aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Transforms/Scalar/SROA.cpp
blob: f69c750f3f9d00fe48261937df82ccdcb7aa1b45 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
//===- SROA.cpp - Scalar Replacement Of Aggregates ------------------------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
/// \file
/// This transformation implements the well known scalar replacement of
/// aggregates transformation. It tries to identify promotable elements of an
/// aggregate alloca, and promote them to registers. It will also try to
/// convert uses of an element (or set of elements) of an alloca into a vector
/// or bitfield-style integer scalar if appropriate.
///
/// It works to do this with minimal slicing of the alloca so that regions
/// which are merely transferred in and out of external memory remain unchanged
/// and are not decomposed to scalar code.
///
/// Because this also performs alloca promotion, it can be thought of as also
/// serving the purpose of SSA formation. The algorithm iterates on the
/// function until all opportunities for promotion have been realized.
///
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/Loads.h"
#include "llvm/Analysis/PtrUseVisitor.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DIBuilder.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstVisitor.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Operator.h"
#include "llvm/Pass.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/TimeValue.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/PromoteMemToReg.h"
#include "llvm/Transforms/Utils/SSAUpdater.h"

#if __cplusplus >= 201103L && !defined(NDEBUG)
// We only use this for a debug check in C++11
#include <random>
#endif

using namespace llvm;

#define DEBUG_TYPE "sroa"

STATISTIC(NumAllocasAnalyzed, "Number of allocas analyzed for replacement");
STATISTIC(NumAllocaPartitions, "Number of alloca partitions formed");
STATISTIC(MaxPartitionsPerAlloca, "Maximum number of partitions per alloca");
STATISTIC(NumAllocaPartitionUses, "Number of alloca partition uses rewritten");
STATISTIC(MaxUsesPerAllocaPartition, "Maximum number of uses of a partition");
STATISTIC(NumNewAllocas, "Number of new, smaller allocas introduced");
STATISTIC(NumPromoted, "Number of allocas promoted to SSA values");
STATISTIC(NumLoadsSpeculated, "Number of loads speculated to allow promotion");
STATISTIC(NumDeleted, "Number of instructions deleted");
STATISTIC(NumVectorized, "Number of vectorized aggregates");

/// Hidden option to force the pass to not use DomTree and mem2reg, instead
/// forming SSA values through the SSAUpdater infrastructure.
static cl::opt<bool> ForceSSAUpdater("force-ssa-updater", cl::init(false),
                                     cl::Hidden);

/// Hidden option to enable randomly shuffling the slices to help uncover
/// instability in their order.
static cl::opt<bool> SROARandomShuffleSlices("sroa-random-shuffle-slices",
                                             cl::init(false), cl::Hidden);

/// Hidden option to experiment with completely strict handling of inbounds
/// GEPs.
static cl::opt<bool> SROAStrictInbounds("sroa-strict-inbounds", cl::init(false),
                                        cl::Hidden);

namespace {
/// \brief A custom IRBuilder inserter which prefixes all names if they are
/// preserved.
template <bool preserveNames = true>
class IRBuilderPrefixedInserter
    : public IRBuilderDefaultInserter<preserveNames> {
  std::string Prefix;

public:
  void SetNamePrefix(const Twine &P) { Prefix = P.str(); }

protected:
  void InsertHelper(Instruction *I, const Twine &Name, BasicBlock *BB,
                    BasicBlock::iterator InsertPt) const {
    IRBuilderDefaultInserter<preserveNames>::InsertHelper(
        I, Name.isTriviallyEmpty() ? Name : Prefix + Name, BB, InsertPt);
  }
};

// Specialization for not preserving the name is trivial.
template <>
class IRBuilderPrefixedInserter<false>
    : public IRBuilderDefaultInserter<false> {
public:
  void SetNamePrefix(const Twine &P) {}
};

/// \brief Provide a typedef for IRBuilder that drops names in release builds.
#ifndef NDEBUG
typedef llvm::IRBuilder<true, ConstantFolder, IRBuilderPrefixedInserter<true>>
    IRBuilderTy;
#else
typedef llvm::IRBuilder<false, ConstantFolder, IRBuilderPrefixedInserter<false>>
    IRBuilderTy;
#endif
}

namespace {
/// \brief A used slice of an alloca.
///
/// This structure represents a slice of an alloca used by some instruction. It
/// stores both the begin and end offsets of this use, a pointer to the use
/// itself, and a flag indicating whether we can classify the use as splittable
/// or not when forming partitions of the alloca.
class Slice {
  /// \brief The beginning offset of the range.
  uint64_t BeginOffset;

  /// \brief The ending offset, not included in the range.
  uint64_t EndOffset;

  /// \brief Storage for both the use of this slice and whether it can be
  /// split.
  PointerIntPair<Use *, 1, bool> UseAndIsSplittable;

public:
  Slice() : BeginOffset(), EndOffset() {}
  Slice(uint64_t BeginOffset, uint64_t EndOffset, Use *U, bool IsSplittable)
      : BeginOffset(BeginOffset), EndOffset(EndOffset),
        UseAndIsSplittable(U, IsSplittable) {}

  uint64_t beginOffset() const { return BeginOffset; }
  uint64_t endOffset() const { return EndOffset; }

  bool isSplittable() const { return UseAndIsSplittable.getInt(); }
  void makeUnsplittable() { UseAndIsSplittable.setInt(false); }

  Use *getUse() const { return UseAndIsSplittable.getPointer(); }

  bool isDead() const { return getUse() == nullptr; }
  void kill() { UseAndIsSplittable.setPointer(nullptr); }

  /// \brief Support for ordering ranges.
  ///
  /// This provides an ordering over ranges such that start offsets are
  /// always increasing, and within equal start offsets, the end offsets are
  /// decreasing. Thus the spanning range comes first in a cluster with the
  /// same start position.
  bool operator<(const Slice &RHS) const {
    if (beginOffset() < RHS.beginOffset())
      return true;
    if (beginOffset() > RHS.beginOffset())
      return false;
    if (isSplittable() != RHS.isSplittable())
      return !isSplittable();
    if (endOffset() > RHS.endOffset())
      return true;
    return false;
  }

  /// \brief Support comparison with a single offset to allow binary searches.
  friend LLVM_ATTRIBUTE_UNUSED bool operator<(const Slice &LHS,
                                              uint64_t RHSOffset) {
    return LHS.beginOffset() < RHSOffset;
  }
  friend LLVM_ATTRIBUTE_UNUSED bool operator<(uint64_t LHSOffset,
                                              const Slice &RHS) {
    return LHSOffset < RHS.beginOffset();
  }

  bool operator==(const Slice &RHS) const {
    return isSplittable() == RHS.isSplittable() &&
           beginOffset() == RHS.beginOffset() && endOffset() == RHS.endOffset();
  }
  bool operator!=(const Slice &RHS) const { return !operator==(RHS); }
};
} // end anonymous namespace

namespace llvm {
template <typename T> struct isPodLike;
template <> struct isPodLike<Slice> { static const bool value = true; };
}

namespace {
/// \brief Representation of the alloca slices.
///
/// This class represents the slices of an alloca which are formed by its
/// various uses. If a pointer escapes, we can't fully build a representation
/// for the slices used and we reflect that in this structure. The uses are
/// stored, sorted by increasing beginning offset and with unsplittable slices
/// starting at a particular offset before splittable slices.
class AllocaSlices {
public:
  /// \brief Construct the slices of a particular alloca.
  AllocaSlices(const DataLayout &DL, AllocaInst &AI);

  /// \brief Test whether a pointer to the allocation escapes our analysis.
  ///
  /// If this is true, the slices are never fully built and should be
  /// ignored.
  bool isEscaped() const { return PointerEscapingInstr; }

  /// \brief Support for iterating over the slices.
  /// @{
  typedef SmallVectorImpl<Slice>::iterator iterator;
  typedef iterator_range<iterator> range;
  iterator begin() { return Slices.begin(); }
  iterator end() { return Slices.end(); }

  typedef SmallVectorImpl<Slice>::const_iterator const_iterator;
  typedef iterator_range<const_iterator> const_range;
  const_iterator begin() const { return Slices.begin(); }
  const_iterator end() const { return Slices.end(); }
  /// @}

  /// \brief Erase a range of slices.
  void erase(iterator Start, iterator Stop) { Slices.erase(Start, Stop); }

  /// \brief Insert new slices for this alloca.
  ///
  /// This moves the slices into the alloca's slices collection, and re-sorts
  /// everything so that the usual ordering properties of the alloca's slices
  /// hold.
  void insert(ArrayRef<Slice> NewSlices) {
    int OldSize = Slices.size();
    std::move(NewSlices.begin(), NewSlices.end(), std::back_inserter(Slices));
    auto SliceI = Slices.begin() + OldSize;
    std::sort(SliceI, Slices.end());
    std::inplace_merge(Slices.begin(), SliceI, Slices.end());
  }

  // Forward declare an iterator to befriend it.
  class partition_iterator;

  /// \brief A partition of the slices.
  ///
  /// An ephemeral representation for a range of slices which can be viewed as
  /// a partition of the alloca. This range represents a span of the alloca's
  /// memory which cannot be split, and provides access to all of the slices
  /// overlapping some part of the partition.
  ///
  /// Objects of this type are produced by traversing the alloca's slices, but
  /// are only ephemeral and not persistent.
  class Partition {
  private:
    friend class AllocaSlices;
    friend class AllocaSlices::partition_iterator;

    /// \brief The begining and ending offsets of the alloca for this partition.
    uint64_t BeginOffset, EndOffset;

    /// \brief The start end end iterators of this partition.
    iterator SI, SJ;

    /// \brief A collection of split slice tails overlapping the partition.
    SmallVector<Slice *, 4> SplitTails;

    /// \brief Raw constructor builds an empty partition starting and ending at
    /// the given iterator.
    Partition(iterator SI) : SI(SI), SJ(SI) {}

  public:
    /// \brief The start offset of this partition.
    ///
    /// All of the contained slices start at or after this offset.
    uint64_t beginOffset() const { return BeginOffset; }

    /// \brief The end offset of this partition.
    ///
    /// All of the contained slices end at or before this offset.
    uint64_t endOffset() const { return EndOffset; }

    /// \brief The size of the partition.
    ///
    /// Note that this can never be zero.
    uint64_t size() const {
      assert(BeginOffset < EndOffset && "Partitions must span some bytes!");
      return EndOffset - BeginOffset;
    }

    /// \brief Test whether this partition contains no slices, and merely spans
    /// a region occupied by split slices.
    bool empty() const { return SI == SJ; }

    /// \name Iterate slices that start within the partition.
    /// These may be splittable or unsplittable. They have a begin offset >= the
    /// partition begin offset.
    /// @{
    // FIXME: We should probably define a "concat_iterator" helper and use that
    // to stitch together pointee_iterators over the split tails and the
    // contiguous iterators of the partition. That would give a much nicer
    // interface here. We could then additionally expose filtered iterators for
    // split, unsplit, and unsplittable splices based on the usage patterns.
    iterator begin() const { return SI; }
    iterator end() const { return SJ; }
    /// @}

    /// \brief Get the sequence of split slice tails.
    ///
    /// These tails are of slices which start before this partition but are
    /// split and overlap into the partition. We accumulate these while forming
    /// partitions.
    ArrayRef<Slice *> splitSliceTails() const { return SplitTails; }
  };

  /// \brief An iterator over partitions of the alloca's slices.
  ///
  /// This iterator implements the core algorithm for partitioning the alloca's
  /// slices. It is a forward iterator as we don't support backtracking for
  /// efficiency reasons, and re-use a single storage area to maintain the
  /// current set of split slices.
  ///
  /// It is templated on the slice iterator type to use so that it can operate
  /// with either const or non-const slice iterators.
  class partition_iterator
      : public iterator_facade_base<partition_iterator,
                                    std::forward_iterator_tag, Partition> {
    friend class AllocaSlices;

    /// \brief Most of the state for walking the partitions is held in a class
    /// with a nice interface for examining them.
    Partition P;

    /// \brief We need to keep the end of the slices to know when to stop.
    AllocaSlices::iterator SE;

    /// \brief We also need to keep track of the maximum split end offset seen.
    /// FIXME: Do we really?
    uint64_t MaxSplitSliceEndOffset;

    /// \brief Sets the partition to be empty at given iterator, and sets the
    /// end iterator.
    partition_iterator(AllocaSlices::iterator SI, AllocaSlices::iterator SE)
        : P(SI), SE(SE), MaxSplitSliceEndOffset(0) {
      // If not already at the end, advance our state to form the initial
      // partition.
      if (SI != SE)
        advance();
    }

    /// \brief Advance the iterator to the next partition.
    ///
    /// Requires that the iterator not be at the end of the slices.
    void advance() {
      assert((P.SI != SE || !P.SplitTails.empty()) &&
             "Cannot advance past the end of the slices!");

      // Clear out any split uses which have ended.
      if (!P.SplitTails.empty()) {
        if (P.EndOffset >= MaxSplitSliceEndOffset) {
          // If we've finished all splits, this is easy.
          P.SplitTails.clear();
          MaxSplitSliceEndOffset = 0;
        } else {
          // Remove the uses which have ended in the prior partition. This
          // cannot change the max split slice end because we just checked that
          // the prior partition ended prior to that max.
          P.SplitTails.erase(
              std::remove_if(
                  P.SplitTails.begin(), P.SplitTails.end(),
                  [&](Slice *S) { return S->endOffset() <= P.EndOffset; }),
              P.SplitTails.end());
          assert(std::any_of(P.SplitTails.begin(), P.SplitTails.end(),
                             [&](Slice *S) {
                               return S->endOffset() == MaxSplitSliceEndOffset;
                             }) &&
                 "Could not find the current max split slice offset!");
          assert(std::all_of(P.SplitTails.begin(), P.SplitTails.end(),
                             [&](Slice *S) {
                               return S->endOffset() <= MaxSplitSliceEndOffset;
                             }) &&
                 "Max split slice end offset is not actually the max!");
        }
      }

      // If P.SI is already at the end, then we've cleared the split tail and
      // now have an end iterator.
      if (P.SI == SE) {
        assert(P.SplitTails.empty() && "Failed to clear the split slices!");
        return;
      }

      // If we had a non-empty partition previously, set up the state for
      // subsequent partitions.
      if (P.SI != P.SJ) {
        // Accumulate all the splittable slices which started in the old
        // partition into the split list.
        for (Slice &S : P)
          if (S.isSplittable() && S.endOffset() > P.EndOffset) {
            P.SplitTails.push_back(&S);
            MaxSplitSliceEndOffset =
                std::max(S.endOffset(), MaxSplitSliceEndOffset);
          }

        // Start from the end of the previous partition.
        P.SI = P.SJ;

        // If P.SI is now at the end, we at most have a tail of split slices.
        if (P.SI == SE) {
          P.BeginOffset = P.EndOffset;
          P.EndOffset = MaxSplitSliceEndOffset;
          return;
        }

        // If the we have split slices and the next slice is after a gap and is
        // not splittable immediately form an empty partition for the split
        // slices up until the next slice begins.
        if (!P.SplitTails.empty() && P.SI->beginOffset() != P.EndOffset &&
            !P.SI->isSplittable()) {
          P.BeginOffset = P.EndOffset;
          P.EndOffset = P.SI->beginOffset();
          return;
        }
      }

      // OK, we need to consume new slices. Set the end offset based on the
      // current slice, and step SJ past it. The beginning offset of the
      // parttion is the beginning offset of the next slice unless we have
      // pre-existing split slices that are continuing, in which case we begin
      // at the prior end offset.
      P.BeginOffset = P.SplitTails.empty() ? P.SI->beginOffset() : P.EndOffset;
      P.EndOffset = P.SI->endOffset();
      ++P.SJ;

      // There are two strategies to form a partition based on whether the
      // partition starts with an unsplittable slice or a splittable slice.
      if (!P.SI->isSplittable()) {
        // When we're forming an unsplittable region, it must always start at
        // the first slice and will extend through its end.
        assert(P.BeginOffset == P.SI->beginOffset());

        // Form a partition including all of the overlapping slices with this
        // unsplittable slice.
        while (P.SJ != SE && P.SJ->beginOffset() < P.EndOffset) {
          if (!P.SJ->isSplittable())
            P.EndOffset = std::max(P.EndOffset, P.SJ->endOffset());
          ++P.SJ;
        }

        // We have a partition across a set of overlapping unsplittable
        // partitions.
        return;
      }

      // If we're starting with a splittable slice, then we need to form
      // a synthetic partition spanning it and any other overlapping splittable
      // splices.
      assert(P.SI->isSplittable() && "Forming a splittable partition!");

      // Collect all of the overlapping splittable slices.
      while (P.SJ != SE && P.SJ->beginOffset() < P.EndOffset &&
             P.SJ->isSplittable()) {
        P.EndOffset = std::max(P.EndOffset, P.SJ->endOffset());
        ++P.SJ;
      }

      // Back upiP.EndOffset if we ended the span early when encountering an
      // unsplittable slice. This synthesizes the early end offset of
      // a partition spanning only splittable slices.
      if (P.SJ != SE && P.SJ->beginOffset() < P.EndOffset) {
        assert(!P.SJ->isSplittable());
        P.EndOffset = P.SJ->beginOffset();
      }
    }

  public:
    bool operator==(const partition_iterator &RHS) const {
      assert(SE == RHS.SE &&
             "End iterators don't match between compared partition iterators!");

      // The observed positions of partitions is marked by the P.SI iterator and
      // the emptyness of the split slices. The latter is only relevant when
      // P.SI == SE, as the end iterator will additionally have an empty split
      // slices list, but the prior may have the same P.SI and a tail of split
      // slices.
      if (P.SI == RHS.P.SI &&
          P.SplitTails.empty() == RHS.P.SplitTails.empty()) {
        assert(P.SJ == RHS.P.SJ &&
               "Same set of slices formed two different sized partitions!");
        assert(P.SplitTails.size() == RHS.P.SplitTails.size() &&
               "Same slice position with differently sized non-empty split "
               "slice tails!");
        return true;
      }
      return false;
    }

    partition_iterator &operator++() {
      advance();
      return *this;
    }

    Partition &operator*() { return P; }
  };

  /// \brief A forward range over the partitions of the alloca's slices.
  ///
  /// This accesses an iterator range over the partitions of the alloca's
  /// slices. It computes these partitions on the fly based on the overlapping
  /// offsets of the slices and the ability to split them. It will visit "empty"
  /// partitions to cover regions of the alloca only accessed via split
  /// slices.
  iterator_range<partition_iterator> partitions() {
    return make_range(partition_iterator(begin(), end()),
                      partition_iterator(end(), end()));
  }

  /// \brief Access the dead users for this alloca.
  ArrayRef<Instruction *> getDeadUsers() const { return DeadUsers; }

  /// \brief Access the dead operands referring to this alloca.
  ///
  /// These are operands which have cannot actually be used to refer to the
  /// alloca as they are outside its range and the user doesn't correct for
  /// that. These mostly consist of PHI node inputs and the like which we just
  /// need to replace with undef.
  ArrayRef<Use *> getDeadOperands() const { return DeadOperands; }

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
  void print(raw_ostream &OS, const_iterator I, StringRef Indent = "  ") const;
  void printSlice(raw_ostream &OS, const_iterator I,
                  StringRef Indent = "  ") const;
  void printUse(raw_ostream &OS, const_iterator I,
                StringRef Indent = "  ") const;
  void print(raw_ostream &OS) const;
  void dump(const_iterator I) const;
  void dump() const;
#endif

private:
  template <typename DerivedT, typename RetT = void> class BuilderBase;
  class SliceBuilder;
  friend class AllocaSlices::SliceBuilder;

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
  /// \brief Handle to alloca instruction to simplify method interfaces.
  AllocaInst &AI;
#endif

  /// \brief The instruction responsible for this alloca not having a known set
  /// of slices.
  ///
  /// When an instruction (potentially) escapes the pointer to the alloca, we
  /// store a pointer to that here and abort trying to form slices of the
  /// alloca. This will be null if the alloca slices are analyzed successfully.
  Instruction *PointerEscapingInstr;

  /// \brief The slices of the alloca.
  ///
  /// We store a vector of the slices formed by uses of the alloca here. This
  /// vector is sorted by increasing begin offset, and then the unsplittable
  /// slices before the splittable ones. See the Slice inner class for more
  /// details.
  SmallVector<Slice, 8> Slices;

  /// \brief Instructions which will become dead if we rewrite the alloca.
  ///
  /// Note that these are not separated by slice. This is because we expect an
  /// alloca to be completely rewritten or not rewritten at all. If rewritten,
  /// all these instructions can simply be removed and replaced with undef as
  /// they come from outside of the allocated space.
  SmallVector<Instruction *, 8> DeadUsers;

  /// \brief Operands which will become dead if we rewrite the alloca.
  ///
  /// These are operands that in their particular use can be replaced with
  /// undef when we rewrite the alloca. These show up in out-of-bounds inputs
  /// to PHI nodes and the like. They aren't entirely dead (there might be
  /// a GEP back into the bounds using it elsewhere) and nor is the PHI, but we
  /// want to swap this particular input for undef to simplify the use lists of
  /// the alloca.
  SmallVector<Use *, 8> DeadOperands;
};
}

static Value *foldSelectInst(SelectInst &SI) {
  // If the condition being selected on is a constant or the same value is
  // being selected between, fold the select. Yes this does (rarely) happen
  // early on.
  if (ConstantInt *CI = dyn_cast<ConstantInt>(SI.getCondition()))
    return SI.getOperand(1 + CI->isZero());
  if (SI.getOperand(1) == SI.getOperand(2))
    return SI.getOperand(1);

  return nullptr;
}

/// \brief A helper that folds a PHI node or a select.
static Value *foldPHINodeOrSelectInst(Instruction &I) {
  if (PHINode *PN = dyn_cast<PHINode>(&I)) {
    // If PN merges together the same value, return that value.
    return PN->hasConstantValue();
  }
  return foldSelectInst(cast<SelectInst>(I));
}

/// \brief Builder for the alloca slices.
///
/// This class builds a set of alloca slices by recursively visiting the uses
/// of an alloca and making a slice for each load and store at each offset.
class AllocaSlices::SliceBuilder : public PtrUseVisitor<SliceBuilder> {
  friend class PtrUseVisitor<SliceBuilder>;
  friend class InstVisitor<SliceBuilder>;
  typedef PtrUseVisitor<SliceBuilder> Base;

  const uint64_t AllocSize;
  AllocaSlices &AS;

  SmallDenseMap<Instruction *, unsigned> MemTransferSliceMap;
  SmallDenseMap<Instruction *, uint64_t> PHIOrSelectSizes;

