump, "versioning not supported when optimizing for size.");
      return false;
    }

  /* FORNOW: We don't support versioning with outer-loop vectorization.  */
  if (loop->inner)
    {
      if (vect_print_dump_info (REPORT_DR_DETAILS))
	fprintf (vect_dump, "versioning not yet supported for outer-loops.");
      return false;
    }

  VEC_safe_push (ddr_p, heap, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo), ddr);
  return true;
}


/* Function vect_analyze_data_ref_dependence.

   Return TRUE if there (might) exist a dependence between a memory-reference
   DRA and a memory-reference DRB.  When versioning for alias may check a
   dependence at run-time, return FALSE.  Adjust *MAX_VF according to
   the data dependence.  */

static bool
vect_analyze_data_ref_dependence (struct data_dependence_relation *ddr,
                                  loop_vec_info loop_vinfo, int *max_vf,
                                  bool *data_dependence_in_bb)
{
  unsigned int i;
  struct loop *loop = NULL;
  struct data_reference *dra = DDR_A (ddr);
  struct data_reference *drb = DDR_B (ddr);
  stmt_vec_info stmtinfo_a = vinfo_for_stmt (DR_STMT (dra));
  stmt_vec_info stmtinfo_b = vinfo_for_stmt (DR_STMT (drb));
  lambda_vector dist_v;
  unsigned int loop_depth;

  /* Don't bother to analyze statements marked as unvectorizable.  */
  if (!STMT_VINFO_VECTORIZABLE (stmtinfo_a)
      || !STMT_VINFO_VECTORIZABLE (stmtinfo_b))
    return false;

  if (DDR_ARE_DEPENDENT (ddr) == chrec_known)
    {
      /* Independent data accesses.  */
      vect_check_interleaving (dra, drb);
      return false;
    }

  if (loop_vinfo)
    loop = LOOP_VINFO_LOOP (loop_vinfo);

  if ((DR_IS_READ (dra) && DR_IS_READ (drb) && loop_vinfo) || dra == drb)
    return false;

  if (DDR_ARE_DEPENDENT (ddr) == chrec_dont_know)
    {
      if (loop_vinfo)
        {
          if (vect_print_dump_info (REPORT_DR_DETAILS))
            {
              fprintf (vect_dump, "versioning for alias required: "
                                  "can't determine dependence between ");
              print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
              fprintf (vect_dump, " and ");
              print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
            }

          /* Add to list of ddrs that need to be tested at run-time.  */
          return !vect_mark_for_runtime_alias_test (ddr, loop_vinfo);
        }

      /* When vectorizing a basic block unknown depnedence can still mean
	 strided access.  */
      if (vect_check_interleaving (dra, drb))
         return false;

      if (vect_print_dump_info (REPORT_DR_DETAILS))
        {
          fprintf (vect_dump, "can't determine dependence between ");
          print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
          fprintf (vect_dump, " and ");
          print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
        }

      /* We do not vectorize basic blocks with write-write dependencies.  */
      if (DR_IS_WRITE (dra) && DR_IS_WRITE (drb))
        return true;

      /* We deal with read-write dependencies in basic blocks later (by
         verifying that all the loads in the basic block are before all the
         stores).  */
      *data_dependence_in_bb = true;
      return false;
    }

  /* Versioning for alias is not yet supported for basic block SLP, and
     dependence distance is unapplicable, hence, in case of known data
     dependence, basic block vectorization is impossible for now.  */
  if (!loop_vinfo)
    {
      if (dra != drb && vect_check_interleaving (dra, drb))
        return false;

      if (vect_print_dump_info (REPORT_DR_DETAILS))
        {
          fprintf (vect_dump, "determined dependence between ");
          print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
          fprintf (vect_dump, " and ");
          print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
        }

      /* Do not vectorize basic blcoks with write-write dependences.  */
      if (DR_IS_WRITE (dra) && DR_IS_WRITE (drb))
        return true;

      /* Check if this dependence is allowed in basic block vectorization.  */ 
      return vect_drs_dependent_in_basic_block (dra, drb);
    }

  /* Loop-based vectorization and known data dependence.  */
  if (DDR_NUM_DIST_VECTS (ddr) == 0)
    {
      if (vect_print_dump_info (REPORT_DR_DETAILS))
        {
          fprintf (vect_dump, "versioning for alias required: bad dist vector for ");
          print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
          fprintf (vect_dump, " and ");
          print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
        }
      /* Add to list of ddrs that need to be tested at run-time.  */
      return !vect_mark_for_runtime_alias_test (ddr, loop_vinfo);
    }

  loop_depth = index_in_loop_nest (loop->num, DDR_LOOP_NEST (ddr));
  FOR_EACH_VEC_ELT (lambda_vector, DDR_DIST_VECTS (ddr), i, dist_v)
    {
      int dist = dist_v[loop_depth];

      if (vect_print_dump_info (REPORT_DR_DETAILS))
	fprintf (vect_dump, "dependence distance  = %d.", dist);

      if (dist == 0)
	{
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    {
	      fprintf (vect_dump, "dependence distance == 0 between ");
	      print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
	      fprintf (vect_dump, " and ");
	      print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
	    }

          /* For interleaving, mark that there is a read-write dependency if
             necessary. We check before that one of the data-refs is store.  */
          if (DR_IS_READ (dra))
            DR_GROUP_READ_WRITE_DEPENDENCE (stmtinfo_a) = true;
	  else
            {
              if (DR_IS_READ (drb))
                DR_GROUP_READ_WRITE_DEPENDENCE (stmtinfo_b) = true;
	    }

	  continue;
	}

      if (dist > 0 && DDR_REVERSED_P (ddr))
	{
	  /* If DDR_REVERSED_P the order of the data-refs in DDR was
	     reversed (to make distance vector positive), and the actual
	     distance is negative.  */
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    fprintf (vect_dump, "dependence distance negative.");
	  continue;
	}

      if (abs (dist) >= 2
	  && abs (dist) < *max_vf)
	{
	  /* The dependence distance requires reduction of the maximal
	     vectorization factor.  */
	  *max_vf = abs (dist);
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    fprintf (vect_dump, "adjusting maximal vectorization factor to %i",
		     *max_vf);
	}

      if (abs (dist) >= *max_vf)
	{
	  /* Dependence distance does not create dependence, as far as
	     vectorization is concerned, in this case.  */
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    fprintf (vect_dump, "dependence distance >= VF.");
	  continue;
	}

      if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	{
	  fprintf (vect_dump, "not vectorized, possible dependence "
    		              "between data-refs ");
	  print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
	  fprintf (vect_dump, " and ");
	  print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
	}

      return true;
    }

  return false;
}

/* Function vect_analyze_data_ref_dependences.

   Examine all the data references in the loop, and make sure there do not
   exist any data dependences between them.  Set *MAX_VF according to
   the maximum vectorization factor the data dependences allow.  */

bool
vect_analyze_data_ref_dependences (loop_vec_info loop_vinfo,
                                   bb_vec_info bb_vinfo, int *max_vf,
                                   bool *data_dependence_in_bb)
{
  unsigned int i;
  VEC (ddr_p, heap) *ddrs = NULL;
  struct data_dependence_relation *ddr;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_analyze_dependences ===");

  if (loop_vinfo)
    ddrs = LOOP_VINFO_DDRS (loop_vinfo);
  else
    ddrs = BB_VINFO_DDRS (bb_vinfo);

  FOR_EACH_VEC_ELT (ddr_p, ddrs, i, ddr)
    if (vect_analyze_data_ref_dependence (ddr, loop_vinfo, max_vf,
					  data_dependence_in_bb))
      return false;

  return true;
}


/* Function vect_compute_data_ref_alignment

   Compute the misalignment of the data reference DR.

   Output:
   1. If during the misalignment computation it is found that the data reference
      cannot be vectorized then false is returned.
   2. DR_MISALIGNMENT (DR) is defined.

   FOR NOW: No analysis is actually performed. Misalignment is calculated
   only for trivial cases. TODO.  */

static bool
vect_compute_data_ref_alignment (struct data_reference *dr)
{
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  struct loop *loop = NULL;
  tree ref = DR_REF (dr);
  tree vectype;
  tree base, base_addr;
  bool base_aligned;
  tree misalign;
  tree aligned_to, alignment;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "vect_compute_data_ref_alignment:");

  if (loop_vinfo)
    loop = LOOP_VINFO_LOOP (loop_vinfo);

  /* Initialize misalignment to unknown.  */
  SET_DR_MISALIGNMENT (dr, -1);

  misalign = DR_INIT (dr);
  aligned_to = DR_ALIGNED_TO (dr);
  base_addr = DR_BASE_ADDRESS (dr);
  vectype = STMT_VINFO_VECTYPE (stmt_info);

  /* In case the dataref is in an inner-loop of the loop that is being
     vectorized (LOOP), we use the base and misalignment information
     relative to the outer-loop (LOOP).  This is ok only if the misalignment
     stays the same throughout the execution of the inner-loop, which is why
     we have to check that the stride of the dataref in the inner-loop evenly
     divides by the vector size.  */
  if (loop && nested_in_vect_loop_p (loop, stmt))
    {
      tree step = DR_STEP (dr);
      HOST_WIDE_INT dr_step = TREE_INT_CST_LOW (step);

      if (dr_step % GET_MODE_SIZE (TYPE_MODE (vectype)) == 0)
        {
          if (vect_print_dump_info (REPORT_ALIGNMENT))
            fprintf (vect_dump, "inner step divides the vector-size.");
	  misalign = STMT_VINFO_DR_INIT (stmt_info);
	  aligned_to = STMT_VINFO_DR_ALIGNED_TO (stmt_info);
	  base_addr = STMT_VINFO_DR_BASE_ADDRESS (stmt_info);
        }
      else
	{
	  if (vect_print_dump_info (REPORT_ALIGNMENT))
	    fprintf (vect_dump, "inner step doesn't divide the vector-size.");
	  misalign = NULL_TREE;
	}
    }

  base = build_fold_indirect_ref (base_addr);
  alignment = ssize_int (TYPE_ALIGN (vectype)/BITS_PER_UNIT);

  if ((aligned_to && tree_int_cst_compare (aligned_to, alignment) < 0)
      || !misalign)
    {
      if (vect_print_dump_info (REPORT_ALIGNMENT))
	{
	  fprintf (vect_dump, "Unknown alignment for access: ");
	  print_generic_expr (vect_dump, base, TDF_SLIM);
	}
      return true;
    }

  if ((DECL_P (base)
       && tree_int_cst_compare (ssize_int (DECL_ALIGN_UNIT (base)),
				alignment) >= 0)
      || (TREE_CODE (base_addr) == SSA_NAME
	  && tree_int_cst_compare (ssize_int (TYPE_ALIGN_UNIT (TREE_TYPE (
						      TREE_TYPE (base_addr)))),
				   alignment) >= 0))
    base_aligned = true;
  else
    base_aligned = false;

  if (!base_aligned)
    {
      /* Do not change the alignment of global variables if
	 flag_section_anchors is enabled.  */
      if (!vect_can_force_dr_alignment_p (base, TYPE_ALIGN (vectype))
	  || (TREE_STATIC (base) && flag_section_anchors))
	{
	  if (vect_print_dump_info (REPORT_DETAILS))
	    {
	      fprintf (vect_dump, "can't force alignment of ref: ");
	      print_generic_expr (vect_dump, ref, TDF_SLIM);
	    }
	  return true;
	}

      /* Force the alignment of the decl.
	 NOTE: This is the only change to the code we make during
	 the analysis phase, before deciding to vectorize the loop.  */
      if (vect_print_dump_info (REPORT_DETAILS))
        {
          fprintf (vect_dump, "force alignment of ");
          print_generic_expr (vect_dump, ref, TDF_SLIM);
        }

      DECL_ALIGN (base) = TYPE_ALIGN (vectype);
      DECL_USER_ALIGN (base) = 1;
    }

  /* At this point we assume that the base is aligned.  */
  gcc_assert (base_aligned
	      || (TREE_CODE (base) == VAR_DECL
		  && DECL_ALIGN (base) >= TYPE_ALIGN (vectype)));

  /* If this is a backward running DR then first access in the larger
     vectype actually is N-1 elements before the address in the DR.
     Adjust misalign accordingly.  */
  if (tree_int_cst_compare (DR_STEP (dr), size_zero_node) < 0)
    {
      tree offset = ssize_int (TYPE_VECTOR_SUBPARTS (vectype) - 1);
      /* DR_STEP(dr) is the same as -TYPE_SIZE of the scalar type,
	 otherwise we wouldn't be here.  */
      offset = fold_build2 (MULT_EXPR, ssizetype, offset, DR_STEP (dr));
      /* PLUS because DR_STEP was negative.  */
      misalign = size_binop (PLUS_EXPR, misalign, offset);
    }

  /* Modulo alignment.  */
  misalign = size_binop (FLOOR_MOD_EXPR, misalign, alignment);

  if (!host_integerp (misalign, 1))
    {
      /* Negative or overflowed misalignment value.  */
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "unexpected misalign value");
      return false;
    }

  SET_DR_MISALIGNMENT (dr, TREE_INT_CST_LOW (misalign));

  if (vect_print_dump_info (REPORT_DETAILS))
    {
      fprintf (vect_dump, "misalign = %d bytes of ref ", DR_MISALIGNMENT (dr));
      print_generic_expr (vect_dump, ref, TDF_SLIM);
    }

  return true;
}


/* Function vect_compute_data_refs_alignment

   Compute the misalignment of data references in the loop.
   Return FALSE if a data reference is found that cannot be vectorized.  */

static bool
vect_compute_data_refs_alignment (loop_vec_info loop_vinfo,
                                  bb_vec_info bb_vinfo)
{
  VEC (data_reference_p, heap) *datarefs;
  struct data_reference *dr;
  unsigned int i;

  if (loop_vinfo)
    datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
  else
    datarefs = BB_VINFO_DATAREFS (bb_vinfo);

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    if (STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (DR_STMT (dr)))
        && !vect_compute_data_ref_alignment (dr))
      {
        if (bb_vinfo)
          {
            /* Mark unsupported statement as unvectorizable.  */
            STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (DR_STMT (dr))) = false;
            continue;
          }
        else
          return false;
      }

  return true;
}


/* Function vect_update_misalignment_for_peel

   DR - the data reference whose misalignment is to be adjusted.
   DR_PEEL - the data reference whose misalignment is being made
             zero in the vector loop by the peel.
   NPEEL - the number of iterations in the peel loop if the misalignment
           of DR_PEEL is known at compile time.  */

static void
vect_update_misalignment_for_peel (struct data_reference *dr,
                                   struct data_reference *dr_peel, int npeel)
{
  unsigned int i;
  VEC(dr_p,heap) *same_align_drs;
  struct data_reference *current_dr;
  int dr_size = GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (dr))));
  int dr_peel_size = GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (dr_peel))));
  stmt_vec_info stmt_info = vinfo_for_stmt (DR_STMT (dr));
  stmt_vec_info peel_stmt_info = vinfo_for_stmt (DR_STMT (dr_peel));

 /* For interleaved data accesses the step in the loop must be multiplied by
     the size of the interleaving group.  */
  if (STMT_VINFO_STRIDED_ACCESS (stmt_info))
    dr_size *= DR_GROUP_SIZE (vinfo_for_stmt (DR_GROUP_FIRST_DR (stmt_info)));
  if (STMT_VINFO_STRIDED_ACCESS (peel_stmt_info))
    dr_peel_size *= DR_GROUP_SIZE (peel_stmt_info);

  /* It can be assumed that the data refs with the same alignment as dr_peel
     are aligned in the vector loop.  */
  same_align_drs
    = STMT_VINFO_SAME_ALIGN_REFS (vinfo_for_stmt (DR_STMT (dr_peel)));
  FOR_EACH_VEC_ELT (dr_p, same_align_drs, i, current_dr)
    {
      if (current_dr != dr)
        continue;
      gcc_assert (DR_MISALIGNMENT (dr) / dr_size ==
                  DR_MISALIGNMENT (dr_peel) / dr_peel_size);
      SET_DR_MISALIGNMENT (dr, 0);
      return;
    }

  if (known_alignment_for_access_p (dr)
      && known_alignment_for_access_p (dr_peel))
    {
      bool negative = tree_int_cst_compare (DR_STEP (dr), size_zero_node) < 0;
      int misal = DR_MISALIGNMENT (dr);
      tree vectype = STMT_VINFO_VECTYPE (stmt_info);
      misal += negative ? -npeel * dr_size : npeel * dr_size;
      misal &= (TYPE_ALIGN (vectype) / BITS_PER_UNIT) - 1;
      SET_DR_MISALIGNMENT (dr, misal);
      return;
    }

