summaryrefslogtreecommitdiff
path: root/lib/Transforms/Vectorize/LoopVectorize.cpp
blob: bd29d7d359d8bd9e7f18c4670912305c2f992cc6 (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
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
//===- LoopVectorize.cpp - A Loop Vectorizer ------------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This is the LLVM loop vectorizer. This pass modifies 'vectorizable' loops
// and generates target-independent LLVM-IR.
// The vectorizer uses the TargetTransformInfo analysis to estimate the costs
// of instructions in order to estimate the profitability of vectorization.
//
// The loop vectorizer combines consecutive loop iterations into a single
// 'wide' iteration. After this transformation the index is incremented
// by the SIMD vector width, and not by one.
//
// This pass has three parts:
// 1. The main loop pass that drives the different parts.
// 2. LoopVectorizationLegality - A unit that checks for the legality
//    of the vectorization.
// 3. InnerLoopVectorizer - A unit that performs the actual
//    widening of instructions.
// 4. LoopVectorizationCostModel - A unit that checks for the profitability
//    of vectorization. It decides on the optimal vector width, which
//    can be one, if vectorization is not profitable.
//
//===----------------------------------------------------------------------===//
//
// The reduction-variable vectorization is based on the paper:
//  D. Nuzman and R. Henderson. Multi-platform Auto-vectorization.
//
// Variable uniformity checks are inspired by:
//  Karrenberg, R. and Hack, S. Whole Function Vectorization.
//
// Other ideas/concepts are from:
//  A. Zaks and D. Nuzman. Autovectorization in GCC-two years later.
//
//  S. Maleki, Y. Gao, M. Garzaran, T. Wong and D. Padua.  An Evaluation of
//  Vectorizing Compilers.
//
//===----------------------------------------------------------------------===//

#define LV_NAME "loop-vectorize"
#define DEBUG_TYPE LV_NAME

#include "llvm/Transforms/Vectorize.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/EquivalenceClasses.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpander.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/IR/Verifier.h"
#include "llvm/Pass.h"
#include "llvm/Support/BranchProbability.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/PatternMatch.h"
#include "llvm/Support/ValueHandle.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetLibraryInfo.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Local.h"
#include <algorithm>
#include <map>

using namespace llvm;
using namespace llvm::PatternMatch;

static cl::opt<unsigned>
VectorizationFactor("force-vector-width", cl::init(0), cl::Hidden,
                    cl::desc("Sets the SIMD width. Zero is autoselect."));

static cl::opt<unsigned>
VectorizationUnroll("force-vector-unroll", cl::init(0), cl::Hidden,
                    cl::desc("Sets the vectorization unroll count. "
                             "Zero is autoselect."));

static cl::opt<bool>
EnableIfConversion("enable-if-conversion", cl::init(true), cl::Hidden,
                   cl::desc("Enable if-conversion during vectorization."));

/// We don't vectorize loops with a known constant trip count below this number.
static cl::opt<unsigned>
TinyTripCountVectorThreshold("vectorizer-min-trip-count", cl::init(16),
                             cl::Hidden,
                             cl::desc("Don't vectorize loops with a constant "
                                      "trip count that is smaller than this "
                                      "value."));

/// This enables versioning on the strides of symbolically striding memory
/// accesses in code like the following.
///   for (i = 0; i < N; ++i)
///     A[i * Stride1] += B[i * Stride2] ...
///
/// Will be roughly translated to
///    if (Stride1 == 1 && Stride2 == 1) {
///      for (i = 0; i < N; i+=4)
///       A[i:i+3] += ...
///    } else
///      ...
static cl::opt<bool> EnableMemAccessVersioning(
    "enable-mem-access-versioning", cl::init(true), cl::Hidden,
    cl::desc("Enable symblic stride memory access versioning"));

/// We don't unroll loops with a known constant trip count below this number.
static const unsigned TinyTripCountUnrollThreshold = 128;

/// When performing memory disambiguation checks at runtime do not make more
/// than this number of comparisons.
static const unsigned RuntimeMemoryCheckThreshold = 8;

/// Maximum simd width.
static const unsigned MaxVectorWidth = 64;

static cl::opt<unsigned> ForceTargetNumScalarRegs(
    "force-target-num-scalar-regs", cl::init(0), cl::Hidden,
    cl::desc("A flag that overrides the target's number of scalar registers."));

static cl::opt<unsigned> ForceTargetNumVectorRegs(
    "force-target-num-vector-regs", cl::init(0), cl::Hidden,
    cl::desc("A flag that overrides the target's number of vector registers."));

/// Maximum vectorization unroll count.
static const unsigned MaxUnrollFactor = 16;

static cl::opt<unsigned> ForceTargetMaxScalarUnrollFactor(
    "force-target-max-scalar-unroll", cl::init(0), cl::Hidden,
    cl::desc("A flag that overrides the target's max unroll factor for scalar "
             "loops."));

static cl::opt<unsigned> ForceTargetMaxVectorUnrollFactor(
    "force-target-max-vector-unroll", cl::init(0), cl::Hidden,
    cl::desc("A flag that overrides the target's max unroll factor for "
             "vectorized loops."));

static cl::opt<unsigned> ForceTargetInstructionCost(
    "force-target-instruction-cost", cl::init(0), cl::Hidden,
    cl::desc("A flag that overrides the target's expected cost for "
             "an instruction to a single constant value. Mostly "
             "useful for getting consistent testing."));

static cl::opt<unsigned> SmallLoopCost(
    "small-loop-cost", cl::init(20), cl::Hidden,
    cl::desc("The cost of a loop that is considered 'small' by the unroller."));

static cl::opt<bool> LoopVectorizeWithBlockFrequency(
    "loop-vectorize-with-block-frequency", cl::init(false), cl::Hidden,
    cl::desc("Enable the use of the block frequency analysis to access PGO "
             "heuristics minimizing code growth in cold regions and being more "
             "aggressive in hot regions."));

// Runtime unroll loops for load/store throughput.
static cl::opt<bool> EnableLoadStoreRuntimeUnroll(
    "enable-loadstore-runtime-unroll", cl::init(true), cl::Hidden,
    cl::desc("Enable runtime unrolling until load/store ports are saturated"));

/// The number of stores in a loop that are allowed to need predication.
static cl::opt<unsigned> NumberOfStoresToPredicate(
    "vectorize-num-stores-pred", cl::init(1), cl::Hidden,
    cl::desc("Max number of stores to be predicated behind an if."));

static cl::opt<bool> EnableIndVarRegisterHeur(
    "enable-ind-var-reg-heur", cl::init(true), cl::Hidden,
    cl::desc("Count the induction variable only once when unrolling"));

static cl::opt<bool> EnableCondStoresVectorization(
    "enable-cond-stores-vec", cl::init(false), cl::Hidden,
    cl::desc("Enable if predication of stores during vectorization."));

namespace {

// Forward declarations.
class LoopVectorizationLegality;
class LoopVectorizationCostModel;

/// InnerLoopVectorizer vectorizes loops which contain only one basic
/// block to a specified vectorization factor (VF).
/// This class performs the widening of scalars into vectors, or multiple
/// scalars. This class also implements the following features:
/// * It inserts an epilogue loop for handling loops that don't have iteration
///   counts that are known to be a multiple of the vectorization factor.
/// * It handles the code generation for reduction variables.
/// * Scalarization (implementation using scalars) of un-vectorizable
///   instructions.
/// InnerLoopVectorizer does not perform any vectorization-legality
/// checks, and relies on the caller to check for the different legality
/// aspects. The InnerLoopVectorizer relies on the
/// LoopVectorizationLegality class to provide information about the induction
/// and reduction variables that were found to a given vectorization factor.
class InnerLoopVectorizer {
public:
  InnerLoopVectorizer(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
                      DominatorTree *DT, const DataLayout *DL,
                      const TargetLibraryInfo *TLI, unsigned VecWidth,
                      unsigned UnrollFactor)
      : OrigLoop(OrigLoop), SE(SE), LI(LI), DT(DT), DL(DL), TLI(TLI),
        VF(VecWidth), UF(UnrollFactor), Builder(SE->getContext()), Induction(0),
        OldInduction(0), WidenMap(UnrollFactor), Legal(0) {}

  // Perform the actual loop widening (vectorization).
  void vectorize(LoopVectorizationLegality *L) {
    Legal = L;
    // Create a new empty loop. Unlink the old loop and connect the new one.
    createEmptyLoop();
    // Widen each instruction in the old loop to a new one in the new loop.
    // Use the Legality module to find the induction and reduction variables.
    vectorizeLoop();
    // Register the new loop and update the analysis passes.
    updateAnalysis();
  }

  virtual ~InnerLoopVectorizer() {}

protected:
  /// A small list of PHINodes.
  typedef SmallVector<PHINode*, 4> PhiVector;
  /// When we unroll loops we have multiple vector values for each scalar.
  /// This data structure holds the unrolled and vectorized values that
  /// originated from one scalar instruction.
  typedef SmallVector<Value*, 2> VectorParts;

  // When we if-convert we need create edge masks. We have to cache values so
  // that we don't end up with exponential recursion/IR.
  typedef DenseMap<std::pair<BasicBlock*, BasicBlock*>,
                   VectorParts> EdgeMaskCache;

  /// \brief Add code that checks at runtime if the accessed arrays overlap.
  ///
  /// Returns a pair of instructions where the first element is the first
  /// instruction generated in possibly a sequence of instructions and the
  /// second value is the final comparator value or NULL if no check is needed.
  std::pair<Instruction *, Instruction *> addRuntimeCheck(Instruction *Loc);

  /// \brief Add checks for strides that where assumed to be 1.
  ///
  /// Returns the last check instruction and the first check instruction in the
  /// pair as (first, last).
  std::pair<Instruction *, Instruction *> addStrideCheck(Instruction *Loc);

  /// Create an empty loop, based on the loop ranges of the old loop.
  void createEmptyLoop();
  /// Copy and widen the instructions from the old loop.
  virtual void vectorizeLoop();

  /// \brief The Loop exit block may have single value PHI nodes where the
  /// incoming value is 'Undef'. While vectorizing we only handled real values
  /// that were defined inside the loop. Here we fix the 'undef case'.
  /// See PR14725.
  void fixLCSSAPHIs();

  /// A helper function that computes the predicate of the block BB, assuming
  /// that the header block of the loop is set to True. It returns the *entry*
  /// mask for the block BB.
  VectorParts createBlockInMask(BasicBlock *BB);
  /// A helper function that computes the predicate of the edge between SRC
  /// and DST.
  VectorParts createEdgeMask(BasicBlock *Src, BasicBlock *Dst);

  /// A helper function to vectorize a single BB within the innermost loop.
  void vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV);

  /// Vectorize a single PHINode in a block. This method handles the induction
  /// variable canonicalization. It supports both VF = 1 for unrolled loops and
  /// arbitrary length vectors.
  void widenPHIInstruction(Instruction *PN, VectorParts &Entry,
                           unsigned UF, unsigned VF, PhiVector *PV);

  /// Insert the new loop to the loop hierarchy and pass manager
  /// and update the analysis passes.
  void updateAnalysis();

  /// This instruction is un-vectorizable. Implement it as a sequence
  /// of scalars. If \p IfPredicateStore is true we need to 'hide' each
  /// scalarized instruction behind an if block predicated on the control
  /// dependence of the instruction.
  virtual void scalarizeInstruction(Instruction *Instr,
                                    bool IfPredicateStore=false);

  /// Vectorize Load and Store instructions,
  virtual void vectorizeMemoryInstruction(Instruction *Instr);

  /// Create a broadcast instruction. This method generates a broadcast
  /// instruction (shuffle) for loop invariant values and for the induction
  /// value. If this is the induction variable then we extend it to N, N+1, ...
  /// this is needed because each iteration in the loop corresponds to a SIMD
  /// element.
  virtual Value *getBroadcastInstrs(Value *V);

  /// This function adds 0, 1, 2 ... to each vector element, starting at zero.
  /// If Negate is set then negative numbers are added e.g. (0, -1, -2, ...).
  /// The sequence starts at StartIndex.
  virtual Value *getConsecutiveVector(Value* Val, int StartIdx, bool Negate);

  /// When we go over instructions in the basic block we rely on previous
  /// values within the current basic block or on loop invariant values.
  /// When we widen (vectorize) values we place them in the map. If the values
  /// are not within the map, they have to be loop invariant, so we simply
  /// broadcast them into a vector.
  VectorParts &getVectorValue(Value *V);

  /// Generate a shuffle sequence that will reverse the vector Vec.
  virtual Value *reverseVector(Value *Vec);

  /// This is a helper class that holds the vectorizer state. It maps scalar
  /// instructions to vector instructions. When the code is 'unrolled' then
  /// then a single scalar value is mapped to multiple vector parts. The parts
  /// are stored in the VectorPart type.
  struct ValueMap {
    /// C'tor.  UnrollFactor controls the number of vectors ('parts') that
    /// are mapped.
    ValueMap(unsigned UnrollFactor) : UF(UnrollFactor) {}

    /// \return True if 'Key' is saved in the Value Map.
    bool has(Value *Key) const { return MapStorage.count(Key); }

    /// Initializes a new entry in the map. Sets all of the vector parts to the
    /// save value in 'Val'.
    /// \return A reference to a vector with splat values.
    VectorParts &splat(Value *Key, Value *Val) {
      VectorParts &Entry = MapStorage[Key];
      Entry.assign(UF, Val);
      return Entry;
    }

    ///\return A reference to the value that is stored at 'Key'.
    VectorParts &get(Value *Key) {
      VectorParts &Entry = MapStorage[Key];
      if (Entry.empty())
        Entry.resize(UF);
      assert(Entry.size() == UF);
      return Entry;
    }

  private:
    /// The unroll factor. Each entry in the map stores this number of vector
    /// elements.
    unsigned UF;

    /// Map storage. We use std::map and not DenseMap because insertions to a
    /// dense map invalidates its iterators.
    std::map<Value *, VectorParts> MapStorage;
  };

  /// The original loop.
  Loop *OrigLoop;
  /// Scev analysis to use.
  ScalarEvolution *SE;
  /// Loop Info.
  LoopInfo *LI;
  /// Dominator Tree.
  DominatorTree *DT;
  /// Data Layout.
  const DataLayout *DL;
  /// Target Library Info.
  const TargetLibraryInfo *TLI;

  /// The vectorization SIMD factor to use. Each vector will have this many
  /// vector elements.
  unsigned VF;

protected:
  /// The vectorization unroll factor to use. Each scalar is vectorized to this
  /// many different vector instructions.
  unsigned UF;

  /// The builder that we use
  IRBuilder<> Builder;

  // --- Vectorization state ---

  /// The vector-loop preheader.
  BasicBlock *LoopVectorPreHeader;
  /// The scalar-loop preheader.
  BasicBlock *LoopScalarPreHeader;
  /// Middle Block between the vector and the scalar.
  BasicBlock *LoopMiddleBlock;
  ///The ExitBlock of the scalar loop.
  BasicBlock *LoopExitBlock;
  ///The vector loop body.
  SmallVector<BasicBlock *, 4> LoopVectorBody;
  ///The scalar loop body.
  BasicBlock *LoopScalarBody;
  /// A list of all bypass blocks. The first block is the entry of the loop.
  SmallVector<BasicBlock *, 4> LoopBypassBlocks;

  /// The new Induction variable which was added to the new block.
  PHINode *Induction;
  /// The induction variable of the old basic block.
  PHINode *OldInduction;
  /// Holds the extended (to the widest induction type) start index.
  Value *ExtendedIdx;
  /// Maps scalars to widened vectors.
  ValueMap WidenMap;
  EdgeMaskCache MaskCache;

  LoopVectorizationLegality *Legal;
};

class InnerLoopUnroller : public InnerLoopVectorizer {
public:
  InnerLoopUnroller(Loop *OrigLoop, ScalarEvolution *SE, LoopInfo *LI,
                    DominatorTree *DT, const DataLayout *DL,
                    const TargetLibraryInfo *TLI, unsigned UnrollFactor) :
    InnerLoopVectorizer(OrigLoop, SE, LI, DT, DL, TLI, 1, UnrollFactor) { }

private:
  virtual void scalarizeInstruction(Instruction *Instr, bool IfPredicateStore = false);
  virtual void vectorizeMemoryInstruction(Instruction *Instr);
  virtual Value *getBroadcastInstrs(Value *V);
  virtual Value *getConsecutiveVector(Value* Val, int StartIdx, bool Negate);
  virtual Value *reverseVector(Value *Vec);
};

/// \brief Look for a meaningful debug location on the instruction or it's
/// operands.
static Instruction *getDebugLocFromInstOrOperands(Instruction *I) {
  if (!I)
    return I;

  DebugLoc Empty;
  if (I->getDebugLoc() != Empty)
    return I;

  for (User::op_iterator OI = I->op_begin(), OE = I->op_end(); OI != OE; ++OI) {
    if (Instruction *OpInst = dyn_cast<Instruction>(*OI))
      if (OpInst->getDebugLoc() != Empty)
        return OpInst;
  }

  return I;
}

/// \brief Set the debug location in the builder using the debug location in the
/// instruction.
static void setDebugLocFromInst(IRBuilder<> &B, const Value *Ptr) {
  if (const Instruction *Inst = dyn_cast_or_null<Instruction>(Ptr))
    B.SetCurrentDebugLocation(Inst->getDebugLoc());
  else
    B.SetCurrentDebugLocation(DebugLoc());
}

/// LoopVectorizationLegality checks if it is legal to vectorize a loop, and
/// to what vectorization factor.
/// This class does not look at the profitability of vectorization, only the
/// legality. This class has two main kinds of checks:
/// * Memory checks - The code in canVectorizeMemory checks if vectorization
///   will change the order of memory accesses in a way that will change the
///   correctness of the program.
/// * Scalars checks - The code in canVectorizeInstrs and canVectorizeMemory
/// checks for a number of different conditions, such as the availability of a
/// single induction variable, that all types are supported and vectorize-able,
/// etc. This code reflects the capabilities of InnerLoopVectorizer.
/// This class is also used by InnerLoopVectorizer for identifying
/// induction variable and the different reduction variables.
class LoopVectorizationLegality {
public:
  unsigned NumLoads;
  unsigned NumStores;
  unsigned NumPredStores;

  LoopVectorizationLegality(Loop *L, ScalarEvolution *SE, const DataLayout *DL,
                            DominatorTree *DT, TargetLibraryInfo *TLI)
      : NumLoads(0), NumStores(0), NumPredStores(0), TheLoop(L), SE(SE), DL(DL),
        DT(DT), TLI(TLI), Induction(0), WidestIndTy(0), HasFunNoNaNAttr(false),
        MaxSafeDepDistBytes(-1U) {}

  /// This enum represents the kinds of reductions that we support.
  enum ReductionKind {
    RK_NoReduction, ///< Not a reduction.
    RK_IntegerAdd,  ///< Sum of integers.
    RK_IntegerMult, ///< Product of integers.
    RK_IntegerOr,   ///< Bitwise or logical OR of numbers.
    RK_IntegerAnd,  ///< Bitwise or logical AND of numbers.
    RK_IntegerXor,  ///< Bitwise or logical XOR of numbers.
    RK_IntegerMinMax, ///< Min/max implemented in terms of select(cmp()).
    RK_FloatAdd,    ///< Sum of floats.
    RK_FloatMult,   ///< Product of floats.
    RK_FloatMinMax  ///< Min/max implemented in terms of select(cmp()).
  };

  /// This enum represents the kinds of inductions that we support.
  enum InductionKind {
    IK_NoInduction,         ///< Not an induction variable.
    IK_IntInduction,        ///< Integer induction variable. Step = 1.
    IK_ReverseIntInduction, ///< Reverse int induction variable. Step = -1.
    IK_PtrInduction,        ///< Pointer induction var. Step = sizeof(elem).
    IK_ReversePtrInduction  ///< Reverse ptr indvar. Step = - sizeof(elem).
  };

  // This enum represents the kind of minmax reduction.
  enum MinMaxReductionKind {
    MRK_Invalid,
    MRK_UIntMin,
    MRK_UIntMax,
    MRK_SIntMin,
    MRK_SIntMax,
    MRK_FloatMin,
    MRK_FloatMax
  };

  /// This struct holds information about reduction variables.
  struct ReductionDescriptor {
    ReductionDescriptor() : StartValue(0), LoopExitInstr(0),
      Kind(RK_NoReduction), MinMaxKind(MRK_Invalid) {}

    ReductionDescriptor(Value *Start, Instruction *Exit, ReductionKind K,
                        MinMaxReductionKind MK)
        : StartValue(Start), LoopExitInstr(Exit), Kind(K), MinMaxKind(MK) {}

    // The starting value of the reduction.
    // It does not have to be zero!
    TrackingVH<Value> StartValue;
    // The instruction who's value is used outside the loop.
    Instruction *LoopExitInstr;
    // The kind of the reduction.
    ReductionKind Kind;
    // If this a min/max reduction the kind of reduction.
    MinMaxReductionKind MinMaxKind;
  };

  /// This POD struct holds information about a potential reduction operation.
  struct ReductionInstDesc {
    ReductionInstDesc(bool IsRedux, Instruction *I) :
      IsReduction(IsRedux), PatternLastInst(I), MinMaxKind(MRK_Invalid) {}

    ReductionInstDesc(Instruction *I, MinMaxReductionKind K) :
      IsReduction(true), PatternLastInst(I), MinMaxKind(K) {}

    // Is this instruction a reduction candidate.
    bool IsReduction;
    // The last instruction in a min/max pattern (select of the select(icmp())
    // pattern), or the current reduction instruction otherwise.
    Instruction *PatternLastInst;
    // If this is a min/max pattern the comparison predicate.
    MinMaxReductionKind MinMaxKind;
  };

  /// This struct holds information about the memory runtime legality
  /// check that a group of pointers do not overlap.
  struct RuntimePointerCheck {
    RuntimePointerCheck() : Need(false) {}

    /// Reset the state of the pointer runtime information.
    void reset() {
      Need = false;
      Pointers.clear();
      Starts.clear();
      Ends.clear();
      IsWritePtr.clear();
      DependencySetId.clear();
    }

    /// Insert a pointer and calculate the start and end SCEVs.
    void insert(ScalarEvolution *SE, Loop *Lp, Value *Ptr, bool WritePtr,
                unsigned DepSetId, ValueToValueMap &Strides);

    /// This flag indicates if we need to add the runtime check.
    bool Need;
    /// Holds the pointers that we need to check.
    SmallVector<TrackingVH<Value>, 2> Pointers;
    /// Holds the pointer value at the beginning of the loop.
    SmallVector<const SCEV*, 2> Starts;
    /// Holds the pointer value at the end of the loop.
    SmallVector<const SCEV*, 2> Ends;
    /// Holds the information if this pointer is used for writing to memory.
    SmallVector<bool, 2> IsWritePtr;
    /// Holds the id of the set of pointers that could be dependent because of a
    /// shared underlying object.
    SmallVector<unsigned, 2> DependencySetId;
  };

  /// A struct for saving information about induction variables.
  struct InductionInfo {
    InductionInfo(Value *Start, InductionKind K) : StartValue(Start), IK(K) {}
    InductionInfo() : StartValue(0), IK(IK_NoInduction) {}
    /// Start value.
    TrackingVH<Value> StartValue;
    /// Induction kind.
    InductionKind IK;
  };

  /// ReductionList contains the reduction descriptors for all
  /// of the reductions that were found in the loop.
  typedef DenseMap<PHINode*, ReductionDescriptor> ReductionList;

  /// InductionList saves induction variables and maps them to the
  /// induction descriptor.
  typedef MapVector<PHINode*, InductionInfo> InductionList;

  /// Returns true if it is legal to vectorize this loop.
  /// This does not mean that it is profitable to vectorize this
  /// loop, only that it is legal to do so.
  bool canVectorize();

  /// Returns the Induction variable.
  PHINode *getInduction() { return Induction; }

  /// Returns the reduction variables found in the loop.
  ReductionList *getReductionVars() { return &Reductions; }

  /// Returns the induction variables found in the loop.
  InductionList *getInductionVars() { return &Inductions; }

  /// Returns the widest induction type.
  Type *getWidestInductionType() { return WidestIndTy; }

  /// Returns True if V is an induction variable in this loop.
  bool isInductionVariable(const Value *V);

  /// Return true if the block BB needs to be predicated in order for the loop
  /// to be vectorized.
  bool blockNeedsPredication(BasicBlock *BB);

  /// Check if this  pointer is consecutive when vectorizing. This happens
  /// when the last index of the GEP is the induction variable, or that the
  /// pointer itself is an induction variable.
  /// This check allows us to vectorize A[idx] into a wide load/store.
  /// Returns:
  /// 0 - Stride is unknown or non-consecutive.
  /// 1 - Address is consecutive.
  /// -1 - Address is consecutive, and decreasing.
  int isConsecutivePtr(Value *Ptr);

  /// Returns true if the value V is uniform within the loop.
  bool isUniform(Value *V);

  /// Returns true if this instruction will remain scalar after vectorization.
  bool isUniformAfterVectorization(Instruction* I) { return Uniforms.count(I); }

  /// Returns the information that we collected about runtime memory check.
  RuntimePointerCheck *getRuntimePointerCheck() { return &PtrRtCheck; }

  /// This function returns the identity element (or neutral element) for
  /// the operation K.
  static Constant *getReductionIdentity(ReductionKind K, Type *Tp);

  unsigned getMaxSafeDepDistBytes() { return MaxSafeDepDistBytes; }

  bool hasStride(Value *V) { return StrideSet.count(V); }
  bool mustCheckStrides() { return !StrideSet.empty(); }
  SmallPtrSet<Value *, 8>::iterator strides_begin() {
    return StrideSet.begin();
  }
  SmallPtrSet<Value *, 8>::iterator strides_end() { return StrideSet.end(); }

private:
  /// Check if a single basic block loop is vectorizable.
  /// At this point we know that this is a loop with a constant trip count
  /// and we only need to check individual instructions.
  bool canVectorizeInstrs();

  /// When we vectorize loops we may change the order in which
  /// we read and write from memory. This method checks if it is
  /// legal to vectorize the code, considering only memory constrains.
  /// Returns true if the loop is vectorizable
  bool canVectorizeMemory();

  /// Return true if we can vectorize this loop using the IF-conversion
  /// transformation.
  bool canVectorizeWithIfConvert();

  /// Collect the variables that need to stay uniform after vectorization.
  void collectLoopUniforms();

  /// Return true if all of the instructions in the block can be speculatively
  /// executed. \p SafePtrs is a list of addresses that are known to be legal
  /// and we know that we can read from them without segfault.
  bool blockCanBePredicated(BasicBlock *BB, SmallPtrSet<Value *, 8>& SafePtrs);

  /// Returns True, if 'Phi' is the kind of reduction variable for type
  /// 'Kind'. If this is a reduction variable, it adds it to ReductionList.
  bool AddReductionVar(PHINode *Phi, ReductionKind Kind);
  /// Returns a struct describing if the instruction 'I' can be a reduction
  /// variable of type 'Kind'. If the reduction is a min/max pattern of
  /// select(icmp()) this function advances the instruction pointer 'I' from the
  /// compare instruction to the select instruction and stores this pointer in
  /// 'PatternLastInst' member of the returned struct.
  ReductionInstDesc isReductionInstr(Instruction *I, ReductionKind Kind,
                                     ReductionInstDesc &Desc);
  /// Returns true if the instruction is a Select(ICmp(X, Y), X, Y) instruction
  /// pattern corresponding to a min(X, Y) or max(X, Y).
  static ReductionInstDesc isMinMaxSelectCmpPattern(Instruction *I,
                                                    ReductionInstDesc &Prev);
  /// Returns the induction kind of Phi. This function may return NoInduction
  /// if the PHI is not an induction variable.
  InductionKind isInductionVariable(PHINode *Phi);

  /// \brief Collect memory access with loop invariant strides.
  ///
  /// Looks for accesses like "a[i * StrideA]" where "StrideA" is loop
  /// invariant.
  void collectStridedAcccess(Value *LoadOrStoreInst);

  /// The loop that we evaluate.
  Loop *TheLoop;
  /// Scev analysis.
  ScalarEvolution *SE;
  /// DataLayout analysis.
  const DataLayout *DL;
  /// Dominators.
  DominatorTree *DT;
  /// Target Library Info.
  TargetLibraryInfo *TLI;

  //  ---  vectorization state --- //

  /// Holds the integer induction variable. This is the counter of the
  /// loop.
  PHINode *Induction;
  /// Holds the reduction variables.
  ReductionList Reductions;
  /// Holds all of the induction variables that we found in the loop.
  /// Notice that inductions don't need to start at zero and that induction
  /// variables can be pointers.
  InductionList Inductions;
  /// Holds the widest induction type encountered.
  Type *WidestIndTy;