  /// \brief Set to de-duplicate dead instructions found in the use walk.
  SmallPtrSet<Instruction *, 4> VisitedDeadInsts;

public:
  SliceBuilder(const DataLayout &DL, AllocaInst &AI, AllocaSlices &AS)
      : PtrUseVisitor<SliceBuilder>(DL),
        AllocSize(DL.getTypeAllocSize(AI.getAllocatedType())), AS(AS) {}

private:
  void markAsDead(Instruction &I) {
    if (VisitedDeadInsts.insert(&I).second)
      AS.DeadUsers.push_back(&I);
  }

  void insertUse(Instruction &I, const APInt &Offset, uint64_t Size,
                 bool IsSplittable = false) {
    // Completely skip uses which have a zero size or start either before or
    // past the end of the allocation.
    if (Size == 0 || Offset.uge(AllocSize)) {
      DEBUG(dbgs() << "WARNING: Ignoring " << Size << " byte use @" << Offset
                   << " which has zero size or starts outside of the "
                   << AllocSize << " byte alloca:\n"
                   << "    alloca: " << AS.AI << "\n"
                   << "       use: " << I << "\n");
      return markAsDead(I);
    }

    uint64_t BeginOffset = Offset.getZExtValue();
    uint64_t EndOffset = BeginOffset + Size;

    // Clamp the end offset to the end of the allocation. Note that this is
    // formulated to handle even the case where "BeginOffset + Size" overflows.
    // This may appear superficially to be something we could ignore entirely,
    // but that is not so! There may be widened loads or PHI-node uses where
    // some instructions are dead but not others. We can't completely ignore
    // them, and so have to record at least the information here.
    assert(AllocSize >= BeginOffset); // Established above.
    if (Size > AllocSize - BeginOffset) {
      DEBUG(dbgs() << "WARNING: Clamping a " << Size << " byte use @" << Offset
                   << " to remain within the " << AllocSize << " byte alloca:\n"
                   << "    alloca: " << AS.AI << "\n"
                   << "       use: " << I << "\n");
      EndOffset = AllocSize;
    }

    AS.Slices.push_back(Slice(BeginOffset, EndOffset, U, IsSplittable));
  }

  void visitBitCastInst(BitCastInst &BC) {
    if (BC.use_empty())
      return markAsDead(BC);

    return Base::visitBitCastInst(BC);
  }

  void visitGetElementPtrInst(GetElementPtrInst &GEPI) {
    if (GEPI.use_empty())
      return markAsDead(GEPI);

    if (SROAStrictInbounds && GEPI.isInBounds()) {
      // FIXME: This is a manually un-factored variant of the basic code inside
      // of GEPs with checking of the inbounds invariant specified in the
      // langref in a very strict sense. If we ever want to enable
      // SROAStrictInbounds, this code should be factored cleanly into
      // PtrUseVisitor, but it is easier to experiment with SROAStrictInbounds
      // by writing out the code here where we have tho underlying allocation
      // size readily available.
      APInt GEPOffset = Offset;
      for (gep_type_iterator GTI = gep_type_begin(GEPI),
                             GTE = gep_type_end(GEPI);
           GTI != GTE; ++GTI) {
        ConstantInt *OpC = dyn_cast<ConstantInt>(GTI.getOperand());
        if (!OpC)
          break;

        // Handle a struct index, which adds its field offset to the pointer.
        if (StructType *STy = dyn_cast<StructType>(*GTI)) {
          unsigned ElementIdx = OpC->getZExtValue();
          const StructLayout *SL = DL.getStructLayout(STy);
          GEPOffset +=
              APInt(Offset.getBitWidth(), SL->getElementOffset(ElementIdx));
        } else {
          // For array or vector indices, scale the index by the size of the
          // type.
          APInt Index = OpC->getValue().sextOrTrunc(Offset.getBitWidth());
          GEPOffset += Index * APInt(Offset.getBitWidth(),
                                     DL.getTypeAllocSize(GTI.getIndexedType()));
        }

        // If this index has computed an intermediate pointer which is not
        // inbounds, then the result of the GEP is a poison value and we can
        // delete it and all uses.
        if (GEPOffset.ugt(AllocSize))
          return markAsDead(GEPI);
      }
    }

    return Base::visitGetElementPtrInst(GEPI);
  }

  void handleLoadOrStore(Type *Ty, Instruction &I, const APInt &Offset,
                         uint64_t Size, bool IsVolatile) {
    // We allow splitting of non-volatile loads and stores where the type is an
    // integer type. These may be used to implement 'memcpy' or other "transfer
    // of bits" patterns.
    bool IsSplittable = Ty->isIntegerTy() && !IsVolatile;

    insertUse(I, Offset, Size, IsSplittable);
  }

  void visitLoadInst(LoadInst &LI) {
    assert((!LI.isSimple() || LI.getType()->isSingleValueType()) &&
           "All simple FCA loads should have been pre-split");

    if (!IsOffsetKnown)
      return PI.setAborted(&LI);

    uint64_t Size = DL.getTypeStoreSize(LI.getType());
    return handleLoadOrStore(LI.getType(), LI, Offset, Size, LI.isVolatile());
  }

  void visitStoreInst(StoreInst &SI) {
    Value *ValOp = SI.getValueOperand();
    if (ValOp == *U)
      return PI.setEscapedAndAborted(&SI);
    if (!IsOffsetKnown)
      return PI.setAborted(&SI);

    uint64_t Size = DL.getTypeStoreSize(ValOp->getType());

    // If this memory access can be shown to *statically* extend outside the
    // bounds of of the allocation, it's behavior is undefined, so simply
    // ignore it. Note that this is more strict than the generic clamping
    // behavior of insertUse. We also try to handle cases which might run the
    // risk of overflow.
    // FIXME: We should instead consider the pointer to have escaped if this
    // function is being instrumented for addressing bugs or race conditions.
    if (Size > AllocSize || Offset.ugt(AllocSize - Size)) {
      DEBUG(dbgs() << "WARNING: Ignoring " << Size << " byte store @" << Offset
                   << " which extends past the end of the " << AllocSize
                   << " byte alloca:\n"
                   << "    alloca: " << AS.AI << "\n"
                   << "       use: " << SI << "\n");
      return markAsDead(SI);
    }

    assert((!SI.isSimple() || ValOp->getType()->isSingleValueType()) &&
           "All simple FCA stores should have been pre-split");
    handleLoadOrStore(ValOp->getType(), SI, Offset, Size, SI.isVolatile());
  }

  void visitMemSetInst(MemSetInst &II) {
    assert(II.getRawDest() == *U && "Pointer use is not the destination?");
    ConstantInt *Length = dyn_cast<ConstantInt>(II.getLength());
    if ((Length && Length->getValue() == 0) ||
        (IsOffsetKnown && Offset.uge(AllocSize)))
      // Zero-length mem transfer intrinsics can be ignored entirely.
      return markAsDead(II);

    if (!IsOffsetKnown)
      return PI.setAborted(&II);

    insertUse(II, Offset, Length ? Length->getLimitedValue()
                                 : AllocSize - Offset.getLimitedValue(),
              (bool)Length);
  }

  void visitMemTransferInst(MemTransferInst &II) {
    ConstantInt *Length = dyn_cast<ConstantInt>(II.getLength());
    if (Length && Length->getValue() == 0)
      // Zero-length mem transfer intrinsics can be ignored entirely.
      return markAsDead(II);

    // Because we can visit these intrinsics twice, also check to see if the
    // first time marked this instruction as dead. If so, skip it.
    if (VisitedDeadInsts.count(&II))
      return;

    if (!IsOffsetKnown)
      return PI.setAborted(&II);

    // This side of the transfer is completely out-of-bounds, and so we can
    // nuke the entire transfer. However, we also need to nuke the other side
    // if already added to our partitions.
    // FIXME: Yet another place we really should bypass this when
    // instrumenting for ASan.
    if (Offset.uge(AllocSize)) {
      SmallDenseMap<Instruction *, unsigned>::iterator MTPI =
          MemTransferSliceMap.find(&II);
      if (MTPI != MemTransferSliceMap.end())
        AS.Slices[MTPI->second].kill();
      return markAsDead(II);
    }

    uint64_t RawOffset = Offset.getLimitedValue();
    uint64_t Size = Length ? Length->getLimitedValue() : AllocSize - RawOffset;

    // Check for the special case where the same exact value is used for both
    // source and dest.
    if (*U == II.getRawDest() && *U == II.getRawSource()) {
      // For non-volatile transfers this is a no-op.
      if (!II.isVolatile())
        return markAsDead(II);

      return insertUse(II, Offset, Size, /*IsSplittable=*/false);
    }

    // If we have seen both source and destination for a mem transfer, then
    // they both point to the same alloca.
    bool Inserted;
    SmallDenseMap<Instruction *, unsigned>::iterator MTPI;
    std::tie(MTPI, Inserted) =
        MemTransferSliceMap.insert(std::make_pair(&II, AS.Slices.size()));
    unsigned PrevIdx = MTPI->second;
    if (!Inserted) {
      Slice &PrevP = AS.Slices[PrevIdx];

      // Check if the begin offsets match and this is a non-volatile transfer.
      // In that case, we can completely elide the transfer.
      if (!II.isVolatile() && PrevP.beginOffset() == RawOffset) {
        PrevP.kill();
        return markAsDead(II);
      }

      // Otherwise we have an offset transfer within the same alloca. We can't
      // split those.
      PrevP.makeUnsplittable();
    }

    // Insert the use now that we've fixed up the splittable nature.
    insertUse(II, Offset, Size, /*IsSplittable=*/Inserted && Length);

    // Check that we ended up with a valid index in the map.
    assert(AS.Slices[PrevIdx].getUse()->getUser() == &II &&
           "Map index doesn't point back to a slice with this user.");
  }

  // Disable SRoA for any intrinsics except for lifetime invariants.
  // FIXME: What about debug intrinsics? This matches old behavior, but
  // doesn't make sense.
  void visitIntrinsicInst(IntrinsicInst &II) {
    if (!IsOffsetKnown)
      return PI.setAborted(&II);

    if (II.getIntrinsicID() == Intrinsic::lifetime_start ||
        II.getIntrinsicID() == Intrinsic::lifetime_end) {
      ConstantInt *Length = cast<ConstantInt>(II.getArgOperand(0));
      uint64_t Size = std::min(AllocSize - Offset.getLimitedValue(),
                               Length->getLimitedValue());
      insertUse(II, Offset, Size, true);
      return;
    }

    Base::visitIntrinsicInst(II);
  }

  Instruction *hasUnsafePHIOrSelectUse(Instruction *Root, uint64_t &Size) {
    // We consider any PHI or select that results in a direct load or store of
    // the same offset to be a viable use for slicing purposes. These uses
    // are considered unsplittable and the size is the maximum loaded or stored
    // size.
    SmallPtrSet<Instruction *, 4> Visited;
    SmallVector<std::pair<Instruction *, Instruction *>, 4> Uses;
    Visited.insert(Root);
    Uses.push_back(std::make_pair(cast<Instruction>(*U), Root));
    // If there are no loads or stores, the access is dead. We mark that as
    // a size zero access.
    Size = 0;
    do {
      Instruction *I, *UsedI;
      std::tie(UsedI, I) = Uses.pop_back_val();

      if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
        Size = std::max(Size, DL.getTypeStoreSize(LI->getType()));
        continue;
      }
      if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
        Value *Op = SI->getOperand(0);
        if (Op == UsedI)
          return SI;
        Size = std::max(Size, DL.getTypeStoreSize(Op->getType()));
        continue;
      }

      if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(I)) {
        if (!GEP->hasAllZeroIndices())
          return GEP;
      } else if (!isa<BitCastInst>(I) && !isa<PHINode>(I) &&
                 !isa<SelectInst>(I)) {
        return I;
      }

      for (User *U : I->users())
        if (Visited.insert(cast<Instruction>(U)).second)
          Uses.push_back(std::make_pair(I, cast<Instruction>(U)));
    } while (!Uses.empty());

    return nullptr;
  }

  void visitPHINodeOrSelectInst(Instruction &I) {
    assert(isa<PHINode>(I) || isa<SelectInst>(I));
    if (I.use_empty())
      return markAsDead(I);

    // TODO: We could use SimplifyInstruction here to fold PHINodes and
    // SelectInsts. However, doing so requires to change the current
    // dead-operand-tracking mechanism. For instance, suppose neither loading
    // from %U nor %other traps. Then "load (select undef, %U, %other)" does not
    // trap either.  However, if we simply replace %U with undef using the
    // current dead-operand-tracking mechanism, "load (select undef, undef,
    // %other)" may trap because the select may return the first operand
    // "undef".
    if (Value *Result = foldPHINodeOrSelectInst(I)) {
      if (Result == *U)
        // If the result of the constant fold will be the pointer, recurse
        // through the PHI/select as if we had RAUW'ed it.
        enqueueUsers(I);
      else
        // Otherwise the operand to the PHI/select is dead, and we can replace
        // it with undef.
        AS.DeadOperands.push_back(U);

      return;
    }

    if (!IsOffsetKnown)
      return PI.setAborted(&I);

    // See if we already have computed info on this node.
    uint64_t &Size = PHIOrSelectSizes[&I];
    if (!Size) {
      // This is a new PHI/Select, check for an unsafe use of it.
      if (Instruction *UnsafeI = hasUnsafePHIOrSelectUse(&I, Size))
        return PI.setAborted(UnsafeI);
    }

    // For PHI and select operands outside the alloca, we can't nuke the entire
    // phi or select -- the other side might still be relevant, so we special
    // case them here and use a separate structure to track the operands
    // themselves which should be replaced with undef.
    // FIXME: This should instead be escaped in the event we're instrumenting
    // for address sanitization.
    if (Offset.uge(AllocSize)) {
      AS.DeadOperands.push_back(U);
      return;
    }

    insertUse(I, Offset, Size);
  }

  void visitPHINode(PHINode &PN) { visitPHINodeOrSelectInst(PN); }

  void visitSelectInst(SelectInst &SI) { visitPHINodeOrSelectInst(SI); }

  /// \brief Disable SROA entirely if there are unhandled users of the alloca.
  void visitInstruction(Instruction &I) { PI.setAborted(&I); }
};

AllocaSlices::AllocaSlices(const DataLayout &DL, AllocaInst &AI)
    :
#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)
      AI(AI),
#endif
      PointerEscapingInstr(nullptr) {
  SliceBuilder PB(DL, AI, *this);
  SliceBuilder::PtrInfo PtrI = PB.visitPtr(AI);
  if (PtrI.isEscaped() || PtrI.isAborted()) {
    // FIXME: We should sink the escape vs. abort info into the caller nicely,
    // possibly by just storing the PtrInfo in the AllocaSlices.
    PointerEscapingInstr = PtrI.getEscapingInst() ? PtrI.getEscapingInst()
                                                  : PtrI.getAbortingInst();
    assert(PointerEscapingInstr && "Did not track a bad instruction");
    return;
  }

  Slices.erase(std::remove_if(Slices.begin(), Slices.end(),
                              [](const Slice &S) {
                                return S.isDead();
                              }),
               Slices.end());

#if __cplusplus >= 201103L && !defined(NDEBUG)
  if (SROARandomShuffleSlices) {
    std::mt19937 MT(static_cast<unsigned>(sys::TimeValue::now().msec()));
    std::shuffle(Slices.begin(), Slices.end(), MT);
  }
#endif

  // Sort the uses. This arranges for the offsets to be in ascending order,
  // and the sizes to be in descending order.
  std::sort(Slices.begin(), Slices.end());
}

#if !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)

void AllocaSlices::print(raw_ostream &OS, const_iterator I,
                         StringRef Indent) const {
  printSlice(OS, I, Indent);
  OS << "\n";
  printUse(OS, I, Indent);
}

void AllocaSlices::printSlice(raw_ostream &OS, const_iterator I,
                              StringRef Indent) const {
  OS << Indent << "[" << I->beginOffset() << "," << I->endOffset() << ")"
     << " slice #" << (I - begin())
     << (I->isSplittable() ? " (splittable)" : "");
}

void AllocaSlices::printUse(raw_ostream &OS, const_iterator I,
                            StringRef Indent) const {
  OS << Indent << "  used by: " << *I->getUse()->getUser() << "\n";
}

void AllocaSlices::print(raw_ostream &OS) const {
  if (PointerEscapingInstr) {
    OS << "Can't analyze slices for alloca: " << AI << "\n"
       << "  A pointer to this alloca escaped by:\n"
       << "  " << *PointerEscapingInstr << "\n";
    return;
  }

  OS << "Slices of alloca: " << AI << "\n";
  for (const_iterator I = begin(), E = end(); I != E; ++I)
    print(OS, I);
}

LLVM_DUMP_METHOD void AllocaSlices::dump(const_iterator I) const {
  print(dbgs(), I);
}
LLVM_DUMP_METHOD void AllocaSlices::dump() const { print(dbgs()); }

#endif // !defined(NDEBUG) || defined(LLVM_ENABLE_DUMP)

namespace {
/// \brief Implementation of LoadAndStorePromoter for promoting allocas.
///
/// This subclass of LoadAndStorePromoter adds overrides to handle promoting
/// the loads and stores of an alloca instruction, as well as updating its
/// debug information. This is used when a domtree is unavailable and thus
/// mem2reg in its full form can't be used to handle promotion of allocas to
/// scalar values.
class AllocaPromoter : public LoadAndStorePromoter {
  AllocaInst &AI;
  DIBuilder &DIB;

  SmallVector<DbgDeclareInst *, 4> DDIs;
  SmallVector<DbgValueInst *, 4> DVIs;

public:
  AllocaPromoter(const SmallVectorImpl<Instruction *> &Insts, SSAUpdater &S,
                 AllocaInst &AI, DIBuilder &DIB)
      : LoadAndStorePromoter(Insts, S), AI(AI), DIB(DIB) {}

  void run(const SmallVectorImpl<Instruction *> &Insts) {
    // Retain the debug information attached to the alloca for use when
    // rewriting loads and stores.
    if (auto *L = LocalAsMetadata::getIfExists(&AI)) {
      if (auto *DebugNode = MetadataAsValue::getIfExists(AI.getContext(), L)) {
        for (User *U : DebugNode->users())
          if (DbgDeclareInst *DDI = dyn_cast<DbgDeclareInst>(U))
            DDIs.push_back(DDI);
          else if (DbgValueInst *DVI = dyn_cast<DbgValueInst>(U))
            DVIs.push_back(DVI);
      }
    }

    LoadAndStorePromoter::run(Insts);

    // While we have the debug information, clear it off of the alloca. The
    // caller takes care of deleting the alloca.
    while (!DDIs.empty())
      DDIs.pop_back_val()->eraseFromParent();
    while (!DVIs.empty())
      DVIs.pop_back_val()->eraseFromParent();
  }

  bool
  isInstInList(Instruction *I,
               const SmallVectorImpl<Instruction *> &Insts) const override {
    Value *Ptr;
    if (LoadInst *LI = dyn_cast<LoadInst>(I))
      Ptr = LI->getOperand(0);
    else
      Ptr = cast<StoreInst>(I)->getPointerOperand();

    // Only used to detect cycles, which will be rare and quickly found as
    // we're walking up a chain of defs rather than down through uses.
    SmallPtrSet<Value *, 4> Visited;

    do {
      if (Ptr == &AI)
        return true;

      if (BitCastInst *BCI = dyn_cast<BitCastInst>(Ptr))
        Ptr = BCI->getOperand(0);
      else if (GetElementPtrInst *GEPI = dyn_cast<GetElementPtrInst>(Ptr))
        Ptr = GEPI->getPointerOperand();
      else
        return false;

    } while (Visited.insert(Ptr).second);

    return false;
  }

  void updateDebugInfo(Instruction *Inst) const override {
    for (DbgDeclareInst *DDI : DDIs)
      if (StoreInst *SI = dyn_cast<StoreInst>(Inst))
        ConvertDebugDeclareToDebugValue(DDI, SI, DIB);
      else if (LoadInst *LI = dyn_cast<LoadInst>(Inst))
        ConvertDebugDeclareToDebugValue(DDI, LI, DIB);
    for (DbgValueInst *DVI : DVIs) {
      Value *Arg = nullptr;
      if (StoreInst *SI = dyn_cast<StoreInst>(Inst)) {
        // If an argument is zero extended then use argument directly. The ZExt
        // may be zapped by an optimization pass in future.
        if (ZExtInst *ZExt = dyn_cast<ZExtInst>(SI->getOperand(0)))
          Arg = dyn_cast<Argument>(ZExt->getOperand(0));
        else if (SExtInst *SExt = dyn_cast<SExtInst>(SI->getOperand(0)))
          Arg = dyn_cast<Argument>(SExt->getOperand(0));
        if (!Arg)
          Arg = SI->getValueOperand();
      } else if (LoadInst *LI = dyn_cast<LoadInst>(Inst)) {
        Arg = LI->getPointerOperand();
      } else {
        continue;
      }
      Instruction *DbgVal =
          DIB.insertDbgValueIntrinsic(Arg, 0, DIVariable(DVI->getVariable()),
                                      DIExpression(DVI->getExpression()), Inst);
      DbgVal->setDebugLoc(DVI->getDebugLoc());
    }
  }
};
} // end anon namespace

namespace {
/// \brief An optimization pass providing Scalar Replacement of Aggregates.
///
/// This pass takes allocations which can be completely analyzed (that is, they
/// don't escape) and tries to turn them into scalar SSA values. There are
/// a few steps to this process.
///
/// 1) It takes allocations of aggregates and analyzes the ways in which they
///    are used to try to split them into smaller allocations, ideally of
///    a single scalar data type. It will split up memcpy and memset accesses
///    as necessary and try to isolate individual scalar accesses.
/// 2) It will transform accesses into forms which are suitable for SSA value
///    promotion. This can be replacing a memset with a scalar store of an
///    integer value, or it can involve speculating operations on a PHI or
///    select to be a PHI or select of the results.
/// 3) Finally, this will try to detect a pattern of accesses which map cleanly
///    onto insert and extract operations on a vector value, and convert them to
///    this form. By doing so, it will enable promotion of vector aggregates to
///    SSA vector values.
class SROA : public FunctionPass {
  const bool RequiresDomTree;

  LLVMContext *C;
  const DataLayout *DL;
  DominatorTree *DT;
  AssumptionCache *AC;

  /// \brief Worklist of alloca instructions to simplify.
  ///
  /// Each alloca in the function is added to this. Each new alloca formed gets
  /// added to it as well to recursively simplify unless that alloca can be
  /// directly promoted. Finally, each time we rewrite a use of an alloca other
  /// the one being actively rewritten, we add it back onto the list if not
  /// already present to ensure it is re-visited.
  SetVector<AllocaInst *, SmallVector<AllocaInst *, 16>> Worklist;

