aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Transforms/Vectorize/SLPVectorizer.cpp
blob: 328f2700296042e10e685fa8f77f001b77cedec8 (plain) (blame)
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
//===- SLPVectorizer.cpp - A bottom up SLP Vectorizer ---------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
// This pass implements the Bottom Up SLP vectorizer. It detects consecutive
// stores that can be put together into vector-stores. Next, it attempts to
// construct vectorizable tree using the use-def chains. If a profitable tree
// was found, the SLP vectorizer performs vectorization on the tree.
//
// The pass is inspired by the work described in the paper:
//  "Loop-Aware SLP in GCC" by Ira Rosen, Dorit Nuzman, Ayal Zaks.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Vectorize/SLPVectorizer.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/LoopAccessAnalysis.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/Analysis/VectorUtils.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/NoFolder.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/IR/Verifier.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Vectorize.h"
#include <algorithm>
#include <memory>

using namespace llvm;
using namespace slpvectorizer;

#define SV_NAME "slp-vectorizer"
#define DEBUG_TYPE "SLP"

STATISTIC(NumVectorInstructions, "Number of vector instructions generated");

static cl::opt<int>
    SLPCostThreshold("slp-threshold", cl::init(0), cl::Hidden,
                     cl::desc("Only vectorize if you gain more than this "
                              "number "));

static cl::opt<bool>
ShouldVectorizeHor("slp-vectorize-hor", cl::init(true), cl::Hidden,
                   cl::desc("Attempt to vectorize horizontal reductions"));

static cl::opt<bool> ShouldStartVectorizeHorAtStore(
    "slp-vectorize-hor-store", cl::init(false), cl::Hidden,
    cl::desc(
        "Attempt to vectorize horizontal reductions feeding into a store"));

static cl::opt<int>
MaxVectorRegSizeOption("slp-max-reg-size", cl::init(128), cl::Hidden,
    cl::desc("Attempt to vectorize for this register size in bits"));

/// Limits the size of scheduling regions in a block.
/// It avoid long compile times for _very_ large blocks where vector
/// instructions are spread over a wide range.
/// This limit is way higher than needed by real-world functions.
static cl::opt<int>
ScheduleRegionSizeBudget("slp-schedule-budget", cl::init(100000), cl::Hidden,
    cl::desc("Limit the size of the SLP scheduling region per block"));

static cl::opt<int> MinVectorRegSizeOption(
    "slp-min-reg-size", cl::init(128), cl::Hidden,
    cl::desc("Attempt to vectorize for this register size in bits"));

static cl::opt<unsigned> RecursionMaxDepth(
    "slp-recursion-max-depth", cl::init(12), cl::Hidden,
    cl::desc("Limit the recursion depth when building a vectorizable tree"));

static cl::opt<unsigned> MinTreeSize(
    "slp-min-tree-size", cl::init(3), cl::Hidden,
    cl::desc("Only vectorize small trees if they are fully vectorizable"));

// Limit the number of alias checks. The limit is chosen so that
// it has no negative effect on the llvm benchmarks.
static const unsigned AliasedCheckLimit = 10;

// Another limit for the alias checks: The maximum distance between load/store
// instructions where alias checks are done.
// This limit is useful for very large basic blocks.
static const unsigned MaxMemDepDistance = 160;

/// If the ScheduleRegionSizeBudget is exhausted, we allow small scheduling
/// regions to be handled.
static const int MinScheduleRegionSize = 16;

/// \brief Predicate for the element types that the SLP vectorizer supports.
///
/// The most important thing to filter here are types which are invalid in LLVM
/// vectors. We also filter target specific types which have absolutely no
/// meaningful vectorization path such as x86_fp80 and ppc_f128. This just
/// avoids spending time checking the cost model and realizing that they will
/// be inevitably scalarized.
static bool isValidElementType(Type *Ty) {
  return VectorType::isValidElementType(Ty) && !Ty->isX86_FP80Ty() &&
         !Ty->isPPC_FP128Ty();
}

/// \returns true if all of the instructions in \p VL are in the same block or
/// false otherwise.
static bool allSameBlock(ArrayRef<Value *> VL) {
  Instruction *I0 = dyn_cast<Instruction>(VL[0]);
  if (!I0)
    return false;
  BasicBlock *BB = I0->getParent();
  for (int i = 1, e = VL.size(); i < e; i++) {
    Instruction *I = dyn_cast<Instruction>(VL[i]);
    if (!I)
      return false;

    if (BB != I->getParent())
      return false;
  }
  return true;
}

/// \returns True if all of the values in \p VL are constants.
static bool allConstant(ArrayRef<Value *> VL) {
  for (Value *i : VL)
    if (!isa<Constant>(i))
      return false;
  return true;
}

/// \returns True if all of the values in \p VL are identical.
static bool isSplat(ArrayRef<Value *> VL) {
  for (unsigned i = 1, e = VL.size(); i < e; ++i)
    if (VL[i] != VL[0])
      return false;
  return true;
}

///\returns Opcode that can be clubbed with \p Op to create an alternate
/// sequence which can later be merged as a ShuffleVector instruction.
static unsigned getAltOpcode(unsigned Op) {
  switch (Op) {
  case Instruction::FAdd:
    return Instruction::FSub;
  case Instruction::FSub:
    return Instruction::FAdd;
  case Instruction::Add:
    return Instruction::Sub;
  case Instruction::Sub:
    return Instruction::Add;
  default:
    return 0;
  }
}

///\returns bool representing if Opcode \p Op can be part
/// of an alternate sequence which can later be merged as
/// a ShuffleVector instruction.
static bool canCombineAsAltInst(unsigned Op) {
  return Op == Instruction::FAdd || Op == Instruction::FSub ||
         Op == Instruction::Sub || Op == Instruction::Add;
}

/// \returns ShuffleVector instruction if instructions in \p VL have
///  alternate fadd,fsub / fsub,fadd/add,sub/sub,add sequence.
/// (i.e. e.g. opcodes of fadd,fsub,fadd,fsub...)
static unsigned isAltInst(ArrayRef<Value *> VL) {
  Instruction *I0 = dyn_cast<Instruction>(VL[0]);
  unsigned Opcode = I0->getOpcode();
  unsigned AltOpcode = getAltOpcode(Opcode);
  for (int i = 1, e = VL.size(); i < e; i++) {
    Instruction *I = dyn_cast<Instruction>(VL[i]);
    if (!I || I->getOpcode() != ((i & 1) ? AltOpcode : Opcode))
      return 0;
  }
  return Instruction::ShuffleVector;
}

/// \returns The opcode if all of the Instructions in \p VL have the same
/// opcode, or zero.
static unsigned getSameOpcode(ArrayRef<Value *> VL) {
  Instruction *I0 = dyn_cast<Instruction>(VL[0]);
  if (!I0)
    return 0;
  unsigned Opcode = I0->getOpcode();
  for (int i = 1, e = VL.size(); i < e; i++) {
    Instruction *I = dyn_cast<Instruction>(VL[i]);
    if (!I || Opcode != I->getOpcode()) {
      if (canCombineAsAltInst(Opcode) && i == 1)
        return isAltInst(VL);
      return 0;
    }
  }
  return Opcode;
}

/// Get the intersection (logical and) of all of the potential IR flags
/// of each scalar operation (VL) that will be converted into a vector (I).
/// Flag set: NSW, NUW, exact, and all of fast-math.
static void propagateIRFlags(Value *I, ArrayRef<Value *> VL) {
  if (auto *VecOp = dyn_cast<Instruction>(I)) {
    if (auto *Intersection = dyn_cast<Instruction>(VL[0])) {
      // Intersection is initialized to the 0th scalar,
      // so start counting from index '1'.
      for (int i = 1, e = VL.size(); i < e; ++i) {
        if (auto *Scalar = dyn_cast<Instruction>(VL[i]))
          Intersection->andIRFlags(Scalar);
      }
      VecOp->copyIRFlags(Intersection);
    }
  }
}

/// \returns true if all of the values in \p VL have the same type or false
/// otherwise.
static bool allSameType(ArrayRef<Value *> VL) {
  Type *Ty = VL[0]->getType();
  for (int i = 1, e = VL.size(); i < e; i++)
    if (VL[i]->getType() != Ty)
      return false;

  return true;
}

/// \returns True if Extract{Value,Element} instruction extracts element Idx.
static bool matchExtractIndex(Instruction *E, unsigned Idx, unsigned Opcode) {
  assert(Opcode == Instruction::ExtractElement ||
         Opcode == Instruction::ExtractValue);
  if (Opcode == Instruction::ExtractElement) {
    ConstantInt *CI = dyn_cast<ConstantInt>(E->getOperand(1));
    return CI && CI->getZExtValue() == Idx;
  } else {
    ExtractValueInst *EI = cast<ExtractValueInst>(E);
    return EI->getNumIndices() == 1 && *EI->idx_begin() == Idx;
  }
}

/// \returns True if in-tree use also needs extract. This refers to
/// possible scalar operand in vectorized instruction.
static bool InTreeUserNeedToExtract(Value *Scalar, Instruction *UserInst,
                                    TargetLibraryInfo *TLI) {

  unsigned Opcode = UserInst->getOpcode();
  switch (Opcode) {
  case Instruction::Load: {
    LoadInst *LI = cast<LoadInst>(UserInst);
    return (LI->getPointerOperand() == Scalar);
  }
  case Instruction::Store: {
    StoreInst *SI = cast<StoreInst>(UserInst);
    return (SI->getPointerOperand() == Scalar);
  }
  case Instruction::Call: {
    CallInst *CI = cast<CallInst>(UserInst);
    Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
    if (hasVectorInstrinsicScalarOpd(ID, 1)) {
      return (CI->getArgOperand(1) == Scalar);
    }
  }
  default:
    return false;
  }
}

/// \returns the AA location that is being access by the instruction.
static MemoryLocation getLocation(Instruction *I, AliasAnalysis *AA) {
  if (StoreInst *SI = dyn_cast<StoreInst>(I))
    return MemoryLocation::get(SI);
  if (LoadInst *LI = dyn_cast<LoadInst>(I))
    return MemoryLocation::get(LI);
  return MemoryLocation();
}

/// \returns True if the instruction is not a volatile or atomic load/store.
static bool isSimple(Instruction *I) {
  if (LoadInst *LI = dyn_cast<LoadInst>(I))
    return LI->isSimple();
  if (StoreInst *SI = dyn_cast<StoreInst>(I))
    return SI->isSimple();
  if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(I))
    return !MI->isVolatile();
  return true;
}

namespace llvm {
namespace slpvectorizer {
/// Bottom Up SLP Vectorizer.
class BoUpSLP {
public:
  typedef SmallVector<Value *, 8> ValueList;
  typedef SmallVector<Instruction *, 16> InstrList;
  typedef SmallPtrSet<Value *, 16> ValueSet;
  typedef SmallVector<StoreInst *, 8> StoreList;

  BoUpSLP(Function *Func, ScalarEvolution *Se, TargetTransformInfo *Tti,
          TargetLibraryInfo *TLi, AliasAnalysis *Aa, LoopInfo *Li,
          DominatorTree *Dt, AssumptionCache *AC, DemandedBits *DB,
          const DataLayout *DL)
      : NumLoadsWantToKeepOrder(0), NumLoadsWantToChangeOrder(0), F(Func),
        SE(Se), TTI(Tti), TLI(TLi), AA(Aa), LI(Li), DT(Dt), AC(AC), DB(DB),
        DL(DL), Builder(Se->getContext()) {
    CodeMetrics::collectEphemeralValues(F, AC, EphValues);
    // Use the vector register size specified by the target unless overridden
    // by a command-line option.
    // TODO: It would be better to limit the vectorization factor based on
    //       data type rather than just register size. For example, x86 AVX has
    //       256-bit registers, but it does not support integer operations
    //       at that width (that requires AVX2).
    if (MaxVectorRegSizeOption.getNumOccurrences())
      MaxVecRegSize = MaxVectorRegSizeOption;
    else
      MaxVecRegSize = TTI->getRegisterBitWidth(true);

    MinVecRegSize = MinVectorRegSizeOption;
  }

  /// \brief Vectorize the tree that starts with the elements in \p VL.
  /// Returns the vectorized root.
  Value *vectorizeTree();

  /// \returns the cost incurred by unwanted spills and fills, caused by
  /// holding live values over call sites.
  int getSpillCost();

  /// \returns the vectorization cost of the subtree that starts at \p VL.
  /// A negative number means that this is profitable.
  int getTreeCost();

  /// Construct a vectorizable tree that starts at \p Roots, ignoring users for
  /// the purpose of scheduling and extraction in the \p UserIgnoreLst.
  void buildTree(ArrayRef<Value *> Roots,
                 ArrayRef<Value *> UserIgnoreLst = None);

  /// Clear the internal data structures that are created by 'buildTree'.
  void deleteTree() {
    VectorizableTree.clear();
    ScalarToTreeEntry.clear();
    MustGather.clear();
    ExternalUses.clear();
    NumLoadsWantToKeepOrder = 0;
    NumLoadsWantToChangeOrder = 0;
    for (auto &Iter : BlocksSchedules) {
      BlockScheduling *BS = Iter.second.get();
      BS->clear();
    }
    MinBWs.clear();
  }

  /// \brief Perform LICM and CSE on the newly generated gather sequences.
  void optimizeGatherSequence();

  /// \returns true if it is beneficial to reverse the vector order.
  bool shouldReorder() const {
    return NumLoadsWantToChangeOrder > NumLoadsWantToKeepOrder;
  }

  /// \return The vector element size in bits to use when vectorizing the
  /// expression tree ending at \p V. If V is a store, the size is the width of
  /// the stored value. Otherwise, the size is the width of the largest loaded
  /// value reaching V. This method is used by the vectorizer to calculate
  /// vectorization factors.
  unsigned getVectorElementSize(Value *V);

  /// Compute the minimum type sizes required to represent the entries in a
  /// vectorizable tree.
  void computeMinimumValueSizes();

  // \returns maximum vector register size as set by TTI or overridden by cl::opt.
  unsigned getMaxVecRegSize() const {
    return MaxVecRegSize;
  }

  // \returns minimum vector register size as set by cl::opt.
  unsigned getMinVecRegSize() const {
    return MinVecRegSize;
  }

  /// \brief Check if ArrayType or StructType is isomorphic to some VectorType.
  ///
  /// \returns number of elements in vector if isomorphism exists, 0 otherwise.
  unsigned canMapToVector(Type *T, const DataLayout &DL) const;

  /// \returns True if the VectorizableTree is both tiny and not fully
  /// vectorizable. We do not vectorize such trees.
  bool isTreeTinyAndNotFullyVectorizable();

private:
  struct TreeEntry;

  /// \returns the cost of the vectorizable entry.
  int getEntryCost(TreeEntry *E);

  /// This is the recursive part of buildTree.
  void buildTree_rec(ArrayRef<Value *> Roots, unsigned Depth);

  /// \returns True if the ExtractElement/ExtractValue instructions in VL can
  /// be vectorized to use the original vector (or aggregate "bitcast" to a vector).
  bool canReuseExtract(ArrayRef<Value *> VL, unsigned Opcode) const;

  /// Vectorize a single entry in the tree.
  Value *vectorizeTree(TreeEntry *E);

  /// Vectorize a single entry in the tree, starting in \p VL.
  Value *vectorizeTree(ArrayRef<Value *> VL);

  /// \returns the pointer to the vectorized value if \p VL is already
  /// vectorized, or NULL. They may happen in cycles.
  Value *alreadyVectorized(ArrayRef<Value *> VL) const;

  /// \returns the scalarization cost for this type. Scalarization in this
  /// context means the creation of vectors from a group of scalars.
  int getGatherCost(Type *Ty);

  /// \returns the scalarization cost for this list of values. Assuming that
  /// this subtree gets vectorized, we may need to extract the values from the
  /// roots. This method calculates the cost of extracting the values.
  int getGatherCost(ArrayRef<Value *> VL);

  /// \brief Set the Builder insert point to one after the last instruction in
  /// the bundle
  void setInsertPointAfterBundle(ArrayRef<Value *> VL);

  /// \returns a vector from a collection of scalars in \p VL.
  Value *Gather(ArrayRef<Value *> VL, VectorType *Ty);

  /// \returns whether the VectorizableTree is fully vectorizable and will
  /// be beneficial even the tree height is tiny.
  bool isFullyVectorizableTinyTree();

  /// \reorder commutative operands in alt shuffle if they result in
  ///  vectorized code.
  void reorderAltShuffleOperands(ArrayRef<Value *> VL,
                                 SmallVectorImpl<Value *> &Left,
                                 SmallVectorImpl<Value *> &Right);
  /// \reorder commutative operands to get better probability of
  /// generating vectorized code.
  void reorderInputsAccordingToOpcode(ArrayRef<Value *> VL,
                                      SmallVectorImpl<Value *> &Left,
                                      SmallVectorImpl<Value *> &Right);
  struct TreeEntry {
    TreeEntry() : Scalars(), VectorizedValue(nullptr),
    NeedToGather(0) {}

    /// \returns true if the scalars in VL are equal to this entry.
    bool isSame(ArrayRef<Value *> VL) const {
      assert(VL.size() == Scalars.size() && "Invalid size");
      return std::equal(VL.begin(), VL.end(), Scalars.begin());
    }

    /// A vector of scalars.
    ValueList Scalars;

    /// The Scalars are vectorized into this value. It is initialized to Null.
    Value *VectorizedValue;

    /// Do we need to gather this sequence ?
    bool NeedToGather;
  };

  /// Create a new VectorizableTree entry.
  TreeEntry *newTreeEntry(ArrayRef<Value *> VL, bool Vectorized) {
    VectorizableTree.emplace_back();
    int idx = VectorizableTree.size() - 1;
    TreeEntry *Last = &VectorizableTree[idx];
    Last->Scalars.insert(Last->Scalars.begin(), VL.begin(), VL.end());
    Last->NeedToGather = !Vectorized;
    if (Vectorized) {
      for (int i = 0, e = VL.size(); i != e; ++i) {
        assert(!ScalarToTreeEntry.count(VL[i]) && "Scalar already in tree!");
        ScalarToTreeEntry[VL[i]] = idx;
      }
    } else {
      MustGather.insert(VL.begin(), VL.end());
    }
    return Last;
  }

  /// -- Vectorization State --
  /// Holds all of the tree entries.
  std::vector<TreeEntry> VectorizableTree;

  /// Maps a specific scalar to its tree entry.
  SmallDenseMap<Value*, int> ScalarToTreeEntry;

  /// A list of scalars that we found that we need to keep as scalars.
  ValueSet MustGather;

  /// This POD struct describes one external user in the vectorized tree.
  struct ExternalUser {
    ExternalUser (Value *S, llvm::User *U, int L) :
      Scalar(S), User(U), Lane(L){}
    // Which scalar in our function.
    Value *Scalar;
    // Which user that uses the scalar.
    llvm::User *User;
    // Which lane does the scalar belong to.
    int Lane;
  };
  typedef SmallVector<ExternalUser, 16> UserList;

  /// Checks if two instructions may access the same memory.
  ///
  /// \p Loc1 is the location of \p Inst1. It is passed explicitly because it
  /// is invariant in the calling loop.
  bool isAliased(const MemoryLocation &Loc1, Instruction *Inst1,
                 Instruction *Inst2) {

    // First check if the result is already in the cache.
    AliasCacheKey key = std::make_pair(Inst1, Inst2);
    Optional<bool> &result = AliasCache[key];
    if (result.hasValue()) {
      return result.getValue();
    }
    MemoryLocation Loc2 = getLocation(Inst2, AA);
    bool aliased = true;
    if (Loc1.Ptr && Loc2.Ptr && isSimple(Inst1) && isSimple(Inst2)) {
      // Do the alias check.
      aliased = AA->alias(Loc1, Loc2);
    }
    // Store the result in the cache.
    result = aliased;
    return aliased;
  }

  typedef std::pair<Instruction *, Instruction *> AliasCacheKey;

  /// Cache for alias results.
  /// TODO: consider moving this to the AliasAnalysis itself.
  DenseMap<AliasCacheKey, Optional<bool>> AliasCache;

  /// Removes an instruction from its block and eventually deletes it.
  /// It's like Instruction::eraseFromParent() except that the actual deletion
  /// is delayed until BoUpSLP is destructed.
  /// This is required to ensure that there are no incorrect collisions in the
  /// AliasCache, which can happen if a new instruction is allocated at the
  /// same address as a previously deleted instruction.
  void eraseInstruction(Instruction *I) {
    I->removeFromParent();
    I->dropAllReferences();
    DeletedInstructions.push_back(std::unique_ptr<Instruction>(I));
  }

  /// Temporary store for deleted instructions. Instructions will be deleted
  /// eventually when the BoUpSLP is destructed.
  SmallVector<std::unique_ptr<Instruction>, 8> DeletedInstructions;

  /// A list of values that need to extracted out of the tree.
  /// This list holds pairs of (Internal Scalar : External User).
  UserList ExternalUses;

  /// Values used only by @llvm.assume calls.
  SmallPtrSet<const Value *, 32> EphValues;

  /// Holds all of the instructions that we gathered.
  SetVector<Instruction *> GatherSeq;
  /// A list of blocks that we are going to CSE.
  SetVector<BasicBlock *> CSEBlocks;

  /// Contains all scheduling relevant data for an instruction.
  /// A ScheduleData either represents a single instruction or a member of an
  /// instruction bundle (= a group of instructions which is combined into a
  /// vector instruction).
  struct ScheduleData {

    // The initial value for the dependency counters. It means that the
    // dependencies are not calculated yet.
    enum { InvalidDeps = -1 };

    ScheduleData()
        : Inst(nullptr), FirstInBundle(nullptr), NextInBundle(nullptr),
          NextLoadStore(nullptr), SchedulingRegionID(0), SchedulingPriority(0),
          Dependencies(InvalidDeps), UnscheduledDeps(InvalidDeps),
          UnscheduledDepsInBundle(InvalidDeps), IsScheduled(false) {}

    void init(int BlockSchedulingRegionID) {
      FirstInBundle = this;
      NextInBundle = nullptr;
      NextLoadStore = nullptr;
      IsScheduled = false;
      SchedulingRegionID = BlockSchedulingRegionID;
      UnscheduledDepsInBundle = UnscheduledDeps;
      clearDependencies();
    }

    /// Returns true if the dependency information has been calculated.
    bool hasValidDependencies() const { return Dependencies != InvalidDeps; }

    /// Returns true for single instructions and for bundle representatives
    /// (= the head of a bundle).
    bool isSchedulingEntity() const { return FirstInBundle == this; }