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "Setting misalignment to -1.");
  SET_DR_MISALIGNMENT (dr, -1);
}


/* Function vect_verify_datarefs_alignment

   Return TRUE if all data references in the loop can be
   handled with respect to alignment.  */

bool
vect_verify_datarefs_alignment (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
{
  VEC (data_reference_p, heap) *datarefs;
  struct data_reference *dr;
  enum dr_alignment_support supportable_dr_alignment;
  unsigned int i;

  if (loop_vinfo)
    datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
  else
    datarefs = BB_VINFO_DATAREFS (bb_vinfo);

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    {
      gimple stmt = DR_STMT (dr);
      stmt_vec_info stmt_info = vinfo_for_stmt (stmt);

      /* For interleaving, only the alignment of the first access matters. 
         Skip statements marked as not vectorizable.  */
      if ((STMT_VINFO_STRIDED_ACCESS (stmt_info)
           && DR_GROUP_FIRST_DR (stmt_info) != stmt)
          || !STMT_VINFO_VECTORIZABLE (stmt_info))
        continue;

      supportable_dr_alignment = vect_supportable_dr_alignment (dr, false);
      if (!supportable_dr_alignment)
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              if (DR_IS_READ (dr))
                fprintf (vect_dump,
                         "not vectorized: unsupported unaligned load.");
              else
                fprintf (vect_dump,
                         "not vectorized: unsupported unaligned store.");

              print_generic_expr (vect_dump, DR_REF (dr), TDF_SLIM);
            }
          return false;
        }
      if (supportable_dr_alignment != dr_aligned
          && vect_print_dump_info (REPORT_ALIGNMENT))
        fprintf (vect_dump, "Vectorizing an unaligned access.");
    }
  return true;
}


/* Function vector_alignment_reachable_p

   Return true if vector alignment for DR is reachable by peeling
   a few loop iterations.  Return false otherwise.  */

static bool
vector_alignment_reachable_p (struct data_reference *dr)
{
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  tree vectype = STMT_VINFO_VECTYPE (stmt_info);

  if (STMT_VINFO_STRIDED_ACCESS (stmt_info))
    {
      /* For interleaved access we peel only if number of iterations in
	 the prolog loop ({VF - misalignment}), is a multiple of the
	 number of the interleaved accesses.  */
      int elem_size, mis_in_elements;
      int nelements = TYPE_VECTOR_SUBPARTS (vectype);

      /* FORNOW: handle only known alignment.  */
      if (!known_alignment_for_access_p (dr))
	return false;

      elem_size = GET_MODE_SIZE (TYPE_MODE (vectype)) / nelements;
      mis_in_elements = DR_MISALIGNMENT (dr) / elem_size;

      if ((nelements - mis_in_elements) % DR_GROUP_SIZE (stmt_info))
	return false;
    }

  /* If misalignment is known at the compile time then allow peeling
     only if natural alignment is reachable through peeling.  */
  if (known_alignment_for_access_p (dr) && !aligned_access_p (dr))
    {
      HOST_WIDE_INT elmsize =
		int_cst_value (TYPE_SIZE_UNIT (TREE_TYPE (vectype)));
      if (vect_print_dump_info (REPORT_DETAILS))
	{
	  fprintf (vect_dump, "data size =" HOST_WIDE_INT_PRINT_DEC, elmsize);
	  fprintf (vect_dump, ". misalignment = %d. ", DR_MISALIGNMENT (dr));
	}
      if (DR_MISALIGNMENT (dr) % elmsize)
	{
	  if (vect_print_dump_info (REPORT_DETAILS))
	    fprintf (vect_dump, "data size does not divide the misalignment.\n");
	  return false;
	}
    }

  if (!known_alignment_for_access_p (dr))
    {
      tree type = (TREE_TYPE (DR_REF (dr)));
      tree ba = DR_BASE_OBJECT (dr);
      bool is_packed = false;

      if (ba)
	is_packed = contains_packed_reference (ba);

      if (compare_tree_int (TYPE_SIZE (type), TYPE_ALIGN (type)) > 0)
	is_packed = true;

      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "Unknown misalignment, is_packed = %d",is_packed);
      if (targetm.vectorize.vector_alignment_reachable (type, is_packed))
	return true;
      else
	return false;
    }

  return true;
}


/* Calculate the cost of the memory access represented by DR.  */

static void
vect_get_data_access_cost (struct data_reference *dr,
                           unsigned int *inside_cost,
                           unsigned int *outside_cost)
{
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  int nunits = TYPE_VECTOR_SUBPARTS (STMT_VINFO_VECTYPE (stmt_info));
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  int vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
  int ncopies = vf / nunits;
  bool supportable_dr_alignment = vect_supportable_dr_alignment (dr, true);

  if (!supportable_dr_alignment)
    *inside_cost = VECT_MAX_COST;
  else
    {
      if (DR_IS_READ (dr))
        vect_get_load_cost (dr, ncopies, true, inside_cost, outside_cost);
      else
        vect_get_store_cost (dr, ncopies, inside_cost);
    }

  if (vect_print_dump_info (REPORT_COST))
    fprintf (vect_dump, "vect_get_data_access_cost: inside_cost = %d, "
             "outside_cost = %d.", *inside_cost, *outside_cost);
}


static hashval_t
vect_peeling_hash (const void *elem)
{
  const struct _vect_peel_info *peel_info;

  peel_info = (const struct _vect_peel_info *) elem;
  return (hashval_t) peel_info->npeel;
}


static int
vect_peeling_hash_eq (const void *elem1, const void *elem2)
{
  const struct _vect_peel_info *a, *b;

  a = (const struct _vect_peel_info *) elem1;
  b = (const struct _vect_peel_info *) elem2;
  return (a->npeel == b->npeel);
}


/* Insert DR into peeling hash table with NPEEL as key.  */

static void
vect_peeling_hash_insert (loop_vec_info loop_vinfo, struct data_reference *dr,
                          int npeel)
{
  struct _vect_peel_info elem, *slot;
  void **new_slot;
  bool supportable_dr_alignment = vect_supportable_dr_alignment (dr, true);

  elem.npeel = npeel;
  slot = (vect_peel_info) htab_find (LOOP_VINFO_PEELING_HTAB (loop_vinfo),
                                     &elem);
  if (slot)
    slot->count++;
  else
    {
      slot = XNEW (struct _vect_peel_info);
      slot->npeel = npeel;
      slot->dr = dr;
      slot->count = 1;
      new_slot = htab_find_slot (LOOP_VINFO_PEELING_HTAB (loop_vinfo), slot,
                                 INSERT);
      *new_slot = slot;
    }

  if (!supportable_dr_alignment && !flag_vect_cost_model)
    slot->count += VECT_MAX_COST;
}


/* Traverse peeling hash table to find peeling option that aligns maximum
   number of data accesses.  */

static int
vect_peeling_hash_get_most_frequent (void **slot, void *data)
{
  vect_peel_info elem = (vect_peel_info) *slot;
  vect_peel_extended_info max = (vect_peel_extended_info) data;

  if (elem->count > max->peel_info.count)
    {
      max->peel_info.npeel = elem->npeel;
      max->peel_info.count = elem->count;
      max->peel_info.dr = elem->dr;
    }

  return 1;
}


/* Traverse peeling hash table and calculate cost for each peeling option.
   Find the one with the lowest cost.  */

static int
vect_peeling_hash_get_lowest_cost (void **slot, void *data)
{
  vect_peel_info elem = (vect_peel_info) *slot;
  vect_peel_extended_info min = (vect_peel_extended_info) data;
  int save_misalignment, dummy;
  unsigned int inside_cost = 0, outside_cost = 0, i;
  gimple stmt = DR_STMT (elem->dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  VEC (data_reference_p, heap) *datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
  struct data_reference *dr;

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    {
      stmt = DR_STMT (dr);
      stmt_info = vinfo_for_stmt (stmt);
      /* For interleaving, only the alignment of the first access
         matters.  */
      if (STMT_VINFO_STRIDED_ACCESS (stmt_info)
          && DR_GROUP_FIRST_DR (stmt_info) != stmt)
        continue;

      save_misalignment = DR_MISALIGNMENT (dr);
      vect_update_misalignment_for_peel (dr, elem->dr, elem->npeel);
      vect_get_data_access_cost (dr, &inside_cost, &outside_cost);
      SET_DR_MISALIGNMENT (dr, save_misalignment);
    }

  outside_cost += vect_get_known_peeling_cost (loop_vinfo, elem->npeel, &dummy,
                         vect_get_single_scalar_iteration_cost (loop_vinfo));

  if (inside_cost < min->inside_cost
      || (inside_cost == min->inside_cost && outside_cost < min->outside_cost))
    {
      min->inside_cost = inside_cost;
      min->outside_cost = outside_cost;
      min->peel_info.dr = elem->dr;
      min->peel_info.npeel = elem->npeel;
    }

  return 1;
}


/* Choose best peeling option by traversing peeling hash table and either
   choosing an option with the lowest cost (if cost model is enabled) or the
   option that aligns as many accesses as possible.  */

static struct data_reference *
vect_peeling_hash_choose_best_peeling (loop_vec_info loop_vinfo,
                                       unsigned int *npeel)
{
   struct _vect_peel_extended_info res;

   res.peel_info.dr = NULL;

   if (flag_vect_cost_model)
     {
       res.inside_cost = INT_MAX;
       res.outside_cost = INT_MAX;
       htab_traverse (LOOP_VINFO_PEELING_HTAB (loop_vinfo),
                      vect_peeling_hash_get_lowest_cost, &res);
     }
   else
     {
       res.peel_info.count = 0;
       htab_traverse (LOOP_VINFO_PEELING_HTAB (loop_vinfo),
                      vect_peeling_hash_get_most_frequent, &res);
     }

   *npeel = res.peel_info.npeel;
   return res.peel_info.dr;
}


/* Function vect_enhance_data_refs_alignment

   This pass will use loop versioning and loop peeling in order to enhance
   the alignment of data references in the loop.

   FOR NOW: we assume that whatever versioning/peeling takes place, only the
   original loop is to be vectorized.  Any other loops that are created by
   the transformations performed in this pass - are not supposed to be
   vectorized.  This restriction will be relaxed.

   This pass will require a cost model to guide it whether to apply peeling
   or versioning or a combination of the two.  For example, the scheme that
   intel uses when given a loop with several memory accesses, is as follows:
   choose one memory access ('p') which alignment you want to force by doing
   peeling.  Then, either (1) generate a loop in which 'p' is aligned and all
   other accesses are not necessarily aligned, or (2) use loop versioning to
   generate one loop in which all accesses are aligned, and another loop in
   which only 'p' is necessarily aligned.

   ("Automatic Intra-Register Vectorization for the Intel Architecture",
   Aart J.C. Bik, Milind Girkar, Paul M. Grey and Ximmin Tian, International
   Journal of Parallel Programming, Vol. 30, No. 2, April 2002.)

   Devising a cost model is the most critical aspect of this work.  It will
   guide us on which access to peel for, whether to use loop versioning, how
   many versions to create, etc.  The cost model will probably consist of
   generic considerations as well as target specific considerations (on
   powerpc for example, misaligned stores are more painful than misaligned
   loads).

   Here are the general steps involved in alignment enhancements:

     -- original loop, before alignment analysis:
	for (i=0; i<N; i++){
	  x = q[i];			# DR_MISALIGNMENT(q) = unknown
	  p[i] = y;			# DR_MISALIGNMENT(p) = unknown
	}

     -- After vect_compute_data_refs_alignment:
	for (i=0; i<N; i++){
	  x = q[i];			# DR_MISALIGNMENT(q) = 3
	  p[i] = y;			# DR_MISALIGNMENT(p) = unknown
	}

     -- Possibility 1: we do loop versioning:
     if (p is aligned) {
	for (i=0; i<N; i++){	# loop 1A
	  x = q[i];			# DR_MISALIGNMENT(q) = 3
	  p[i] = y;			# DR_MISALIGNMENT(p) = 0
	}
     }
     else {
	for (i=0; i<N; i++){	# loop 1B
	  x = q[i];			# DR_MISALIGNMENT(q) = 3
	  p[i] = y;			# DR_MISALIGNMENT(p) = unaligned
	}
     }

     -- Possibility 2: we do loop peeling:
     for (i = 0; i < 3; i++){	# (scalar loop, not to be vectorized).
	x = q[i];
	p[i] = y;
     }
     for (i = 3; i < N; i++){	# loop 2A
	x = q[i];			# DR_MISALIGNMENT(q) = 0
	p[i] = y;			# DR_MISALIGNMENT(p) = unknown
     }

     -- Possibility 3: combination of loop peeling and versioning:
     for (i = 0; i < 3; i++){	# (scalar loop, not to be vectorized).
	x = q[i];
	p[i] = y;
     }
     if (p is aligned) {
	for (i = 3; i<N; i++){	# loop 3A
	  x = q[i];			# DR_MISALIGNMENT(q) = 0
	  p[i] = y;			# DR_MISALIGNMENT(p) = 0
	}
     }
     else {
	for (i = 3; i<N; i++){	# loop 3B
	  x = q[i];			# DR_MISALIGNMENT(q) = 0
	  p[i] = y;			# DR_MISALIGNMENT(p) = unaligned
	}
     }

     These loops are later passed to loop_transform to be vectorized.  The
     vectorizer will use the alignment information to guide the transformation
     (whether to generate regular loads/stores, or with special handling for
     misalignment).  */

bool
vect_enhance_data_refs_alignment (loop_vec_info loop_vinfo)
{
  VEC (data_reference_p, heap) *datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
  struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
  enum dr_alignment_support supportable_dr_alignment;
  struct data_reference *dr0 = NULL, *first_store = NULL;
  struct data_reference *dr;
  unsigned int i, j;
  bool do_peeling = false;
  bool do_versioning = false;
  bool stat;
  gimple stmt;
  stmt_vec_info stmt_info;
  int vect_versioning_for_alias_required;
  unsigned int npeel = 0;
  bool all_misalignments_unknown = true;
  unsigned int vf = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
  unsigned possible_npeel_number = 1;
  tree vectype;
  unsigned int nelements, mis, same_align_drs_max = 0;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_enhance_data_refs_alignment ===");

  /* While cost model enhancements are expected in the future, the high level
     view of the code at this time is as follows:

     A) If there is a misaligned access then see if peeling to align
        this access can make all data references satisfy
        vect_supportable_dr_alignment.  If so, update data structures
        as needed and return true.

     B) If peeling wasn't possible and there is a data reference with an
        unknown misalignment that does not satisfy vect_supportable_dr_alignment
        then see if loop versioning checks can be used to make all data
        references satisfy vect_supportable_dr_alignment.  If so, update
        data structures as needed and return true.

     C) If neither peeling nor versioning were successful then return false if
        any data reference does not satisfy vect_supportable_dr_alignment.

     D) Return true (all data references satisfy vect_supportable_dr_alignment).