  /// \brief A collection of instructions to delete.
  /// We try to batch deletions to simplify code and make things a bit more
  /// efficient.
  SetVector<Instruction *, SmallVector<Instruction *, 8>> DeadInsts;

  /// \brief Post-promotion worklist.
  ///
  /// Sometimes we discover an alloca which has a high probability of becoming
  /// viable for SROA after a round of promotion takes place. In those cases,
  /// the alloca is enqueued here for re-processing.
  ///
  /// Note that we have to be very careful to clear allocas out of this list in
  /// the event they are deleted.
  SetVector<AllocaInst *, SmallVector<AllocaInst *, 16>> PostPromotionWorklist;

  /// \brief A collection of alloca instructions we can directly promote.
  std::vector<AllocaInst *> PromotableAllocas;

  /// \brief A worklist of PHIs to speculate prior to promoting allocas.
  ///
  /// All of these PHIs have been checked for the safety of speculation and by
  /// being speculated will allow promoting allocas currently in the promotable
  /// queue.
  SetVector<PHINode *, SmallVector<PHINode *, 2>> SpeculatablePHIs;

  /// \brief A worklist of select instructions to speculate prior to promoting
  /// allocas.
  ///
  /// All of these select instructions have been checked for the safety of
  /// speculation and by being speculated will allow promoting allocas
  /// currently in the promotable queue.
  SetVector<SelectInst *, SmallVector<SelectInst *, 2>> SpeculatableSelects;

public:
  SROA(bool RequiresDomTree = true)
      : FunctionPass(ID), RequiresDomTree(RequiresDomTree), C(nullptr),
        DL(nullptr), DT(nullptr) {
    initializeSROAPass(*PassRegistry::getPassRegistry());
  }
  bool runOnFunction(Function &F) override;
  void getAnalysisUsage(AnalysisUsage &AU) const override;

  const char *getPassName() const override { return "SROA"; }
  static char ID;

private:
  friend class PHIOrSelectSpeculator;
  friend class AllocaSliceRewriter;

  bool presplitLoadsAndStores(AllocaInst &AI, AllocaSlices &AS);
  AllocaInst *rewritePartition(AllocaInst &AI, AllocaSlices &AS,
                               AllocaSlices::Partition &P);
  bool splitAlloca(AllocaInst &AI, AllocaSlices &AS);
  bool runOnAlloca(AllocaInst &AI);
  void clobberUse(Use &U);
  void deleteDeadInstructions(SmallPtrSetImpl<AllocaInst *> &DeletedAllocas);
  bool promoteAllocas(Function &F);
};
}

char SROA::ID = 0;

FunctionPass *llvm::createSROAPass(bool RequiresDomTree) {
  return new SROA(RequiresDomTree);
}

INITIALIZE_PASS_BEGIN(SROA, "sroa", "Scalar Replacement Of Aggregates", false,
                      false)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_END(SROA, "sroa", "Scalar Replacement Of Aggregates", false,
                    false)

/// Walk the range of a partitioning looking for a common type to cover this
/// sequence of slices.
static Type *findCommonType(AllocaSlices::const_iterator B,
                            AllocaSlices::const_iterator E,
                            uint64_t EndOffset) {
  Type *Ty = nullptr;
  bool TyIsCommon = true;
  IntegerType *ITy = nullptr;

  // Note that we need to look at *every* alloca slice's Use to ensure we
  // always get consistent results regardless of the order of slices.
  for (AllocaSlices::const_iterator I = B; I != E; ++I) {
    Use *U = I->getUse();
    if (isa<IntrinsicInst>(*U->getUser()))
      continue;
    if (I->beginOffset() != B->beginOffset() || I->endOffset() != EndOffset)
      continue;

    Type *UserTy = nullptr;
    if (LoadInst *LI = dyn_cast<LoadInst>(U->getUser())) {
      UserTy = LI->getType();
    } else if (StoreInst *SI = dyn_cast<StoreInst>(U->getUser())) {
      UserTy = SI->getValueOperand()->getType();
    }

    if (IntegerType *UserITy = dyn_cast_or_null<IntegerType>(UserTy)) {
      // If the type is larger than the partition, skip it. We only encounter
      // this for split integer operations where we want to use the type of the
      // entity causing the split. Also skip if the type is not a byte width
      // multiple.
      if (UserITy->getBitWidth() % 8 != 0 ||
          UserITy->getBitWidth() / 8 > (EndOffset - B->beginOffset()))
        continue;

      // Track the largest bitwidth integer type used in this way in case there
      // is no common type.
      if (!ITy || ITy->getBitWidth() < UserITy->getBitWidth())
        ITy = UserITy;
    }

    // To avoid depending on the order of slices, Ty and TyIsCommon must not
    // depend on types skipped above.
    if (!UserTy || (Ty && Ty != UserTy))
      TyIsCommon = false; // Give up on anything but an iN type.
    else
      Ty = UserTy;
  }

  return TyIsCommon ? Ty : ITy;
}

/// PHI instructions that use an alloca and are subsequently loaded can be
/// rewritten to load both input pointers in the pred blocks and then PHI the
/// results, allowing the load of the alloca to be promoted.
/// From this:
///   %P2 = phi [i32* %Alloca, i32* %Other]
///   %V = load i32* %P2
/// to:
///   %V1 = load i32* %Alloca      -> will be mem2reg'd
///   ...
///   %V2 = load i32* %Other
///   ...
///   %V = phi [i32 %V1, i32 %V2]
///
/// We can do this to a select if its only uses are loads and if the operands
/// to the select can be loaded unconditionally.
///
/// FIXME: This should be hoisted into a generic utility, likely in
/// Transforms/Util/Local.h
static bool isSafePHIToSpeculate(PHINode &PN, const DataLayout *DL = nullptr) {
  // For now, we can only do this promotion if the load is in the same block
  // as the PHI, and if there are no stores between the phi and load.
  // TODO: Allow recursive phi users.
  // TODO: Allow stores.
  BasicBlock *BB = PN.getParent();
  unsigned MaxAlign = 0;
  bool HaveLoad = false;
  for (User *U : PN.users()) {
    LoadInst *LI = dyn_cast<LoadInst>(U);
    if (!LI || !LI->isSimple())
      return false;

    // For now we only allow loads in the same block as the PHI.  This is
    // a common case that happens when instcombine merges two loads through
    // a PHI.
    if (LI->getParent() != BB)
      return false;

    // Ensure that there are no instructions between the PHI and the load that
    // could store.
    for (BasicBlock::iterator BBI = &PN; &*BBI != LI; ++BBI)
      if (BBI->mayWriteToMemory())
        return false;

    MaxAlign = std::max(MaxAlign, LI->getAlignment());
    HaveLoad = true;
  }

  if (!HaveLoad)
    return false;

  // We can only transform this if it is safe to push the loads into the
  // predecessor blocks. The only thing to watch out for is that we can't put
  // a possibly trapping load in the predecessor if it is a critical edge.
  for (unsigned Idx = 0, Num = PN.getNumIncomingValues(); Idx != Num; ++Idx) {
    TerminatorInst *TI = PN.getIncomingBlock(Idx)->getTerminator();
    Value *InVal = PN.getIncomingValue(Idx);

    // If the value is produced by the terminator of the predecessor (an
    // invoke) or it has side-effects, there is no valid place to put a load
    // in the predecessor.
    if (TI == InVal || TI->mayHaveSideEffects())
      return false;

    // If the predecessor has a single successor, then the edge isn't
    // critical.
    if (TI->getNumSuccessors() == 1)
      continue;

    // If this pointer is always safe to load, or if we can prove that there
    // is already a load in the block, then we can move the load to the pred
    // block.
    if (InVal->isDereferenceablePointer(DL) ||
        isSafeToLoadUnconditionally(InVal, TI, MaxAlign, DL))
      continue;

    return false;
  }

  return true;
}

static void speculatePHINodeLoads(PHINode &PN) {
  DEBUG(dbgs() << "    original: " << PN << "\n");

  Type *LoadTy = cast<PointerType>(PN.getType())->getElementType();
  IRBuilderTy PHIBuilder(&PN);
  PHINode *NewPN = PHIBuilder.CreatePHI(LoadTy, PN.getNumIncomingValues(),
                                        PN.getName() + ".sroa.speculated");

  // Get the AA tags and alignment to use from one of the loads.  It doesn't
  // matter which one we get and if any differ.
  LoadInst *SomeLoad = cast<LoadInst>(PN.user_back());

  AAMDNodes AATags;
  SomeLoad->getAAMetadata(AATags);
  unsigned Align = SomeLoad->getAlignment();

  // Rewrite all loads of the PN to use the new PHI.
  while (!PN.use_empty()) {
    LoadInst *LI = cast<LoadInst>(PN.user_back());
    LI->replaceAllUsesWith(NewPN);
    LI->eraseFromParent();
  }

  // Inject loads into all of the pred blocks.
  for (unsigned Idx = 0, Num = PN.getNumIncomingValues(); Idx != Num; ++Idx) {
    BasicBlock *Pred = PN.getIncomingBlock(Idx);
    TerminatorInst *TI = Pred->getTerminator();
    Value *InVal = PN.getIncomingValue(Idx);
    IRBuilderTy PredBuilder(TI);

    LoadInst *Load = PredBuilder.CreateLoad(
        InVal, (PN.getName() + ".sroa.speculate.load." + Pred->getName()));
    ++NumLoadsSpeculated;
    Load->setAlignment(Align);
    if (AATags)
      Load->setAAMetadata(AATags);
    NewPN->addIncoming(Load, Pred);
  }

  DEBUG(dbgs() << "          speculated to: " << *NewPN << "\n");
  PN.eraseFromParent();
}

/// Select instructions that use an alloca and are subsequently loaded can be
/// rewritten to load both input pointers and then select between the result,
/// allowing the load of the alloca to be promoted.
/// From this:
///   %P2 = select i1 %cond, i32* %Alloca, i32* %Other
///   %V = load i32* %P2
/// to:
///   %V1 = load i32* %Alloca      -> will be mem2reg'd
///   %V2 = load i32* %Other
///   %V = select i1 %cond, i32 %V1, i32 %V2
///
/// We can do this to a select if its only uses are loads and if the operand
/// to the select can be loaded unconditionally.
static bool isSafeSelectToSpeculate(SelectInst &SI,
                                    const DataLayout *DL = nullptr) {
  Value *TValue = SI.getTrueValue();
  Value *FValue = SI.getFalseValue();
  bool TDerefable = TValue->isDereferenceablePointer(DL);
  bool FDerefable = FValue->isDereferenceablePointer(DL);

  for (User *U : SI.users()) {
    LoadInst *LI = dyn_cast<LoadInst>(U);
    if (!LI || !LI->isSimple())
      return false;

    // Both operands to the select need to be dereferencable, either
    // absolutely (e.g. allocas) or at this point because we can see other
    // accesses to it.
    if (!TDerefable &&
        !isSafeToLoadUnconditionally(TValue, LI, LI->getAlignment(), DL))
      return false;
    if (!FDerefable &&
        !isSafeToLoadUnconditionally(FValue, LI, LI->getAlignment(), DL))
      return false;
  }

  return true;
}

static void speculateSelectInstLoads(SelectInst &SI) {
  DEBUG(dbgs() << "    original: " << SI << "\n");

  IRBuilderTy IRB(&SI);
  Value *TV = SI.getTrueValue();
  Value *FV = SI.getFalseValue();
  // Replace the loads of the select with a select of two loads.
  while (!SI.use_empty()) {
    LoadInst *LI = cast<LoadInst>(SI.user_back());
    assert(LI->isSimple() && "We only speculate simple loads");

    IRB.SetInsertPoint(LI);
    LoadInst *TL =
        IRB.CreateLoad(TV, LI->getName() + ".sroa.speculate.load.true");
    LoadInst *FL =
        IRB.CreateLoad(FV, LI->getName() + ".sroa.speculate.load.false");
    NumLoadsSpeculated += 2;

    // Transfer alignment and AA info if present.
    TL->setAlignment(LI->getAlignment());
    FL->setAlignment(LI->getAlignment());

    AAMDNodes Tags;
    LI->getAAMetadata(Tags);
    if (Tags) {
      TL->setAAMetadata(Tags);
      FL->setAAMetadata(Tags);
    }

    Value *V = IRB.CreateSelect(SI.getCondition(), TL, FL,
                                LI->getName() + ".sroa.speculated");

    DEBUG(dbgs() << "          speculated to: " << *V << "\n");
    LI->replaceAllUsesWith(V);
    LI->eraseFromParent();
  }
  SI.eraseFromParent();
}

/// \brief Build a GEP out of a base pointer and indices.
///
/// This will return the BasePtr if that is valid, or build a new GEP
/// instruction using the IRBuilder if GEP-ing is needed.
static Value *buildGEP(IRBuilderTy &IRB, Value *BasePtr,
                       SmallVectorImpl<Value *> &Indices, Twine NamePrefix) {
  if (Indices.empty())
    return BasePtr;

  // A single zero index is a no-op, so check for this and avoid building a GEP
  // in that case.
  if (Indices.size() == 1 && cast<ConstantInt>(Indices.back())->isZero())
    return BasePtr;

  return IRB.CreateInBoundsGEP(BasePtr, Indices, NamePrefix + "sroa_idx");
}

/// \brief Get a natural GEP off of the BasePtr walking through Ty toward
/// TargetTy without changing the offset of the pointer.
///
/// This routine assumes we've already established a properly offset GEP with
/// Indices, and arrived at the Ty type. The goal is to continue to GEP with
/// zero-indices down through type layers until we find one the same as
/// TargetTy. If we can't find one with the same type, we at least try to use
/// one with the same size. If none of that works, we just produce the GEP as
/// indicated by Indices to have the correct offset.
static Value *getNaturalGEPWithType(IRBuilderTy &IRB, const DataLayout &DL,
                                    Value *BasePtr, Type *Ty, Type *TargetTy,
                                    SmallVectorImpl<Value *> &Indices,
                                    Twine NamePrefix) {
  if (Ty == TargetTy)
    return buildGEP(IRB, BasePtr, Indices, NamePrefix);

  // Pointer size to use for the indices.
  unsigned PtrSize = DL.getPointerTypeSizeInBits(BasePtr->getType());

  // See if we can descend into a struct and locate a field with the correct
  // type.
  unsigned NumLayers = 0;
  Type *ElementTy = Ty;
  do {
    if (ElementTy->isPointerTy())
      break;

    if (ArrayType *ArrayTy = dyn_cast<ArrayType>(ElementTy)) {
      ElementTy = ArrayTy->getElementType();
      Indices.push_back(IRB.getIntN(PtrSize, 0));
    } else if (VectorType *VectorTy = dyn_cast<VectorType>(ElementTy)) {
      ElementTy = VectorTy->getElementType();
      Indices.push_back(IRB.getInt32(0));
    } else if (StructType *STy = dyn_cast<StructType>(ElementTy)) {
      if (STy->element_begin() == STy->element_end())
        break; // Nothing left to descend into.
      ElementTy = *STy->element_begin();
      Indices.push_back(IRB.getInt32(0));
    } else {
      break;
    }
    ++NumLayers;
  } while (ElementTy != TargetTy);
  if (ElementTy != TargetTy)
    Indices.erase(Indices.end() - NumLayers, Indices.end());

  return buildGEP(IRB, BasePtr, Indices, NamePrefix);
}

/// \brief Recursively compute indices for a natural GEP.
///
/// This is the recursive step for getNaturalGEPWithOffset that walks down the
/// element types adding appropriate indices for the GEP.
static Value *getNaturalGEPRecursively(IRBuilderTy &IRB, const DataLayout &DL,
                                       Value *Ptr, Type *Ty, APInt &Offset,
                                       Type *TargetTy,
                                       SmallVectorImpl<Value *> &Indices,
                                       Twine NamePrefix) {
  if (Offset == 0)
    return getNaturalGEPWithType(IRB, DL, Ptr, Ty, TargetTy, Indices,
                                 NamePrefix);

  // We can't recurse through pointer types.
  if (Ty->isPointerTy())
    return nullptr;

  // We try to analyze GEPs over vectors here, but note that these GEPs are
  // extremely poorly defined currently. The long-term goal is to remove GEPing
  // over a vector from the IR completely.
  if (VectorType *VecTy = dyn_cast<VectorType>(Ty)) {
    unsigned ElementSizeInBits = DL.getTypeSizeInBits(VecTy->getScalarType());
    if (ElementSizeInBits % 8 != 0) {
      // GEPs over non-multiple of 8 size vector elements are invalid.
      return nullptr;
    }
    APInt ElementSize(Offset.getBitWidth(), ElementSizeInBits / 8);
    APInt NumSkippedElements = Offset.sdiv(ElementSize);
    if (NumSkippedElements.ugt(VecTy->getNumElements()))
      return nullptr;
    Offset -= NumSkippedElements * ElementSize;
    Indices.push_back(IRB.getInt(NumSkippedElements));
    return getNaturalGEPRecursively(IRB, DL, Ptr, VecTy->getElementType(),
                                    Offset, TargetTy, Indices, NamePrefix);
  }

  if (ArrayType *ArrTy = dyn_cast<ArrayType>(Ty)) {
    Type *ElementTy = ArrTy->getElementType();
    APInt ElementSize(Offset.getBitWidth(), DL.getTypeAllocSize(ElementTy));
    APInt NumSkippedElements = Offset.sdiv(ElementSize);
    if (NumSkippedElements.ugt(ArrTy->getNumElements()))
      return nullptr;

    Offset -= NumSkippedElements * ElementSize;
    Indices.push_back(IRB.getInt(NumSkippedElements));
    return getNaturalGEPRecursively(IRB, DL, Ptr, ElementTy, Offset, TargetTy,
                                    Indices, NamePrefix);
  }

  StructType *STy = dyn_cast<StructType>(Ty);
  if (!STy)
    return nullptr;

  const StructLayout *SL = DL.getStructLayout(STy);
  uint64_t StructOffset = Offset.getZExtValue();
  if (StructOffset >= SL->getSizeInBytes())
    return nullptr;
  unsigned Index = SL->getElementContainingOffset(StructOffset);
  Offset -= APInt(Offset.getBitWidth(), SL->getElementOffset(Index));
  Type *ElementTy = STy->getElementType(Index);
  if (Offset.uge(DL.getTypeAllocSize(ElementTy)))
    return nullptr; // The offset points into alignment padding.

  Indices.push_back(IRB.getInt32(Index));
  return getNaturalGEPRecursively(IRB, DL, Ptr, ElementTy, Offset, TargetTy,
                                  Indices, NamePrefix);
}

/// \brief Get a natural GEP from a base pointer to a particular offset and
/// resulting in a particular type.
///
/// The goal is to produce a "natural" looking GEP that works with the existing
/// composite types to arrive at the appropriate offset and element type for
/// a pointer. TargetTy is the element type the returned GEP should point-to if
/// possible. We recurse by decreasing Offset, adding the appropriate index to
/// Indices, and setting Ty to the result subtype.
///
/// If no natural GEP can be constructed, this function returns null.
static Value *getNaturalGEPWithOffset(IRBuilderTy &IRB, const DataLayout &DL,
                                      Value *Ptr, APInt Offset, Type *TargetTy,
                                      SmallVectorImpl<Value *> &Indices,
                                      Twine NamePrefix) {
  PointerType *Ty = cast<PointerType>(Ptr->getType());

  // Don't consider any GEPs through an i8* as natural unless the TargetTy is
  // an i8.
  if (Ty == IRB.getInt8PtrTy(Ty->getAddressSpace()) && TargetTy->isIntegerTy(8))
    return nullptr;

  Type *ElementTy = Ty->getElementType();
  if (!ElementTy->isSized())
    return nullptr; // We can't GEP through an unsized element.
  APInt ElementSize(Offset.getBitWidth(), DL.getTypeAllocSize(ElementTy));
  if (ElementSize == 0)
    return nullptr; // Zero-length arrays can't help us build a natural GEP.
  APInt NumSkippedElements = Offset.sdiv(ElementSize);

  Offset -= NumSkippedElements * ElementSize;
  Indices.push_back(IRB.getInt(NumSkippedElements));
  return getNaturalGEPRecursively(IRB, DL, Ptr, ElementTy, Offset, TargetTy,
                                  Indices, NamePrefix);
}

/// \brief Compute an adjusted pointer from Ptr by Offset bytes where the
/// resulting pointer has PointerTy.
///
/// This tries very hard to compute a "natural" GEP which arrives at the offset
/// and produces the pointer type desired. Where it cannot, it will try to use
/// the natural GEP to arrive at the offset and bitcast to the type. Where that
/// fails, it will try to use an existing i8* and GEP to the byte offset and
/// bitcast to the type.
///
/// The strategy for finding the more natural GEPs is to peel off layers of the
/// pointer, walking back through bit casts and GEPs, searching for a base
/// pointer from which we can compute a natural GEP with the desired
/// properties. The algorithm tries to fold as many constant indices into
/// a single GEP as possible, thus making each GEP more independent of the
/// surrounding code.
static Value *getAdjustedPtr(IRBuilderTy &IRB, const DataLayout &DL, Value *Ptr,
                             APInt Offset, Type *PointerTy, Twine NamePrefix) {
  // Even though we don't look through PHI nodes, we could be called on an
  // instruction in an unreachable block, which may be on a cycle.
  SmallPtrSet<Value *, 4> Visited;
  Visited.insert(Ptr);
  SmallVector<Value *, 4> Indices;

  // We may end up computing an offset pointer that has the wrong type. If we
  // never are able to compute one directly that has the correct type, we'll
  // fall back to it, so keep it and the base it was computed from around here.
  Value *OffsetPtr = nullptr;
  Value *OffsetBasePtr;

  // Remember any i8 pointer we come across to re-use if we need to do a raw
  // byte offset.
  Value *Int8Ptr = nullptr;
  APInt Int8PtrOffset(Offset.getBitWidth(), 0);

  Type *TargetTy = PointerTy->getPointerElementType();

  do {
    // First fold any existing GEPs into the offset.
    while (GEPOperator *GEP = dyn_cast<GEPOperator>(Ptr)) {
      APInt GEPOffset(Offset.getBitWidth(), 0);
      if (!GEP->accumulateConstantOffset(DL, GEPOffset))
        break;
      Offset += GEPOffset;
      Ptr = GEP->getPointerOperand();
      if (!Visited.insert(Ptr).second)
        break;
    }