    /// Returns true if it represents an instruction bundle and not only a
    /// single instruction.
    bool isPartOfBundle() const {
      return NextInBundle != nullptr || FirstInBundle != this;
    }

    /// Returns true if it is ready for scheduling, i.e. it has no more
    /// unscheduled depending instructions/bundles.
    bool isReady() const {
      assert(isSchedulingEntity() &&
             "can't consider non-scheduling entity for ready list");
      return UnscheduledDepsInBundle == 0 && !IsScheduled;
    }

    /// Modifies the number of unscheduled dependencies, also updating it for
    /// the whole bundle.
    int incrementUnscheduledDeps(int Incr) {
      UnscheduledDeps += Incr;
      return FirstInBundle->UnscheduledDepsInBundle += Incr;
    }

    /// Sets the number of unscheduled dependencies to the number of
    /// dependencies.
    void resetUnscheduledDeps() {
      incrementUnscheduledDeps(Dependencies - UnscheduledDeps);
    }

    /// Clears all dependency information.
    void clearDependencies() {
      Dependencies = InvalidDeps;
      resetUnscheduledDeps();
      MemoryDependencies.clear();
    }

    void dump(raw_ostream &os) const {
      if (!isSchedulingEntity()) {
        os << "/ " << *Inst;
      } else if (NextInBundle) {
        os << '[' << *Inst;
        ScheduleData *SD = NextInBundle;
        while (SD) {
          os << ';' << *SD->Inst;
          SD = SD->NextInBundle;
        }
        os << ']';
      } else {
        os << *Inst;
      }
    }

    Instruction *Inst;

    /// Points to the head in an instruction bundle (and always to this for
    /// single instructions).
    ScheduleData *FirstInBundle;

    /// Single linked list of all instructions in a bundle. Null if it is a
    /// single instruction.
    ScheduleData *NextInBundle;

    /// Single linked list of all memory instructions (e.g. load, store, call)
    /// in the block - until the end of the scheduling region.
    ScheduleData *NextLoadStore;

    /// The dependent memory instructions.
    /// This list is derived on demand in calculateDependencies().
    SmallVector<ScheduleData *, 4> MemoryDependencies;

    /// This ScheduleData is in the current scheduling region if this matches
    /// the current SchedulingRegionID of BlockScheduling.
    int SchedulingRegionID;

    /// Used for getting a "good" final ordering of instructions.
    int SchedulingPriority;

    /// The number of dependencies. Constitutes of the number of users of the
    /// instruction plus the number of dependent memory instructions (if any).
    /// This value is calculated on demand.
    /// If InvalidDeps, the number of dependencies is not calculated yet.
    ///
    int Dependencies;

    /// The number of dependencies minus the number of dependencies of scheduled
    /// instructions. As soon as this is zero, the instruction/bundle gets ready
    /// for scheduling.
    /// Note that this is negative as long as Dependencies is not calculated.
    int UnscheduledDeps;

    /// The sum of UnscheduledDeps in a bundle. Equals to UnscheduledDeps for
    /// single instructions.
    int UnscheduledDepsInBundle;

    /// True if this instruction is scheduled (or considered as scheduled in the
    /// dry-run).
    bool IsScheduled;
  };

#ifndef NDEBUG
  friend inline raw_ostream &operator<<(raw_ostream &os,
                                        const BoUpSLP::ScheduleData &SD) {
    SD.dump(os);
    return os;
  }
#endif

  /// Contains all scheduling data for a basic block.
  ///
  struct BlockScheduling {

    BlockScheduling(BasicBlock *BB)
        : BB(BB), ChunkSize(BB->size()), ChunkPos(ChunkSize),
          ScheduleStart(nullptr), ScheduleEnd(nullptr),
          FirstLoadStoreInRegion(nullptr), LastLoadStoreInRegion(nullptr),
          ScheduleRegionSize(0),
          ScheduleRegionSizeLimit(ScheduleRegionSizeBudget),
          // Make sure that the initial SchedulingRegionID is greater than the
          // initial SchedulingRegionID in ScheduleData (which is 0).
          SchedulingRegionID(1) {}

    void clear() {
      ReadyInsts.clear();
      ScheduleStart = nullptr;
      ScheduleEnd = nullptr;
      FirstLoadStoreInRegion = nullptr;
      LastLoadStoreInRegion = nullptr;

      // Reduce the maximum schedule region size by the size of the
      // previous scheduling run.
      ScheduleRegionSizeLimit -= ScheduleRegionSize;
      if (ScheduleRegionSizeLimit < MinScheduleRegionSize)
        ScheduleRegionSizeLimit = MinScheduleRegionSize;
      ScheduleRegionSize = 0;

      // Make a new scheduling region, i.e. all existing ScheduleData is not
      // in the new region yet.
      ++SchedulingRegionID;
    }

    ScheduleData *getScheduleData(Value *V) {
      ScheduleData *SD = ScheduleDataMap[V];
      if (SD && SD->SchedulingRegionID == SchedulingRegionID)
        return SD;
      return nullptr;
    }

    bool isInSchedulingRegion(ScheduleData *SD) {
      return SD->SchedulingRegionID == SchedulingRegionID;
    }

    /// Marks an instruction as scheduled and puts all dependent ready
    /// instructions into the ready-list.
    template <typename ReadyListType>
    void schedule(ScheduleData *SD, ReadyListType &ReadyList) {
      SD->IsScheduled = true;
      DEBUG(dbgs() << "SLP:   schedule " << *SD << "\n");

      ScheduleData *BundleMember = SD;
      while (BundleMember) {
        // Handle the def-use chain dependencies.
        for (Use &U : BundleMember->Inst->operands()) {
          ScheduleData *OpDef = getScheduleData(U.get());
          if (OpDef && OpDef->hasValidDependencies() &&
              OpDef->incrementUnscheduledDeps(-1) == 0) {
            // There are no more unscheduled dependencies after decrementing,
            // so we can put the dependent instruction into the ready list.
            ScheduleData *DepBundle = OpDef->FirstInBundle;
            assert(!DepBundle->IsScheduled &&
                   "already scheduled bundle gets ready");
            ReadyList.insert(DepBundle);
            DEBUG(dbgs() << "SLP:    gets ready (def): " << *DepBundle << "\n");
          }
        }
        // Handle the memory dependencies.
        for (ScheduleData *MemoryDepSD : BundleMember->MemoryDependencies) {
          if (MemoryDepSD->incrementUnscheduledDeps(-1) == 0) {
            // There are no more unscheduled dependencies after decrementing,
            // so we can put the dependent instruction into the ready list.
            ScheduleData *DepBundle = MemoryDepSD->FirstInBundle;
            assert(!DepBundle->IsScheduled &&
                   "already scheduled bundle gets ready");
            ReadyList.insert(DepBundle);
            DEBUG(dbgs() << "SLP:    gets ready (mem): " << *DepBundle << "\n");
          }
        }
        BundleMember = BundleMember->NextInBundle;
      }
    }

    /// Put all instructions into the ReadyList which are ready for scheduling.
    template <typename ReadyListType>
    void initialFillReadyList(ReadyListType &ReadyList) {
      for (auto *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode()) {
        ScheduleData *SD = getScheduleData(I);
        if (SD->isSchedulingEntity() && SD->isReady()) {
          ReadyList.insert(SD);
          DEBUG(dbgs() << "SLP:    initially in ready list: " << *I << "\n");
        }
      }
    }

    /// Checks if a bundle of instructions can be scheduled, i.e. has no
    /// cyclic dependencies. This is only a dry-run, no instructions are
    /// actually moved at this stage.
    bool tryScheduleBundle(ArrayRef<Value *> VL, BoUpSLP *SLP);

    /// Un-bundles a group of instructions.
    void cancelScheduling(ArrayRef<Value *> VL);

    /// Extends the scheduling region so that V is inside the region.
    /// \returns true if the region size is within the limit.
    bool extendSchedulingRegion(Value *V);

    /// Initialize the ScheduleData structures for new instructions in the
    /// scheduling region.
    void initScheduleData(Instruction *FromI, Instruction *ToI,
                          ScheduleData *PrevLoadStore,
                          ScheduleData *NextLoadStore);

    /// Updates the dependency information of a bundle and of all instructions/
    /// bundles which depend on the original bundle.
    void calculateDependencies(ScheduleData *SD, bool InsertInReadyList,
                               BoUpSLP *SLP);

    /// Sets all instruction in the scheduling region to un-scheduled.
    void resetSchedule();

    BasicBlock *BB;

    /// Simple memory allocation for ScheduleData.
    std::vector<std::unique_ptr<ScheduleData[]>> ScheduleDataChunks;

    /// The size of a ScheduleData array in ScheduleDataChunks.
    int ChunkSize;

    /// The allocator position in the current chunk, which is the last entry
    /// of ScheduleDataChunks.
    int ChunkPos;

    /// Attaches ScheduleData to Instruction.
    /// Note that the mapping survives during all vectorization iterations, i.e.
    /// ScheduleData structures are recycled.
    DenseMap<Value *, ScheduleData *> ScheduleDataMap;

    struct ReadyList : SmallVector<ScheduleData *, 8> {
      void insert(ScheduleData *SD) { push_back(SD); }
    };

    /// The ready-list for scheduling (only used for the dry-run).
    ReadyList ReadyInsts;

    /// The first instruction of the scheduling region.
    Instruction *ScheduleStart;

    /// The first instruction _after_ the scheduling region.
    Instruction *ScheduleEnd;

    /// The first memory accessing instruction in the scheduling region
    /// (can be null).
    ScheduleData *FirstLoadStoreInRegion;

    /// The last memory accessing instruction in the scheduling region
    /// (can be null).
    ScheduleData *LastLoadStoreInRegion;

    /// The current size of the scheduling region.
    int ScheduleRegionSize;

    /// The maximum size allowed for the scheduling region.
    int ScheduleRegionSizeLimit;

    /// The ID of the scheduling region. For a new vectorization iteration this
    /// is incremented which "removes" all ScheduleData from the region.
    int SchedulingRegionID;
  };

  /// Attaches the BlockScheduling structures to basic blocks.
  MapVector<BasicBlock *, std::unique_ptr<BlockScheduling>> BlocksSchedules;

  /// Performs the "real" scheduling. Done before vectorization is actually
  /// performed in a basic block.
  void scheduleBlock(BlockScheduling *BS);

  /// List of users to ignore during scheduling and that don't need extracting.
  ArrayRef<Value *> UserIgnoreList;

  // Number of load bundles that contain consecutive loads.
  int NumLoadsWantToKeepOrder;

  // Number of load bundles that contain consecutive loads in reversed order.
  int NumLoadsWantToChangeOrder;

  // Analysis and block reference.
  Function *F;
  ScalarEvolution *SE;
  TargetTransformInfo *TTI;
  TargetLibraryInfo *TLI;
  AliasAnalysis *AA;
  LoopInfo *LI;
  DominatorTree *DT;
  AssumptionCache *AC;
  DemandedBits *DB;
  const DataLayout *DL;
  unsigned MaxVecRegSize; // This is set by TTI or overridden by cl::opt.
  unsigned MinVecRegSize; // Set by cl::opt (default: 128).
  /// Instruction builder to construct the vectorized tree.
  IRBuilder<> Builder;

  /// A map of scalar integer values to the smallest bit width with which they
  /// can legally be represented. The values map to (width, signed) pairs,
  /// where "width" indicates the minimum bit width and "signed" is True if the
  /// value must be signed-extended, rather than zero-extended, back to its
  /// original width.
  MapVector<Value *, std::pair<uint64_t, bool>> MinBWs;
};

} // end namespace llvm
} // end namespace slpvectorizer

void BoUpSLP::buildTree(ArrayRef<Value *> Roots,
                        ArrayRef<Value *> UserIgnoreLst) {
  deleteTree();
  UserIgnoreList = UserIgnoreLst;
  if (!allSameType(Roots))
    return;
  buildTree_rec(Roots, 0);

  // Collect the values that we need to extract from the tree.
  for (TreeEntry &EIdx : VectorizableTree) {
    TreeEntry *Entry = &EIdx;

    // For each lane:
    for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
      Value *Scalar = Entry->Scalars[Lane];

      // No need to handle users of gathered values.
      if (Entry->NeedToGather)
        continue;

      for (User *U : Scalar->users()) {
        DEBUG(dbgs() << "SLP: Checking user:" << *U << ".\n");

        Instruction *UserInst = dyn_cast<Instruction>(U);
        if (!UserInst)
          continue;

        // Skip in-tree scalars that become vectors
        if (ScalarToTreeEntry.count(U)) {
          int Idx = ScalarToTreeEntry[U];
          TreeEntry *UseEntry = &VectorizableTree[Idx];
          Value *UseScalar = UseEntry->Scalars[0];
          // Some in-tree scalars will remain as scalar in vectorized
          // instructions. If that is the case, the one in Lane 0 will
          // be used.
          if (UseScalar != U ||
              !InTreeUserNeedToExtract(Scalar, UserInst, TLI)) {
            DEBUG(dbgs() << "SLP: \tInternal user will be removed:" << *U
                         << ".\n");
            assert(!VectorizableTree[Idx].NeedToGather && "Bad state");
            continue;
          }
        }

        // Ignore users in the user ignore list.
        if (is_contained(UserIgnoreList, UserInst))
          continue;

        DEBUG(dbgs() << "SLP: Need to extract:" << *U << " from lane " <<
              Lane << " from " << *Scalar << ".\n");
        ExternalUses.push_back(ExternalUser(Scalar, U, Lane));
      }
    }
  }
}


void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
  bool isAltShuffle = false;
  assert((allConstant(VL) || allSameType(VL)) && "Invalid types!");

  if (Depth == RecursionMaxDepth) {
    DEBUG(dbgs() << "SLP: Gathering due to max recursion depth.\n");
    newTreeEntry(VL, false);
    return;
  }

  // Don't handle vectors.
  if (VL[0]->getType()->isVectorTy()) {
    DEBUG(dbgs() << "SLP: Gathering due to vector type.\n");
    newTreeEntry(VL, false);
    return;
  }

  if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
    if (SI->getValueOperand()->getType()->isVectorTy()) {
      DEBUG(dbgs() << "SLP: Gathering due to store vector type.\n");
      newTreeEntry(VL, false);
      return;
    }
  unsigned Opcode = getSameOpcode(VL);

  // Check that this shuffle vector refers to the alternate
  // sequence of opcodes.
  if (Opcode == Instruction::ShuffleVector) {
    Instruction *I0 = dyn_cast<Instruction>(VL[0]);
    unsigned Op = I0->getOpcode();
    if (Op != Instruction::ShuffleVector)
      isAltShuffle = true;
  }

  // If all of the operands are identical or constant we have a simple solution.
  if (allConstant(VL) || isSplat(VL) || !allSameBlock(VL) || !Opcode) {
    DEBUG(dbgs() << "SLP: Gathering due to C,S,B,O. \n");
    newTreeEntry(VL, false);
    return;
  }

  // We now know that this is a vector of instructions of the same type from
  // the same block.

  // Don't vectorize ephemeral values.
  for (unsigned i = 0, e = VL.size(); i != e; ++i) {
    if (EphValues.count(VL[i])) {
      DEBUG(dbgs() << "SLP: The instruction (" << *VL[i] <<
            ") is ephemeral.\n");
      newTreeEntry(VL, false);
      return;
    }
  }

  // Check if this is a duplicate of another entry.
  if (ScalarToTreeEntry.count(VL[0])) {
    int Idx = ScalarToTreeEntry[VL[0]];
    TreeEntry *E = &VectorizableTree[Idx];
    for (unsigned i = 0, e = VL.size(); i != e; ++i) {
      DEBUG(dbgs() << "SLP: \tChecking bundle: " << *VL[i] << ".\n");
      if (E->Scalars[i] != VL[i]) {
        DEBUG(dbgs() << "SLP: Gathering due to partial overlap.\n");
        newTreeEntry(VL, false);
        return;
      }
    }
    DEBUG(dbgs() << "SLP: Perfect diamond merge at " << *VL[0] << ".\n");
    return;
  }

  // Check that none of the instructions in the bundle are already in the tree.
  for (unsigned i = 0, e = VL.size(); i != e; ++i) {
    if (ScalarToTreeEntry.count(VL[i])) {
      DEBUG(dbgs() << "SLP: The instruction (" << *VL[i] <<
            ") is already in tree.\n");
      newTreeEntry(VL, false);
      return;
    }
  }

  // If any of the scalars is marked as a value that needs to stay scalar then
  // we need to gather the scalars.
  for (unsigned i = 0, e = VL.size(); i != e; ++i) {
    if (MustGather.count(VL[i])) {
      DEBUG(dbgs() << "SLP: Gathering due to gathered scalar.\n");
      newTreeEntry(VL, false);
      return;
    }
  }

  // Check that all of the users of the scalars that we want to vectorize are
  // schedulable.
  Instruction *VL0 = cast<Instruction>(VL[0]);
  BasicBlock *BB = cast<Instruction>(VL0)->getParent();

  if (!DT->isReachableFromEntry(BB)) {
    // Don't go into unreachable blocks. They may contain instructions with
    // dependency cycles which confuse the final scheduling.
    DEBUG(dbgs() << "SLP: bundle in unreachable block.\n");
    newTreeEntry(VL, false);
    return;
  }

  // Check that every instructions appears once in this bundle.
  for (unsigned i = 0, e = VL.size(); i < e; ++i)
    for (unsigned j = i+1; j < e; ++j)
      if (VL[i] == VL[j]) {
        DEBUG(dbgs() << "SLP: Scalar used twice in bundle.\n");
        newTreeEntry(VL, false);
        return;
      }

  auto &BSRef = BlocksSchedules[BB];
  if (!BSRef) {
    BSRef = llvm::make_unique<BlockScheduling>(BB);
  }
  BlockScheduling &BS = *BSRef.get();

  if (!BS.tryScheduleBundle(VL, this)) {
    DEBUG(dbgs() << "SLP: We are not able to schedule this bundle!\n");
    assert((!BS.getScheduleData(VL[0]) ||
            !BS.getScheduleData(VL[0])->isPartOfBundle()) &&
           "tryScheduleBundle should cancelScheduling on failure");
    newTreeEntry(VL, false);
    return;
  }
  DEBUG(dbgs() << "SLP: We are able to schedule this bundle.\n");

  switch (Opcode) {
    case Instruction::PHI: {
      PHINode *PH = dyn_cast<PHINode>(VL0);

      // Check for terminator values (e.g. invoke).
      for (unsigned j = 0; j < VL.size(); ++j)
        for (unsigned i = 0, e = PH->getNumIncomingValues(); i < e; ++i) {
          TerminatorInst *Term = dyn_cast<TerminatorInst>(
              cast<PHINode>(VL[j])->getIncomingValueForBlock(PH->getIncomingBlock(i)));
          if (Term) {
            DEBUG(dbgs() << "SLP: Need to swizzle PHINodes (TerminatorInst use).\n");
            BS.cancelScheduling(VL);
            newTreeEntry(VL, false);
            return;
          }
        }

      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of PHINodes.\n");

      for (unsigned i = 0, e = PH->getNumIncomingValues(); i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<PHINode>(j)->getIncomingValueForBlock(
              PH->getIncomingBlock(i)));

        buildTree_rec(Operands, Depth + 1);
      }
      return;
    }
    case Instruction::ExtractValue:
    case Instruction::ExtractElement: {
      bool Reuse = canReuseExtract(VL, Opcode);
      if (Reuse) {
        DEBUG(dbgs() << "SLP: Reusing extract sequence.\n");
      } else {
        BS.cancelScheduling(VL);
      }
      newTreeEntry(VL, Reuse);
      return;
    }
    case Instruction::Load: {
      // Check that a vectorized load would load the same memory as a scalar
      // load.
      // For example we don't want vectorize loads that are smaller than 8 bit.
      // Even though we have a packed struct {<i2, i2, i2, i2>} LLVM treats
      // loading/storing it as an i8 struct. If we vectorize loads/stores from
      // such a struct we read/write packed bits disagreeing with the
      // unvectorized version.
      Type *ScalarTy = VL[0]->getType();

      if (DL->getTypeSizeInBits(ScalarTy) !=
          DL->getTypeAllocSizeInBits(ScalarTy)) {
        BS.cancelScheduling(VL);
        newTreeEntry(VL, false);
        DEBUG(dbgs() << "SLP: Gathering loads of non-packed type.\n");
        return;
      }

      // Make sure all loads in the bundle are simple - we can't vectorize
      // atomic or volatile loads.
      for (unsigned i = 0, e = VL.size() - 1; i < e; ++i) {
        LoadInst *L = cast<LoadInst>(VL[i]);
        if (!L->isSimple()) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: Gathering non-simple loads.\n");
          return;
        }
      }

      // Check if the loads are consecutive, reversed, or neither.
      // TODO: What we really want is to sort the loads, but for now, check
      // the two likely directions.
      bool Consecutive = true;
      bool ReverseConsecutive = true;
      for (unsigned i = 0, e = VL.size() - 1; i < e; ++i) {
        if (!isConsecutiveAccess(VL[i], VL[i + 1], *DL, *SE)) {
          Consecutive = false;
          break;
        } else {
          ReverseConsecutive = false;
        }
      }

      if (Consecutive) {
        ++NumLoadsWantToKeepOrder;
        newTreeEntry(VL, true);
        DEBUG(dbgs() << "SLP: added a vector of loads.\n");
        return;
      }

      // If none of the load pairs were consecutive when checked in order,
      // check the reverse order.
      if (ReverseConsecutive)
        for (unsigned i = VL.size() - 1; i > 0; --i)
          if (!isConsecutiveAccess(VL[i], VL[i - 1], *DL, *SE)) {
            ReverseConsecutive = false;
            break;
          }