     Note, Possibility 3 above (which is peeling and versioning together) is not
     being done at this time.  */

  /* (1) Peeling to force alignment.  */

  /* (1.1) Decide whether to perform peeling, and how many iterations to peel:
     Considerations:
     + How many accesses will become aligned due to the peeling
     - How many accesses will become unaligned due to the peeling,
       and the cost of misaligned accesses.
     - The cost of peeling (the extra runtime checks, the increase
       in code size).  */

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    {
      stmt = DR_STMT (dr);
      stmt_info = vinfo_for_stmt (stmt);

      if (!STMT_VINFO_RELEVANT (stmt_info))
	continue;

      /* For interleaving, only the alignment of the first access
         matters.  */
      if (STMT_VINFO_STRIDED_ACCESS (stmt_info)
          && DR_GROUP_FIRST_DR (stmt_info) != stmt)
        continue;

      supportable_dr_alignment = vect_supportable_dr_alignment (dr, true);
      do_peeling = vector_alignment_reachable_p (dr);
      if (do_peeling)
        {
          if (known_alignment_for_access_p (dr))
            {
              unsigned int npeel_tmp;
	      bool negative = tree_int_cst_compare (DR_STEP (dr),
						    size_zero_node) < 0;

              /* Save info about DR in the hash table.  */
              if (!LOOP_VINFO_PEELING_HTAB (loop_vinfo))
                LOOP_VINFO_PEELING_HTAB (loop_vinfo) =
                           htab_create (1, vect_peeling_hash,
                                        vect_peeling_hash_eq, free);

              vectype = STMT_VINFO_VECTYPE (stmt_info);
              nelements = TYPE_VECTOR_SUBPARTS (vectype);
              mis = DR_MISALIGNMENT (dr) / GET_MODE_SIZE (TYPE_MODE (
                                                TREE_TYPE (DR_REF (dr))));
              npeel_tmp = (negative
			   ? (mis - nelements) : (nelements - mis))
		  & (nelements - 1);

              /* For multiple types, it is possible that the bigger type access
                 will have more than one peeling option.  E.g., a loop with two
                 types: one of size (vector size / 4), and the other one of
                 size (vector size / 8).  Vectorization factor will 8.  If both
                 access are misaligned by 3, the first one needs one scalar
                 iteration to be aligned, and the second one needs 5.  But the
                 the first one will be aligned also by peeling 5 scalar
                 iterations, and in that case both accesses will be aligned.
                 Hence, except for the immediate peeling amount, we also want
                 to try to add full vector size, while we don't exceed
                 vectorization factor.
                 We do this automtically for cost model, since we calculate cost
                 for every peeling option.  */
              if (!flag_vect_cost_model)
                possible_npeel_number = vf /nelements;

              /* Handle the aligned case. We may decide to align some other
                 access, making DR unaligned.  */
              if (DR_MISALIGNMENT (dr) == 0)
                {
                  npeel_tmp = 0;
                  if (!flag_vect_cost_model)
                    possible_npeel_number++;
                }

              for (j = 0; j < possible_npeel_number; j++)
                {
                  gcc_assert (npeel_tmp <= vf);
                  vect_peeling_hash_insert (loop_vinfo, dr, npeel_tmp);
                  npeel_tmp += nelements;
                }

              all_misalignments_unknown = false;
              /* Data-ref that was chosen for the case that all the
                 misalignments are unknown is not relevant anymore, since we
                 have a data-ref with known alignment.  */
              dr0 = NULL;
            }
          else
            {
              /* If we don't know all the misalignment values, we prefer
                 peeling for data-ref that has maximum number of data-refs
                 with the same alignment, unless the target prefers to align
                 stores over load.  */
              if (all_misalignments_unknown)
                {
                  if (same_align_drs_max  < VEC_length (dr_p,
                                       STMT_VINFO_SAME_ALIGN_REFS (stmt_info))
                      || !dr0)
                    {
                      same_align_drs_max = VEC_length (dr_p,
                                       STMT_VINFO_SAME_ALIGN_REFS (stmt_info));
                      dr0 = dr;
                    }

                  if (!first_store && DR_IS_WRITE (dr))
                    first_store = dr;
                }

              /* If there are both known and unknown misaligned accesses in the
                 loop, we choose peeling amount according to the known
                 accesses.  */


              if (!supportable_dr_alignment)
                {
                  dr0 = dr;
                  if (!first_store && DR_IS_WRITE (dr))
                    first_store = dr;
                }
            }
        }
      else
        {
          if (!aligned_access_p (dr))
            {
              if (vect_print_dump_info (REPORT_DETAILS))
                fprintf (vect_dump, "vector alignment may not be reachable");

              break;
            }
        }
    }

  vect_versioning_for_alias_required
    = LOOP_REQUIRES_VERSIONING_FOR_ALIAS (loop_vinfo);

  /* Temporarily, if versioning for alias is required, we disable peeling
     until we support peeling and versioning.  Often peeling for alignment
     will require peeling for loop-bound, which in turn requires that we
     know how to adjust the loop ivs after the loop.  */
  if (vect_versioning_for_alias_required
      || !vect_can_advance_ivs_p (loop_vinfo)
      || !slpeel_can_duplicate_loop_p (loop, single_exit (loop)))
    do_peeling = false;

  if (do_peeling && all_misalignments_unknown
      && vect_supportable_dr_alignment (dr0, false))
    {

      /* Check if the target requires to prefer stores over loads, i.e., if
         misaligned stores are more expensive than misaligned loads (taking
         drs with same alignment into account).  */
      if (first_store && DR_IS_READ (dr0))
        {
          unsigned int load_inside_cost = 0, load_outside_cost = 0;
          unsigned int store_inside_cost = 0, store_outside_cost = 0;
          unsigned int load_inside_penalty = 0, load_outside_penalty = 0;
          unsigned int store_inside_penalty = 0, store_outside_penalty = 0;

          vect_get_data_access_cost (dr0, &load_inside_cost,
                                     &load_outside_cost);
          vect_get_data_access_cost (first_store, &store_inside_cost,
                                     &store_outside_cost);

          /* Calculate the penalty for leaving FIRST_STORE unaligned (by
             aligning the load DR0).  */
          load_inside_penalty = store_inside_cost;
          load_outside_penalty = store_outside_cost;
          for (i = 0; VEC_iterate (dr_p, STMT_VINFO_SAME_ALIGN_REFS
                                   (vinfo_for_stmt (DR_STMT (first_store))),
                                   i, dr);
               i++)
            if (DR_IS_READ (dr))
              {
                load_inside_penalty += load_inside_cost;
                load_outside_penalty += load_outside_cost;
              }
            else
              {
                load_inside_penalty += store_inside_cost;
                load_outside_penalty += store_outside_cost;
              }

          /* Calculate the penalty for leaving DR0 unaligned (by
             aligning the FIRST_STORE).  */
          store_inside_penalty = load_inside_cost;
          store_outside_penalty = load_outside_cost;
          for (i = 0; VEC_iterate (dr_p, STMT_VINFO_SAME_ALIGN_REFS
                                   (vinfo_for_stmt (DR_STMT (dr0))),
                                   i, dr);
               i++)
            if (DR_IS_READ (dr))
              {
                store_inside_penalty += load_inside_cost;
                store_outside_penalty += load_outside_cost;
              }
            else
              {
                store_inside_penalty += store_inside_cost;
                store_outside_penalty += store_outside_cost;
              }

          if (load_inside_penalty > store_inside_penalty
              || (load_inside_penalty == store_inside_penalty
                  && load_outside_penalty > store_outside_penalty))
            dr0 = first_store;
        }

      /* In case there are only loads with different unknown misalignments, use
         peeling only if it may help to align other accesses in the loop.  */
      if (!first_store && !VEC_length (dr_p, STMT_VINFO_SAME_ALIGN_REFS
                                            (vinfo_for_stmt (DR_STMT (dr0))))
          && vect_supportable_dr_alignment (dr0, false)
              != dr_unaligned_supported)
        do_peeling = false;
    }

  if (do_peeling && !dr0)
    {
      /* Peeling is possible, but there is no data access that is not supported
         unless aligned. So we try to choose the best possible peeling.  */

      /* We should get here only if there are drs with known misalignment.  */
      gcc_assert (!all_misalignments_unknown);

      /* Choose the best peeling from the hash table.  */
      dr0 = vect_peeling_hash_choose_best_peeling (loop_vinfo, &npeel);
      if (!dr0 || !npeel)
        do_peeling = false;
    }

  if (do_peeling)
    {
      stmt = DR_STMT (dr0);
      stmt_info = vinfo_for_stmt (stmt);
      vectype = STMT_VINFO_VECTYPE (stmt_info);
      nelements = TYPE_VECTOR_SUBPARTS (vectype);

      if (known_alignment_for_access_p (dr0))
        {
	  bool negative = tree_int_cst_compare (DR_STEP (dr0),
						size_zero_node) < 0;
          if (!npeel)
            {
              /* Since it's known at compile time, compute the number of
                 iterations in the peeled loop (the peeling factor) for use in
                 updating DR_MISALIGNMENT values.  The peeling factor is the
                 vectorization factor minus the misalignment as an element
                 count.  */
              mis = DR_MISALIGNMENT (dr0);
              mis /= GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (dr0))));
              npeel = ((negative ? mis - nelements : nelements - mis)
		       & (nelements - 1));
            }

	  /* For interleaved data access every iteration accesses all the
	     members of the group, therefore we divide the number of iterations
	     by the group size.  */
	  stmt_info = vinfo_for_stmt (DR_STMT (dr0));
	  if (STMT_VINFO_STRIDED_ACCESS (stmt_info))
	    npeel /= DR_GROUP_SIZE (stmt_info);

          if (vect_print_dump_info (REPORT_DETAILS))
            fprintf (vect_dump, "Try peeling by %d", npeel);
        }

      /* Ensure that all data refs can be vectorized after the peel.  */
      FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
        {
          int save_misalignment;

	  if (dr == dr0)
	    continue;

	  stmt = DR_STMT (dr);
	  stmt_info = vinfo_for_stmt (stmt);
	  /* For interleaving, only the alignment of the first access
            matters.  */
	  if (STMT_VINFO_STRIDED_ACCESS (stmt_info)
	      && DR_GROUP_FIRST_DR (stmt_info) != stmt)
	    continue;

	  save_misalignment = DR_MISALIGNMENT (dr);
	  vect_update_misalignment_for_peel (dr, dr0, npeel);
	  supportable_dr_alignment = vect_supportable_dr_alignment (dr, false);
	  SET_DR_MISALIGNMENT (dr, save_misalignment);

	  if (!supportable_dr_alignment)
	    {
	      do_peeling = false;
	      break;
	    }
	}

      if (do_peeling && known_alignment_for_access_p (dr0) && npeel == 0)
        {
          stat = vect_verify_datarefs_alignment (loop_vinfo, NULL);
          if (!stat)
            do_peeling = false;
          else
            return stat;
        }

      if (do_peeling)
        {
          /* (1.2) Update the DR_MISALIGNMENT of each data reference DR_i.
             If the misalignment of DR_i is identical to that of dr0 then set
             DR_MISALIGNMENT (DR_i) to zero.  If the misalignment of DR_i and
             dr0 are known at compile time then increment DR_MISALIGNMENT (DR_i)
             by the peeling factor times the element size of DR_i (MOD the
             vectorization factor times the size).  Otherwise, the
             misalignment of DR_i must be set to unknown.  */
	  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
	    if (dr != dr0)
	      vect_update_misalignment_for_peel (dr, dr0, npeel);

          LOOP_VINFO_UNALIGNED_DR (loop_vinfo) = dr0;
          if (npeel)
            LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo) = npeel;
          else
            LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo) = DR_MISALIGNMENT (dr0);
	  SET_DR_MISALIGNMENT (dr0, 0);
	  if (vect_print_dump_info (REPORT_ALIGNMENT))
            fprintf (vect_dump, "Alignment of access forced using peeling.");

          if (vect_print_dump_info (REPORT_DETAILS))
            fprintf (vect_dump, "Peeling for alignment will be applied.");

	  stat = vect_verify_datarefs_alignment (loop_vinfo, NULL);
	  gcc_assert (stat);
          return stat;
        }
    }


  /* (2) Versioning to force alignment.  */

  /* Try versioning if:
     1) flag_tree_vect_loop_version is TRUE
     2) optimize loop for speed
     3) there is at least one unsupported misaligned data ref with an unknown
        misalignment, and
     4) all misaligned data refs with a known misalignment are supported, and
     5) the number of runtime alignment checks is within reason.  */

  do_versioning =
	flag_tree_vect_loop_version
	&& optimize_loop_nest_for_speed_p (loop)
	&& (!loop->inner); /* FORNOW */

  if (do_versioning)
    {
      FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
        {
	  stmt = DR_STMT (dr);
	  stmt_info = vinfo_for_stmt (stmt);

	  /* For interleaving, only the alignment of the first access
	     matters.  */
	  if (aligned_access_p (dr)
	      || (STMT_VINFO_STRIDED_ACCESS (stmt_info)
		  && DR_GROUP_FIRST_DR (stmt_info) != stmt))
	    continue;

	  supportable_dr_alignment = vect_supportable_dr_alignment (dr, false);

          if (!supportable_dr_alignment)
            {
              gimple stmt;
              int mask;
              tree vectype;

              if (known_alignment_for_access_p (dr)
                  || VEC_length (gimple,
                                 LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo))
                     >= (unsigned) PARAM_VALUE (PARAM_VECT_MAX_VERSION_FOR_ALIGNMENT_CHECKS))
                {
                  do_versioning = false;
                  break;
                }

              stmt = DR_STMT (dr);
              vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt));
              gcc_assert (vectype);

              /* The rightmost bits of an aligned address must be zeros.
                 Construct the mask needed for this test.  For example,
                 GET_MODE_SIZE for the vector mode V4SI is 16 bytes so the
                 mask must be 15 = 0xf. */
              mask = GET_MODE_SIZE (TYPE_MODE (vectype)) - 1;

              /* FORNOW: use the same mask to test all potentially unaligned
                 references in the loop.  The vectorizer currently supports
                 a single vector size, see the reference to
                 GET_MODE_NUNITS (TYPE_MODE (vectype)) where the
                 vectorization factor is computed.  */
              gcc_assert (!LOOP_VINFO_PTR_MASK (loop_vinfo)
                          || LOOP_VINFO_PTR_MASK (loop_vinfo) == mask);
              LOOP_VINFO_PTR_MASK (loop_vinfo) = mask;
              VEC_safe_push (gimple, heap,
                             LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo),
                             DR_STMT (dr));
            }
        }

      /* Versioning requires at least one misaligned data reference.  */
      if (!LOOP_REQUIRES_VERSIONING_FOR_ALIGNMENT (loop_vinfo))
        do_versioning = false;
      else if (!do_versioning)
        VEC_truncate (gimple, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo), 0);
    }

  if (do_versioning)
    {
      VEC(gimple,heap) *may_misalign_stmts
        = LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo);
      gimple stmt;

      /* It can now be assumed that the data references in the statements
         in LOOP_VINFO_MAY_MISALIGN_STMTS will be aligned in the version
         of the loop being vectorized.  */
      FOR_EACH_VEC_ELT (gimple, may_misalign_stmts, i, stmt)
        {
          stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
          dr = STMT_VINFO_DATA_REF (stmt_info);
	  SET_DR_MISALIGNMENT (dr, 0);
	  if (vect_print_dump_info (REPORT_ALIGNMENT))
            fprintf (vect_dump, "Alignment of access forced using versioning.");
        }

      if (vect_print_dump_info (REPORT_DETAILS))
        fprintf (vect_dump, "Versioning for alignment will be applied.");

      /* Peeling and versioning can't be done together at this time.  */
      gcc_assert (! (do_peeling && do_versioning));

      stat = vect_verify_datarefs_alignment (loop_vinfo, NULL);
      gcc_assert (stat);
      return stat;
    }

  /* This point is reached if neither peeling nor versioning is being done.  */
  gcc_assert (! (do_peeling || do_versioning));

  stat = vect_verify_datarefs_alignment (loop_vinfo, NULL);
  return stat;
}


/* Function vect_find_same_alignment_drs.