    // See if we can perform a natural GEP here.
    Indices.clear();
    if (Value *P = getNaturalGEPWithOffset(IRB, DL, Ptr, Offset, TargetTy,
                                           Indices, NamePrefix)) {
      // If we have a new natural pointer at the offset, clear out any old
      // offset pointer we computed. Unless it is the base pointer or
      // a non-instruction, we built a GEP we don't need. Zap it.
      if (OffsetPtr && OffsetPtr != OffsetBasePtr)
        if (Instruction *I = dyn_cast<Instruction>(OffsetPtr)) {
          assert(I->use_empty() && "Built a GEP with uses some how!");
          I->eraseFromParent();
        }
      OffsetPtr = P;
      OffsetBasePtr = Ptr;
      // If we also found a pointer of the right type, we're done.
      if (P->getType() == PointerTy)
        return P;
    }

    // Stash this pointer if we've found an i8*.
    if (Ptr->getType()->isIntegerTy(8)) {
      Int8Ptr = Ptr;
      Int8PtrOffset = Offset;
    }

    // Peel off a layer of the pointer and update the offset appropriately.
    if (Operator::getOpcode(Ptr) == Instruction::BitCast) {
      Ptr = cast<Operator>(Ptr)->getOperand(0);
    } else if (GlobalAlias *GA = dyn_cast<GlobalAlias>(Ptr)) {
      if (GA->mayBeOverridden())
        break;
      Ptr = GA->getAliasee();
    } else {
      break;
    }
    assert(Ptr->getType()->isPointerTy() && "Unexpected operand type!");
  } while (Visited.insert(Ptr).second);

  if (!OffsetPtr) {
    if (!Int8Ptr) {
      Int8Ptr = IRB.CreateBitCast(
          Ptr, IRB.getInt8PtrTy(PointerTy->getPointerAddressSpace()),
          NamePrefix + "sroa_raw_cast");
      Int8PtrOffset = Offset;
    }

    OffsetPtr = Int8PtrOffset == 0
                    ? Int8Ptr
                    : IRB.CreateInBoundsGEP(Int8Ptr, IRB.getInt(Int8PtrOffset),
                                            NamePrefix + "sroa_raw_idx");
  }
  Ptr = OffsetPtr;

  // On the off chance we were targeting i8*, guard the bitcast here.
  if (Ptr->getType() != PointerTy)
    Ptr = IRB.CreateBitCast(Ptr, PointerTy, NamePrefix + "sroa_cast");

  return Ptr;
}

/// \brief Compute the adjusted alignment for a load or store from an offset.
static unsigned getAdjustedAlignment(Instruction *I, uint64_t Offset,
                                     const DataLayout &DL) {
  unsigned Alignment;
  Type *Ty;
  if (auto *LI = dyn_cast<LoadInst>(I)) {
    Alignment = LI->getAlignment();
    Ty = LI->getType();
  } else if (auto *SI = dyn_cast<StoreInst>(I)) {
    Alignment = SI->getAlignment();
    Ty = SI->getValueOperand()->getType();
  } else {
    llvm_unreachable("Only loads and stores are allowed!");
  }

  if (!Alignment)
    Alignment = DL.getABITypeAlignment(Ty);

  return MinAlign(Alignment, Offset);
}

/// \brief Test whether we can convert a value from the old to the new type.
///
/// This predicate should be used to guard calls to convertValue in order to
/// ensure that we only try to convert viable values. The strategy is that we
/// will peel off single element struct and array wrappings to get to an
/// underlying value, and convert that value.
static bool canConvertValue(const DataLayout &DL, Type *OldTy, Type *NewTy) {
  if (OldTy == NewTy)
    return true;
  if (IntegerType *OldITy = dyn_cast<IntegerType>(OldTy))
    if (IntegerType *NewITy = dyn_cast<IntegerType>(NewTy))
      if (NewITy->getBitWidth() >= OldITy->getBitWidth())
        return true;
  if (DL.getTypeSizeInBits(NewTy) != DL.getTypeSizeInBits(OldTy))
    return false;
  if (!NewTy->isSingleValueType() || !OldTy->isSingleValueType())
    return false;

  // We can convert pointers to integers and vice-versa. Same for vectors
  // of pointers and integers.
  OldTy = OldTy->getScalarType();
  NewTy = NewTy->getScalarType();
  if (NewTy->isPointerTy() || OldTy->isPointerTy()) {
    if (NewTy->isPointerTy() && OldTy->isPointerTy())
      return true;
    if (NewTy->isIntegerTy() || OldTy->isIntegerTy())
      return true;
    return false;
  }

  return true;
}

/// \brief Generic routine to convert an SSA value to a value of a different
/// type.
///
/// This will try various different casting techniques, such as bitcasts,
/// inttoptr, and ptrtoint casts. Use the \c canConvertValue predicate to test
/// two types for viability with this routine.
static Value *convertValue(const DataLayout &DL, IRBuilderTy &IRB, Value *V,
                           Type *NewTy) {
  Type *OldTy = V->getType();
  assert(canConvertValue(DL, OldTy, NewTy) && "Value not convertable to type");

  if (OldTy == NewTy)
    return V;

  if (IntegerType *OldITy = dyn_cast<IntegerType>(OldTy))
    if (IntegerType *NewITy = dyn_cast<IntegerType>(NewTy))
      if (NewITy->getBitWidth() > OldITy->getBitWidth())
        return IRB.CreateZExt(V, NewITy);

  // See if we need inttoptr for this type pair. A cast involving both scalars
  // and vectors requires and additional bitcast.
  if (OldTy->getScalarType()->isIntegerTy() &&
      NewTy->getScalarType()->isPointerTy()) {
    // Expand <2 x i32> to i8* --> <2 x i32> to i64 to i8*
    if (OldTy->isVectorTy() && !NewTy->isVectorTy())
      return IRB.CreateIntToPtr(IRB.CreateBitCast(V, DL.getIntPtrType(NewTy)),
                                NewTy);

    // Expand i128 to <2 x i8*> --> i128 to <2 x i64> to <2 x i8*>
    if (!OldTy->isVectorTy() && NewTy->isVectorTy())
      return IRB.CreateIntToPtr(IRB.CreateBitCast(V, DL.getIntPtrType(NewTy)),
                                NewTy);

    return IRB.CreateIntToPtr(V, NewTy);
  }

  // See if we need ptrtoint for this type pair. A cast involving both scalars
  // and vectors requires and additional bitcast.
  if (OldTy->getScalarType()->isPointerTy() &&
      NewTy->getScalarType()->isIntegerTy()) {
    // Expand <2 x i8*> to i128 --> <2 x i8*> to <2 x i64> to i128
    if (OldTy->isVectorTy() && !NewTy->isVectorTy())
      return IRB.CreateBitCast(IRB.CreatePtrToInt(V, DL.getIntPtrType(OldTy)),
                               NewTy);

    // Expand i8* to <2 x i32> --> i8* to i64 to <2 x i32>
    if (!OldTy->isVectorTy() && NewTy->isVectorTy())
      return IRB.CreateBitCast(IRB.CreatePtrToInt(V, DL.getIntPtrType(OldTy)),
                               NewTy);

    return IRB.CreatePtrToInt(V, NewTy);
  }

  return IRB.CreateBitCast(V, NewTy);
}

/// \brief Test whether the given slice use can be promoted to a vector.
///
/// This function is called to test each entry in a partioning which is slated
/// for a single slice.
static bool isVectorPromotionViableForSlice(AllocaSlices::Partition &P,
                                            const Slice &S, VectorType *Ty,
                                            uint64_t ElementSize,
                                            const DataLayout &DL) {
  // First validate the slice offsets.
  uint64_t BeginOffset =
      std::max(S.beginOffset(), P.beginOffset()) - P.beginOffset();
  uint64_t BeginIndex = BeginOffset / ElementSize;
  if (BeginIndex * ElementSize != BeginOffset ||
      BeginIndex >= Ty->getNumElements())
    return false;
  uint64_t EndOffset =
      std::min(S.endOffset(), P.endOffset()) - P.beginOffset();
  uint64_t EndIndex = EndOffset / ElementSize;
  if (EndIndex * ElementSize != EndOffset || EndIndex > Ty->getNumElements())
    return false;

  assert(EndIndex > BeginIndex && "Empty vector!");
  uint64_t NumElements = EndIndex - BeginIndex;
  Type *SliceTy = (NumElements == 1)
                      ? Ty->getElementType()
                      : VectorType::get(Ty->getElementType(), NumElements);

  Type *SplitIntTy =
      Type::getIntNTy(Ty->getContext(), NumElements * ElementSize * 8);

  Use *U = S.getUse();

  if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(U->getUser())) {
    if (MI->isVolatile())
      return false;
    if (!S.isSplittable())
      return false; // Skip any unsplittable intrinsics.
  } else if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(U->getUser())) {
    if (II->getIntrinsicID() != Intrinsic::lifetime_start &&
        II->getIntrinsicID() != Intrinsic::lifetime_end)
      return false;
  } else if (U->get()->getType()->getPointerElementType()->isStructTy()) {
    // Disable vector promotion when there are loads or stores of an FCA.
    return false;
  } else if (LoadInst *LI = dyn_cast<LoadInst>(U->getUser())) {
    if (LI->isVolatile())
      return false;
    Type *LTy = LI->getType();
    if (P.beginOffset() > S.beginOffset() || P.endOffset() < S.endOffset()) {
      assert(LTy->isIntegerTy());
      LTy = SplitIntTy;
    }
    if (!canConvertValue(DL, SliceTy, LTy))
      return false;
  } else if (StoreInst *SI = dyn_cast<StoreInst>(U->getUser())) {
    if (SI->isVolatile())
      return false;
    Type *STy = SI->getValueOperand()->getType();
    if (P.beginOffset() > S.beginOffset() || P.endOffset() < S.endOffset()) {
      assert(STy->isIntegerTy());
      STy = SplitIntTy;
    }
    if (!canConvertValue(DL, STy, SliceTy))
      return false;
  } else {
    return false;
  }

  return true;
}

/// \brief Test whether the given alloca partitioning and range of slices can be
/// promoted to a vector.
///
/// This is a quick test to check whether we can rewrite a particular alloca
/// partition (and its newly formed alloca) into a vector alloca with only
/// whole-vector loads and stores such that it could be promoted to a vector
/// SSA value. We only can ensure this for a limited set of operations, and we
/// don't want to do the rewrites unless we are confident that the result will
/// be promotable, so we have an early test here.
static VectorType *isVectorPromotionViable(AllocaSlices::Partition &P,
                                           const DataLayout &DL) {
  // Collect the candidate types for vector-based promotion. Also track whether
  // we have different element types.
  SmallVector<VectorType *, 4> CandidateTys;
  Type *CommonEltTy = nullptr;
  bool HaveCommonEltTy = true;
  auto CheckCandidateType = [&](Type *Ty) {
    if (auto *VTy = dyn_cast<VectorType>(Ty)) {
      CandidateTys.push_back(VTy);
      if (!CommonEltTy)
        CommonEltTy = VTy->getElementType();
      else if (CommonEltTy != VTy->getElementType())
        HaveCommonEltTy = false;
    }
  };
  // Consider any loads or stores that are the exact size of the slice.
  for (const Slice &S : P)
    if (S.beginOffset() == P.beginOffset() &&
        S.endOffset() == P.endOffset()) {
      if (auto *LI = dyn_cast<LoadInst>(S.getUse()->getUser()))
        CheckCandidateType(LI->getType());
      else if (auto *SI = dyn_cast<StoreInst>(S.getUse()->getUser()))
        CheckCandidateType(SI->getValueOperand()->getType());
    }

  // If we didn't find a vector type, nothing to do here.
  if (CandidateTys.empty())
    return nullptr;

  // Remove non-integer vector types if we had multiple common element types.
  // FIXME: It'd be nice to replace them with integer vector types, but we can't
  // do that until all the backends are known to produce good code for all
  // integer vector types.
  if (!HaveCommonEltTy) {
    CandidateTys.erase(std::remove_if(CandidateTys.begin(), CandidateTys.end(),
                                      [](VectorType *VTy) {
                         return !VTy->getElementType()->isIntegerTy();
                       }),
                       CandidateTys.end());

    // If there were no integer vector types, give up.
    if (CandidateTys.empty())
      return nullptr;

    // Rank the remaining candidate vector types. This is easy because we know
    // they're all integer vectors. We sort by ascending number of elements.
    auto RankVectorTypes = [&DL](VectorType *RHSTy, VectorType *LHSTy) {
      assert(DL.getTypeSizeInBits(RHSTy) == DL.getTypeSizeInBits(LHSTy) &&
             "Cannot have vector types of different sizes!");
      assert(RHSTy->getElementType()->isIntegerTy() &&
             "All non-integer types eliminated!");
      assert(LHSTy->getElementType()->isIntegerTy() &&
             "All non-integer types eliminated!");
      return RHSTy->getNumElements() < LHSTy->getNumElements();
    };
    std::sort(CandidateTys.begin(), CandidateTys.end(), RankVectorTypes);
    CandidateTys.erase(
        std::unique(CandidateTys.begin(), CandidateTys.end(), RankVectorTypes),
        CandidateTys.end());
  } else {
// The only way to have the same element type in every vector type is to
// have the same vector type. Check that and remove all but one.
#ifndef NDEBUG
    for (VectorType *VTy : CandidateTys) {
      assert(VTy->getElementType() == CommonEltTy &&
             "Unaccounted for element type!");
      assert(VTy == CandidateTys[0] &&
             "Different vector types with the same element type!");
    }
#endif
    CandidateTys.resize(1);
  }

  // Try each vector type, and return the one which works.
  auto CheckVectorTypeForPromotion = [&](VectorType *VTy) {
    uint64_t ElementSize = DL.getTypeSizeInBits(VTy->getElementType());

    // While the definition of LLVM vectors is bitpacked, we don't support sizes
    // that aren't byte sized.
    if (ElementSize % 8)
      return false;
    assert((DL.getTypeSizeInBits(VTy) % 8) == 0 &&
           "vector size not a multiple of element size?");
    ElementSize /= 8;

    for (const Slice &S : P)
      if (!isVectorPromotionViableForSlice(P, S, VTy, ElementSize, DL))
        return false;

    for (const Slice *S : P.splitSliceTails())
      if (!isVectorPromotionViableForSlice(P, *S, VTy, ElementSize, DL))
        return false;

    return true;
  };
  for (VectorType *VTy : CandidateTys)
    if (CheckVectorTypeForPromotion(VTy))
      return VTy;

  return nullptr;
}

/// \brief Test whether a slice of an alloca is valid for integer widening.
///
/// This implements the necessary checking for the \c isIntegerWideningViable
/// test below on a single slice of the alloca.
static bool isIntegerWideningViableForSlice(const Slice &S,
                                            uint64_t AllocBeginOffset,
                                            Type *AllocaTy,
                                            const DataLayout &DL,
                                            bool &WholeAllocaOp) {
  uint64_t Size = DL.getTypeStoreSize(AllocaTy);

  uint64_t RelBegin = S.beginOffset() - AllocBeginOffset;
  uint64_t RelEnd = S.endOffset() - AllocBeginOffset;

  // We can't reasonably handle cases where the load or store extends past
  // the end of the aloca's type and into its padding.
  if (RelEnd > Size)
    return false;

  Use *U = S.getUse();

  if (LoadInst *LI = dyn_cast<LoadInst>(U->getUser())) {
    if (LI->isVolatile())
      return false;
    // Note that we don't count vector loads or stores as whole-alloca
    // operations which enable integer widening because we would prefer to use
    // vector widening instead.
    if (!isa<VectorType>(LI->getType()) && RelBegin == 0 && RelEnd == Size)
      WholeAllocaOp = true;
    if (IntegerType *ITy = dyn_cast<IntegerType>(LI->getType())) {
      if (ITy->getBitWidth() < DL.getTypeStoreSizeInBits(ITy))
        return false;
    } else if (RelBegin != 0 || RelEnd != Size ||
               !canConvertValue(DL, AllocaTy, LI->getType())) {
      // Non-integer loads need to be convertible from the alloca type so that
      // they are promotable.
      return false;
    }
  } else if (StoreInst *SI = dyn_cast<StoreInst>(U->getUser())) {
    Type *ValueTy = SI->getValueOperand()->getType();
    if (SI->isVolatile())
      return false;
    // Note that we don't count vector loads or stores as whole-alloca
    // operations which enable integer widening because we would prefer to use
    // vector widening instead.
    if (!isa<VectorType>(ValueTy) && RelBegin == 0 && RelEnd == Size)
      WholeAllocaOp = true;
    if (IntegerType *ITy = dyn_cast<IntegerType>(ValueTy)) {
      if (ITy->getBitWidth() < DL.getTypeStoreSizeInBits(ITy))
        return false;
    } else if (RelBegin != 0 || RelEnd != Size ||
               !canConvertValue(DL, ValueTy, AllocaTy)) {
      // Non-integer stores need to be convertible to the alloca type so that
      // they are promotable.
      return false;
    }
  } else if (MemIntrinsic *MI = dyn_cast<MemIntrinsic>(U->getUser())) {
    if (MI->isVolatile() || !isa<Constant>(MI->getLength()))
      return false;
    if (!S.isSplittable())
      return false; // Skip any unsplittable intrinsics.
  } else if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(U->getUser())) {
    if (II->getIntrinsicID() != Intrinsic::lifetime_start &&
        II->getIntrinsicID() != Intrinsic::lifetime_end)
      return false;
  } else {
    return false;
  }

  return true;
}

/// \brief Test whether the given alloca partition's integer operations can be
/// widened to promotable ones.
///
/// This is a quick test to check whether we can rewrite the integer loads and
/// stores to a particular alloca into wider loads and stores and be able to
/// promote the resulting alloca.
static bool isIntegerWideningViable(AllocaSlices::Partition &P, Type *AllocaTy,
                                    const DataLayout &DL) {
  uint64_t SizeInBits = DL.getTypeSizeInBits(AllocaTy);
  // Don't create integer types larger than the maximum bitwidth.
  if (SizeInBits > IntegerType::MAX_INT_BITS)
    return false;

  // Don't try to handle allocas with bit-padding.
  if (SizeInBits != DL.getTypeStoreSizeInBits(AllocaTy))
    return false;

  // We need to ensure that an integer type with the appropriate bitwidth can
  // be converted to the alloca type, whatever that is. We don't want to force
  // the alloca itself to have an integer type if there is a more suitable one.
  Type *IntTy = Type::getIntNTy(AllocaTy->getContext(), SizeInBits);
  if (!canConvertValue(DL, AllocaTy, IntTy) ||
      !canConvertValue(DL, IntTy, AllocaTy))
    return false;

  // While examining uses, we ensure that the alloca has a covering load or
  // store. We don't want to widen the integer operations only to fail to
  // promote due to some other unsplittable entry (which we may make splittable
  // later). However, if there are only splittable uses, go ahead and assume
  // that we cover the alloca.
  // FIXME: We shouldn't consider split slices that happen to start in the
  // partition here...
  bool WholeAllocaOp =
      P.begin() != P.end() ? false : DL.isLegalInteger(SizeInBits);

  for (const Slice &S : P)
    if (!isIntegerWideningViableForSlice(S, P.beginOffset(), AllocaTy, DL,
                                         WholeAllocaOp))
      return false;

  for (const Slice *S : P.splitSliceTails())
    if (!isIntegerWideningViableForSlice(*S, P.beginOffset(), AllocaTy, DL,
                                         WholeAllocaOp))
      return false;

  return WholeAllocaOp;
}

static Value *extractInteger(const DataLayout &DL, IRBuilderTy &IRB, Value *V,
                             IntegerType *Ty, uint64_t Offset,
                             const Twine &Name) {
  DEBUG(dbgs() << "       start: " << *V << "\n");
  IntegerType *IntTy = cast<IntegerType>(V->getType());
  assert(DL.getTypeStoreSize(Ty) + Offset <= DL.getTypeStoreSize(IntTy) &&
         "Element extends past full value");
  uint64_t ShAmt = 8 * Offset;
  if (DL.isBigEndian())
    ShAmt = 8 * (DL.getTypeStoreSize(IntTy) - DL.getTypeStoreSize(Ty) - Offset);
  if (ShAmt) {
    V = IRB.CreateLShr(V, ShAmt, Name + ".shift");
    DEBUG(dbgs() << "     shifted: " << *V << "\n");
  }
  assert(Ty->getBitWidth() <= IntTy->getBitWidth() &&
         "Cannot extract to a larger integer!");
  if (Ty != IntTy) {
    V = IRB.CreateTrunc(V, Ty, Name + ".trunc");
    DEBUG(dbgs() << "     trunced: " << *V << "\n");
  }
  return V;
}

static Value *insertInteger(const DataLayout &DL, IRBuilderTy &IRB, Value *Old,
                            Value *V, uint64_t Offset, const Twine &Name) {
  IntegerType *IntTy = cast<IntegerType>(Old->getType());
  IntegerType *Ty = cast<IntegerType>(V->getType());
  assert(Ty->getBitWidth() <= IntTy->getBitWidth() &&
         "Cannot insert a larger integer!");
  DEBUG(dbgs() << "       start: " << *V << "\n");
  if (Ty != IntTy) {
    V = IRB.CreateZExt(V, IntTy, Name + ".ext");
    DEBUG(dbgs() << "    extended: " << *V << "\n");
  }
  assert(DL.getTypeStoreSize(Ty) + Offset <= DL.getTypeStoreSize(IntTy) &&
         "Element store outside of alloca store");
  uint64_t ShAmt = 8 * Offset;
  if (DL.isBigEndian())
    ShAmt = 8 * (DL.getTypeStoreSize(IntTy) - DL.getTypeStoreSize(Ty) - Offset);
  if (ShAmt) {
    V = IRB.CreateShl(V, ShAmt, Name + ".shift");
    DEBUG(dbgs() << "     shifted: " << *V << "\n");
  }

  if (ShAmt || Ty->getBitWidth() < IntTy->getBitWidth()) {
    APInt Mask = ~Ty->getMask().zext(IntTy->getBitWidth()).shl(ShAmt);
    Old = IRB.CreateAnd(Old, Mask, Name + ".mask");
    DEBUG(dbgs() << "      masked: " << *Old << "\n");
    V = IRB.CreateOr(Old, V, Name + ".insert");
    DEBUG(dbgs() << "    inserted: " << *V << "\n");
  }
  return V;
}

static Value *extractVector(IRBuilderTy &IRB, Value *V, unsigned BeginIndex,
                            unsigned EndIndex, const Twine &Name) {
  VectorType *VecTy = cast<VectorType>(V->getType());
  unsigned NumElements = EndIndex - BeginIndex;
  assert(NumElements <= VecTy->getNumElements() && "Too many elements!");

  if (NumElements == VecTy->getNumElements())
    return V;

  if (NumElements == 1) {
    V = IRB.CreateExtractElement(V, IRB.getInt32(BeginIndex),
                                 Name + ".extract");
    DEBUG(dbgs() << "     extract: " << *V << "\n");
    return V;
  }