  /// Allowed outside users. This holds the reduction
  /// vars which can be accessed from outside the loop.
  SmallPtrSet<Value*, 4> AllowedExit;
  /// This set holds the variables which are known to be uniform after
  /// vectorization.
  SmallPtrSet<Instruction*, 4> Uniforms;
  /// We need to check that all of the pointers in this list are disjoint
  /// at runtime.
  RuntimePointerCheck PtrRtCheck;
  /// Can we assume the absence of NaNs.
  bool HasFunNoNaNAttr;

  unsigned MaxSafeDepDistBytes;

  ValueToValueMap Strides;
  SmallPtrSet<Value *, 8> StrideSet;
};

/// LoopVectorizationCostModel - estimates the expected speedups due to
/// vectorization.
/// In many cases vectorization is not profitable. This can happen because of
/// a number of reasons. In this class we mainly attempt to predict the
/// expected speedup/slowdowns due to the supported instruction set. We use the
/// TargetTransformInfo to query the different backends for the cost of
/// different operations.
class LoopVectorizationCostModel {
public:
  LoopVectorizationCostModel(Loop *L, ScalarEvolution *SE, LoopInfo *LI,
                             LoopVectorizationLegality *Legal,
                             const TargetTransformInfo &TTI,
                             const DataLayout *DL, const TargetLibraryInfo *TLI)
      : TheLoop(L), SE(SE), LI(LI), Legal(Legal), TTI(TTI), DL(DL), TLI(TLI) {}

  /// Information about vectorization costs
  struct VectorizationFactor {
    unsigned Width; // Vector width with best cost
    unsigned Cost; // Cost of the loop with that width
  };
  /// \return The most profitable vectorization factor and the cost of that VF.
  /// This method checks every power of two up to VF. If UserVF is not ZERO
  /// then this vectorization factor will be selected if vectorization is
  /// possible.
  VectorizationFactor selectVectorizationFactor(bool OptForSize,
                                                unsigned UserVF);

  /// \return The size (in bits) of the widest type in the code that
  /// needs to be vectorized. We ignore values that remain scalar such as
  /// 64 bit loop indices.
  unsigned getWidestType();

  /// \return The most profitable unroll factor.
  /// If UserUF is non-zero then this method finds the best unroll-factor
  /// based on register pressure and other parameters.
  /// VF and LoopCost are the selected vectorization factor and the cost of the
  /// selected VF.
  unsigned selectUnrollFactor(bool OptForSize, unsigned UserUF, unsigned VF,
                              unsigned LoopCost);

  /// \brief A struct that represents some properties of the register usage
  /// of a loop.
  struct RegisterUsage {
    /// Holds the number of loop invariant values that are used in the loop.
    unsigned LoopInvariantRegs;
    /// Holds the maximum number of concurrent live intervals in the loop.
    unsigned MaxLocalUsers;
    /// Holds the number of instructions in the loop.
    unsigned NumInstructions;
  };

  /// \return  information about the register usage of the loop.
  RegisterUsage calculateRegisterUsage();

private:
  /// Returns the expected execution cost. The unit of the cost does
  /// not matter because we use the 'cost' units to compare different
  /// vector widths. The cost that is returned is *not* normalized by
  /// the factor width.
  unsigned expectedCost(unsigned VF);

  /// Returns the execution time cost of an instruction for a given vector
  /// width. Vector width of one means scalar.
  unsigned getInstructionCost(Instruction *I, unsigned VF);

  /// A helper function for converting Scalar types to vector types.
  /// If the incoming type is void, we return void. If the VF is 1, we return
  /// the scalar type.
  static Type* ToVectorTy(Type *Scalar, unsigned VF);

  /// Returns whether the instruction is a load or store and will be a emitted
  /// as a vector operation.
  bool isConsecutiveLoadOrStore(Instruction *I);

  /// The loop that we evaluate.
  Loop *TheLoop;
  /// Scev analysis.
  ScalarEvolution *SE;
  /// Loop Info analysis.
  LoopInfo *LI;
  /// Vectorization legality.
  LoopVectorizationLegality *Legal;
  /// Vector target information.
  const TargetTransformInfo &TTI;
  /// Target data layout information.
  const DataLayout *DL;
  /// Target Library Info.
  const TargetLibraryInfo *TLI;
};

/// Utility class for getting and setting loop vectorizer hints in the form
/// of loop metadata.
struct LoopVectorizeHints {
  /// Vectorization width.
  unsigned Width;
  /// Vectorization unroll factor.
  unsigned Unroll;
  /// Vectorization forced (-1 not selected, 0 force disabled, 1 force enabled)
  int Force;

  LoopVectorizeHints(const Loop *L, bool DisableUnrolling)
  : Width(VectorizationFactor)
  , Unroll(DisableUnrolling ? 1 : VectorizationUnroll)
  , Force(-1)
  , LoopID(L->getLoopID()) {
    getHints(L);
    // The command line options override any loop metadata except for when
    // width == 1 which is used to indicate the loop is already vectorized.
    if (VectorizationFactor.getNumOccurrences() > 0 && Width != 1)
      Width = VectorizationFactor;
    if (VectorizationUnroll.getNumOccurrences() > 0)
      Unroll = VectorizationUnroll;

    DEBUG(if (DisableUnrolling && Unroll == 1)
            dbgs() << "LV: Unrolling disabled by the pass manager\n");
  }

  /// Return the loop vectorizer metadata prefix.
  static StringRef Prefix() { return "llvm.vectorizer."; }

  MDNode *createHint(LLVMContext &Context, StringRef Name, unsigned V) {
    SmallVector<Value*, 2> Vals;
    Vals.push_back(MDString::get(Context, Name));
    Vals.push_back(ConstantInt::get(Type::getInt32Ty(Context), V));
    return MDNode::get(Context, Vals);
  }

  /// Mark the loop L as already vectorized by setting the width to 1.
  void setAlreadyVectorized(Loop *L) {
    LLVMContext &Context = L->getHeader()->getContext();

    Width = 1;

    // Create a new loop id with one more operand for the already_vectorized
    // hint. If the loop already has a loop id then copy the existing operands.
    SmallVector<Value*, 4> Vals(1);
    if (LoopID)
      for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i)
        Vals.push_back(LoopID->getOperand(i));

    Vals.push_back(createHint(Context, Twine(Prefix(), "width").str(), Width));
    Vals.push_back(createHint(Context, Twine(Prefix(), "unroll").str(), 1));

    MDNode *NewLoopID = MDNode::get(Context, Vals);
    // Set operand 0 to refer to the loop id itself.
    NewLoopID->replaceOperandWith(0, NewLoopID);

    L->setLoopID(NewLoopID);
    if (LoopID)
      LoopID->replaceAllUsesWith(NewLoopID);

    LoopID = NewLoopID;
  }

private:
  MDNode *LoopID;

  /// Find hints specified in the loop metadata.
  void getHints(const Loop *L) {
    if (!LoopID)
      return;

    // First operand should refer to the loop id itself.
    assert(LoopID->getNumOperands() > 0 && "requires at least one operand");
    assert(LoopID->getOperand(0) == LoopID && "invalid loop id");

    for (unsigned i = 1, ie = LoopID->getNumOperands(); i < ie; ++i) {
      const MDString *S = 0;
      SmallVector<Value*, 4> Args;

      // The expected hint is either a MDString or a MDNode with the first
      // operand a MDString.
      if (const MDNode *MD = dyn_cast<MDNode>(LoopID->getOperand(i))) {
        if (!MD || MD->getNumOperands() == 0)
          continue;
        S = dyn_cast<MDString>(MD->getOperand(0));
        for (unsigned i = 1, ie = MD->getNumOperands(); i < ie; ++i)
          Args.push_back(MD->getOperand(i));
      } else {
        S = dyn_cast<MDString>(LoopID->getOperand(i));
        assert(Args.size() == 0 && "too many arguments for MDString");
      }

      if (!S)
        continue;

      // Check if the hint starts with the vectorizer prefix.
      StringRef Hint = S->getString();
      if (!Hint.startswith(Prefix()))
        continue;
      // Remove the prefix.
      Hint = Hint.substr(Prefix().size(), StringRef::npos);

      if (Args.size() == 1)
        getHint(Hint, Args[0]);
    }
  }

  // Check string hint with one operand.
  void getHint(StringRef Hint, Value *Arg) {
    const ConstantInt *C = dyn_cast<ConstantInt>(Arg);
    if (!C) return;
    unsigned Val = C->getZExtValue();

    if (Hint == "width") {
      if (isPowerOf2_32(Val) && Val <= MaxVectorWidth)
        Width = Val;
      else
        DEBUG(dbgs() << "LV: ignoring invalid width hint metadata\n");
    } else if (Hint == "unroll") {
      if (isPowerOf2_32(Val) && Val <= MaxUnrollFactor)
        Unroll = Val;
      else
        DEBUG(dbgs() << "LV: ignoring invalid unroll hint metadata\n");
    } else if (Hint == "enable") {
      if (C->getBitWidth() == 1)
        Force = Val;
      else
        DEBUG(dbgs() << "LV: ignoring invalid enable hint metadata\n");
    } else {
      DEBUG(dbgs() << "LV: ignoring unknown hint " << Hint << '\n');
    }
  }
};

static void addInnerLoop(Loop *L, SmallVectorImpl<Loop *> &V) {
  if (L->empty())
    return V.push_back(L);

  for (Loop::iterator I = L->begin(), E = L->end(); I != E; ++I)
    addInnerLoop(*I, V);
}

/// The LoopVectorize Pass.
struct LoopVectorize : public FunctionPass {
  /// Pass identification, replacement for typeid
  static char ID;

  explicit LoopVectorize(bool NoUnrolling = false, bool AlwaysVectorize = true)
    : FunctionPass(ID),
      DisableUnrolling(NoUnrolling),
      AlwaysVectorize(AlwaysVectorize) {
    initializeLoopVectorizePass(*PassRegistry::getPassRegistry());
  }

  ScalarEvolution *SE;
  const DataLayout *DL;
  LoopInfo *LI;
  TargetTransformInfo *TTI;
  DominatorTree *DT;
  BlockFrequencyInfo *BFI;
  TargetLibraryInfo *TLI;
  bool DisableUnrolling;
  bool AlwaysVectorize;

  BlockFrequency ColdEntryFreq;

  virtual bool runOnFunction(Function &F) {
    SE = &getAnalysis<ScalarEvolution>();
    DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
    DL = DLP ? &DLP->getDataLayout() : 0;
    LI = &getAnalysis<LoopInfo>();
    TTI = &getAnalysis<TargetTransformInfo>();
    DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    BFI = &getAnalysis<BlockFrequencyInfo>();
    TLI = getAnalysisIfAvailable<TargetLibraryInfo>();

    // Compute some weights outside of the loop over the loops. Compute this
    // using a BranchProbability to re-use its scaling math.
    const BranchProbability ColdProb(1, 5); // 20%
    ColdEntryFreq = BlockFrequency(BFI->getEntryFreq()) * ColdProb;

    // If the target claims to have no vector registers don't attempt
    // vectorization.
    if (!TTI->getNumberOfRegisters(true))
      return false;

    if (DL == NULL) {
      DEBUG(dbgs() << "LV: Not vectorizing: Missing data layout\n");
      return false;
    }

    // Build up a worklist of inner-loops to vectorize. This is necessary as
    // the act of vectorizing or partially unrolling a loop creates new loops
    // and can invalidate iterators across the loops.
    SmallVector<Loop *, 8> Worklist;

    for (LoopInfo::iterator I = LI->begin(), E = LI->end(); I != E; ++I)
      addInnerLoop(*I, Worklist);

    // Now walk the identified inner loops.
    bool Changed = false;
    while (!Worklist.empty())
      Changed |= processLoop(Worklist.pop_back_val());

    // Process each loop nest in the function.
    return Changed;
  }

  bool processLoop(Loop *L) {
    // We only handle inner loops, so if there are children just recurse.
    if (!L->empty()) {
      bool Changed = false;
      for (Loop::iterator I = L->begin(), E = L->begin(); I != E; ++I)
        Changed |= processLoop(*I);
      return Changed;
    }

    DEBUG(dbgs() << "LV: Checking a loop in \"" <<
          L->getHeader()->getParent()->getName() << "\"\n");

    LoopVectorizeHints Hints(L, DisableUnrolling);

    if (Hints.Force == 0) {
      DEBUG(dbgs() << "LV: Not vectorizing: #pragma vectorize disable.\n");
      return false;
    }

    if (!AlwaysVectorize && Hints.Force != 1) {
      DEBUG(dbgs() << "LV: Not vectorizing: No #pragma vectorize enable.\n");
      return false;
    }

    if (Hints.Width == 1 && Hints.Unroll == 1) {
      DEBUG(dbgs() << "LV: Not vectorizing: Disabled/already vectorized.\n");
      return false;
    }

    // Check if it is legal to vectorize the loop.
    LoopVectorizationLegality LVL(L, SE, DL, DT, TLI);
    if (!LVL.canVectorize()) {
      DEBUG(dbgs() << "LV: Not vectorizing: Cannot prove legality.\n");
      return false;
    }

    // Use the cost model.
    LoopVectorizationCostModel CM(L, SE, LI, &LVL, *TTI, DL, TLI);

    // Check the function attributes to find out if this function should be
    // optimized for size.
    Function *F = L->getHeader()->getParent();
    bool OptForSize =
        Hints.Force != 1 && F->hasFnAttribute(Attribute::OptimizeForSize);

    // Compute the weighted frequency of this loop being executed and see if it
    // is less than 20% of the function entry baseline frequency. Note that we
    // always have a canonical loop here because we think we *can* vectoriez.
    // FIXME: This is hidden behind a flag due to pervasive problems with
    // exactly what block frequency models.
    if (LoopVectorizeWithBlockFrequency) {
      BlockFrequency LoopEntryFreq = BFI->getBlockFreq(L->getLoopPreheader());
      if (Hints.Force != 1 && LoopEntryFreq < ColdEntryFreq)
        OptForSize = true;
    }

    // Check the function attributes to see if implicit floats are allowed.a
    // FIXME: This check doesn't seem possibly correct -- what if the loop is
    // an integer loop and the vector instructions selected are purely integer
    // vector instructions?
    if (F->hasFnAttribute(Attribute::NoImplicitFloat)) {
      DEBUG(dbgs() << "LV: Can't vectorize when the NoImplicitFloat"
            "attribute is used.\n");
      return false;
    }

    // Select the optimal vectorization factor.
    LoopVectorizationCostModel::VectorizationFactor VF;
    VF = CM.selectVectorizationFactor(OptForSize, Hints.Width);
    // Select the unroll factor.
    unsigned UF = CM.selectUnrollFactor(OptForSize, Hints.Unroll, VF.Width,
                                        VF.Cost);

    DEBUG(dbgs() << "LV: Found a vectorizable loop ("<< VF.Width << ") in "<<
          F->getParent()->getModuleIdentifier() << '\n');
    DEBUG(dbgs() << "LV: Unroll Factor is " << UF << '\n');

    if (VF.Width == 1) {
      DEBUG(dbgs() << "LV: Vectorization is possible but not beneficial.\n");
      if (UF == 1)
        return false;
      DEBUG(dbgs() << "LV: Trying to at least unroll the loops.\n");
      // We decided not to vectorize, but we may want to unroll.
      InnerLoopUnroller Unroller(L, SE, LI, DT, DL, TLI, UF);
      Unroller.vectorize(&LVL);
    } else {
      // If we decided that it is *legal* to vectorize the loop then do it.
      InnerLoopVectorizer LB(L, SE, LI, DT, DL, TLI, VF.Width, UF);
      LB.vectorize(&LVL);
    }

    // Mark the loop as already vectorized to avoid vectorizing again.
    Hints.setAlreadyVectorized(L);

    DEBUG(verifyFunction(*L->getHeader()->getParent()));
    return true;
  }

  virtual void getAnalysisUsage(AnalysisUsage &AU) const {
    AU.addRequiredID(LoopSimplifyID);
    AU.addRequiredID(LCSSAID);
    AU.addRequired<BlockFrequencyInfo>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<LoopInfo>();
    AU.addRequired<ScalarEvolution>();
    AU.addRequired<TargetTransformInfo>();
    AU.addPreserved<LoopInfo>();
    AU.addPreserved<DominatorTreeWrapperPass>();
  }

};

} // end anonymous namespace

//===----------------------------------------------------------------------===//
// Implementation of LoopVectorizationLegality, InnerLoopVectorizer and
// LoopVectorizationCostModel.
//===----------------------------------------------------------------------===//

static Value *stripIntegerCast(Value *V) {
  if (CastInst *CI = dyn_cast<CastInst>(V))
    if (CI->getOperand(0)->getType()->isIntegerTy())
      return CI->getOperand(0);
  return V;
}

///\brief Replaces the symbolic stride in a pointer SCEV expression by one.
///
/// If \p OrigPtr is not null, use it to look up the stride value instead of
/// \p Ptr.
static const SCEV *replaceSymbolicStrideSCEV(ScalarEvolution *SE,
                                             ValueToValueMap &PtrToStride,
                                             Value *Ptr, Value *OrigPtr = 0) {

  const SCEV *OrigSCEV = SE->getSCEV(Ptr);

  // If there is an entry in the map return the SCEV of the pointer with the
  // symbolic stride replaced by one.
  ValueToValueMap::iterator SI = PtrToStride.find(OrigPtr ? OrigPtr : Ptr);
  if (SI != PtrToStride.end()) {
    Value *StrideVal = SI->second;

    // Strip casts.
    StrideVal = stripIntegerCast(StrideVal);

    // Replace symbolic stride by one.
    Value *One = ConstantInt::get(StrideVal->getType(), 1);
    ValueToValueMap RewriteMap;
    RewriteMap[StrideVal] = One;

    const SCEV *ByOne =
        SCEVParameterRewriter::rewrite(OrigSCEV, *SE, RewriteMap, true);
    DEBUG(dbgs() << "LV: Replacing SCEV: " << *OrigSCEV << " by: " << *ByOne
                 << "\n");
    return ByOne;
  }

  // Otherwise, just return the SCEV of the original pointer.
  return SE->getSCEV(Ptr);
}

void LoopVectorizationLegality::RuntimePointerCheck::insert(
    ScalarEvolution *SE, Loop *Lp, Value *Ptr, bool WritePtr, unsigned DepSetId,
    ValueToValueMap &Strides) {
  // Get the stride replaced scev.
  const SCEV *Sc = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Sc);
  assert(AR && "Invalid addrec expression");
  const SCEV *Ex = SE->getBackedgeTakenCount(Lp);
  const SCEV *ScEnd = AR->evaluateAtIteration(Ex, *SE);
  Pointers.push_back(Ptr);
  Starts.push_back(AR->getStart());
  Ends.push_back(ScEnd);
  IsWritePtr.push_back(WritePtr);
  DependencySetId.push_back(DepSetId);
}

Value *InnerLoopVectorizer::getBroadcastInstrs(Value *V) {
  // We need to place the broadcast of invariant variables outside the loop.
  Instruction *Instr = dyn_cast<Instruction>(V);
  bool NewInstr =
      (Instr && std::find(LoopVectorBody.begin(), LoopVectorBody.end(),
                          Instr->getParent()) != LoopVectorBody.end());
  bool Invariant = OrigLoop->isLoopInvariant(V) && !NewInstr;

  // Place the code for broadcasting invariant variables in the new preheader.
  IRBuilder<>::InsertPointGuard Guard(Builder);
  if (Invariant)
    Builder.SetInsertPoint(LoopVectorPreHeader->getTerminator());

  // Broadcast the scalar into all locations in the vector.
  Value *Shuf = Builder.CreateVectorSplat(VF, V, "broadcast");

  return Shuf;
}

Value *InnerLoopVectorizer::getConsecutiveVector(Value* Val, int StartIdx,
                                                 bool Negate) {
  assert(Val->getType()->isVectorTy() && "Must be a vector");
  assert(Val->getType()->getScalarType()->isIntegerTy() &&
         "Elem must be an integer");
  // Create the types.
  Type *ITy = Val->getType()->getScalarType();
  VectorType *Ty = cast<VectorType>(Val->getType());
  int VLen = Ty->getNumElements();
  SmallVector<Constant*, 8> Indices;

  // Create a vector of consecutive numbers from zero to VF.
  for (int i = 0; i < VLen; ++i) {
    int64_t Idx = Negate ? (-i) : i;
    Indices.push_back(ConstantInt::get(ITy, StartIdx + Idx, Negate));
  }

  // Add the consecutive indices to the vector value.
  Constant *Cv = ConstantVector::get(Indices);
  assert(Cv->getType() == Val->getType() && "Invalid consecutive vec");
  return Builder.CreateAdd(Val, Cv, "induction");
}

/// \brief Find the operand of the GEP that should be checked for consecutive
/// stores. This ignores trailing indices that have no effect on the final
/// pointer.
static unsigned getGEPInductionOperand(const DataLayout *DL,
                                       const GetElementPtrInst *Gep) {
  unsigned LastOperand = Gep->getNumOperands() - 1;
  unsigned GEPAllocSize = DL->getTypeAllocSize(
      cast<PointerType>(Gep->getType()->getScalarType())->getElementType());

  // Walk backwards and try to peel off zeros.
  while (LastOperand > 1 && match(Gep->getOperand(LastOperand), m_Zero())) {
    // Find the type we're currently indexing into.
    gep_type_iterator GEPTI = gep_type_begin(Gep);
    std::advance(GEPTI, LastOperand - 1);

    // If it's a type with the same allocation size as the result of the GEP we
    // can peel off the zero index.
    if (DL->getTypeAllocSize(*GEPTI) != GEPAllocSize)
      break;
    --LastOperand;
  }

  return LastOperand;
}

int LoopVectorizationLegality::isConsecutivePtr(Value *Ptr) {
  assert(Ptr->getType()->isPointerTy() && "Unexpected non-ptr");
  // Make sure that the pointer does not point to structs.
  if (Ptr->getType()->getPointerElementType()->isAggregateType())
    return 0;

  // If this value is a pointer induction variable we know it is consecutive.
  PHINode *Phi = dyn_cast_or_null<PHINode>(Ptr);
  if (Phi && Inductions.count(Phi)) {
    InductionInfo II = Inductions[Phi];
    if (IK_PtrInduction == II.IK)
      return 1;
    else if (IK_ReversePtrInduction == II.IK)
      return -1;
  }

  GetElementPtrInst *Gep = dyn_cast_or_null<GetElementPtrInst>(Ptr);
  if (!Gep)
    return 0;

  unsigned NumOperands = Gep->getNumOperands();
  Value *GpPtr = Gep->getPointerOperand();
  // If this GEP value is a consecutive pointer induction variable and all of
  // the indices are constant then we know it is consecutive. We can
  Phi = dyn_cast<PHINode>(GpPtr);
  if (Phi && Inductions.count(Phi)) {

    // Make sure that the pointer does not point to structs.
    PointerType *GepPtrType = cast<PointerType>(GpPtr->getType());
    if (GepPtrType->getElementType()->isAggregateType())
      return 0;

    // Make sure that all of the index operands are loop invariant.
    for (unsigned i = 1; i < NumOperands; ++i)
      if (!SE->isLoopInvariant(SE->getSCEV(Gep->getOperand(i)), TheLoop))
        return 0;

    InductionInfo II = Inductions[Phi];
    if (IK_PtrInduction == II.IK)
      return 1;
    else if (IK_ReversePtrInduction == II.IK)
      return -1;
  }

  unsigned InductionOperand = getGEPInductionOperand(DL, Gep);

  // Check that all of the gep indices are uniform except for our induction
  // operand.
  for (unsigned i = 0; i != NumOperands; ++i)
    if (i != InductionOperand &&
        !SE->isLoopInvariant(SE->getSCEV(Gep->getOperand(i)), TheLoop))
      return 0;

  // We can emit wide load/stores only if the last non-zero index is the
  // induction variable.
  const SCEV *Last = 0;
  if (!Strides.count(Gep))
    Last = SE->getSCEV(Gep->getOperand(InductionOperand));
  else {
    // Because of the multiplication by a stride we can have a s/zext cast.
    // We are going to replace this stride by 1 so the cast is safe to ignore.
    //
    //  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
    //  %0 = trunc i64 %indvars.iv to i32
    //  %mul = mul i32 %0, %Stride1
    //  %idxprom = zext i32 %mul to i64  << Safe cast.
    //  %arrayidx = getelementptr inbounds i32* %B, i64 %idxprom
    //
    Last = replaceSymbolicStrideSCEV(SE, Strides,
                                     Gep->getOperand(InductionOperand), Gep);
    if (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(Last))
      Last =
          (C->getSCEVType() == scSignExtend || C->getSCEVType() == scZeroExtend)
              ? C->getOperand()
              : Last;
  }
  if (const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Last)) {
    const SCEV *Step = AR->getStepRecurrence(*SE);

    // The memory is consecutive because the last index is consecutive
    // and all other indices are loop invariant.
    if (Step->isOne())
      return 1;
    if (Step->isAllOnesValue())
      return -1;
  }

  return 0;
}

bool LoopVectorizationLegality::isUniform(Value *V) {
  return (SE->isLoopInvariant(SE->getSCEV(V), TheLoop));
}

InnerLoopVectorizer::VectorParts&
InnerLoopVectorizer::getVectorValue(Value *V) {
  assert(V != Induction && "The new induction variable should not be used.");
  assert(!V->getType()->isVectorTy() && "Can't widen a vector");

  // If we have a stride that is replaced by one, do it here.
  if (Legal->hasStride(V))
    V = ConstantInt::get(V->getType(), 1);

  // If we have this scalar in the map, return it.
  if (WidenMap.has(V))
    return WidenMap.get(V);

  // If this scalar is unknown, assume that it is a constant or that it is
  // loop invariant. Broadcast V and save the value for future uses.
  Value *B = getBroadcastInstrs(V);
  return WidenMap.splat(V, B);
}

Value *InnerLoopVectorizer::reverseVector(Value *Vec) {
  assert(Vec->getType()->isVectorTy() && "Invalid type");
  SmallVector<Constant*, 8> ShuffleMask;
  for (unsigned i = 0; i < VF; ++i)
    ShuffleMask.push_back(Builder.getInt32(VF - i - 1));

  return Builder.CreateShuffleVector(Vec, UndefValue::get(Vec->getType()),
                                     ConstantVector::get(ShuffleMask),
                                     "reverse");
}

void InnerLoopVectorizer::vectorizeMemoryInstruction(Instruction *Instr) {
  // Attempt to issue a wide load.
  LoadInst *LI = dyn_cast<LoadInst>(Instr);
  StoreInst *SI = dyn_cast<StoreInst>(Instr);

  assert((LI || SI) && "Invalid Load/Store instruction");

  Type *ScalarDataTy = LI ? LI->getType() : SI->getValueOperand()->getType();
  Type *DataTy = VectorType::get(ScalarDataTy, VF);
  Value *Ptr = LI ? LI->getPointerOperand() : SI->getPointerOperand();
  unsigned Alignment = LI ? LI->getAlignment() : SI->getAlignment();
  // An alignment of 0 means target abi alignment. We need to use the scalar's
  // target abi alignment in such a case.
  if (!Alignment)
    Alignment = DL->getABITypeAlignment(ScalarDataTy);
  unsigned AddressSpace = Ptr->getType()->getPointerAddressSpace();
  unsigned ScalarAllocatedSize = DL->getTypeAllocSize(ScalarDataTy);
  unsigned VectorElementSize = DL->getTypeStoreSize(DataTy)/VF;

  if (SI && Legal->blockNeedsPredication(SI->getParent()))
    return scalarizeInstruction(Instr, true);

  if (ScalarAllocatedSize != VectorElementSize)
    return scalarizeInstruction(Instr);

  // If the pointer is loop invariant or if it is non-consecutive,
  // scalarize the load.
  int ConsecutiveStride = Legal->isConsecutivePtr(Ptr);
  bool Reverse = ConsecutiveStride < 0;
  bool UniformLoad = LI && Legal->isUniform(Ptr);
  if (!ConsecutiveStride || UniformLoad)
    return scalarizeInstruction(Instr);

  Constant *Zero = Builder.getInt32(0);
  VectorParts &Entry = WidenMap.get(Instr);

  // Handle consecutive loads/stores.
  GetElementPtrInst *Gep = dyn_cast<GetElementPtrInst>(Ptr);
  if (Gep && Legal->isInductionVariable(Gep->getPointerOperand())) {
    setDebugLocFromInst(Builder, Gep);
    Value *PtrOperand = Gep->getPointerOperand();
    Value *FirstBasePtr = getVectorValue(PtrOperand)[0];
    FirstBasePtr = Builder.CreateExtractElement(FirstBasePtr, Zero);