   Update group and alignment relations according to the chosen
   vectorization factor.  */

static void
vect_find_same_alignment_drs (struct data_dependence_relation *ddr,
			      loop_vec_info loop_vinfo)
{
  unsigned int i;
  struct loop *loop = LOOP_VINFO_LOOP (loop_vinfo);
  int vectorization_factor = LOOP_VINFO_VECT_FACTOR (loop_vinfo);
  struct data_reference *dra = DDR_A (ddr);
  struct data_reference *drb = DDR_B (ddr);
  stmt_vec_info stmtinfo_a = vinfo_for_stmt (DR_STMT (dra));
  stmt_vec_info stmtinfo_b = vinfo_for_stmt (DR_STMT (drb));
  int dra_size = GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (dra))));
  int drb_size = GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (drb))));
  lambda_vector dist_v;
  unsigned int loop_depth;

  if (DDR_ARE_DEPENDENT (ddr) == chrec_known)
    return;

  if (dra == drb)
    return;

  if (DDR_ARE_DEPENDENT (ddr) == chrec_dont_know)
    return;

  /* Loop-based vectorization and known data dependence.  */
  if (DDR_NUM_DIST_VECTS (ddr) == 0)
    return;

  /* Data-dependence analysis reports a distance vector of zero
     for data-references that overlap only in the first iteration
     but have different sign step (see PR45764).
     So as a sanity check require equal DR_STEP.  */
  if (!operand_equal_p (DR_STEP (dra), DR_STEP (drb), 0))
    return;

  loop_depth = index_in_loop_nest (loop->num, DDR_LOOP_NEST (ddr));
  FOR_EACH_VEC_ELT (lambda_vector, DDR_DIST_VECTS (ddr), i, dist_v)
    {
      int dist = dist_v[loop_depth];

      if (vect_print_dump_info (REPORT_DR_DETAILS))
	fprintf (vect_dump, "dependence distance  = %d.", dist);

      /* Same loop iteration.  */
      if (dist == 0
	  || (dist % vectorization_factor == 0 && dra_size == drb_size))
	{
	  /* Two references with distance zero have the same alignment.  */
	  VEC_safe_push (dr_p, heap, STMT_VINFO_SAME_ALIGN_REFS (stmtinfo_a), drb);
	  VEC_safe_push (dr_p, heap, STMT_VINFO_SAME_ALIGN_REFS (stmtinfo_b), dra);
	  if (vect_print_dump_info (REPORT_ALIGNMENT))
	    fprintf (vect_dump, "accesses have the same alignment.");
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    {
	      fprintf (vect_dump, "dependence distance modulo vf == 0 between ");
	      print_generic_expr (vect_dump, DR_REF (dra), TDF_SLIM);
	      fprintf (vect_dump, " and ");
	      print_generic_expr (vect_dump, DR_REF (drb), TDF_SLIM);
	    }
	}
    }
}


/* Function vect_analyze_data_refs_alignment

   Analyze the alignment of the data-references in the loop.
   Return FALSE if a data reference is found that cannot be vectorized.  */

bool
vect_analyze_data_refs_alignment (loop_vec_info loop_vinfo,
                                  bb_vec_info bb_vinfo)
{
  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_analyze_data_refs_alignment ===");

  /* Mark groups of data references with same alignment using
     data dependence information.  */
  if (loop_vinfo)
    {
      VEC (ddr_p, heap) *ddrs = LOOP_VINFO_DDRS (loop_vinfo);
      struct data_dependence_relation *ddr;
      unsigned int i;

      FOR_EACH_VEC_ELT (ddr_p, ddrs, i, ddr)
	vect_find_same_alignment_drs (ddr, loop_vinfo);
    }

  if (!vect_compute_data_refs_alignment (loop_vinfo, bb_vinfo))
    {
      if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	fprintf (vect_dump,
		 "not vectorized: can't calculate alignment for data ref.");
      return false;
    }

  return true;
}


/* Analyze groups of strided accesses: check that DR belongs to a group of
   strided accesses of legal size, step, etc.  Detect gaps, single element
   interleaving, and other special cases. Set strided access info.
   Collect groups of strided stores for further use in SLP analysis.  */

static bool
vect_analyze_group_access (struct data_reference *dr)
{
  tree step = DR_STEP (dr);
  tree scalar_type = TREE_TYPE (DR_REF (dr));
  HOST_WIDE_INT type_size = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (scalar_type));
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_info);
  HOST_WIDE_INT dr_step = TREE_INT_CST_LOW (step);
  HOST_WIDE_INT stride, last_accessed_element = 1;
  bool slp_impossible = false;
  struct loop *loop = NULL;

  if (loop_vinfo)
    loop = LOOP_VINFO_LOOP (loop_vinfo);

  /* For interleaving, STRIDE is STEP counted in elements, i.e., the size of the
     interleaving group (including gaps).  */
  stride = dr_step / type_size;

  /* Not consecutive access is possible only if it is a part of interleaving.  */
  if (!DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)))
    {
      /* Check if it this DR is a part of interleaving, and is a single
	 element of the group that is accessed in the loop.  */

      /* Gaps are supported only for loads. STEP must be a multiple of the type
	 size.  The size of the group must be a power of 2.  */
      if (DR_IS_READ (dr)
	  && (dr_step % type_size) == 0
	  && stride > 0
	  && exact_log2 (stride) != -1)
	{
	  DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)) = stmt;
	  DR_GROUP_SIZE (vinfo_for_stmt (stmt)) = stride;
	  if (vect_print_dump_info (REPORT_DR_DETAILS))
	    {
	      fprintf (vect_dump, "Detected single element interleaving ");
	      print_generic_expr (vect_dump, DR_REF (dr), TDF_SLIM);
	      fprintf (vect_dump, " step ");
	      print_generic_expr (vect_dump, step, TDF_SLIM);
	    }

	  if (loop_vinfo)
	    {
	      if (vect_print_dump_info (REPORT_DETAILS))
		fprintf (vect_dump, "Data access with gaps requires scalar "
				    "epilogue loop");
              if (loop->inner)
                {
                  if (vect_print_dump_info (REPORT_DETAILS))
                    fprintf (vect_dump, "Peeling for outer loop is not"
                                        " supported");
                  return false;
                }

              LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo) = true;
	    }

	  return true;
	}

      if (vect_print_dump_info (REPORT_DETAILS))
        {
 	  fprintf (vect_dump, "not consecutive access ");
          print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
        }

      if (bb_vinfo)
        {
          /* Mark the statement as unvectorizable.  */
          STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (DR_STMT (dr))) = false;
          return true;
        }
    
      return false;
    }

  if (DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)) == stmt)
    {
      /* First stmt in the interleaving chain. Check the chain.  */
      gimple next = DR_GROUP_NEXT_DR (vinfo_for_stmt (stmt));
      struct data_reference *data_ref = dr;
      unsigned int count = 1;
      tree next_step;
      tree prev_init = DR_INIT (data_ref);
      gimple prev = stmt;
      HOST_WIDE_INT diff, count_in_bytes, gaps = 0;

      while (next)
        {
          /* Skip same data-refs.  In case that two or more stmts share
             data-ref (supported only for loads), we vectorize only the first
             stmt, and the rest get their vectorized loads from the first
             one.  */
          if (!tree_int_cst_compare (DR_INIT (data_ref),
                                     DR_INIT (STMT_VINFO_DATA_REF (
						   vinfo_for_stmt (next)))))
            {
              if (DR_IS_WRITE (data_ref))
                {
                  if (vect_print_dump_info (REPORT_DETAILS))
                    fprintf (vect_dump, "Two store stmts share the same dr.");
                  return false;
                }

              /* Check that there is no load-store dependencies for this loads
                 to prevent a case of load-store-load to the same location.  */
              if (DR_GROUP_READ_WRITE_DEPENDENCE (vinfo_for_stmt (next))
                  || DR_GROUP_READ_WRITE_DEPENDENCE (vinfo_for_stmt (prev)))
                {
                  if (vect_print_dump_info (REPORT_DETAILS))
                    fprintf (vect_dump,
                             "READ_WRITE dependence in interleaving.");
                  return false;
                }

              /* For load use the same data-ref load.  */
              DR_GROUP_SAME_DR_STMT (vinfo_for_stmt (next)) = prev;

              prev = next;
              next = DR_GROUP_NEXT_DR (vinfo_for_stmt (next));
              continue;
            }

          prev = next;

          /* Check that all the accesses have the same STEP.  */
          next_step = DR_STEP (STMT_VINFO_DATA_REF (vinfo_for_stmt (next)));
          if (tree_int_cst_compare (step, next_step))
            {
              if (vect_print_dump_info (REPORT_DETAILS))
                fprintf (vect_dump, "not consecutive access in interleaving");
              return false;
            }

          data_ref = STMT_VINFO_DATA_REF (vinfo_for_stmt (next));
          /* Check that the distance between two accesses is equal to the type
             size. Otherwise, we have gaps.  */
          diff = (TREE_INT_CST_LOW (DR_INIT (data_ref))
                  - TREE_INT_CST_LOW (prev_init)) / type_size;
	  if (diff != 1)
	    {
	      /* FORNOW: SLP of accesses with gaps is not supported.  */
	      slp_impossible = true;
	      if (DR_IS_WRITE (data_ref))
		{
		  if (vect_print_dump_info (REPORT_DETAILS))
		    fprintf (vect_dump, "interleaved store with gaps");
		  return false;
		}

              gaps += diff - 1;
	    }

	  last_accessed_element += diff;

          /* Store the gap from the previous member of the group. If there is no
             gap in the access, DR_GROUP_GAP is always 1.  */
          DR_GROUP_GAP (vinfo_for_stmt (next)) = diff;

          prev_init = DR_INIT (data_ref);
          next = DR_GROUP_NEXT_DR (vinfo_for_stmt (next));
          /* Count the number of data-refs in the chain.  */
          count++;
        }

      /* COUNT is the number of accesses found, we multiply it by the size of
         the type to get COUNT_IN_BYTES.  */
      count_in_bytes = type_size * count;

      /* Check that the size of the interleaving (including gaps) is not
         greater than STEP.  */
      if (dr_step && dr_step < count_in_bytes + gaps * type_size)
        {
          if (vect_print_dump_info (REPORT_DETAILS))
            {
              fprintf (vect_dump, "interleaving size is greater than step for ");
              print_generic_expr (vect_dump, DR_REF (dr), TDF_SLIM);
            }
          return false;
        }

      /* Check that the size of the interleaving is equal to STEP for stores,
         i.e., that there are no gaps.  */
      if (dr_step && dr_step != count_in_bytes)
        {
          if (DR_IS_READ (dr))
            {
              slp_impossible = true;
              /* There is a gap after the last load in the group. This gap is a
                 difference between the stride and the number of elements. When
                 there is no gap, this difference should be 0.  */
              DR_GROUP_GAP (vinfo_for_stmt (stmt)) = stride - count;
            }
          else
            {
              if (vect_print_dump_info (REPORT_DETAILS))
                fprintf (vect_dump, "interleaved store with gaps");
              return false;
            }
        }

      /* Check that STEP is a multiple of type size.  */
      if (dr_step && (dr_step % type_size) != 0)
        {
          if (vect_print_dump_info (REPORT_DETAILS))
            {
              fprintf (vect_dump, "step is not a multiple of type size: step ");
              print_generic_expr (vect_dump, step, TDF_SLIM);
              fprintf (vect_dump, " size ");
              print_generic_expr (vect_dump, TYPE_SIZE_UNIT (scalar_type),
                                  TDF_SLIM);
            }
          return false;
        }

      /* FORNOW: we handle only interleaving that is a power of 2.
         We don't fail here if it may be still possible to vectorize the
         group using SLP.  If not, the size of the group will be checked in
         vect_analyze_operations, and the vectorization will fail.  */
      if (exact_log2 (stride) == -1)
	{
	  if (vect_print_dump_info (REPORT_DETAILS))
	    fprintf (vect_dump, "interleaving is not a power of 2");

	  if (slp_impossible)
	    return false;
	}

      if (stride == 0)
        stride = count;

      DR_GROUP_SIZE (vinfo_for_stmt (stmt)) = stride;
      if (vect_print_dump_info (REPORT_DETAILS))
        fprintf (vect_dump, "Detected interleaving of size %d", (int)stride);

      /* SLP: create an SLP data structure for every interleaving group of
	 stores for further analysis in vect_analyse_slp.  */
      if (DR_IS_WRITE (dr) && !slp_impossible)
        {
          if (loop_vinfo)
            VEC_safe_push (gimple, heap, LOOP_VINFO_STRIDED_STORES (loop_vinfo),
                           stmt);
          if (bb_vinfo)
            VEC_safe_push (gimple, heap, BB_VINFO_STRIDED_STORES (bb_vinfo),
                           stmt);
        }

      /* There is a gap in the end of the group.  */
      if (stride - last_accessed_element > 0 && loop_vinfo)
	{
	  if (vect_print_dump_info (REPORT_DETAILS))
	    fprintf (vect_dump, "Data access with gaps requires scalar "
				"epilogue loop");
          if (loop->inner)
            {
              if (vect_print_dump_info (REPORT_DETAILS))
                fprintf (vect_dump, "Peeling for outer loop is not supported");
              return false;
            }

          LOOP_VINFO_PEELING_FOR_GAPS (loop_vinfo) = true;
	}
    }

  return true;
}


/* Analyze the access pattern of the data-reference DR.
   In case of non-consecutive accesses call vect_analyze_group_access() to
   analyze groups of strided accesses.  */

static bool
vect_analyze_data_ref_access (struct data_reference *dr)
{
  tree step = DR_STEP (dr);
  tree scalar_type = TREE_TYPE (DR_REF (dr));
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  struct loop *loop = NULL;
  HOST_WIDE_INT dr_step = TREE_INT_CST_LOW (step);

  if (loop_vinfo)
    loop = LOOP_VINFO_LOOP (loop_vinfo);

  if (loop_vinfo && !step)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "bad data-ref access in loop");
      return false;
    }

  /* Don't allow invariant accesses in loops.  */
  if (loop_vinfo && dr_step == 0)
    return false;

  if (loop && nested_in_vect_loop_p (loop, stmt))
    {
      /* Interleaved accesses are not yet supported within outer-loop
        vectorization for references in the inner-loop.  */
      DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)) = NULL;

      /* For the rest of the analysis we use the outer-loop step.  */
      step = STMT_VINFO_DR_STEP (stmt_info);
      dr_step = TREE_INT_CST_LOW (step);

      if (dr_step == 0)
	{
	  if (vect_print_dump_info (REPORT_ALIGNMENT))
	    fprintf (vect_dump, "zero step in outer loop.");
	  if (DR_IS_READ (dr))
  	    return true;
	  else
	    return false;
	}
    }

  /* Consecutive?  */
  if (!tree_int_cst_compare (step, TYPE_SIZE_UNIT (scalar_type))
      || (dr_step < 0
	  && !compare_tree_int (TYPE_SIZE_UNIT (scalar_type), -dr_step)))
    {
      /* Mark that it is not interleaving.  */
      DR_GROUP_FIRST_DR (vinfo_for_stmt (stmt)) = NULL;
      return true;
    }

  if (loop && nested_in_vect_loop_p (loop, stmt))
    {
      if (vect_print_dump_info (REPORT_ALIGNMENT))
	fprintf (vect_dump, "strided access in outer loop.");
      return false;
    }

  /* Not consecutive access - check if it's a part of interleaving group.  */
  return vect_analyze_group_access (dr);
}


/* Function vect_analyze_data_ref_accesses.

   Analyze the access pattern of all the data references in the loop.

   FORNOW: the only access pattern that is considered vectorizable is a
	   simple step 1 (consecutive) access.

   FORNOW: handle only arrays and pointer accesses.  */

bool
vect_analyze_data_ref_accesses (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
{
  unsigned int i;
  VEC (data_reference_p, heap) *datarefs;
  struct data_reference *dr;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_analyze_data_ref_accesses ===");

  if (loop_vinfo)
    datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
  else
    datarefs = BB_VINFO_DATAREFS (bb_vinfo);

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    if (STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (DR_STMT (dr))) 
        && !vect_analyze_data_ref_access (dr))
      {
	if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	  fprintf (vect_dump, "not vectorized: complicated access pattern.");

        if (bb_vinfo)
          {
            /* Mark the statement as not vectorizable.  */
            STMT_VINFO_VECTORIZABLE (vinfo_for_stmt (DR_STMT (dr))) = false;
            continue;
          }
        else
          return false;
      }

  return true;
}

/* Function vect_prune_runtime_alias_test_list.

   Prune a list of ddrs to be tested at run-time by versioning for alias.
   Return FALSE if resulting list of ddrs is longer then allowed by
   PARAM_VECT_MAX_VERSION_FOR_ALIAS_CHECKS, otherwise return TRUE.  */

bool
vect_prune_runtime_alias_test_list (loop_vec_info loop_vinfo)
{
  VEC (ddr_p, heap) * ddrs =
    LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo);
  unsigned i, j;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_prune_runtime_alias_test_list ===");

  for (i = 0; i < VEC_length (ddr_p, ddrs); )
    {
      bool found;
      ddr_p ddr_i;

      ddr_i = VEC_index (ddr_p, ddrs, i);
      found = false;

      for (j = 0; j < i; j++)
        {
	  ddr_p ddr_j = VEC_index (ddr_p, ddrs, j);

	  if (vect_vfa_range_equal (ddr_i, ddr_j))
	    {
	      if (vect_print_dump_info (REPORT_DR_DETAILS))
		{
		  fprintf (vect_dump, "found equal ranges ");
		  print_generic_expr (vect_dump, DR_REF (DDR_A (ddr_i)), TDF_SLIM);
		  fprintf (vect_dump, ", ");
		  print_generic_expr (vect_dump, DR_REF (DDR_B (ddr_i)), TDF_SLIM);
		  fprintf (vect_dump, " and ");
		  print_generic_expr (vect_dump, DR_REF (DDR_A (ddr_j)), TDF_SLIM);
		  fprintf (vect_dump, ", ");
		  print_generic_expr (vect_dump, DR_REF (DDR_B (ddr_j)), TDF_SLIM);
		}
	      found = true;
	      break;
	    }
	}

      if (found)
      {
	VEC_ordered_remove (ddr_p, ddrs, i);
	continue;
      }
      i++;
    }

  if (VEC_length (ddr_p, ddrs) >
       (unsigned) PARAM_VALUE (PARAM_VECT_MAX_VERSION_FOR_ALIAS_CHECKS))
    {
      if (vect_print_dump_info (REPORT_DR_DETAILS))
	{
	  fprintf (vect_dump,
		   "disable versioning for alias - max number of generated "
		   "checks exceeded.");
	}

      VEC_truncate (ddr_p, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo), 0);

      return false;
    }

  return true;
}


/* Function vect_analyze_data_refs.