  SmallVector<Constant *, 8> Mask;
  Mask.reserve(NumElements);
  for (unsigned i = BeginIndex; i != EndIndex; ++i)
    Mask.push_back(IRB.getInt32(i));
  V = IRB.CreateShuffleVector(V, UndefValue::get(V->getType()),
                              ConstantVector::get(Mask), Name + ".extract");
  DEBUG(dbgs() << "     shuffle: " << *V << "\n");
  return V;
}

static Value *insertVector(IRBuilderTy &IRB, Value *Old, Value *V,
                           unsigned BeginIndex, const Twine &Name) {
  VectorType *VecTy = cast<VectorType>(Old->getType());
  assert(VecTy && "Can only insert a vector into a vector");

  VectorType *Ty = dyn_cast<VectorType>(V->getType());
  if (!Ty) {
    // Single element to insert.
    V = IRB.CreateInsertElement(Old, V, IRB.getInt32(BeginIndex),
                                Name + ".insert");
    DEBUG(dbgs() << "     insert: " << *V << "\n");
    return V;
  }

  assert(Ty->getNumElements() <= VecTy->getNumElements() &&
         "Too many elements!");
  if (Ty->getNumElements() == VecTy->getNumElements()) {
    assert(V->getType() == VecTy && "Vector type mismatch");
    return V;
  }
  unsigned EndIndex = BeginIndex + Ty->getNumElements();

  // When inserting a smaller vector into the larger to store, we first
  // use a shuffle vector to widen it with undef elements, and then
  // a second shuffle vector to select between the loaded vector and the
  // incoming vector.
  SmallVector<Constant *, 8> Mask;
  Mask.reserve(VecTy->getNumElements());
  for (unsigned i = 0; i != VecTy->getNumElements(); ++i)
    if (i >= BeginIndex && i < EndIndex)
      Mask.push_back(IRB.getInt32(i - BeginIndex));
    else
      Mask.push_back(UndefValue::get(IRB.getInt32Ty()));
  V = IRB.CreateShuffleVector(V, UndefValue::get(V->getType()),
                              ConstantVector::get(Mask), Name + ".expand");
  DEBUG(dbgs() << "    shuffle: " << *V << "\n");

  Mask.clear();
  for (unsigned i = 0; i != VecTy->getNumElements(); ++i)
    Mask.push_back(IRB.getInt1(i >= BeginIndex && i < EndIndex));

  V = IRB.CreateSelect(ConstantVector::get(Mask), V, Old, Name + "blend");

  DEBUG(dbgs() << "    blend: " << *V << "\n");
  return V;
}

namespace {
/// \brief Visitor to rewrite instructions using p particular slice of an alloca
/// to use a new alloca.
///
/// Also implements the rewriting to vector-based accesses when the partition
/// passes the isVectorPromotionViable predicate. Most of the rewriting logic
/// lives here.
class AllocaSliceRewriter : public InstVisitor<AllocaSliceRewriter, bool> {
  // Befriend the base class so it can delegate to private visit methods.
  friend class llvm::InstVisitor<AllocaSliceRewriter, bool>;
  typedef llvm::InstVisitor<AllocaSliceRewriter, bool> Base;

  const DataLayout &DL;
  AllocaSlices &AS;
  SROA &Pass;
  AllocaInst &OldAI, &NewAI;
  const uint64_t NewAllocaBeginOffset, NewAllocaEndOffset;
  Type *NewAllocaTy;

  // This is a convenience and flag variable that will be null unless the new
  // alloca's integer operations should be widened to this integer type due to
  // passing isIntegerWideningViable above. If it is non-null, the desired
  // integer type will be stored here for easy access during rewriting.
  IntegerType *IntTy;

  // If we are rewriting an alloca partition which can be written as pure
  // vector operations, we stash extra information here. When VecTy is
  // non-null, we have some strict guarantees about the rewritten alloca:
  //   - The new alloca is exactly the size of the vector type here.
  //   - The accesses all either map to the entire vector or to a single
  //     element.
  //   - The set of accessing instructions is only one of those handled above
  //     in isVectorPromotionViable. Generally these are the same access kinds
  //     which are promotable via mem2reg.
  VectorType *VecTy;
  Type *ElementTy;
  uint64_t ElementSize;

  // The original offset of the slice currently being rewritten relative to
  // the original alloca.
  uint64_t BeginOffset, EndOffset;
  // The new offsets of the slice currently being rewritten relative to the
  // original alloca.
  uint64_t NewBeginOffset, NewEndOffset;

  uint64_t SliceSize;
  bool IsSplittable;
  bool IsSplit;
  Use *OldUse;
  Instruction *OldPtr;

  // Track post-rewrite users which are PHI nodes and Selects.
  SmallPtrSetImpl<PHINode *> &PHIUsers;
  SmallPtrSetImpl<SelectInst *> &SelectUsers;

  // Utility IR builder, whose name prefix is setup for each visited use, and
  // the insertion point is set to point to the user.
  IRBuilderTy IRB;

public:
  AllocaSliceRewriter(const DataLayout &DL, AllocaSlices &AS, SROA &Pass,
                      AllocaInst &OldAI, AllocaInst &NewAI,
                      uint64_t NewAllocaBeginOffset,
                      uint64_t NewAllocaEndOffset, bool IsIntegerPromotable,
                      VectorType *PromotableVecTy,
                      SmallPtrSetImpl<PHINode *> &PHIUsers,
                      SmallPtrSetImpl<SelectInst *> &SelectUsers)
      : DL(DL), AS(AS), Pass(Pass), OldAI(OldAI), NewAI(NewAI),
        NewAllocaBeginOffset(NewAllocaBeginOffset),
        NewAllocaEndOffset(NewAllocaEndOffset),
        NewAllocaTy(NewAI.getAllocatedType()),
        IntTy(IsIntegerPromotable
                  ? Type::getIntNTy(
                        NewAI.getContext(),
                        DL.getTypeSizeInBits(NewAI.getAllocatedType()))
                  : nullptr),
        VecTy(PromotableVecTy),
        ElementTy(VecTy ? VecTy->getElementType() : nullptr),
        ElementSize(VecTy ? DL.getTypeSizeInBits(ElementTy) / 8 : 0),
        BeginOffset(), EndOffset(), IsSplittable(), IsSplit(), OldUse(),
        OldPtr(), PHIUsers(PHIUsers), SelectUsers(SelectUsers),
        IRB(NewAI.getContext(), ConstantFolder()) {
    if (VecTy) {
      assert((DL.getTypeSizeInBits(ElementTy) % 8) == 0 &&
             "Only multiple-of-8 sized vector elements are viable");
      ++NumVectorized;
    }
    assert((!IntTy && !VecTy) || (IntTy && !VecTy) || (!IntTy && VecTy));
  }

  bool visit(AllocaSlices::const_iterator I) {
    bool CanSROA = true;
    BeginOffset = I->beginOffset();
    EndOffset = I->endOffset();
    IsSplittable = I->isSplittable();
    IsSplit =
        BeginOffset < NewAllocaBeginOffset || EndOffset > NewAllocaEndOffset;
    DEBUG(dbgs() << "  rewriting " << (IsSplit ? "split " : ""));
    DEBUG(AS.printSlice(dbgs(), I, ""));
    DEBUG(dbgs() << "\n");

    // Compute the intersecting offset range.
    assert(BeginOffset < NewAllocaEndOffset);
    assert(EndOffset > NewAllocaBeginOffset);
    NewBeginOffset = std::max(BeginOffset, NewAllocaBeginOffset);
    NewEndOffset = std::min(EndOffset, NewAllocaEndOffset);

    SliceSize = NewEndOffset - NewBeginOffset;

    OldUse = I->getUse();
    OldPtr = cast<Instruction>(OldUse->get());

    Instruction *OldUserI = cast<Instruction>(OldUse->getUser());
    IRB.SetInsertPoint(OldUserI);
    IRB.SetCurrentDebugLocation(OldUserI->getDebugLoc());
    IRB.SetNamePrefix(Twine(NewAI.getName()) + "." + Twine(BeginOffset) + ".");

    CanSROA &= visit(cast<Instruction>(OldUse->getUser()));
    if (VecTy || IntTy)
      assert(CanSROA);
    return CanSROA;
  }

private:
  // Make sure the other visit overloads are visible.
  using Base::visit;

  // Every instruction which can end up as a user must have a rewrite rule.
  bool visitInstruction(Instruction &I) {
    DEBUG(dbgs() << "    !!!! Cannot rewrite: " << I << "\n");
    llvm_unreachable("No rewrite rule for this instruction!");
  }

  Value *getNewAllocaSlicePtr(IRBuilderTy &IRB, Type *PointerTy) {
    // Note that the offset computation can use BeginOffset or NewBeginOffset
    // interchangeably for unsplit slices.
    assert(IsSplit || BeginOffset == NewBeginOffset);
    uint64_t Offset = NewBeginOffset - NewAllocaBeginOffset;

#ifndef NDEBUG
    StringRef OldName = OldPtr->getName();
    // Skip through the last '.sroa.' component of the name.
    size_t LastSROAPrefix = OldName.rfind(".sroa.");
    if (LastSROAPrefix != StringRef::npos) {
      OldName = OldName.substr(LastSROAPrefix + strlen(".sroa."));
      // Look for an SROA slice index.
      size_t IndexEnd = OldName.find_first_not_of("0123456789");
      if (IndexEnd != StringRef::npos && OldName[IndexEnd] == '.') {
        // Strip the index and look for the offset.
        OldName = OldName.substr(IndexEnd + 1);
        size_t OffsetEnd = OldName.find_first_not_of("0123456789");
        if (OffsetEnd != StringRef::npos && OldName[OffsetEnd] == '.')
          // Strip the offset.
          OldName = OldName.substr(OffsetEnd + 1);
      }
    }
    // Strip any SROA suffixes as well.
    OldName = OldName.substr(0, OldName.find(".sroa_"));
#endif

    return getAdjustedPtr(IRB, DL, &NewAI,
                          APInt(DL.getPointerSizeInBits(), Offset), PointerTy,
#ifndef NDEBUG
                          Twine(OldName) + "."
#else
                          Twine()
#endif
                          );
  }

  /// \brief Compute suitable alignment to access this slice of the *new*
  /// alloca.
  ///
  /// You can optionally pass a type to this routine and if that type's ABI
  /// alignment is itself suitable, this will return zero.
  unsigned getSliceAlign(Type *Ty = nullptr) {
    unsigned NewAIAlign = NewAI.getAlignment();
    if (!NewAIAlign)
      NewAIAlign = DL.getABITypeAlignment(NewAI.getAllocatedType());
    unsigned Align =
        MinAlign(NewAIAlign, NewBeginOffset - NewAllocaBeginOffset);
    return (Ty && Align == DL.getABITypeAlignment(Ty)) ? 0 : Align;
  }

  unsigned getIndex(uint64_t Offset) {
    assert(VecTy && "Can only call getIndex when rewriting a vector");
    uint64_t RelOffset = Offset - NewAllocaBeginOffset;
    assert(RelOffset / ElementSize < UINT32_MAX && "Index out of bounds");
    uint32_t Index = RelOffset / ElementSize;
    assert(Index * ElementSize == RelOffset);
    return Index;
  }

  void deleteIfTriviallyDead(Value *V) {
    Instruction *I = cast<Instruction>(V);
    if (isInstructionTriviallyDead(I))
      Pass.DeadInsts.insert(I);
  }

  Value *rewriteVectorizedLoadInst() {
    unsigned BeginIndex = getIndex(NewBeginOffset);
    unsigned EndIndex = getIndex(NewEndOffset);
    assert(EndIndex > BeginIndex && "Empty vector!");

    Value *V = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "load");
    return extractVector(IRB, V, BeginIndex, EndIndex, "vec");
  }

  Value *rewriteIntegerLoad(LoadInst &LI) {
    assert(IntTy && "We cannot insert an integer to the alloca");
    assert(!LI.isVolatile());
    Value *V = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "load");
    V = convertValue(DL, IRB, V, IntTy);
    assert(NewBeginOffset >= NewAllocaBeginOffset && "Out of bounds offset");
    uint64_t Offset = NewBeginOffset - NewAllocaBeginOffset;
    if (Offset > 0 || NewEndOffset < NewAllocaEndOffset)
      V = extractInteger(DL, IRB, V, cast<IntegerType>(LI.getType()), Offset,
                         "extract");
    return V;
  }

  bool visitLoadInst(LoadInst &LI) {
    DEBUG(dbgs() << "    original: " << LI << "\n");
    Value *OldOp = LI.getOperand(0);
    assert(OldOp == OldPtr);

    Type *TargetTy = IsSplit ? Type::getIntNTy(LI.getContext(), SliceSize * 8)
                             : LI.getType();
    bool IsPtrAdjusted = false;
    Value *V;
    if (VecTy) {
      V = rewriteVectorizedLoadInst();
    } else if (IntTy && LI.getType()->isIntegerTy()) {
      V = rewriteIntegerLoad(LI);
    } else if (NewBeginOffset == NewAllocaBeginOffset &&
               canConvertValue(DL, NewAllocaTy, LI.getType())) {
      V = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), LI.isVolatile(),
                                LI.getName());
    } else {
      Type *LTy = TargetTy->getPointerTo();
      V = IRB.CreateAlignedLoad(getNewAllocaSlicePtr(IRB, LTy),
                                getSliceAlign(TargetTy), LI.isVolatile(),
                                LI.getName());
      IsPtrAdjusted = true;
    }
    V = convertValue(DL, IRB, V, TargetTy);

    if (IsSplit) {
      assert(!LI.isVolatile());
      assert(LI.getType()->isIntegerTy() &&
             "Only integer type loads and stores are split");
      assert(SliceSize < DL.getTypeStoreSize(LI.getType()) &&
             "Split load isn't smaller than original load");
      assert(LI.getType()->getIntegerBitWidth() ==
                 DL.getTypeStoreSizeInBits(LI.getType()) &&
             "Non-byte-multiple bit width");
      // Move the insertion point just past the load so that we can refer to it.
      IRB.SetInsertPoint(std::next(BasicBlock::iterator(&LI)));
      // Create a placeholder value with the same type as LI to use as the
      // basis for the new value. This allows us to replace the uses of LI with
      // the computed value, and then replace the placeholder with LI, leaving
      // LI only used for this computation.
      Value *Placeholder =
          new LoadInst(UndefValue::get(LI.getType()->getPointerTo()));
      V = insertInteger(DL, IRB, Placeholder, V, NewBeginOffset - BeginOffset,
                        "insert");
      LI.replaceAllUsesWith(V);
      Placeholder->replaceAllUsesWith(&LI);
      delete Placeholder;
    } else {
      LI.replaceAllUsesWith(V);
    }

    Pass.DeadInsts.insert(&LI);
    deleteIfTriviallyDead(OldOp);
    DEBUG(dbgs() << "          to: " << *V << "\n");
    return !LI.isVolatile() && !IsPtrAdjusted;
  }

  bool rewriteVectorizedStoreInst(Value *V, StoreInst &SI, Value *OldOp) {
    if (V->getType() != VecTy) {
      unsigned BeginIndex = getIndex(NewBeginOffset);
      unsigned EndIndex = getIndex(NewEndOffset);
      assert(EndIndex > BeginIndex && "Empty vector!");
      unsigned NumElements = EndIndex - BeginIndex;
      assert(NumElements <= VecTy->getNumElements() && "Too many elements!");
      Type *SliceTy = (NumElements == 1)
                          ? ElementTy
                          : VectorType::get(ElementTy, NumElements);
      if (V->getType() != SliceTy)
        V = convertValue(DL, IRB, V, SliceTy);

      // Mix in the existing elements.
      Value *Old = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "load");
      V = insertVector(IRB, Old, V, BeginIndex, "vec");
    }
    StoreInst *Store = IRB.CreateAlignedStore(V, &NewAI, NewAI.getAlignment());
    Pass.DeadInsts.insert(&SI);

    (void)Store;
    DEBUG(dbgs() << "          to: " << *Store << "\n");
    return true;
  }

  bool rewriteIntegerStore(Value *V, StoreInst &SI) {
    assert(IntTy && "We cannot extract an integer from the alloca");
    assert(!SI.isVolatile());
    if (DL.getTypeSizeInBits(V->getType()) != IntTy->getBitWidth()) {
      Value *Old =
          IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "oldload");
      Old = convertValue(DL, IRB, Old, IntTy);
      assert(BeginOffset >= NewAllocaBeginOffset && "Out of bounds offset");
      uint64_t Offset = BeginOffset - NewAllocaBeginOffset;
      V = insertInteger(DL, IRB, Old, SI.getValueOperand(), Offset, "insert");
    }
    V = convertValue(DL, IRB, V, NewAllocaTy);
    StoreInst *Store = IRB.CreateAlignedStore(V, &NewAI, NewAI.getAlignment());
    Pass.DeadInsts.insert(&SI);
    (void)Store;
    DEBUG(dbgs() << "          to: " << *Store << "\n");
    return true;
  }

  bool visitStoreInst(StoreInst &SI) {
    DEBUG(dbgs() << "    original: " << SI << "\n");
    Value *OldOp = SI.getOperand(1);
    assert(OldOp == OldPtr);

    Value *V = SI.getValueOperand();

    // Strip all inbounds GEPs and pointer casts to try to dig out any root
    // alloca that should be re-examined after promoting this alloca.
    if (V->getType()->isPointerTy())
      if (AllocaInst *AI = dyn_cast<AllocaInst>(V->stripInBoundsOffsets()))
        Pass.PostPromotionWorklist.insert(AI);

    if (SliceSize < DL.getTypeStoreSize(V->getType())) {
      assert(!SI.isVolatile());
      assert(V->getType()->isIntegerTy() &&
             "Only integer type loads and stores are split");
      assert(V->getType()->getIntegerBitWidth() ==
                 DL.getTypeStoreSizeInBits(V->getType()) &&
             "Non-byte-multiple bit width");
      IntegerType *NarrowTy = Type::getIntNTy(SI.getContext(), SliceSize * 8);
      V = extractInteger(DL, IRB, V, NarrowTy, NewBeginOffset - BeginOffset,
                         "extract");
    }

    if (VecTy)
      return rewriteVectorizedStoreInst(V, SI, OldOp);
    if (IntTy && V->getType()->isIntegerTy())
      return rewriteIntegerStore(V, SI);

    StoreInst *NewSI;
    if (NewBeginOffset == NewAllocaBeginOffset &&
        NewEndOffset == NewAllocaEndOffset &&
        canConvertValue(DL, V->getType(), NewAllocaTy)) {
      V = convertValue(DL, IRB, V, NewAllocaTy);
      NewSI = IRB.CreateAlignedStore(V, &NewAI, NewAI.getAlignment(),
                                     SI.isVolatile());
    } else {
      Value *NewPtr = getNewAllocaSlicePtr(IRB, V->getType()->getPointerTo());
      NewSI = IRB.CreateAlignedStore(V, NewPtr, getSliceAlign(V->getType()),
                                     SI.isVolatile());
    }
    (void)NewSI;
    Pass.DeadInsts.insert(&SI);
    deleteIfTriviallyDead(OldOp);

    DEBUG(dbgs() << "          to: " << *NewSI << "\n");
    return NewSI->getPointerOperand() == &NewAI && !SI.isVolatile();
  }

  /// \brief Compute an integer value from splatting an i8 across the given
  /// number of bytes.
  ///
  /// Note that this routine assumes an i8 is a byte. If that isn't true, don't
  /// call this routine.
  /// FIXME: Heed the advice above.
  ///
  /// \param V The i8 value to splat.
  /// \param Size The number of bytes in the output (assuming i8 is one byte)
  Value *getIntegerSplat(Value *V, unsigned Size) {
    assert(Size > 0 && "Expected a positive number of bytes.");
    IntegerType *VTy = cast<IntegerType>(V->getType());
    assert(VTy->getBitWidth() == 8 && "Expected an i8 value for the byte");
    if (Size == 1)
      return V;

    Type *SplatIntTy = Type::getIntNTy(VTy->getContext(), Size * 8);
    V = IRB.CreateMul(
        IRB.CreateZExt(V, SplatIntTy, "zext"),
        ConstantExpr::getUDiv(
            Constant::getAllOnesValue(SplatIntTy),
            ConstantExpr::getZExt(Constant::getAllOnesValue(V->getType()),
                                  SplatIntTy)),
        "isplat");
    return V;
  }

  /// \brief Compute a vector splat for a given element value.
  Value *getVectorSplat(Value *V, unsigned NumElements) {
    V = IRB.CreateVectorSplat(NumElements, V, "vsplat");
    DEBUG(dbgs() << "       splat: " << *V << "\n");
    return V;
  }

  bool visitMemSetInst(MemSetInst &II) {
    DEBUG(dbgs() << "    original: " << II << "\n");
    assert(II.getRawDest() == OldPtr);

    // If the memset has a variable size, it cannot be split, just adjust the
    // pointer to the new alloca.
    if (!isa<Constant>(II.getLength())) {
      assert(!IsSplit);
      assert(NewBeginOffset == BeginOffset);
      II.setDest(getNewAllocaSlicePtr(IRB, OldPtr->getType()));
      Type *CstTy = II.getAlignmentCst()->getType();
      II.setAlignment(ConstantInt::get(CstTy, getSliceAlign()));

      deleteIfTriviallyDead(OldPtr);
      return false;
    }

    // Record this instruction for deletion.
    Pass.DeadInsts.insert(&II);

    Type *AllocaTy = NewAI.getAllocatedType();
    Type *ScalarTy = AllocaTy->getScalarType();

    // If this doesn't map cleanly onto the alloca type, and that type isn't
    // a single value type, just emit a memset.
    if (!VecTy && !IntTy &&
        (BeginOffset > NewAllocaBeginOffset || EndOffset < NewAllocaEndOffset ||
         SliceSize != DL.getTypeStoreSize(AllocaTy) ||
         !AllocaTy->isSingleValueType() ||
         !DL.isLegalInteger(DL.getTypeSizeInBits(ScalarTy)) ||
         DL.getTypeSizeInBits(ScalarTy) % 8 != 0)) {
      Type *SizeTy = II.getLength()->getType();
      Constant *Size = ConstantInt::get(SizeTy, NewEndOffset - NewBeginOffset);
      CallInst *New = IRB.CreateMemSet(
          getNewAllocaSlicePtr(IRB, OldPtr->getType()), II.getValue(), Size,
          getSliceAlign(), II.isVolatile());
      (void)New;
      DEBUG(dbgs() << "          to: " << *New << "\n");
      return false;
    }

    // If we can represent this as a simple value, we have to build the actual
    // value to store, which requires expanding the byte present in memset to
    // a sensible representation for the alloca type. This is essentially
    // splatting the byte to a sufficiently wide integer, splatting it across
    // any desired vector width, and bitcasting to the final type.
    Value *V;

    if (VecTy) {
      // If this is a memset of a vectorized alloca, insert it.
      assert(ElementTy == ScalarTy);

      unsigned BeginIndex = getIndex(NewBeginOffset);
      unsigned EndIndex = getIndex(NewEndOffset);
      assert(EndIndex > BeginIndex && "Empty vector!");
      unsigned NumElements = EndIndex - BeginIndex;
      assert(NumElements <= VecTy->getNumElements() && "Too many elements!");

      Value *Splat =
          getIntegerSplat(II.getValue(), DL.getTypeSizeInBits(ElementTy) / 8);
      Splat = convertValue(DL, IRB, Splat, ElementTy);
      if (NumElements > 1)
        Splat = getVectorSplat(Splat, NumElements);

      Value *Old =
          IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "oldload");
      V = insertVector(IRB, Old, Splat, BeginIndex, "vec");
    } else if (IntTy) {
      // If this is a memset on an alloca where we can widen stores, insert the
      // set integer.
      assert(!II.isVolatile());

      uint64_t Size = NewEndOffset - NewBeginOffset;
      V = getIntegerSplat(II.getValue(), Size);

      if (IntTy && (BeginOffset != NewAllocaBeginOffset ||
                    EndOffset != NewAllocaBeginOffset)) {
        Value *Old =
            IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "oldload");
        Old = convertValue(DL, IRB, Old, IntTy);
        uint64_t Offset = NewBeginOffset - NewAllocaBeginOffset;
        V = insertInteger(DL, IRB, Old, V, Offset, "insert");
      } else {
        assert(V->getType() == IntTy &&
               "Wrong type for an alloca wide integer!");
      }
      V = convertValue(DL, IRB, V, AllocaTy);
    } else {
      // Established these invariants above.
      assert(NewBeginOffset == NewAllocaBeginOffset);
      assert(NewEndOffset == NewAllocaEndOffset);

      V = getIntegerSplat(II.getValue(), DL.getTypeSizeInBits(ScalarTy) / 8);
      if (VectorType *AllocaVecTy = dyn_cast<VectorType>(AllocaTy))
        V = getVectorSplat(V, AllocaVecTy->getNumElements());

      V = convertValue(DL, IRB, V, AllocaTy);
    }

    Value *New = IRB.CreateAlignedStore(V, &NewAI, NewAI.getAlignment(),
                                        II.isVolatile());
    (void)New;
    DEBUG(dbgs() << "          to: " << *New << "\n");
    return !II.isVolatile();
  }

  bool visitMemTransferInst(MemTransferInst &II) {
    // Rewriting of memory transfer instructions can be a bit tricky. We break
    // them into two categories: split intrinsics and unsplit intrinsics.