    // Create the new GEP with the new induction variable.
    GetElementPtrInst *Gep2 = cast<GetElementPtrInst>(Gep->clone());
    Gep2->setOperand(0, FirstBasePtr);
    Gep2->setName("gep.indvar.base");
    Ptr = Builder.Insert(Gep2);
  } else if (Gep) {
    setDebugLocFromInst(Builder, Gep);
    assert(SE->isLoopInvariant(SE->getSCEV(Gep->getPointerOperand()),
                               OrigLoop) && "Base ptr must be invariant");

    // The last index does not have to be the induction. It can be
    // consecutive and be a function of the index. For example A[I+1];
    unsigned NumOperands = Gep->getNumOperands();
    unsigned InductionOperand = getGEPInductionOperand(DL, Gep);
    // Create the new GEP with the new induction variable.
    GetElementPtrInst *Gep2 = cast<GetElementPtrInst>(Gep->clone());

    for (unsigned i = 0; i < NumOperands; ++i) {
      Value *GepOperand = Gep->getOperand(i);
      Instruction *GepOperandInst = dyn_cast<Instruction>(GepOperand);

      // Update last index or loop invariant instruction anchored in loop.
      if (i == InductionOperand ||
          (GepOperandInst && OrigLoop->contains(GepOperandInst))) {
        assert((i == InductionOperand ||
               SE->isLoopInvariant(SE->getSCEV(GepOperandInst), OrigLoop)) &&
               "Must be last index or loop invariant");

        VectorParts &GEPParts = getVectorValue(GepOperand);
        Value *Index = GEPParts[0];
        Index = Builder.CreateExtractElement(Index, Zero);
        Gep2->setOperand(i, Index);
        Gep2->setName("gep.indvar.idx");
      }
    }
    Ptr = Builder.Insert(Gep2);
  } else {
    // Use the induction element ptr.
    assert(isa<PHINode>(Ptr) && "Invalid induction ptr");
    setDebugLocFromInst(Builder, Ptr);
    VectorParts &PtrVal = getVectorValue(Ptr);
    Ptr = Builder.CreateExtractElement(PtrVal[0], Zero);
  }

  // Handle Stores:
  if (SI) {
    assert(!Legal->isUniform(SI->getPointerOperand()) &&
           "We do not allow storing to uniform addresses");
    setDebugLocFromInst(Builder, SI);
    // We don't want to update the value in the map as it might be used in
    // another expression. So don't use a reference type for "StoredVal".
    VectorParts StoredVal = getVectorValue(SI->getValueOperand());

    for (unsigned Part = 0; Part < UF; ++Part) {
      // Calculate the pointer for the specific unroll-part.
      Value *PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(Part * VF));

      if (Reverse) {
        // If we store to reverse consecutive memory locations then we need
        // to reverse the order of elements in the stored value.
        StoredVal[Part] = reverseVector(StoredVal[Part]);
        // If the address is consecutive but reversed, then the
        // wide store needs to start at the last vector element.
        PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(-Part * VF));
        PartPtr = Builder.CreateGEP(PartPtr, Builder.getInt32(1 - VF));
      }

      Value *VecPtr = Builder.CreateBitCast(PartPtr,
                                            DataTy->getPointerTo(AddressSpace));
      Builder.CreateStore(StoredVal[Part], VecPtr)->setAlignment(Alignment);
    }
    return;
  }

  // Handle loads.
  assert(LI && "Must have a load instruction");
  setDebugLocFromInst(Builder, LI);
  for (unsigned Part = 0; Part < UF; ++Part) {
    // Calculate the pointer for the specific unroll-part.
    Value *PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(Part * VF));

    if (Reverse) {
      // If the address is consecutive but reversed, then the
      // wide store needs to start at the last vector element.
      PartPtr = Builder.CreateGEP(Ptr, Builder.getInt32(-Part * VF));
      PartPtr = Builder.CreateGEP(PartPtr, Builder.getInt32(1 - VF));
    }

    Value *VecPtr = Builder.CreateBitCast(PartPtr,
                                          DataTy->getPointerTo(AddressSpace));
    Value *LI = Builder.CreateLoad(VecPtr, "wide.load");
    cast<LoadInst>(LI)->setAlignment(Alignment);
    Entry[Part] = Reverse ? reverseVector(LI) :  LI;
  }
}

void InnerLoopVectorizer::scalarizeInstruction(Instruction *Instr, bool IfPredicateStore) {
  assert(!Instr->getType()->isAggregateType() && "Can't handle vectors");
  // Holds vector parameters or scalars, in case of uniform vals.
  SmallVector<VectorParts, 4> Params;

  setDebugLocFromInst(Builder, Instr);

  // Find all of the vectorized parameters.
  for (unsigned op = 0, e = Instr->getNumOperands(); op != e; ++op) {
    Value *SrcOp = Instr->getOperand(op);

    // If we are accessing the old induction variable, use the new one.
    if (SrcOp == OldInduction) {
      Params.push_back(getVectorValue(SrcOp));
      continue;
    }

    // Try using previously calculated values.
    Instruction *SrcInst = dyn_cast<Instruction>(SrcOp);

    // If the src is an instruction that appeared earlier in the basic block
    // then it should already be vectorized.
    if (SrcInst && OrigLoop->contains(SrcInst)) {
      assert(WidenMap.has(SrcInst) && "Source operand is unavailable");
      // The parameter is a vector value from earlier.
      Params.push_back(WidenMap.get(SrcInst));
    } else {
      // The parameter is a scalar from outside the loop. Maybe even a constant.
      VectorParts Scalars;
      Scalars.append(UF, SrcOp);
      Params.push_back(Scalars);
    }
  }

  assert(Params.size() == Instr->getNumOperands() &&
         "Invalid number of operands");

  // Does this instruction return a value ?
  bool IsVoidRetTy = Instr->getType()->isVoidTy();

  Value *UndefVec = IsVoidRetTy ? 0 :
    UndefValue::get(VectorType::get(Instr->getType(), VF));
  // Create a new entry in the WidenMap and initialize it to Undef or Null.
  VectorParts &VecResults = WidenMap.splat(Instr, UndefVec);

  Instruction *InsertPt = Builder.GetInsertPoint();
  BasicBlock *IfBlock = Builder.GetInsertBlock();
  BasicBlock *CondBlock = 0;

  VectorParts Cond;
  Loop *VectorLp = 0;
  if (IfPredicateStore) {
    assert(Instr->getParent()->getSinglePredecessor() &&
           "Only support single predecessor blocks");
    Cond = createEdgeMask(Instr->getParent()->getSinglePredecessor(),
                          Instr->getParent());
    VectorLp = LI->getLoopFor(IfBlock);
    assert(VectorLp && "Must have a loop for this block");
  }

  // For each vector unroll 'part':
  for (unsigned Part = 0; Part < UF; ++Part) {
    // For each scalar that we create:
    for (unsigned Width = 0; Width < VF; ++Width) {

      // Start if-block.
      Value *Cmp = 0;
      if (IfPredicateStore) {
        Cmp = Builder.CreateExtractElement(Cond[Part], Builder.getInt32(Width));
        Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Cmp, ConstantInt::get(Cmp->getType(), 1));
        CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
        LoopVectorBody.push_back(CondBlock);
        VectorLp->addBasicBlockToLoop(CondBlock, LI->getBase());
        // Update Builder with newly created basic block.
        Builder.SetInsertPoint(InsertPt);
      }

      Instruction *Cloned = Instr->clone();
      if (!IsVoidRetTy)
        Cloned->setName(Instr->getName() + ".cloned");
      // Replace the operands of the cloned instructions with extracted scalars.
      for (unsigned op = 0, e = Instr->getNumOperands(); op != e; ++op) {
        Value *Op = Params[op][Part];
        // Param is a vector. Need to extract the right lane.
        if (Op->getType()->isVectorTy())
          Op = Builder.CreateExtractElement(Op, Builder.getInt32(Width));
        Cloned->setOperand(op, Op);
      }

      // Place the cloned scalar in the new loop.
      Builder.Insert(Cloned);

      // If the original scalar returns a value we need to place it in a vector
      // so that future users will be able to use it.
      if (!IsVoidRetTy)
        VecResults[Part] = Builder.CreateInsertElement(VecResults[Part], Cloned,
                                                       Builder.getInt32(Width));
      // End if-block.
      if (IfPredicateStore) {
         BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
         LoopVectorBody.push_back(NewIfBlock);
         VectorLp->addBasicBlockToLoop(NewIfBlock, LI->getBase());
         Builder.SetInsertPoint(InsertPt);
         Instruction *OldBr = IfBlock->getTerminator();
         BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
         OldBr->eraseFromParent();
         IfBlock = NewIfBlock;
      }
    }
  }
}

static Instruction *getFirstInst(Instruction *FirstInst, Value *V,
                                 Instruction *Loc) {
  if (FirstInst)
    return FirstInst;
  if (Instruction *I = dyn_cast<Instruction>(V))
    return I->getParent() == Loc->getParent() ? I : 0;
  return 0;
}

std::pair<Instruction *, Instruction *>
InnerLoopVectorizer::addStrideCheck(Instruction *Loc) {
  Instruction *tnullptr = 0;
  if (!Legal->mustCheckStrides())
    return std::pair<Instruction *, Instruction *>(tnullptr, tnullptr);

  IRBuilder<> ChkBuilder(Loc);

  // Emit checks.
  Value *Check = 0;
  Instruction *FirstInst = 0;
  for (SmallPtrSet<Value *, 8>::iterator SI = Legal->strides_begin(),
                                         SE = Legal->strides_end();
       SI != SE; ++SI) {
    Value *Ptr = stripIntegerCast(*SI);
    Value *C = ChkBuilder.CreateICmpNE(Ptr, ConstantInt::get(Ptr->getType(), 1),
                                       "stride.chk");
    // Store the first instruction we create.
    FirstInst = getFirstInst(FirstInst, C, Loc);
    if (Check)
      Check = ChkBuilder.CreateOr(Check, C);
    else
      Check = C;
  }

  // We have to do this trickery because the IRBuilder might fold the check to a
  // constant expression in which case there is no Instruction anchored in a
  // the block.
  LLVMContext &Ctx = Loc->getContext();
  Instruction *TheCheck =
      BinaryOperator::CreateAnd(Check, ConstantInt::getTrue(Ctx));
  ChkBuilder.Insert(TheCheck, "stride.not.one");
  FirstInst = getFirstInst(FirstInst, TheCheck, Loc);

  return std::make_pair(FirstInst, TheCheck);
}

std::pair<Instruction *, Instruction *>
InnerLoopVectorizer::addRuntimeCheck(Instruction *Loc) {
  LoopVectorizationLegality::RuntimePointerCheck *PtrRtCheck =
  Legal->getRuntimePointerCheck();

  Instruction *tnullptr = 0;
  if (!PtrRtCheck->Need)
    return std::pair<Instruction *, Instruction *>(tnullptr, tnullptr);

  unsigned NumPointers = PtrRtCheck->Pointers.size();
  SmallVector<TrackingVH<Value> , 2> Starts;
  SmallVector<TrackingVH<Value> , 2> Ends;

  LLVMContext &Ctx = Loc->getContext();
  SCEVExpander Exp(*SE, "induction");
  Instruction *FirstInst = 0;

  for (unsigned i = 0; i < NumPointers; ++i) {
    Value *Ptr = PtrRtCheck->Pointers[i];
    const SCEV *Sc = SE->getSCEV(Ptr);

    if (SE->isLoopInvariant(Sc, OrigLoop)) {
      DEBUG(dbgs() << "LV: Adding RT check for a loop invariant ptr:" <<
            *Ptr <<"\n");
      Starts.push_back(Ptr);
      Ends.push_back(Ptr);
    } else {
      DEBUG(dbgs() << "LV: Adding RT check for range:" << *Ptr << '\n');
      unsigned AS = Ptr->getType()->getPointerAddressSpace();

      // Use this type for pointer arithmetic.
      Type *PtrArithTy = Type::getInt8PtrTy(Ctx, AS);

      Value *Start = Exp.expandCodeFor(PtrRtCheck->Starts[i], PtrArithTy, Loc);
      Value *End = Exp.expandCodeFor(PtrRtCheck->Ends[i], PtrArithTy, Loc);
      Starts.push_back(Start);
      Ends.push_back(End);
    }
  }

  IRBuilder<> ChkBuilder(Loc);
  // Our instructions might fold to a constant.
  Value *MemoryRuntimeCheck = 0;
  for (unsigned i = 0; i < NumPointers; ++i) {
    for (unsigned j = i+1; j < NumPointers; ++j) {
      // No need to check if two readonly pointers intersect.
      if (!PtrRtCheck->IsWritePtr[i] && !PtrRtCheck->IsWritePtr[j])
        continue;

      // Only need to check pointers between two different dependency sets.
      if (PtrRtCheck->DependencySetId[i] == PtrRtCheck->DependencySetId[j])
       continue;

      unsigned AS0 = Starts[i]->getType()->getPointerAddressSpace();
      unsigned AS1 = Starts[j]->getType()->getPointerAddressSpace();

      assert((AS0 == Ends[j]->getType()->getPointerAddressSpace()) &&
             (AS1 == Ends[i]->getType()->getPointerAddressSpace()) &&
             "Trying to bounds check pointers with different address spaces");

      Type *PtrArithTy0 = Type::getInt8PtrTy(Ctx, AS0);
      Type *PtrArithTy1 = Type::getInt8PtrTy(Ctx, AS1);

      Value *Start0 = ChkBuilder.CreateBitCast(Starts[i], PtrArithTy0, "bc");
      Value *Start1 = ChkBuilder.CreateBitCast(Starts[j], PtrArithTy1, "bc");
      Value *End0 =   ChkBuilder.CreateBitCast(Ends[i],   PtrArithTy1, "bc");
      Value *End1 =   ChkBuilder.CreateBitCast(Ends[j],   PtrArithTy0, "bc");

      Value *Cmp0 = ChkBuilder.CreateICmpULE(Start0, End1, "bound0");
      FirstInst = getFirstInst(FirstInst, Cmp0, Loc);
      Value *Cmp1 = ChkBuilder.CreateICmpULE(Start1, End0, "bound1");
      FirstInst = getFirstInst(FirstInst, Cmp1, Loc);
      Value *IsConflict = ChkBuilder.CreateAnd(Cmp0, Cmp1, "found.conflict");
      FirstInst = getFirstInst(FirstInst, IsConflict, Loc);
      if (MemoryRuntimeCheck) {
        IsConflict = ChkBuilder.CreateOr(MemoryRuntimeCheck, IsConflict,
                                         "conflict.rdx");
        FirstInst = getFirstInst(FirstInst, IsConflict, Loc);
      }
      MemoryRuntimeCheck = IsConflict;
    }
  }

  // We have to do this trickery because the IRBuilder might fold the check to a
  // constant expression in which case there is no Instruction anchored in a
  // the block.
  Instruction *Check = BinaryOperator::CreateAnd(MemoryRuntimeCheck,
                                                 ConstantInt::getTrue(Ctx));
  ChkBuilder.Insert(Check, "memcheck.conflict");
  FirstInst = getFirstInst(FirstInst, Check, Loc);
  return std::make_pair(FirstInst, Check);
}

void InnerLoopVectorizer::createEmptyLoop() {
  /*
   In this function we generate a new loop. The new loop will contain
   the vectorized instructions while the old loop will continue to run the
   scalar remainder.

       [ ] <-- vector loop bypass (may consist of multiple blocks).
     /  |
    /   v
   |   [ ]     <-- vector pre header.
   |    |
   |    v
   |   [  ] \
   |   [  ]_|   <-- vector loop.
   |    |
    \   v
      >[ ]   <--- middle-block.
     /  |
    /   v
   |   [ ]     <--- new preheader.
   |    |
   |    v
   |   [ ] \
   |   [ ]_|   <-- old scalar loop to handle remainder.
    \   |
     \  v
      >[ ]     <-- exit block.
   ...
   */

  BasicBlock *OldBasicBlock = OrigLoop->getHeader();
  BasicBlock *BypassBlock = OrigLoop->getLoopPreheader();
  BasicBlock *ExitBlock = OrigLoop->getExitBlock();
  assert(ExitBlock && "Must have an exit block");

  // Some loops have a single integer induction variable, while other loops
  // don't. One example is c++ iterators that often have multiple pointer
  // induction variables. In the code below we also support a case where we
  // don't have a single induction variable.
  OldInduction = Legal->getInduction();
  Type *IdxTy = Legal->getWidestInductionType();

  // Find the loop boundaries.
  const SCEV *ExitCount = SE->getBackedgeTakenCount(OrigLoop);
  assert(ExitCount != SE->getCouldNotCompute() && "Invalid loop count");

  // The exit count might have the type of i64 while the phi is i32. This can
  // happen if we have an induction variable that is sign extended before the
  // compare. The only way that we get a backedge taken count is that the
  // induction variable was signed and as such will not overflow. In such a case
  // truncation is legal.
  if (ExitCount->getType()->getPrimitiveSizeInBits() >
      IdxTy->getPrimitiveSizeInBits())
    ExitCount = SE->getTruncateOrNoop(ExitCount, IdxTy);

  ExitCount = SE->getNoopOrZeroExtend(ExitCount, IdxTy);
  // Get the total trip count from the count by adding 1.
  ExitCount = SE->getAddExpr(ExitCount,
                             SE->getConstant(ExitCount->getType(), 1));

  // Expand the trip count and place the new instructions in the preheader.
  // Notice that the pre-header does not change, only the loop body.
  SCEVExpander Exp(*SE, "induction");

  // Count holds the overall loop count (N).
  Value *Count = Exp.expandCodeFor(ExitCount, ExitCount->getType(),
                                   BypassBlock->getTerminator());

  // The loop index does not have to start at Zero. Find the original start
  // value from the induction PHI node. If we don't have an induction variable
  // then we know that it starts at zero.
  Builder.SetInsertPoint(BypassBlock->getTerminator());
  Value *StartIdx = ExtendedIdx = OldInduction ?
    Builder.CreateZExt(OldInduction->getIncomingValueForBlock(BypassBlock),
                       IdxTy):
    ConstantInt::get(IdxTy, 0);

  assert(BypassBlock && "Invalid loop structure");
  LoopBypassBlocks.push_back(BypassBlock);

  // Split the single block loop into the two loop structure described above.
  BasicBlock *VectorPH =
  BypassBlock->splitBasicBlock(BypassBlock->getTerminator(), "vector.ph");
  BasicBlock *VecBody =
  VectorPH->splitBasicBlock(VectorPH->getTerminator(), "vector.body");
  BasicBlock *MiddleBlock =
  VecBody->splitBasicBlock(VecBody->getTerminator(), "middle.block");
  BasicBlock *ScalarPH =
  MiddleBlock->splitBasicBlock(MiddleBlock->getTerminator(), "scalar.ph");

  // Create and register the new vector loop.
  Loop* Lp = new Loop();
  Loop *ParentLoop = OrigLoop->getParentLoop();

  // Insert the new loop into the loop nest and register the new basic blocks
  // before calling any utilities such as SCEV that require valid LoopInfo.
  if (ParentLoop) {
    ParentLoop->addChildLoop(Lp);
    ParentLoop->addBasicBlockToLoop(ScalarPH, LI->getBase());
    ParentLoop->addBasicBlockToLoop(VectorPH, LI->getBase());
    ParentLoop->addBasicBlockToLoop(MiddleBlock, LI->getBase());
  } else {
    LI->addTopLevelLoop(Lp);
  }
  Lp->addBasicBlockToLoop(VecBody, LI->getBase());

  // Use this IR builder to create the loop instructions (Phi, Br, Cmp)
  // inside the loop.
  Builder.SetInsertPoint(VecBody->getFirstNonPHI());

  // Generate the induction variable.
  setDebugLocFromInst(Builder, getDebugLocFromInstOrOperands(OldInduction));
  Induction = Builder.CreatePHI(IdxTy, 2, "index");
  // The loop step is equal to the vectorization factor (num of SIMD elements)
  // times the unroll factor (num of SIMD instructions).
  Constant *Step = ConstantInt::get(IdxTy, VF * UF);

  // This is the IR builder that we use to add all of the logic for bypassing
  // the new vector loop.
  IRBuilder<> BypassBuilder(BypassBlock->getTerminator());
  setDebugLocFromInst(BypassBuilder,
                      getDebugLocFromInstOrOperands(OldInduction));

  // We may need to extend the index in case there is a type mismatch.
  // We know that the count starts at zero and does not overflow.
  if (Count->getType() != IdxTy) {
    // The exit count can be of pointer type. Convert it to the correct
    // integer type.
    if (ExitCount->getType()->isPointerTy())
      Count = BypassBuilder.CreatePointerCast(Count, IdxTy, "ptrcnt.to.int");
    else
      Count = BypassBuilder.CreateZExtOrTrunc(Count, IdxTy, "cnt.cast");
  }

  // Add the start index to the loop count to get the new end index.
  Value *IdxEnd = BypassBuilder.CreateAdd(Count, StartIdx, "end.idx");

  // Now we need to generate the expression for N - (N % VF), which is
  // the part that the vectorized body will execute.
  Value *R = BypassBuilder.CreateURem(Count, Step, "n.mod.vf");
  Value *CountRoundDown = BypassBuilder.CreateSub(Count, R, "n.vec");
  Value *IdxEndRoundDown = BypassBuilder.CreateAdd(CountRoundDown, StartIdx,
                                                     "end.idx.rnd.down");

  // Now, compare the new count to zero. If it is zero skip the vector loop and
  // jump to the scalar loop.
  Value *Cmp = BypassBuilder.CreateICmpEQ(IdxEndRoundDown, StartIdx,
                                          "cmp.zero");

  BasicBlock *LastBypassBlock = BypassBlock;

  // Generate the code to check that the strides we assumed to be one are really
  // one. We want the new basic block to start at the first instruction in a
  // sequence of instructions that form a check.
  Instruction *StrideCheck;
  Instruction *FirstCheckInst;
  tie(FirstCheckInst, StrideCheck) =
      addStrideCheck(BypassBlock->getTerminator());
  if (StrideCheck) {
    // Create a new block containing the stride check.
    BasicBlock *CheckBlock =
        BypassBlock->splitBasicBlock(FirstCheckInst, "vector.stridecheck");
    if (ParentLoop)
      ParentLoop->addBasicBlockToLoop(CheckBlock, LI->getBase());
    LoopBypassBlocks.push_back(CheckBlock);

    // Replace the branch into the memory check block with a conditional branch
    // for the "few elements case".
    Instruction *OldTerm = BypassBlock->getTerminator();
    BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm);
    OldTerm->eraseFromParent();

    Cmp = StrideCheck;
    LastBypassBlock = CheckBlock;
  }

  // Generate the code that checks in runtime if arrays overlap. We put the
  // checks into a separate block to make the more common case of few elements
  // faster.
  Instruction *MemRuntimeCheck;
  tie(FirstCheckInst, MemRuntimeCheck) =
      addRuntimeCheck(LastBypassBlock->getTerminator());
  if (MemRuntimeCheck) {
    // Create a new block containing the memory check.
    BasicBlock *CheckBlock =
        LastBypassBlock->splitBasicBlock(MemRuntimeCheck, "vector.memcheck");
    if (ParentLoop)
      ParentLoop->addBasicBlockToLoop(CheckBlock, LI->getBase());
    LoopBypassBlocks.push_back(CheckBlock);

    // Replace the branch into the memory check block with a conditional branch
    // for the "few elements case".
    Instruction *OldTerm = LastBypassBlock->getTerminator();
    BranchInst::Create(MiddleBlock, CheckBlock, Cmp, OldTerm);
    OldTerm->eraseFromParent();

    Cmp = MemRuntimeCheck;
    LastBypassBlock = CheckBlock;
  }

  LastBypassBlock->getTerminator()->eraseFromParent();
  BranchInst::Create(MiddleBlock, VectorPH, Cmp,
                     LastBypassBlock);

  // We are going to resume the execution of the scalar loop.
  // Go over all of the induction variables that we found and fix the
  // PHIs that are left in the scalar version of the loop.
  // The starting values of PHI nodes depend on the counter of the last
  // iteration in the vectorized loop.
  // If we come from a bypass edge then we need to start from the original
  // start value.