  Find all the data references in the loop or basic block.

   The general structure of the analysis of data refs in the vectorizer is as
   follows:
   1- vect_analyze_data_refs(loop/bb): call
      compute_data_dependences_for_loop/bb to find and analyze all data-refs
      in the loop/bb and their dependences.
   2- vect_analyze_dependences(): apply dependence testing using ddrs.
   3- vect_analyze_drs_alignment(): check that ref_stmt.alignment is ok.
   4- vect_analyze_drs_access(): check that ref_stmt.step is ok.

*/

bool
vect_analyze_data_refs (loop_vec_info loop_vinfo,
			bb_vec_info bb_vinfo,
			int *min_vf)
{
  struct loop *loop = NULL;
  basic_block bb = NULL;
  unsigned int i;
  VEC (data_reference_p, heap) *datarefs;
  struct data_reference *dr;
  tree scalar_type;
  bool res;

  if (vect_print_dump_info (REPORT_DETAILS))
    fprintf (vect_dump, "=== vect_analyze_data_refs ===\n");

  if (loop_vinfo)
    {
      loop = LOOP_VINFO_LOOP (loop_vinfo);
      res = compute_data_dependences_for_loop
	(loop, true,
	 &LOOP_VINFO_LOOP_NEST (loop_vinfo),
	 &LOOP_VINFO_DATAREFS (loop_vinfo),
	 &LOOP_VINFO_DDRS (loop_vinfo));

      if (!res)
	{
	  if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	    fprintf (vect_dump, "not vectorized: loop contains function calls"
		     " or data references that cannot be analyzed");
	  return false;
	}

      datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
    }
  else
    {
      bb = BB_VINFO_BB (bb_vinfo);
      res = compute_data_dependences_for_bb (bb, true,
					     &BB_VINFO_DATAREFS (bb_vinfo),
					     &BB_VINFO_DDRS (bb_vinfo));
      if (!res)
	{
	  if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	    fprintf (vect_dump, "not vectorized: basic block contains function"
		     " calls or data references that cannot be analyzed");
	  return false;
	}

      datarefs = BB_VINFO_DATAREFS (bb_vinfo);
    }

  /* Go through the data-refs, check that the analysis succeeded.  Update
     pointer from stmt_vec_info struct to DR and vectype.  */

  FOR_EACH_VEC_ELT (data_reference_p, datarefs, i, dr)
    {
      gimple stmt;
      stmt_vec_info stmt_info;
      tree base, offset, init;
      int vf;

      if (!dr || !DR_REF (dr))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	    fprintf (vect_dump, "not vectorized: unhandled data-ref ");
          return false;
        }

      stmt = DR_STMT (dr);
      stmt_info = vinfo_for_stmt (stmt);

      /* Check that analysis of the data-ref succeeded.  */
      if (!DR_BASE_ADDRESS (dr) || !DR_OFFSET (dr) || !DR_INIT (dr)
          || !DR_STEP (dr))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              fprintf (vect_dump, "not vectorized: data ref analysis failed ");
              print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
            }

          return false;
        }

      if (TREE_CODE (DR_BASE_ADDRESS (dr)) == INTEGER_CST)
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            fprintf (vect_dump, "not vectorized: base addr of dr is a "
                     "constant");
          return false;
        }

      if (TREE_THIS_VOLATILE (DR_REF (dr)))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              fprintf (vect_dump, "not vectorized: volatile type ");
              print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
            }
          return false;
        }

      base = unshare_expr (DR_BASE_ADDRESS (dr));
      offset = unshare_expr (DR_OFFSET (dr));
      init = unshare_expr (DR_INIT (dr));

      if (stmt_can_throw_internal (stmt))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              fprintf (vect_dump, "not vectorized: statement can throw an "
                       "exception ");
              print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
            }
          return false;
        }

      if (is_gimple_call (stmt))
	{
	  if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
	    {
	      fprintf (vect_dump, "not vectorized: dr in a call ");
	      print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
	    }
	  return false;
	}

      /* Update DR field in stmt_vec_info struct.  */

      /* If the dataref is in an inner-loop of the loop that is considered for
	 for vectorization, we also want to analyze the access relative to
	 the outer-loop (DR contains information only relative to the
	 inner-most enclosing loop).  We do that by building a reference to the
	 first location accessed by the inner-loop, and analyze it relative to
	 the outer-loop.  */
      if (loop && nested_in_vect_loop_p (loop, stmt))
	{
	  tree outer_step, outer_base, outer_init;
	  HOST_WIDE_INT pbitsize, pbitpos;
	  tree poffset;
	  enum machine_mode pmode;
	  int punsignedp, pvolatilep;
	  affine_iv base_iv, offset_iv;
	  tree dinit;

	  /* Build a reference to the first location accessed by the
	     inner-loop: *(BASE+INIT).  (The first location is actually
	     BASE+INIT+OFFSET, but we add OFFSET separately later).  */
          tree inner_base = build_fold_indirect_ref
                                (fold_build2 (POINTER_PLUS_EXPR,
                                              TREE_TYPE (base), base,
                                              fold_convert (sizetype, init)));

	  if (vect_print_dump_info (REPORT_DETAILS))
	    {
	      fprintf (vect_dump, "analyze in outer-loop: ");
	      print_generic_expr (vect_dump, inner_base, TDF_SLIM);
	    }

	  outer_base = get_inner_reference (inner_base, &pbitsize, &pbitpos,
		          &poffset, &pmode, &punsignedp, &pvolatilep, false);
	  gcc_assert (outer_base != NULL_TREE);

	  if (pbitpos % BITS_PER_UNIT != 0)
	    {
	      if (vect_print_dump_info (REPORT_DETAILS))
		fprintf (vect_dump, "failed: bit offset alignment.\n");
	      return false;
	    }

	  outer_base = build_fold_addr_expr (outer_base);
	  if (!simple_iv (loop, loop_containing_stmt (stmt), outer_base,
                          &base_iv, false))
	    {
	      if (vect_print_dump_info (REPORT_DETAILS))
		fprintf (vect_dump, "failed: evolution of base is not affine.\n");
	      return false;
	    }

	  if (offset)
	    {
	      if (poffset)
		poffset = fold_build2 (PLUS_EXPR, TREE_TYPE (offset), offset,
                                       poffset);
	      else
		poffset = offset;
	    }

	  if (!poffset)
	    {
	      offset_iv.base = ssize_int (0);
	      offset_iv.step = ssize_int (0);
	    }
	  else if (!simple_iv (loop, loop_containing_stmt (stmt), poffset,
                               &offset_iv, false))
	    {
	      if (vect_print_dump_info (REPORT_DETAILS))
	        fprintf (vect_dump, "evolution of offset is not affine.\n");
	      return false;
	    }

	  outer_init = ssize_int (pbitpos / BITS_PER_UNIT);
	  split_constant_offset (base_iv.base, &base_iv.base, &dinit);
	  outer_init =  size_binop (PLUS_EXPR, outer_init, dinit);
	  split_constant_offset (offset_iv.base, &offset_iv.base, &dinit);
	  outer_init =  size_binop (PLUS_EXPR, outer_init, dinit);

	  outer_step = size_binop (PLUS_EXPR,
				fold_convert (ssizetype, base_iv.step),
				fold_convert (ssizetype, offset_iv.step));

	  STMT_VINFO_DR_STEP (stmt_info) = outer_step;
	  /* FIXME: Use canonicalize_base_object_address (base_iv.base); */
	  STMT_VINFO_DR_BASE_ADDRESS (stmt_info) = base_iv.base;
	  STMT_VINFO_DR_INIT (stmt_info) = outer_init;
	  STMT_VINFO_DR_OFFSET (stmt_info) =
				fold_convert (ssizetype, offset_iv.base);
	  STMT_VINFO_DR_ALIGNED_TO (stmt_info) =
				size_int (highest_pow2_factor (offset_iv.base));

	  if (vect_print_dump_info (REPORT_DETAILS))
	    {
	      fprintf (vect_dump, "\touter base_address: ");
	      print_generic_expr (vect_dump, STMT_VINFO_DR_BASE_ADDRESS (stmt_info), TDF_SLIM);
	      fprintf (vect_dump, "\n\touter offset from base address: ");
	      print_generic_expr (vect_dump, STMT_VINFO_DR_OFFSET (stmt_info), TDF_SLIM);
	      fprintf (vect_dump, "\n\touter constant offset from base address: ");
	      print_generic_expr (vect_dump, STMT_VINFO_DR_INIT (stmt_info), TDF_SLIM);
	      fprintf (vect_dump, "\n\touter step: ");
	      print_generic_expr (vect_dump, STMT_VINFO_DR_STEP (stmt_info), TDF_SLIM);
	      fprintf (vect_dump, "\n\touter aligned to: ");
	      print_generic_expr (vect_dump, STMT_VINFO_DR_ALIGNED_TO (stmt_info), TDF_SLIM);
	    }
	}

      if (STMT_VINFO_DATA_REF (stmt_info))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              fprintf (vect_dump,
                       "not vectorized: more than one data ref in stmt: ");
              print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
            }
          return false;
        }

      STMT_VINFO_DATA_REF (stmt_info) = dr;

      /* Set vectype for STMT.  */
      scalar_type = TREE_TYPE (DR_REF (dr));
      STMT_VINFO_VECTYPE (stmt_info) =
                get_vectype_for_scalar_type (scalar_type);
      if (!STMT_VINFO_VECTYPE (stmt_info))
        {
          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
            {
              fprintf (vect_dump,
                       "not vectorized: no vectype for stmt: ");
              print_gimple_stmt (vect_dump, stmt, 0, TDF_SLIM);
              fprintf (vect_dump, " scalar_type: ");
              print_generic_expr (vect_dump, scalar_type, TDF_DETAILS);
            }

          if (bb_vinfo)
            {
              /* Mark the statement as not vectorizable.  */
              STMT_VINFO_VECTORIZABLE (stmt_info) = false;
              continue;
            }
          else
            return false;
        }

      /* Adjust the minimal vectorization factor according to the
	 vector type.  */
      vf = TYPE_VECTOR_SUBPARTS (STMT_VINFO_VECTYPE (stmt_info));
      if (vf > *min_vf)
	*min_vf = vf;
    }

  return true;
}


/* Function vect_get_new_vect_var.

   Returns a name for a new variable.  The current naming scheme appends the
   prefix "vect_" or "vect_p" (depending on the value of VAR_KIND) to
   the name of vectorizer generated variables, and appends that to NAME if
   provided.  */

tree
vect_get_new_vect_var (tree type, enum vect_var_kind var_kind, const char *name)
{
  const char *prefix;
  tree new_vect_var;

  switch (var_kind)
  {
  case vect_simple_var:
    prefix = "vect_";
    break;
  case vect_scalar_var:
    prefix = "stmp_";
    break;
  case vect_pointer_var:
    prefix = "vect_p";
    break;
  default:
    gcc_unreachable ();
  }

  if (name)
    {
      char* tmp = concat (prefix, name, NULL);
      new_vect_var = create_tmp_var (type, tmp);
      free (tmp);
    }
  else
    new_vect_var = create_tmp_var (type, prefix);

  /* Mark vector typed variable as a gimple register variable.  */
  if (TREE_CODE (type) == VECTOR_TYPE)
    DECL_GIMPLE_REG_P (new_vect_var) = true;

  return new_vect_var;
}


/* Function vect_create_addr_base_for_vector_ref.

   Create an expression that computes the address of the first memory location
   that will be accessed for a data reference.

   Input:
   STMT: The statement containing the data reference.
   NEW_STMT_LIST: Must be initialized to NULL_TREE or a statement list.
   OFFSET: Optional. If supplied, it is be added to the initial address.
   LOOP:    Specify relative to which loop-nest should the address be computed.
            For example, when the dataref is in an inner-loop nested in an
	    outer-loop that is now being vectorized, LOOP can be either the
	    outer-loop, or the inner-loop.  The first memory location accessed
	    by the following dataref ('in' points to short):

		for (i=0; i<N; i++)
		   for (j=0; j<M; j++)
		     s += in[i+j]

	    is as follows:
	    if LOOP=i_loop:	&in		(relative to i_loop)
	    if LOOP=j_loop: 	&in+i*2B	(relative to j_loop)

   Output:
   1. Return an SSA_NAME whose value is the address of the memory location of
      the first vector of the data reference.
   2. If new_stmt_list is not NULL_TREE after return then the caller must insert
      these statement(s) which define the returned SSA_NAME.

   FORNOW: We are only handling array accesses with step 1.  */

tree
vect_create_addr_base_for_vector_ref (gimple stmt,
				      gimple_seq *new_stmt_list,
				      tree offset,
				      struct loop *loop)
{
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info);
  tree data_ref_base = unshare_expr (DR_BASE_ADDRESS (dr));
  tree base_name;
  tree data_ref_base_var;
  tree vec_stmt;
  tree addr_base, addr_expr;
  tree dest;
  gimple_seq seq = NULL;
  tree base_offset = unshare_expr (DR_OFFSET (dr));
  tree init = unshare_expr (DR_INIT (dr));
  tree vect_ptr_type;
  tree step = TYPE_SIZE_UNIT (TREE_TYPE (DR_REF (dr)));
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  tree base;

  if (loop_vinfo && loop && loop != (gimple_bb (stmt))->loop_father)
    {
      struct loop *outer_loop = LOOP_VINFO_LOOP (loop_vinfo);

      gcc_assert (nested_in_vect_loop_p (outer_loop, stmt));

      data_ref_base = unshare_expr (STMT_VINFO_DR_BASE_ADDRESS (stmt_info));
      base_offset = unshare_expr (STMT_VINFO_DR_OFFSET (stmt_info));
      init = unshare_expr (STMT_VINFO_DR_INIT (stmt_info));
    }

  if (loop_vinfo)
    base_name = build_fold_indirect_ref (data_ref_base);
  else
    {
      base_offset = ssize_int (0);
      init = ssize_int (0);
      base_name = build_fold_indirect_ref (unshare_expr (DR_REF (dr)));
    }

  data_ref_base_var = create_tmp_var (TREE_TYPE (data_ref_base), "batmp");
  add_referenced_var (data_ref_base_var);
  data_ref_base = force_gimple_operand (data_ref_base, &seq, true,
					data_ref_base_var);
  gimple_seq_add_seq (new_stmt_list, seq);

  /* Create base_offset */
  base_offset = size_binop (PLUS_EXPR,
			    fold_convert (sizetype, base_offset),
			    fold_convert (sizetype, init));
  dest = create_tmp_var (sizetype, "base_off");
  add_referenced_var (dest);
  base_offset = force_gimple_operand (base_offset, &seq, true, dest);
  gimple_seq_add_seq (new_stmt_list, seq);

  if (offset)
    {
      tree tmp = create_tmp_var (sizetype, "offset");

      add_referenced_var (tmp);
      offset = fold_build2 (MULT_EXPR, sizetype,
			    fold_convert (sizetype, offset), step);
      base_offset = fold_build2 (PLUS_EXPR, sizetype,
				 base_offset, offset);
      base_offset = force_gimple_operand (base_offset, &seq, false, tmp);
      gimple_seq_add_seq (new_stmt_list, seq);
    }

  /* base + base_offset */
  if (loop_vinfo)
    addr_base = fold_build2 (POINTER_PLUS_EXPR, TREE_TYPE (data_ref_base),
                             data_ref_base, base_offset);
  else
    {
      addr_base = build1 (ADDR_EXPR,
			  build_pointer_type (TREE_TYPE (DR_REF (dr))),
			  unshare_expr (DR_REF (dr)));
    }

  vect_ptr_type = build_pointer_type (STMT_VINFO_VECTYPE (stmt_info));
  base = get_base_address (DR_REF (dr));
  if (base
      && TREE_CODE (base) == MEM_REF)
    vect_ptr_type
      = build_qualified_type (vect_ptr_type,
			      TYPE_QUALS (TREE_TYPE (TREE_OPERAND (base, 0))));

  vec_stmt = fold_convert (vect_ptr_type, addr_base);
  addr_expr = vect_get_new_vect_var (vect_ptr_type, vect_pointer_var,
                                     get_name (base_name));
  add_referenced_var (addr_expr);
  vec_stmt = force_gimple_operand (vec_stmt, &seq, false, addr_expr);
  gimple_seq_add_seq (new_stmt_list, seq);

  if (DR_PTR_INFO (dr)
      && TREE_CODE (vec_stmt) == SSA_NAME)
    {
      duplicate_ssa_name_ptr_info (vec_stmt, DR_PTR_INFO (dr));
      if (offset)
	{
	  SSA_NAME_PTR_INFO (vec_stmt)->align = 1;
	  SSA_NAME_PTR_INFO (vec_stmt)->misalign = 0;
	}
    }

  if (vect_print_dump_info (REPORT_DETAILS))
    {
      fprintf (vect_dump, "created ");
      print_generic_expr (vect_dump, vec_stmt, TDF_SLIM);
    }

  return vec_stmt;
}


/* Function vect_create_data_ref_ptr.