    DEBUG(dbgs() << "    original: " << II << "\n");

    bool IsDest = &II.getRawDestUse() == OldUse;
    assert((IsDest && II.getRawDest() == OldPtr) ||
           (!IsDest && II.getRawSource() == OldPtr));

    unsigned SliceAlign = getSliceAlign();

    // For unsplit intrinsics, we simply modify the source and destination
    // pointers in place. This isn't just an optimization, it is a matter of
    // correctness. With unsplit intrinsics we may be dealing with transfers
    // within a single alloca before SROA ran, or with transfers that have
    // a variable length. We may also be dealing with memmove instead of
    // memcpy, and so simply updating the pointers is the necessary for us to
    // update both source and dest of a single call.
    if (!IsSplittable) {
      Value *AdjustedPtr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
      if (IsDest)
        II.setDest(AdjustedPtr);
      else
        II.setSource(AdjustedPtr);

      if (II.getAlignment() > SliceAlign) {
        Type *CstTy = II.getAlignmentCst()->getType();
        II.setAlignment(
            ConstantInt::get(CstTy, MinAlign(II.getAlignment(), SliceAlign)));
      }

      DEBUG(dbgs() << "          to: " << II << "\n");
      deleteIfTriviallyDead(OldPtr);
      return false;
    }
    // For split transfer intrinsics we have an incredibly useful assurance:
    // the source and destination do not reside within the same alloca, and at
    // least one of them does not escape. This means that we can replace
    // memmove with memcpy, and we don't need to worry about all manner of
    // downsides to splitting and transforming the operations.

    // If this doesn't map cleanly onto the alloca type, and that type isn't
    // a single value type, just emit a memcpy.
    bool EmitMemCpy =
        !VecTy && !IntTy &&
        (BeginOffset > NewAllocaBeginOffset || EndOffset < NewAllocaEndOffset ||
         SliceSize != DL.getTypeStoreSize(NewAI.getAllocatedType()) ||
         !NewAI.getAllocatedType()->isSingleValueType());

    // If we're just going to emit a memcpy, the alloca hasn't changed, and the
    // size hasn't been shrunk based on analysis of the viable range, this is
    // a no-op.
    if (EmitMemCpy && &OldAI == &NewAI) {
      // Ensure the start lines up.
      assert(NewBeginOffset == BeginOffset);

      // Rewrite the size as needed.
      if (NewEndOffset != EndOffset)
        II.setLength(ConstantInt::get(II.getLength()->getType(),
                                      NewEndOffset - NewBeginOffset));
      return false;
    }
    // Record this instruction for deletion.
    Pass.DeadInsts.insert(&II);

    // Strip all inbounds GEPs and pointer casts to try to dig out any root
    // alloca that should be re-examined after rewriting this instruction.
    Value *OtherPtr = IsDest ? II.getRawSource() : II.getRawDest();
    if (AllocaInst *AI =
            dyn_cast<AllocaInst>(OtherPtr->stripInBoundsOffsets())) {
      assert(AI != &OldAI && AI != &NewAI &&
             "Splittable transfers cannot reach the same alloca on both ends.");
      Pass.Worklist.insert(AI);
    }

    Type *OtherPtrTy = OtherPtr->getType();
    unsigned OtherAS = OtherPtrTy->getPointerAddressSpace();

    // Compute the relative offset for the other pointer within the transfer.
    unsigned IntPtrWidth = DL.getPointerSizeInBits(OtherAS);
    APInt OtherOffset(IntPtrWidth, NewBeginOffset - BeginOffset);
    unsigned OtherAlign = MinAlign(II.getAlignment() ? II.getAlignment() : 1,
                                   OtherOffset.zextOrTrunc(64).getZExtValue());

    if (EmitMemCpy) {
      // Compute the other pointer, folding as much as possible to produce
      // a single, simple GEP in most cases.
      OtherPtr = getAdjustedPtr(IRB, DL, OtherPtr, OtherOffset, OtherPtrTy,
                                OtherPtr->getName() + ".");

      Value *OurPtr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
      Type *SizeTy = II.getLength()->getType();
      Constant *Size = ConstantInt::get(SizeTy, NewEndOffset - NewBeginOffset);

      CallInst *New = IRB.CreateMemCpy(
          IsDest ? OurPtr : OtherPtr, IsDest ? OtherPtr : OurPtr, Size,
          MinAlign(SliceAlign, OtherAlign), II.isVolatile());
      (void)New;
      DEBUG(dbgs() << "          to: " << *New << "\n");
      return false;
    }

    bool IsWholeAlloca = NewBeginOffset == NewAllocaBeginOffset &&
                         NewEndOffset == NewAllocaEndOffset;
    uint64_t Size = NewEndOffset - NewBeginOffset;
    unsigned BeginIndex = VecTy ? getIndex(NewBeginOffset) : 0;
    unsigned EndIndex = VecTy ? getIndex(NewEndOffset) : 0;
    unsigned NumElements = EndIndex - BeginIndex;
    IntegerType *SubIntTy =
        IntTy ? Type::getIntNTy(IntTy->getContext(), Size * 8) : nullptr;

    // Reset the other pointer type to match the register type we're going to
    // use, but using the address space of the original other pointer.
    if (VecTy && !IsWholeAlloca) {
      if (NumElements == 1)
        OtherPtrTy = VecTy->getElementType();
      else
        OtherPtrTy = VectorType::get(VecTy->getElementType(), NumElements);

      OtherPtrTy = OtherPtrTy->getPointerTo(OtherAS);
    } else if (IntTy && !IsWholeAlloca) {
      OtherPtrTy = SubIntTy->getPointerTo(OtherAS);
    } else {
      OtherPtrTy = NewAllocaTy->getPointerTo(OtherAS);
    }

    Value *SrcPtr = getAdjustedPtr(IRB, DL, OtherPtr, OtherOffset, OtherPtrTy,
                                   OtherPtr->getName() + ".");
    unsigned SrcAlign = OtherAlign;
    Value *DstPtr = &NewAI;
    unsigned DstAlign = SliceAlign;
    if (!IsDest) {
      std::swap(SrcPtr, DstPtr);
      std::swap(SrcAlign, DstAlign);
    }

    Value *Src;
    if (VecTy && !IsWholeAlloca && !IsDest) {
      Src = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "load");
      Src = extractVector(IRB, Src, BeginIndex, EndIndex, "vec");
    } else if (IntTy && !IsWholeAlloca && !IsDest) {
      Src = IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "load");
      Src = convertValue(DL, IRB, Src, IntTy);
      uint64_t Offset = NewBeginOffset - NewAllocaBeginOffset;
      Src = extractInteger(DL, IRB, Src, SubIntTy, Offset, "extract");
    } else {
      Src =
          IRB.CreateAlignedLoad(SrcPtr, SrcAlign, II.isVolatile(), "copyload");
    }

    if (VecTy && !IsWholeAlloca && IsDest) {
      Value *Old =
          IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "oldload");
      Src = insertVector(IRB, Old, Src, BeginIndex, "vec");
    } else if (IntTy && !IsWholeAlloca && IsDest) {
      Value *Old =
          IRB.CreateAlignedLoad(&NewAI, NewAI.getAlignment(), "oldload");
      Old = convertValue(DL, IRB, Old, IntTy);
      uint64_t Offset = NewBeginOffset - NewAllocaBeginOffset;
      Src = insertInteger(DL, IRB, Old, Src, Offset, "insert");
      Src = convertValue(DL, IRB, Src, NewAllocaTy);
    }

    StoreInst *Store = cast<StoreInst>(
        IRB.CreateAlignedStore(Src, DstPtr, DstAlign, II.isVolatile()));
    (void)Store;
    DEBUG(dbgs() << "          to: " << *Store << "\n");
    return !II.isVolatile();
  }

  bool visitIntrinsicInst(IntrinsicInst &II) {
    assert(II.getIntrinsicID() == Intrinsic::lifetime_start ||
           II.getIntrinsicID() == Intrinsic::lifetime_end);
    DEBUG(dbgs() << "    original: " << II << "\n");
    assert(II.getArgOperand(1) == OldPtr);

    // Record this instruction for deletion.
    Pass.DeadInsts.insert(&II);

    ConstantInt *Size =
        ConstantInt::get(cast<IntegerType>(II.getArgOperand(0)->getType()),
                         NewEndOffset - NewBeginOffset);
    Value *Ptr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
    Value *New;
    if (II.getIntrinsicID() == Intrinsic::lifetime_start)
      New = IRB.CreateLifetimeStart(Ptr, Size);
    else
      New = IRB.CreateLifetimeEnd(Ptr, Size);

    (void)New;
    DEBUG(dbgs() << "          to: " << *New << "\n");
    return true;
  }

  bool visitPHINode(PHINode &PN) {
    DEBUG(dbgs() << "    original: " << PN << "\n");
    assert(BeginOffset >= NewAllocaBeginOffset && "PHIs are unsplittable");
    assert(EndOffset <= NewAllocaEndOffset && "PHIs are unsplittable");

    // We would like to compute a new pointer in only one place, but have it be
    // as local as possible to the PHI. To do that, we re-use the location of
    // the old pointer, which necessarily must be in the right position to
    // dominate the PHI.
    IRBuilderTy PtrBuilder(IRB);
    if (isa<PHINode>(OldPtr))
      PtrBuilder.SetInsertPoint(OldPtr->getParent()->getFirstInsertionPt());
    else
      PtrBuilder.SetInsertPoint(OldPtr);
    PtrBuilder.SetCurrentDebugLocation(OldPtr->getDebugLoc());

    Value *NewPtr = getNewAllocaSlicePtr(PtrBuilder, OldPtr->getType());
    // Replace the operands which were using the old pointer.
    std::replace(PN.op_begin(), PN.op_end(), cast<Value>(OldPtr), NewPtr);

    DEBUG(dbgs() << "          to: " << PN << "\n");
    deleteIfTriviallyDead(OldPtr);

    // PHIs can't be promoted on their own, but often can be speculated. We
    // check the speculation outside of the rewriter so that we see the
    // fully-rewritten alloca.
    PHIUsers.insert(&PN);
    return true;
  }

  bool visitSelectInst(SelectInst &SI) {
    DEBUG(dbgs() << "    original: " << SI << "\n");
    assert((SI.getTrueValue() == OldPtr || SI.getFalseValue() == OldPtr) &&
           "Pointer isn't an operand!");
    assert(BeginOffset >= NewAllocaBeginOffset && "Selects are unsplittable");
    assert(EndOffset <= NewAllocaEndOffset && "Selects are unsplittable");

    Value *NewPtr = getNewAllocaSlicePtr(IRB, OldPtr->getType());
    // Replace the operands which were using the old pointer.
    if (SI.getOperand(1) == OldPtr)
      SI.setOperand(1, NewPtr);
    if (SI.getOperand(2) == OldPtr)
      SI.setOperand(2, NewPtr);

    DEBUG(dbgs() << "          to: " << SI << "\n");
    deleteIfTriviallyDead(OldPtr);

    // Selects can't be promoted on their own, but often can be speculated. We
    // check the speculation outside of the rewriter so that we see the
    // fully-rewritten alloca.
    SelectUsers.insert(&SI);
    return true;
  }
};
}

namespace {
/// \brief Visitor to rewrite aggregate loads and stores as scalar.
///
/// This pass aggressively rewrites all aggregate loads and stores on
/// a particular pointer (or any pointer derived from it which we can identify)
/// with scalar loads and stores.
class AggLoadStoreRewriter : public InstVisitor<AggLoadStoreRewriter, bool> {
  // Befriend the base class so it can delegate to private visit methods.
  friend class llvm::InstVisitor<AggLoadStoreRewriter, bool>;

  const DataLayout &DL;

  /// Queue of pointer uses to analyze and potentially rewrite.
  SmallVector<Use *, 8> Queue;

  /// Set to prevent us from cycling with phi nodes and loops.
  SmallPtrSet<User *, 8> Visited;

  /// The current pointer use being rewritten. This is used to dig up the used
  /// value (as opposed to the user).
  Use *U;

public:
  AggLoadStoreRewriter(const DataLayout &DL) : DL(DL) {}

  /// Rewrite loads and stores through a pointer and all pointers derived from
  /// it.
  bool rewrite(Instruction &I) {
    DEBUG(dbgs() << "  Rewriting FCA loads and stores...\n");
    enqueueUsers(I);
    bool Changed = false;
    while (!Queue.empty()) {
      U = Queue.pop_back_val();
      Changed |= visit(cast<Instruction>(U->getUser()));
    }
    return Changed;
  }

private:
  /// Enqueue all the users of the given instruction for further processing.
  /// This uses a set to de-duplicate users.
  void enqueueUsers(Instruction &I) {
    for (Use &U : I.uses())
      if (Visited.insert(U.getUser()).second)
        Queue.push_back(&U);
  }

  // Conservative default is to not rewrite anything.
  bool visitInstruction(Instruction &I) { return false; }

  /// \brief Generic recursive split emission class.
  template <typename Derived> class OpSplitter {
  protected:
    /// The builder used to form new instructions.
    IRBuilderTy IRB;
    /// The indices which to be used with insert- or extractvalue to select the
    /// appropriate value within the aggregate.
    SmallVector<unsigned, 4> Indices;
    /// The indices to a GEP instruction which will move Ptr to the correct slot
    /// within the aggregate.
    SmallVector<Value *, 4> GEPIndices;
    /// The base pointer of the original op, used as a base for GEPing the
    /// split operations.
    Value *Ptr;

    /// Initialize the splitter with an insertion point, Ptr and start with a
    /// single zero GEP index.
    OpSplitter(Instruction *InsertionPoint, Value *Ptr)
        : IRB(InsertionPoint), GEPIndices(1, IRB.getInt32(0)), Ptr(Ptr) {}

  public:
    /// \brief Generic recursive split emission routine.
    ///
    /// This method recursively splits an aggregate op (load or store) into
    /// scalar or vector ops. It splits recursively until it hits a single value
    /// and emits that single value operation via the template argument.
    ///
    /// The logic of this routine relies on GEPs and insertvalue and
    /// extractvalue all operating with the same fundamental index list, merely
    /// formatted differently (GEPs need actual values).
    ///
    /// \param Ty  The type being split recursively into smaller ops.
    /// \param Agg The aggregate value being built up or stored, depending on
    /// whether this is splitting a load or a store respectively.
    void emitSplitOps(Type *Ty, Value *&Agg, const Twine &Name) {
      if (Ty->isSingleValueType())
        return static_cast<Derived *>(this)->emitFunc(Ty, Agg, Name);

      if (ArrayType *ATy = dyn_cast<ArrayType>(Ty)) {
        unsigned OldSize = Indices.size();
        (void)OldSize;
        for (unsigned Idx = 0, Size = ATy->getNumElements(); Idx != Size;
             ++Idx) {
          assert(Indices.size() == OldSize && "Did not return to the old size");
          Indices.push_back(Idx);
          GEPIndices.push_back(IRB.getInt32(Idx));
          emitSplitOps(ATy->getElementType(), Agg, Name + "." + Twine(Idx));
          GEPIndices.pop_back();
          Indices.pop_back();
        }
        return;
      }

      if (StructType *STy = dyn_cast<StructType>(Ty)) {
        unsigned OldSize = Indices.size();
        (void)OldSize;
        for (unsigned Idx = 0, Size = STy->getNumElements(); Idx != Size;
             ++Idx) {
          assert(Indices.size() == OldSize && "Did not return to the old size");
          Indices.push_back(Idx);
          GEPIndices.push_back(IRB.getInt32(Idx));
          emitSplitOps(STy->getElementType(Idx), Agg, Name + "." + Twine(Idx));
          GEPIndices.pop_back();
          Indices.pop_back();
        }
        return;
      }

      llvm_unreachable("Only arrays and structs are aggregate loadable types");
    }
  };

  struct LoadOpSplitter : public OpSplitter<LoadOpSplitter> {
    LoadOpSplitter(Instruction *InsertionPoint, Value *Ptr)
        : OpSplitter<LoadOpSplitter>(InsertionPoint, Ptr) {}

    /// Emit a leaf load of a single value. This is called at the leaves of the
    /// recursive emission to actually load values.
    void emitFunc(Type *Ty, Value *&Agg, const Twine &Name) {
      assert(Ty->isSingleValueType());
      // Load the single value and insert it using the indices.
      Value *GEP = IRB.CreateInBoundsGEP(Ptr, GEPIndices, Name + ".gep");
      Value *Load = IRB.CreateLoad(GEP, Name + ".load");
      Agg = IRB.CreateInsertValue(Agg, Load, Indices, Name + ".insert");
      DEBUG(dbgs() << "          to: " << *Load << "\n");
    }
  };

  bool visitLoadInst(LoadInst &LI) {
    assert(LI.getPointerOperand() == *U);
    if (!LI.isSimple() || LI.getType()->isSingleValueType())
      return false;

    // We have an aggregate being loaded, split it apart.
    DEBUG(dbgs() << "    original: " << LI << "\n");
    LoadOpSplitter Splitter(&LI, *U);
    Value *V = UndefValue::get(LI.getType());
    Splitter.emitSplitOps(LI.getType(), V, LI.getName() + ".fca");
    LI.replaceAllUsesWith(V);
    LI.eraseFromParent();
    return true;
  }

  struct StoreOpSplitter : public OpSplitter<StoreOpSplitter> {
    StoreOpSplitter(Instruction *InsertionPoint, Value *Ptr)
        : OpSplitter<StoreOpSplitter>(InsertionPoint, Ptr) {}

    /// Emit a leaf store of a single value. This is called at the leaves of the
    /// recursive emission to actually produce stores.
    void emitFunc(Type *Ty, Value *&Agg, const Twine &Name) {
      assert(Ty->isSingleValueType());
      // Extract the single value and store it using the indices.
      Value *Store = IRB.CreateStore(
          IRB.CreateExtractValue(Agg, Indices, Name + ".extract"),
          IRB.CreateInBoundsGEP(Ptr, GEPIndices, Name + ".gep"));
      (void)Store;
      DEBUG(dbgs() << "          to: " << *Store << "\n");
    }
  };

  bool visitStoreInst(StoreInst &SI) {
    if (!SI.isSimple() || SI.getPointerOperand() != *U)
      return false;
    Value *V = SI.getValueOperand();
    if (V->getType()->isSingleValueType())
      return false;

    // We have an aggregate being stored, split it apart.
    DEBUG(dbgs() << "    original: " << SI << "\n");
    StoreOpSplitter Splitter(&SI, *U);
    Splitter.emitSplitOps(V->getType(), V, V->getName() + ".fca");
    SI.eraseFromParent();
    return true;
  }

  bool visitBitCastInst(BitCastInst &BC) {
    enqueueUsers(BC);
    return false;
  }

  bool visitGetElementPtrInst(GetElementPtrInst &GEPI) {
    enqueueUsers(GEPI);
    return false;
  }

  bool visitPHINode(PHINode &PN) {
    enqueueUsers(PN);
    return false;
  }

  bool visitSelectInst(SelectInst &SI) {
    enqueueUsers(SI);
    return false;
  }
};
}

/// \brief Strip aggregate type wrapping.
///
/// This removes no-op aggregate types wrapping an underlying type. It will
/// strip as many layers of types as it can without changing either the type
/// size or the allocated size.
static Type *stripAggregateTypeWrapping(const DataLayout &DL, Type *Ty) {
  if (Ty->isSingleValueType())
    return Ty;

  uint64_t AllocSize = DL.getTypeAllocSize(Ty);
  uint64_t TypeSize = DL.getTypeSizeInBits(Ty);