  // This variable saves the new starting index for the scalar loop.
  PHINode *ResumeIndex = 0;
  LoopVectorizationLegality::InductionList::iterator I, E;
  LoopVectorizationLegality::InductionList *List = Legal->getInductionVars();
  // Set builder to point to last bypass block.
  BypassBuilder.SetInsertPoint(LoopBypassBlocks.back()->getTerminator());
  for (I = List->begin(), E = List->end(); I != E; ++I) {
    PHINode *OrigPhi = I->first;
    LoopVectorizationLegality::InductionInfo II = I->second;

    Type *ResumeValTy = (OrigPhi == OldInduction) ? IdxTy : OrigPhi->getType();
    PHINode *ResumeVal = PHINode::Create(ResumeValTy, 2, "resume.val",
                                         MiddleBlock->getTerminator());
    // We might have extended the type of the induction variable but we need a
    // truncated version for the scalar loop.
    PHINode *TruncResumeVal = (OrigPhi == OldInduction) ?
      PHINode::Create(OrigPhi->getType(), 2, "trunc.resume.val",
                      MiddleBlock->getTerminator()) : 0;

    Value *EndValue = 0;
    switch (II.IK) {
    case LoopVectorizationLegality::IK_NoInduction:
      llvm_unreachable("Unknown induction");
    case LoopVectorizationLegality::IK_IntInduction: {
      // Handle the integer induction counter.
      assert(OrigPhi->getType()->isIntegerTy() && "Invalid type");

      // We have the canonical induction variable.
      if (OrigPhi == OldInduction) {
        // Create a truncated version of the resume value for the scalar loop,
        // we might have promoted the type to a larger width.
        EndValue =
          BypassBuilder.CreateTrunc(IdxEndRoundDown, OrigPhi->getType());
        // The new PHI merges the original incoming value, in case of a bypass,
        // or the value at the end of the vectorized loop.
        for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I)
          TruncResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[I]);
        TruncResumeVal->addIncoming(EndValue, VecBody);

        // We know what the end value is.
        EndValue = IdxEndRoundDown;
        // We also know which PHI node holds it.
        ResumeIndex = ResumeVal;
        break;
      }

      // Not the canonical induction variable - add the vector loop count to the
      // start value.
      Value *CRD = BypassBuilder.CreateSExtOrTrunc(CountRoundDown,
                                                   II.StartValue->getType(),
                                                   "cast.crd");
      EndValue = BypassBuilder.CreateAdd(CRD, II.StartValue , "ind.end");
      break;
    }
    case LoopVectorizationLegality::IK_ReverseIntInduction: {
      // Convert the CountRoundDown variable to the PHI size.
      Value *CRD = BypassBuilder.CreateSExtOrTrunc(CountRoundDown,
                                                   II.StartValue->getType(),
                                                   "cast.crd");
      // Handle reverse integer induction counter.
      EndValue = BypassBuilder.CreateSub(II.StartValue, CRD, "rev.ind.end");
      break;
    }
    case LoopVectorizationLegality::IK_PtrInduction: {
      // For pointer induction variables, calculate the offset using
      // the end index.
      EndValue = BypassBuilder.CreateGEP(II.StartValue, CountRoundDown,
                                         "ptr.ind.end");
      break;
    }
    case LoopVectorizationLegality::IK_ReversePtrInduction: {
      // The value at the end of the loop for the reverse pointer is calculated
      // by creating a GEP with a negative index starting from the start value.
      Value *Zero = ConstantInt::get(CountRoundDown->getType(), 0);
      Value *NegIdx = BypassBuilder.CreateSub(Zero, CountRoundDown,
                                              "rev.ind.end");
      EndValue = BypassBuilder.CreateGEP(II.StartValue, NegIdx,
                                         "rev.ptr.ind.end");
      break;
    }
    }// end of case

    // The new PHI merges the original incoming value, in case of a bypass,
    // or the value at the end of the vectorized loop.
    for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I) {
      if (OrigPhi == OldInduction)
        ResumeVal->addIncoming(StartIdx, LoopBypassBlocks[I]);
      else
        ResumeVal->addIncoming(II.StartValue, LoopBypassBlocks[I]);
    }
    ResumeVal->addIncoming(EndValue, VecBody);

    // Fix the scalar body counter (PHI node).
    unsigned BlockIdx = OrigPhi->getBasicBlockIndex(ScalarPH);
    // The old inductions phi node in the scalar body needs the truncated value.
    if (OrigPhi == OldInduction)
      OrigPhi->setIncomingValue(BlockIdx, TruncResumeVal);
    else
      OrigPhi->setIncomingValue(BlockIdx, ResumeVal);
  }

  // If we are generating a new induction variable then we also need to
  // generate the code that calculates the exit value. This value is not
  // simply the end of the counter because we may skip the vectorized body
  // in case of a runtime check.
  if (!OldInduction){
    assert(!ResumeIndex && "Unexpected resume value found");
    ResumeIndex = PHINode::Create(IdxTy, 2, "new.indc.resume.val",
                                  MiddleBlock->getTerminator());
    for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I)
      ResumeIndex->addIncoming(StartIdx, LoopBypassBlocks[I]);
    ResumeIndex->addIncoming(IdxEndRoundDown, VecBody);
  }

  // Make sure that we found the index where scalar loop needs to continue.
  assert(ResumeIndex && ResumeIndex->getType()->isIntegerTy() &&
         "Invalid resume Index");

  // Add a check in the middle block to see if we have completed
  // all of the iterations in the first vector loop.
  // If (N - N%VF) == N, then we *don't* need to run the remainder.
  Value *CmpN = CmpInst::Create(Instruction::ICmp, CmpInst::ICMP_EQ, IdxEnd,
                                ResumeIndex, "cmp.n",
                                MiddleBlock->getTerminator());

  BranchInst::Create(ExitBlock, ScalarPH, CmpN, MiddleBlock->getTerminator());
  // Remove the old terminator.
  MiddleBlock->getTerminator()->eraseFromParent();

  // Create i+1 and fill the PHINode.
  Value *NextIdx = Builder.CreateAdd(Induction, Step, "index.next");
  Induction->addIncoming(StartIdx, VectorPH);
  Induction->addIncoming(NextIdx, VecBody);
  // Create the compare.
  Value *ICmp = Builder.CreateICmpEQ(NextIdx, IdxEndRoundDown);
  Builder.CreateCondBr(ICmp, MiddleBlock, VecBody);

  // Now we have two terminators. Remove the old one from the block.
  VecBody->getTerminator()->eraseFromParent();

  // Get ready to start creating new instructions into the vectorized body.
  Builder.SetInsertPoint(VecBody->getFirstInsertionPt());

  // Save the state.
  LoopVectorPreHeader = VectorPH;
  LoopScalarPreHeader = ScalarPH;
  LoopMiddleBlock = MiddleBlock;
  LoopExitBlock = ExitBlock;
  LoopVectorBody.push_back(VecBody);
  LoopScalarBody = OldBasicBlock;

  LoopVectorizeHints Hints(Lp, true);
  Hints.setAlreadyVectorized(Lp);
}

/// This function returns the identity element (or neutral element) for
/// the operation K.
Constant*
LoopVectorizationLegality::getReductionIdentity(ReductionKind K, Type *Tp) {
  switch (K) {
  case RK_IntegerXor:
  case RK_IntegerAdd:
  case RK_IntegerOr:
    // Adding, Xoring, Oring zero to a number does not change it.
    return ConstantInt::get(Tp, 0);
  case RK_IntegerMult:
    // Multiplying a number by 1 does not change it.
    return ConstantInt::get(Tp, 1);
  case RK_IntegerAnd:
    // AND-ing a number with an all-1 value does not change it.
    return ConstantInt::get(Tp, -1, true);
  case  RK_FloatMult:
    // Multiplying a number by 1 does not change it.
    return ConstantFP::get(Tp, 1.0L);
  case  RK_FloatAdd:
    // Adding zero to a number does not change it.
    return ConstantFP::get(Tp, 0.0L);
  default:
    llvm_unreachable("Unknown reduction kind");
  }
}

static Intrinsic::ID checkUnaryFloatSignature(const CallInst &I,
                                              Intrinsic::ID ValidIntrinsicID) {
  if (I.getNumArgOperands() != 1 ||
      !I.getArgOperand(0)->getType()->isFloatingPointTy() ||
      I.getType() != I.getArgOperand(0)->getType() ||
      !I.onlyReadsMemory())
    return Intrinsic::not_intrinsic;

  return ValidIntrinsicID;
}

static Intrinsic::ID checkBinaryFloatSignature(const CallInst &I,
                                               Intrinsic::ID ValidIntrinsicID) {
  if (I.getNumArgOperands() != 2 ||
      !I.getArgOperand(0)->getType()->isFloatingPointTy() ||
      !I.getArgOperand(1)->getType()->isFloatingPointTy() ||
      I.getType() != I.getArgOperand(0)->getType() ||
      I.getType() != I.getArgOperand(1)->getType() ||
      !I.onlyReadsMemory())
    return Intrinsic::not_intrinsic;

  return ValidIntrinsicID;
}


static Intrinsic::ID
getIntrinsicIDForCall(CallInst *CI, const TargetLibraryInfo *TLI) {
  // If we have an intrinsic call, check if it is trivially vectorizable.
  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(CI)) {
    switch (II->getIntrinsicID()) {
    case Intrinsic::sqrt:
    case Intrinsic::sin:
    case Intrinsic::cos:
    case Intrinsic::exp:
    case Intrinsic::exp2:
    case Intrinsic::log:
    case Intrinsic::log10:
    case Intrinsic::log2:
    case Intrinsic::fabs:
    case Intrinsic::copysign:
    case Intrinsic::floor:
    case Intrinsic::ceil:
    case Intrinsic::trunc:
    case Intrinsic::rint:
    case Intrinsic::nearbyint:
    case Intrinsic::round:
    case Intrinsic::pow:
    case Intrinsic::fma:
    case Intrinsic::fmuladd:
    case Intrinsic::lifetime_start:
    case Intrinsic::lifetime_end:
      return II->getIntrinsicID();
    default:
      return Intrinsic::not_intrinsic;
    }
  }

  if (!TLI)
    return Intrinsic::not_intrinsic;

  LibFunc::Func Func;
  Function *F = CI->getCalledFunction();
  // We're going to make assumptions on the semantics of the functions, check
  // that the target knows that it's available in this environment and it does
  // not have local linkage.
  if (!F || F->hasLocalLinkage() || !TLI->getLibFunc(F->getName(), Func))
    return Intrinsic::not_intrinsic;

  // Otherwise check if we have a call to a function that can be turned into a
  // vector intrinsic.
  switch (Func) {
  default:
    break;
  case LibFunc::sin:
  case LibFunc::sinf:
  case LibFunc::sinl:
    return checkUnaryFloatSignature(*CI, Intrinsic::sin);
  case LibFunc::cos:
  case LibFunc::cosf:
  case LibFunc::cosl:
    return checkUnaryFloatSignature(*CI, Intrinsic::cos);
  case LibFunc::exp:
  case LibFunc::expf:
  case LibFunc::expl:
    return checkUnaryFloatSignature(*CI, Intrinsic::exp);
  case LibFunc::exp2:
  case LibFunc::exp2f:
  case LibFunc::exp2l:
    return checkUnaryFloatSignature(*CI, Intrinsic::exp2);
  case LibFunc::log:
  case LibFunc::logf:
  case LibFunc::logl:
    return checkUnaryFloatSignature(*CI, Intrinsic::log);
  case LibFunc::log10:
  case LibFunc::log10f:
  case LibFunc::log10l:
    return checkUnaryFloatSignature(*CI, Intrinsic::log10);
  case LibFunc::log2:
  case LibFunc::log2f:
  case LibFunc::log2l:
    return checkUnaryFloatSignature(*CI, Intrinsic::log2);
  case LibFunc::fabs:
  case LibFunc::fabsf:
  case LibFunc::fabsl:
    return checkUnaryFloatSignature(*CI, Intrinsic::fabs);
  case LibFunc::copysign:
  case LibFunc::copysignf:
  case LibFunc::copysignl:
    return checkBinaryFloatSignature(*CI, Intrinsic::copysign);
  case LibFunc::floor:
  case LibFunc::floorf:
  case LibFunc::floorl:
    return checkUnaryFloatSignature(*CI, Intrinsic::floor);
  case LibFunc::ceil:
  case LibFunc::ceilf:
  case LibFunc::ceill:
    return checkUnaryFloatSignature(*CI, Intrinsic::ceil);
  case LibFunc::trunc:
  case LibFunc::truncf:
  case LibFunc::truncl:
    return checkUnaryFloatSignature(*CI, Intrinsic::trunc);
  case LibFunc::rint:
  case LibFunc::rintf:
  case LibFunc::rintl:
    return checkUnaryFloatSignature(*CI, Intrinsic::rint);
  case LibFunc::nearbyint:
  case LibFunc::nearbyintf:
  case LibFunc::nearbyintl:
    return checkUnaryFloatSignature(*CI, Intrinsic::nearbyint);
  case LibFunc::round:
  case LibFunc::roundf:
  case LibFunc::roundl:
    return checkUnaryFloatSignature(*CI, Intrinsic::round);
  case LibFunc::pow:
  case LibFunc::powf:
  case LibFunc::powl:
    return checkBinaryFloatSignature(*CI, Intrinsic::pow);
  }

  return Intrinsic::not_intrinsic;
}

/// This function translates the reduction kind to an LLVM binary operator.
static unsigned
getReductionBinOp(LoopVectorizationLegality::ReductionKind Kind) {
  switch (Kind) {
    case LoopVectorizationLegality::RK_IntegerAdd:
      return Instruction::Add;
    case LoopVectorizationLegality::RK_IntegerMult:
      return Instruction::Mul;
    case LoopVectorizationLegality::RK_IntegerOr:
      return Instruction::Or;
    case LoopVectorizationLegality::RK_IntegerAnd:
      return Instruction::And;
    case LoopVectorizationLegality::RK_IntegerXor:
      return Instruction::Xor;
    case LoopVectorizationLegality::RK_FloatMult:
      return Instruction::FMul;
    case LoopVectorizationLegality::RK_FloatAdd:
      return Instruction::FAdd;
    case LoopVectorizationLegality::RK_IntegerMinMax:
      return Instruction::ICmp;
    case LoopVectorizationLegality::RK_FloatMinMax:
      return Instruction::FCmp;
    default:
      llvm_unreachable("Unknown reduction operation");
  }
}

Value *createMinMaxOp(IRBuilder<> &Builder,
                      LoopVectorizationLegality::MinMaxReductionKind RK,
                      Value *Left,
                      Value *Right) {
  CmpInst::Predicate P = CmpInst::ICMP_NE;
  switch (RK) {
  default:
    llvm_unreachable("Unknown min/max reduction kind");
  case LoopVectorizationLegality::MRK_UIntMin:
    P = CmpInst::ICMP_ULT;
    break;
  case LoopVectorizationLegality::MRK_UIntMax:
    P = CmpInst::ICMP_UGT;
    break;
  case LoopVectorizationLegality::MRK_SIntMin:
    P = CmpInst::ICMP_SLT;
    break;
  case LoopVectorizationLegality::MRK_SIntMax:
    P = CmpInst::ICMP_SGT;
    break;
  case LoopVectorizationLegality::MRK_FloatMin:
    P = CmpInst::FCMP_OLT;
    break;
  case LoopVectorizationLegality::MRK_FloatMax:
    P = CmpInst::FCMP_OGT;
    break;
  }

  Value *Cmp;
  if (RK == LoopVectorizationLegality::MRK_FloatMin ||
      RK == LoopVectorizationLegality::MRK_FloatMax)
    Cmp = Builder.CreateFCmp(P, Left, Right, "rdx.minmax.cmp");
  else
    Cmp = Builder.CreateICmp(P, Left, Right, "rdx.minmax.cmp");

  Value *Select = Builder.CreateSelect(Cmp, Left, Right, "rdx.minmax.select");
  return Select;
}

namespace {
struct CSEDenseMapInfo {
  static bool canHandle(Instruction *I) {
    return isa<InsertElementInst>(I) || isa<ExtractElementInst>(I) ||
           isa<ShuffleVectorInst>(I) || isa<GetElementPtrInst>(I);
  }
  static inline Instruction *getEmptyKey() {
    return DenseMapInfo<Instruction *>::getEmptyKey();
  }
  static inline Instruction *getTombstoneKey() {
    return DenseMapInfo<Instruction *>::getTombstoneKey();
  }
  static unsigned getHashValue(Instruction *I) {
    assert(canHandle(I) && "Unknown instruction!");
    return hash_combine(I->getOpcode(), hash_combine_range(I->value_op_begin(),
                                                           I->value_op_end()));
  }
  static bool isEqual(Instruction *LHS, Instruction *RHS) {
    if (LHS == getEmptyKey() || RHS == getEmptyKey() ||
        LHS == getTombstoneKey() || RHS == getTombstoneKey())
      return LHS == RHS;
    return LHS->isIdenticalTo(RHS);
  }
};
}

/// \brief Check whether this block is a predicated block.
/// Due to if predication of stores we might create a sequence of "if(pred) a[i]
/// = ...;  " blocks. We start with one vectorized basic block. For every
/// conditional block we split this vectorized block. Therefore, every second
/// block will be a predicated one.
static bool isPredicatedBlock(unsigned BlockNum) {
  return BlockNum % 2;
}

///\brief Perform cse of induction variable instructions.
static void cse(SmallVector<BasicBlock *, 4> &BBs) {
  // Perform simple cse.
  SmallDenseMap<Instruction *, Instruction *, 4, CSEDenseMapInfo> CSEMap;
  for (unsigned i = 0, e = BBs.size(); i != e; ++i) {
    BasicBlock *BB = BBs[i];
    for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) {
      Instruction *In = I++;

      if (!CSEDenseMapInfo::canHandle(In))
        continue;

      // Check if we can replace this instruction with any of the
      // visited instructions.
      if (Instruction *V = CSEMap.lookup(In)) {
        In->replaceAllUsesWith(V);
        In->eraseFromParent();
        continue;
      }
      // Ignore instructions in conditional blocks. We create "if (pred) a[i] =
      // ...;" blocks for predicated stores. Every second block is a predicated
      // block.
      if (isPredicatedBlock(i))
        continue;

      CSEMap[In] = In;
    }
  }
}

void InnerLoopVectorizer::vectorizeLoop() {
  //===------------------------------------------------===//
  //
  // Notice: any optimization or new instruction that go
  // into the code below should be also be implemented in
  // the cost-model.
  //
  //===------------------------------------------------===//
  Constant *Zero = Builder.getInt32(0);

  // In order to support reduction variables we need to be able to vectorize
  // Phi nodes. Phi nodes have cycles, so we need to vectorize them in two
  // stages. First, we create a new vector PHI node with no incoming edges.
  // We use this value when we vectorize all of the instructions that use the
  // PHI. Next, after all of the instructions in the block are complete we
  // add the new incoming edges to the PHI. At this point all of the
  // instructions in the basic block are vectorized, so we can use them to
  // construct the PHI.
  PhiVector RdxPHIsToFix;

  // Scan the loop in a topological order to ensure that defs are vectorized
  // before users.
  LoopBlocksDFS DFS(OrigLoop);
  DFS.perform(LI);

  // Vectorize all of the blocks in the original loop.
  for (LoopBlocksDFS::RPOIterator bb = DFS.beginRPO(),
       be = DFS.endRPO(); bb != be; ++bb)
    vectorizeBlockInLoop(*bb, &RdxPHIsToFix);

  // At this point every instruction in the original loop is widened to
  // a vector form. We are almost done. Now, we need to fix the PHI nodes
  // that we vectorized. The PHI nodes are currently empty because we did
  // not want to introduce cycles. Notice that the remaining PHI nodes
  // that we need to fix are reduction variables.

  // Create the 'reduced' values for each of the induction vars.
  // The reduced values are the vector values that we scalarize and combine
  // after the loop is finished.
  for (PhiVector::iterator it = RdxPHIsToFix.begin(), e = RdxPHIsToFix.end();
       it != e; ++it) {
    PHINode *RdxPhi = *it;
    assert(RdxPhi && "Unable to recover vectorized PHI");

    // Find the reduction variable descriptor.
    assert(Legal->getReductionVars()->count(RdxPhi) &&
           "Unable to find the reduction variable");
    LoopVectorizationLegality::ReductionDescriptor RdxDesc =
    (*Legal->getReductionVars())[RdxPhi];

    setDebugLocFromInst(Builder, RdxDesc.StartValue);

    // We need to generate a reduction vector from the incoming scalar.
    // To do so, we need to generate the 'identity' vector and override
    // one of the elements with the incoming scalar reduction. We need
    // to do it in the vector-loop preheader.
    Builder.SetInsertPoint(LoopBypassBlocks.front()->getTerminator());

    // This is the vector-clone of the value that leaves the loop.
    VectorParts &VectorExit = getVectorValue(RdxDesc.LoopExitInstr);
    Type *VecTy = VectorExit[0]->getType();

    // Find the reduction identity variable. Zero for addition, or, xor,
    // one for multiplication, -1 for And.
    Value *Identity;
    Value *VectorStart;
    if (RdxDesc.Kind == LoopVectorizationLegality::RK_IntegerMinMax ||
        RdxDesc.Kind == LoopVectorizationLegality::RK_FloatMinMax) {
      // MinMax reduction have the start value as their identify.
      if (VF == 1) {
        VectorStart = Identity = RdxDesc.StartValue;
      } else {
        VectorStart = Identity = Builder.CreateVectorSplat(VF,
                                                           RdxDesc.StartValue,
                                                           "minmax.ident");
      }
    } else {
      // Handle other reduction kinds:
      Constant *Iden =
      LoopVectorizationLegality::getReductionIdentity(RdxDesc.Kind,
                                                      VecTy->getScalarType());
      if (VF == 1) {
        Identity = Iden;
        // This vector is the Identity vector where the first element is the
        // incoming scalar reduction.
        VectorStart = RdxDesc.StartValue;
      } else {
        Identity = ConstantVector::getSplat(VF, Iden);

        // This vector is the Identity vector where the first element is the
        // incoming scalar reduction.
        VectorStart = Builder.CreateInsertElement(Identity,
                                                  RdxDesc.StartValue, Zero);
      }
    }

    // Fix the vector-loop phi.
    // We created the induction variable so we know that the
    // preheader is the first entry.
    BasicBlock *VecPreheader = Induction->getIncomingBlock(0);

    // Reductions do not have to start at zero. They can start with
    // any loop invariant values.
    VectorParts &VecRdxPhi = WidenMap.get(RdxPhi);
    BasicBlock *Latch = OrigLoop->getLoopLatch();
    Value *LoopVal = RdxPhi->getIncomingValueForBlock(Latch);
    VectorParts &Val = getVectorValue(LoopVal);
    for (unsigned part = 0; part < UF; ++part) {
      // Make sure to add the reduction stat value only to the
      // first unroll part.
      Value *StartVal = (part == 0) ? VectorStart : Identity;
      cast<PHINode>(VecRdxPhi[part])->addIncoming(StartVal, VecPreheader);
      cast<PHINode>(VecRdxPhi[part])->addIncoming(Val[part],
                                                  LoopVectorBody.back());
    }

    // Before each round, move the insertion point right between
    // the PHIs and the values we are going to write.
    // This allows us to write both PHINodes and the extractelement
    // instructions.
    Builder.SetInsertPoint(LoopMiddleBlock->getFirstInsertionPt());

    VectorParts RdxParts;
    setDebugLocFromInst(Builder, RdxDesc.LoopExitInstr);
    for (unsigned part = 0; part < UF; ++part) {
      // This PHINode contains the vectorized reduction variable, or
      // the initial value vector, if we bypass the vector loop.
      VectorParts &RdxExitVal = getVectorValue(RdxDesc.LoopExitInstr);
      PHINode *NewPhi = Builder.CreatePHI(VecTy, 2, "rdx.vec.exit.phi");
      Value *StartVal = (part == 0) ? VectorStart : Identity;
      for (unsigned I = 0, E = LoopBypassBlocks.size(); I != E; ++I)
        NewPhi->addIncoming(StartVal, LoopBypassBlocks[I]);
      NewPhi->addIncoming(RdxExitVal[part],
                          LoopVectorBody.back());
      RdxParts.push_back(NewPhi);
    }

    // Reduce all of the unrolled parts into a single vector.
    Value *ReducedPartRdx = RdxParts[0];
    unsigned Op = getReductionBinOp(RdxDesc.Kind);
    setDebugLocFromInst(Builder, ReducedPartRdx);
    for (unsigned part = 1; part < UF; ++part) {
      if (Op != Instruction::ICmp && Op != Instruction::FCmp)
        ReducedPartRdx = Builder.CreateBinOp((Instruction::BinaryOps)Op,
                                             RdxParts[part], ReducedPartRdx,
                                             "bin.rdx");
      else
        ReducedPartRdx = createMinMaxOp(Builder, RdxDesc.MinMaxKind,
                                        ReducedPartRdx, RdxParts[part]);
    }

    if (VF > 1) {
      // VF is a power of 2 so we can emit the reduction using log2(VF) shuffles
      // and vector ops, reducing the set of values being computed by half each
      // round.
      assert(isPowerOf2_32(VF) &&
             "Reduction emission only supported for pow2 vectors!");
      Value *TmpVec = ReducedPartRdx;
      SmallVector<Constant*, 32> ShuffleMask(VF, 0);
      for (unsigned i = VF; i != 1; i >>= 1) {
        // Move the upper half of the vector to the lower half.
        for (unsigned j = 0; j != i/2; ++j)
          ShuffleMask[j] = Builder.getInt32(i/2 + j);

        // Fill the rest of the mask with undef.
        std::fill(&ShuffleMask[i/2], ShuffleMask.end(),
                  UndefValue::get(Builder.getInt32Ty()));

        Value *Shuf =
        Builder.CreateShuffleVector(TmpVec,
                                    UndefValue::get(TmpVec->getType()),
                                    ConstantVector::get(ShuffleMask),
                                    "rdx.shuf");

        if (Op != Instruction::ICmp && Op != Instruction::FCmp)
          TmpVec = Builder.CreateBinOp((Instruction::BinaryOps)Op, TmpVec, Shuf,
                                       "bin.rdx");
        else
          TmpVec = createMinMaxOp(Builder, RdxDesc.MinMaxKind, TmpVec, Shuf);
      }

      // The result is in the first element of the vector.
      ReducedPartRdx = Builder.CreateExtractElement(TmpVec,
                                                    Builder.getInt32(0));
    }

    // Now, we need to fix the users of the reduction variable
    // inside and outside of the scalar remainder loop.
    // We know that the loop is in LCSSA form. We need to update the
    // PHI nodes in the exit blocks.
    for (BasicBlock::iterator LEI = LoopExitBlock->begin(),
         LEE = LoopExitBlock->end(); LEI != LEE; ++LEI) {
      PHINode *LCSSAPhi = dyn_cast<PHINode>(LEI);
      if (!LCSSAPhi) break;

      // All PHINodes need to have a single entry edge, or two if
      // we already fixed them.
      assert(LCSSAPhi->getNumIncomingValues() < 3 && "Invalid LCSSA PHI");

      // We found our reduction value exit-PHI. Update it with the
      // incoming bypass edge.
      if (LCSSAPhi->getIncomingValue(0) == RdxDesc.LoopExitInstr) {
        // Add an edge coming from the bypass.
        LCSSAPhi->addIncoming(ReducedPartRdx, LoopMiddleBlock);
        break;
      }
    }// end of the LCSSA phi scan.

    // Fix the scalar loop reduction variable with the incoming reduction sum
    // from the vector body and from the backedge value.
    int IncomingEdgeBlockIdx =
    (RdxPhi)->getBasicBlockIndex(OrigLoop->getLoopLatch());
    assert(IncomingEdgeBlockIdx >= 0 && "Invalid block index");
    // Pick the other block.
    int SelfEdgeBlockIdx = (IncomingEdgeBlockIdx ? 0 : 1);
    (RdxPhi)->setIncomingValue(SelfEdgeBlockIdx, ReducedPartRdx);
    (RdxPhi)->setIncomingValue(IncomingEdgeBlockIdx, RdxDesc.LoopExitInstr);
  }// end of for each redux variable.

  fixLCSSAPHIs();

  // Remove redundant induction instructions.
  cse(LoopVectorBody);
}

void InnerLoopVectorizer::fixLCSSAPHIs() {
  for (BasicBlock::iterator LEI = LoopExitBlock->begin(),
       LEE = LoopExitBlock->end(); LEI != LEE; ++LEI) {
    PHINode *LCSSAPhi = dyn_cast<PHINode>(LEI);
    if (!LCSSAPhi) break;
    if (LCSSAPhi->getNumIncomingValues() == 1)
      LCSSAPhi->addIncoming(UndefValue::get(LCSSAPhi->getType()),
                            LoopMiddleBlock);
  }
} 

InnerLoopVectorizer::VectorParts
InnerLoopVectorizer::createEdgeMask(BasicBlock *Src, BasicBlock *Dst) {
  assert(std::find(pred_begin(Dst), pred_end(Dst), Src) != pred_end(Dst) &&
         "Invalid edge");

  // Look for cached value.
  std::pair<BasicBlock*, BasicBlock*> Edge(Src, Dst);
  EdgeMaskCache::iterator ECEntryIt = MaskCache.find(Edge);
  if (ECEntryIt != MaskCache.end())
    return ECEntryIt->second;

  VectorParts SrcMask = createBlockInMask(Src);

  // The terminator has to be a branch inst!
  BranchInst *BI = dyn_cast<BranchInst>(Src->getTerminator());
  assert(BI && "Unexpected terminator found");

  if (BI->isConditional()) {
    VectorParts EdgeMask = getVectorValue(BI->getCondition());

    if (BI->getSuccessor(0) != Dst)
      for (unsigned part = 0; part < UF; ++part)
        EdgeMask[part] = Builder.CreateNot(EdgeMask[part]);

    for (unsigned part = 0; part < UF; ++part)
      EdgeMask[part] = Builder.CreateAnd(EdgeMask[part], SrcMask[part]);

    MaskCache[Edge] = EdgeMask;
    return EdgeMask;
  }

  MaskCache[Edge] = SrcMask;
  return SrcMask;
}

InnerLoopVectorizer::VectorParts
InnerLoopVectorizer::createBlockInMask(BasicBlock *BB) {
  assert(OrigLoop->contains(BB) && "Block is not a part of a loop");

  // Loop incoming mask is all-one.
  if (OrigLoop->getHeader() == BB) {
    Value *C = ConstantInt::get(IntegerType::getInt1Ty(BB->getContext()), 1);
    return getVectorValue(C);
  }

  // This is the block mask. We OR all incoming edges, and with zero.
  Value *Zero = ConstantInt::get(IntegerType::getInt1Ty(BB->getContext()), 0);
  VectorParts BlockMask = getVectorValue(Zero);

  // For each pred:
  for (pred_iterator it = pred_begin(BB), e = pred_end(BB); it != e; ++it) {
    VectorParts EM = createEdgeMask(*it, BB);
    for (unsigned part = 0; part < UF; ++part)
      BlockMask[part] = Builder.CreateOr(BlockMask[part], EM[part]);
  }

  return BlockMask;
}

void InnerLoopVectorizer::widenPHIInstruction(Instruction *PN,
                                              InnerLoopVectorizer::VectorParts &Entry,
                                              unsigned UF, unsigned VF, PhiVector *PV) {
  PHINode* P = cast<PHINode>(PN);
  // Handle reduction variables:
  if (Legal->getReductionVars()->count(P)) {
    for (unsigned part = 0; part < UF; ++part) {
      // This is phase one of vectorizing PHIs.
      Type *VecTy = (VF == 1) ? PN->getType() :
      VectorType::get(PN->getType(), VF);
      Entry[part] = PHINode::Create(VecTy, 2, "vec.phi",
                                    LoopVectorBody.back()-> getFirstInsertionPt());
    }
    PV->push_back(P);
    return;
  }

  setDebugLocFromInst(Builder, P);
  // Check for PHI nodes that are lowered to vector selects.
  if (P->getParent() != OrigLoop->getHeader()) {
    // We know that all PHIs in non-header blocks are converted into
    // selects, so we don't have to worry about the insertion order and we
    // can just use the builder.
    // At this point we generate the predication tree. There may be
    // duplications since this is a simple recursive scan, but future
    // optimizations will clean it up.

    unsigned NumIncoming = P->getNumIncomingValues();