   Create a new pointer to vector type (vp), that points to the first location
   accessed in the loop by STMT, along with the def-use update chain to
   appropriately advance the pointer through the loop iterations. Also set
   aliasing information for the pointer.  This vector pointer is used by the
   callers to this function to create a memory reference expression for vector
   load/store access.

   Input:
   1. STMT: a stmt that references memory. Expected to be of the form
         GIMPLE_ASSIGN <name, data-ref> or
	 GIMPLE_ASSIGN <data-ref, name>.
   2. AT_LOOP: the loop where the vector memref is to be created.
   3. OFFSET (optional): an offset to be added to the initial address accessed
        by the data-ref in STMT.
   4. ONLY_INIT: indicate if vp is to be updated in the loop, or remain
        pointing to the initial address.
   5. TYPE: if not NULL indicates the required type of the data-ref.

   Output:
   1. Declare a new ptr to vector_type, and have it point to the base of the
      data reference (initial addressed accessed by the data reference).
      For example, for vector of type V8HI, the following code is generated:

      v8hi *vp;
      vp = (v8hi *)initial_address;

      if OFFSET is not supplied:
         initial_address = &a[init];
      if OFFSET is supplied:
         initial_address = &a[init + OFFSET];

      Return the initial_address in INITIAL_ADDRESS.

   2. If ONLY_INIT is true, just return the initial pointer.  Otherwise, also
      update the pointer in each iteration of the loop.

      Return the increment stmt that updates the pointer in PTR_INCR.

   3. Set INV_P to true if the access pattern of the data reference in the
      vectorized loop is invariant.  Set it to false otherwise.

   4. Return the pointer.  */

tree
vect_create_data_ref_ptr (gimple stmt, struct loop *at_loop,
			  tree offset, tree *initial_address, gimple *ptr_incr,
			  bool only_init, bool *inv_p)
{
  tree base_name;
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  struct loop *loop = NULL;
  bool nested_in_vect_loop = false;
  struct loop *containing_loop = NULL;
  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
  tree vect_ptr_type;
  tree vect_ptr;
  tree new_temp;
  gimple vec_stmt;
  gimple_seq new_stmt_list = NULL;
  edge pe = NULL;
  basic_block new_bb;
  tree vect_ptr_init;
  struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info);
  tree vptr;
  gimple_stmt_iterator incr_gsi;
  bool insert_after;
  bool negative;
  tree indx_before_incr, indx_after_incr;
  gimple incr;
  tree step;
  bb_vec_info bb_vinfo = STMT_VINFO_BB_VINFO (stmt_info);
  gimple_stmt_iterator gsi = gsi_for_stmt (stmt);
  tree base;

  if (loop_vinfo)
    {
      loop = LOOP_VINFO_LOOP (loop_vinfo);
      nested_in_vect_loop = nested_in_vect_loop_p (loop, stmt);
      containing_loop = (gimple_bb (stmt))->loop_father;
      pe = loop_preheader_edge (loop);
    }
  else
    {
      gcc_assert (bb_vinfo);
      only_init = true;
      *ptr_incr = NULL;
    }

  /* Check the step (evolution) of the load in LOOP, and record
     whether it's invariant.  */
  if (nested_in_vect_loop)
    step = STMT_VINFO_DR_STEP (stmt_info);
  else
    step = DR_STEP (STMT_VINFO_DATA_REF (stmt_info));

  if (tree_int_cst_compare (step, size_zero_node) == 0)
    *inv_p = true;
  else
    *inv_p = false;
  negative = tree_int_cst_compare (step, size_zero_node) < 0;

  /* Create an expression for the first address accessed by this load
     in LOOP.  */
  base_name = build_fold_indirect_ref (unshare_expr (DR_BASE_ADDRESS (dr)));

  if (vect_print_dump_info (REPORT_DETAILS))
    {
      tree data_ref_base = base_name;
      fprintf (vect_dump, "create vector-pointer variable to type: ");
      print_generic_expr (vect_dump, vectype, TDF_SLIM);
      if (TREE_CODE (data_ref_base) == VAR_DECL
          || TREE_CODE (data_ref_base) == ARRAY_REF)
        fprintf (vect_dump, "  vectorizing an array ref: ");
      else if (TREE_CODE (data_ref_base) == COMPONENT_REF)
        fprintf (vect_dump, "  vectorizing a record based array ref: ");
      else if (TREE_CODE (data_ref_base) == SSA_NAME)
        fprintf (vect_dump, "  vectorizing a pointer ref: ");
      print_generic_expr (vect_dump, base_name, TDF_SLIM);
    }

  /* (1) Create the new vector-pointer variable.  */
  vect_ptr_type = build_pointer_type (vectype);
  base = get_base_address (DR_REF (dr));
  if (base
      && TREE_CODE (base) == MEM_REF)
    vect_ptr_type
      = build_qualified_type (vect_ptr_type,
			      TYPE_QUALS (TREE_TYPE (TREE_OPERAND (base, 0))));
  vect_ptr = vect_get_new_vect_var (vect_ptr_type, vect_pointer_var,
                                    get_name (base_name));

  /* Vector types inherit the alias set of their component type by default so
     we need to use a ref-all pointer if the data reference does not conflict
     with the created vector data reference because it is not addressable.  */
  if (!alias_sets_conflict_p (get_deref_alias_set (vect_ptr),
			      get_alias_set (DR_REF (dr))))
    {
      vect_ptr_type
	= build_pointer_type_for_mode (vectype,
				       TYPE_MODE (vect_ptr_type), true);
      vect_ptr = vect_get_new_vect_var (vect_ptr_type, vect_pointer_var,
					get_name (base_name));
    }

  /* Likewise for any of the data references in the stmt group.  */
  else if (STMT_VINFO_DR_GROUP_SIZE (stmt_info) > 1)
    {
      gimple orig_stmt = STMT_VINFO_DR_GROUP_FIRST_DR (stmt_info);
      do
	{
	  tree lhs = gimple_assign_lhs (orig_stmt);
	  if (!alias_sets_conflict_p (get_deref_alias_set (vect_ptr),
				      get_alias_set (lhs)))
	    {
	      vect_ptr_type
		= build_pointer_type_for_mode (vectype,
					       TYPE_MODE (vect_ptr_type), true);
	      vect_ptr
		= vect_get_new_vect_var (vect_ptr_type, vect_pointer_var,
					 get_name (base_name));
	      break;
	    }

	  orig_stmt = STMT_VINFO_DR_GROUP_NEXT_DR (vinfo_for_stmt (orig_stmt));
	}
      while (orig_stmt);
    }

  add_referenced_var (vect_ptr);

  /* Note: If the dataref is in an inner-loop nested in LOOP, and we are
     vectorizing LOOP (i.e., outer-loop vectorization), we need to create two
     def-use update cycles for the pointer: one relative to the outer-loop
     (LOOP), which is what steps (3) and (4) below do.  The other is relative
     to the inner-loop (which is the inner-most loop containing the dataref),
     and this is done be step (5) below.

     When vectorizing inner-most loops, the vectorized loop (LOOP) is also the
     inner-most loop, and so steps (3),(4) work the same, and step (5) is
     redundant.  Steps (3),(4) create the following:

	vp0 = &base_addr;
	LOOP:	vp1 = phi(vp0,vp2)
		...
		...
		vp2 = vp1 + step
		goto LOOP

     If there is an inner-loop nested in loop, then step (5) will also be
     applied, and an additional update in the inner-loop will be created:

	vp0 = &base_addr;
	LOOP:   vp1 = phi(vp0,vp2)
		...
        inner:     vp3 = phi(vp1,vp4)
	           vp4 = vp3 + inner_step
	           if () goto inner
		...
		vp2 = vp1 + step
		if () goto LOOP   */

  /* (2) Calculate the initial address the vector-pointer, and set
         the vector-pointer to point to it before the loop.  */

  /* Create: (&(base[init_val+offset]) in the loop preheader.  */

  new_temp = vect_create_addr_base_for_vector_ref (stmt, &new_stmt_list,
                                                   offset, loop);
  if (new_stmt_list)
    {
      if (pe)
        {
          new_bb = gsi_insert_seq_on_edge_immediate (pe, new_stmt_list);
          gcc_assert (!new_bb);
        }
      else
        gsi_insert_seq_before (&gsi, new_stmt_list, GSI_SAME_STMT);
    }

  *initial_address = new_temp;

  /* Create: p = (vectype *) initial_base  */
  if (TREE_CODE (new_temp) != SSA_NAME
      || !useless_type_conversion_p (vect_ptr_type, TREE_TYPE (new_temp)))
    {
      vec_stmt = gimple_build_assign (vect_ptr,
				      fold_convert (vect_ptr_type, new_temp));
      vect_ptr_init = make_ssa_name (vect_ptr, vec_stmt);
      /* Copy the points-to information if it exists. */
      if (DR_PTR_INFO (dr))
	duplicate_ssa_name_ptr_info (vect_ptr_init, DR_PTR_INFO (dr));
      gimple_assign_set_lhs (vec_stmt, vect_ptr_init);
      if (pe)
	{
	  new_bb = gsi_insert_on_edge_immediate (pe, vec_stmt);
	  gcc_assert (!new_bb);
	}
      else
	gsi_insert_before (&gsi, vec_stmt, GSI_SAME_STMT);
    }
  else
    vect_ptr_init = new_temp;

  /* (3) Handle the updating of the vector-pointer inside the loop.
     This is needed when ONLY_INIT is false, and also when AT_LOOP is the
     inner-loop nested in LOOP (during outer-loop vectorization).  */

  /* No update in loop is required.  */
  if (only_init && (!loop_vinfo || at_loop == loop))
    vptr = vect_ptr_init;
  else
    {
      /* The step of the vector pointer is the Vector Size.  */
      tree step = TYPE_SIZE_UNIT (vectype);
      /* One exception to the above is when the scalar step of the load in
	 LOOP is zero. In this case the step here is also zero.  */
      if (*inv_p)
	step = size_zero_node;
      else if (negative)
	step = fold_build1 (NEGATE_EXPR, TREE_TYPE (step), step);

      standard_iv_increment_position (loop, &incr_gsi, &insert_after);

      create_iv (vect_ptr_init,
		 fold_convert (vect_ptr_type, step),
		 vect_ptr, loop, &incr_gsi, insert_after,
		 &indx_before_incr, &indx_after_incr);
      incr = gsi_stmt (incr_gsi);
      set_vinfo_for_stmt (incr, new_stmt_vec_info (incr, loop_vinfo, NULL));

      /* Copy the points-to information if it exists. */
      if (DR_PTR_INFO (dr))
	{
	  duplicate_ssa_name_ptr_info (indx_before_incr, DR_PTR_INFO (dr));
	  duplicate_ssa_name_ptr_info (indx_after_incr, DR_PTR_INFO (dr));
	}
      if (ptr_incr)
	*ptr_incr = incr;

      vptr = indx_before_incr;
    }

  if (!nested_in_vect_loop || only_init)
    return vptr;


  /* (4) Handle the updating of the vector-pointer inside the inner-loop
     nested in LOOP, if exists.  */

  gcc_assert (nested_in_vect_loop);
  if (!only_init)
    {
      standard_iv_increment_position (containing_loop, &incr_gsi,
				      &insert_after);
      create_iv (vptr, fold_convert (vect_ptr_type, DR_STEP (dr)), vect_ptr,
		 containing_loop, &incr_gsi, insert_after, &indx_before_incr,
		 &indx_after_incr);
      incr = gsi_stmt (incr_gsi);
      set_vinfo_for_stmt (incr, new_stmt_vec_info (incr, loop_vinfo, NULL));

      /* Copy the points-to information if it exists. */
      if (DR_PTR_INFO (dr))
	{
	  duplicate_ssa_name_ptr_info (indx_before_incr, DR_PTR_INFO (dr));
	  duplicate_ssa_name_ptr_info (indx_after_incr, DR_PTR_INFO (dr));
	}
      if (ptr_incr)
	*ptr_incr = incr;

      return indx_before_incr;
    }
  else
    gcc_unreachable ();
}


/* Function bump_vector_ptr

   Increment a pointer (to a vector type) by vector-size. If requested,
   i.e. if PTR-INCR is given, then also connect the new increment stmt
   to the existing def-use update-chain of the pointer, by modifying
   the PTR_INCR as illustrated below:

   The pointer def-use update-chain before this function:
                        DATAREF_PTR = phi (p_0, p_2)
                        ....
        PTR_INCR:       p_2 = DATAREF_PTR + step

   The pointer def-use update-chain after this function:
                        DATAREF_PTR = phi (p_0, p_2)
                        ....
                        NEW_DATAREF_PTR = DATAREF_PTR + BUMP
                        ....
        PTR_INCR:       p_2 = NEW_DATAREF_PTR + step

   Input:
   DATAREF_PTR - ssa_name of a pointer (to vector type) that is being updated
                 in the loop.
   PTR_INCR - optional. The stmt that updates the pointer in each iteration of
	      the loop.  The increment amount across iterations is expected
	      to be vector_size.
   BSI - location where the new update stmt is to be placed.
   STMT - the original scalar memory-access stmt that is being vectorized.
   BUMP - optional. The offset by which to bump the pointer. If not given,
	  the offset is assumed to be vector_size.

   Output: Return NEW_DATAREF_PTR as illustrated above.

*/

tree
bump_vector_ptr (tree dataref_ptr, gimple ptr_incr, gimple_stmt_iterator *gsi,
		 gimple stmt, tree bump)
{
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info);
  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
  tree ptr_var = SSA_NAME_VAR (dataref_ptr);
  tree update = TYPE_SIZE_UNIT (vectype);
  gimple incr_stmt;
  ssa_op_iter iter;
  use_operand_p use_p;
  tree new_dataref_ptr;

  if (bump)
    update = bump;

  incr_stmt = gimple_build_assign_with_ops (POINTER_PLUS_EXPR, ptr_var,
					    dataref_ptr, update);
  new_dataref_ptr = make_ssa_name (ptr_var, incr_stmt);
  gimple_assign_set_lhs (incr_stmt, new_dataref_ptr);
  vect_finish_stmt_generation (stmt, incr_stmt, gsi);

  /* Copy the points-to information if it exists. */
  if (DR_PTR_INFO (dr))
    {
      duplicate_ssa_name_ptr_info (new_dataref_ptr, DR_PTR_INFO (dr));
      SSA_NAME_PTR_INFO (new_dataref_ptr)->align = 1;
      SSA_NAME_PTR_INFO (new_dataref_ptr)->misalign = 0;
    }

  if (!ptr_incr)
    return new_dataref_ptr;

  /* Update the vector-pointer's cross-iteration increment.  */
  FOR_EACH_SSA_USE_OPERAND (use_p, ptr_incr, iter, SSA_OP_USE)
    {
      tree use = USE_FROM_PTR (use_p);

      if (use == dataref_ptr)
        SET_USE (use_p, new_dataref_ptr);
      else
        gcc_assert (tree_int_cst_compare (use, update) == 0);
    }

  return new_dataref_ptr;
}


/* Function vect_create_destination_var.