      BS.cancelScheduling(VL);
      newTreeEntry(VL, false);

      if (ReverseConsecutive) {
        ++NumLoadsWantToChangeOrder;
        DEBUG(dbgs() << "SLP: Gathering reversed loads.\n");
      } else {
        DEBUG(dbgs() << "SLP: Gathering non-consecutive loads.\n");
      }
      return;
    }
    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: {
      Type *SrcTy = VL0->getOperand(0)->getType();
      for (unsigned i = 0; i < VL.size(); ++i) {
        Type *Ty = cast<Instruction>(VL[i])->getOperand(0)->getType();
        if (Ty != SrcTy || !isValidElementType(Ty)) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: Gathering casts with different src types.\n");
          return;
        }
      }
      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of casts.\n");

      for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<Instruction>(j)->getOperand(i));

        buildTree_rec(Operands, Depth+1);
      }
      return;
    }
    case Instruction::ICmp:
    case Instruction::FCmp: {
      // Check that all of the compares have the same predicate.
      CmpInst::Predicate P0 = cast<CmpInst>(VL0)->getPredicate();
      Type *ComparedTy = cast<Instruction>(VL[0])->getOperand(0)->getType();
      for (unsigned i = 1, e = VL.size(); i < e; ++i) {
        CmpInst *Cmp = cast<CmpInst>(VL[i]);
        if (Cmp->getPredicate() != P0 ||
            Cmp->getOperand(0)->getType() != ComparedTy) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: Gathering cmp with different predicate.\n");
          return;
        }
      }

      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of compares.\n");

      for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<Instruction>(j)->getOperand(i));

        buildTree_rec(Operands, Depth+1);
      }
      return;
    }
    case Instruction::Select:
    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: {
      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of bin op.\n");

      // Sort operands of the instructions so that each side is more likely to
      // have the same opcode.
      if (isa<BinaryOperator>(VL0) && VL0->isCommutative()) {
        ValueList Left, Right;
        reorderInputsAccordingToOpcode(VL, Left, Right);
        buildTree_rec(Left, Depth + 1);
        buildTree_rec(Right, Depth + 1);
        return;
      }

      for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<Instruction>(j)->getOperand(i));

        buildTree_rec(Operands, Depth+1);
      }
      return;
    }
    case Instruction::GetElementPtr: {
      // We don't combine GEPs with complicated (nested) indexing.
      for (unsigned j = 0; j < VL.size(); ++j) {
        if (cast<Instruction>(VL[j])->getNumOperands() != 2) {
          DEBUG(dbgs() << "SLP: not-vectorizable GEP (nested indexes).\n");
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          return;
        }
      }

      // We can't combine several GEPs into one vector if they operate on
      // different types.
      Type *Ty0 = cast<Instruction>(VL0)->getOperand(0)->getType();
      for (unsigned j = 0; j < VL.size(); ++j) {
        Type *CurTy = cast<Instruction>(VL[j])->getOperand(0)->getType();
        if (Ty0 != CurTy) {
          DEBUG(dbgs() << "SLP: not-vectorizable GEP (different types).\n");
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          return;
        }
      }

      // We don't combine GEPs with non-constant indexes.
      for (unsigned j = 0; j < VL.size(); ++j) {
        auto Op = cast<Instruction>(VL[j])->getOperand(1);
        if (!isa<ConstantInt>(Op)) {
          DEBUG(
              dbgs() << "SLP: not-vectorizable GEP (non-constant indexes).\n");
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          return;
        }
      }

      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of GEPs.\n");
      for (unsigned i = 0, e = 2; i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<Instruction>(j)->getOperand(i));

        buildTree_rec(Operands, Depth + 1);
      }
      return;
    }
    case Instruction::Store: {
      // Check if the stores are consecutive or of we need to swizzle them.
      for (unsigned i = 0, e = VL.size() - 1; i < e; ++i)
        if (!isConsecutiveAccess(VL[i], VL[i + 1], *DL, *SE)) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: Non-consecutive store.\n");
          return;
        }

      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a vector of stores.\n");

      ValueList Operands;
      for (Value *j : VL)
        Operands.push_back(cast<Instruction>(j)->getOperand(0));

      buildTree_rec(Operands, Depth + 1);
      return;
    }
    case Instruction::Call: {
      // Check if the calls are all to the same vectorizable intrinsic.
      CallInst *CI = cast<CallInst>(VL[0]);
      // Check if this is an Intrinsic call or something that can be
      // represented by an intrinsic call
      Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
      if (!isTriviallyVectorizable(ID)) {
        BS.cancelScheduling(VL);
        newTreeEntry(VL, false);
        DEBUG(dbgs() << "SLP: Non-vectorizable call.\n");
        return;
      }
      Function *Int = CI->getCalledFunction();
      Value *A1I = nullptr;
      if (hasVectorInstrinsicScalarOpd(ID, 1))
        A1I = CI->getArgOperand(1);
      for (unsigned i = 1, e = VL.size(); i != e; ++i) {
        CallInst *CI2 = dyn_cast<CallInst>(VL[i]);
        if (!CI2 || CI2->getCalledFunction() != Int ||
            getVectorIntrinsicIDForCall(CI2, TLI) != ID ||
            !CI->hasIdenticalOperandBundleSchema(*CI2)) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: mismatched calls:" << *CI << "!=" << *VL[i]
                       << "\n");
          return;
        }
        // ctlz,cttz and powi are special intrinsics whose second argument
        // should be same in order for them to be vectorized.
        if (hasVectorInstrinsicScalarOpd(ID, 1)) {
          Value *A1J = CI2->getArgOperand(1);
          if (A1I != A1J) {
            BS.cancelScheduling(VL);
            newTreeEntry(VL, false);
            DEBUG(dbgs() << "SLP: mismatched arguments in call:" << *CI
                         << " argument "<< A1I<<"!=" << A1J
                         << "\n");
            return;
          }
        }
        // Verify that the bundle operands are identical between the two calls.
        if (CI->hasOperandBundles() &&
            !std::equal(CI->op_begin() + CI->getBundleOperandsStartIndex(),
                        CI->op_begin() + CI->getBundleOperandsEndIndex(),
                        CI2->op_begin() + CI2->getBundleOperandsStartIndex())) {
          BS.cancelScheduling(VL);
          newTreeEntry(VL, false);
          DEBUG(dbgs() << "SLP: mismatched bundle operands in calls:" << *CI << "!="
                       << *VL[i] << '\n');
          return;
        }
      }

      newTreeEntry(VL, true);
      for (unsigned i = 0, e = CI->getNumArgOperands(); i != e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL) {
          CallInst *CI2 = dyn_cast<CallInst>(j);
          Operands.push_back(CI2->getArgOperand(i));
        }
        buildTree_rec(Operands, Depth + 1);
      }
      return;
    }
    case Instruction::ShuffleVector: {
      // If this is not an alternate sequence of opcode like add-sub
      // then do not vectorize this instruction.
      if (!isAltShuffle) {
        BS.cancelScheduling(VL);
        newTreeEntry(VL, false);
        DEBUG(dbgs() << "SLP: ShuffleVector are not vectorized.\n");
        return;
      }
      newTreeEntry(VL, true);
      DEBUG(dbgs() << "SLP: added a ShuffleVector op.\n");

      // Reorder operands if reordering would enable vectorization.
      if (isa<BinaryOperator>(VL0)) {
        ValueList Left, Right;
        reorderAltShuffleOperands(VL, Left, Right);
        buildTree_rec(Left, Depth + 1);
        buildTree_rec(Right, Depth + 1);
        return;
      }

      for (unsigned i = 0, e = VL0->getNumOperands(); i < e; ++i) {
        ValueList Operands;
        // Prepare the operand vector.
        for (Value *j : VL)
          Operands.push_back(cast<Instruction>(j)->getOperand(i));

        buildTree_rec(Operands, Depth + 1);
      }
      return;
    }
    default:
      BS.cancelScheduling(VL);
      newTreeEntry(VL, false);
      DEBUG(dbgs() << "SLP: Gathering unknown instruction.\n");
      return;
  }
}

unsigned BoUpSLP::canMapToVector(Type *T, const DataLayout &DL) const {
  unsigned N;
  Type *EltTy;
  auto *ST = dyn_cast<StructType>(T);
  if (ST) {
    N = ST->getNumElements();
    EltTy = *ST->element_begin();
  } else {
    N = cast<ArrayType>(T)->getNumElements();
    EltTy = cast<ArrayType>(T)->getElementType();
  }
  if (!isValidElementType(EltTy))
    return 0;
  uint64_t VTSize = DL.getTypeStoreSizeInBits(VectorType::get(EltTy, N));
  if (VTSize < MinVecRegSize || VTSize > MaxVecRegSize || VTSize != DL.getTypeStoreSizeInBits(T))
    return 0;
  if (ST) {
    // Check that struct is homogeneous.
    for (const auto *Ty : ST->elements())
      if (Ty != EltTy)
        return 0;
  }
  return N;
}

bool BoUpSLP::canReuseExtract(ArrayRef<Value *> VL, unsigned Opcode) const {
  assert(Opcode == Instruction::ExtractElement ||
         Opcode == Instruction::ExtractValue);
  assert(Opcode == getSameOpcode(VL) && "Invalid opcode");
  // Check if all of the extracts come from the same vector and from the
  // correct offset.
  Value *VL0 = VL[0];
  Instruction *E0 = cast<Instruction>(VL0);
  Value *Vec = E0->getOperand(0);

  // We have to extract from a vector/aggregate with the same number of elements.
  unsigned NElts;
  if (Opcode == Instruction::ExtractValue) {
    const DataLayout &DL = E0->getModule()->getDataLayout();
    NElts = canMapToVector(Vec->getType(), DL);
    if (!NElts)
      return false;
    // Check if load can be rewritten as load of vector.
    LoadInst *LI = dyn_cast<LoadInst>(Vec);
    if (!LI || !LI->isSimple() || !LI->hasNUses(VL.size()))
      return false;
  } else {
    NElts = Vec->getType()->getVectorNumElements();
  }

  if (NElts != VL.size())
    return false;

  // Check that all of the indices extract from the correct offset.
  if (!matchExtractIndex(E0, 0, Opcode))
    return false;

  for (unsigned i = 1, e = VL.size(); i < e; ++i) {
    Instruction *E = cast<Instruction>(VL[i]);
    if (!matchExtractIndex(E, i, Opcode))
      return false;
    if (E->getOperand(0) != Vec)
      return false;
  }

  return true;
}

int BoUpSLP::getEntryCost(TreeEntry *E) {
  ArrayRef<Value*> VL = E->Scalars;

  Type *ScalarTy = VL[0]->getType();
  if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
    ScalarTy = SI->getValueOperand()->getType();
  VectorType *VecTy = VectorType::get(ScalarTy, VL.size());

  // If we have computed a smaller type for the expression, update VecTy so
  // that the costs will be accurate.
  if (MinBWs.count(VL[0]))
    VecTy = VectorType::get(
        IntegerType::get(F->getContext(), MinBWs[VL[0]].first), VL.size());

  if (E->NeedToGather) {
    if (allConstant(VL))
      return 0;
    if (isSplat(VL)) {
      return TTI->getShuffleCost(TargetTransformInfo::SK_Broadcast, VecTy, 0);
    }
    return getGatherCost(E->Scalars);
  }
  unsigned Opcode = getSameOpcode(VL);
  assert(Opcode && allSameType(VL) && allSameBlock(VL) && "Invalid VL");
  Instruction *VL0 = cast<Instruction>(VL[0]);
  switch (Opcode) {
    case Instruction::PHI: {
      return 0;
    }
    case Instruction::ExtractValue:
    case Instruction::ExtractElement: {
      if (canReuseExtract(VL, Opcode)) {
        int DeadCost = 0;
        for (unsigned i = 0, e = VL.size(); i < e; ++i) {
          Instruction *E = cast<Instruction>(VL[i]);
          if (E->hasOneUse())
            // Take credit for instruction that will become dead.
            DeadCost +=
                TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, i);
        }
        return -DeadCost;
      }
      return getGatherCost(VecTy);
    }
    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: {
      Type *SrcTy = VL0->getOperand(0)->getType();

      // Calculate the cost of this instruction.
      int ScalarCost = VL.size() * TTI->getCastInstrCost(VL0->getOpcode(),
                                                         VL0->getType(), SrcTy);

      VectorType *SrcVecTy = VectorType::get(SrcTy, VL.size());
      int VecCost = TTI->getCastInstrCost(VL0->getOpcode(), VecTy, SrcVecTy);
      return VecCost - ScalarCost;
    }
    case Instruction::FCmp:
    case Instruction::ICmp:
    case Instruction::Select: {
      // Calculate the cost of this instruction.
      VectorType *MaskTy = VectorType::get(Builder.getInt1Ty(), VL.size());
      int ScalarCost = VecTy->getNumElements() *
          TTI->getCmpSelInstrCost(Opcode, ScalarTy, Builder.getInt1Ty());
      int VecCost = TTI->getCmpSelInstrCost(Opcode, VecTy, MaskTy);
      return VecCost - ScalarCost;
    }
    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: {
      // Certain instructions can be cheaper to vectorize if they have a
      // constant second vector operand.
      TargetTransformInfo::OperandValueKind Op1VK =
          TargetTransformInfo::OK_AnyValue;
      TargetTransformInfo::OperandValueKind Op2VK =
          TargetTransformInfo::OK_UniformConstantValue;
      TargetTransformInfo::OperandValueProperties Op1VP =
          TargetTransformInfo::OP_None;
      TargetTransformInfo::OperandValueProperties Op2VP =
          TargetTransformInfo::OP_None;

      // If all operands are exactly the same ConstantInt then set the
      // operand kind to OK_UniformConstantValue.
      // If instead not all operands are constants, then set the operand kind
      // to OK_AnyValue. If all operands are constants but not the same,
      // then set the operand kind to OK_NonUniformConstantValue.
      ConstantInt *CInt = nullptr;
      for (unsigned i = 0; i < VL.size(); ++i) {
        const Instruction *I = cast<Instruction>(VL[i]);
        if (!isa<ConstantInt>(I->getOperand(1))) {
          Op2VK = TargetTransformInfo::OK_AnyValue;
          break;
        }
        if (i == 0) {
          CInt = cast<ConstantInt>(I->getOperand(1));
          continue;
        }
        if (Op2VK == TargetTransformInfo::OK_UniformConstantValue &&
            CInt != cast<ConstantInt>(I->getOperand(1)))
          Op2VK = TargetTransformInfo::OK_NonUniformConstantValue;
      }
      // FIXME: Currently cost of model modification for division by power of
      // 2 is handled for X86 and AArch64. Add support for other targets.
      if (Op2VK == TargetTransformInfo::OK_UniformConstantValue && CInt &&
          CInt->getValue().isPowerOf2())
        Op2VP = TargetTransformInfo::OP_PowerOf2;

      int ScalarCost = VecTy->getNumElements() *
                       TTI->getArithmeticInstrCost(Opcode, ScalarTy, Op1VK,
                                                   Op2VK, Op1VP, Op2VP);
      int VecCost = TTI->getArithmeticInstrCost(Opcode, VecTy, Op1VK, Op2VK,
                                                Op1VP, Op2VP);
      return VecCost - ScalarCost;
    }
    case Instruction::GetElementPtr: {
      TargetTransformInfo::OperandValueKind Op1VK =
          TargetTransformInfo::OK_AnyValue;
      TargetTransformInfo::OperandValueKind Op2VK =
          TargetTransformInfo::OK_UniformConstantValue;

      int ScalarCost =
          VecTy->getNumElements() *
          TTI->getArithmeticInstrCost(Instruction::Add, ScalarTy, Op1VK, Op2VK);
      int VecCost =
          TTI->getArithmeticInstrCost(Instruction::Add, VecTy, Op1VK, Op2VK);

      return VecCost - ScalarCost;
    }
    case Instruction::Load: {
      // Cost of wide load - cost of scalar loads.
      unsigned alignment = dyn_cast<LoadInst>(VL0)->getAlignment();
      int ScalarLdCost = VecTy->getNumElements() *
            TTI->getMemoryOpCost(Instruction::Load, ScalarTy, alignment, 0);
      int VecLdCost = TTI->getMemoryOpCost(Instruction::Load,
                                           VecTy, alignment, 0);
      return VecLdCost - ScalarLdCost;
    }
    case Instruction::Store: {
      // We know that we can merge the stores. Calculate the cost.
      unsigned alignment = dyn_cast<StoreInst>(VL0)->getAlignment();
      int ScalarStCost = VecTy->getNumElements() *
            TTI->getMemoryOpCost(Instruction::Store, ScalarTy, alignment, 0);
      int VecStCost = TTI->getMemoryOpCost(Instruction::Store,
                                           VecTy, alignment, 0);
      return VecStCost - ScalarStCost;
    }
    case Instruction::Call: {
      CallInst *CI = cast<CallInst>(VL0);
      Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);

      // Calculate the cost of the scalar and vector calls.
      SmallVector<Type*, 4> ScalarTys, VecTys;
      for (unsigned op = 0, opc = CI->getNumArgOperands(); op!= opc; ++op) {
        ScalarTys.push_back(CI->getArgOperand(op)->getType());
        VecTys.push_back(VectorType::get(CI->getArgOperand(op)->getType(),
                                         VecTy->getNumElements()));
      }

      FastMathFlags FMF;
      if (auto *FPMO = dyn_cast<FPMathOperator>(CI))
        FMF = FPMO->getFastMathFlags();

      int ScalarCallCost = VecTy->getNumElements() *
          TTI->getIntrinsicInstrCost(ID, ScalarTy, ScalarTys, FMF);

      int VecCallCost = TTI->getIntrinsicInstrCost(ID, VecTy, VecTys, FMF);

      DEBUG(dbgs() << "SLP: Call cost "<< VecCallCost - ScalarCallCost
            << " (" << VecCallCost  << "-" <<  ScalarCallCost << ")"
            << " for " << *CI << "\n");

      return VecCallCost - ScalarCallCost;
    }
    case Instruction::ShuffleVector: {
      TargetTransformInfo::OperandValueKind Op1VK =
          TargetTransformInfo::OK_AnyValue;
      TargetTransformInfo::OperandValueKind Op2VK =
          TargetTransformInfo::OK_AnyValue;
      int ScalarCost = 0;
      int VecCost = 0;
      for (Value *i : VL) {
        Instruction *I = cast<Instruction>(i);
        if (!I)
          break;
        ScalarCost +=
            TTI->getArithmeticInstrCost(I->getOpcode(), ScalarTy, Op1VK, Op2VK);
      }
      // VecCost is equal to sum of the cost of creating 2 vectors
      // and the cost of creating shuffle.
      Instruction *I0 = cast<Instruction>(VL[0]);
      VecCost =
          TTI->getArithmeticInstrCost(I0->getOpcode(), VecTy, Op1VK, Op2VK);
      Instruction *I1 = cast<Instruction>(VL[1]);
      VecCost +=
          TTI->getArithmeticInstrCost(I1->getOpcode(), VecTy, Op1VK, Op2VK);
      VecCost +=
          TTI->getShuffleCost(TargetTransformInfo::SK_Alternate, VecTy, 0);
      return VecCost - ScalarCost;
    }
    default:
      llvm_unreachable("Unknown instruction");
  }
}

bool BoUpSLP::isFullyVectorizableTinyTree() {
  DEBUG(dbgs() << "SLP: Check whether the tree with height " <<
        VectorizableTree.size() << " is fully vectorizable .\n");

  // We only handle trees of heights 1 and 2.
  if (VectorizableTree.size() == 1 && !VectorizableTree[0].NeedToGather)
    return true;

  if (VectorizableTree.size() != 2)
    return false;

  // Handle splat and all-constants stores.
  if (!VectorizableTree[0].NeedToGather &&
      (allConstant(VectorizableTree[1].Scalars) ||
       isSplat(VectorizableTree[1].Scalars)))
    return true;

  // Gathering cost would be too much for tiny trees.
  if (VectorizableTree[0].NeedToGather || VectorizableTree[1].NeedToGather)
    return false;

  return true;
}

bool BoUpSLP::isTreeTinyAndNotFullyVectorizable() {

  // We can vectorize the tree if its size is greater than or equal to the
  // minimum size specified by the MinTreeSize command line option.
  if (VectorizableTree.size() >= MinTreeSize)
    return false;

  // If we have a tiny tree (a tree whose size is less than MinTreeSize), we
  // can vectorize it if we can prove it fully vectorizable.
  if (isFullyVectorizableTinyTree())
    return false;

  assert(VectorizableTree.empty()
             ? ExternalUses.empty()
             : true && "We shouldn't have any external users");

  // Otherwise, we can't vectorize the tree. It is both tiny and not fully
  // vectorizable.
  return true;
}

int BoUpSLP::getSpillCost() {
  // Walk from the bottom of the tree to the top, tracking which values are
  // live. When we see a call instruction that is not part of our tree,
  // query TTI to see if there is a cost to keeping values live over it
  // (for example, if spills and fills are required).
  unsigned BundleWidth = VectorizableTree.front().Scalars.size();
  int Cost = 0;

  SmallPtrSet<Instruction*, 4> LiveValues;
  Instruction *PrevInst = nullptr;

  for (const auto &N : VectorizableTree) {
    Instruction *Inst = dyn_cast<Instruction>(N.Scalars[0]);
    if (!Inst)
      continue;

    if (!PrevInst) {
      PrevInst = Inst;
      continue;
    }

    // Update LiveValues.
    LiveValues.erase(PrevInst);
    for (auto &J : PrevInst->operands()) {
      if (isa<Instruction>(&*J) && ScalarToTreeEntry.count(&*J))
        LiveValues.insert(cast<Instruction>(&*J));
    }

    DEBUG(
      dbgs() << "SLP: #LV: " << LiveValues.size();
      for (auto *X : LiveValues)
        dbgs() << " " << X->getName();
      dbgs() << ", Looking at ";
      Inst->dump();
      );

    // Now find the sequence of instructions between PrevInst and Inst.
    BasicBlock::reverse_iterator InstIt = ++Inst->getIterator().getReverse(),
                                 PrevInstIt =
                                     PrevInst->getIterator().getReverse();
    while (InstIt != PrevInstIt) {
      if (PrevInstIt == PrevInst->getParent()->rend()) {
        PrevInstIt = Inst->getParent()->rbegin();
        continue;
      }

      if (isa<CallInst>(&*PrevInstIt) && &*PrevInstIt != PrevInst) {
        SmallVector<Type*, 4> V;
        for (auto *II : LiveValues)
          V.push_back(VectorType::get(II->getType(), BundleWidth));
        Cost += TTI->getCostOfKeepingLiveOverCall(V);
      }

      ++PrevInstIt;
    }

    PrevInst = Inst;
  }

  return Cost;
}

int BoUpSLP::getTreeCost() {
  int Cost = 0;
  DEBUG(dbgs() << "SLP: Calculating cost for tree of size " <<
        VectorizableTree.size() << ".\n");

  unsigned BundleWidth = VectorizableTree[0].Scalars.size();

  for (TreeEntry &TE : VectorizableTree) {
    int C = getEntryCost(&TE);
    DEBUG(dbgs() << "SLP: Adding cost " << C << " for bundle that starts with "
                 << *TE.Scalars[0] << ".\n");
    Cost += C;
  }