    // Generate a sequence of selects of the form:
    // SELECT(Mask3, In3,
    //      SELECT(Mask2, In2,
    //                   ( ...)))
    for (unsigned In = 0; In < NumIncoming; In++) {
      VectorParts Cond = createEdgeMask(P->getIncomingBlock(In),
                                        P->getParent());
      VectorParts &In0 = getVectorValue(P->getIncomingValue(In));

      for (unsigned part = 0; part < UF; ++part) {
        // We might have single edge PHIs (blocks) - use an identity
        // 'select' for the first PHI operand.
        if (In == 0)
          Entry[part] = Builder.CreateSelect(Cond[part], In0[part],
                                             In0[part]);
        else
          // Select between the current value and the previous incoming edge
          // based on the incoming mask.
          Entry[part] = Builder.CreateSelect(Cond[part], In0[part],
                                             Entry[part], "predphi");
      }
    }
    return;
  }

  // This PHINode must be an induction variable.
  // Make sure that we know about it.
  assert(Legal->getInductionVars()->count(P) &&
         "Not an induction variable");

  LoopVectorizationLegality::InductionInfo II =
  Legal->getInductionVars()->lookup(P);

  switch (II.IK) {
    case LoopVectorizationLegality::IK_NoInduction:
      llvm_unreachable("Unknown induction");
    case LoopVectorizationLegality::IK_IntInduction: {
      assert(P->getType() == II.StartValue->getType() && "Types must match");
      Type *PhiTy = P->getType();
      Value *Broadcasted;
      if (P == OldInduction) {
        // Handle the canonical induction variable. We might have had to
        // extend the type.
        Broadcasted = Builder.CreateTrunc(Induction, PhiTy);
      } else {
        // Handle other induction variables that are now based on the
        // canonical one.
        Value *NormalizedIdx = Builder.CreateSub(Induction, ExtendedIdx,
                                                 "normalized.idx");
        NormalizedIdx = Builder.CreateSExtOrTrunc(NormalizedIdx, PhiTy);
        Broadcasted = Builder.CreateAdd(II.StartValue, NormalizedIdx,
                                        "offset.idx");
      }
      Broadcasted = getBroadcastInstrs(Broadcasted);
      // After broadcasting the induction variable we need to make the vector
      // consecutive by adding 0, 1, 2, etc.
      for (unsigned part = 0; part < UF; ++part)
        Entry[part] = getConsecutiveVector(Broadcasted, VF * part, false);
      return;
    }
    case LoopVectorizationLegality::IK_ReverseIntInduction:
    case LoopVectorizationLegality::IK_PtrInduction:
    case LoopVectorizationLegality::IK_ReversePtrInduction:
      // Handle reverse integer and pointer inductions.
      Value *StartIdx = ExtendedIdx;
      // This is the normalized GEP that starts counting at zero.
      Value *NormalizedIdx = Builder.CreateSub(Induction, StartIdx,
                                               "normalized.idx");

      // Handle the reverse integer induction variable case.
      if (LoopVectorizationLegality::IK_ReverseIntInduction == II.IK) {
        IntegerType *DstTy = cast<IntegerType>(II.StartValue->getType());
        Value *CNI = Builder.CreateSExtOrTrunc(NormalizedIdx, DstTy,
                                               "resize.norm.idx");
        Value *ReverseInd  = Builder.CreateSub(II.StartValue, CNI,
                                               "reverse.idx");

        // This is a new value so do not hoist it out.
        Value *Broadcasted = getBroadcastInstrs(ReverseInd);
        // After broadcasting the induction variable we need to make the
        // vector consecutive by adding  ... -3, -2, -1, 0.
        for (unsigned part = 0; part < UF; ++part)
          Entry[part] = getConsecutiveVector(Broadcasted, -(int)VF * part,
                                             true);
        return;
      }

      // Handle the pointer induction variable case.
      assert(P->getType()->isPointerTy() && "Unexpected type.");

      // Is this a reverse induction ptr or a consecutive induction ptr.
      bool Reverse = (LoopVectorizationLegality::IK_ReversePtrInduction ==
                      II.IK);

      // This is the vector of results. Notice that we don't generate
      // vector geps because scalar geps result in better code.
      for (unsigned part = 0; part < UF; ++part) {
        if (VF == 1) {
          int EltIndex = (part) * (Reverse ? -1 : 1);
          Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
          Value *GlobalIdx;
          if (Reverse)
            GlobalIdx = Builder.CreateSub(Idx, NormalizedIdx, "gep.ridx");
          else
            GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx, "gep.idx");

          Value *SclrGep = Builder.CreateGEP(II.StartValue, GlobalIdx,
                                             "next.gep");
          Entry[part] = SclrGep;
          continue;
        }

        Value *VecVal = UndefValue::get(VectorType::get(P->getType(), VF));
        for (unsigned int i = 0; i < VF; ++i) {
          int EltIndex = (i + part * VF) * (Reverse ? -1 : 1);
          Constant *Idx = ConstantInt::get(Induction->getType(), EltIndex);
          Value *GlobalIdx;
          if (!Reverse)
            GlobalIdx = Builder.CreateAdd(NormalizedIdx, Idx, "gep.idx");
          else
            GlobalIdx = Builder.CreateSub(Idx, NormalizedIdx, "gep.ridx");

          Value *SclrGep = Builder.CreateGEP(II.StartValue, GlobalIdx,
                                             "next.gep");
          VecVal = Builder.CreateInsertElement(VecVal, SclrGep,
                                               Builder.getInt32(i),
                                               "insert.gep");
        }
        Entry[part] = VecVal;
      }
      return;
  }
}

void InnerLoopVectorizer::vectorizeBlockInLoop(BasicBlock *BB, PhiVector *PV) {
  // For each instruction in the old loop.
  for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
    VectorParts &Entry = WidenMap.get(it);
    switch (it->getOpcode()) {
    case Instruction::Br:
      // Nothing to do for PHIs and BR, since we already took care of the
      // loop control flow instructions.
      continue;
    case Instruction::PHI:{
      // Vectorize PHINodes.
      widenPHIInstruction(it, Entry, UF, VF, PV);
      continue;
    }// End of PHI.

    case Instruction::Add:
    case Instruction::FAdd:
    case Instruction::Sub:
    case Instruction::FSub:
    case Instruction::Mul:
    case Instruction::FMul:
    case Instruction::UDiv:
    case Instruction::SDiv:
    case Instruction::FDiv:
    case Instruction::URem:
    case Instruction::SRem:
    case Instruction::FRem:
    case Instruction::Shl:
    case Instruction::LShr:
    case Instruction::AShr:
    case Instruction::And:
    case Instruction::Or:
    case Instruction::Xor: {
      // Just widen binops.
      BinaryOperator *BinOp = dyn_cast<BinaryOperator>(it);
      setDebugLocFromInst(Builder, BinOp);
      VectorParts &A = getVectorValue(it->getOperand(0));
      VectorParts &B = getVectorValue(it->getOperand(1));

      // Use this vector value for all users of the original instruction.
      for (unsigned Part = 0; Part < UF; ++Part) {
        Value *V = Builder.CreateBinOp(BinOp->getOpcode(), A[Part], B[Part]);

        // Update the NSW, NUW and Exact flags. Notice: V can be an Undef.
        BinaryOperator *VecOp = dyn_cast<BinaryOperator>(V);
        if (VecOp && isa<OverflowingBinaryOperator>(BinOp)) {
          VecOp->setHasNoSignedWrap(BinOp->hasNoSignedWrap());
          VecOp->setHasNoUnsignedWrap(BinOp->hasNoUnsignedWrap());
        }
        if (VecOp && isa<PossiblyExactOperator>(VecOp))
          VecOp->setIsExact(BinOp->isExact());

        Entry[Part] = V;
      }
      break;
    }
    case Instruction::Select: {
      // Widen selects.
      // If the selector is loop invariant we can create a select
      // instruction with a scalar condition. Otherwise, use vector-select.
      bool InvariantCond = SE->isLoopInvariant(SE->getSCEV(it->getOperand(0)),
                                               OrigLoop);
      setDebugLocFromInst(Builder, it);

      // The condition can be loop invariant  but still defined inside the
      // loop. This means that we can't just use the original 'cond' value.
      // We have to take the 'vectorized' value and pick the first lane.
      // Instcombine will make this a no-op.
      VectorParts &Cond = getVectorValue(it->getOperand(0));
      VectorParts &Op0  = getVectorValue(it->getOperand(1));
      VectorParts &Op1  = getVectorValue(it->getOperand(2));

      Value *ScalarCond = (VF == 1) ? Cond[0] :
        Builder.CreateExtractElement(Cond[0], Builder.getInt32(0));

      for (unsigned Part = 0; Part < UF; ++Part) {
        Entry[Part] = Builder.CreateSelect(
          InvariantCond ? ScalarCond : Cond[Part],
          Op0[Part],
          Op1[Part]);
      }
      break;
    }

    case Instruction::ICmp:
    case Instruction::FCmp: {
      // Widen compares. Generate vector compares.
      bool FCmp = (it->getOpcode() == Instruction::FCmp);
      CmpInst *Cmp = dyn_cast<CmpInst>(it);
      setDebugLocFromInst(Builder, it);
      VectorParts &A = getVectorValue(it->getOperand(0));
      VectorParts &B = getVectorValue(it->getOperand(1));
      for (unsigned Part = 0; Part < UF; ++Part) {
        Value *C = 0;
        if (FCmp)
          C = Builder.CreateFCmp(Cmp->getPredicate(), A[Part], B[Part]);
        else
          C = Builder.CreateICmp(Cmp->getPredicate(), A[Part], B[Part]);
        Entry[Part] = C;
      }
      break;
    }

    case Instruction::Store:
    case Instruction::Load:
      vectorizeMemoryInstruction(it);
        break;
    case Instruction::ZExt:
    case Instruction::SExt:
    case Instruction::FPToUI:
    case Instruction::FPToSI:
    case Instruction::FPExt:
    case Instruction::PtrToInt:
    case Instruction::IntToPtr:
    case Instruction::SIToFP:
    case Instruction::UIToFP:
    case Instruction::Trunc:
    case Instruction::FPTrunc:
    case Instruction::BitCast: {
      CastInst *CI = dyn_cast<CastInst>(it);
      setDebugLocFromInst(Builder, it);
      /// Optimize the special case where the source is the induction
      /// variable. Notice that we can only optimize the 'trunc' case
      /// because: a. FP conversions lose precision, b. sext/zext may wrap,
      /// c. other casts depend on pointer size.
      if (CI->getOperand(0) == OldInduction &&
          it->getOpcode() == Instruction::Trunc) {
        Value *ScalarCast = Builder.CreateCast(CI->getOpcode(), Induction,
                                               CI->getType());
        Value *Broadcasted = getBroadcastInstrs(ScalarCast);
        for (unsigned Part = 0; Part < UF; ++Part)
          Entry[Part] = getConsecutiveVector(Broadcasted, VF * Part, false);
        break;
      }
      /// Vectorize casts.
      Type *DestTy = (VF == 1) ? CI->getType() :
                                 VectorType::get(CI->getType(), VF);

      VectorParts &A = getVectorValue(it->getOperand(0));
      for (unsigned Part = 0; Part < UF; ++Part)
        Entry[Part] = Builder.CreateCast(CI->getOpcode(), A[Part], DestTy);
      break;
    }

    case Instruction::Call: {
      // Ignore dbg intrinsics.
      if (isa<DbgInfoIntrinsic>(it))
        break;
      setDebugLocFromInst(Builder, it);

      Module *M = BB->getParent()->getParent();
      CallInst *CI = cast<CallInst>(it);
      Intrinsic::ID ID = getIntrinsicIDForCall(CI, TLI);
      assert(ID && "Not an intrinsic call!");
      switch (ID) {
      case Intrinsic::lifetime_end:
      case Intrinsic::lifetime_start:
        scalarizeInstruction(it);
        break;
      default:
        for (unsigned Part = 0; Part < UF; ++Part) {
          SmallVector<Value *, 4> Args;
          for (unsigned i = 0, ie = CI->getNumArgOperands(); i != ie; ++i) {
            VectorParts &Arg = getVectorValue(CI->getArgOperand(i));
            Args.push_back(Arg[Part]);
          }
          Type *Tys[] = {CI->getType()};
          if (VF > 1)
            Tys[0] = VectorType::get(CI->getType()->getScalarType(), VF);

          Function *F = Intrinsic::getDeclaration(M, ID, Tys);
          Entry[Part] = Builder.CreateCall(F, Args);
        }
        break;
      }
      break;
    }

    default:
      // All other instructions are unsupported. Scalarize them.
      scalarizeInstruction(it);
      break;
    }// end of switch.
  }// end of for_each instr.
}

void InnerLoopVectorizer::updateAnalysis() {
  // Forget the original basic block.
  SE->forgetLoop(OrigLoop);

  // Update the dominator tree information.
  assert(DT->properlyDominates(LoopBypassBlocks.front(), LoopExitBlock) &&
         "Entry does not dominate exit.");

  for (unsigned I = 1, E = LoopBypassBlocks.size(); I != E; ++I)
    DT->addNewBlock(LoopBypassBlocks[I], LoopBypassBlocks[I-1]);
  DT->addNewBlock(LoopVectorPreHeader, LoopBypassBlocks.back());

  // Due to if predication of stores we might create a sequence of "if(pred)
  // a[i] = ...;  " blocks.
  for (unsigned i = 0, e = LoopVectorBody.size(); i != e; ++i) {
    if (i == 0)
      DT->addNewBlock(LoopVectorBody[0], LoopVectorPreHeader);
    else if (isPredicatedBlock(i)) {
      DT->addNewBlock(LoopVectorBody[i], LoopVectorBody[i-1]);
    } else {
      DT->addNewBlock(LoopVectorBody[i], LoopVectorBody[i-2]);
    }
  }

  DT->addNewBlock(LoopMiddleBlock, LoopBypassBlocks.front());
  DT->addNewBlock(LoopScalarPreHeader, LoopMiddleBlock);
  DT->changeImmediateDominator(LoopScalarBody, LoopScalarPreHeader);
  DT->changeImmediateDominator(LoopExitBlock, LoopMiddleBlock);

  DEBUG(DT->verifyDomTree());
}

/// \brief Check whether it is safe to if-convert this phi node.
///
/// Phi nodes with constant expressions that can trap are not safe to if
/// convert.
static bool canIfConvertPHINodes(BasicBlock *BB) {
  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
    PHINode *Phi = dyn_cast<PHINode>(I);
    if (!Phi)
      return true;
    for (unsigned p = 0, e = Phi->getNumIncomingValues(); p != e; ++p)
      if (Constant *C = dyn_cast<Constant>(Phi->getIncomingValue(p)))
        if (C->canTrap())
          return false;
  }
  return true;
}

bool LoopVectorizationLegality::canVectorizeWithIfConvert() {
  if (!EnableIfConversion)
    return false;

  assert(TheLoop->getNumBlocks() > 1 && "Single block loops are vectorizable");

  // A list of pointers that we can safely read and write to.
  SmallPtrSet<Value *, 8> SafePointes;

  // Collect safe addresses.
  for (Loop::block_iterator BI = TheLoop->block_begin(),
         BE = TheLoop->block_end(); BI != BE; ++BI) {
    BasicBlock *BB = *BI;

    if (blockNeedsPredication(BB))
      continue;

    for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ++I) {
      if (LoadInst *LI = dyn_cast<LoadInst>(I))
        SafePointes.insert(LI->getPointerOperand());
      else if (StoreInst *SI = dyn_cast<StoreInst>(I))
        SafePointes.insert(SI->getPointerOperand());
    }
  }

  // Collect the blocks that need predication.
  BasicBlock *Header = TheLoop->getHeader();
  for (Loop::block_iterator BI = TheLoop->block_begin(),
         BE = TheLoop->block_end(); BI != BE; ++BI) {
    BasicBlock *BB = *BI;

    // We don't support switch statements inside loops.
    if (!isa<BranchInst>(BB->getTerminator()))
      return false;

    // We must be able to predicate all blocks that need to be predicated.
    if (blockNeedsPredication(BB)) {
      if (!blockCanBePredicated(BB, SafePointes))
        return false;
    } else if (BB != Header && !canIfConvertPHINodes(BB))
      return false;

  }

  // We can if-convert this loop.
  return true;
}

bool LoopVectorizationLegality::canVectorize() {
  // We must have a loop in canonical form. Loops with indirectbr in them cannot
  // be canonicalized.
  if (!TheLoop->getLoopPreheader())
    return false;

  // We can only vectorize innermost loops.
  if (TheLoop->getSubLoopsVector().size())
    return false;

  // We must have a single backedge.
  if (TheLoop->getNumBackEdges() != 1)
    return false;

  // We must have a single exiting block.
  if (!TheLoop->getExitingBlock())
    return false;

  // We need to have a loop header.
  DEBUG(dbgs() << "LV: Found a loop: " <<
        TheLoop->getHeader()->getName() << '\n');

  // Check if we can if-convert non-single-bb loops.
  unsigned NumBlocks = TheLoop->getNumBlocks();
  if (NumBlocks != 1 && !canVectorizeWithIfConvert()) {
    DEBUG(dbgs() << "LV: Can't if-convert the loop.\n");
    return false;
  }

  // ScalarEvolution needs to be able to find the exit count.
  const SCEV *ExitCount = SE->getBackedgeTakenCount(TheLoop);
  if (ExitCount == SE->getCouldNotCompute()) {
    DEBUG(dbgs() << "LV: SCEV could not compute the loop exit count.\n");
    return false;
  }

  // Do not loop-vectorize loops with a tiny trip count.
  BasicBlock *Latch = TheLoop->getLoopLatch();
  unsigned TC = SE->getSmallConstantTripCount(TheLoop, Latch);
  if (TC > 0u && TC < TinyTripCountVectorThreshold) {
    DEBUG(dbgs() << "LV: Found a loop with a very small trip count. " <<
          "This loop is not worth vectorizing.\n");
    return false;
  }

  // Check if we can vectorize the instructions and CFG in this loop.
  if (!canVectorizeInstrs()) {
    DEBUG(dbgs() << "LV: Can't vectorize the instructions or CFG\n");
    return false;
  }

  // Go over each instruction and look at memory deps.
  if (!canVectorizeMemory()) {
    DEBUG(dbgs() << "LV: Can't vectorize due to memory conflicts\n");
    return false;
  }

  // Collect all of the variables that remain uniform after vectorization.
  collectLoopUniforms();

  DEBUG(dbgs() << "LV: We can vectorize this loop" <<
        (PtrRtCheck.Need ? " (with a runtime bound check)" : "")
        <<"!\n");

  // Okay! We can vectorize. At this point we don't have any other mem analysis
  // which may limit our maximum vectorization factor, so just return true with
  // no restrictions.
  return true;
}

static Type *convertPointerToIntegerType(const DataLayout &DL, Type *Ty) {
  if (Ty->isPointerTy())
    return DL.getIntPtrType(Ty);

  // It is possible that char's or short's overflow when we ask for the loop's
  // trip count, work around this by changing the type size.
  if (Ty->getScalarSizeInBits() < 32)
    return Type::getInt32Ty(Ty->getContext());

  return Ty;
}

static Type* getWiderType(const DataLayout &DL, Type *Ty0, Type *Ty1) {
  Ty0 = convertPointerToIntegerType(DL, Ty0);
  Ty1 = convertPointerToIntegerType(DL, Ty1);
  if (Ty0->getScalarSizeInBits() > Ty1->getScalarSizeInBits())
    return Ty0;
  return Ty1;
}

/// \brief Check that the instruction has outside loop users and is not an
/// identified reduction variable.
static bool hasOutsideLoopUser(const Loop *TheLoop, Instruction *Inst,
                               SmallPtrSet<Value *, 4> &Reductions) {
  // Reduction instructions are allowed to have exit users. All other
  // instructions must not have external users.
  if (!Reductions.count(Inst))
    //Check that all of the users of the loop are inside the BB.
    for (Value::use_iterator I = Inst->use_begin(), E = Inst->use_end();
         I != E; ++I) {
      Instruction *U = cast<Instruction>(*I);
      // This user may be a reduction exit value.
      if (!TheLoop->contains(U)) {
        DEBUG(dbgs() << "LV: Found an outside user for : " << *U << '\n');
        return true;
      }
    }
  return false;
}

bool LoopVectorizationLegality::canVectorizeInstrs() {
  BasicBlock *PreHeader = TheLoop->getLoopPreheader();
  BasicBlock *Header = TheLoop->getHeader();

  // Look for the attribute signaling the absence of NaNs.
  Function &F = *Header->getParent();
  if (F.hasFnAttribute("no-nans-fp-math"))
    HasFunNoNaNAttr = F.getAttributes().getAttribute(
      AttributeSet::FunctionIndex,
      "no-nans-fp-math").getValueAsString() == "true";

  // For each block in the loop.
  for (Loop::block_iterator bb = TheLoop->block_begin(),
       be = TheLoop->block_end(); bb != be; ++bb) {

    // Scan the instructions in the block and look for hazards.
    for (BasicBlock::iterator it = (*bb)->begin(), e = (*bb)->end(); it != e;
         ++it) {

      if (PHINode *Phi = dyn_cast<PHINode>(it)) {
        Type *PhiTy = Phi->getType();
        // Check that this PHI type is allowed.
        if (!PhiTy->isIntegerTy() &&
            !PhiTy->isFloatingPointTy() &&
            !PhiTy->isPointerTy()) {
          DEBUG(dbgs() << "LV: Found an non-int non-pointer PHI.\n");
          return false;
        }

        // If this PHINode is not in the header block, then we know that we
        // can convert it to select during if-conversion. No need to check if
        // the PHIs in this block are induction or reduction variables.
        if (*bb != Header) {
          // Check that this instruction has no outside users or is an
          // identified reduction value with an outside user.
          if(!hasOutsideLoopUser(TheLoop, it, AllowedExit))
            continue;
          return false;
        }

        // We only allow if-converted PHIs with more than two incoming values.
        if (Phi->getNumIncomingValues() != 2) {
          DEBUG(dbgs() << "LV: Found an invalid PHI.\n");
          return false;
        }

        // This is the value coming from the preheader.
        Value *StartValue = Phi->getIncomingValueForBlock(PreHeader);
        // Check if this is an induction variable.
        InductionKind IK = isInductionVariable(Phi);

        if (IK_NoInduction != IK) {
          // Get the widest type.
          if (!WidestIndTy)
            WidestIndTy = convertPointerToIntegerType(*DL, PhiTy);
          else
            WidestIndTy = getWiderType(*DL, PhiTy, WidestIndTy);

          // Int inductions are special because we only allow one IV.
          if (IK == IK_IntInduction) {
            // Use the phi node with the widest type as induction. Use the last
            // one if there are multiple (no good reason for doing this other
            // than it is expedient).
            if (!Induction || PhiTy == WidestIndTy)
              Induction = Phi;
          }

          DEBUG(dbgs() << "LV: Found an induction variable.\n");
          Inductions[Phi] = InductionInfo(StartValue, IK);

          // Until we explicitly handle the case of an induction variable with
          // an outside loop user we have to give up vectorizing this loop.
          if (hasOutsideLoopUser(TheLoop, it, AllowedExit))
            return false;

          continue;
        }

        if (AddReductionVar(Phi, RK_IntegerAdd)) {
          DEBUG(dbgs() << "LV: Found an ADD reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_IntegerMult)) {
          DEBUG(dbgs() << "LV: Found a MUL reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_IntegerOr)) {
          DEBUG(dbgs() << "LV: Found an OR reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_IntegerAnd)) {
          DEBUG(dbgs() << "LV: Found an AND reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_IntegerXor)) {
          DEBUG(dbgs() << "LV: Found a XOR reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_IntegerMinMax)) {
          DEBUG(dbgs() << "LV: Found a MINMAX reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_FloatMult)) {
          DEBUG(dbgs() << "LV: Found an FMult reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_FloatAdd)) {
          DEBUG(dbgs() << "LV: Found an FAdd reduction PHI."<< *Phi <<"\n");
          continue;
        }
        if (AddReductionVar(Phi, RK_FloatMinMax)) {
          DEBUG(dbgs() << "LV: Found an float MINMAX reduction PHI."<< *Phi <<
                "\n");
          continue;
        }

        DEBUG(dbgs() << "LV: Found an unidentified PHI."<< *Phi <<"\n");
        return false;
      }// end of PHI handling

      // We still don't handle functions. However, we can ignore dbg intrinsic
      // calls and we do handle certain intrinsic and libm functions.
      CallInst *CI = dyn_cast<CallInst>(it);
      if (CI && !getIntrinsicIDForCall(CI, TLI) && !isa<DbgInfoIntrinsic>(CI)) {
        DEBUG(dbgs() << "LV: Found a call site.\n");
        return false;
      }

      // Check that the instruction return type is vectorizable.
      // Also, we can't vectorize extractelement instructions.
      if ((!VectorType::isValidElementType(it->getType()) &&
           !it->getType()->isVoidTy()) || isa<ExtractElementInst>(it)) {
        DEBUG(dbgs() << "LV: Found unvectorizable type.\n");
        return false;
      }

      // Check that the stored type is vectorizable.
      if (StoreInst *ST = dyn_cast<StoreInst>(it)) {
        Type *T = ST->getValueOperand()->getType();
        if (!VectorType::isValidElementType(T))
          return false;
        if (EnableMemAccessVersioning)
          collectStridedAcccess(ST);
      }

      if (EnableMemAccessVersioning)
        if (LoadInst *LI = dyn_cast<LoadInst>(it))
          collectStridedAcccess(LI);

      // Reduction instructions are allowed to have exit users.
      // All other instructions must not have external users.
      if (hasOutsideLoopUser(TheLoop, it, AllowedExit))
        return false;

    } // next instr.