  Type *InnerTy;
  if (ArrayType *ArrTy = dyn_cast<ArrayType>(Ty)) {
    InnerTy = ArrTy->getElementType();
  } else if (StructType *STy = dyn_cast<StructType>(Ty)) {
    const StructLayout *SL = DL.getStructLayout(STy);
    unsigned Index = SL->getElementContainingOffset(0);
    InnerTy = STy->getElementType(Index);
  } else {
    return Ty;
  }

  if (AllocSize > DL.getTypeAllocSize(InnerTy) ||
      TypeSize > DL.getTypeSizeInBits(InnerTy))
    return Ty;

  return stripAggregateTypeWrapping(DL, InnerTy);
}

/// \brief Try to find a partition of the aggregate type passed in for a given
/// offset and size.
///
/// This recurses through the aggregate type and tries to compute a subtype
/// based on the offset and size. When the offset and size span a sub-section
/// of an array, it will even compute a new array type for that sub-section,
/// and the same for structs.
///
/// Note that this routine is very strict and tries to find a partition of the
/// type which produces the *exact* right offset and size. It is not forgiving
/// when the size or offset cause either end of type-based partition to be off.
/// Also, this is a best-effort routine. It is reasonable to give up and not
/// return a type if necessary.
static Type *getTypePartition(const DataLayout &DL, Type *Ty, uint64_t Offset,
                              uint64_t Size) {
  if (Offset == 0 && DL.getTypeAllocSize(Ty) == Size)
    return stripAggregateTypeWrapping(DL, Ty);
  if (Offset > DL.getTypeAllocSize(Ty) ||
      (DL.getTypeAllocSize(Ty) - Offset) < Size)
    return nullptr;

  if (SequentialType *SeqTy = dyn_cast<SequentialType>(Ty)) {
    // We can't partition pointers...
    if (SeqTy->isPointerTy())
      return nullptr;

    Type *ElementTy = SeqTy->getElementType();
    uint64_t ElementSize = DL.getTypeAllocSize(ElementTy);
    uint64_t NumSkippedElements = Offset / ElementSize;
    if (ArrayType *ArrTy = dyn_cast<ArrayType>(SeqTy)) {
      if (NumSkippedElements >= ArrTy->getNumElements())
        return nullptr;
    } else if (VectorType *VecTy = dyn_cast<VectorType>(SeqTy)) {
      if (NumSkippedElements >= VecTy->getNumElements())
        return nullptr;
    }
    Offset -= NumSkippedElements * ElementSize;

    // First check if we need to recurse.
    if (Offset > 0 || Size < ElementSize) {
      // Bail if the partition ends in a different array element.
      if ((Offset + Size) > ElementSize)
        return nullptr;
      // Recurse through the element type trying to peel off offset bytes.
      return getTypePartition(DL, ElementTy, Offset, Size);
    }
    assert(Offset == 0);

    if (Size == ElementSize)
      return stripAggregateTypeWrapping(DL, ElementTy);
    assert(Size > ElementSize);
    uint64_t NumElements = Size / ElementSize;
    if (NumElements * ElementSize != Size)
      return nullptr;
    return ArrayType::get(ElementTy, NumElements);
  }

  StructType *STy = dyn_cast<StructType>(Ty);
  if (!STy)
    return nullptr;

  const StructLayout *SL = DL.getStructLayout(STy);
  if (Offset >= SL->getSizeInBytes())
    return nullptr;
  uint64_t EndOffset = Offset + Size;
  if (EndOffset > SL->getSizeInBytes())
    return nullptr;

  unsigned Index = SL->getElementContainingOffset(Offset);
  Offset -= SL->getElementOffset(Index);

  Type *ElementTy = STy->getElementType(Index);
  uint64_t ElementSize = DL.getTypeAllocSize(ElementTy);
  if (Offset >= ElementSize)
    return nullptr; // The offset points into alignment padding.

  // See if any partition must be contained by the element.
  if (Offset > 0 || Size < ElementSize) {
    if ((Offset + Size) > ElementSize)
      return nullptr;
    return getTypePartition(DL, ElementTy, Offset, Size);
  }
  assert(Offset == 0);

  if (Size == ElementSize)
    return stripAggregateTypeWrapping(DL, ElementTy);

  StructType::element_iterator EI = STy->element_begin() + Index,
                               EE = STy->element_end();
  if (EndOffset < SL->getSizeInBytes()) {
    unsigned EndIndex = SL->getElementContainingOffset(EndOffset);
    if (Index == EndIndex)
      return nullptr; // Within a single element and its padding.

    // Don't try to form "natural" types if the elements don't line up with the
    // expected size.
    // FIXME: We could potentially recurse down through the last element in the
    // sub-struct to find a natural end point.
    if (SL->getElementOffset(EndIndex) != EndOffset)
      return nullptr;

    assert(Index < EndIndex);
    EE = STy->element_begin() + EndIndex;
  }

  // Try to build up a sub-structure.
  StructType *SubTy =
      StructType::get(STy->getContext(), makeArrayRef(EI, EE), STy->isPacked());
  const StructLayout *SubSL = DL.getStructLayout(SubTy);
  if (Size != SubSL->getSizeInBytes())
    return nullptr; // The sub-struct doesn't have quite the size needed.

  return SubTy;
}

/// \brief Pre-split loads and stores to simplify rewriting.
///
/// We want to break up the splittable load+store pairs as much as
/// possible. This is important to do as a preprocessing step, as once we
/// start rewriting the accesses to partitions of the alloca we lose the
/// necessary information to correctly split apart paired loads and stores
/// which both point into this alloca. The case to consider is something like
/// the following:
///
///   %a = alloca [12 x i8]
///   %gep1 = getelementptr [12 x i8]* %a, i32 0, i32 0
///   %gep2 = getelementptr [12 x i8]* %a, i32 0, i32 4
///   %gep3 = getelementptr [12 x i8]* %a, i32 0, i32 8
///   %iptr1 = bitcast i8* %gep1 to i64*
///   %iptr2 = bitcast i8* %gep2 to i64*
///   %fptr1 = bitcast i8* %gep1 to float*
///   %fptr2 = bitcast i8* %gep2 to float*
///   %fptr3 = bitcast i8* %gep3 to float*
///   store float 0.0, float* %fptr1
///   store float 1.0, float* %fptr2
///   %v = load i64* %iptr1
///   store i64 %v, i64* %iptr2
///   %f1 = load float* %fptr2
///   %f2 = load float* %fptr3
///
/// Here we want to form 3 partitions of the alloca, each 4 bytes large, and
/// promote everything so we recover the 2 SSA values that should have been
/// there all along.
///
/// \returns true if any changes are made.
bool SROA::presplitLoadsAndStores(AllocaInst &AI, AllocaSlices &AS) {
  DEBUG(dbgs() << "Pre-splitting loads and stores\n");

  // Track the loads and stores which are candidates for pre-splitting here, in
  // the order they first appear during the partition scan. These give stable
  // iteration order and a basis for tracking which loads and stores we
  // actually split.
  SmallVector<LoadInst *, 4> Loads;
  SmallVector<StoreInst *, 4> Stores;

  // We need to accumulate the splits required of each load or store where we
  // can find them via a direct lookup. This is important to cross-check loads
  // and stores against each other. We also track the slice so that we can kill
  // all the slices that end up split.
  struct SplitOffsets {
    Slice *S;
    std::vector<uint64_t> Splits;
  };
  SmallDenseMap<Instruction *, SplitOffsets, 8> SplitOffsetsMap;

  // Track loads out of this alloca which cannot, for any reason, be pre-split.
  // This is important as we also cannot pre-split stores of those loads!
  // FIXME: This is all pretty gross. It means that we can be more aggressive
  // in pre-splitting when the load feeding the store happens to come from
  // a separate alloca. Put another way, the effectiveness of SROA would be
  // decreased by a frontend which just concatenated all of its local allocas
  // into one big flat alloca. But defeating such patterns is exactly the job
  // SROA is tasked with! Sadly, to not have this discrepancy we would have
  // change store pre-splitting to actually force pre-splitting of the load
  // that feeds it *and all stores*. That makes pre-splitting much harder, but
  // maybe it would make it more principled?
  SmallPtrSet<LoadInst *, 8> UnsplittableLoads;

  DEBUG(dbgs() << "  Searching for candidate loads and stores\n");
  for (auto &P : AS.partitions()) {
    for (Slice &S : P) {
      Instruction *I = cast<Instruction>(S.getUse()->getUser());
      if (!S.isSplittable() ||S.endOffset() <= P.endOffset()) {
        // If this was a load we have to track that it can't participate in any
        // pre-splitting!
        if (auto *LI = dyn_cast<LoadInst>(I))
          UnsplittableLoads.insert(LI);
        continue;
      }
      assert(P.endOffset() > S.beginOffset() &&
             "Empty or backwards partition!");

      // Determine if this is a pre-splittable slice.
      if (auto *LI = dyn_cast<LoadInst>(I)) {
        assert(!LI->isVolatile() && "Cannot split volatile loads!");

        // The load must be used exclusively to store into other pointers for
        // us to be able to arbitrarily pre-split it. The stores must also be
        // simple to avoid changing semantics.
        auto IsLoadSimplyStored = [](LoadInst *LI) {
          for (User *LU : LI->users()) {
            auto *SI = dyn_cast<StoreInst>(LU);
            if (!SI || !SI->isSimple())
              return false;
          }
          return true;
        };
        if (!IsLoadSimplyStored(LI)) {
          UnsplittableLoads.insert(LI);
          continue;
        }

        Loads.push_back(LI);
      } else if (auto *SI = dyn_cast<StoreInst>(S.getUse()->getUser())) {
        if (!SI ||
            S.getUse() != &SI->getOperandUse(SI->getPointerOperandIndex()))
          continue;
        auto *StoredLoad = dyn_cast<LoadInst>(SI->getValueOperand());
        if (!StoredLoad || !StoredLoad->isSimple())
          continue;
        assert(!SI->isVolatile() && "Cannot split volatile stores!");

        Stores.push_back(SI);
      } else {
        // Other uses cannot be pre-split.
        continue;
      }

      // Record the initial split.
      DEBUG(dbgs() << "    Candidate: " << *I << "\n");
      auto &Offsets = SplitOffsetsMap[I];
      assert(Offsets.Splits.empty() &&
             "Should not have splits the first time we see an instruction!");
      Offsets.S = &S;
      Offsets.Splits.push_back(P.endOffset() - S.beginOffset());
    }

    // Now scan the already split slices, and add a split for any of them which
    // we're going to pre-split.
    for (Slice *S : P.splitSliceTails()) {
      auto SplitOffsetsMapI =
          SplitOffsetsMap.find(cast<Instruction>(S->getUse()->getUser()));
      if (SplitOffsetsMapI == SplitOffsetsMap.end())
        continue;
      auto &Offsets = SplitOffsetsMapI->second;

      assert(Offsets.S == S && "Found a mismatched slice!");
      assert(!Offsets.Splits.empty() &&
             "Cannot have an empty set of splits on the second partition!");
      assert(Offsets.Splits.back() ==
                 P.beginOffset() - Offsets.S->beginOffset() &&
             "Previous split does not end where this one begins!");

      // Record each split. The last partition's end isn't needed as the size
      // of the slice dictates that.
      if (S->endOffset() > P.endOffset())
        Offsets.Splits.push_back(P.endOffset() - Offsets.S->beginOffset());
    }
  }

  // We may have split loads where some of their stores are split stores. For
  // such loads and stores, we can only pre-split them if their splits exactly
  // match relative to their starting offset. We have to verify this prior to
  // any rewriting.
  Stores.erase(
      std::remove_if(Stores.begin(), Stores.end(),
                     [&UnsplittableLoads, &SplitOffsetsMap](StoreInst *SI) {
                       // Lookup the load we are storing in our map of split
                       // offsets.
                       auto *LI = cast<LoadInst>(SI->getValueOperand());
                       // If it was completely unsplittable, then we're done,
                       // and this store can't be pre-split.
                       if (UnsplittableLoads.count(LI))
                         return true;

                       auto LoadOffsetsI = SplitOffsetsMap.find(LI);
                       if (LoadOffsetsI == SplitOffsetsMap.end())
                         return false; // Unrelated loads are definitely safe.
                       auto &LoadOffsets = LoadOffsetsI->second;

                       // Now lookup the store's offsets.
                       auto &StoreOffsets = SplitOffsetsMap[SI];

                       // If the relative offsets of each split in the load and
                       // store match exactly, then we can split them and we
                       // don't need to remove them here.
                       if (LoadOffsets.Splits == StoreOffsets.Splits)
                         return false;

                       DEBUG(dbgs()
                             << "    Mismatched splits for load and store:\n"
                             << "      " << *LI << "\n"
                             << "      " << *SI << "\n");

                       // We've found a store and load that we need to split
                       // with mismatched relative splits. Just give up on them
                       // and remove both instructions from our list of
                       // candidates.
                       UnsplittableLoads.insert(LI);
                       return true;
                     }),
      Stores.end());
  // Now we have to go *back* through all te stores, because a later store may
  // have caused an earlier store's load to become unsplittable and if it is
  // unsplittable for the later store, then we can't rely on it being split in
  // the earlier store either.
  Stores.erase(std::remove_if(Stores.begin(), Stores.end(),
                              [&UnsplittableLoads](StoreInst *SI) {
                                auto *LI =
                                    cast<LoadInst>(SI->getValueOperand());
                                return UnsplittableLoads.count(LI);
                              }),
               Stores.end());
  // Once we've established all the loads that can't be split for some reason,
  // filter any that made it into our list out.
  Loads.erase(std::remove_if(Loads.begin(), Loads.end(),
                             [&UnsplittableLoads](LoadInst *LI) {
                               return UnsplittableLoads.count(LI);
                             }),
              Loads.end());


  // If no loads or stores are left, there is no pre-splitting to be done for
  // this alloca.
  if (Loads.empty() && Stores.empty())
    return false;

  // From here on, we can't fail and will be building new accesses, so rig up
  // an IR builder.
  IRBuilderTy IRB(&AI);

  // Collect the new slices which we will merge into the alloca slices.
  SmallVector<Slice, 4> NewSlices;

  // Track any allocas we end up splitting loads and stores for so we iterate
  // on them.
  SmallPtrSet<AllocaInst *, 4> ResplitPromotableAllocas;

  // At this point, we have collected all of the loads and stores we can
  // pre-split, and the specific splits needed for them. We actually do the
  // splitting in a specific order in order to handle when one of the loads in
  // the value operand to one of the stores.
  //
  // First, we rewrite all of the split loads, and just accumulate each split
  // load in a parallel structure. We also build the slices for them and append
  // them to the alloca slices.
  SmallDenseMap<LoadInst *, std::vector<LoadInst *>, 1> SplitLoadsMap;
  std::vector<LoadInst *> SplitLoads;
  for (LoadInst *LI : Loads) {
    SplitLoads.clear();

    IntegerType *Ty = cast<IntegerType>(LI->getType());
    uint64_t LoadSize = Ty->getBitWidth() / 8;
    assert(LoadSize > 0 && "Cannot have a zero-sized integer load!");

    auto &Offsets = SplitOffsetsMap[LI];
    assert(LoadSize == Offsets.S->endOffset() - Offsets.S->beginOffset() &&
           "Slice size should always match load size exactly!");
    uint64_t BaseOffset = Offsets.S->beginOffset();
    assert(BaseOffset + LoadSize > BaseOffset &&
           "Cannot represent alloca access size using 64-bit integers!");

    Instruction *BasePtr = cast<Instruction>(LI->getPointerOperand());
    IRB.SetInsertPoint(BasicBlock::iterator(LI));

    DEBUG(dbgs() << "  Splitting load: " << *LI << "\n");

    uint64_t PartOffset = 0, PartSize = Offsets.Splits.front();
    int Idx = 0, Size = Offsets.Splits.size();
    for (;;) {
      auto *PartTy = Type::getIntNTy(Ty->getContext(), PartSize * 8);
      auto *PartPtrTy = PartTy->getPointerTo(LI->getPointerAddressSpace());
      LoadInst *PLoad = IRB.CreateAlignedLoad(
          getAdjustedPtr(IRB, *DL, BasePtr,
                         APInt(DL->getPointerSizeInBits(), PartOffset),
                         PartPtrTy, BasePtr->getName() + "."),
          getAdjustedAlignment(LI, PartOffset, *DL), /*IsVolatile*/ false,
          LI->getName());

      // Append this load onto the list of split loads so we can find it later
      // to rewrite the stores.
      SplitLoads.push_back(PLoad);

      // Now build a new slice for the alloca.
      NewSlices.push_back(
          Slice(BaseOffset + PartOffset, BaseOffset + PartOffset + PartSize,
                &PLoad->getOperandUse(PLoad->getPointerOperandIndex()),
                /*IsSplittable*/ false));
      DEBUG(dbgs() << "    new slice [" << NewSlices.back().beginOffset()
                   << ", " << NewSlices.back().endOffset() << "): " << *PLoad
                   << "\n");

      // See if we've handled all the splits.
      if (Idx >= Size)
        break;

      // Setup the next partition.
      PartOffset = Offsets.Splits[Idx];
      ++Idx;
      PartSize = (Idx < Size ? Offsets.Splits[Idx] : LoadSize) - PartOffset;
    }

    // Now that we have the split loads, do the slow walk over all uses of the
    // load and rewrite them as split stores, or save the split loads to use
    // below if the store is going to be split there anyways.
    bool DeferredStores = false;
    for (User *LU : LI->users()) {
      StoreInst *SI = cast<StoreInst>(LU);
      if (!Stores.empty() && SplitOffsetsMap.count(SI)) {
        DeferredStores = true;
        DEBUG(dbgs() << "    Deferred splitting of store: " << *SI << "\n");
        continue;
      }

      Value *StoreBasePtr = SI->getPointerOperand();
      IRB.SetInsertPoint(BasicBlock::iterator(SI));

      DEBUG(dbgs() << "    Splitting store of load: " << *SI << "\n");

      for (int Idx = 0, Size = SplitLoads.size(); Idx < Size; ++Idx) {
        LoadInst *PLoad = SplitLoads[Idx];
        uint64_t PartOffset = Idx == 0 ? 0 : Offsets.Splits[Idx - 1];
        auto *PartPtrTy =
            PLoad->getType()->getPointerTo(SI->getPointerAddressSpace());

        StoreInst *PStore = IRB.CreateAlignedStore(
            PLoad, getAdjustedPtr(IRB, *DL, StoreBasePtr,
                                  APInt(DL->getPointerSizeInBits(), PartOffset),
                                  PartPtrTy, StoreBasePtr->getName() + "."),
            getAdjustedAlignment(SI, PartOffset, *DL), /*IsVolatile*/ false);
        (void)PStore;
        DEBUG(dbgs() << "      +" << PartOffset << ":" << *PStore << "\n");
      }

      // We want to immediately iterate on any allocas impacted by splitting
      // this store, and we have to track any promotable alloca (indicated by
      // a direct store) as needing to be resplit because it is no longer
      // promotable.
      if (AllocaInst *OtherAI = dyn_cast<AllocaInst>(StoreBasePtr)) {
        ResplitPromotableAllocas.insert(OtherAI);
        Worklist.insert(OtherAI);
      } else if (AllocaInst *OtherAI = dyn_cast<AllocaInst>(
                     StoreBasePtr->stripInBoundsOffsets())) {
        Worklist.insert(OtherAI);
      }

      // Mark the original store as dead.
      DeadInsts.insert(SI);
    }

    // Save the split loads if there are deferred stores among the users.
    if (DeferredStores)
      SplitLoadsMap.insert(std::make_pair(LI, std::move(SplitLoads)));

    // Mark the original load as dead and kill the original slice.
    DeadInsts.insert(LI);
    Offsets.S->kill();
  }

  // Second, we rewrite all of the split stores. At this point, we know that
  // all loads from this alloca have been split already. For stores of such
  // loads, we can simply look up the pre-existing split loads. For stores of
  // other loads, we split those loads first and then write split stores of
  // them.
  for (StoreInst *SI : Stores) {
    auto *LI = cast<LoadInst>(SI->getValueOperand());
    IntegerType *Ty = cast<IntegerType>(LI->getType());
    uint64_t StoreSize = Ty->getBitWidth() / 8;
    assert(StoreSize > 0 && "Cannot have a zero-sized integer store!");

    auto &Offsets = SplitOffsetsMap[SI];
    assert(StoreSize == Offsets.S->endOffset() - Offsets.S->beginOffset() &&
           "Slice size should always match load size exactly!");
    uint64_t BaseOffset = Offsets.S->beginOffset();
    assert(BaseOffset + StoreSize > BaseOffset &&
           "Cannot represent alloca access size using 64-bit integers!");

    Value *LoadBasePtr = LI->getPointerOperand();
    Instruction *StoreBasePtr = cast<Instruction>(SI->getPointerOperand());

    DEBUG(dbgs() << "  Splitting store: " << *SI << "\n");

    // Check whether we have an already split load.
    auto SplitLoadsMapI = SplitLoadsMap.find(LI);
    std::vector<LoadInst *> *SplitLoads = nullptr;
    if (SplitLoadsMapI != SplitLoadsMap.end()) {
      SplitLoads = &SplitLoadsMapI->second;
      assert(SplitLoads->size() == Offsets.Splits.size() + 1 &&
             "Too few split loads for the number of splits in the store!");
    } else {
      DEBUG(dbgs() << "          of load: " << *LI << "\n");
    }

    uint64_t PartOffset = 0, PartSize = Offsets.Splits.front();
    int Idx = 0, Size = Offsets.Splits.size();
    for (;;) {
      auto *PartTy = Type::getIntNTy(Ty->getContext(), PartSize * 8);
      auto *PartPtrTy = PartTy->getPointerTo(SI->getPointerAddressSpace());

      // Either lookup a split load or create one.
      LoadInst *PLoad;
      if (SplitLoads) {
        PLoad = (*SplitLoads)[Idx];
      } else {
        IRB.SetInsertPoint(BasicBlock::iterator(LI));
        PLoad = IRB.CreateAlignedLoad(
            getAdjustedPtr(IRB, *DL, LoadBasePtr,
                           APInt(DL->getPointerSizeInBits(), PartOffset),
                           PartPtrTy, LoadBasePtr->getName() + "."),
            getAdjustedAlignment(LI, PartOffset, *DL), /*IsVolatile*/ false,
            LI->getName());
      }

      // And store this partition.
      IRB.SetInsertPoint(BasicBlock::iterator(SI));
      StoreInst *PStore = IRB.CreateAlignedStore(
          PLoad, getAdjustedPtr(IRB, *DL, StoreBasePtr,
                                APInt(DL->getPointerSizeInBits(), PartOffset),
                                PartPtrTy, StoreBasePtr->getName() + "."),
          getAdjustedAlignment(SI, PartOffset, *DL), /*IsVolatile*/ false);