  SmallSet<Value *, 16> ExtractCostCalculated;
  int ExtractCost = 0;
  for (ExternalUser &EU : ExternalUses) {
    // We only add extract cost once for the same scalar.
    if (!ExtractCostCalculated.insert(EU.Scalar).second)
      continue;

    // Uses by ephemeral values are free (because the ephemeral value will be
    // removed prior to code generation, and so the extraction will be
    // removed as well).
    if (EphValues.count(EU.User))
      continue;

    // If we plan to rewrite the tree in a smaller type, we will need to sign
    // extend the extracted value back to the original type. Here, we account
    // for the extract and the added cost of the sign extend if needed.
    auto *VecTy = VectorType::get(EU.Scalar->getType(), BundleWidth);
    auto *ScalarRoot = VectorizableTree[0].Scalars[0];
    if (MinBWs.count(ScalarRoot)) {
      auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
      auto Extend =
          MinBWs[ScalarRoot].second ? Instruction::SExt : Instruction::ZExt;
      VecTy = VectorType::get(MinTy, BundleWidth);
      ExtractCost += TTI->getExtractWithExtendCost(Extend, EU.Scalar->getType(),
                                                   VecTy, EU.Lane);
    } else {
      ExtractCost +=
          TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, EU.Lane);
    }
  }

  int SpillCost = getSpillCost();
  Cost += SpillCost + ExtractCost;

  DEBUG(dbgs() << "SLP: Spill Cost = " << SpillCost << ".\n"
               << "SLP: Extract Cost = " << ExtractCost << ".\n"
               << "SLP: Total Cost = " << Cost << ".\n");
  return Cost;
}

int BoUpSLP::getGatherCost(Type *Ty) {
  int Cost = 0;
  for (unsigned i = 0, e = cast<VectorType>(Ty)->getNumElements(); i < e; ++i)
    Cost += TTI->getVectorInstrCost(Instruction::InsertElement, Ty, i);
  return Cost;
}

int BoUpSLP::getGatherCost(ArrayRef<Value *> VL) {
  // Find the type of the operands in VL.
  Type *ScalarTy = VL[0]->getType();
  if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
    ScalarTy = SI->getValueOperand()->getType();
  VectorType *VecTy = VectorType::get(ScalarTy, VL.size());
  // Find the cost of inserting/extracting values from the vector.
  return getGatherCost(VecTy);
}

// Reorder commutative operations in alternate shuffle if the resulting vectors
// are consecutive loads. This would allow us to vectorize the tree.
// If we have something like-
// load a[0] - load b[0]
// load b[1] + load a[1]
// load a[2] - load b[2]
// load a[3] + load b[3]
// Reordering the second load b[1]  load a[1] would allow us to vectorize this
// code.
void BoUpSLP::reorderAltShuffleOperands(ArrayRef<Value *> VL,
                                        SmallVectorImpl<Value *> &Left,
                                        SmallVectorImpl<Value *> &Right) {
  // Push left and right operands of binary operation into Left and Right
  for (Value *i : VL) {
    Left.push_back(cast<Instruction>(i)->getOperand(0));
    Right.push_back(cast<Instruction>(i)->getOperand(1));
  }

  // Reorder if we have a commutative operation and consecutive access
  // are on either side of the alternate instructions.
  for (unsigned j = 0; j < VL.size() - 1; ++j) {
    if (LoadInst *L = dyn_cast<LoadInst>(Left[j])) {
      if (LoadInst *L1 = dyn_cast<LoadInst>(Right[j + 1])) {
        Instruction *VL1 = cast<Instruction>(VL[j]);
        Instruction *VL2 = cast<Instruction>(VL[j + 1]);
        if (VL1->isCommutative() && isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j], Right[j]);
          continue;
        } else if (VL2->isCommutative() &&
                   isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j + 1], Right[j + 1]);
          continue;
        }
        // else unchanged
      }
    }
    if (LoadInst *L = dyn_cast<LoadInst>(Right[j])) {
      if (LoadInst *L1 = dyn_cast<LoadInst>(Left[j + 1])) {
        Instruction *VL1 = cast<Instruction>(VL[j]);
        Instruction *VL2 = cast<Instruction>(VL[j + 1]);
        if (VL1->isCommutative() && isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j], Right[j]);
          continue;
        } else if (VL2->isCommutative() &&
                   isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j + 1], Right[j + 1]);
          continue;
        }
        // else unchanged
      }
    }
  }
}

// Return true if I should be commuted before adding it's left and right
// operands to the arrays Left and Right.
//
// The vectorizer is trying to either have all elements one side being
// instruction with the same opcode to enable further vectorization, or having
// a splat to lower the vectorizing cost.
static bool shouldReorderOperands(int i, Instruction &I,
                                  SmallVectorImpl<Value *> &Left,
                                  SmallVectorImpl<Value *> &Right,
                                  bool AllSameOpcodeLeft,
                                  bool AllSameOpcodeRight, bool SplatLeft,
                                  bool SplatRight) {
  Value *VLeft = I.getOperand(0);
  Value *VRight = I.getOperand(1);
  // If we have "SplatRight", try to see if commuting is needed to preserve it.
  if (SplatRight) {
    if (VRight == Right[i - 1])
      // Preserve SplatRight
      return false;
    if (VLeft == Right[i - 1]) {
      // Commuting would preserve SplatRight, but we don't want to break
      // SplatLeft either, i.e. preserve the original order if possible.
      // (FIXME: why do we care?)
      if (SplatLeft && VLeft == Left[i - 1])
        return false;
      return true;
    }
  }
  // Symmetrically handle Right side.
  if (SplatLeft) {
    if (VLeft == Left[i - 1])
      // Preserve SplatLeft
      return false;
    if (VRight == Left[i - 1])
      return true;
  }

  Instruction *ILeft = dyn_cast<Instruction>(VLeft);
  Instruction *IRight = dyn_cast<Instruction>(VRight);

  // If we have "AllSameOpcodeRight", try to see if the left operands preserves
  // it and not the right, in this case we want to commute.
  if (AllSameOpcodeRight) {
    unsigned RightPrevOpcode = cast<Instruction>(Right[i - 1])->getOpcode();
    if (IRight && RightPrevOpcode == IRight->getOpcode())
      // Do not commute, a match on the right preserves AllSameOpcodeRight
      return false;
    if (ILeft && RightPrevOpcode == ILeft->getOpcode()) {
      // We have a match and may want to commute, but first check if there is
      // not also a match on the existing operands on the Left to preserve
      // AllSameOpcodeLeft, i.e. preserve the original order if possible.
      // (FIXME: why do we care?)
      if (AllSameOpcodeLeft && ILeft &&
          cast<Instruction>(Left[i - 1])->getOpcode() == ILeft->getOpcode())
        return false;
      return true;
    }
  }
  // Symmetrically handle Left side.
  if (AllSameOpcodeLeft) {
    unsigned LeftPrevOpcode = cast<Instruction>(Left[i - 1])->getOpcode();
    if (ILeft && LeftPrevOpcode == ILeft->getOpcode())
      return false;
    if (IRight && LeftPrevOpcode == IRight->getOpcode())
      return true;
  }
  return false;
}

void BoUpSLP::reorderInputsAccordingToOpcode(ArrayRef<Value *> VL,
                                             SmallVectorImpl<Value *> &Left,
                                             SmallVectorImpl<Value *> &Right) {

  if (VL.size()) {
    // Peel the first iteration out of the loop since there's nothing
    // interesting to do anyway and it simplifies the checks in the loop.
    auto VLeft = cast<Instruction>(VL[0])->getOperand(0);
    auto VRight = cast<Instruction>(VL[0])->getOperand(1);
    if (!isa<Instruction>(VRight) && isa<Instruction>(VLeft))
      // Favor having instruction to the right. FIXME: why?
      std::swap(VLeft, VRight);
    Left.push_back(VLeft);
    Right.push_back(VRight);
  }

  // Keep track if we have instructions with all the same opcode on one side.
  bool AllSameOpcodeLeft = isa<Instruction>(Left[0]);
  bool AllSameOpcodeRight = isa<Instruction>(Right[0]);
  // Keep track if we have one side with all the same value (broadcast).
  bool SplatLeft = true;
  bool SplatRight = true;

  for (unsigned i = 1, e = VL.size(); i != e; ++i) {
    Instruction *I = cast<Instruction>(VL[i]);
    assert(I->isCommutative() && "Can only process commutative instruction");
    // Commute to favor either a splat or maximizing having the same opcodes on
    // one side.
    if (shouldReorderOperands(i, *I, Left, Right, AllSameOpcodeLeft,
                              AllSameOpcodeRight, SplatLeft, SplatRight)) {
      Left.push_back(I->getOperand(1));
      Right.push_back(I->getOperand(0));
    } else {
      Left.push_back(I->getOperand(0));
      Right.push_back(I->getOperand(1));
    }
    // Update Splat* and AllSameOpcode* after the insertion.
    SplatRight = SplatRight && (Right[i - 1] == Right[i]);
    SplatLeft = SplatLeft && (Left[i - 1] == Left[i]);
    AllSameOpcodeLeft = AllSameOpcodeLeft && isa<Instruction>(Left[i]) &&
                        (cast<Instruction>(Left[i - 1])->getOpcode() ==
                         cast<Instruction>(Left[i])->getOpcode());
    AllSameOpcodeRight = AllSameOpcodeRight && isa<Instruction>(Right[i]) &&
                         (cast<Instruction>(Right[i - 1])->getOpcode() ==
                          cast<Instruction>(Right[i])->getOpcode());
  }

  // If one operand end up being broadcast, return this operand order.
  if (SplatRight || SplatLeft)
    return;

  // Finally check if we can get longer vectorizable chain by reordering
  // without breaking the good operand order detected above.
  // E.g. If we have something like-
  // load a[0]  load b[0]
  // load b[1]  load a[1]
  // load a[2]  load b[2]
  // load a[3]  load b[3]
  // Reordering the second load b[1]  load a[1] would allow us to vectorize
  // this code and we still retain AllSameOpcode property.
  // FIXME: This load reordering might break AllSameOpcode in some rare cases
  // such as-
  // add a[0],c[0]  load b[0]
  // add a[1],c[2]  load b[1]
  // b[2]           load b[2]
  // add a[3],c[3]  load b[3]
  for (unsigned j = 0; j < VL.size() - 1; ++j) {
    if (LoadInst *L = dyn_cast<LoadInst>(Left[j])) {
      if (LoadInst *L1 = dyn_cast<LoadInst>(Right[j + 1])) {
        if (isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j + 1], Right[j + 1]);
          continue;
        }
      }
    }
    if (LoadInst *L = dyn_cast<LoadInst>(Right[j])) {
      if (LoadInst *L1 = dyn_cast<LoadInst>(Left[j + 1])) {
        if (isConsecutiveAccess(L, L1, *DL, *SE)) {
          std::swap(Left[j + 1], Right[j + 1]);
          continue;
        }
      }
    }
    // else unchanged
  }
}

void BoUpSLP::setInsertPointAfterBundle(ArrayRef<Value *> VL) {

  // Get the basic block this bundle is in. All instructions in the bundle
  // should be in this block.
  auto *Front = cast<Instruction>(VL.front());
  auto *BB = Front->getParent();
  assert(all_of(make_range(VL.begin(), VL.end()), [&](Value *V) -> bool {
    return cast<Instruction>(V)->getParent() == BB;
  }));

  // The last instruction in the bundle in program order.
  Instruction *LastInst = nullptr;

  // Find the last instruction. The common case should be that BB has been
  // scheduled, and the last instruction is VL.back(). So we start with
  // VL.back() and iterate over schedule data until we reach the end of the
  // bundle. The end of the bundle is marked by null ScheduleData.
  if (BlocksSchedules.count(BB)) {
    auto *Bundle = BlocksSchedules[BB]->getScheduleData(VL.back());
    if (Bundle && Bundle->isPartOfBundle())
      for (; Bundle; Bundle = Bundle->NextInBundle)
        LastInst = Bundle->Inst;
  }

  // LastInst can still be null at this point if there's either not an entry
  // for BB in BlocksSchedules or there's no ScheduleData available for
  // VL.back(). This can be the case if buildTree_rec aborts for various
  // reasons (e.g., the maximum recursion depth is reached, the maximum region
  // size is reached, etc.). ScheduleData is initialized in the scheduling
  // "dry-run".
  //
  // If this happens, we can still find the last instruction by brute force. We
  // iterate forwards from Front (inclusive) until we either see all
  // instructions in the bundle or reach the end of the block. If Front is the
  // last instruction in program order, LastInst will be set to Front, and we
  // will visit all the remaining instructions in the block.
  //
  // One of the reasons we exit early from buildTree_rec is to place an upper
  // bound on compile-time. Thus, taking an additional compile-time hit here is
  // not ideal. However, this should be exceedingly rare since it requires that
  // we both exit early from buildTree_rec and that the bundle be out-of-order
  // (causing us to iterate all the way to the end of the block).
  if (!LastInst) {
    SmallPtrSet<Value *, 16> Bundle(VL.begin(), VL.end());
    for (auto &I : make_range(BasicBlock::iterator(Front), BB->end())) {
      if (Bundle.erase(&I))
        LastInst = &I;
      if (Bundle.empty())
        break;
    }
  }

  // Set the insertion point after the last instruction in the bundle. Set the
  // debug location to Front.
  Builder.SetInsertPoint(BB, ++LastInst->getIterator());
  Builder.SetCurrentDebugLocation(Front->getDebugLoc());
}

Value *BoUpSLP::Gather(ArrayRef<Value *> VL, VectorType *Ty) {
  Value *Vec = UndefValue::get(Ty);
  // Generate the 'InsertElement' instruction.
  for (unsigned i = 0; i < Ty->getNumElements(); ++i) {
    Vec = Builder.CreateInsertElement(Vec, VL[i], Builder.getInt32(i));
    if (Instruction *Insrt = dyn_cast<Instruction>(Vec)) {
      GatherSeq.insert(Insrt);
      CSEBlocks.insert(Insrt->getParent());

      // Add to our 'need-to-extract' list.
      if (ScalarToTreeEntry.count(VL[i])) {
        int Idx = ScalarToTreeEntry[VL[i]];
        TreeEntry *E = &VectorizableTree[Idx];
        // Find which lane we need to extract.
        int FoundLane = -1;
        for (unsigned Lane = 0, LE = VL.size(); Lane != LE; ++Lane) {
          // Is this the lane of the scalar that we are looking for ?
          if (E->Scalars[Lane] == VL[i]) {
            FoundLane = Lane;
            break;
          }
        }
        assert(FoundLane >= 0 && "Could not find the correct lane");
        ExternalUses.push_back(ExternalUser(VL[i], Insrt, FoundLane));
      }
    }
  }

  return Vec;
}

Value *BoUpSLP::alreadyVectorized(ArrayRef<Value *> VL) const {
  SmallDenseMap<Value*, int>::const_iterator Entry
    = ScalarToTreeEntry.find(VL[0]);
  if (Entry != ScalarToTreeEntry.end()) {
    int Idx = Entry->second;
    const TreeEntry *En = &VectorizableTree[Idx];
    if (En->isSame(VL) && En->VectorizedValue)
      return En->VectorizedValue;
  }
  return nullptr;
}

Value *BoUpSLP::vectorizeTree(ArrayRef<Value *> VL) {
  if (ScalarToTreeEntry.count(VL[0])) {
    int Idx = ScalarToTreeEntry[VL[0]];
    TreeEntry *E = &VectorizableTree[Idx];
    if (E->isSame(VL))
      return vectorizeTree(E);
  }

  Type *ScalarTy = VL[0]->getType();
  if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
    ScalarTy = SI->getValueOperand()->getType();
  VectorType *VecTy = VectorType::get(ScalarTy, VL.size());

  return Gather(VL, VecTy);
}

Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
  IRBuilder<>::InsertPointGuard Guard(Builder);

  if (E->VectorizedValue) {
    DEBUG(dbgs() << "SLP: Diamond merged for " << *E->Scalars[0] << ".\n");
    return E->VectorizedValue;
  }

  Instruction *VL0 = cast<Instruction>(E->Scalars[0]);
  Type *ScalarTy = VL0->getType();
  if (StoreInst *SI = dyn_cast<StoreInst>(VL0))
    ScalarTy = SI->getValueOperand()->getType();
  VectorType *VecTy = VectorType::get(ScalarTy, E->Scalars.size());

  if (E->NeedToGather) {
    setInsertPointAfterBundle(E->Scalars);
    auto *V = Gather(E->Scalars, VecTy);
    E->VectorizedValue = V;
    return V;
  }

  unsigned Opcode = getSameOpcode(E->Scalars);

  switch (Opcode) {
    case Instruction::PHI: {
      PHINode *PH = dyn_cast<PHINode>(VL0);
      Builder.SetInsertPoint(PH->getParent()->getFirstNonPHI());
      Builder.SetCurrentDebugLocation(PH->getDebugLoc());
      PHINode *NewPhi = Builder.CreatePHI(VecTy, PH->getNumIncomingValues());
      E->VectorizedValue = NewPhi;

      // PHINodes may have multiple entries from the same block. We want to
      // visit every block once.
      SmallSet<BasicBlock*, 4> VisitedBBs;

      for (unsigned i = 0, e = PH->getNumIncomingValues(); i < e; ++i) {
        ValueList Operands;
        BasicBlock *IBB = PH->getIncomingBlock(i);

        if (!VisitedBBs.insert(IBB).second) {
          NewPhi->addIncoming(NewPhi->getIncomingValueForBlock(IBB), IBB);
          continue;
        }

        // Prepare the operand vector.
        for (Value *V : E->Scalars)
          Operands.push_back(cast<PHINode>(V)->getIncomingValueForBlock(IBB));

        Builder.SetInsertPoint(IBB->getTerminator());
        Builder.SetCurrentDebugLocation(PH->getDebugLoc());
        Value *Vec = vectorizeTree(Operands);
        NewPhi->addIncoming(Vec, IBB);
      }

      assert(NewPhi->getNumIncomingValues() == PH->getNumIncomingValues() &&
             "Invalid number of incoming values");
      return NewPhi;
    }

    case Instruction::ExtractElement: {
      if (canReuseExtract(E->Scalars, Instruction::ExtractElement)) {
        Value *V = VL0->getOperand(0);
        E->VectorizedValue = V;
        return V;
      }
      setInsertPointAfterBundle(E->Scalars);
      auto *V = Gather(E->Scalars, VecTy);
      E->VectorizedValue = V;
      return V;
    }
    case Instruction::ExtractValue: {
      if (canReuseExtract(E->Scalars, Instruction::ExtractValue)) {
        LoadInst *LI = cast<LoadInst>(VL0->getOperand(0));
        Builder.SetInsertPoint(LI);
        PointerType *PtrTy = PointerType::get(VecTy, LI->getPointerAddressSpace());
        Value *Ptr = Builder.CreateBitCast(LI->getOperand(0), PtrTy);
        LoadInst *V = Builder.CreateAlignedLoad(Ptr, LI->getAlignment());
        E->VectorizedValue = V;
        return propagateMetadata(V, E->Scalars);
      }
      setInsertPointAfterBundle(E->Scalars);
      auto *V = Gather(E->Scalars, VecTy);
      E->VectorizedValue = V;
      return V;
    }
    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: {
      ValueList INVL;
      for (Value *V : E->Scalars)
        INVL.push_back(cast<Instruction>(V)->getOperand(0));

      setInsertPointAfterBundle(E->Scalars);

      Value *InVec = vectorizeTree(INVL);

      if (Value *V = alreadyVectorized(E->Scalars))
        return V;

      CastInst *CI = dyn_cast<CastInst>(VL0);
      Value *V = Builder.CreateCast(CI->getOpcode(), InVec, VecTy);
      E->VectorizedValue = V;
      ++NumVectorInstructions;
      return V;
    }
    case Instruction::FCmp:
    case Instruction::ICmp: {
      ValueList LHSV, RHSV;
      for (Value *V : E->Scalars) {
        LHSV.push_back(cast<Instruction>(V)->getOperand(0));
        RHSV.push_back(cast<Instruction>(V)->getOperand(1));
      }

      setInsertPointAfterBundle(E->Scalars);

      Value *L = vectorizeTree(LHSV);
      Value *R = vectorizeTree(RHSV);

      if (Value *V = alreadyVectorized(E->Scalars))
        return V;

      CmpInst::Predicate P0 = cast<CmpInst>(VL0)->getPredicate();
      Value *V;
      if (Opcode == Instruction::FCmp)
        V = Builder.CreateFCmp(P0, L, R);
      else
        V = Builder.CreateICmp(P0, L, R);

      E->VectorizedValue = V;
      propagateIRFlags(E->VectorizedValue, E->Scalars);
      ++NumVectorInstructions;
      return V;
    }
    case Instruction::Select: {
      ValueList TrueVec, FalseVec, CondVec;
      for (Value *V : E->Scalars) {
        CondVec.push_back(cast<Instruction>(V)->getOperand(0));
        TrueVec.push_back(cast<Instruction>(V)->getOperand(1));
        FalseVec.push_back(cast<Instruction>(V)->getOperand(2));
      }

      setInsertPointAfterBundle(E->Scalars);

      Value *Cond = vectorizeTree(CondVec);
      Value *True = vectorizeTree(TrueVec);
      Value *False = vectorizeTree(FalseVec);

      if (Value *V = alreadyVectorized(E->Scalars))
        return V;

      Value *V = Builder.CreateSelect(Cond, True, False);
      E->VectorizedValue = V;
      ++NumVectorInstructions;
      return V;
    }
    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: {
      ValueList LHSVL, RHSVL;
      if (isa<BinaryOperator>(VL0) && VL0->isCommutative())
        reorderInputsAccordingToOpcode(E->Scalars, LHSVL, RHSVL);
      else
        for (Value *V : E->Scalars) {
          LHSVL.push_back(cast<Instruction>(V)->getOperand(0));
          RHSVL.push_back(cast<Instruction>(V)->getOperand(1));
        }

      setInsertPointAfterBundle(E->Scalars);

      Value *LHS = vectorizeTree(LHSVL);
      Value *RHS = vectorizeTree(RHSVL);

      if (Value *V = alreadyVectorized(E->Scalars))
        return V;