  }

  if (!Induction) {
    DEBUG(dbgs() << "LV: Did not find one integer induction var.\n");
    if (Inductions.empty())
      return false;
  }

  return true;
}

///\brief Remove GEPs whose indices but the last one are loop invariant and
/// return the induction operand of the gep pointer.
static Value *stripGetElementPtr(Value *Ptr, ScalarEvolution *SE,
                                 const DataLayout *DL, Loop *Lp) {
  GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Ptr);
  if (!GEP)
    return Ptr;

  unsigned InductionOperand = getGEPInductionOperand(DL, GEP);

  // Check that all of the gep indices are uniform except for our induction
  // operand.
  for (unsigned i = 0, e = GEP->getNumOperands(); i != e; ++i)
    if (i != InductionOperand &&
        !SE->isLoopInvariant(SE->getSCEV(GEP->getOperand(i)), Lp))
      return Ptr;
  return GEP->getOperand(InductionOperand);
}

///\brief Look for a cast use of the passed value.
static Value *getUniqueCastUse(Value *Ptr, Loop *Lp, Type *Ty) {
  Value *UniqueCast = 0;
  for (Value::use_iterator UI = Ptr->use_begin(), UE = Ptr->use_end(); UI != UE;
       ++UI) {
    CastInst *CI = dyn_cast<CastInst>(*UI);
    if (CI && CI->getType() == Ty) {
      if (!UniqueCast)
        UniqueCast = CI;
      else
        return 0;
    }
  }
  return UniqueCast;
}

///\brief Get the stride of a pointer access in a loop.
/// Looks for symbolic strides "a[i*stride]". Returns the symbolic stride as a
/// pointer to the Value, or null otherwise.
static Value *getStrideFromPointer(Value *Ptr, ScalarEvolution *SE,
                                   const DataLayout *DL, Loop *Lp) {
  const PointerType *PtrTy = dyn_cast<PointerType>(Ptr->getType());
  if (!PtrTy || PtrTy->isAggregateType())
    return 0;

  // Try to remove a gep instruction to make the pointer (actually index at this
  // point) easier analyzable. If OrigPtr is equal to Ptr we are analzying the
  // pointer, otherwise, we are analyzing the index.
  Value *OrigPtr = Ptr;

  // The size of the pointer access.
  int64_t PtrAccessSize = 1;

  Ptr = stripGetElementPtr(Ptr, SE, DL, Lp);
  const SCEV *V = SE->getSCEV(Ptr);

  if (Ptr != OrigPtr)
    // Strip off casts.
    while (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(V))
      V = C->getOperand();

  const SCEVAddRecExpr *S = dyn_cast<SCEVAddRecExpr>(V);
  if (!S)
    return 0;

  V = S->getStepRecurrence(*SE);
  if (!V)
    return 0;

  // Strip off the size of access multiplication if we are still analyzing the
  // pointer.
  if (OrigPtr == Ptr) {
    DL->getTypeAllocSize(PtrTy->getElementType());
    if (const SCEVMulExpr *M = dyn_cast<SCEVMulExpr>(V)) {
      if (M->getOperand(0)->getSCEVType() != scConstant)
        return 0;

      const APInt &APStepVal =
          cast<SCEVConstant>(M->getOperand(0))->getValue()->getValue();

      // Huge step value - give up.
      if (APStepVal.getBitWidth() > 64)
        return 0;

      int64_t StepVal = APStepVal.getSExtValue();
      if (PtrAccessSize != StepVal)
        return 0;
      V = M->getOperand(1);
    }
  }

  // Strip off casts.
  Type *StripedOffRecurrenceCast = 0;
  if (const SCEVCastExpr *C = dyn_cast<SCEVCastExpr>(V)) {
    StripedOffRecurrenceCast = C->getType();
    V = C->getOperand();
  }

  // Look for the loop invariant symbolic value.
  const SCEVUnknown *U = dyn_cast<SCEVUnknown>(V);
  if (!U)
    return 0;

  Value *Stride = U->getValue();
  if (!Lp->isLoopInvariant(Stride))
    return 0;

  // If we have stripped off the recurrence cast we have to make sure that we
  // return the value that is used in this loop so that we can replace it later.
  if (StripedOffRecurrenceCast)
    Stride = getUniqueCastUse(Stride, Lp, StripedOffRecurrenceCast);

  return Stride;
}

void LoopVectorizationLegality::collectStridedAcccess(Value *MemAccess) {
  Value *Ptr = 0;
  if (LoadInst *LI = dyn_cast<LoadInst>(MemAccess))
    Ptr = LI->getPointerOperand();
  else if (StoreInst *SI = dyn_cast<StoreInst>(MemAccess))
    Ptr = SI->getPointerOperand();
  else
    return;

  Value *Stride = getStrideFromPointer(Ptr, SE, DL, TheLoop);
  if (!Stride)
    return;

  DEBUG(dbgs() << "LV: Found a strided access that we can version");
  DEBUG(dbgs() << "  Ptr: " << *Ptr << " Stride: " << *Stride << "\n");
  Strides[Ptr] = Stride;
  StrideSet.insert(Stride);
}

void LoopVectorizationLegality::collectLoopUniforms() {
  // We now know that the loop is vectorizable!
  // Collect variables that will remain uniform after vectorization.
  std::vector<Value*> Worklist;
  BasicBlock *Latch = TheLoop->getLoopLatch();

  // Start with the conditional branch and walk up the block.
  Worklist.push_back(Latch->getTerminator()->getOperand(0));

  while (Worklist.size()) {
    Instruction *I = dyn_cast<Instruction>(Worklist.back());
    Worklist.pop_back();

    // Look at instructions inside this loop.
    // Stop when reaching PHI nodes.
    // TODO: we need to follow values all over the loop, not only in this block.
    if (!I || !TheLoop->contains(I) || isa<PHINode>(I))
      continue;

    // This is a known uniform.
    Uniforms.insert(I);

    // Insert all operands.
    Worklist.insert(Worklist.end(), I->op_begin(), I->op_end());
  }
}

namespace {
/// \brief Analyses memory accesses in a loop.
///
/// Checks whether run time pointer checks are needed and builds sets for data
/// dependence checking.
class AccessAnalysis {
public:
  /// \brief Read or write access location.
  typedef PointerIntPair<Value *, 1, bool> MemAccessInfo;
  typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;

  /// \brief Set of potential dependent memory accesses.
  typedef EquivalenceClasses<MemAccessInfo> DepCandidates;

  AccessAnalysis(const DataLayout *Dl, DepCandidates &DA) :
    DL(Dl), DepCands(DA), AreAllWritesIdentified(true),
    AreAllReadsIdentified(true), IsRTCheckNeeded(false) {}

  /// \brief Register a load  and whether it is only read from.
  void addLoad(Value *Ptr, bool IsReadOnly) {
    Accesses.insert(MemAccessInfo(Ptr, false));
    if (IsReadOnly)
      ReadOnlyPtr.insert(Ptr);
  }

  /// \brief Register a store.
  void addStore(Value *Ptr) {
    Accesses.insert(MemAccessInfo(Ptr, true));
  }

  /// \brief Check whether we can check the pointers at runtime for
  /// non-intersection.
  bool canCheckPtrAtRT(LoopVectorizationLegality::RuntimePointerCheck &RtCheck,
                       unsigned &NumComparisons, ScalarEvolution *SE,
                       Loop *TheLoop, ValueToValueMap &Strides,
                       bool ShouldCheckStride = false);

  /// \brief Goes over all memory accesses, checks whether a RT check is needed
  /// and builds sets of dependent accesses.
  void buildDependenceSets() {
    // Process read-write pointers first.
    processMemAccesses(false);
    // Next, process read pointers.
    processMemAccesses(true);
  }

  bool isRTCheckNeeded() { return IsRTCheckNeeded; }

  bool isDependencyCheckNeeded() { return !CheckDeps.empty(); }
  void resetDepChecks() { CheckDeps.clear(); }

  MemAccessInfoSet &getDependenciesToCheck() { return CheckDeps; }

private:
  typedef SetVector<MemAccessInfo> PtrAccessSet;
  typedef DenseMap<Value*, MemAccessInfo> UnderlyingObjToAccessMap;

  /// \brief Go over all memory access or only the deferred ones if
  /// \p UseDeferred is true and check whether runtime pointer checks are needed
  /// and build sets of dependency check candidates.
  void processMemAccesses(bool UseDeferred);

  /// Set of all accesses.
  PtrAccessSet Accesses;

  /// Set of access to check after all writes have been processed.
  PtrAccessSet DeferredAccesses;

  /// Map of pointers to last access encountered.
  UnderlyingObjToAccessMap ObjToLastAccess;

  /// Set of accesses that need a further dependence check.
  MemAccessInfoSet CheckDeps;

  /// Set of pointers that are read only.
  SmallPtrSet<Value*, 16> ReadOnlyPtr;

  /// Set of underlying objects already written to.
  SmallPtrSet<Value*, 16> WriteObjects;

  const DataLayout *DL;

  /// Sets of potentially dependent accesses - members of one set share an
  /// underlying pointer. The set "CheckDeps" identfies which sets really need a
  /// dependence check.
  DepCandidates &DepCands;

  bool AreAllWritesIdentified;
  bool AreAllReadsIdentified;
  bool IsRTCheckNeeded;
};

} // end anonymous namespace

/// \brief Check whether a pointer can participate in a runtime bounds check.
static bool hasComputableBounds(ScalarEvolution *SE, ValueToValueMap &Strides,
                                Value *Ptr) {
  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, Strides, Ptr);
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
  if (!AR)
    return false;

  return AR->isAffine();
}

/// \brief Check the stride of the pointer and ensure that it does not wrap in
/// the address space.
static int isStridedPtr(ScalarEvolution *SE, const DataLayout *DL, Value *Ptr,
                        const Loop *Lp, ValueToValueMap &StridesMap);

bool AccessAnalysis::canCheckPtrAtRT(
    LoopVectorizationLegality::RuntimePointerCheck &RtCheck,
    unsigned &NumComparisons, ScalarEvolution *SE, Loop *TheLoop,
    ValueToValueMap &StridesMap, bool ShouldCheckStride) {
  // Find pointers with computable bounds. We are going to use this information
  // to place a runtime bound check.
  unsigned NumReadPtrChecks = 0;
  unsigned NumWritePtrChecks = 0;
  bool CanDoRT = true;

  bool IsDepCheckNeeded = isDependencyCheckNeeded();
  // We assign consecutive id to access from different dependence sets.
  // Accesses within the same set don't need a runtime check.
  unsigned RunningDepId = 1;
  DenseMap<Value *, unsigned> DepSetId;

  for (PtrAccessSet::iterator AI = Accesses.begin(), AE = Accesses.end();
       AI != AE; ++AI) {
    const MemAccessInfo &Access = *AI;
    Value *Ptr = Access.getPointer();
    bool IsWrite = Access.getInt();

    // Just add write checks if we have both.
    if (!IsWrite && Accesses.count(MemAccessInfo(Ptr, true)))
      continue;

    if (IsWrite)
      ++NumWritePtrChecks;
    else
      ++NumReadPtrChecks;

    if (hasComputableBounds(SE, StridesMap, Ptr) &&
        // When we run after a failing dependency check we have to make sure we
        // don't have wrapping pointers.
        (!ShouldCheckStride ||
         isStridedPtr(SE, DL, Ptr, TheLoop, StridesMap) == 1)) {
      // The id of the dependence set.
      unsigned DepId;

      if (IsDepCheckNeeded) {
        Value *Leader = DepCands.getLeaderValue(Access).getPointer();
        unsigned &LeaderId = DepSetId[Leader];
        if (!LeaderId)
          LeaderId = RunningDepId++;
        DepId = LeaderId;
      } else
        // Each access has its own dependence set.
        DepId = RunningDepId++;

      RtCheck.insert(SE, TheLoop, Ptr, IsWrite, DepId, StridesMap);

      DEBUG(dbgs() << "LV: Found a runtime check ptr:" << *Ptr << '\n');
    } else {
      CanDoRT = false;
    }
  }

  if (IsDepCheckNeeded && CanDoRT && RunningDepId == 2)
    NumComparisons = 0; // Only one dependence set.
  else {
    NumComparisons = (NumWritePtrChecks * (NumReadPtrChecks +
                                           NumWritePtrChecks - 1));
  }

  // If the pointers that we would use for the bounds comparison have different
  // address spaces, assume the values aren't directly comparable, so we can't
  // use them for the runtime check. We also have to assume they could
  // overlap. In the future there should be metadata for whether address spaces
  // are disjoint.
  unsigned NumPointers = RtCheck.Pointers.size();
  for (unsigned i = 0; i < NumPointers; ++i) {
    for (unsigned j = i + 1; j < NumPointers; ++j) {
      // Only need to check pointers between two different dependency sets.
      if (RtCheck.DependencySetId[i] == RtCheck.DependencySetId[j])
       continue;

      Value *PtrI = RtCheck.Pointers[i];
      Value *PtrJ = RtCheck.Pointers[j];

      unsigned ASi = PtrI->getType()->getPointerAddressSpace();
      unsigned ASj = PtrJ->getType()->getPointerAddressSpace();
      if (ASi != ASj) {
        DEBUG(dbgs() << "LV: Runtime check would require comparison between"
                       " different address spaces\n");
        return false;
      }
    }
  }

  return CanDoRT;
}

static bool isFunctionScopeIdentifiedObject(Value *Ptr) {
  return isNoAliasArgument(Ptr) || isNoAliasCall(Ptr) || isa<AllocaInst>(Ptr);
}

void AccessAnalysis::processMemAccesses(bool UseDeferred) {
  // We process the set twice: first we process read-write pointers, last we
  // process read-only pointers. This allows us to skip dependence tests for
  // read-only pointers.

  PtrAccessSet &S = UseDeferred ? DeferredAccesses : Accesses;
  for (PtrAccessSet::iterator AI = S.begin(), AE = S.end(); AI != AE; ++AI) {
    const MemAccessInfo &Access = *AI;
    Value *Ptr = Access.getPointer();
    bool IsWrite = Access.getInt();

    DepCands.insert(Access);

    // Memorize read-only pointers for later processing and skip them in the
    // first round (they need to be checked after we have seen all write
    // pointers). Note: we also mark pointer that are not consecutive as
    // "read-only" pointers (so that we check "a[b[i]] +="). Hence, we need the
    // second check for "!IsWrite".
    bool IsReadOnlyPtr = ReadOnlyPtr.count(Ptr) && !IsWrite;
    if (!UseDeferred && IsReadOnlyPtr) {
      DeferredAccesses.insert(Access);
      continue;
    }

    bool NeedDepCheck = false;
    // Check whether there is the possibility of dependency because of
    // underlying objects being the same.
    typedef SmallVector<Value*, 16> ValueVector;
    ValueVector TempObjects;
    GetUnderlyingObjects(Ptr, TempObjects, DL);
    for (ValueVector::iterator UI = TempObjects.begin(), UE = TempObjects.end();
         UI != UE; ++UI) {
      Value *UnderlyingObj = *UI;

      // If this is a write then it needs to be an identified object.  If this a
      // read and all writes (so far) are identified function scope objects we
      // don't need an identified underlying object but only an Argument (the
      // next write is going to invalidate this assumption if it is
      // unidentified).
      // This is a micro-optimization for the case where all writes are
      // identified and we have one argument pointer.
      // Otherwise, we do need a runtime check.
      if ((IsWrite && !isFunctionScopeIdentifiedObject(UnderlyingObj)) ||
          (!IsWrite && (!AreAllWritesIdentified ||
                        !isa<Argument>(UnderlyingObj)) &&
           !isIdentifiedObject(UnderlyingObj))) {
        DEBUG(dbgs() << "LV: Found an unidentified " <<
              (IsWrite ?  "write" : "read" ) << " ptr: " << *UnderlyingObj <<
              "\n");
        IsRTCheckNeeded = (IsRTCheckNeeded ||
                           !isIdentifiedObject(UnderlyingObj) ||
                           !AreAllReadsIdentified);

        if (IsWrite)
          AreAllWritesIdentified = false;
        if (!IsWrite)
          AreAllReadsIdentified = false;
      }

      // If this is a write - check other reads and writes for conflicts.  If
      // this is a read only check other writes for conflicts (but only if there
      // is no other write to the ptr - this is an optimization to catch "a[i] =
      // a[i] + " without having to do a dependence check).
      if ((IsWrite || IsReadOnlyPtr) && WriteObjects.count(UnderlyingObj))
        NeedDepCheck = true;

      if (IsWrite)
        WriteObjects.insert(UnderlyingObj);

      // Create sets of pointers connected by shared underlying objects.
      UnderlyingObjToAccessMap::iterator Prev =
        ObjToLastAccess.find(UnderlyingObj);
      if (Prev != ObjToLastAccess.end())
        DepCands.unionSets(Access, Prev->second);

      ObjToLastAccess[UnderlyingObj] = Access;
    }

    if (NeedDepCheck)
      CheckDeps.insert(Access);
  }
}

namespace {
/// \brief Checks memory dependences among accesses to the same underlying
/// object to determine whether there vectorization is legal or not (and at
/// which vectorization factor).
///
/// This class works under the assumption that we already checked that memory
/// locations with different underlying pointers are "must-not alias".
/// We use the ScalarEvolution framework to symbolically evalutate access
/// functions pairs. Since we currently don't restructure the loop we can rely
/// on the program order of memory accesses to determine their safety.
/// At the moment we will only deem accesses as safe for:
///  * A negative constant distance assuming program order.
///
///      Safe: tmp = a[i + 1];     OR     a[i + 1] = x;
///            a[i] = tmp;                y = a[i];
///
///   The latter case is safe because later checks guarantuee that there can't
///   be a cycle through a phi node (that is, we check that "x" and "y" is not
///   the same variable: a header phi can only be an induction or a reduction, a
///   reduction can't have a memory sink, an induction can't have a memory
///   source). This is important and must not be violated (or we have to
///   resort to checking for cycles through memory).
///
///  * A positive constant distance assuming program order that is bigger
///    than the biggest memory access.
///
///     tmp = a[i]        OR              b[i] = x
///     a[i+2] = tmp                      y = b[i+2];
///
///     Safe distance: 2 x sizeof(a[0]), and 2 x sizeof(b[0]), respectively.
///
///  * Zero distances and all accesses have the same size.
///
class MemoryDepChecker {
public:
  typedef PointerIntPair<Value *, 1, bool> MemAccessInfo;
  typedef SmallPtrSet<MemAccessInfo, 8> MemAccessInfoSet;

  MemoryDepChecker(ScalarEvolution *Se, const DataLayout *Dl, const Loop *L)
      : SE(Se), DL(Dl), InnermostLoop(L), AccessIdx(0),
        ShouldRetryWithRuntimeCheck(false) {}

  /// \brief Register the location (instructions are given increasing numbers)
  /// of a write access.
  void addAccess(StoreInst *SI) {
    Value *Ptr = SI->getPointerOperand();
    Accesses[MemAccessInfo(Ptr, true)].push_back(AccessIdx);
    InstMap.push_back(SI);
    ++AccessIdx;
  }

  /// \brief Register the location (instructions are given increasing numbers)
  /// of a write access.
  void addAccess(LoadInst *LI) {
    Value *Ptr = LI->getPointerOperand();
    Accesses[MemAccessInfo(Ptr, false)].push_back(AccessIdx);
    InstMap.push_back(LI);
    ++AccessIdx;
  }

  /// \brief Check whether the dependencies between the accesses are safe.
  ///
  /// Only checks sets with elements in \p CheckDeps.
  bool areDepsSafe(AccessAnalysis::DepCandidates &AccessSets,
                   MemAccessInfoSet &CheckDeps, ValueToValueMap &Strides);

  /// \brief The maximum number of bytes of a vector register we can vectorize
  /// the accesses safely with.
  unsigned getMaxSafeDepDistBytes() { return MaxSafeDepDistBytes; }

  /// \brief In same cases when the dependency check fails we can still
  /// vectorize the loop with a dynamic array access check.
  bool shouldRetryWithRuntimeCheck() { return ShouldRetryWithRuntimeCheck; }

private:
  ScalarEvolution *SE;
  const DataLayout *DL;
  const Loop *InnermostLoop;

  /// \brief Maps access locations (ptr, read/write) to program order.
  DenseMap<MemAccessInfo, std::vector<unsigned> > Accesses;

  /// \brief Memory access instructions in program order.
  SmallVector<Instruction *, 16> InstMap;

  /// \brief The program order index to be used for the next instruction.
  unsigned AccessIdx;

  // We can access this many bytes in parallel safely.
  unsigned MaxSafeDepDistBytes;

  /// \brief If we see a non-constant dependence distance we can still try to
  /// vectorize this loop with runtime checks.
  bool ShouldRetryWithRuntimeCheck;

  /// \brief Check whether there is a plausible dependence between the two
  /// accesses.
  ///
  /// Access \p A must happen before \p B in program order. The two indices
  /// identify the index into the program order map.
  ///
  /// This function checks  whether there is a plausible dependence (or the
  /// absence of such can't be proved) between the two accesses. If there is a
  /// plausible dependence but the dependence distance is bigger than one
  /// element access it records this distance in \p MaxSafeDepDistBytes (if this
  /// distance is smaller than any other distance encountered so far).
  /// Otherwise, this function returns true signaling a possible dependence.
  bool isDependent(const MemAccessInfo &A, unsigned AIdx,
                   const MemAccessInfo &B, unsigned BIdx,
                   ValueToValueMap &Strides);

  /// \brief Check whether the data dependence could prevent store-load
  /// forwarding.
  bool couldPreventStoreLoadForward(unsigned Distance, unsigned TypeByteSize);
};

} // end anonymous namespace

static bool isInBoundsGep(Value *Ptr) {
  if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(Ptr))
    return GEP->isInBounds();
  return false;
}

/// \brief Check whether the access through \p Ptr has a constant stride.
static int isStridedPtr(ScalarEvolution *SE, const DataLayout *DL, Value *Ptr,
                        const Loop *Lp, ValueToValueMap &StridesMap) {
  const Type *Ty = Ptr->getType();
  assert(Ty->isPointerTy() && "Unexpected non-ptr");

  // Make sure that the pointer does not point to aggregate types.
  const PointerType *PtrTy = cast<PointerType>(Ty);
  if (PtrTy->getElementType()->isAggregateType()) {
    DEBUG(dbgs() << "LV: Bad stride - Not a pointer to a scalar type" << *Ptr <<
          "\n");
    return 0;
  }

  const SCEV *PtrScev = replaceSymbolicStrideSCEV(SE, StridesMap, Ptr);

  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PtrScev);
  if (!AR) {
    DEBUG(dbgs() << "LV: Bad stride - Not an AddRecExpr pointer "
          << *Ptr << " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  // The accesss function must stride over the innermost loop.
  if (Lp != AR->getLoop()) {
    DEBUG(dbgs() << "LV: Bad stride - Not striding over innermost loop " <<
          *Ptr << " SCEV: " << *PtrScev << "\n");
  }

  // The address calculation must not wrap. Otherwise, a dependence could be
  // inverted.
  // An inbounds getelementptr that is a AddRec with a unit stride
  // cannot wrap per definition. The unit stride requirement is checked later.
  // An getelementptr without an inbounds attribute and unit stride would have
  // to access the pointer value "0" which is undefined behavior in address
  // space 0, therefore we can also vectorize this case.
  bool IsInBoundsGEP = isInBoundsGep(Ptr);
  bool IsNoWrapAddRec = AR->getNoWrapFlags(SCEV::NoWrapMask);
  bool IsInAddressSpaceZero = PtrTy->getAddressSpace() == 0;
  if (!IsNoWrapAddRec && !IsInBoundsGEP && !IsInAddressSpaceZero) {
    DEBUG(dbgs() << "LV: Bad stride - Pointer may wrap in the address space "
          << *Ptr << " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  // Check the step is constant.
  const SCEV *Step = AR->getStepRecurrence(*SE);

  // Calculate the pointer stride and check if it is consecutive.
  const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
  if (!C) {
    DEBUG(dbgs() << "LV: Bad stride - Not a constant strided " << *Ptr <<
          " SCEV: " << *PtrScev << "\n");
    return 0;
  }

  int64_t Size = DL->getTypeAllocSize(PtrTy->getElementType());
  const APInt &APStepVal = C->getValue()->getValue();

  // Huge step value - give up.
  if (APStepVal.getBitWidth() > 64)
    return 0;

  int64_t StepVal = APStepVal.getSExtValue();

  // Strided access.
  int64_t Stride = StepVal / Size;
  int64_t Rem = StepVal % Size;
  if (Rem)
    return 0;

  // If the SCEV could wrap but we have an inbounds gep with a unit stride we
  // know we can't "wrap around the address space". In case of address space
  // zero we know that this won't happen without triggering undefined behavior.
  if (!IsNoWrapAddRec && (IsInBoundsGEP || IsInAddressSpaceZero) &&
      Stride != 1 && Stride != -1)
    return 0;

  return Stride;
}

bool MemoryDepChecker::couldPreventStoreLoadForward(unsigned Distance,
                                                    unsigned TypeByteSize) {
  // If loads occur at a distance that is not a multiple of a feasible vector
  // factor store-load forwarding does not take place.
  // Positive dependences might cause troubles because vectorizing them might
  // prevent store-load forwarding making vectorized code run a lot slower.
  //   a[i] = a[i-3] ^ a[i-8];
  //   The stores to a[i:i+1] don't align with the stores to a[i-3:i-2] and
  //   hence on your typical architecture store-load forwarding does not take
  //   place. Vectorizing in such cases does not make sense.
  // Store-load forwarding distance.
  const unsigned NumCyclesForStoreLoadThroughMemory = 8*TypeByteSize;
  // Maximum vector factor.
  unsigned MaxVFWithoutSLForwardIssues = MaxVectorWidth*TypeByteSize;
  if(MaxSafeDepDistBytes < MaxVFWithoutSLForwardIssues)
    MaxVFWithoutSLForwardIssues = MaxSafeDepDistBytes;

  for (unsigned vf = 2*TypeByteSize; vf <= MaxVFWithoutSLForwardIssues;
       vf *= 2) {
    if (Distance % vf && Distance / vf < NumCyclesForStoreLoadThroughMemory) {
      MaxVFWithoutSLForwardIssues = (vf >>=1);
      break;
    }
  }

  if (MaxVFWithoutSLForwardIssues< 2*TypeByteSize) {
    DEBUG(dbgs() << "LV: Distance " << Distance <<
          " that could cause a store-load forwarding conflict\n");
    return true;
  }

  if (MaxVFWithoutSLForwardIssues < MaxSafeDepDistBytes &&
      MaxVFWithoutSLForwardIssues != MaxVectorWidth*TypeByteSize)
    MaxSafeDepDistBytes = MaxVFWithoutSLForwardIssues;
  return false;
}

bool MemoryDepChecker::isDependent(const MemAccessInfo &A, unsigned AIdx,
                                   const MemAccessInfo &B, unsigned BIdx,
                                   ValueToValueMap &Strides) {
  assert (AIdx < BIdx && "Must pass arguments in program order");

  Value *APtr = A.getPointer();
  Value *BPtr = B.getPointer();
  bool AIsWrite = A.getInt();
  bool BIsWrite = B.getInt();

  // Two reads are independent.
  if (!AIsWrite && !BIsWrite)
    return false;

  const SCEV *AScev = replaceSymbolicStrideSCEV(SE, Strides, APtr);
  const SCEV *BScev = replaceSymbolicStrideSCEV(SE, Strides, BPtr);

  int StrideAPtr = isStridedPtr(SE, DL, APtr, InnermostLoop, Strides);
  int StrideBPtr = isStridedPtr(SE, DL, BPtr, InnermostLoop, Strides);

  const SCEV *Src = AScev;
  const SCEV *Sink = BScev;

  // If the induction step is negative we have to invert source and sink of the
  // dependence.
  if (StrideAPtr < 0) {
    //Src = BScev;
    //Sink = AScev;
    std::swap(APtr, BPtr);
    std::swap(Src, Sink);
    std::swap(AIsWrite, BIsWrite);
    std::swap(AIdx, BIdx);
    std::swap(StrideAPtr, StrideBPtr);
  }

  const SCEV *Dist = SE->getMinusSCEV(Sink, Src);

  DEBUG(dbgs() << "LV: Src Scev: " << *Src << "Sink Scev: " << *Sink
        << "(Induction step: " << StrideAPtr <<  ")\n");
  DEBUG(dbgs() << "LV: Distance for " << *InstMap[AIdx] << " to "
        << *InstMap[BIdx] << ": " << *Dist << "\n");

  // Need consecutive accesses. We don't want to vectorize
  // "A[B[i]] += ..." and similar code or pointer arithmetic that could wrap in
  // the address space.
  if (!StrideAPtr || !StrideBPtr || StrideAPtr != StrideBPtr){
    DEBUG(dbgs() << "Non-consecutive pointer access\n");
    return true;
  }

  const SCEVConstant *C = dyn_cast<SCEVConstant>(Dist);
  if (!C) {
    DEBUG(dbgs() << "LV: Dependence because of non-constant distance\n");
    ShouldRetryWithRuntimeCheck = true;
    return true;
  }

  Type *ATy = APtr->getType()->getPointerElementType();
  Type *BTy = BPtr->getType()->getPointerElementType();
  unsigned TypeByteSize = DL->getTypeAllocSize(ATy);

  // Negative distances are not plausible dependencies.
  const APInt &Val = C->getValue()->getValue();
  if (Val.isNegative()) {
    bool IsTrueDataDependence = (AIsWrite && !BIsWrite);
    if (IsTrueDataDependence &&
        (couldPreventStoreLoadForward(Val.abs().getZExtValue(), TypeByteSize) ||
         ATy != BTy))
      return true;

    DEBUG(dbgs() << "LV: Dependence is negative: NoDep\n");
    return false;
  }

  // Write to the same location with the same size.
  // Could be improved to assert type sizes are the same (i32 == float, etc).
  if (Val == 0) {
    if (ATy == BTy)
      return false;
    DEBUG(dbgs() << "LV: Zero dependence difference but different types\n");
    return true;
  }

  assert(Val.isStrictlyPositive() && "Expect a positive value");

  // Positive distance bigger than max vectorization factor.
  if (ATy != BTy) {
    DEBUG(dbgs() <<
          "LV: ReadWrite-Write positive dependency with different types\n");
    return false;
  }

  unsigned Distance = (unsigned) Val.getZExtValue();

  // Bail out early if passed-in parameters make vectorization not feasible.
  unsigned ForcedFactor = VectorizationFactor ? VectorizationFactor : 1;
  unsigned ForcedUnroll = VectorizationUnroll ? VectorizationUnroll : 1;

  // The distance must be bigger than the size needed for a vectorized version
  // of the operation and the size of the vectorized operation must not be
  // bigger than the currrent maximum size.
  if (Distance < 2*TypeByteSize ||
      2*TypeByteSize > MaxSafeDepDistBytes ||
      Distance < TypeByteSize * ForcedUnroll * ForcedFactor) {
    DEBUG(dbgs() << "LV: Failure because of Positive distance "
        << Val.getSExtValue() << '\n');
    return true;
  }

  MaxSafeDepDistBytes = Distance < MaxSafeDepDistBytes ?
    Distance : MaxSafeDepDistBytes;

  bool IsTrueDataDependence = (!AIsWrite && BIsWrite);
  if (IsTrueDataDependence &&
      couldPreventStoreLoadForward(Distance, TypeByteSize))
     return true;

  DEBUG(dbgs() << "LV: Positive distance " << Val.getSExtValue() <<
        " with max VF = " << MaxSafeDepDistBytes / TypeByteSize << '\n');

  return false;
}

bool MemoryDepChecker::areDepsSafe(AccessAnalysis::DepCandidates &AccessSets,
                                   MemAccessInfoSet &CheckDeps,
                                   ValueToValueMap &Strides) {

  MaxSafeDepDistBytes = -1U;
  while (!CheckDeps.empty()) {
    MemAccessInfo CurAccess = *CheckDeps.begin();

    // Get the relevant memory access set.
    EquivalenceClasses<MemAccessInfo>::iterator I =
      AccessSets.findValue(AccessSets.getLeaderValue(CurAccess));

    // Check accesses within this set.
    EquivalenceClasses<MemAccessInfo>::member_iterator AI, AE;
    AI = AccessSets.member_begin(I), AE = AccessSets.member_end();

    // Check every access pair.
    while (AI != AE) {
      CheckDeps.erase(*AI);
      EquivalenceClasses<MemAccessInfo>::member_iterator OI = llvm::next(AI);
      while (OI != AE) {
        // Check every accessing instruction pair in program order.
        for (std::vector<unsigned>::iterator I1 = Accesses[*AI].begin(),
             I1E = Accesses[*AI].end(); I1 != I1E; ++I1)
          for (std::vector<unsigned>::iterator I2 = Accesses[*OI].begin(),
               I2E = Accesses[*OI].end(); I2 != I2E; ++I2) {
            if (*I1 < *I2 && isDependent(*AI, *I1, *OI, *I2, Strides))
              return false;
            if (*I2 < *I1 && isDependent(*OI, *I2, *AI, *I1, Strides))
              return false;
          }
        ++OI;
      }
      AI++;
    }
  }
  return true;
}

bool LoopVectorizationLegality::canVectorizeMemory() {

  typedef SmallVector<Value*, 16> ValueVector;
  typedef SmallPtrSet<Value*, 16> ValueSet;

  // Holds the Load and Store *instructions*.
  ValueVector Loads;
  ValueVector Stores;

  // Holds all the different accesses in the loop.
  unsigned NumReads = 0;
  unsigned NumReadWrites = 0;

  PtrRtCheck.Pointers.clear();
  PtrRtCheck.Need = false;

  const bool IsAnnotatedParallel = TheLoop->isAnnotatedParallel();
  MemoryDepChecker DepChecker(SE, DL, TheLoop);

  // For each block.
  for (Loop::block_iterator bb = TheLoop->block_begin(),
       be = TheLoop->block_end(); bb != be; ++bb) {

    // Scan the BB and collect legal loads and stores.
    for (BasicBlock::iterator it = (*bb)->begin(), e = (*bb)->end(); it != e;
         ++it) {

      // If this is a load, save it. If this instruction can read from memory
      // but is not a load, then we quit. Notice that we don't handle function
      // calls that read or write.
      if (it->mayReadFromMemory()) {
        // Many math library functions read the rounding mode. We will only
        // vectorize a loop if it contains known function calls that don't set
        // the flag. Therefore, it is safe to ignore this read from memory.
        CallInst *Call = dyn_cast<CallInst>(it);
        if (Call && getIntrinsicIDForCall(Call, TLI))
          continue;

        LoadInst *Ld = dyn_cast<LoadInst>(it);
        if (!Ld) return false;
        if (!Ld->isSimple() && !IsAnnotatedParallel) {
          DEBUG(dbgs() << "LV: Found a non-simple load.\n");
          return false;
        }
        NumLoads++;
        Loads.push_back(Ld);
        DepChecker.addAccess(Ld);
        continue;
      }

      // Save 'store' instructions. Abort if other instructions write to memory.
      if (it->mayWriteToMemory()) {
        StoreInst *St = dyn_cast<StoreInst>(it);
        if (!St) return false;
        if (!St->isSimple() && !IsAnnotatedParallel) {
          DEBUG(dbgs() << "LV: Found a non-simple store.\n");
          return false;
        }
        NumStores++;
        Stores.push_back(St);
        DepChecker.addAccess(St);
      }
    } // Next instr.
  } // Next block.