   Create a new temporary of type VECTYPE.  */

tree
vect_create_destination_var (tree scalar_dest, tree vectype)
{
  tree vec_dest;
  const char *new_name;
  tree type;
  enum vect_var_kind kind;

  kind = vectype ? vect_simple_var : vect_scalar_var;
  type = vectype ? vectype : TREE_TYPE (scalar_dest);

  gcc_assert (TREE_CODE (scalar_dest) == SSA_NAME);

  new_name = get_name (scalar_dest);
  if (!new_name)
    new_name = "var_";
  vec_dest = vect_get_new_vect_var (type, kind, new_name);
  add_referenced_var (vec_dest);

  return vec_dest;
}

/* Function vect_strided_store_supported.

   Returns TRUE is INTERLEAVE_HIGH and INTERLEAVE_LOW operations are supported,
   and FALSE otherwise.  */

bool
vect_strided_store_supported (tree vectype)
{
  optab interleave_high_optab, interleave_low_optab;
  enum machine_mode mode;

  mode = TYPE_MODE (vectype);

  /* Check that the operation is supported.  */
  interleave_high_optab = optab_for_tree_code (VEC_INTERLEAVE_HIGH_EXPR,
					       vectype, optab_default);
  interleave_low_optab = optab_for_tree_code (VEC_INTERLEAVE_LOW_EXPR,
					      vectype, optab_default);
  if (!interleave_high_optab || !interleave_low_optab)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "no optab for interleave.");
      return false;
    }

  if (optab_handler (interleave_high_optab, mode) == CODE_FOR_nothing
      || optab_handler (interleave_low_optab, mode) == CODE_FOR_nothing)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "interleave op not supported by target.");
      return false;
    }

  return true;
}


/* Function vect_permute_store_chain.

   Given a chain of interleaved stores in DR_CHAIN of LENGTH that must be
   a power of 2, generate interleave_high/low stmts to reorder the data
   correctly for the stores.  Return the final references for stores in
   RESULT_CHAIN.

   E.g., LENGTH is 4 and the scalar type is short, i.e., VF is 8.
   The input is 4 vectors each containing 8 elements.  We assign a number to
   each element, the input sequence is:

   1st vec:   0  1  2  3  4  5  6  7
   2nd vec:   8  9 10 11 12 13 14 15
   3rd vec:  16 17 18 19 20 21 22 23
   4th vec:  24 25 26 27 28 29 30 31

   The output sequence should be:

   1st vec:  0  8 16 24  1  9 17 25
   2nd vec:  2 10 18 26  3 11 19 27
   3rd vec:  4 12 20 28  5 13 21 30
   4th vec:  6 14 22 30  7 15 23 31

   i.e., we interleave the contents of the four vectors in their order.

   We use interleave_high/low instructions to create such output.  The input of
   each interleave_high/low operation is two vectors:
   1st vec    2nd vec
   0 1 2 3    4 5 6 7
   the even elements of the result vector are obtained left-to-right from the
   high/low elements of the first vector.  The odd elements of the result are
   obtained left-to-right from the high/low elements of the second vector.
   The output of interleave_high will be:   0 4 1 5
   and of interleave_low:                   2 6 3 7


   The permutation is done in log LENGTH stages.  In each stage interleave_high
   and interleave_low stmts are created for each pair of vectors in DR_CHAIN,
   where the first argument is taken from the first half of DR_CHAIN and the
   second argument from it's second half.
   In our example,

   I1: interleave_high (1st vec, 3rd vec)
   I2: interleave_low (1st vec, 3rd vec)
   I3: interleave_high (2nd vec, 4th vec)
   I4: interleave_low (2nd vec, 4th vec)

   The output for the first stage is:

   I1:  0 16  1 17  2 18  3 19
   I2:  4 20  5 21  6 22  7 23
   I3:  8 24  9 25 10 26 11 27
   I4: 12 28 13 29 14 30 15 31

   The output of the second stage, i.e. the final result is:

   I1:  0  8 16 24  1  9 17 25
   I2:  2 10 18 26  3 11 19 27
   I3:  4 12 20 28  5 13 21 30
   I4:  6 14 22 30  7 15 23 31.  */

bool
vect_permute_store_chain (VEC(tree,heap) *dr_chain,
			  unsigned int length,
			  gimple stmt,
			  gimple_stmt_iterator *gsi,
			  VEC(tree,heap) **result_chain)
{
  tree perm_dest, vect1, vect2, high, low;
  gimple perm_stmt;
  tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt));
  int i;
  unsigned int j;
  enum tree_code high_code, low_code;

  /* Check that the operation is supported.  */
  if (!vect_strided_store_supported (vectype))
    return false;

  *result_chain = VEC_copy (tree, heap, dr_chain);

  for (i = 0; i < exact_log2 (length); i++)
    {
      for (j = 0; j < length/2; j++)
	{
	  vect1 = VEC_index (tree, dr_chain, j);
	  vect2 = VEC_index (tree, dr_chain, j+length/2);

	  /* Create interleaving stmt:
	     in the case of big endian:
                                high = interleave_high (vect1, vect2)
             and in the case of little endian:
                                high = interleave_low (vect1, vect2).  */
	  perm_dest = create_tmp_var (vectype, "vect_inter_high");
	  DECL_GIMPLE_REG_P (perm_dest) = 1;
	  add_referenced_var (perm_dest);
          if (BYTES_BIG_ENDIAN)
	    {
	      high_code = VEC_INTERLEAVE_HIGH_EXPR;
	      low_code = VEC_INTERLEAVE_LOW_EXPR;
	    }
	  else
	    {
	      low_code = VEC_INTERLEAVE_HIGH_EXPR;
	      high_code = VEC_INTERLEAVE_LOW_EXPR;
	    }
	  perm_stmt = gimple_build_assign_with_ops (high_code, perm_dest,
						    vect1, vect2);
	  high = make_ssa_name (perm_dest, perm_stmt);
	  gimple_assign_set_lhs (perm_stmt, high);
	  vect_finish_stmt_generation (stmt, perm_stmt, gsi);
	  VEC_replace (tree, *result_chain, 2*j, high);

	  /* Create interleaving stmt:
             in the case of big endian:
                               low  = interleave_low (vect1, vect2)
             and in the case of little endian:
                               low  = interleave_high (vect1, vect2).  */
	  perm_dest = create_tmp_var (vectype, "vect_inter_low");
	  DECL_GIMPLE_REG_P (perm_dest) = 1;
	  add_referenced_var (perm_dest);
	  perm_stmt = gimple_build_assign_with_ops (low_code, perm_dest,
						    vect1, vect2);
	  low = make_ssa_name (perm_dest, perm_stmt);
	  gimple_assign_set_lhs (perm_stmt, low);
	  vect_finish_stmt_generation (stmt, perm_stmt, gsi);
	  VEC_replace (tree, *result_chain, 2*j+1, low);
	}
      dr_chain = VEC_copy (tree, heap, *result_chain);
    }
  return true;
}

/* Function vect_setup_realignment

   This function is called when vectorizing an unaligned load using
   the dr_explicit_realign[_optimized] scheme.
   This function generates the following code at the loop prolog:

      p = initial_addr;
   x  msq_init = *(floor(p));   # prolog load
      realignment_token = call target_builtin;
    loop:
   x  msq = phi (msq_init, ---)

   The stmts marked with x are generated only for the case of
   dr_explicit_realign_optimized.

   The code above sets up a new (vector) pointer, pointing to the first
   location accessed by STMT, and a "floor-aligned" load using that pointer.
   It also generates code to compute the "realignment-token" (if the relevant
   target hook was defined), and creates a phi-node at the loop-header bb
   whose arguments are the result of the prolog-load (created by this
   function) and the result of a load that takes place in the loop (to be
   created by the caller to this function).

   For the case of dr_explicit_realign_optimized:
   The caller to this function uses the phi-result (msq) to create the
   realignment code inside the loop, and sets up the missing phi argument,
   as follows:
    loop:
      msq = phi (msq_init, lsq)
      lsq = *(floor(p'));        # load in loop
      result = realign_load (msq, lsq, realignment_token);

   For the case of dr_explicit_realign:
    loop:
      msq = *(floor(p)); 	# load in loop
      p' = p + (VS-1);
      lsq = *(floor(p'));	# load in loop
      result = realign_load (msq, lsq, realignment_token);

   Input:
   STMT - (scalar) load stmt to be vectorized. This load accesses
          a memory location that may be unaligned.
   BSI - place where new code is to be inserted.
   ALIGNMENT_SUPPORT_SCHEME - which of the two misalignment handling schemes
			      is used.

   Output:
   REALIGNMENT_TOKEN - the result of a call to the builtin_mask_for_load
                       target hook, if defined.
   Return value - the result of the loop-header phi node.  */

tree
vect_setup_realignment (gimple stmt, gimple_stmt_iterator *gsi,
                        tree *realignment_token,
			enum dr_alignment_support alignment_support_scheme,
			tree init_addr,
			struct loop **at_loop)
{
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  struct data_reference *dr = STMT_VINFO_DATA_REF (stmt_info);
  struct loop *loop = NULL;
  edge pe = NULL;
  tree scalar_dest = gimple_assign_lhs (stmt);
  tree vec_dest;
  gimple inc;
  tree ptr;
  tree data_ref;
  gimple new_stmt;
  basic_block new_bb;
  tree msq_init = NULL_TREE;
  tree new_temp;
  gimple phi_stmt;
  tree msq = NULL_TREE;
  gimple_seq stmts = NULL;
  bool inv_p;
  bool compute_in_loop = false;
  bool nested_in_vect_loop = false;
  struct loop *containing_loop = (gimple_bb (stmt))->loop_father;
  struct loop *loop_for_initial_load = NULL;

  if (loop_vinfo)
    {
      loop = LOOP_VINFO_LOOP (loop_vinfo);
      nested_in_vect_loop = nested_in_vect_loop_p (loop, stmt);
    }

  gcc_assert (alignment_support_scheme == dr_explicit_realign
	      || alignment_support_scheme == dr_explicit_realign_optimized);

  /* We need to generate three things:
     1. the misalignment computation
     2. the extra vector load (for the optimized realignment scheme).
     3. the phi node for the two vectors from which the realignment is
      done (for the optimized realignment scheme).  */

  /* 1. Determine where to generate the misalignment computation.

     If INIT_ADDR is NULL_TREE, this indicates that the misalignment
     calculation will be generated by this function, outside the loop (in the
     preheader).  Otherwise, INIT_ADDR had already been computed for us by the
     caller, inside the loop.

     Background: If the misalignment remains fixed throughout the iterations of
     the loop, then both realignment schemes are applicable, and also the
     misalignment computation can be done outside LOOP.  This is because we are
     vectorizing LOOP, and so the memory accesses in LOOP advance in steps that
     are a multiple of VS (the Vector Size), and therefore the misalignment in
     different vectorized LOOP iterations is always the same.
     The problem arises only if the memory access is in an inner-loop nested
     inside LOOP, which is now being vectorized using outer-loop vectorization.
     This is the only case when the misalignment of the memory access may not
     remain fixed throughout the iterations of the inner-loop (as explained in
     detail in vect_supportable_dr_alignment).  In this case, not only is the
     optimized realignment scheme not applicable, but also the misalignment
     computation (and generation of the realignment token that is passed to
     REALIGN_LOAD) have to be done inside the loop.

     In short, INIT_ADDR indicates whether we are in a COMPUTE_IN_LOOP mode
     or not, which in turn determines if the misalignment is computed inside
     the inner-loop, or outside LOOP.  */

  if (init_addr != NULL_TREE || !loop_vinfo)
    {
      compute_in_loop = true;
      gcc_assert (alignment_support_scheme == dr_explicit_realign);
    }


  /* 2. Determine where to generate the extra vector load.

     For the optimized realignment scheme, instead of generating two vector
     loads in each iteration, we generate a single extra vector load in the
     preheader of the loop, and in each iteration reuse the result of the
     vector load from the previous iteration.  In case the memory access is in
     an inner-loop nested inside LOOP, which is now being vectorized using
     outer-loop vectorization, we need to determine whether this initial vector
     load should be generated at the preheader of the inner-loop, or can be
     generated at the preheader of LOOP.  If the memory access has no evolution
     in LOOP, it can be generated in the preheader of LOOP. Otherwise, it has
     to be generated inside LOOP (in the preheader of the inner-loop).  */

  if (nested_in_vect_loop)
    {
      tree outerloop_step = STMT_VINFO_DR_STEP (stmt_info);
      bool invariant_in_outerloop =
            (tree_int_cst_compare (outerloop_step, size_zero_node) == 0);
      loop_for_initial_load = (invariant_in_outerloop ? loop : loop->inner);
    }
  else
    loop_for_initial_load = loop;
  if (at_loop)
    *at_loop = loop_for_initial_load;

  if (loop_for_initial_load)
    pe = loop_preheader_edge (loop_for_initial_load);

  /* 3. For the case of the optimized realignment, create the first vector
      load at the loop preheader.  */

  if (alignment_support_scheme == dr_explicit_realign_optimized)
    {
      /* Create msq_init = *(floor(p1)) in the loop preheader  */

      gcc_assert (!compute_in_loop);
      vec_dest = vect_create_destination_var (scalar_dest, vectype);
      ptr = vect_create_data_ref_ptr (stmt, loop_for_initial_load, NULL_TREE,
				      &init_addr, &inc, true, &inv_p);
      new_stmt = gimple_build_assign_with_ops
		   (BIT_AND_EXPR, NULL_TREE, ptr,
		    build_int_cst (TREE_TYPE (ptr),
				   -(HOST_WIDE_INT)TYPE_ALIGN_UNIT (vectype)));
      new_temp = make_ssa_name (SSA_NAME_VAR (ptr), new_stmt);
      gimple_assign_set_lhs (new_stmt, new_temp);
      new_bb = gsi_insert_on_edge_immediate (pe, new_stmt);
      gcc_assert (!new_bb);
      data_ref
	= build2 (MEM_REF, TREE_TYPE (vec_dest), new_temp,
		  build_int_cst (reference_alias_ptr_type (DR_REF (dr)), 0));
      new_stmt = gimple_build_assign (vec_dest, data_ref);
      new_temp = make_ssa_name (vec_dest, new_stmt);
      gimple_assign_set_lhs (new_stmt, new_temp);
      mark_symbols_for_renaming (new_stmt);
      if (pe)
        {
          new_bb = gsi_insert_on_edge_immediate (pe, new_stmt);
          gcc_assert (!new_bb);
        }
      else
         gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);

      msq_init = gimple_assign_lhs (new_stmt);
    }

  /* 4. Create realignment token using a target builtin, if available.
      It is done either inside the containing loop, or before LOOP (as
      determined above).  */

  if (targetm.vectorize.builtin_mask_for_load)
    {
      tree builtin_decl;

      /* Compute INIT_ADDR - the initial addressed accessed by this memref.  */
      if (!init_addr)
	{
	  /* Generate the INIT_ADDR computation outside LOOP.  */
	  init_addr = vect_create_addr_base_for_vector_ref (stmt, &stmts,
							NULL_TREE, loop);
          if (loop)
            {
   	      pe = loop_preheader_edge (loop);
	      new_bb = gsi_insert_seq_on_edge_immediate (pe, stmts);
	      gcc_assert (!new_bb);
            }
          else
             gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
	}

      builtin_decl = targetm.vectorize.builtin_mask_for_load ();
      new_stmt = gimple_build_call (builtin_decl, 1, init_addr);
      vec_dest =
	vect_create_destination_var (scalar_dest,
				     gimple_call_return_type (new_stmt));
      new_temp = make_ssa_name (vec_dest, new_stmt);
      gimple_call_set_lhs (new_stmt, new_temp);

      if (compute_in_loop)
	gsi_insert_before (gsi, new_stmt, GSI_SAME_STMT);
      else
	{
	  /* Generate the misalignment computation outside LOOP.  */
	  pe = loop_preheader_edge (loop);
	  new_bb = gsi_insert_on_edge_immediate (pe, new_stmt);
	  gcc_assert (!new_bb);
	}

      *realignment_token = gimple_call_lhs (new_stmt);

      /* The result of the CALL_EXPR to this builtin is determined from
         the value of the parameter and no global variables are touched
         which makes the builtin a "const" function.  Requiring the
         builtin to have the "const" attribute makes it unnecessary
         to call mark_call_clobbered.  */
      gcc_assert (TREE_READONLY (builtin_decl));
    }

  if (alignment_support_scheme == dr_explicit_realign)
    return msq;

  gcc_assert (!compute_in_loop);
  gcc_assert (alignment_support_scheme == dr_explicit_realign_optimized);


  /* 5. Create msq = phi <msq_init, lsq> in loop  */

  pe = loop_preheader_edge (containing_loop);
  vec_dest = vect_create_destination_var (scalar_dest, vectype);
  msq = make_ssa_name (vec_dest, NULL);
  phi_stmt = create_phi_node (msq, containing_loop->header);
  SSA_NAME_DEF_STMT (msq) = phi_stmt;
  add_phi_arg (phi_stmt, msq_init, pe, UNKNOWN_LOCATION);

  return msq;
}


/* Function vect_strided_load_supported.