      BinaryOperator *BinOp = cast<BinaryOperator>(VL0);
      Value *V = Builder.CreateBinOp(BinOp->getOpcode(), LHS, RHS);
      E->VectorizedValue = V;
      propagateIRFlags(E->VectorizedValue, E->Scalars);
      ++NumVectorInstructions;

      if (Instruction *I = dyn_cast<Instruction>(V))
        return propagateMetadata(I, E->Scalars);

      return V;
    }
    case Instruction::Load: {
      // Loads are inserted at the head of the tree because we don't want to
      // sink them all the way down past store instructions.
      setInsertPointAfterBundle(E->Scalars);

      LoadInst *LI = cast<LoadInst>(VL0);
      Type *ScalarLoadTy = LI->getType();
      unsigned AS = LI->getPointerAddressSpace();

      Value *VecPtr = Builder.CreateBitCast(LI->getPointerOperand(),
                                            VecTy->getPointerTo(AS));

      // The pointer operand uses an in-tree scalar so we add the new BitCast to
      // ExternalUses list to make sure that an extract will be generated in the
      // future.
      if (ScalarToTreeEntry.count(LI->getPointerOperand()))
        ExternalUses.push_back(
            ExternalUser(LI->getPointerOperand(), cast<User>(VecPtr), 0));

      unsigned Alignment = LI->getAlignment();
      LI = Builder.CreateLoad(VecPtr);
      if (!Alignment) {
        Alignment = DL->getABITypeAlignment(ScalarLoadTy);
      }
      LI->setAlignment(Alignment);
      E->VectorizedValue = LI;
      ++NumVectorInstructions;
      return propagateMetadata(LI, E->Scalars);
    }
    case Instruction::Store: {
      StoreInst *SI = cast<StoreInst>(VL0);
      unsigned Alignment = SI->getAlignment();
      unsigned AS = SI->getPointerAddressSpace();

      ValueList ValueOp;
      for (Value *V : E->Scalars)
        ValueOp.push_back(cast<StoreInst>(V)->getValueOperand());

      setInsertPointAfterBundle(E->Scalars);

      Value *VecValue = vectorizeTree(ValueOp);
      Value *VecPtr = Builder.CreateBitCast(SI->getPointerOperand(),
                                            VecTy->getPointerTo(AS));
      StoreInst *S = Builder.CreateStore(VecValue, VecPtr);

      // The pointer operand uses an in-tree scalar so we add the new BitCast to
      // ExternalUses list to make sure that an extract will be generated in the
      // future.
      if (ScalarToTreeEntry.count(SI->getPointerOperand()))
        ExternalUses.push_back(
            ExternalUser(SI->getPointerOperand(), cast<User>(VecPtr), 0));

      if (!Alignment) {
        Alignment = DL->getABITypeAlignment(SI->getValueOperand()->getType());
      }
      S->setAlignment(Alignment);
      E->VectorizedValue = S;
      ++NumVectorInstructions;
      return propagateMetadata(S, E->Scalars);
    }
    case Instruction::GetElementPtr: {
      setInsertPointAfterBundle(E->Scalars);

      ValueList Op0VL;
      for (Value *V : E->Scalars)
        Op0VL.push_back(cast<GetElementPtrInst>(V)->getOperand(0));

      Value *Op0 = vectorizeTree(Op0VL);

      std::vector<Value *> OpVecs;
      for (int j = 1, e = cast<GetElementPtrInst>(VL0)->getNumOperands(); j < e;
           ++j) {
        ValueList OpVL;
        for (Value *V : E->Scalars)
          OpVL.push_back(cast<GetElementPtrInst>(V)->getOperand(j));

        Value *OpVec = vectorizeTree(OpVL);
        OpVecs.push_back(OpVec);
      }

      Value *V = Builder.CreateGEP(
          cast<GetElementPtrInst>(VL0)->getSourceElementType(), Op0, OpVecs);
      E->VectorizedValue = V;
      ++NumVectorInstructions;

      if (Instruction *I = dyn_cast<Instruction>(V))
        return propagateMetadata(I, E->Scalars);

      return V;
    }
    case Instruction::Call: {
      CallInst *CI = cast<CallInst>(VL0);
      setInsertPointAfterBundle(E->Scalars);
      Function *FI;
      Intrinsic::ID IID  = Intrinsic::not_intrinsic;
      Value *ScalarArg = nullptr;
      if (CI && (FI = CI->getCalledFunction())) {
        IID = FI->getIntrinsicID();
      }
      std::vector<Value *> OpVecs;
      for (int j = 0, e = CI->getNumArgOperands(); j < e; ++j) {
        ValueList OpVL;
        // ctlz,cttz and powi are special intrinsics whose second argument is
        // a scalar. This argument should not be vectorized.
        if (hasVectorInstrinsicScalarOpd(IID, 1) && j == 1) {
          CallInst *CEI = cast<CallInst>(E->Scalars[0]);
          ScalarArg = CEI->getArgOperand(j);
          OpVecs.push_back(CEI->getArgOperand(j));
          continue;
        }
        for (Value *V : E->Scalars) {
          CallInst *CEI = cast<CallInst>(V);
          OpVL.push_back(CEI->getArgOperand(j));
        }

        Value *OpVec = vectorizeTree(OpVL);
        DEBUG(dbgs() << "SLP: OpVec[" << j << "]: " << *OpVec << "\n");
        OpVecs.push_back(OpVec);
      }

      Module *M = F->getParent();
      Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
      Type *Tys[] = { VectorType::get(CI->getType(), E->Scalars.size()) };
      Function *CF = Intrinsic::getDeclaration(M, ID, Tys);
      SmallVector<OperandBundleDef, 1> OpBundles;
      CI->getOperandBundlesAsDefs(OpBundles);
      Value *V = Builder.CreateCall(CF, OpVecs, OpBundles);

      // The scalar argument uses an in-tree scalar so we add the new vectorized
      // call to ExternalUses list to make sure that an extract will be
      // generated in the future.
      if (ScalarArg && ScalarToTreeEntry.count(ScalarArg))
        ExternalUses.push_back(ExternalUser(ScalarArg, cast<User>(V), 0));

      E->VectorizedValue = V;
      propagateIRFlags(E->VectorizedValue, E->Scalars);
      ++NumVectorInstructions;
      return V;
    }
    case Instruction::ShuffleVector: {
      ValueList LHSVL, RHSVL;
      assert(isa<BinaryOperator>(VL0) && "Invalid Shuffle Vector Operand");
      reorderAltShuffleOperands(E->Scalars, LHSVL, RHSVL);
      setInsertPointAfterBundle(E->Scalars);

      Value *LHS = vectorizeTree(LHSVL);
      Value *RHS = vectorizeTree(RHSVL);

      if (Value *V = alreadyVectorized(E->Scalars))
        return V;

      // Create a vector of LHS op1 RHS
      BinaryOperator *BinOp0 = cast<BinaryOperator>(VL0);
      Value *V0 = Builder.CreateBinOp(BinOp0->getOpcode(), LHS, RHS);

      // Create a vector of LHS op2 RHS
      Instruction *VL1 = cast<Instruction>(E->Scalars[1]);
      BinaryOperator *BinOp1 = cast<BinaryOperator>(VL1);
      Value *V1 = Builder.CreateBinOp(BinOp1->getOpcode(), LHS, RHS);

      // Create shuffle to take alternate operations from the vector.
      // Also, gather up odd and even scalar ops to propagate IR flags to
      // each vector operation.
      ValueList OddScalars, EvenScalars;
      unsigned e = E->Scalars.size();
      SmallVector<Constant *, 8> Mask(e);
      for (unsigned i = 0; i < e; ++i) {
        if (i & 1) {
          Mask[i] = Builder.getInt32(e + i);
          OddScalars.push_back(E->Scalars[i]);
        } else {
          Mask[i] = Builder.getInt32(i);
          EvenScalars.push_back(E->Scalars[i]);
        }
      }

      Value *ShuffleMask = ConstantVector::get(Mask);
      propagateIRFlags(V0, EvenScalars);
      propagateIRFlags(V1, OddScalars);

      Value *V = Builder.CreateShuffleVector(V0, V1, ShuffleMask);
      E->VectorizedValue = V;
      ++NumVectorInstructions;
      if (Instruction *I = dyn_cast<Instruction>(V))
        return propagateMetadata(I, E->Scalars);

      return V;
    }
    default:
    llvm_unreachable("unknown inst");
  }
  return nullptr;
}

Value *BoUpSLP::vectorizeTree() {

  // All blocks must be scheduled before any instructions are inserted.
  for (auto &BSIter : BlocksSchedules) {
    scheduleBlock(BSIter.second.get());
  }

  Builder.SetInsertPoint(&F->getEntryBlock().front());
  auto *VectorRoot = vectorizeTree(&VectorizableTree[0]);

  // If the vectorized tree can be rewritten in a smaller type, we truncate the
  // vectorized root. InstCombine will then rewrite the entire expression. We
  // sign extend the extracted values below.
  auto *ScalarRoot = VectorizableTree[0].Scalars[0];
  if (MinBWs.count(ScalarRoot)) {
    if (auto *I = dyn_cast<Instruction>(VectorRoot))
      Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
    auto BundleWidth = VectorizableTree[0].Scalars.size();
    auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
    auto *VecTy = VectorType::get(MinTy, BundleWidth);
    auto *Trunc = Builder.CreateTrunc(VectorRoot, VecTy);
    VectorizableTree[0].VectorizedValue = Trunc;
  }

  DEBUG(dbgs() << "SLP: Extracting " << ExternalUses.size() << " values .\n");

  // If necessary, sign-extend or zero-extend ScalarRoot to the larger type
  // specified by ScalarType.
  auto extend = [&](Value *ScalarRoot, Value *Ex, Type *ScalarType) {
    if (!MinBWs.count(ScalarRoot))
      return Ex;
    if (MinBWs[ScalarRoot].second)
      return Builder.CreateSExt(Ex, ScalarType);
    return Builder.CreateZExt(Ex, ScalarType);
  };

  // Extract all of the elements with the external uses.
  for (const auto &ExternalUse : ExternalUses) {
    Value *Scalar = ExternalUse.Scalar;
    llvm::User *User = ExternalUse.User;

    // Skip users that we already RAUW. This happens when one instruction
    // has multiple uses of the same value.
    if (!is_contained(Scalar->users(), User))
      continue;
    assert(ScalarToTreeEntry.count(Scalar) && "Invalid scalar");

    int Idx = ScalarToTreeEntry[Scalar];
    TreeEntry *E = &VectorizableTree[Idx];
    assert(!E->NeedToGather && "Extracting from a gather list");

    Value *Vec = E->VectorizedValue;
    assert(Vec && "Can't find vectorizable value");

    Value *Lane = Builder.getInt32(ExternalUse.Lane);
    // Generate extracts for out-of-tree users.
    // Find the insertion point for the extractelement lane.
    if (auto *VecI = dyn_cast<Instruction>(Vec)) {
      if (PHINode *PH = dyn_cast<PHINode>(User)) {
        for (int i = 0, e = PH->getNumIncomingValues(); i != e; ++i) {
          if (PH->getIncomingValue(i) == Scalar) {
            TerminatorInst *IncomingTerminator =
                PH->getIncomingBlock(i)->getTerminator();
            if (isa<CatchSwitchInst>(IncomingTerminator)) {
              Builder.SetInsertPoint(VecI->getParent(),
                                     std::next(VecI->getIterator()));
            } else {
              Builder.SetInsertPoint(PH->getIncomingBlock(i)->getTerminator());
            }
            Value *Ex = Builder.CreateExtractElement(Vec, Lane);
            Ex = extend(ScalarRoot, Ex, Scalar->getType());
            CSEBlocks.insert(PH->getIncomingBlock(i));
            PH->setOperand(i, Ex);
          }
        }
      } else {
        Builder.SetInsertPoint(cast<Instruction>(User));
        Value *Ex = Builder.CreateExtractElement(Vec, Lane);
        Ex = extend(ScalarRoot, Ex, Scalar->getType());
        CSEBlocks.insert(cast<Instruction>(User)->getParent());
        User->replaceUsesOfWith(Scalar, Ex);
     }
    } else {
      Builder.SetInsertPoint(&F->getEntryBlock().front());
      Value *Ex = Builder.CreateExtractElement(Vec, Lane);
      Ex = extend(ScalarRoot, Ex, Scalar->getType());
      CSEBlocks.insert(&F->getEntryBlock());
      User->replaceUsesOfWith(Scalar, Ex);
    }

    DEBUG(dbgs() << "SLP: Replaced:" << *User << ".\n");
  }

  // For each vectorized value:
  for (TreeEntry &EIdx : VectorizableTree) {
    TreeEntry *Entry = &EIdx;

    // For each lane:
    for (int Lane = 0, LE = Entry->Scalars.size(); Lane != LE; ++Lane) {
      Value *Scalar = Entry->Scalars[Lane];
      // No need to handle users of gathered values.
      if (Entry->NeedToGather)
        continue;

      assert(Entry->VectorizedValue && "Can't find vectorizable value");

      Type *Ty = Scalar->getType();
      if (!Ty->isVoidTy()) {
#ifndef NDEBUG
        for (User *U : Scalar->users()) {
          DEBUG(dbgs() << "SLP: \tvalidating user:" << *U << ".\n");

          assert((ScalarToTreeEntry.count(U) ||
                  // It is legal to replace users in the ignorelist by undef.
                  is_contained(UserIgnoreList, U)) &&
                 "Replacing out-of-tree value with undef");
        }
#endif
        Value *Undef = UndefValue::get(Ty);
        Scalar->replaceAllUsesWith(Undef);
      }
      DEBUG(dbgs() << "SLP: \tErasing scalar:" << *Scalar << ".\n");
      eraseInstruction(cast<Instruction>(Scalar));
    }
  }

  Builder.ClearInsertionPoint();

  return VectorizableTree[0].VectorizedValue;
}

void BoUpSLP::optimizeGatherSequence() {
  DEBUG(dbgs() << "SLP: Optimizing " << GatherSeq.size()
        << " gather sequences instructions.\n");
  // LICM InsertElementInst sequences.
  for (Instruction *it : GatherSeq) {
    InsertElementInst *Insert = dyn_cast<InsertElementInst>(it);

    if (!Insert)
      continue;

    // Check if this block is inside a loop.
    Loop *L = LI->getLoopFor(Insert->getParent());
    if (!L)
      continue;

    // Check if it has a preheader.
    BasicBlock *PreHeader = L->getLoopPreheader();
    if (!PreHeader)
      continue;

    // If the vector or the element that we insert into it are
    // instructions that are defined in this basic block then we can't
    // hoist this instruction.
    Instruction *CurrVec = dyn_cast<Instruction>(Insert->getOperand(0));
    Instruction *NewElem = dyn_cast<Instruction>(Insert->getOperand(1));
    if (CurrVec && L->contains(CurrVec))
      continue;
    if (NewElem && L->contains(NewElem))
      continue;

    // We can hoist this instruction. Move it to the pre-header.
    Insert->moveBefore(PreHeader->getTerminator());
  }

  // Make a list of all reachable blocks in our CSE queue.
  SmallVector<const DomTreeNode *, 8> CSEWorkList;
  CSEWorkList.reserve(CSEBlocks.size());
  for (BasicBlock *BB : CSEBlocks)
    if (DomTreeNode *N = DT->getNode(BB)) {
      assert(DT->isReachableFromEntry(N));
      CSEWorkList.push_back(N);
    }

  // Sort blocks by domination. This ensures we visit a block after all blocks
  // dominating it are visited.
  std::stable_sort(CSEWorkList.begin(), CSEWorkList.end(),
                   [this](const DomTreeNode *A, const DomTreeNode *B) {
    return DT->properlyDominates(A, B);
  });

  // Perform O(N^2) search over the gather sequences and merge identical
  // instructions. TODO: We can further optimize this scan if we split the
  // instructions into different buckets based on the insert lane.
  SmallVector<Instruction *, 16> Visited;
  for (auto I = CSEWorkList.begin(), E = CSEWorkList.end(); I != E; ++I) {
    assert((I == CSEWorkList.begin() || !DT->dominates(*I, *std::prev(I))) &&
           "Worklist not sorted properly!");
    BasicBlock *BB = (*I)->getBlock();
    // For all instructions in blocks containing gather sequences:
    for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e;) {
      Instruction *In = &*it++;
      if (!isa<InsertElementInst>(In) && !isa<ExtractElementInst>(In))
        continue;

      // Check if we can replace this instruction with any of the
      // visited instructions.
      for (Instruction *v : Visited) {
        if (In->isIdenticalTo(v) &&
            DT->dominates(v->getParent(), In->getParent())) {
          In->replaceAllUsesWith(v);
          eraseInstruction(In);
          In = nullptr;
          break;
        }
      }
      if (In) {
        assert(!is_contained(Visited, In));
        Visited.push_back(In);
      }
    }
  }
  CSEBlocks.clear();
  GatherSeq.clear();
}

// Groups the instructions to a bundle (which is then a single scheduling entity)
// and schedules instructions until the bundle gets ready.
bool BoUpSLP::BlockScheduling::tryScheduleBundle(ArrayRef<Value *> VL,
                                                 BoUpSLP *SLP) {
  if (isa<PHINode>(VL[0]))
    return true;

  // Initialize the instruction bundle.
  Instruction *OldScheduleEnd = ScheduleEnd;
  ScheduleData *PrevInBundle = nullptr;
  ScheduleData *Bundle = nullptr;
  bool ReSchedule = false;
  DEBUG(dbgs() << "SLP:  bundle: " << *VL[0] << "\n");

  // Make sure that the scheduling region contains all
  // instructions of the bundle.
  for (Value *V : VL) {
    if (!extendSchedulingRegion(V))
      return false;
  }

  for (Value *V : VL) {
    ScheduleData *BundleMember = getScheduleData(V);
    assert(BundleMember &&
           "no ScheduleData for bundle member (maybe not in same basic block)");
    if (BundleMember->IsScheduled) {
      // A bundle member was scheduled as single instruction before and now
      // needs to be scheduled as part of the bundle. We just get rid of the
      // existing schedule.
      DEBUG(dbgs() << "SLP:  reset schedule because " << *BundleMember
                   << " was already scheduled\n");
      ReSchedule = true;
    }
    assert(BundleMember->isSchedulingEntity() &&
           "bundle member already part of other bundle");
    if (PrevInBundle) {
      PrevInBundle->NextInBundle = BundleMember;
    } else {
      Bundle = BundleMember;
    }
    BundleMember->UnscheduledDepsInBundle = 0;
    Bundle->UnscheduledDepsInBundle += BundleMember->UnscheduledDeps;

    // Group the instructions to a bundle.
    BundleMember->FirstInBundle = Bundle;
    PrevInBundle = BundleMember;
  }
  if (ScheduleEnd != OldScheduleEnd) {
    // The scheduling region got new instructions at the lower end (or it is a
    // new region for the first bundle). This makes it necessary to
    // recalculate all dependencies.
    // It is seldom that this needs to be done a second time after adding the
    // initial bundle to the region.
    for (auto *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode()) {
      ScheduleData *SD = getScheduleData(I);
      SD->clearDependencies();
    }
    ReSchedule = true;
  }
  if (ReSchedule) {
    resetSchedule();
    initialFillReadyList(ReadyInsts);
  }

  DEBUG(dbgs() << "SLP: try schedule bundle " << *Bundle << " in block "
               << BB->getName() << "\n");

  calculateDependencies(Bundle, true, SLP);

  // Now try to schedule the new bundle. As soon as the bundle is "ready" it
  // means that there are no cyclic dependencies and we can schedule it.
  // Note that's important that we don't "schedule" the bundle yet (see
  // cancelScheduling).
  while (!Bundle->isReady() && !ReadyInsts.empty()) {

    ScheduleData *pickedSD = ReadyInsts.back();
    ReadyInsts.pop_back();

    if (pickedSD->isSchedulingEntity() && pickedSD->isReady()) {
      schedule(pickedSD, ReadyInsts);
    }
  }
  if (!Bundle->isReady()) {
    cancelScheduling(VL);
    return false;
  }
  return true;
}

void BoUpSLP::BlockScheduling::cancelScheduling(ArrayRef<Value *> VL) {
  if (isa<PHINode>(VL[0]))
    return;

  ScheduleData *Bundle = getScheduleData(VL[0]);
  DEBUG(dbgs() << "SLP:  cancel scheduling of " << *Bundle << "\n");
  assert(!Bundle->IsScheduled &&
         "Can't cancel bundle which is already scheduled");
  assert(Bundle->isSchedulingEntity() && Bundle->isPartOfBundle() &&
         "tried to unbundle something which is not a bundle");