  // Now we have two lists that hold the loads and the stores.
  // Next, we find the pointers that they use.

  // Check if we see any stores. If there are no stores, then we don't
  // care if the pointers are *restrict*.
  if (!Stores.size()) {
    DEBUG(dbgs() << "LV: Found a read-only loop!\n");
    return true;
  }

  AccessAnalysis::DepCandidates DependentAccesses;
  AccessAnalysis Accesses(DL, DependentAccesses);

  // Holds the analyzed pointers. We don't want to call GetUnderlyingObjects
  // multiple times on the same object. If the ptr is accessed twice, once
  // for read and once for write, it will only appear once (on the write
  // list). This is okay, since we are going to check for conflicts between
  // writes and between reads and writes, but not between reads and reads.
  ValueSet Seen;

  ValueVector::iterator I, IE;
  for (I = Stores.begin(), IE = Stores.end(); I != IE; ++I) {
    StoreInst *ST = cast<StoreInst>(*I);
    Value* Ptr = ST->getPointerOperand();

    if (isUniform(Ptr)) {
      DEBUG(dbgs() << "LV: We don't allow storing to uniform addresses\n");
      return false;
    }

    // If we did *not* see this pointer before, insert it to  the read-write
    // list. At this phase it is only a 'write' list.
    if (Seen.insert(Ptr)) {
      ++NumReadWrites;
      Accesses.addStore(Ptr);
    }
  }

  if (IsAnnotatedParallel) {
    DEBUG(dbgs()
          << "LV: A loop annotated parallel, ignore memory dependency "
          << "checks.\n");
    return true;
  }

  for (I = Loads.begin(), IE = Loads.end(); I != IE; ++I) {
    LoadInst *LD = cast<LoadInst>(*I);
    Value* Ptr = LD->getPointerOperand();
    // If we did *not* see this pointer before, insert it to the
    // read list. If we *did* see it before, then it is already in
    // the read-write list. This allows us to vectorize expressions
    // such as A[i] += x;  Because the address of A[i] is a read-write
    // pointer. This only works if the index of A[i] is consecutive.
    // If the address of i is unknown (for example A[B[i]]) then we may
    // read a few words, modify, and write a few words, and some of the
    // words may be written to the same address.
    bool IsReadOnlyPtr = false;
    if (Seen.insert(Ptr) || !isStridedPtr(SE, DL, Ptr, TheLoop, Strides)) {
      ++NumReads;
      IsReadOnlyPtr = true;
    }
    Accesses.addLoad(Ptr, IsReadOnlyPtr);
  }

  // If we write (or read-write) to a single destination and there are no
  // other reads in this loop then is it safe to vectorize.
  if (NumReadWrites == 1 && NumReads == 0) {
    DEBUG(dbgs() << "LV: Found a write-only loop!\n");
    return true;
  }

  // Build dependence sets and check whether we need a runtime pointer bounds
  // check.
  Accesses.buildDependenceSets();
  bool NeedRTCheck = Accesses.isRTCheckNeeded();

  // Find pointers with computable bounds. We are going to use this information
  // to place a runtime bound check.
  unsigned NumComparisons = 0;
  bool CanDoRT = false;
  if (NeedRTCheck)
    CanDoRT = Accesses.canCheckPtrAtRT(PtrRtCheck, NumComparisons, SE, TheLoop,
                                       Strides);

  DEBUG(dbgs() << "LV: We need to do " << NumComparisons <<
        " pointer comparisons.\n");

  // If we only have one set of dependences to check pointers among we don't
  // need a runtime check.
  if (NumComparisons == 0 && NeedRTCheck)
    NeedRTCheck = false;

  // Check that we did not collect too many pointers or found an unsizeable
  // pointer.
  if (!CanDoRT || NumComparisons > RuntimeMemoryCheckThreshold) {
    PtrRtCheck.reset();
    CanDoRT = false;
  }

  if (CanDoRT) {
    DEBUG(dbgs() << "LV: We can perform a memory runtime check if needed.\n");
  }

  if (NeedRTCheck && !CanDoRT) {
    DEBUG(dbgs() << "LV: We can't vectorize because we can't find " <<
          "the array bounds.\n");
    PtrRtCheck.reset();
    return false;
  }

  PtrRtCheck.Need = NeedRTCheck;

  bool CanVecMem = true;
  if (Accesses.isDependencyCheckNeeded()) {
    DEBUG(dbgs() << "LV: Checking memory dependencies\n");
    CanVecMem = DepChecker.areDepsSafe(
        DependentAccesses, Accesses.getDependenciesToCheck(), Strides);
    MaxSafeDepDistBytes = DepChecker.getMaxSafeDepDistBytes();

    if (!CanVecMem && DepChecker.shouldRetryWithRuntimeCheck()) {
      DEBUG(dbgs() << "LV: Retrying with memory checks\n");
      NeedRTCheck = true;

      // Clear the dependency checks. We assume they are not needed.
      Accesses.resetDepChecks();

      PtrRtCheck.reset();
      PtrRtCheck.Need = true;

      CanDoRT = Accesses.canCheckPtrAtRT(PtrRtCheck, NumComparisons, SE,
                                         TheLoop, Strides, true);
      // Check that we did not collect too many pointers or found an unsizeable
      // pointer.
      if (!CanDoRT || NumComparisons > RuntimeMemoryCheckThreshold) {
        DEBUG(dbgs() << "LV: Can't vectorize with memory checks\n");
        PtrRtCheck.reset();
        return false;
      }

      CanVecMem = true;
    }
  }

  DEBUG(dbgs() << "LV: We" << (NeedRTCheck ? "" : " don't") <<
        " need a runtime memory check.\n");

  return CanVecMem;
}

static bool hasMultipleUsesOf(Instruction *I,
                              SmallPtrSet<Instruction *, 8> &Insts) {
  unsigned NumUses = 0;
  for(User::op_iterator Use = I->op_begin(), E = I->op_end(); Use != E; ++Use) {
    if (Insts.count(dyn_cast<Instruction>(*Use)))
      ++NumUses;
    if (NumUses > 1)
      return true;
  }

  return false;
}

static bool areAllUsesIn(Instruction *I, SmallPtrSet<Instruction *, 8> &Set) {
  for(User::op_iterator Use = I->op_begin(), E = I->op_end(); Use != E; ++Use)
    if (!Set.count(dyn_cast<Instruction>(*Use)))
      return false;
  return true;
}

bool LoopVectorizationLegality::AddReductionVar(PHINode *Phi,
                                                ReductionKind Kind) {
  if (Phi->getNumIncomingValues() != 2)
    return false;

  // Reduction variables are only found in the loop header block.
  if (Phi->getParent() != TheLoop->getHeader())
    return false;

  // Obtain the reduction start value from the value that comes from the loop
  // preheader.
  Value *RdxStart = Phi->getIncomingValueForBlock(TheLoop->getLoopPreheader());

  // ExitInstruction is the single value which is used outside the loop.
  // We only allow for a single reduction value to be used outside the loop.
  // This includes users of the reduction, variables (which form a cycle
  // which ends in the phi node).
  Instruction *ExitInstruction = 0;
  // Indicates that we found a reduction operation in our scan.
  bool FoundReduxOp = false;

  // We start with the PHI node and scan for all of the users of this
  // instruction. All users must be instructions that can be used as reduction
  // variables (such as ADD). We must have a single out-of-block user. The cycle
  // must include the original PHI.
  bool FoundStartPHI = false;

  // To recognize min/max patterns formed by a icmp select sequence, we store
  // the number of instruction we saw from the recognized min/max pattern,
  //  to make sure we only see exactly the two instructions.
  unsigned NumCmpSelectPatternInst = 0;
  ReductionInstDesc ReduxDesc(false, 0);

  SmallPtrSet<Instruction *, 8> VisitedInsts;
  SmallVector<Instruction *, 8> Worklist;
  Worklist.push_back(Phi);
  VisitedInsts.insert(Phi);

  // A value in the reduction can be used:
  //  - By the reduction:
  //      - Reduction operation:
  //        - One use of reduction value (safe).
  //        - Multiple use of reduction value (not safe).
  //      - PHI:
  //        - All uses of the PHI must be the reduction (safe).
  //        - Otherwise, not safe.
  //  - By one instruction outside of the loop (safe).
  //  - By further instructions outside of the loop (not safe).
  //  - By an instruction that is not part of the reduction (not safe).
  //    This is either:
  //      * An instruction type other than PHI or the reduction operation.
  //      * A PHI in the header other than the initial PHI.
  while (!Worklist.empty()) {
    Instruction *Cur = Worklist.back();
    Worklist.pop_back();

    // No Users.
    // If the instruction has no users then this is a broken chain and can't be
    // a reduction variable.
    if (Cur->use_empty())
      return false;

    bool IsAPhi = isa<PHINode>(Cur);

    // A header PHI use other than the original PHI.
    if (Cur != Phi && IsAPhi && Cur->getParent() == Phi->getParent())
      return false;

    // Reductions of instructions such as Div, and Sub is only possible if the
    // LHS is the reduction variable.
    if (!Cur->isCommutative() && !IsAPhi && !isa<SelectInst>(Cur) &&
        !isa<ICmpInst>(Cur) && !isa<FCmpInst>(Cur) &&
        !VisitedInsts.count(dyn_cast<Instruction>(Cur->getOperand(0))))
      return false;

    // Any reduction instruction must be of one of the allowed kinds.
    ReduxDesc = isReductionInstr(Cur, Kind, ReduxDesc);
    if (!ReduxDesc.IsReduction)
      return false;

    // A reduction operation must only have one use of the reduction value.
    if (!IsAPhi && Kind != RK_IntegerMinMax && Kind != RK_FloatMinMax &&
        hasMultipleUsesOf(Cur, VisitedInsts))
      return false;

    // All inputs to a PHI node must be a reduction value.
    if(IsAPhi && Cur != Phi && !areAllUsesIn(Cur, VisitedInsts))
      return false;

    if (Kind == RK_IntegerMinMax && (isa<ICmpInst>(Cur) ||
                                     isa<SelectInst>(Cur)))
      ++NumCmpSelectPatternInst;
    if (Kind == RK_FloatMinMax && (isa<FCmpInst>(Cur) ||
                                   isa<SelectInst>(Cur)))
      ++NumCmpSelectPatternInst;

    // Check  whether we found a reduction operator.
    FoundReduxOp |= !IsAPhi;

    // Process users of current instruction. Push non-PHI nodes after PHI nodes
    // onto the stack. This way we are going to have seen all inputs to PHI
    // nodes once we get to them.
    SmallVector<Instruction *, 8> NonPHIs;
    SmallVector<Instruction *, 8> PHIs;
    for (Value::use_iterator UI = Cur->use_begin(), E = Cur->use_end(); UI != E;
         ++UI) {
      Instruction *Usr = cast<Instruction>(*UI);

      // Check if we found the exit user.
      BasicBlock *Parent = Usr->getParent();
      if (!TheLoop->contains(Parent)) {
        // Exit if you find multiple outside users or if the header phi node is
        // being used. In this case the user uses the value of the previous
        // iteration, in which case we would loose "VF-1" iterations of the
        // reduction operation if we vectorize.
        if (ExitInstruction != 0 || Cur == Phi)
          return false;

        // The instruction used by an outside user must be the last instruction
        // before we feed back to the reduction phi. Otherwise, we loose VF-1
        // operations on the value.
        if (std::find(Phi->op_begin(), Phi->op_end(), Cur) == Phi->op_end())
         return false;

        ExitInstruction = Cur;
        continue;
      }

      // Process instructions only once (termination). Each reduction cycle
      // value must only be used once, except by phi nodes and min/max
      // reductions which are represented as a cmp followed by a select.
      ReductionInstDesc IgnoredVal(false, 0);
      if (VisitedInsts.insert(Usr)) {
        if (isa<PHINode>(Usr))
          PHIs.push_back(Usr);
        else
          NonPHIs.push_back(Usr);
      } else if (!isa<PHINode>(Usr) &&
                 ((!isa<FCmpInst>(Usr) &&
                   !isa<ICmpInst>(Usr) &&
                   !isa<SelectInst>(Usr)) ||
                  !isMinMaxSelectCmpPattern(Usr, IgnoredVal).IsReduction))
        return false;

      // Remember that we completed the cycle.
      if (Usr == Phi)
        FoundStartPHI = true;
    }
    Worklist.append(PHIs.begin(), PHIs.end());
    Worklist.append(NonPHIs.begin(), NonPHIs.end());
  }

  // This means we have seen one but not the other instruction of the
  // pattern or more than just a select and cmp.
  if ((Kind == RK_IntegerMinMax || Kind == RK_FloatMinMax) &&
      NumCmpSelectPatternInst != 2)
    return false;

  if (!FoundStartPHI || !FoundReduxOp || !ExitInstruction)
    return false;

  // We found a reduction var if we have reached the original phi node and we
  // only have a single instruction with out-of-loop users.

  // This instruction is allowed to have out-of-loop users.
  AllowedExit.insert(ExitInstruction);

  // Save the description of this reduction variable.
  ReductionDescriptor RD(RdxStart, ExitInstruction, Kind,
                         ReduxDesc.MinMaxKind);
  Reductions[Phi] = RD;
  // We've ended the cycle. This is a reduction variable if we have an
  // outside user and it has a binary op.

  return true;
}

/// Returns true if the instruction is a Select(ICmp(X, Y), X, Y) instruction
/// pattern corresponding to a min(X, Y) or max(X, Y).
LoopVectorizationLegality::ReductionInstDesc
LoopVectorizationLegality::isMinMaxSelectCmpPattern(Instruction *I,
                                                    ReductionInstDesc &Prev) {

  assert((isa<ICmpInst>(I) || isa<FCmpInst>(I) || isa<SelectInst>(I)) &&
         "Expect a select instruction");
  Instruction *Cmp = 0;
  SelectInst *Select = 0;

  // We must handle the select(cmp()) as a single instruction. Advance to the
  // select.
  if ((Cmp = dyn_cast<ICmpInst>(I)) || (Cmp = dyn_cast<FCmpInst>(I))) {
    if (!Cmp->hasOneUse() || !(Select = dyn_cast<SelectInst>(*I->use_begin())))
      return ReductionInstDesc(false, I);
    return ReductionInstDesc(Select, Prev.MinMaxKind);
  }

  // Only handle single use cases for now.
  if (!(Select = dyn_cast<SelectInst>(I)))
    return ReductionInstDesc(false, I);
  if (!(Cmp = dyn_cast<ICmpInst>(I->getOperand(0))) &&
      !(Cmp = dyn_cast<FCmpInst>(I->getOperand(0))))
    return ReductionInstDesc(false, I);
  if (!Cmp->hasOneUse())
    return ReductionInstDesc(false, I);

  Value *CmpLeft;
  Value *CmpRight;

  // Look for a min/max pattern.
  if (m_UMin(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_UIntMin);
  else if (m_UMax(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_UIntMax);
  else if (m_SMax(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_SIntMax);
  else if (m_SMin(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_SIntMin);
  else if (m_OrdFMin(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_FloatMin);
  else if (m_OrdFMax(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_FloatMax);
  else if (m_UnordFMin(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_FloatMin);
  else if (m_UnordFMax(m_Value(CmpLeft), m_Value(CmpRight)).match(Select))
    return ReductionInstDesc(Select, MRK_FloatMax);

  return ReductionInstDesc(false, I);
}

LoopVectorizationLegality::ReductionInstDesc
LoopVectorizationLegality::isReductionInstr(Instruction *I,
                                            ReductionKind Kind,
                                            ReductionInstDesc &Prev) {
  bool FP = I->getType()->isFloatingPointTy();
  bool FastMath = (FP && I->isCommutative() && I->isAssociative());
  switch (I->getOpcode()) {
  default:
    return ReductionInstDesc(false, I);
  case Instruction::PHI:
      if (FP && (Kind != RK_FloatMult && Kind != RK_FloatAdd &&
                 Kind != RK_FloatMinMax))
        return ReductionInstDesc(false, I);
    return ReductionInstDesc(I, Prev.MinMaxKind);
  case Instruction::Sub:
  case Instruction::Add:
    return ReductionInstDesc(Kind == RK_IntegerAdd, I);
  case Instruction::Mul:
    return ReductionInstDesc(Kind == RK_IntegerMult, I);
  case Instruction::And:
    return ReductionInstDesc(Kind == RK_IntegerAnd, I);
  case Instruction::Or:
    return ReductionInstDesc(Kind == RK_IntegerOr, I);
  case Instruction::Xor:
    return ReductionInstDesc(Kind == RK_IntegerXor, I);
  case Instruction::FMul:
    return ReductionInstDesc(Kind == RK_FloatMult && FastMath, I);
  case Instruction::FAdd:
    return ReductionInstDesc(Kind == RK_FloatAdd && FastMath, I);
  case Instruction::FCmp:
  case Instruction::ICmp:
  case Instruction::Select:
    if (Kind != RK_IntegerMinMax &&
        (!HasFunNoNaNAttr || Kind != RK_FloatMinMax))
      return ReductionInstDesc(false, I);
    return isMinMaxSelectCmpPattern(I, Prev);
  }
}

LoopVectorizationLegality::InductionKind
LoopVectorizationLegality::isInductionVariable(PHINode *Phi) {
  Type *PhiTy = Phi->getType();
  // We only handle integer and pointer inductions variables.
  if (!PhiTy->isIntegerTy() && !PhiTy->isPointerTy())
    return IK_NoInduction;

  // Check that the PHI is consecutive.
  const SCEV *PhiScev = SE->getSCEV(Phi);
  const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(PhiScev);
  if (!AR) {
    DEBUG(dbgs() << "LV: PHI is not a poly recurrence.\n");
    return IK_NoInduction;
  }
  const SCEV *Step = AR->getStepRecurrence(*SE);

  // Integer inductions need to have a stride of one.
  if (PhiTy->isIntegerTy()) {
    if (Step->isOne())
      return IK_IntInduction;
    if (Step->isAllOnesValue())
      return IK_ReverseIntInduction;
    return IK_NoInduction;
  }

  // Calculate the pointer stride and check if it is consecutive.
  const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
  if (!C)
    return IK_NoInduction;

  assert(PhiTy->isPointerTy() && "The PHI must be a pointer");
  uint64_t Size = DL->getTypeAllocSize(PhiTy->getPointerElementType());
  if (C->getValue()->equalsInt(Size))
    return IK_PtrInduction;
  else if (C->getValue()->equalsInt(0 - Size))
    return IK_ReversePtrInduction;

  return IK_NoInduction;
}

bool LoopVectorizationLegality::isInductionVariable(const Value *V) {
  Value *In0 = const_cast<Value*>(V);
  PHINode *PN = dyn_cast_or_null<PHINode>(In0);
  if (!PN)
    return false;

  return Inductions.count(PN);
}

bool LoopVectorizationLegality::blockNeedsPredication(BasicBlock *BB)  {
  assert(TheLoop->contains(BB) && "Unknown block used");

  // Blocks that do not dominate the latch need predication.
  BasicBlock* Latch = TheLoop->getLoopLatch();
  return !DT->dominates(BB, Latch);
}

bool LoopVectorizationLegality::blockCanBePredicated(BasicBlock *BB,
                                            SmallPtrSet<Value *, 8>& SafePtrs) {
  for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
    // We might be able to hoist the load.
    if (it->mayReadFromMemory()) {
      LoadInst *LI = dyn_cast<LoadInst>(it);
      if (!LI || !SafePtrs.count(LI->getPointerOperand()))
        return false;
    }

    // We don't predicate stores at the moment.
    if (it->mayWriteToMemory()) {
      StoreInst *SI = dyn_cast<StoreInst>(it);
      // We only support predication of stores in basic blocks with one
      // predecessor.
      if (!SI || ++NumPredStores > NumberOfStoresToPredicate ||
          !SafePtrs.count(SI->getPointerOperand()) ||
          !SI->getParent()->getSinglePredecessor())
        return false;
    }
    if (it->mayThrow())
      return false;

    // Check that we don't have a constant expression that can trap as operand.
    for (Instruction::op_iterator OI = it->op_begin(), OE = it->op_end();
         OI != OE; ++OI) {
      if (Constant *C = dyn_cast<Constant>(*OI))
        if (C->canTrap())
          return false;
    }

    // The instructions below can trap.
    switch (it->getOpcode()) {
    default: continue;
    case Instruction::UDiv:
    case Instruction::SDiv:
    case Instruction::URem:
    case Instruction::SRem:
             return false;
    }
  }

  return true;
}

LoopVectorizationCostModel::VectorizationFactor
LoopVectorizationCostModel::selectVectorizationFactor(bool OptForSize,
                                                      unsigned UserVF) {
  // Width 1 means no vectorize
  VectorizationFactor Factor = { 1U, 0U };
  if (OptForSize && Legal->getRuntimePointerCheck()->Need) {
    DEBUG(dbgs() << "LV: Aborting. Runtime ptr check is required in Os.\n");
    return Factor;
  }

  if (!EnableCondStoresVectorization && Legal->NumPredStores) {
    DEBUG(dbgs() << "LV: No vectorization. There are conditional stores.\n");
    return Factor;
  }

  // Find the trip count.
  unsigned TC = SE->getSmallConstantTripCount(TheLoop, TheLoop->getLoopLatch());
  DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');

  unsigned WidestType = getWidestType();
  unsigned WidestRegister = TTI.getRegisterBitWidth(true);
  unsigned MaxSafeDepDist = -1U;
  if (Legal->getMaxSafeDepDistBytes() != -1U)
    MaxSafeDepDist = Legal->getMaxSafeDepDistBytes() * 8;
  WidestRegister = ((WidestRegister < MaxSafeDepDist) ?
                    WidestRegister : MaxSafeDepDist);
  unsigned MaxVectorSize = WidestRegister / WidestType;
  DEBUG(dbgs() << "LV: The Widest type: " << WidestType << " bits.\n");
  DEBUG(dbgs() << "LV: The Widest register is: "
          << WidestRegister << " bits.\n");

  if (MaxVectorSize == 0) {
    DEBUG(dbgs() << "LV: The target has no vector registers.\n");
    MaxVectorSize = 1;
  }

  assert(MaxVectorSize <= 32 && "Did not expect to pack so many elements"
         " into one vector!");

  unsigned VF = MaxVectorSize;

  // If we optimize the program for size, avoid creating the tail loop.
  if (OptForSize) {
    // If we are unable to calculate the trip count then don't try to vectorize.
    if (TC < 2) {
      DEBUG(dbgs() << "LV: Aborting. A tail loop is required in Os.\n");
      return Factor;
    }

    // Find the maximum SIMD width that can fit within the trip count.
    VF = TC % MaxVectorSize;

    if (VF == 0)
      VF = MaxVectorSize;

    // If the trip count that we found modulo the vectorization factor is not
    // zero then we require a tail.
    if (VF < 2) {
      DEBUG(dbgs() << "LV: Aborting. A tail loop is required in Os.\n");
      return Factor;
    }
  }

  if (UserVF != 0) {
    assert(isPowerOf2_32(UserVF) && "VF needs to be a power of two");
    DEBUG(dbgs() << "LV: Using user VF " << UserVF << ".\n");

    Factor.Width = UserVF;
    return Factor;
  }

  float Cost = expectedCost(1);
  unsigned Width = 1;
  DEBUG(dbgs() << "LV: Scalar loop costs: " << (int)Cost << ".\n");
  for (unsigned i=2; i <= VF; i*=2) {
    // Notice that the vector loop needs to be executed less times, so
    // we need to divide the cost of the vector loops by the width of
    // the vector elements.
    float VectorCost = expectedCost(i) / (float)i;
    DEBUG(dbgs() << "LV: Vector loop of width " << i << " costs: " <<
          (int)VectorCost << ".\n");
    if (VectorCost < Cost) {
      Cost = VectorCost;
      Width = i;
    }
  }

  DEBUG(dbgs() << "LV: Selecting VF = : "<< Width << ".\n");
  Factor.Width = Width;
  Factor.Cost = Width * Cost;
  return Factor;
}

unsigned LoopVectorizationCostModel::getWidestType() {
  unsigned MaxWidth = 8;

  // For each block.
  for (Loop::block_iterator bb = TheLoop->block_begin(),
       be = TheLoop->block_end(); bb != be; ++bb) {
    BasicBlock *BB = *bb;

    // For each instruction in the loop.
    for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
      Type *T = it->getType();

      // Only examine Loads, Stores and PHINodes.
      if (!isa<LoadInst>(it) && !isa<StoreInst>(it) && !isa<PHINode>(it))
        continue;

      // Examine PHI nodes that are reduction variables.
      if (PHINode *PN = dyn_cast<PHINode>(it))
        if (!Legal->getReductionVars()->count(PN))
          continue;

      // Examine the stored values.
      if (StoreInst *ST = dyn_cast<StoreInst>(it))
        T = ST->getValueOperand()->getType();

      // Ignore loaded pointer types and stored pointer types that are not
      // consecutive. However, we do want to take consecutive stores/loads of
      // pointer vectors into account.
      if (T->isPointerTy() && !isConsecutiveLoadOrStore(it))
        continue;

      MaxWidth = std::max(MaxWidth,
                          (unsigned)DL->getTypeSizeInBits(T->getScalarType()));
    }
  }

  return MaxWidth;
}

unsigned
LoopVectorizationCostModel::selectUnrollFactor(bool OptForSize,
                                               unsigned UserUF,
                                               unsigned VF,
                                               unsigned LoopCost) {

  // -- The unroll heuristics --
  // We unroll the loop in order to expose ILP and reduce the loop overhead.
  // There are many micro-architectural considerations that we can't predict
  // at this level. For example frontend pressure (on decode or fetch) due to
  // code size, or the number and capabilities of the execution ports.
  //
  // We use the following heuristics to select the unroll factor:
  // 1. If the code has reductions the we unroll in order to break the cross
  // iteration dependency.
  // 2. If the loop is really small then we unroll in order to reduce the loop
  // overhead.
  // 3. We don't unroll if we think that we will spill registers to memory due
  // to the increased register pressure.