   Returns TRUE is EXTRACT_EVEN and EXTRACT_ODD operations are supported,
   and FALSE otherwise.  */

bool
vect_strided_load_supported (tree vectype)
{
  optab perm_even_optab, perm_odd_optab;
  enum machine_mode mode;

  mode = TYPE_MODE (vectype);

  perm_even_optab = optab_for_tree_code (VEC_EXTRACT_EVEN_EXPR, vectype,
					 optab_default);
  if (!perm_even_optab)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "no optab for perm_even.");
      return false;
    }

  if (optab_handler (perm_even_optab, mode) == CODE_FOR_nothing)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "perm_even op not supported by target.");
      return false;
    }

  perm_odd_optab = optab_for_tree_code (VEC_EXTRACT_ODD_EXPR, vectype,
					optab_default);
  if (!perm_odd_optab)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "no optab for perm_odd.");
      return false;
    }

  if (optab_handler (perm_odd_optab, mode) == CODE_FOR_nothing)
    {
      if (vect_print_dump_info (REPORT_DETAILS))
	fprintf (vect_dump, "perm_odd op not supported by target.");
      return false;
    }
  return true;
}


/* Function vect_permute_load_chain.

   Given a chain of interleaved loads in DR_CHAIN of LENGTH that must be
   a power of 2, generate extract_even/odd stmts to reorder the input data
   correctly.  Return the final references for loads in RESULT_CHAIN.

   E.g., LENGTH is 4 and the scalar type is short, i.e., VF is 8.
   The input is 4 vectors each containing 8 elements. We assign a number to each
   element, the input sequence is:

   1st vec:   0  1  2  3  4  5  6  7
   2nd vec:   8  9 10 11 12 13 14 15
   3rd vec:  16 17 18 19 20 21 22 23
   4th vec:  24 25 26 27 28 29 30 31

   The output sequence should be:

   1st vec:  0 4  8 12 16 20 24 28
   2nd vec:  1 5  9 13 17 21 25 29
   3rd vec:  2 6 10 14 18 22 26 30
   4th vec:  3 7 11 15 19 23 27 31

   i.e., the first output vector should contain the first elements of each
   interleaving group, etc.

   We use extract_even/odd instructions to create such output.  The input of
   each extract_even/odd operation is two vectors
   1st vec    2nd vec
   0 1 2 3    4 5 6 7

   and the output is the vector of extracted even/odd elements.  The output of
   extract_even will be:   0 2 4 6
   and of extract_odd:     1 3 5 7


   The permutation is done in log LENGTH stages.  In each stage extract_even
   and extract_odd stmts are created for each pair of vectors in DR_CHAIN in
   their order.  In our example,

   E1: extract_even (1st vec, 2nd vec)
   E2: extract_odd (1st vec, 2nd vec)
   E3: extract_even (3rd vec, 4th vec)
   E4: extract_odd (3rd vec, 4th vec)

   The output for the first stage will be:

   E1:  0  2  4  6  8 10 12 14
   E2:  1  3  5  7  9 11 13 15
   E3: 16 18 20 22 24 26 28 30
   E4: 17 19 21 23 25 27 29 31

   In order to proceed and create the correct sequence for the next stage (or
   for the correct output, if the second stage is the last one, as in our
   example), we first put the output of extract_even operation and then the
   output of extract_odd in RESULT_CHAIN (which is then copied to DR_CHAIN).
   The input for the second stage is:

   1st vec (E1):  0  2  4  6  8 10 12 14
   2nd vec (E3): 16 18 20 22 24 26 28 30
   3rd vec (E2):  1  3  5  7  9 11 13 15
   4th vec (E4): 17 19 21 23 25 27 29 31

   The output of the second stage:

   E1: 0 4  8 12 16 20 24 28
   E2: 2 6 10 14 18 22 26 30
   E3: 1 5  9 13 17 21 25 29
   E4: 3 7 11 15 19 23 27 31

   And RESULT_CHAIN after reordering:

   1st vec (E1):  0 4  8 12 16 20 24 28
   2nd vec (E3):  1 5  9 13 17 21 25 29
   3rd vec (E2):  2 6 10 14 18 22 26 30
   4th vec (E4):  3 7 11 15 19 23 27 31.  */

bool
vect_permute_load_chain (VEC(tree,heap) *dr_chain,
			 unsigned int length,
			 gimple stmt,
			 gimple_stmt_iterator *gsi,
			 VEC(tree,heap) **result_chain)
{
  tree perm_dest, data_ref, first_vect, second_vect;
  gimple perm_stmt;
  tree vectype = STMT_VINFO_VECTYPE (vinfo_for_stmt (stmt));
  int i;
  unsigned int j;

  /* Check that the operation is supported.  */
  if (!vect_strided_load_supported (vectype))
    return false;

  *result_chain = VEC_copy (tree, heap, dr_chain);
  for (i = 0; i < exact_log2 (length); i++)
    {
      for (j = 0; j < length; j +=2)
	{
	  first_vect = VEC_index (tree, dr_chain, j);
	  second_vect = VEC_index (tree, dr_chain, j+1);

	  /* data_ref = permute_even (first_data_ref, second_data_ref);  */
	  perm_dest = create_tmp_var (vectype, "vect_perm_even");
	  DECL_GIMPLE_REG_P (perm_dest) = 1;
	  add_referenced_var (perm_dest);

	  perm_stmt = gimple_build_assign_with_ops (VEC_EXTRACT_EVEN_EXPR,
						    perm_dest, first_vect,
						    second_vect);

	  data_ref = make_ssa_name (perm_dest, perm_stmt);
	  gimple_assign_set_lhs (perm_stmt, data_ref);
	  vect_finish_stmt_generation (stmt, perm_stmt, gsi);
	  mark_symbols_for_renaming (perm_stmt);

	  VEC_replace (tree, *result_chain, j/2, data_ref);

	  /* data_ref = permute_odd (first_data_ref, second_data_ref);  */
	  perm_dest = create_tmp_var (vectype, "vect_perm_odd");
	  DECL_GIMPLE_REG_P (perm_dest) = 1;
	  add_referenced_var (perm_dest);

	  perm_stmt = gimple_build_assign_with_ops (VEC_EXTRACT_ODD_EXPR,
						    perm_dest, first_vect,
						    second_vect);
	  data_ref = make_ssa_name (perm_dest, perm_stmt);
	  gimple_assign_set_lhs (perm_stmt, data_ref);
	  vect_finish_stmt_generation (stmt, perm_stmt, gsi);
	  mark_symbols_for_renaming (perm_stmt);

	  VEC_replace (tree, *result_chain, j/2+length/2, data_ref);
	}
      dr_chain = VEC_copy (tree, heap, *result_chain);
    }
  return true;
}


/* Function vect_transform_strided_load.

   Given a chain of input interleaved data-refs (in DR_CHAIN), build statements
   to perform their permutation and ascribe the result vectorized statements to
   the scalar statements.
*/

bool
vect_transform_strided_load (gimple stmt, VEC(tree,heap) *dr_chain, int size,
			     gimple_stmt_iterator *gsi)
{
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  gimple first_stmt = DR_GROUP_FIRST_DR (stmt_info);
  gimple next_stmt, new_stmt;
  VEC(tree,heap) *result_chain = NULL;
  unsigned int i, gap_count;
  tree tmp_data_ref;

  /* DR_CHAIN contains input data-refs that are a part of the interleaving.
     RESULT_CHAIN is the output of vect_permute_load_chain, it contains permuted
     vectors, that are ready for vector computation.  */
  result_chain = VEC_alloc (tree, heap, size);
  /* Permute.  */
  if (!vect_permute_load_chain (dr_chain, size, stmt, gsi, &result_chain))
    return false;

  /* Put a permuted data-ref in the VECTORIZED_STMT field.
     Since we scan the chain starting from it's first node, their order
     corresponds the order of data-refs in RESULT_CHAIN.  */
  next_stmt = first_stmt;
  gap_count = 1;
  FOR_EACH_VEC_ELT (tree, result_chain, i, tmp_data_ref)
    {
      if (!next_stmt)
	break;

      /* Skip the gaps.  Loads created for the gaps will be removed by dead
       code elimination pass later.  No need to check for the first stmt in
       the group, since it always exists.
       DR_GROUP_GAP is the number of steps in elements from the previous
       access (if there is no gap DR_GROUP_GAP is 1).  We skip loads that
       correspond to the gaps.  */
      if (next_stmt != first_stmt
          && gap_count < DR_GROUP_GAP (vinfo_for_stmt (next_stmt)))
      {
        gap_count++;
        continue;
      }

      while (next_stmt)
        {
	  new_stmt = SSA_NAME_DEF_STMT (tmp_data_ref);
	  /* We assume that if VEC_STMT is not NULL, this is a case of multiple
	     copies, and we put the new vector statement in the first available
	     RELATED_STMT.  */
	  if (!STMT_VINFO_VEC_STMT (vinfo_for_stmt (next_stmt)))
	    STMT_VINFO_VEC_STMT (vinfo_for_stmt (next_stmt)) = new_stmt;
	  else
            {
              if (!DR_GROUP_SAME_DR_STMT (vinfo_for_stmt (next_stmt)))
                {
 	          gimple prev_stmt =
		    STMT_VINFO_VEC_STMT (vinfo_for_stmt (next_stmt));
	          gimple rel_stmt =
		    STMT_VINFO_RELATED_STMT (vinfo_for_stmt (prev_stmt));
	          while (rel_stmt)
		    {
		      prev_stmt = rel_stmt;
		      rel_stmt =
                        STMT_VINFO_RELATED_STMT (vinfo_for_stmt (rel_stmt));
		    }

  	          STMT_VINFO_RELATED_STMT (vinfo_for_stmt (prev_stmt)) =
                    new_stmt;
                }
            }

	  next_stmt = DR_GROUP_NEXT_DR (vinfo_for_stmt (next_stmt));
	  gap_count = 1;
	  /* If NEXT_STMT accesses the same DR as the previous statement,
	     put the same TMP_DATA_REF as its vectorized statement; otherwise
	     get the next data-ref from RESULT_CHAIN.  */
	  if (!next_stmt || !DR_GROUP_SAME_DR_STMT (vinfo_for_stmt (next_stmt)))
	    break;
        }
    }

  VEC_free (tree, heap, result_chain);
  return true;
}

/* Function vect_force_dr_alignment_p.

   Returns whether the alignment of a DECL can be forced to be aligned
   on ALIGNMENT bit boundary.  */

bool
vect_can_force_dr_alignment_p (const_tree decl, unsigned int alignment)
{
  if (TREE_CODE (decl) != VAR_DECL)
    return false;

  if (DECL_EXTERNAL (decl))
    return false;

  if (TREE_ASM_WRITTEN (decl))
    return false;

  if (TREE_STATIC (decl))
    return (alignment <= MAX_OFILE_ALIGNMENT);
  else
    return (alignment <= MAX_STACK_ALIGNMENT);
}


/* Return whether the data reference DR is supported with respect to its
   alignment.
   If CHECK_ALIGNED_ACCESSES is TRUE, check if the access is supported even
   it is aligned, i.e., check if it is possible to vectorize it with different
   alignment.  */

enum dr_alignment_support
vect_supportable_dr_alignment (struct data_reference *dr,
                               bool check_aligned_accesses)
{
  gimple stmt = DR_STMT (dr);
  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
  enum machine_mode mode = TYPE_MODE (vectype);
  loop_vec_info loop_vinfo = STMT_VINFO_LOOP_VINFO (stmt_info);
  struct loop *vect_loop = NULL;
  bool nested_in_vect_loop = false;

  if (aligned_access_p (dr) && !check_aligned_accesses)
    return dr_aligned;

  if (loop_vinfo)
    {
      vect_loop = LOOP_VINFO_LOOP (loop_vinfo);
      nested_in_vect_loop = nested_in_vect_loop_p (vect_loop, stmt);
    }

  /* Possibly unaligned access.  */

  /* We can choose between using the implicit realignment scheme (generating
     a misaligned_move stmt) and the explicit realignment scheme (generating
     aligned loads with a REALIGN_LOAD).  There are two variants to the
     explicit realignment scheme: optimized, and unoptimized.
     We can optimize the realignment only if the step between consecutive
     vector loads is equal to the vector size.  Since the vector memory
     accesses advance in steps of VS (Vector Size) in the vectorized loop, it
     is guaranteed that the misalignment amount remains the same throughout the
     execution of the vectorized loop.  Therefore, we can create the
     "realignment token" (the permutation mask that is passed to REALIGN_LOAD)
     at the loop preheader.

     However, in the case of outer-loop vectorization, when vectorizing a
     memory access in the inner-loop nested within the LOOP that is now being
     vectorized, while it is guaranteed that the misalignment of the
     vectorized memory access will remain the same in different outer-loop
     iterations, it is *not* guaranteed that is will remain the same throughout
     the execution of the inner-loop.  This is because the inner-loop advances
     with the original scalar step (and not in steps of VS).  If the inner-loop
     step happens to be a multiple of VS, then the misalignment remains fixed
     and we can use the optimized realignment scheme.  For example:

      for (i=0; i<N; i++)
        for (j=0; j<M; j++)
          s += a[i+j];

     When vectorizing the i-loop in the above example, the step between
     consecutive vector loads is 1, and so the misalignment does not remain
     fixed across the execution of the inner-loop, and the realignment cannot
     be optimized (as illustrated in the following pseudo vectorized loop):

      for (i=0; i<N; i+=4)
        for (j=0; j<M; j++){
          vs += vp[i+j]; // misalignment of &vp[i+j] is {0,1,2,3,0,1,2,3,...}
                         // when j is {0,1,2,3,4,5,6,7,...} respectively.
                         // (assuming that we start from an aligned address).
          }

     We therefore have to use the unoptimized realignment scheme:

      for (i=0; i<N; i+=4)
          for (j=k; j<M; j+=4)
          vs += vp[i+j]; // misalignment of &vp[i+j] is always k (assuming
                           // that the misalignment of the initial address is
                           // 0).

     The loop can then be vectorized as follows:

      for (k=0; k<4; k++){
        rt = get_realignment_token (&vp[k]);
        for (i=0; i<N; i+=4){
          v1 = vp[i+k];
          for (j=k; j<M; j+=4){
            v2 = vp[i+j+VS-1];
            va = REALIGN_LOAD <v1,v2,rt>;
            vs += va;
            v1 = v2;
          }
        }
    } */

  if (DR_IS_READ (dr))
    {
      bool is_packed = false;
      tree type = (TREE_TYPE (DR_REF (dr)));

      if (optab_handler (vec_realign_load_optab, mode) != CODE_FOR_nothing
	  && (!targetm.vectorize.builtin_mask_for_load
	      || targetm.vectorize.builtin_mask_for_load ()))
	{
	  tree vectype = STMT_VINFO_VECTYPE (stmt_info);
	  if ((nested_in_vect_loop
	       && (TREE_INT_CST_LOW (DR_STEP (dr))
	 	   != GET_MODE_SIZE (TYPE_MODE (vectype))))
              || !loop_vinfo)
	    return dr_explicit_realign;
	  else
	    return dr_explicit_realign_optimized;
	}
      if (!known_alignment_for_access_p (dr))
	{
	  tree ba = DR_BASE_OBJECT (dr);

	  if (ba)
	    is_packed = contains_packed_reference (ba);
	}

      if (targetm.vectorize.
	  support_vector_misalignment (mode, type,
				       DR_MISALIGNMENT (dr), is_packed))
	/* Can't software pipeline the loads, but can at least do them.  */
	return dr_unaligned_supported;
    }
  else
    {
      bool is_packed = false;
      tree type = (TREE_TYPE (DR_REF (dr)));

      if (!known_alignment_for_access_p (dr))
	{
	  tree ba = DR_BASE_OBJECT (dr);

	  if (ba)
	    is_packed = contains_packed_reference (ba);
	}

     if (targetm.vectorize.
         support_vector_misalignment (mode, type,
				      DR_MISALIGNMENT (dr), is_packed))
       return dr_unaligned_supported;
    }

  /* Unsupported.  */
  return dr_unaligned_unsupported;
}