  // Un-bundle: make single instructions out of the bundle.
  ScheduleData *BundleMember = Bundle;
  while (BundleMember) {
    assert(BundleMember->FirstInBundle == Bundle && "corrupt bundle links");
    BundleMember->FirstInBundle = BundleMember;
    ScheduleData *Next = BundleMember->NextInBundle;
    BundleMember->NextInBundle = nullptr;
    BundleMember->UnscheduledDepsInBundle = BundleMember->UnscheduledDeps;
    if (BundleMember->UnscheduledDepsInBundle == 0) {
      ReadyInsts.insert(BundleMember);
    }
    BundleMember = Next;
  }
}

bool BoUpSLP::BlockScheduling::extendSchedulingRegion(Value *V) {
  if (getScheduleData(V))
    return true;
  Instruction *I = dyn_cast<Instruction>(V);
  assert(I && "bundle member must be an instruction");
  assert(!isa<PHINode>(I) && "phi nodes don't need to be scheduled");
  if (!ScheduleStart) {
    // It's the first instruction in the new region.
    initScheduleData(I, I->getNextNode(), nullptr, nullptr);
    ScheduleStart = I;
    ScheduleEnd = I->getNextNode();
    assert(ScheduleEnd && "tried to vectorize a TerminatorInst?");
    DEBUG(dbgs() << "SLP:  initialize schedule region to " << *I << "\n");
    return true;
  }
  // Search up and down at the same time, because we don't know if the new
  // instruction is above or below the existing scheduling region.
  BasicBlock::reverse_iterator UpIter =
      ++ScheduleStart->getIterator().getReverse();
  BasicBlock::reverse_iterator UpperEnd = BB->rend();
  BasicBlock::iterator DownIter = ScheduleEnd->getIterator();
  BasicBlock::iterator LowerEnd = BB->end();
  for (;;) {
    if (++ScheduleRegionSize > ScheduleRegionSizeLimit) {
      DEBUG(dbgs() << "SLP:  exceeded schedule region size limit\n");
      return false;
    }

    if (UpIter != UpperEnd) {
      if (&*UpIter == I) {
        initScheduleData(I, ScheduleStart, nullptr, FirstLoadStoreInRegion);
        ScheduleStart = I;
        DEBUG(dbgs() << "SLP:  extend schedule region start to " << *I << "\n");
        return true;
      }
      UpIter++;
    }
    if (DownIter != LowerEnd) {
      if (&*DownIter == I) {
        initScheduleData(ScheduleEnd, I->getNextNode(), LastLoadStoreInRegion,
                         nullptr);
        ScheduleEnd = I->getNextNode();
        assert(ScheduleEnd && "tried to vectorize a TerminatorInst?");
        DEBUG(dbgs() << "SLP:  extend schedule region end to " << *I << "\n");
        return true;
      }
      DownIter++;
    }
    assert((UpIter != UpperEnd || DownIter != LowerEnd) &&
           "instruction not found in block");
  }
  return true;
}

void BoUpSLP::BlockScheduling::initScheduleData(Instruction *FromI,
                                                Instruction *ToI,
                                                ScheduleData *PrevLoadStore,
                                                ScheduleData *NextLoadStore) {
  ScheduleData *CurrentLoadStore = PrevLoadStore;
  for (Instruction *I = FromI; I != ToI; I = I->getNextNode()) {
    ScheduleData *SD = ScheduleDataMap[I];
    if (!SD) {
      // Allocate a new ScheduleData for the instruction.
      if (ChunkPos >= ChunkSize) {
        ScheduleDataChunks.push_back(
            llvm::make_unique<ScheduleData[]>(ChunkSize));
        ChunkPos = 0;
      }
      SD = &(ScheduleDataChunks.back()[ChunkPos++]);
      ScheduleDataMap[I] = SD;
      SD->Inst = I;
    }
    assert(!isInSchedulingRegion(SD) &&
           "new ScheduleData already in scheduling region");
    SD->init(SchedulingRegionID);

    if (I->mayReadOrWriteMemory()) {
      // Update the linked list of memory accessing instructions.
      if (CurrentLoadStore) {
        CurrentLoadStore->NextLoadStore = SD;
      } else {
        FirstLoadStoreInRegion = SD;
      }
      CurrentLoadStore = SD;
    }
  }
  if (NextLoadStore) {
    if (CurrentLoadStore)
      CurrentLoadStore->NextLoadStore = NextLoadStore;
  } else {
    LastLoadStoreInRegion = CurrentLoadStore;
  }
}

void BoUpSLP::BlockScheduling::calculateDependencies(ScheduleData *SD,
                                                     bool InsertInReadyList,
                                                     BoUpSLP *SLP) {
  assert(SD->isSchedulingEntity());

  SmallVector<ScheduleData *, 10> WorkList;
  WorkList.push_back(SD);

  while (!WorkList.empty()) {
    ScheduleData *SD = WorkList.back();
    WorkList.pop_back();

    ScheduleData *BundleMember = SD;
    while (BundleMember) {
      assert(isInSchedulingRegion(BundleMember));
      if (!BundleMember->hasValidDependencies()) {

        DEBUG(dbgs() << "SLP:       update deps of " << *BundleMember << "\n");
        BundleMember->Dependencies = 0;
        BundleMember->resetUnscheduledDeps();

        // Handle def-use chain dependencies.
        for (User *U : BundleMember->Inst->users()) {
          if (isa<Instruction>(U)) {
            ScheduleData *UseSD = getScheduleData(U);
            if (UseSD && isInSchedulingRegion(UseSD->FirstInBundle)) {
              BundleMember->Dependencies++;
              ScheduleData *DestBundle = UseSD->FirstInBundle;
              if (!DestBundle->IsScheduled) {
                BundleMember->incrementUnscheduledDeps(1);
              }
              if (!DestBundle->hasValidDependencies()) {
                WorkList.push_back(DestBundle);
              }
            }
          } else {
            // I'm not sure if this can ever happen. But we need to be safe.
            // This lets the instruction/bundle never be scheduled and
            // eventually disable vectorization.
            BundleMember->Dependencies++;
            BundleMember->incrementUnscheduledDeps(1);
          }
        }

        // Handle the memory dependencies.
        ScheduleData *DepDest = BundleMember->NextLoadStore;
        if (DepDest) {
          Instruction *SrcInst = BundleMember->Inst;
          MemoryLocation SrcLoc = getLocation(SrcInst, SLP->AA);
          bool SrcMayWrite = BundleMember->Inst->mayWriteToMemory();
          unsigned numAliased = 0;
          unsigned DistToSrc = 1;

          while (DepDest) {
            assert(isInSchedulingRegion(DepDest));

            // We have two limits to reduce the complexity:
            // 1) AliasedCheckLimit: It's a small limit to reduce calls to
            //    SLP->isAliased (which is the expensive part in this loop).
            // 2) MaxMemDepDistance: It's for very large blocks and it aborts
            //    the whole loop (even if the loop is fast, it's quadratic).
            //    It's important for the loop break condition (see below) to
            //    check this limit even between two read-only instructions.
            if (DistToSrc >= MaxMemDepDistance ||
                    ((SrcMayWrite || DepDest->Inst->mayWriteToMemory()) &&
                     (numAliased >= AliasedCheckLimit ||
                      SLP->isAliased(SrcLoc, SrcInst, DepDest->Inst)))) {

              // We increment the counter only if the locations are aliased
              // (instead of counting all alias checks). This gives a better
              // balance between reduced runtime and accurate dependencies.
              numAliased++;

              DepDest->MemoryDependencies.push_back(BundleMember);
              BundleMember->Dependencies++;
              ScheduleData *DestBundle = DepDest->FirstInBundle;
              if (!DestBundle->IsScheduled) {
                BundleMember->incrementUnscheduledDeps(1);
              }
              if (!DestBundle->hasValidDependencies()) {
                WorkList.push_back(DestBundle);
              }
            }
            DepDest = DepDest->NextLoadStore;

            // Example, explaining the loop break condition: Let's assume our
            // starting instruction is i0 and MaxMemDepDistance = 3.
            //
            //                      +--------v--v--v
            //             i0,i1,i2,i3,i4,i5,i6,i7,i8
            //             +--------^--^--^
            //
            // MaxMemDepDistance let us stop alias-checking at i3 and we add
            // dependencies from i0 to i3,i4,.. (even if they are not aliased).
            // Previously we already added dependencies from i3 to i6,i7,i8
            // (because of MaxMemDepDistance). As we added a dependency from
            // i0 to i3, we have transitive dependencies from i0 to i6,i7,i8
            // and we can abort this loop at i6.
            if (DistToSrc >= 2 * MaxMemDepDistance)
                break;
            DistToSrc++;
          }
        }
      }
      BundleMember = BundleMember->NextInBundle;
    }
    if (InsertInReadyList && SD->isReady()) {
      ReadyInsts.push_back(SD);
      DEBUG(dbgs() << "SLP:     gets ready on update: " << *SD->Inst << "\n");
    }
  }
}

void BoUpSLP::BlockScheduling::resetSchedule() {
  assert(ScheduleStart &&
         "tried to reset schedule on block which has not been scheduled");
  for (Instruction *I = ScheduleStart; I != ScheduleEnd; I = I->getNextNode()) {
    ScheduleData *SD = getScheduleData(I);
    assert(isInSchedulingRegion(SD));
    SD->IsScheduled = false;
    SD->resetUnscheduledDeps();
  }
  ReadyInsts.clear();
}

void BoUpSLP::scheduleBlock(BlockScheduling *BS) {

  if (!BS->ScheduleStart)
    return;

  DEBUG(dbgs() << "SLP: schedule block " << BS->BB->getName() << "\n");

  BS->resetSchedule();

  // For the real scheduling we use a more sophisticated ready-list: it is
  // sorted by the original instruction location. This lets the final schedule
  // be as  close as possible to the original instruction order.
  struct ScheduleDataCompare {
    bool operator()(ScheduleData *SD1, ScheduleData *SD2) {
      return SD2->SchedulingPriority < SD1->SchedulingPriority;
    }
  };
  std::set<ScheduleData *, ScheduleDataCompare> ReadyInsts;

  // Ensure that all dependency data is updated and fill the ready-list with
  // initial instructions.
  int Idx = 0;
  int NumToSchedule = 0;
  for (auto *I = BS->ScheduleStart; I != BS->ScheduleEnd;
       I = I->getNextNode()) {
    ScheduleData *SD = BS->getScheduleData(I);
    assert(
        SD->isPartOfBundle() == (ScalarToTreeEntry.count(SD->Inst) != 0) &&
        "scheduler and vectorizer have different opinion on what is a bundle");
    SD->FirstInBundle->SchedulingPriority = Idx++;
    if (SD->isSchedulingEntity()) {
      BS->calculateDependencies(SD, false, this);
      NumToSchedule++;
    }
  }
  BS->initialFillReadyList(ReadyInsts);

  Instruction *LastScheduledInst = BS->ScheduleEnd;

  // Do the "real" scheduling.
  while (!ReadyInsts.empty()) {
    ScheduleData *picked = *ReadyInsts.begin();
    ReadyInsts.erase(ReadyInsts.begin());

    // Move the scheduled instruction(s) to their dedicated places, if not
    // there yet.
    ScheduleData *BundleMember = picked;
    while (BundleMember) {
      Instruction *pickedInst = BundleMember->Inst;
      if (LastScheduledInst->getNextNode() != pickedInst) {
        BS->BB->getInstList().remove(pickedInst);
        BS->BB->getInstList().insert(LastScheduledInst->getIterator(),
                                     pickedInst);
      }
      LastScheduledInst = pickedInst;
      BundleMember = BundleMember->NextInBundle;
    }

    BS->schedule(picked, ReadyInsts);
    NumToSchedule--;
  }
  assert(NumToSchedule == 0 && "could not schedule all instructions");

  // Avoid duplicate scheduling of the block.
  BS->ScheduleStart = nullptr;
}

unsigned BoUpSLP::getVectorElementSize(Value *V) {
  // If V is a store, just return the width of the stored value without
  // traversing the expression tree. This is the common case.
  if (auto *Store = dyn_cast<StoreInst>(V))
    return DL->getTypeSizeInBits(Store->getValueOperand()->getType());

  // If V is not a store, we can traverse the expression tree to find loads
  // that feed it. The type of the loaded value may indicate a more suitable
  // width than V's type. We want to base the vector element size on the width
  // of memory operations where possible.
  SmallVector<Instruction *, 16> Worklist;
  SmallPtrSet<Instruction *, 16> Visited;
  if (auto *I = dyn_cast<Instruction>(V))
    Worklist.push_back(I);

  // Traverse the expression tree in bottom-up order looking for loads. If we
  // encounter an instruciton we don't yet handle, we give up.
  auto MaxWidth = 0u;
  auto FoundUnknownInst = false;
  while (!Worklist.empty() && !FoundUnknownInst) {
    auto *I = Worklist.pop_back_val();
    Visited.insert(I);

    // We should only be looking at scalar instructions here. If the current
    // instruction has a vector type, give up.
    auto *Ty = I->getType();
    if (isa<VectorType>(Ty))
      FoundUnknownInst = true;

    // If the current instruction is a load, update MaxWidth to reflect the
    // width of the loaded value.
    else if (isa<LoadInst>(I))
      MaxWidth = std::max<unsigned>(MaxWidth, DL->getTypeSizeInBits(Ty));

    // Otherwise, we need to visit the operands of the instruction. We only
    // handle the interesting cases from buildTree here. If an operand is an
    // instruction we haven't yet visited, we add it to the worklist.
    else if (isa<PHINode>(I) || isa<CastInst>(I) || isa<GetElementPtrInst>(I) ||
             isa<CmpInst>(I) || isa<SelectInst>(I) || isa<BinaryOperator>(I)) {
      for (Use &U : I->operands())
        if (auto *J = dyn_cast<Instruction>(U.get()))
          if (!Visited.count(J))
            Worklist.push_back(J);
    }

    // If we don't yet handle the instruction, give up.
    else
      FoundUnknownInst = true;
  }

  // If we didn't encounter a memory access in the expression tree, or if we
  // gave up for some reason, just return the width of V.
  if (!MaxWidth || FoundUnknownInst)
    return DL->getTypeSizeInBits(V->getType());

  // Otherwise, return the maximum width we found.
  return MaxWidth;
}

// Determine if a value V in a vectorizable expression Expr can be demoted to a
// smaller type with a truncation. We collect the values that will be demoted
// in ToDemote and additional roots that require investigating in Roots.
static bool collectValuesToDemote(Value *V, SmallPtrSetImpl<Value *> &Expr,
                                  SmallVectorImpl<Value *> &ToDemote,
                                  SmallVectorImpl<Value *> &Roots) {

  // We can always demote constants.
  if (isa<Constant>(V)) {
    ToDemote.push_back(V);
    return true;
  }

  // If the value is not an instruction in the expression with only one use, it
  // cannot be demoted.
  auto *I = dyn_cast<Instruction>(V);
  if (!I || !I->hasOneUse() || !Expr.count(I))
    return false;

  switch (I->getOpcode()) {

  // We can always demote truncations and extensions. Since truncations can
  // seed additional demotion, we save the truncated value.
  case Instruction::Trunc:
    Roots.push_back(I->getOperand(0));
  case Instruction::ZExt:
  case Instruction::SExt:
    break;

  // We can demote certain binary operations if we can demote both of their
  // operands.
  case Instruction::Add:
  case Instruction::Sub:
  case Instruction::Mul:
  case Instruction::And:
  case Instruction::Or:
  case Instruction::Xor:
    if (!collectValuesToDemote(I->getOperand(0), Expr, ToDemote, Roots) ||
        !collectValuesToDemote(I->getOperand(1), Expr, ToDemote, Roots))
      return false;
    break;

  // We can demote selects if we can demote their true and false values.
  case Instruction::Select: {
    SelectInst *SI = cast<SelectInst>(I);
    if (!collectValuesToDemote(SI->getTrueValue(), Expr, ToDemote, Roots) ||
        !collectValuesToDemote(SI->getFalseValue(), Expr, ToDemote, Roots))
      return false;
    break;
  }

  // We can demote phis if we can demote all their incoming operands. Note that
  // we don't need to worry about cycles since we ensure single use above.
  case Instruction::PHI: {
    PHINode *PN = cast<PHINode>(I);
    for (Value *IncValue : PN->incoming_values())
      if (!collectValuesToDemote(IncValue, Expr, ToDemote, Roots))
        return false;
    break;
  }

  // Otherwise, conservatively give up.
  default:
    return false;
  }

  // Record the value that we can demote.
  ToDemote.push_back(V);
  return true;
}

void BoUpSLP::computeMinimumValueSizes() {
  // If there are no external uses, the expression tree must be rooted by a
  // store. We can't demote in-memory values, so there is nothing to do here.
  if (ExternalUses.empty())
    return;

  // We only attempt to truncate integer expressions.
  auto &TreeRoot = VectorizableTree[0].Scalars;
  auto *TreeRootIT = dyn_cast<IntegerType>(TreeRoot[0]->getType());
  if (!TreeRootIT)
    return;

  // If the expression is not rooted by a store, these roots should have
  // external uses. We will rely on InstCombine to rewrite the expression in
  // the narrower type. However, InstCombine only rewrites single-use values.
  // This means that if a tree entry other than a root is used externally, it
  // must have multiple uses and InstCombine will not rewrite it. The code
  // below ensures that only the roots are used externally.
  SmallPtrSet<Value *, 32> Expr(TreeRoot.begin(), TreeRoot.end());
  for (auto &EU : ExternalUses)
    if (!Expr.erase(EU.Scalar))
      return;
  if (!Expr.empty())
    return;

  // Collect the scalar values of the vectorizable expression. We will use this
  // context to determine which values can be demoted. If we see a truncation,
  // we mark it as seeding another demotion.
  for (auto &Entry : VectorizableTree)
    Expr.insert(Entry.Scalars.begin(), Entry.Scalars.end());

  // Ensure the roots of the vectorizable tree don't form a cycle. They must
  // have a single external user that is not in the vectorizable tree.
  for (auto *Root : TreeRoot)
    if (!Root->hasOneUse() || Expr.count(*Root->user_begin()))
      return;

  // Conservatively determine if we can actually truncate the roots of the
  // expression. Collect the values that can be demoted in ToDemote and
  // additional roots that require investigating in Roots.
  SmallVector<Value *, 32> ToDemote;
  SmallVector<Value *, 4> Roots;
  for (auto *Root : TreeRoot)
    if (!collectValuesToDemote(Root, Expr, ToDemote, Roots))
      return;

  // The maximum bit width required to represent all the values that can be
  // demoted without loss of precision. It would be safe to truncate the roots
  // of the expression to this width.
  auto MaxBitWidth = 8u;

  // We first check if all the bits of the roots are demanded. If they're not,
  // we can truncate the roots to this narrower type.
  for (auto *Root : TreeRoot) {
    auto Mask = DB->getDemandedBits(cast<Instruction>(Root));
    MaxBitWidth = std::max<unsigned>(
        Mask.getBitWidth() - Mask.countLeadingZeros(), MaxBitWidth);
  }

  // True if the roots can be zero-extended back to their original type, rather
  // than sign-extended. We know that if the leading bits are not demanded, we
  // can safely zero-extend. So we initialize IsKnownPositive to True.
  bool IsKnownPositive = true;

  // If all the bits of the roots are demanded, we can try a little harder to
  // compute a narrower type. This can happen, for example, if the roots are
  // getelementptr indices. InstCombine promotes these indices to the pointer
  // width. Thus, all their bits are technically demanded even though the
  // address computation might be vectorized in a smaller type.
  //
  // We start by looking at each entry that can be demoted. We compute the
  // maximum bit width required to store the scalar by using ValueTracking to
  // compute the number of high-order bits we can truncate.
  if (MaxBitWidth == DL->getTypeSizeInBits(TreeRoot[0]->getType())) {
    MaxBitWidth = 8u;

    // Determine if the sign bit of all the roots is known to be zero. If not,
    // IsKnownPositive is set to False.
    IsKnownPositive = all_of(TreeRoot, [&](Value *R) {
      bool KnownZero = false;
      bool KnownOne = false;
      ComputeSignBit(R, KnownZero, KnownOne, *DL);
      return KnownZero;
    });

    // Determine the maximum number of bits required to store the scalar
    // values.
    for (auto *Scalar : ToDemote) {
      auto NumSignBits = ComputeNumSignBits(Scalar, *DL, 0, AC, 0, DT);
      auto NumTypeBits = DL->getTypeSizeInBits(Scalar->getType());
      MaxBitWidth = std::max<unsigned>(NumTypeBits - NumSignBits, MaxBitWidth);
    }

    // If we can't prove that the sign bit is zero, we must add one to the
    // maximum bit width to account for the unknown sign bit. This preserves
    // the existing sign bit so we can safely sign-extend the root back to the
    // original type. Otherwise, if we know the sign bit is zero, we will
    // zero-extend the root instead.
    //
    // FIXME: This is somewhat suboptimal, as there will be cases where adding
    //        one to the maximum bit width will yield a larger-than-necessary
    //        type. In general, we need to add an extra bit only if we can't
    //        prove that the upper bit of the original type is equal to the
    //        upper bit of the proposed smaller type. If these two bits are the
    //        same (either zero or one) we know that sign-extending from the
    //        smaller type will result in the same value. Here, since we can't
    //        yet prove this, we are just making the proposed smaller type
    //        larger to ensure correctness.
    if (!IsKnownPositive)
      ++MaxBitWidth;
  }

  // Round MaxBitWidth up to the next power-of-two.
  if (!isPowerOf2_64(MaxBitWidth))
    MaxBitWidth = NextPowerOf2(MaxBitWidth);

  // If the maximum bit width we compute is less than the with of the roots'
  // type, we can proceed with the narrowing. Otherwise, do nothing.
  if (MaxBitWidth >= TreeRootIT->getBitWidth())
    return;

  // If we can truncate the root, we must collect additional values that might
  // be demoted as a result. That is, those seeded by truncations we will
  // modify.
  while (!Roots.empty())
    collectValuesToDemote(Roots.pop_back_val(), Expr, ToDemote, Roots);

  // Finally, map the values we can demote to the maximum bit with we computed.
  for (auto *Scalar : ToDemote)
    MinBWs[Scalar] = std::make_pair(MaxBitWidth, !IsKnownPositive);
}

namespace {
/// The SLPVectorizer Pass.
struct SLPVectorizer : public FunctionPass {
  SLPVectorizerPass Impl;

  /// Pass identification, replacement for typeid
  static char ID;

  explicit SLPVectorizer() : FunctionPass(ID) {
    initializeSLPVectorizerPass(*PassRegistry::getPassRegistry());
  }


  bool doInitialization(Module &M) override {
    return false;
  }

  bool runOnFunction(Function &F) override {
    if (skipFunction(F))
      return false;

    auto *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
    auto *TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
    auto *TLIP = getAnalysisIfAvailable<TargetLibraryInfoWrapperPass>();
    auto *TLI = TLIP ? &TLIP->getTLI() : nullptr;
    auto *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
    auto *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
    auto *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    auto *AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
    auto *DB = &getAnalysis<DemandedBitsWrapperPass>().getDemandedBits();

    return Impl.runImpl(F, SE, TTI, TLI, AA, LI, DT, AC, DB);
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    FunctionPass::getAnalysisUsage(AU);
    AU.addRequired<AssumptionCacheTracker>();
    AU.addRequired<ScalarEvolutionWrapperPass>();
    AU.addRequired<AAResultsWrapperPass>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    AU.addRequired<LoopInfoWrapperPass>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addRequired<DemandedBitsWrapperPass>();
    AU.addPreserved<LoopInfoWrapperPass>();
    AU.addPreserved<DominatorTreeWrapperPass>();
    AU.addPreserved<AAResultsWrapperPass>();
    AU.addPreserved<GlobalsAAWrapperPass>();
    AU.setPreservesCFG();
  }
};
} // end anonymous namespace

PreservedAnalyses SLPVectorizerPass::run(Function &F, FunctionAnalysisManager &AM) {
  auto *SE = &AM.getResult<ScalarEvolutionAnalysis>(F);
  auto *TTI = &AM.getResult<TargetIRAnalysis>(F);
  auto *TLI = AM.getCachedResult<TargetLibraryAnalysis>(F);
  auto *AA = &AM.getResult<AAManager>(F);
  auto *LI = &AM.getResult<LoopAnalysis>(F);
  auto *DT = &AM.getResult<DominatorTreeAnalysis>(F);
  auto *AC = &AM.getResult<AssumptionAnalysis>(F);
  auto *DB = &AM.getResult<DemandedBitsAnalysis>(F);

  bool Changed = runImpl(F, SE, TTI, TLI, AA, LI, DT, AC, DB);
  if (!Changed)
    return PreservedAnalyses::all();
  PreservedAnalyses PA;
  PA.preserve<LoopAnalysis>();
  PA.preserve<DominatorTreeAnalysis>();
  PA.preserve<AAManager>();
  PA.preserve<GlobalsAA>();
  return PA;
}

bool SLPVectorizerPass::runImpl(Function &F, ScalarEvolution *SE_,
                                TargetTransformInfo *TTI_,
                                TargetLibraryInfo *TLI_, AliasAnalysis *AA_,
                                LoopInfo *LI_, DominatorTree *DT_,
                                AssumptionCache *AC_, DemandedBits *DB_) {
  SE = SE_;
  TTI = TTI_;
  TLI = TLI_;
  AA = AA_;
  LI = LI_;
  DT = DT_;
  AC = AC_;
  DB = DB_;
  DL = &F.getParent()->getDataLayout();

  Stores.clear();
  GEPs.clear();
  bool Changed = false;

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

  // Don't vectorize when the attribute NoImplicitFloat is used.
  if (F.hasFnAttribute(Attribute::NoImplicitFloat))
    return false;

  DEBUG(dbgs() << "SLP: Analyzing blocks in " << F.getName() << ".\n");

  // Use the bottom up slp vectorizer to construct chains that start with
  // store instructions.
  BoUpSLP R(&F, SE, TTI, TLI, AA, LI, DT, AC, DB, DL);

  // A general note: the vectorizer must use BoUpSLP::eraseInstruction() to
  // delete instructions.