  // Use the user preference, unless 'auto' is selected.
  if (UserUF != 0)
    return UserUF;

  // When we optimize for size we don't unroll.
  if (OptForSize)
    return 1;

  // We used the distance for the unroll factor.
  if (Legal->getMaxSafeDepDistBytes() != -1U)
    return 1;

  // Do not unroll loops with a relatively small trip count.
  unsigned TC = SE->getSmallConstantTripCount(TheLoop,
                                              TheLoop->getLoopLatch());
  if (TC > 1 && TC < TinyTripCountUnrollThreshold)
    return 1;

  unsigned TargetNumRegisters = TTI.getNumberOfRegisters(VF > 1);
  DEBUG(dbgs() << "LV: The target has " << TargetNumRegisters <<
        " registers\n");

  if (VF == 1) {
    if (ForceTargetNumScalarRegs.getNumOccurrences() > 0)
      TargetNumRegisters = ForceTargetNumScalarRegs;
  } else {
    if (ForceTargetNumVectorRegs.getNumOccurrences() > 0)
      TargetNumRegisters = ForceTargetNumVectorRegs;
  }

  LoopVectorizationCostModel::RegisterUsage R = calculateRegisterUsage();
  // We divide by these constants so assume that we have at least one
  // instruction that uses at least one register.
  R.MaxLocalUsers = std::max(R.MaxLocalUsers, 1U);
  R.NumInstructions = std::max(R.NumInstructions, 1U);

  // We calculate the unroll factor using the following formula.
  // Subtract the number of loop invariants from the number of available
  // registers. These registers are used by all of the unrolled instances.
  // Next, divide the remaining registers by the number of registers that is
  // required by the loop, in order to estimate how many parallel instances
  // fit without causing spills. All of this is rounded down if necessary to be
  // a power of two. We want power of two unroll factors to simplify any
  // addressing operations or alignment considerations.
  unsigned UF = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs) /
                              R.MaxLocalUsers);

  // Don't count the induction variable as unrolled.
  if (EnableIndVarRegisterHeur)
    UF = PowerOf2Floor((TargetNumRegisters - R.LoopInvariantRegs - 1) /
                       std::max(1U, (R.MaxLocalUsers - 1)));

  // Clamp the unroll factor ranges to reasonable factors.
  unsigned MaxUnrollSize = TTI.getMaximumUnrollFactor();

  // Check if the user has overridden the unroll max.
  if (VF == 1) {
    if (ForceTargetMaxScalarUnrollFactor.getNumOccurrences() > 0)
      MaxUnrollSize = ForceTargetMaxScalarUnrollFactor;
  } else {
    if (ForceTargetMaxVectorUnrollFactor.getNumOccurrences() > 0)
      MaxUnrollSize = ForceTargetMaxVectorUnrollFactor;
  }

  // If we did not calculate the cost for VF (because the user selected the VF)
  // then we calculate the cost of VF here.
  if (LoopCost == 0)
    LoopCost = expectedCost(VF);

  // Clamp the calculated UF to be between the 1 and the max unroll factor
  // that the target allows.
  if (UF > MaxUnrollSize)
    UF = MaxUnrollSize;
  else if (UF < 1)
    UF = 1;

  // Unroll if we vectorized this loop and there is a reduction that could
  // benefit from unrolling.
  if (VF > 1 && Legal->getReductionVars()->size()) {
    DEBUG(dbgs() << "LV: Unrolling because of reductions.\n");
    return UF;
  }

  // Note that if we've already vectorized the loop we will have done the
  // runtime check and so unrolling won't require further checks.
  bool UnrollingRequiresRuntimePointerCheck =
      (VF == 1 && Legal->getRuntimePointerCheck()->Need);

  // We want to unroll small loops in order to reduce the loop overhead and
  // potentially expose ILP opportunities.
  DEBUG(dbgs() << "LV: Loop cost is " << LoopCost << '\n');
  if (!UnrollingRequiresRuntimePointerCheck &&
      LoopCost < SmallLoopCost) {
    // We assume that the cost overhead is 1 and we use the cost model
    // to estimate the cost of the loop and unroll until the cost of the
    // loop overhead is about 5% of the cost of the loop.
    unsigned SmallUF = std::min(UF, (unsigned)PowerOf2Floor(SmallLoopCost / LoopCost));

    // Unroll until store/load ports (estimated by max unroll factor) are
    // saturated.
    unsigned StoresUF = UF / (Legal->NumStores ? Legal->NumStores : 1);
    unsigned LoadsUF = UF /  (Legal->NumLoads ? Legal->NumLoads : 1);

    if (EnableLoadStoreRuntimeUnroll && std::max(StoresUF, LoadsUF) > SmallUF) {
      DEBUG(dbgs() << "LV: Unrolling to saturate store or load ports.\n");
      return std::max(StoresUF, LoadsUF);
    }

    DEBUG(dbgs() << "LV: Unrolling to reduce branch cost.\n");
    return SmallUF;
  }

  DEBUG(dbgs() << "LV: Not Unrolling.\n");
  return 1;
}

LoopVectorizationCostModel::RegisterUsage
LoopVectorizationCostModel::calculateRegisterUsage() {
  // This function calculates the register usage by measuring the highest number
  // of values that are alive at a single location. Obviously, this is a very
  // rough estimation. We scan the loop in a topological order in order and
  // assign a number to each instruction. We use RPO to ensure that defs are
  // met before their users. We assume that each instruction that has in-loop
  // users starts an interval. We record every time that an in-loop value is
  // used, so we have a list of the first and last occurrences of each
  // instruction. Next, we transpose this data structure into a multi map that
  // holds the list of intervals that *end* at a specific location. This multi
  // map allows us to perform a linear search. We scan the instructions linearly
  // and record each time that a new interval starts, by placing it in a set.
  // If we find this value in the multi-map then we remove it from the set.
  // The max register usage is the maximum size of the set.
  // We also search for instructions that are defined outside the loop, but are
  // used inside the loop. We need this number separately from the max-interval
  // usage number because when we unroll, loop-invariant values do not take
  // more register.
  LoopBlocksDFS DFS(TheLoop);
  DFS.perform(LI);

  RegisterUsage R;
  R.NumInstructions = 0;

  // Each 'key' in the map opens a new interval. The values
  // of the map are the index of the 'last seen' usage of the
  // instruction that is the key.
  typedef DenseMap<Instruction*, unsigned> IntervalMap;
  // Maps instruction to its index.
  DenseMap<unsigned, Instruction*> IdxToInstr;
  // Marks the end of each interval.
  IntervalMap EndPoint;
  // Saves the list of instruction indices that are used in the loop.
  SmallSet<Instruction*, 8> Ends;
  // Saves the list of values that are used in the loop but are
  // defined outside the loop, such as arguments and constants.
  SmallPtrSet<Value*, 8> LoopInvariants;

  unsigned Index = 0;
  for (LoopBlocksDFS::RPOIterator bb = DFS.beginRPO(),
       be = DFS.endRPO(); bb != be; ++bb) {
    R.NumInstructions += (*bb)->size();
    for (BasicBlock::iterator it = (*bb)->begin(), e = (*bb)->end(); it != e;
         ++it) {
      Instruction *I = it;
      IdxToInstr[Index++] = I;

      // Save the end location of each USE.
      for (unsigned i = 0; i < I->getNumOperands(); ++i) {
        Value *U = I->getOperand(i);
        Instruction *Instr = dyn_cast<Instruction>(U);

        // Ignore non-instruction values such as arguments, constants, etc.
        if (!Instr) continue;

        // If this instruction is outside the loop then record it and continue.
        if (!TheLoop->contains(Instr)) {
          LoopInvariants.insert(Instr);
          continue;
        }

        // Overwrite previous end points.
        EndPoint[Instr] = Index;
        Ends.insert(Instr);
      }
    }
  }

  // Saves the list of intervals that end with the index in 'key'.
  typedef SmallVector<Instruction*, 2> InstrList;
  DenseMap<unsigned, InstrList> TransposeEnds;

  // Transpose the EndPoints to a list of values that end at each index.
  for (IntervalMap::iterator it = EndPoint.begin(), e = EndPoint.end();
       it != e; ++it)
    TransposeEnds[it->second].push_back(it->first);

  SmallSet<Instruction*, 8> OpenIntervals;
  unsigned MaxUsage = 0;


  DEBUG(dbgs() << "LV(REG): Calculating max register usage:\n");
  for (unsigned int i = 0; i < Index; ++i) {
    Instruction *I = IdxToInstr[i];
    // Ignore instructions that are never used within the loop.
    if (!Ends.count(I)) continue;

    // Remove all of the instructions that end at this location.
    InstrList &List = TransposeEnds[i];
    for (unsigned int j=0, e = List.size(); j < e; ++j)
      OpenIntervals.erase(List[j]);

    // Count the number of live interals.
    MaxUsage = std::max(MaxUsage, OpenIntervals.size());

    DEBUG(dbgs() << "LV(REG): At #" << i << " Interval # " <<
          OpenIntervals.size() << '\n');

    // Add the current instruction to the list of open intervals.
    OpenIntervals.insert(I);
  }

  unsigned Invariant = LoopInvariants.size();
  DEBUG(dbgs() << "LV(REG): Found max usage: " << MaxUsage << '\n');
  DEBUG(dbgs() << "LV(REG): Found invariant usage: " << Invariant << '\n');
  DEBUG(dbgs() << "LV(REG): LoopSize: " << R.NumInstructions << '\n');

  R.LoopInvariantRegs = Invariant;
  R.MaxLocalUsers = MaxUsage;
  return R;
}

unsigned LoopVectorizationCostModel::expectedCost(unsigned VF) {
  unsigned Cost = 0;

  // For each block.
  for (Loop::block_iterator bb = TheLoop->block_begin(),
       be = TheLoop->block_end(); bb != be; ++bb) {
    unsigned BlockCost = 0;
    BasicBlock *BB = *bb;

    // For each instruction in the old loop.
    for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; ++it) {
      // Skip dbg intrinsics.
      if (isa<DbgInfoIntrinsic>(it))
        continue;

      unsigned C = getInstructionCost(it, VF);

      // Check if we should override the cost.
      if (ForceTargetInstructionCost.getNumOccurrences() > 0)
        C = ForceTargetInstructionCost;

      BlockCost += C;
      DEBUG(dbgs() << "LV: Found an estimated cost of " << C << " for VF " <<
            VF << " For instruction: " << *it << '\n');
    }

    // We assume that if-converted blocks have a 50% chance of being executed.
    // When the code is scalar then some of the blocks are avoided due to CF.
    // When the code is vectorized we execute all code paths.
    if (VF == 1 && Legal->blockNeedsPredication(*bb))
      BlockCost /= 2;

    Cost += BlockCost;
  }

  return Cost;
}

/// \brief Check whether the address computation for a non-consecutive memory
/// access looks like an unlikely candidate for being merged into the indexing
/// mode.
///
/// We look for a GEP which has one index that is an induction variable and all
/// other indices are loop invariant. If the stride of this access is also
/// within a small bound we decide that this address computation can likely be
/// merged into the addressing mode.
/// In all other cases, we identify the address computation as complex.
static bool isLikelyComplexAddressComputation(Value *Ptr,
                                              LoopVectorizationLegality *Legal,
                                              ScalarEvolution *SE,
                                              const Loop *TheLoop) {
  GetElementPtrInst *Gep = dyn_cast<GetElementPtrInst>(Ptr);
  if (!Gep)
    return true;

  // We are looking for a gep with all loop invariant indices except for one
  // which should be an induction variable.
  unsigned NumOperands = Gep->getNumOperands();
  for (unsigned i = 1; i < NumOperands; ++i) {
    Value *Opd = Gep->getOperand(i);
    if (!SE->isLoopInvariant(SE->getSCEV(Opd), TheLoop) &&
        !Legal->isInductionVariable(Opd))
      return true;
  }

  // Now we know we have a GEP ptr, %inv, %ind, %inv. Make sure that the step
  // can likely be merged into the address computation.
  unsigned MaxMergeDistance = 64;

  const SCEVAddRecExpr *AddRec = dyn_cast<SCEVAddRecExpr>(SE->getSCEV(Ptr));
  if (!AddRec)
    return true;

  // Check the step is constant.
  const SCEV *Step = AddRec->getStepRecurrence(*SE);
  // Calculate the pointer stride and check if it is consecutive.
  const SCEVConstant *C = dyn_cast<SCEVConstant>(Step);
  if (!C)
    return true;

  const APInt &APStepVal = C->getValue()->getValue();

  // Huge step value - give up.
  if (APStepVal.getBitWidth() > 64)
    return true;

  int64_t StepVal = APStepVal.getSExtValue();

  return StepVal > MaxMergeDistance;
}

static bool isStrideMul(Instruction *I, LoopVectorizationLegality *Legal) {
  if (Legal->hasStride(I->getOperand(0)) || Legal->hasStride(I->getOperand(1)))
    return true;
  return false;
}

unsigned
LoopVectorizationCostModel::getInstructionCost(Instruction *I, unsigned VF) {
  // If we know that this instruction will remain uniform, check the cost of
  // the scalar version.
  if (Legal->isUniformAfterVectorization(I))
    VF = 1;

  Type *RetTy = I->getType();
  Type *VectorTy = ToVectorTy(RetTy, VF);

  // TODO: We need to estimate the cost of intrinsic calls.
  switch (I->getOpcode()) {
  case Instruction::GetElementPtr:
    // We mark this instruction as zero-cost because the cost of GEPs in
    // vectorized code depends on whether the corresponding memory instruction
    // is scalarized or not. Therefore, we handle GEPs with the memory
    // instruction cost.
    return 0;
  case Instruction::Br: {
    return TTI.getCFInstrCost(I->getOpcode());
  }
  case Instruction::PHI:
    //TODO: IF-converted IFs become selects.
    return 0;
  case Instruction::Add:
  case Instruction::FAdd:
  case Instruction::Sub:
  case Instruction::FSub:
  case Instruction::Mul:
  case Instruction::FMul:
  case Instruction::UDiv:
  case Instruction::SDiv:
  case Instruction::FDiv:
  case Instruction::URem:
  case Instruction::SRem:
  case Instruction::FRem:
  case Instruction::Shl:
  case Instruction::LShr:
  case Instruction::AShr:
  case Instruction::And:
  case Instruction::Or:
  case Instruction::Xor: {
    // Since we will replace the stride by 1 the multiplication should go away.
    if (I->getOpcode() == Instruction::Mul && isStrideMul(I, Legal))
      return 0;
    // Certain instructions can be cheaper to vectorize if they have a constant
    // second vector operand. One example of this are shifts on x86.
    TargetTransformInfo::OperandValueKind Op1VK =
      TargetTransformInfo::OK_AnyValue;
    TargetTransformInfo::OperandValueKind Op2VK =
      TargetTransformInfo::OK_AnyValue;
    Value *Op2 = I->getOperand(1);

    // Check for a splat of a constant or for a non uniform vector of constants.
    if (isa<ConstantInt>(Op2))
      Op2VK = TargetTransformInfo::OK_UniformConstantValue;
    else if (isa<ConstantVector>(Op2) || isa<ConstantDataVector>(Op2)) {
      Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
      if (cast<Constant>(Op2)->getSplatValue() != NULL)
        Op2VK = TargetTransformInfo::OK_UniformConstantValue;
    }

    return TTI.getArithmeticInstrCost(I->getOpcode(), VectorTy, Op1VK, Op2VK);
  }
  case Instruction::Select: {
    SelectInst *SI = cast<SelectInst>(I);
    const SCEV *CondSCEV = SE->getSCEV(SI->getCondition());
    bool ScalarCond = (SE->isLoopInvariant(CondSCEV, TheLoop));
    Type *CondTy = SI->getCondition()->getType();
    if (!ScalarCond)
      CondTy = VectorType::get(CondTy, VF);

    return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy, CondTy);
  }
  case Instruction::ICmp:
  case Instruction::FCmp: {
    Type *ValTy = I->getOperand(0)->getType();
    VectorTy = ToVectorTy(ValTy, VF);
    return TTI.getCmpSelInstrCost(I->getOpcode(), VectorTy);
  }
  case Instruction::Store:
  case Instruction::Load: {
    StoreInst *SI = dyn_cast<StoreInst>(I);
    LoadInst *LI = dyn_cast<LoadInst>(I);
    Type *ValTy = (SI ? SI->getValueOperand()->getType() :
                   LI->getType());
    VectorTy = ToVectorTy(ValTy, VF);

    unsigned Alignment = SI ? SI->getAlignment() : LI->getAlignment();
    unsigned AS = SI ? SI->getPointerAddressSpace() :
      LI->getPointerAddressSpace();
    Value *Ptr = SI ? SI->getPointerOperand() : LI->getPointerOperand();
    // We add the cost of address computation here instead of with the gep
    // instruction because only here we know whether the operation is
    // scalarized.
    if (VF == 1)
      return TTI.getAddressComputationCost(VectorTy) +
        TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);

    // Scalarized loads/stores.
    int ConsecutiveStride = Legal->isConsecutivePtr(Ptr);
    bool Reverse = ConsecutiveStride < 0;
    unsigned ScalarAllocatedSize = DL->getTypeAllocSize(ValTy);
    unsigned VectorElementSize = DL->getTypeStoreSize(VectorTy)/VF;
    if (!ConsecutiveStride || ScalarAllocatedSize != VectorElementSize) {
      bool IsComplexComputation =
        isLikelyComplexAddressComputation(Ptr, Legal, SE, TheLoop);
      unsigned Cost = 0;
      // The cost of extracting from the value vector and pointer vector.
      Type *PtrTy = ToVectorTy(Ptr->getType(), VF);
      for (unsigned i = 0; i < VF; ++i) {
        //  The cost of extracting the pointer operand.
        Cost += TTI.getVectorInstrCost(Instruction::ExtractElement, PtrTy, i);
        // In case of STORE, the cost of ExtractElement from the vector.
        // In case of LOAD, the cost of InsertElement into the returned
        // vector.
        Cost += TTI.getVectorInstrCost(SI ? Instruction::ExtractElement :
                                            Instruction::InsertElement,
                                            VectorTy, i);
      }

      // The cost of the scalar loads/stores.
      Cost += VF * TTI.getAddressComputationCost(PtrTy, IsComplexComputation);
      Cost += VF * TTI.getMemoryOpCost(I->getOpcode(), ValTy->getScalarType(),
                                       Alignment, AS);
      return Cost;
    }

    // Wide load/stores.
    unsigned Cost = TTI.getAddressComputationCost(VectorTy);
    Cost += TTI.getMemoryOpCost(I->getOpcode(), VectorTy, Alignment, AS);

    if (Reverse)
      Cost += TTI.getShuffleCost(TargetTransformInfo::SK_Reverse,
                                  VectorTy, 0);
    return Cost;
  }
  case Instruction::ZExt:
  case Instruction::SExt:
  case Instruction::FPToUI:
  case Instruction::FPToSI:
  case Instruction::FPExt:
  case Instruction::PtrToInt:
  case Instruction::IntToPtr:
  case Instruction::SIToFP:
  case Instruction::UIToFP:
  case Instruction::Trunc:
  case Instruction::FPTrunc:
  case Instruction::BitCast: {
    // We optimize the truncation of induction variable.
    // The cost of these is the same as the scalar operation.
    if (I->getOpcode() == Instruction::Trunc &&
        Legal->isInductionVariable(I->getOperand(0)))
      return TTI.getCastInstrCost(I->getOpcode(), I->getType(),
                                  I->getOperand(0)->getType());

    Type *SrcVecTy = ToVectorTy(I->getOperand(0)->getType(), VF);
    return TTI.getCastInstrCost(I->getOpcode(), VectorTy, SrcVecTy);
  }
  case Instruction::Call: {
    CallInst *CI = cast<CallInst>(I);
    Intrinsic::ID ID = getIntrinsicIDForCall(CI, TLI);
    assert(ID && "Not an intrinsic call!");
    Type *RetTy = ToVectorTy(CI->getType(), VF);
    SmallVector<Type*, 4> Tys;
    for (unsigned i = 0, ie = CI->getNumArgOperands(); i != ie; ++i)
      Tys.push_back(ToVectorTy(CI->getArgOperand(i)->getType(), VF));
    return TTI.getIntrinsicInstrCost(ID, RetTy, Tys);
  }
  default: {
    // We are scalarizing the instruction. Return the cost of the scalar
    // instruction, plus the cost of insert and extract into vector
    // elements, times the vector width.
    unsigned Cost = 0;

    if (!RetTy->isVoidTy() && VF != 1) {
      unsigned InsCost = TTI.getVectorInstrCost(Instruction::InsertElement,
                                                VectorTy);
      unsigned ExtCost = TTI.getVectorInstrCost(Instruction::ExtractElement,
                                                VectorTy);

      // The cost of inserting the results plus extracting each one of the
      // operands.
      Cost += VF * (InsCost + ExtCost * I->getNumOperands());
    }

    // The cost of executing VF copies of the scalar instruction. This opcode
    // is unknown. Assume that it is the same as 'mul'.
    Cost += VF * TTI.getArithmeticInstrCost(Instruction::Mul, VectorTy);
    return Cost;
  }
  }// end of switch.
}

Type* LoopVectorizationCostModel::ToVectorTy(Type *Scalar, unsigned VF) {
  if (Scalar->isVoidTy() || VF == 1)
    return Scalar;
  return VectorType::get(Scalar, VF);
}

char LoopVectorize::ID = 0;
static const char lv_name[] = "Loop Vectorization";
INITIALIZE_PASS_BEGIN(LoopVectorize, LV_NAME, lv_name, false, false)
INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfo)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolution)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
INITIALIZE_PASS_DEPENDENCY(LoopInfo)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_END(LoopVectorize, LV_NAME, lv_name, false, false)

namespace llvm {
  Pass *createLoopVectorizePass(bool NoUnrolling, bool AlwaysVectorize) {
    return new LoopVectorize(NoUnrolling, AlwaysVectorize);
  }
}

bool LoopVectorizationCostModel::isConsecutiveLoadOrStore(Instruction *Inst) {
  // Check for a store.
  if (StoreInst *ST = dyn_cast<StoreInst>(Inst))
    return Legal->isConsecutivePtr(ST->getPointerOperand()) != 0;

  // Check for a load.
  if (LoadInst *LI = dyn_cast<LoadInst>(Inst))
    return Legal->isConsecutivePtr(LI->getPointerOperand()) != 0;

  return false;
}


void InnerLoopUnroller::scalarizeInstruction(Instruction *Instr,
                                             bool IfPredicateStore) {
  assert(!Instr->getType()->isAggregateType() && "Can't handle vectors");
  // Holds vector parameters or scalars, in case of uniform vals.
  SmallVector<VectorParts, 4> Params;

  setDebugLocFromInst(Builder, Instr);

  // Find all of the vectorized parameters.
  for (unsigned op = 0, e = Instr->getNumOperands(); op != e; ++op) {
    Value *SrcOp = Instr->getOperand(op);

    // If we are accessing the old induction variable, use the new one.
    if (SrcOp == OldInduction) {
      Params.push_back(getVectorValue(SrcOp));
      continue;
    }

    // Try using previously calculated values.
    Instruction *SrcInst = dyn_cast<Instruction>(SrcOp);

    // If the src is an instruction that appeared earlier in the basic block
    // then it should already be vectorized.
    if (SrcInst && OrigLoop->contains(SrcInst)) {
      assert(WidenMap.has(SrcInst) && "Source operand is unavailable");
      // The parameter is a vector value from earlier.
      Params.push_back(WidenMap.get(SrcInst));
    } else {
      // The parameter is a scalar from outside the loop. Maybe even a constant.
      VectorParts Scalars;
      Scalars.append(UF, SrcOp);
      Params.push_back(Scalars);
    }
  }

  assert(Params.size() == Instr->getNumOperands() &&
         "Invalid number of operands");

  // Does this instruction return a value ?
  bool IsVoidRetTy = Instr->getType()->isVoidTy();

  Value *UndefVec = IsVoidRetTy ? 0 :
  UndefValue::get(Instr->getType());
  // Create a new entry in the WidenMap and initialize it to Undef or Null.
  VectorParts &VecResults = WidenMap.splat(Instr, UndefVec);

  Instruction *InsertPt = Builder.GetInsertPoint();
  BasicBlock *IfBlock = Builder.GetInsertBlock();
  BasicBlock *CondBlock = 0;

  VectorParts Cond;
  Loop *VectorLp = 0;
  if (IfPredicateStore) {
    assert(Instr->getParent()->getSinglePredecessor() &&
           "Only support single predecessor blocks");
    Cond = createEdgeMask(Instr->getParent()->getSinglePredecessor(),
                          Instr->getParent());
    VectorLp = LI->getLoopFor(IfBlock);
    assert(VectorLp && "Must have a loop for this block");
  }

  // For each vector unroll 'part':
  for (unsigned Part = 0; Part < UF; ++Part) {
    // For each scalar that we create:

    // Start an "if (pred) a[i] = ..." block.
    Value *Cmp = 0;
    if (IfPredicateStore) {
      if (Cond[Part]->getType()->isVectorTy())
        Cond[Part] =
            Builder.CreateExtractElement(Cond[Part], Builder.getInt32(0));
      Cmp = Builder.CreateICmp(ICmpInst::ICMP_EQ, Cond[Part],
                               ConstantInt::get(Cond[Part]->getType(), 1));
      CondBlock = IfBlock->splitBasicBlock(InsertPt, "cond.store");
      LoopVectorBody.push_back(CondBlock);
      VectorLp->addBasicBlockToLoop(CondBlock, LI->getBase());
      // Update Builder with newly created basic block.
      Builder.SetInsertPoint(InsertPt);
    }

    Instruction *Cloned = Instr->clone();
      if (!IsVoidRetTy)
        Cloned->setName(Instr->getName() + ".cloned");
      // Replace the operands of the cloned instructions with extracted scalars.
      for (unsigned op = 0, e = Instr->getNumOperands(); op != e; ++op) {
        Value *Op = Params[op][Part];
        Cloned->setOperand(op, Op);
      }

      // Place the cloned scalar in the new loop.
      Builder.Insert(Cloned);

      // If the original scalar returns a value we need to place it in a vector
      // so that future users will be able to use it.
      if (!IsVoidRetTy)
        VecResults[Part] = Cloned;

    // End if-block.
      if (IfPredicateStore) {
        BasicBlock *NewIfBlock = CondBlock->splitBasicBlock(InsertPt, "else");
        LoopVectorBody.push_back(NewIfBlock);
        VectorLp->addBasicBlockToLoop(NewIfBlock, LI->getBase());
        Builder.SetInsertPoint(InsertPt);
        Instruction *OldBr = IfBlock->getTerminator();
        BranchInst::Create(CondBlock, NewIfBlock, Cmp, OldBr);
        OldBr->eraseFromParent();
        IfBlock = NewIfBlock;
      }
  }
}

void InnerLoopUnroller::vectorizeMemoryInstruction(Instruction *Instr) {
  StoreInst *SI = dyn_cast<StoreInst>(Instr);
  bool IfPredicateStore = (SI && Legal->blockNeedsPredication(SI->getParent()));

  return scalarizeInstruction(Instr, IfPredicateStore);
}

Value *InnerLoopUnroller::reverseVector(Value *Vec) {
  return Vec;
}

Value *InnerLoopUnroller::getBroadcastInstrs(Value *V) {
  return V;
}

Value *InnerLoopUnroller::getConsecutiveVector(Value* Val, int StartIdx,
                                               bool Negate) {
  // When unrolling and the VF is 1, we only need to add a simple scalar.
  Type *ITy = Val->getType();
  assert(!ITy->isVectorTy() && "Val must be a scalar");
  Constant *C = ConstantInt::get(ITy, StartIdx, Negate);
  return Builder.CreateAdd(Val, C, "induction");
}