  // Scan the blocks in the function in post order.
  for (auto BB : post_order(&F.getEntryBlock())) {
    collectSeedInstructions(BB);

    // Vectorize trees that end at stores.
    if (!Stores.empty()) {
      DEBUG(dbgs() << "SLP: Found stores for " << Stores.size()
                   << " underlying objects.\n");
      Changed |= vectorizeStoreChains(R);
    }

    // Vectorize trees that end at reductions.
    Changed |= vectorizeChainsInBlock(BB, R);

    // Vectorize the index computations of getelementptr instructions. This
    // is primarily intended to catch gather-like idioms ending at
    // non-consecutive loads.
    if (!GEPs.empty()) {
      DEBUG(dbgs() << "SLP: Found GEPs for " << GEPs.size()
                   << " underlying objects.\n");
      Changed |= vectorizeGEPIndices(BB, R);
    }
  }

  if (Changed) {
    R.optimizeGatherSequence();
    DEBUG(dbgs() << "SLP: vectorized \"" << F.getName() << "\"\n");
    DEBUG(verifyFunction(F));
  }
  return Changed;
}

/// \brief Check that the Values in the slice in VL array are still existent in
/// the WeakVH array.
/// Vectorization of part of the VL array may cause later values in the VL array
/// to become invalid. We track when this has happened in the WeakVH array.
static bool hasValueBeenRAUWed(ArrayRef<Value *> VL, ArrayRef<WeakVH> VH,
                               unsigned SliceBegin, unsigned SliceSize) {
  VL = VL.slice(SliceBegin, SliceSize);
  VH = VH.slice(SliceBegin, SliceSize);
  return !std::equal(VL.begin(), VL.end(), VH.begin());
}

bool SLPVectorizerPass::vectorizeStoreChain(ArrayRef<Value *> Chain, BoUpSLP &R,
                                            unsigned VecRegSize) {
  unsigned ChainLen = Chain.size();
  DEBUG(dbgs() << "SLP: Analyzing a store chain of length " << ChainLen
        << "\n");
  unsigned Sz = R.getVectorElementSize(Chain[0]);
  unsigned VF = VecRegSize / Sz;

  if (!isPowerOf2_32(Sz) || VF < 2)
    return false;

  // Keep track of values that were deleted by vectorizing in the loop below.
  SmallVector<WeakVH, 8> TrackValues(Chain.begin(), Chain.end());

  bool Changed = false;
  // Look for profitable vectorizable trees at all offsets, starting at zero.
  for (unsigned i = 0, e = ChainLen; i < e; ++i) {
    if (i + VF > e)
      break;

    // Check that a previous iteration of this loop did not delete the Value.
    if (hasValueBeenRAUWed(Chain, TrackValues, i, VF))
      continue;

    DEBUG(dbgs() << "SLP: Analyzing " << VF << " stores at offset " << i
          << "\n");
    ArrayRef<Value *> Operands = Chain.slice(i, VF);

    R.buildTree(Operands);
    if (R.isTreeTinyAndNotFullyVectorizable())
      continue;

    R.computeMinimumValueSizes();

    int Cost = R.getTreeCost();

    DEBUG(dbgs() << "SLP: Found cost=" << Cost << " for VF=" << VF << "\n");
    if (Cost < -SLPCostThreshold) {
      DEBUG(dbgs() << "SLP: Decided to vectorize cost=" << Cost << "\n");
      R.vectorizeTree();

      // Move to the next bundle.
      i += VF - 1;
      Changed = true;
    }
  }

  return Changed;
}

bool SLPVectorizerPass::vectorizeStores(ArrayRef<StoreInst *> Stores,
                                        BoUpSLP &R) {
  SetVector<StoreInst *> Heads, Tails;
  SmallDenseMap<StoreInst *, StoreInst *> ConsecutiveChain;

  // We may run into multiple chains that merge into a single chain. We mark the
  // stores that we vectorized so that we don't visit the same store twice.
  BoUpSLP::ValueSet VectorizedStores;
  bool Changed = false;

  // Do a quadratic search on all of the given stores and find
  // all of the pairs of stores that follow each other.
  SmallVector<unsigned, 16> IndexQueue;
  for (unsigned i = 0, e = Stores.size(); i < e; ++i) {
    IndexQueue.clear();
    // If a store has multiple consecutive store candidates, search Stores
    // array according to the sequence: from i+1 to e, then from i-1 to 0.
    // This is because usually pairing with immediate succeeding or preceding
    // candidate create the best chance to find slp vectorization opportunity.
    unsigned j = 0;
    for (j = i + 1; j < e; ++j)
      IndexQueue.push_back(j);
    for (j = i; j > 0; --j)
      IndexQueue.push_back(j - 1);

    for (auto &k : IndexQueue) {
      if (isConsecutiveAccess(Stores[i], Stores[k], *DL, *SE)) {
        Tails.insert(Stores[k]);
        Heads.insert(Stores[i]);
        ConsecutiveChain[Stores[i]] = Stores[k];
        break;
      }
    }
  }

  // For stores that start but don't end a link in the chain:
  for (SetVector<StoreInst *>::iterator it = Heads.begin(), e = Heads.end();
       it != e; ++it) {
    if (Tails.count(*it))
      continue;

    // We found a store instr that starts a chain. Now follow the chain and try
    // to vectorize it.
    BoUpSLP::ValueList Operands;
    StoreInst *I = *it;
    // Collect the chain into a list.
    while (Tails.count(I) || Heads.count(I)) {
      if (VectorizedStores.count(I))
        break;
      Operands.push_back(I);
      // Move to the next value in the chain.
      I = ConsecutiveChain[I];
    }

    // FIXME: Is division-by-2 the correct step? Should we assert that the
    // register size is a power-of-2?
    for (unsigned Size = R.getMaxVecRegSize(); Size >= R.getMinVecRegSize();
         Size /= 2) {
      if (vectorizeStoreChain(Operands, R, Size)) {
        // Mark the vectorized stores so that we don't vectorize them again.
        VectorizedStores.insert(Operands.begin(), Operands.end());
        Changed = true;
        break;
      }
    }
  }

  return Changed;
}

void SLPVectorizerPass::collectSeedInstructions(BasicBlock *BB) {

  // Initialize the collections. We will make a single pass over the block.
  Stores.clear();
  GEPs.clear();

  // Visit the store and getelementptr instructions in BB and organize them in
  // Stores and GEPs according to the underlying objects of their pointer
  // operands.
  for (Instruction &I : *BB) {

    // Ignore store instructions that are volatile or have a pointer operand
    // that doesn't point to a scalar type.
    if (auto *SI = dyn_cast<StoreInst>(&I)) {
      if (!SI->isSimple())
        continue;
      if (!isValidElementType(SI->getValueOperand()->getType()))
        continue;
      Stores[GetUnderlyingObject(SI->getPointerOperand(), *DL)].push_back(SI);
    }

    // Ignore getelementptr instructions that have more than one index, a
    // constant index, or a pointer operand that doesn't point to a scalar
    // type.
    else if (auto *GEP = dyn_cast<GetElementPtrInst>(&I)) {
      auto Idx = GEP->idx_begin()->get();
      if (GEP->getNumIndices() > 1 || isa<Constant>(Idx))
        continue;
      if (!isValidElementType(Idx->getType()))
        continue;
      if (GEP->getType()->isVectorTy())
        continue;
      GEPs[GetUnderlyingObject(GEP->getPointerOperand(), *DL)].push_back(GEP);
    }
  }
}

bool SLPVectorizerPass::tryToVectorizePair(Value *A, Value *B, BoUpSLP &R) {
  if (!A || !B)
    return false;
  Value *VL[] = { A, B };
  return tryToVectorizeList(VL, R, None, true);
}

bool SLPVectorizerPass::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R,
                                           ArrayRef<Value *> BuildVector,
                                           bool AllowReorder) {
  if (VL.size() < 2)
    return false;

  DEBUG(dbgs() << "SLP: Trying to vectorize a list of length = " << VL.size()
               << ".\n");

  // Check that all of the parts are scalar instructions of the same type.
  Instruction *I0 = dyn_cast<Instruction>(VL[0]);
  if (!I0)
    return false;

  unsigned Opcode0 = I0->getOpcode();

  unsigned Sz = R.getVectorElementSize(I0);
  unsigned MinVF = std::max(2U, R.getMinVecRegSize() / Sz);
  unsigned MaxVF = std::max<unsigned>(PowerOf2Floor(VL.size()), MinVF);
  if (MaxVF < 2)
    return false;

  for (Value *V : VL) {
    Type *Ty = V->getType();
    if (!isValidElementType(Ty))
      return false;
    Instruction *Inst = dyn_cast<Instruction>(V);
    if (!Inst || Inst->getOpcode() != Opcode0)
      return false;
  }

  bool Changed = false;

  // Keep track of values that were deleted by vectorizing in the loop below.
  SmallVector<WeakVH, 8> TrackValues(VL.begin(), VL.end());

  unsigned NextInst = 0, MaxInst = VL.size();
  for (unsigned VF = MaxVF; NextInst + 1 < MaxInst && VF >= MinVF;
       VF /= 2) {
    // No actual vectorization should happen, if number of parts is the same as
    // provided vectorization factor (i.e. the scalar type is used for vector
    // code during codegen).
    auto *VecTy = VectorType::get(VL[0]->getType(), VF);
    if (TTI->getNumberOfParts(VecTy) == VF)
      continue;
    for (unsigned I = NextInst; I < MaxInst; ++I) {
      unsigned OpsWidth = 0;

      if (I + VF > MaxInst)
        OpsWidth = MaxInst - I;
      else
        OpsWidth = VF;

      if (!isPowerOf2_32(OpsWidth) || OpsWidth < 2)
        break;

      // Check that a previous iteration of this loop did not delete the Value.
      if (hasValueBeenRAUWed(VL, TrackValues, I, OpsWidth))
        continue;

      DEBUG(dbgs() << "SLP: Analyzing " << OpsWidth << " operations "
                   << "\n");
      ArrayRef<Value *> Ops = VL.slice(I, OpsWidth);

      ArrayRef<Value *> BuildVectorSlice;
      if (!BuildVector.empty())
        BuildVectorSlice = BuildVector.slice(I, OpsWidth);

      R.buildTree(Ops, BuildVectorSlice);
      // TODO: check if we can allow reordering for more cases.
      if (AllowReorder && R.shouldReorder()) {
        // Conceptually, there is nothing actually preventing us from trying to
        // reorder a larger list. In fact, we do exactly this when vectorizing
        // reductions. However, at this point, we only expect to get here from
        // tryToVectorizePair().
        assert(Ops.size() == 2);
        assert(BuildVectorSlice.empty());
        Value *ReorderedOps[] = {Ops[1], Ops[0]};
        R.buildTree(ReorderedOps, None);
      }
      if (R.isTreeTinyAndNotFullyVectorizable())
        continue;

      R.computeMinimumValueSizes();
      int Cost = R.getTreeCost();

      if (Cost < -SLPCostThreshold) {
        DEBUG(dbgs() << "SLP: Vectorizing list at cost:" << Cost << ".\n");
        Value *VectorizedRoot = R.vectorizeTree();

        // Reconstruct the build vector by extracting the vectorized root. This
        // way we handle the case where some elements of the vector are
        // undefined.
        //  (return (inserelt <4 xi32> (insertelt undef (opd0) 0) (opd1) 2))
        if (!BuildVectorSlice.empty()) {
          // The insert point is the last build vector instruction. The
          // vectorized root will precede it. This guarantees that we get an
          // instruction. The vectorized tree could have been constant folded.
          Instruction *InsertAfter = cast<Instruction>(BuildVectorSlice.back());
          unsigned VecIdx = 0;
          for (auto &V : BuildVectorSlice) {
            IRBuilder<NoFolder> Builder(InsertAfter->getParent(),
                                        ++BasicBlock::iterator(InsertAfter));
            Instruction *I = cast<Instruction>(V);
            assert(isa<InsertElementInst>(I) || isa<InsertValueInst>(I));
            Instruction *Extract =
                cast<Instruction>(Builder.CreateExtractElement(
                    VectorizedRoot, Builder.getInt32(VecIdx++)));
            I->setOperand(1, Extract);
            I->removeFromParent();
            I->insertAfter(Extract);
            InsertAfter = I;
          }
        }
        // Move to the next bundle.
        I += VF - 1;
        NextInst = I + 1;
        Changed = true;
      }
    }
  }

  return Changed;
}

bool SLPVectorizerPass::tryToVectorize(BinaryOperator *V, BoUpSLP &R) {
  if (!V)
    return false;

  // Try to vectorize V.
  if (tryToVectorizePair(V->getOperand(0), V->getOperand(1), R))
    return true;

  BinaryOperator *A = dyn_cast<BinaryOperator>(V->getOperand(0));
  BinaryOperator *B = dyn_cast<BinaryOperator>(V->getOperand(1));
  // Try to skip B.
  if (B && B->hasOneUse()) {
    BinaryOperator *B0 = dyn_cast<BinaryOperator>(B->getOperand(0));
    BinaryOperator *B1 = dyn_cast<BinaryOperator>(B->getOperand(1));
    if (tryToVectorizePair(A, B0, R)) {
      return true;
    }
    if (tryToVectorizePair(A, B1, R)) {
      return true;
    }
  }

  // Try to skip A.
  if (A && A->hasOneUse()) {
    BinaryOperator *A0 = dyn_cast<BinaryOperator>(A->getOperand(0));
    BinaryOperator *A1 = dyn_cast<BinaryOperator>(A->getOperand(1));
    if (tryToVectorizePair(A0, B, R)) {
      return true;
    }
    if (tryToVectorizePair(A1, B, R)) {
      return true;
    }
  }
  return 0;
}

/// \brief Generate a shuffle mask to be used in a reduction tree.
///
/// \param VecLen The length of the vector to be reduced.
/// \param NumEltsToRdx The number of elements that should be reduced in the
///        vector.
/// \param IsPairwise Whether the reduction is a pairwise or splitting
///        reduction. A pairwise reduction will generate a mask of
///        <0,2,...> or <1,3,..> while a splitting reduction will generate
///        <2,3, undef,undef> for a vector of 4 and NumElts = 2.
/// \param IsLeft True will generate a mask of even elements, odd otherwise.
static Value *createRdxShuffleMask(unsigned VecLen, unsigned NumEltsToRdx,
                                   bool IsPairwise, bool IsLeft,
                                   IRBuilder<> &Builder) {
  assert((IsPairwise || !IsLeft) && "Don't support a <0,1,undef,...> mask");

  SmallVector<Constant *, 32> ShuffleMask(
      VecLen, UndefValue::get(Builder.getInt32Ty()));

  if (IsPairwise)
    // Build a mask of 0, 2, ... (left) or 1, 3, ... (right).
    for (unsigned i = 0; i != NumEltsToRdx; ++i)
      ShuffleMask[i] = Builder.getInt32(2 * i + !IsLeft);
  else
    // Move the upper half of the vector to the lower half.
    for (unsigned i = 0; i != NumEltsToRdx; ++i)
      ShuffleMask[i] = Builder.getInt32(NumEltsToRdx + i);

  return ConstantVector::get(ShuffleMask);
}

namespace {
/// Model horizontal reductions.
///
/// A horizontal reduction is a tree of reduction operations (currently add and
/// fadd) that has operations that can be put into a vector as its leaf.
/// For example, this tree:
///
/// mul mul mul mul
///  \  /    \  /
///   +       +
///    \     /
///       +
/// This tree has "mul" as its reduced values and "+" as its reduction
/// operations. A reduction might be feeding into a store or a binary operation
/// feeding a phi.
///    ...
///    \  /
///     +
///     |
///  phi +=
///
///  Or:
///    ...
///    \  /
///     +
///     |
///   *p =
///
class HorizontalReduction {
  SmallVector<Value *, 16> ReductionOps;
  SmallVector<Value *, 32> ReducedVals;

  BinaryOperator *ReductionRoot;
  // After successfull horizontal reduction vectorization attempt for PHI node
  // vectorizer tries to update root binary op by combining vectorized tree and
  // the ReductionPHI node. But during vectorization this ReductionPHI can be
  // vectorized itself and replaced by the undef value, while the instruction
  // itself is marked for deletion. This 'marked for deletion' PHI node then can
  // be used in new binary operation, causing "Use still stuck around after Def
  // is destroyed" crash upon PHI node deletion.
  WeakVH ReductionPHI;

  /// The opcode of the reduction.
  unsigned ReductionOpcode;
  /// The opcode of the values we perform a reduction on.
  unsigned ReducedValueOpcode;
  /// Should we model this reduction as a pairwise reduction tree or a tree that
  /// splits the vector in halves and adds those halves.
  bool IsPairwiseReduction;

public:
  /// The width of one full horizontal reduction operation.
  unsigned ReduxWidth;

  /// Minimal width of available vector registers. It's used to determine
  /// ReduxWidth.
  unsigned MinVecRegSize;

  HorizontalReduction(unsigned MinVecRegSize)
      : ReductionRoot(nullptr), ReductionOpcode(0), ReducedValueOpcode(0),
        IsPairwiseReduction(false), ReduxWidth(0),
        MinVecRegSize(MinVecRegSize) {}

  /// \brief Try to find a reduction tree.
  bool matchAssociativeReduction(PHINode *Phi, BinaryOperator *B) {
    assert((!Phi || is_contained(Phi->operands(), B)) &&
           "Thi phi needs to use the binary operator");

    // We could have a initial reductions that is not an add.
    //  r *= v1 + v2 + v3 + v4
    // In such a case start looking for a tree rooted in the first '+'.
    if (Phi) {
      if (B->getOperand(0) == Phi) {
        Phi = nullptr;
        B = dyn_cast<BinaryOperator>(B->getOperand(1));
      } else if (B->getOperand(1) == Phi) {
        Phi = nullptr;
        B = dyn_cast<BinaryOperator>(B->getOperand(0));
      }
    }

    if (!B)
      return false;

    Type *Ty = B->getType();
    if (!isValidElementType(Ty))
      return false;

    const DataLayout &DL = B->getModule()->getDataLayout();
    ReductionOpcode = B->getOpcode();
    ReducedValueOpcode = 0;
    // FIXME: Register size should be a parameter to this function, so we can
    // try different vectorization factors.
    ReduxWidth = MinVecRegSize / DL.getTypeSizeInBits(Ty);
    ReductionRoot = B;
    ReductionPHI = Phi;

    if (ReduxWidth < 4)
      return false;

    // We currently only support adds.
    if (ReductionOpcode != Instruction::Add &&
        ReductionOpcode != Instruction::FAdd)
      return false;

    // Post order traverse the reduction tree starting at B. We only handle true
    // trees containing only binary operators or selects.
    SmallVector<std::pair<Instruction *, unsigned>, 32> Stack;
    Stack.push_back(std::make_pair(B, 0));
    while (!Stack.empty()) {
      Instruction *TreeN = Stack.back().first;
      unsigned EdgeToVist = Stack.back().second++;
      bool IsReducedValue = TreeN->getOpcode() != ReductionOpcode;

      // Only handle trees in the current basic block.
      if (TreeN->getParent() != B->getParent())
        return false;

      // Each tree node needs to have one user except for the ultimate
      // reduction.
      if (!TreeN->hasOneUse() && TreeN != B)
        return false;

      // Postorder vist.
      if (EdgeToVist == 2 || IsReducedValue) {
        if (IsReducedValue) {
          // Make sure that the opcodes of the operations that we are going to
          // reduce match.
          if (!ReducedValueOpcode)
            ReducedValueOpcode = TreeN->getOpcode();
          else if (ReducedValueOpcode != TreeN->getOpcode())
            return false;
          ReducedVals.push_back(TreeN);
        } else {
          // We need to be able to reassociate the adds.
          if (!TreeN->isAssociative())
            return false;
          ReductionOps.push_back(TreeN);
        }
        // Retract.
        Stack.pop_back();
        continue;
      }

      // Visit left or right.
      Value *NextV = TreeN->getOperand(EdgeToVist);
      if (NextV != Phi) {
        auto *I = dyn_cast<Instruction>(NextV);
        // Continue analysis if the next operand is a reduction operation or
        // (possibly) a reduced value. If the reduced value opcode is not set,
        // the first met operation != reduction operation is considered as the
        // reduced value class.
        if (I && (!ReducedValueOpcode || I->getOpcode() == ReducedValueOpcode ||
                  I->getOpcode() == ReductionOpcode)) {
          if (!ReducedValueOpcode && I->getOpcode() != ReductionOpcode)
            ReducedValueOpcode = I->getOpcode();
          Stack.push_back(std::make_pair(I, 0));
          continue;
        }
        return false;
      }
    }
    return true;
  }

  /// \brief Attempt to vectorize the tree found by
  /// matchAssociativeReduction.
  bool tryToReduce(BoUpSLP &V, TargetTransformInfo *TTI) {
    if (ReducedVals.empty())
      return false;

    unsigned NumReducedVals = ReducedVals.size();
    if (NumReducedVals < ReduxWidth)
      return false;

    Value *VectorizedTree = nullptr;
    IRBuilder<> Builder(ReductionRoot);
    FastMathFlags Unsafe;
    Unsafe.setUnsafeAlgebra();
    Builder.setFastMathFlags(Unsafe);
    unsigned i = 0;

    for (; i < NumReducedVals - ReduxWidth + 1; i += ReduxWidth) {
      auto VL = makeArrayRef(&ReducedVals[i], ReduxWidth);
      V.buildTree(VL, ReductionOps);
      if (V.shouldReorder()) {
        SmallVector<Value *, 8> Reversed(VL.rbegin(), VL.rend());
        V.buildTree(Reversed, ReductionOps);
      }
      if (V.isTreeTinyAndNotFullyVectorizable())
        continue;

      V.computeMinimumValueSizes();

      // Estimate cost.
      int Cost = V.getTreeCost() + getReductionCost(TTI, ReducedVals[i]);
      if (Cost >= -SLPCostThreshold)
        break;

      DEBUG(dbgs() << "SLP: Vectorizing horizontal reduction at cost:" << Cost
                   << ". (HorRdx)\n");

      // Vectorize a tree.
      DebugLoc Loc = cast<Instruction>(ReducedVals[i])->getDebugLoc();
      Value *VectorizedRoot = V.vectorizeTree();

      // Emit a reduction.
      Value *ReducedSubTree = emitReduction(VectorizedRoot, Builder);
      if (VectorizedTree) {
        Builder.SetCurrentDebugLocation(Loc);
        VectorizedTree = createBinOp(Builder, ReductionOpcode, VectorizedTree,
                                     ReducedSubTree, "bin.rdx");
      } else
        VectorizedTree = ReducedSubTree;
    }

    if (VectorizedTree) {
      // Finish the reduction.
      for (; i < NumReducedVals; ++i) {
        Builder.SetCurrentDebugLocation(
          cast<Instruction>(ReducedVals[i])->getDebugLoc());
        VectorizedTree = createBinOp(Builder, ReductionOpcode, VectorizedTree,
                                     ReducedVals[i]);
      }
      // Update users.
      if (ReductionPHI && !isa<UndefValue>(ReductionPHI)) {
        assert(ReductionRoot && "Need a reduction operation");
        ReductionRoot->setOperand(0, VectorizedTree);
        ReductionRoot->setOperand(1, ReductionPHI);
      } else
        ReductionRoot->replaceAllUsesWith(VectorizedTree);
    }
    return VectorizedTree != nullptr;
  }

  unsigned numReductionValues() const {
    return ReducedVals.size();
  }

private:
  /// \brief Calculate the cost of a reduction.
  int getReductionCost(TargetTransformInfo *TTI, Value *FirstReducedVal) {
    Type *ScalarTy = FirstReducedVal->getType();
    Type *VecTy = VectorType::get(ScalarTy, ReduxWidth);

    int PairwiseRdxCost = TTI->getReductionCost(ReductionOpcode, VecTy, true);
    int SplittingRdxCost = TTI->getReductionCost(ReductionOpcode, VecTy, false);

    IsPairwiseReduction = PairwiseRdxCost < SplittingRdxCost;
    int VecReduxCost = IsPairwiseReduction ? PairwiseRdxCost : SplittingRdxCost;

    int ScalarReduxCost =
        (ReduxWidth - 1) *
        TTI->getArithmeticInstrCost(ReductionOpcode, ScalarTy);

    DEBUG(dbgs() << "SLP: Adding cost " << VecReduxCost - ScalarReduxCost
                 << " for reduction that starts with " << *FirstReducedVal
                 << " (It is a "
                 << (IsPairwiseReduction ? "pairwise" : "splitting")
                 << " reduction)\n");

    return VecReduxCost - ScalarReduxCost;
  }

  static Value *createBinOp(IRBuilder<> &Builder, unsigned Opcode, Value *L,
                            Value *R, const Twine &Name = "") {
    if (Opcode == Instruction::FAdd)
      return Builder.CreateFAdd(L, R, Name);
    return Builder.CreateBinOp((Instruction::BinaryOps)Opcode, L, R, Name);
  }

  /// \brief Emit a horizontal reduction of the vectorized value.
  Value *emitReduction(Value *VectorizedValue, IRBuilder<> &Builder) {
    assert(VectorizedValue && "Need to have a vectorized tree node");
    assert(isPowerOf2_32(ReduxWidth) &&
           "We only handle power-of-two reductions for now");

    Value *TmpVec = VectorizedValue;
    for (unsigned i = ReduxWidth / 2; i != 0; i >>= 1) {
      if (IsPairwiseReduction) {
        Value *LeftMask =
          createRdxShuffleMask(ReduxWidth, i, true, true, Builder);
        Value *RightMask =
          createRdxShuffleMask(ReduxWidth, i, true, false, Builder);

        Value *LeftShuf = Builder.CreateShuffleVector(
          TmpVec, UndefValue::get(TmpVec->getType()), LeftMask, "rdx.shuf.l");
        Value *RightShuf = Builder.CreateShuffleVector(
          TmpVec, UndefValue::get(TmpVec->getType()), (RightMask),
          "rdx.shuf.r");
        TmpVec = createBinOp(Builder, ReductionOpcode, LeftShuf, RightShuf,
                             "bin.rdx");
      } else {
        Value *UpperHalf =
          createRdxShuffleMask(ReduxWidth, i, false, false, Builder);
        Value *Shuf = Builder.CreateShuffleVector(
          TmpVec, UndefValue::get(TmpVec->getType()), UpperHalf, "rdx.shuf");
        TmpVec = createBinOp(Builder, ReductionOpcode, TmpVec, Shuf, "bin.rdx");
      }
    }

    // The result is in the first element of the vector.
    return Builder.CreateExtractElement(TmpVec, Builder.getInt32(0));
  }
};
} // end anonymous namespace

/// \brief Recognize construction of vectors like
///  %ra = insertelement <4 x float> undef, float %s0, i32 0
///  %rb = insertelement <4 x float> %ra, float %s1, i32 1
///  %rc = insertelement <4 x float> %rb, float %s2, i32 2
///  %rd = insertelement <4 x float> %rc, float %s3, i32 3
///
/// Returns true if it matches
///
static bool findBuildVector(InsertElementInst *FirstInsertElem,
                            SmallVectorImpl<Value *> &BuildVector,
                            SmallVectorImpl<Value *> &BuildVectorOpds) {
  if (!isa<UndefValue>(FirstInsertElem->getOperand(0)))
    return false;

  InsertElementInst *IE = FirstInsertElem;
  while (true) {
    BuildVector.push_back(IE);
    BuildVectorOpds.push_back(IE->getOperand(1));

    if (IE->use_empty())
      return false;

    InsertElementInst *NextUse = dyn_cast<InsertElementInst>(IE->user_back());
    if (!NextUse)
      return true;

    // If this isn't the final use, make sure the next insertelement is the only
    // use. It's OK if the final constructed vector is used multiple times
    if (!IE->hasOneUse())
      return false;

    IE = NextUse;
  }

  return false;
}

/// \brief Like findBuildVector, but looks backwards for construction of aggregate.
///
/// \return true if it matches.
static bool findBuildAggregate(InsertValueInst *IV,
                               SmallVectorImpl<Value *> &BuildVector,
                               SmallVectorImpl<Value *> &BuildVectorOpds) {
  if (!IV->hasOneUse())
    return false;
  Value *V = IV->getAggregateOperand();
  if (!isa<UndefValue>(V)) {
    InsertValueInst *I = dyn_cast<InsertValueInst>(V);
    if (!I || !findBuildAggregate(I, BuildVector, BuildVectorOpds))
      return false;
  }
  BuildVector.push_back(IV);
  BuildVectorOpds.push_back(IV->getInsertedValueOperand());
  return true;
}

static bool PhiTypeSorterFunc(Value *V, Value *V2) {
  return V->getType() < V2->getType();
}

/// \brief Try and get a reduction value from a phi node.
///
/// Given a phi node \p P in a block \p ParentBB, consider possible reductions
/// if they come from either \p ParentBB or a containing loop latch.
///
/// \returns A candidate reduction value if possible, or \code nullptr \endcode
/// if not possible.
static Value *getReductionValue(const DominatorTree *DT, PHINode *P,
                                BasicBlock *ParentBB, LoopInfo *LI) {
  // There are situations where the reduction value is not dominated by the
  // reduction phi. Vectorizing such cases has been reported to cause
  // miscompiles. See PR25787.
  auto DominatedReduxValue = [&](Value *R) {
    return (
        dyn_cast<Instruction>(R) &&
        DT->dominates(P->getParent(), dyn_cast<Instruction>(R)->getParent()));
  };

  Value *Rdx = nullptr;

  // Return the incoming value if it comes from the same BB as the phi node.
  if (P->getIncomingBlock(0) == ParentBB) {
    Rdx = P->getIncomingValue(0);
  } else if (P->getIncomingBlock(1) == ParentBB) {
    Rdx = P->getIncomingValue(1);
  }

  if (Rdx && DominatedReduxValue(Rdx))
    return Rdx;

  // Otherwise, check whether we have a loop latch to look at.
  Loop *BBL = LI->getLoopFor(ParentBB);
  if (!BBL)
    return nullptr;
  BasicBlock *BBLatch = BBL->getLoopLatch();
  if (!BBLatch)
    return nullptr;

  // There is a loop latch, return the incoming value if it comes from
  // that. This reduction pattern occasionally turns up.
  if (P->getIncomingBlock(0) == BBLatch) {
    Rdx = P->getIncomingValue(0);
  } else if (P->getIncomingBlock(1) == BBLatch) {
    Rdx = P->getIncomingValue(1);
  }

  if (Rdx && DominatedReduxValue(Rdx))
    return Rdx;

  return nullptr;
}

/// \brief Attempt to reduce a horizontal reduction.
/// If it is legal to match a horizontal reduction feeding
/// the phi node P with reduction operators BI, then check if it
/// can be done.
/// \returns true if a horizontal reduction was matched and reduced.
/// \returns false if a horizontal reduction was not matched.
static bool canMatchHorizontalReduction(PHINode *P, BinaryOperator *BI,
                                        BoUpSLP &R, TargetTransformInfo *TTI,
                                        unsigned MinRegSize) {
  if (!ShouldVectorizeHor)
    return false;

  HorizontalReduction HorRdx(MinRegSize);
  if (!HorRdx.matchAssociativeReduction(P, BI))
    return false;

  // If there is a sufficient number of reduction values, reduce
  // to a nearby power-of-2. Can safely generate oversized
  // vectors and rely on the backend to split them to legal sizes.
  HorRdx.ReduxWidth =
    std::max((uint64_t)4, PowerOf2Floor(HorRdx.numReductionValues()));

  return HorRdx.tryToReduce(R, TTI);
}

bool SLPVectorizerPass::vectorizeChainsInBlock(BasicBlock *BB, BoUpSLP &R) {
  bool Changed = false;
  SmallVector<Value *, 4> Incoming;
  SmallSet<Value *, 16> VisitedInstrs;

  bool HaveVectorizedPhiNodes = true;
  while (HaveVectorizedPhiNodes) {
    HaveVectorizedPhiNodes = false;

    // Collect the incoming values from the PHIs.
    Incoming.clear();
    for (Instruction &I : *BB) {
      PHINode *P = dyn_cast<PHINode>(&I);
      if (!P)
        break;

      if (!VisitedInstrs.count(P))
        Incoming.push_back(P);
    }

    // Sort by type.
    std::stable_sort(Incoming.begin(), Incoming.end(), PhiTypeSorterFunc);

    // Try to vectorize elements base on their type.
    for (SmallVector<Value *, 4>::iterator IncIt = Incoming.begin(),
                                           E = Incoming.end();
         IncIt != E;) {

      // Look for the next elements with the same type.
      SmallVector<Value *, 4>::iterator SameTypeIt = IncIt;
      while (SameTypeIt != E &&
             (*SameTypeIt)->getType() == (*IncIt)->getType()) {
        VisitedInstrs.insert(*SameTypeIt);
        ++SameTypeIt;
      }

      // Try to vectorize them.
      unsigned NumElts = (SameTypeIt - IncIt);
      DEBUG(errs() << "SLP: Trying to vectorize starting at PHIs (" << NumElts << ")\n");
      if (NumElts > 1 && tryToVectorizeList(makeArrayRef(IncIt, NumElts), R)) {
        // Success start over because instructions might have been changed.
        HaveVectorizedPhiNodes = true;
        Changed = true;
        break;
      }

      // Start over at the next instruction of a different type (or the end).
      IncIt = SameTypeIt;
    }
  }

  VisitedInstrs.clear();

  for (BasicBlock::iterator it = BB->begin(), e = BB->end(); it != e; it++) {
    // We may go through BB multiple times so skip the one we have checked.
    if (!VisitedInstrs.insert(&*it).second)
      continue;

    if (isa<DbgInfoIntrinsic>(it))
      continue;

    // Try to vectorize reductions that use PHINodes.
    if (PHINode *P = dyn_cast<PHINode>(it)) {
      // Check that the PHI is a reduction PHI.
      if (P->getNumIncomingValues() != 2)
        return Changed;

      Value *Rdx = getReductionValue(DT, P, BB, LI);

      // Check if this is a Binary Operator.
      BinaryOperator *BI = dyn_cast_or_null<BinaryOperator>(Rdx);
      if (!BI)
        continue;

      // Try to match and vectorize a horizontal reduction.
      if (canMatchHorizontalReduction(P, BI, R, TTI, R.getMinVecRegSize())) {
        Changed = true;
        it = BB->begin();
        e = BB->end();
        continue;
      }

     Value *Inst = BI->getOperand(0);
      if (Inst == P)
        Inst = BI->getOperand(1);

      if (tryToVectorize(dyn_cast<BinaryOperator>(Inst), R)) {
        // We would like to start over since some instructions are deleted
        // and the iterator may become invalid value.
        Changed = true;
        it = BB->begin();
        e = BB->end();
        continue;
      }

      continue;
    }

    if (ShouldStartVectorizeHorAtStore)
      if (StoreInst *SI = dyn_cast<StoreInst>(it))
        if (BinaryOperator *BinOp =
                dyn_cast<BinaryOperator>(SI->getValueOperand())) {
          if (canMatchHorizontalReduction(nullptr, BinOp, R, TTI,
                                          R.getMinVecRegSize()) ||
              tryToVectorize(BinOp, R)) {
            Changed = true;
            it = BB->begin();
            e = BB->end();
            continue;
          }
        }

    // Try to vectorize horizontal reductions feeding into a return.
    if (ReturnInst *RI = dyn_cast<ReturnInst>(it))
      if (RI->getNumOperands() != 0)
        if (BinaryOperator *BinOp =
                dyn_cast<BinaryOperator>(RI->getOperand(0))) {
          DEBUG(dbgs() << "SLP: Found a return to vectorize.\n");
          if (canMatchHorizontalReduction(nullptr, BinOp, R, TTI,
                                          R.getMinVecRegSize()) ||
              tryToVectorizePair(BinOp->getOperand(0), BinOp->getOperand(1),
                                 R)) {
            Changed = true;
            it = BB->begin();
            e = BB->end();
            continue;
          }
        }

    // Try to vectorize trees that start at compare instructions.
    if (CmpInst *CI = dyn_cast<CmpInst>(it)) {
      if (tryToVectorizePair(CI->getOperand(0), CI->getOperand(1), R)) {
        Changed = true;
        // We would like to start over since some instructions are deleted
        // and the iterator may become invalid value.
        it = BB->begin();
        e = BB->end();
        continue;
      }

      for (int i = 0; i < 2; ++i) {
        if (BinaryOperator *BI = dyn_cast<BinaryOperator>(CI->getOperand(i))) {
          if (tryToVectorizePair(BI->getOperand(0), BI->getOperand(1), R)) {
            Changed = true;
            // We would like to start over since some instructions are deleted
            // and the iterator may become invalid value.
            it = BB->begin();
            e = BB->end();
            break;
          }
        }
      }
      continue;
    }

    // Try to vectorize trees that start at insertelement instructions.
    if (InsertElementInst *FirstInsertElem = dyn_cast<InsertElementInst>(it)) {
      SmallVector<Value *, 16> BuildVector;
      SmallVector<Value *, 16> BuildVectorOpds;
      if (!findBuildVector(FirstInsertElem, BuildVector, BuildVectorOpds))
        continue;

      // Vectorize starting with the build vector operands ignoring the
      // BuildVector instructions for the purpose of scheduling and user
      // extraction.
      if (tryToVectorizeList(BuildVectorOpds, R, BuildVector)) {
        Changed = true;
        it = BB->begin();
        e = BB->end();
      }

      continue;
    }

    // Try to vectorize trees that start at insertvalue instructions feeding into
    // a store.
    if (StoreInst *SI = dyn_cast<StoreInst>(it)) {
      if (InsertValueInst *LastInsertValue = dyn_cast<InsertValueInst>(SI->getValueOperand())) {
        const DataLayout &DL = BB->getModule()->getDataLayout();
        if (R.canMapToVector(SI->getValueOperand()->getType(), DL)) {
          SmallVector<Value *, 16> BuildVector;
          SmallVector<Value *, 16> BuildVectorOpds;
          if (!findBuildAggregate(LastInsertValue, BuildVector, BuildVectorOpds))
            continue;

          DEBUG(dbgs() << "SLP: store of array mappable to vector: " << *SI << "\n");
          if (tryToVectorizeList(BuildVectorOpds, R, BuildVector, false)) {
            Changed = true;
            it = BB->begin();
            e = BB->end();
          }
          continue;
        }
      }
    }
  }

  return Changed;
}

bool SLPVectorizerPass::vectorizeGEPIndices(BasicBlock *BB, BoUpSLP &R) {
  auto Changed = false;
  for (auto &Entry : GEPs) {

    // If the getelementptr list has fewer than two elements, there's nothing
    // to do.
    if (Entry.second.size() < 2)
      continue;

    DEBUG(dbgs() << "SLP: Analyzing a getelementptr list of length "
                 << Entry.second.size() << ".\n");

    // We process the getelementptr list in chunks of 16 (like we do for
    // stores) to minimize compile-time.
    for (unsigned BI = 0, BE = Entry.second.size(); BI < BE; BI += 16) {
      auto Len = std::min<unsigned>(BE - BI, 16);
      auto GEPList = makeArrayRef(&Entry.second[BI], Len);

      // Initialize a set a candidate getelementptrs. Note that we use a
      // SetVector here to preserve program order. If the index computations
      // are vectorizable and begin with loads, we want to minimize the chance
      // of having to reorder them later.
      SetVector<Value *> Candidates(GEPList.begin(), GEPList.end());

      // Some of the candidates may have already been vectorized after we
      // initially collected them. If so, the WeakVHs will have nullified the
      // values, so remove them from the set of candidates.
      Candidates.remove(nullptr);

      // Remove from the set of candidates all pairs of getelementptrs with
      // constant differences. Such getelementptrs are likely not good
      // candidates for vectorization in a bottom-up phase since one can be
      // computed from the other. We also ensure all candidate getelementptr
      // indices are unique.
      for (int I = 0, E = GEPList.size(); I < E && Candidates.size() > 1; ++I) {
        auto *GEPI = cast<GetElementPtrInst>(GEPList[I]);
        if (!Candidates.count(GEPI))
          continue;
        auto *SCEVI = SE->getSCEV(GEPList[I]);
        for (int J = I + 1; J < E && Candidates.size() > 1; ++J) {
          auto *GEPJ = cast<GetElementPtrInst>(GEPList[J]);
          auto *SCEVJ = SE->getSCEV(GEPList[J]);
          if (isa<SCEVConstant>(SE->getMinusSCEV(SCEVI, SCEVJ))) {
            Candidates.remove(GEPList[I]);
            Candidates.remove(GEPList[J]);
          } else if (GEPI->idx_begin()->get() == GEPJ->idx_begin()->get()) {
            Candidates.remove(GEPList[J]);
          }
        }
      }

      // We break out of the above computation as soon as we know there are
      // fewer than two candidates remaining.
      if (Candidates.size() < 2)
        continue;

      // Add the single, non-constant index of each candidate to the bundle. We
      // ensured the indices met these constraints when we originally collected
      // the getelementptrs.
      SmallVector<Value *, 16> Bundle(Candidates.size());
      auto BundleIndex = 0u;
      for (auto *V : Candidates) {
        auto *GEP = cast<GetElementPtrInst>(V);
        auto *GEPIdx = GEP->idx_begin()->get();
        assert(GEP->getNumIndices() == 1 || !isa<Constant>(GEPIdx));
        Bundle[BundleIndex++] = GEPIdx;
      }

      // Try and vectorize the indices. We are currently only interested in
      // gather-like cases of the form:
      //
      // ... = g[a[0] - b[0]] + g[a[1] - b[1]] + ...
      //
      // where the loads of "a", the loads of "b", and the subtractions can be
      // performed in parallel. It's likely that detecting this pattern in a
      // bottom-up phase will be simpler and less costly than building a
      // full-blown top-down phase beginning at the consecutive loads.
      Changed |= tryToVectorizeList(Bundle, R);
    }
  }
  return Changed;
}

bool SLPVectorizerPass::vectorizeStoreChains(BoUpSLP &R) {
  bool Changed = false;
  // Attempt to sort and vectorize each of the store-groups.
  for (StoreListMap::iterator it = Stores.begin(), e = Stores.end(); it != e;
       ++it) {
    if (it->second.size() < 2)
      continue;

    DEBUG(dbgs() << "SLP: Analyzing a store chain of length "
          << it->second.size() << ".\n");

    // Process the stores in chunks of 16.
    // TODO: The limit of 16 inhibits greater vectorization factors.
    //       For example, AVX2 supports v32i8. Increasing this limit, however,
    //       may cause a significant compile-time increase.
    for (unsigned CI = 0, CE = it->second.size(); CI < CE; CI+=16) {
      unsigned Len = std::min<unsigned>(CE - CI, 16);
      Changed |= vectorizeStores(makeArrayRef(&it->second[CI], Len), R);
    }
  }
  return Changed;
}

char SLPVectorizer::ID = 0;
static const char lv_name[] = "SLP Vectorizer";
INITIALIZE_PASS_BEGIN(SLPVectorizer, SV_NAME, lv_name, false, false)
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_DEPENDENCY(DemandedBitsWrapperPass)
INITIALIZE_PASS_END(SLPVectorizer, SV_NAME, lv_name, false, false)

namespace llvm {
Pass *createSLPVectorizerPass() { return new SLPVectorizer(); }
}