      // Now build a new slice for the alloca.
      NewSlices.push_back(
          Slice(BaseOffset + PartOffset, BaseOffset + PartOffset + PartSize,
                &PStore->getOperandUse(PStore->getPointerOperandIndex()),
                /*IsSplittable*/ false));
      DEBUG(dbgs() << "    new slice [" << NewSlices.back().beginOffset()
                   << ", " << NewSlices.back().endOffset() << "): " << *PStore
                   << "\n");
      if (!SplitLoads) {
        DEBUG(dbgs() << "      of split load: " << *PLoad << "\n");
      }

      // See if we've finished all the splits.
      if (Idx >= Size)
        break;

      // Setup the next partition.
      PartOffset = Offsets.Splits[Idx];
      ++Idx;
      PartSize = (Idx < Size ? Offsets.Splits[Idx] : StoreSize) - PartOffset;
    }

    // We want to immediately iterate on any allocas impacted by splitting
    // this load, which is only relevant if it isn't a load of this alloca and
    // thus we didn't already split the loads above. We also have to keep track
    // of any promotable allocas we split loads on as they can no longer be
    // promoted.
    if (!SplitLoads) {
      if (AllocaInst *OtherAI = dyn_cast<AllocaInst>(LoadBasePtr)) {
        assert(OtherAI != &AI && "We can't re-split our own alloca!");
        ResplitPromotableAllocas.insert(OtherAI);
        Worklist.insert(OtherAI);
      } else if (AllocaInst *OtherAI = dyn_cast<AllocaInst>(
                     LoadBasePtr->stripInBoundsOffsets())) {
        assert(OtherAI != &AI && "We can't re-split our own alloca!");
        Worklist.insert(OtherAI);
      }
    }

    // Mark the original store as dead now that we've split it up and kill its
    // slice. Note that we leave the original load in place unless this store
    // was its ownly use. It may in turn be split up if it is an alloca load
    // for some other alloca, but it may be a normal load. This may introduce
    // redundant loads, but where those can be merged the rest of the optimizer
    // should handle the merging, and this uncovers SSA splits which is more
    // important. In practice, the original loads will almost always be fully
    // split and removed eventually, and the splits will be merged by any
    // trivial CSE, including instcombine.
    if (LI->hasOneUse()) {
      assert(*LI->user_begin() == SI && "Single use isn't this store!");
      DeadInsts.insert(LI);
    }
    DeadInsts.insert(SI);
    Offsets.S->kill();
  }

  // Remove the killed slices that have ben pre-split.
  AS.erase(std::remove_if(AS.begin(), AS.end(), [](const Slice &S) {
    return S.isDead();
  }), AS.end());

  // Insert our new slices. This will sort and merge them into the sorted
  // sequence.
  AS.insert(NewSlices);

  DEBUG(dbgs() << "  Pre-split slices:\n");
#ifndef NDEBUG
  for (auto I = AS.begin(), E = AS.end(); I != E; ++I)
    DEBUG(AS.print(dbgs(), I, "    "));
#endif

  // Finally, don't try to promote any allocas that new require re-splitting.
  // They have already been added to the worklist above.
  PromotableAllocas.erase(
      std::remove_if(
          PromotableAllocas.begin(), PromotableAllocas.end(),
          [&](AllocaInst *AI) { return ResplitPromotableAllocas.count(AI); }),
      PromotableAllocas.end());

  return true;
}

/// \brief Rewrite an alloca partition's users.
///
/// This routine drives both of the rewriting goals of the SROA pass. It tries
/// to rewrite uses of an alloca partition to be conducive for SSA value
/// promotion. If the partition needs a new, more refined alloca, this will
/// build that new alloca, preserving as much type information as possible, and
/// rewrite the uses of the old alloca to point at the new one and have the
/// appropriate new offsets. It also evaluates how successful the rewrite was
/// at enabling promotion and if it was successful queues the alloca to be
/// promoted.
AllocaInst *SROA::rewritePartition(AllocaInst &AI, AllocaSlices &AS,
                                   AllocaSlices::Partition &P) {
  // Try to compute a friendly type for this partition of the alloca. This
  // won't always succeed, in which case we fall back to a legal integer type
  // or an i8 array of an appropriate size.
  Type *SliceTy = nullptr;
  if (Type *CommonUseTy = findCommonType(P.begin(), P.end(), P.endOffset()))
    if (DL->getTypeAllocSize(CommonUseTy) >= P.size())
      SliceTy = CommonUseTy;
  if (!SliceTy)
    if (Type *TypePartitionTy = getTypePartition(*DL, AI.getAllocatedType(),
                                                 P.beginOffset(), P.size()))
      SliceTy = TypePartitionTy;
  if ((!SliceTy || (SliceTy->isArrayTy() &&
                    SliceTy->getArrayElementType()->isIntegerTy())) &&
      DL->isLegalInteger(P.size() * 8))
    SliceTy = Type::getIntNTy(*C, P.size() * 8);
  if (!SliceTy)
    SliceTy = ArrayType::get(Type::getInt8Ty(*C), P.size());
  assert(DL->getTypeAllocSize(SliceTy) >= P.size());

  bool IsIntegerPromotable = isIntegerWideningViable(P, SliceTy, *DL);

  VectorType *VecTy =
      IsIntegerPromotable ? nullptr : isVectorPromotionViable(P, *DL);
  if (VecTy)
    SliceTy = VecTy;

  // Check for the case where we're going to rewrite to a new alloca of the
  // exact same type as the original, and with the same access offsets. In that
  // case, re-use the existing alloca, but still run through the rewriter to
  // perform phi and select speculation.
  AllocaInst *NewAI;
  if (SliceTy == AI.getAllocatedType()) {
    assert(P.beginOffset() == 0 &&
           "Non-zero begin offset but same alloca type");
    NewAI = &AI;
    // FIXME: We should be able to bail at this point with "nothing changed".
    // FIXME: We might want to defer PHI speculation until after here.
    // FIXME: return nullptr;
  } else {
    unsigned Alignment = AI.getAlignment();
    if (!Alignment) {
      // The minimum alignment which users can rely on when the explicit
      // alignment is omitted or zero is that required by the ABI for this
      // type.
      Alignment = DL->getABITypeAlignment(AI.getAllocatedType());
    }
    Alignment = MinAlign(Alignment, P.beginOffset());
    // If we will get at least this much alignment from the type alone, leave
    // the alloca's alignment unconstrained.
    if (Alignment <= DL->getABITypeAlignment(SliceTy))
      Alignment = 0;
    NewAI = new AllocaInst(
        SliceTy, nullptr, Alignment,
        AI.getName() + ".sroa." + Twine(P.begin() - AS.begin()), &AI);
    ++NumNewAllocas;
  }

  DEBUG(dbgs() << "Rewriting alloca partition "
               << "[" << P.beginOffset() << "," << P.endOffset()
               << ") to: " << *NewAI << "\n");

  // Track the high watermark on the worklist as it is only relevant for
  // promoted allocas. We will reset it to this point if the alloca is not in
  // fact scheduled for promotion.
  unsigned PPWOldSize = PostPromotionWorklist.size();
  unsigned NumUses = 0;
  SmallPtrSet<PHINode *, 8> PHIUsers;
  SmallPtrSet<SelectInst *, 8> SelectUsers;

  AllocaSliceRewriter Rewriter(*DL, AS, *this, AI, *NewAI, P.beginOffset(),
                               P.endOffset(), IsIntegerPromotable, VecTy,
                               PHIUsers, SelectUsers);
  bool Promotable = true;
  for (Slice *S : P.splitSliceTails()) {
    Promotable &= Rewriter.visit(S);
    ++NumUses;
  }
  for (Slice &S : P) {
    Promotable &= Rewriter.visit(&S);
    ++NumUses;
  }

  NumAllocaPartitionUses += NumUses;
  MaxUsesPerAllocaPartition =
      std::max<unsigned>(NumUses, MaxUsesPerAllocaPartition);

  // Now that we've processed all the slices in the new partition, check if any
  // PHIs or Selects would block promotion.
  for (SmallPtrSetImpl<PHINode *>::iterator I = PHIUsers.begin(),
                                            E = PHIUsers.end();
       I != E; ++I)
    if (!isSafePHIToSpeculate(**I, DL)) {
      Promotable = false;
      PHIUsers.clear();
      SelectUsers.clear();
      break;
    }
  for (SmallPtrSetImpl<SelectInst *>::iterator I = SelectUsers.begin(),
                                               E = SelectUsers.end();
       I != E; ++I)
    if (!isSafeSelectToSpeculate(**I, DL)) {
      Promotable = false;
      PHIUsers.clear();
      SelectUsers.clear();
      break;
    }

  if (Promotable) {
    if (PHIUsers.empty() && SelectUsers.empty()) {
      // Promote the alloca.
      PromotableAllocas.push_back(NewAI);
    } else {
      // If we have either PHIs or Selects to speculate, add them to those
      // worklists and re-queue the new alloca so that we promote in on the
      // next iteration.
      for (PHINode *PHIUser : PHIUsers)
        SpeculatablePHIs.insert(PHIUser);
      for (SelectInst *SelectUser : SelectUsers)
        SpeculatableSelects.insert(SelectUser);
      Worklist.insert(NewAI);
    }
  } else {
    // If we can't promote the alloca, iterate on it to check for new
    // refinements exposed by splitting the current alloca. Don't iterate on an
    // alloca which didn't actually change and didn't get promoted.
    if (NewAI != &AI)
      Worklist.insert(NewAI);

    // Drop any post-promotion work items if promotion didn't happen.
    while (PostPromotionWorklist.size() > PPWOldSize)
      PostPromotionWorklist.pop_back();
  }

  return NewAI;
}

/// \brief Walks the slices of an alloca and form partitions based on them,
/// rewriting each of their uses.
bool SROA::splitAlloca(AllocaInst &AI, AllocaSlices &AS) {
  if (AS.begin() == AS.end())
    return false;

  unsigned NumPartitions = 0;
  bool Changed = false;

  // First try to pre-split loads and stores.
  Changed |= presplitLoadsAndStores(AI, AS);

  // Now that we have identified any pre-splitting opportunities, mark any
  // splittable (non-whole-alloca) loads and stores as unsplittable. If we fail
  // to split these during pre-splitting, we want to force them to be
  // rewritten into a partition.
  bool IsSorted = true;
  for (Slice &S : AS) {
    if (!S.isSplittable())
      continue;
    // FIXME: We currently leave whole-alloca splittable loads and stores. This
    // used to be the only splittable loads and stores and we need to be
    // confident that the above handling of splittable loads and stores is
    // completely sufficient before we forcibly disable the remaining handling.
    if (S.beginOffset() == 0 &&
        S.endOffset() >= DL->getTypeAllocSize(AI.getAllocatedType()))
      continue;
    if (isa<LoadInst>(S.getUse()->getUser()) ||
        isa<StoreInst>(S.getUse()->getUser())) {
      S.makeUnsplittable();
      IsSorted = false;
    }
  }
  if (!IsSorted)
    std::sort(AS.begin(), AS.end());

  /// \brief Describes the allocas introduced by rewritePartition
  /// in order to migrate the debug info.
  struct Piece {
    AllocaInst *Alloca;
    uint64_t Offset;
    uint64_t Size;
    Piece(AllocaInst *AI, uint64_t O, uint64_t S)
      : Alloca(AI), Offset(O), Size(S) {}
  };
  SmallVector<Piece, 4> Pieces;

  // Rewrite each partition.
  for (auto &P : AS.partitions()) {
    if (AllocaInst *NewAI = rewritePartition(AI, AS, P)) {
      Changed = true;
      if (NewAI != &AI) {
        uint64_t SizeOfByte = 8;
        uint64_t AllocaSize = DL->getTypeSizeInBits(NewAI->getAllocatedType());
        // Don't include any padding.
        uint64_t Size = std::min(AllocaSize, P.size() * SizeOfByte);
        Pieces.push_back(Piece(NewAI, P.beginOffset() * SizeOfByte, Size));
      }
    }
    ++NumPartitions;
  }

  NumAllocaPartitions += NumPartitions;
  MaxPartitionsPerAlloca =
      std::max<unsigned>(NumPartitions, MaxPartitionsPerAlloca);

  // Migrate debug information from the old alloca to the new alloca(s)
  // and the individial partitions.
  if (DbgDeclareInst *DbgDecl = FindAllocaDbgDeclare(&AI)) {
    DIVariable Var(DbgDecl->getVariable());
    DIExpression Expr(DbgDecl->getExpression());
    DIBuilder DIB(*AI.getParent()->getParent()->getParent(),
                  /*AllowUnresolved*/ false);
    bool IsSplit = Pieces.size() > 1;
    for (auto Piece : Pieces) {
      // Create a piece expression describing the new partition or reuse AI's
      // expression if there is only one partition.
      DIExpression PieceExpr = Expr;
      if (IsSplit || Expr.isBitPiece()) {
        // If this alloca is already a scalar replacement of a larger aggregate,
        // Piece.Offset describes the offset inside the scalar.
        uint64_t Offset = Expr.isBitPiece() ? Expr.getBitPieceOffset() : 0;
        uint64_t Start = Offset + Piece.Offset;
        uint64_t Size = Piece.Size;
        if (Expr.isBitPiece()) {
          uint64_t AbsEnd = Expr.getBitPieceOffset() + Expr.getBitPieceSize();
          if (Start >= AbsEnd)
            // No need to describe a SROAed padding.
            continue;
          Size = std::min(Size, AbsEnd - Start);
        }
        PieceExpr = DIB.createBitPieceExpression(Start, Size);
      }

      // Remove any existing dbg.declare intrinsic describing the same alloca.
      if (DbgDeclareInst *OldDDI = FindAllocaDbgDeclare(Piece.Alloca))
        OldDDI->eraseFromParent();

      auto *NewDDI = DIB.insertDeclare(Piece.Alloca, Var, PieceExpr, &AI);
      NewDDI->setDebugLoc(DbgDecl->getDebugLoc());
    }
  }
  return Changed;
}

/// \brief Clobber a use with undef, deleting the used value if it becomes dead.
void SROA::clobberUse(Use &U) {
  Value *OldV = U;
  // Replace the use with an undef value.
  U = UndefValue::get(OldV->getType());

  // Check for this making an instruction dead. We have to garbage collect
  // all the dead instructions to ensure the uses of any alloca end up being
  // minimal.
  if (Instruction *OldI = dyn_cast<Instruction>(OldV))
    if (isInstructionTriviallyDead(OldI)) {
      DeadInsts.insert(OldI);
    }
}

/// \brief Analyze an alloca for SROA.
///
/// This analyzes the alloca to ensure we can reason about it, builds
/// the slices of the alloca, and then hands it off to be split and
/// rewritten as needed.
bool SROA::runOnAlloca(AllocaInst &AI) {
  DEBUG(dbgs() << "SROA alloca: " << AI << "\n");
  ++NumAllocasAnalyzed;

  // Special case dead allocas, as they're trivial.
  if (AI.use_empty()) {
    AI.eraseFromParent();
    return true;
  }

  // Skip alloca forms that this analysis can't handle.
  if (AI.isArrayAllocation() || !AI.getAllocatedType()->isSized() ||
      DL->getTypeAllocSize(AI.getAllocatedType()) == 0)
    return false;

  bool Changed = false;

  // First, split any FCA loads and stores touching this alloca to promote
  // better splitting and promotion opportunities.
  AggLoadStoreRewriter AggRewriter(*DL);
  Changed |= AggRewriter.rewrite(AI);

  // Build the slices using a recursive instruction-visiting builder.
  AllocaSlices AS(*DL, AI);
  DEBUG(AS.print(dbgs()));
  if (AS.isEscaped())
    return Changed;

  // Delete all the dead users of this alloca before splitting and rewriting it.
  for (Instruction *DeadUser : AS.getDeadUsers()) {
    // Free up everything used by this instruction.
    for (Use &DeadOp : DeadUser->operands())
      clobberUse(DeadOp);

    // Now replace the uses of this instruction.
    DeadUser->replaceAllUsesWith(UndefValue::get(DeadUser->getType()));

    // And mark it for deletion.
    DeadInsts.insert(DeadUser);
    Changed = true;
  }
  for (Use *DeadOp : AS.getDeadOperands()) {
    clobberUse(*DeadOp);
    Changed = true;
  }

  // No slices to split. Leave the dead alloca for a later pass to clean up.
  if (AS.begin() == AS.end())
    return Changed;

  Changed |= splitAlloca(AI, AS);

  DEBUG(dbgs() << "  Speculating PHIs\n");
  while (!SpeculatablePHIs.empty())
    speculatePHINodeLoads(*SpeculatablePHIs.pop_back_val());

  DEBUG(dbgs() << "  Speculating Selects\n");
  while (!SpeculatableSelects.empty())
    speculateSelectInstLoads(*SpeculatableSelects.pop_back_val());

  return Changed;
}

/// \brief Delete the dead instructions accumulated in this run.
///
/// Recursively deletes the dead instructions we've accumulated. This is done
/// at the very end to maximize locality of the recursive delete and to
/// minimize the problems of invalidated instruction pointers as such pointers
/// are used heavily in the intermediate stages of the algorithm.
///
/// We also record the alloca instructions deleted here so that they aren't
/// subsequently handed to mem2reg to promote.
void SROA::deleteDeadInstructions(
    SmallPtrSetImpl<AllocaInst *> &DeletedAllocas) {
  while (!DeadInsts.empty()) {
    Instruction *I = DeadInsts.pop_back_val();
    DEBUG(dbgs() << "Deleting dead instruction: " << *I << "\n");

    I->replaceAllUsesWith(UndefValue::get(I->getType()));

    for (Use &Operand : I->operands())
      if (Instruction *U = dyn_cast<Instruction>(Operand)) {
        // Zero out the operand and see if it becomes trivially dead.
        Operand = nullptr;
        if (isInstructionTriviallyDead(U))
          DeadInsts.insert(U);
      }

    if (AllocaInst *AI = dyn_cast<AllocaInst>(I)) {
      DeletedAllocas.insert(AI);
      if (DbgDeclareInst *DbgDecl = FindAllocaDbgDeclare(AI))
        DbgDecl->eraseFromParent();
    }

    ++NumDeleted;
    I->eraseFromParent();
  }
}

static void enqueueUsersInWorklist(Instruction &I,
                                   SmallVectorImpl<Instruction *> &Worklist,
                                   SmallPtrSetImpl<Instruction *> &Visited) {
  for (User *U : I.users())
    if (Visited.insert(cast<Instruction>(U)).second)
      Worklist.push_back(cast<Instruction>(U));
}

/// \brief Promote the allocas, using the best available technique.
///
/// This attempts to promote whatever allocas have been identified as viable in
/// the PromotableAllocas list. If that list is empty, there is nothing to do.
/// If there is a domtree available, we attempt to promote using the full power
/// of mem2reg. Otherwise, we build and use the AllocaPromoter above which is
/// based on the SSAUpdater utilities. This function returns whether any
/// promotion occurred.
bool SROA::promoteAllocas(Function &F) {
  if (PromotableAllocas.empty())
    return false;

  NumPromoted += PromotableAllocas.size();

  if (DT && !ForceSSAUpdater) {
    DEBUG(dbgs() << "Promoting allocas with mem2reg...\n");
    PromoteMemToReg(PromotableAllocas, *DT, nullptr, AC);
    PromotableAllocas.clear();
    return true;
  }

  DEBUG(dbgs() << "Promoting allocas with SSAUpdater...\n");
  SSAUpdater SSA;
  DIBuilder DIB(*F.getParent(), /*AllowUnresolved*/ false);
  SmallVector<Instruction *, 64> Insts;

  // We need a worklist to walk the uses of each alloca.
  SmallVector<Instruction *, 8> Worklist;
  SmallPtrSet<Instruction *, 8> Visited;
  SmallVector<Instruction *, 32> DeadInsts;

  for (unsigned Idx = 0, Size = PromotableAllocas.size(); Idx != Size; ++Idx) {
    AllocaInst *AI = PromotableAllocas[Idx];
    Insts.clear();
    Worklist.clear();
    Visited.clear();

    enqueueUsersInWorklist(*AI, Worklist, Visited);

    while (!Worklist.empty()) {
      Instruction *I = Worklist.pop_back_val();

      // FIXME: Currently the SSAUpdater infrastructure doesn't reason about
      // lifetime intrinsics and so we strip them (and the bitcasts+GEPs
      // leading to them) here. Eventually it should use them to optimize the
      // scalar values produced.
      if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
        assert(II->getIntrinsicID() == Intrinsic::lifetime_start ||
               II->getIntrinsicID() == Intrinsic::lifetime_end);
        II->eraseFromParent();
        continue;
      }

      // Push the loads and stores we find onto the list. SROA will already
      // have validated that all loads and stores are viable candidates for
      // promotion.
      if (LoadInst *LI = dyn_cast<LoadInst>(I)) {
        assert(LI->getType() == AI->getAllocatedType());
        Insts.push_back(LI);
        continue;
      }
      if (StoreInst *SI = dyn_cast<StoreInst>(I)) {
        assert(SI->getValueOperand()->getType() == AI->getAllocatedType());
        Insts.push_back(SI);
        continue;
      }

      // For everything else, we know that only no-op bitcasts and GEPs will
      // make it this far, just recurse through them and recall them for later
      // removal.
      DeadInsts.push_back(I);
      enqueueUsersInWorklist(*I, Worklist, Visited);
    }
    AllocaPromoter(Insts, SSA, *AI, DIB).run(Insts);
    while (!DeadInsts.empty())
      DeadInsts.pop_back_val()->eraseFromParent();
    AI->eraseFromParent();
  }

  PromotableAllocas.clear();
  return true;
}

bool SROA::runOnFunction(Function &F) {
  if (skipOptnoneFunction(F))
    return false;

  DEBUG(dbgs() << "SROA function: " << F.getName() << "\n");
  C = &F.getContext();
  DataLayoutPass *DLP = getAnalysisIfAvailable<DataLayoutPass>();
  if (!DLP) {
    DEBUG(dbgs() << "  Skipping SROA -- no target data!\n");
    return false;
  }
  DL = &DLP->getDataLayout();
  DominatorTreeWrapperPass *DTWP =
      getAnalysisIfAvailable<DominatorTreeWrapperPass>();
  DT = DTWP ? &DTWP->getDomTree() : nullptr;
  AC = &getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);

  BasicBlock &EntryBB = F.getEntryBlock();
  for (BasicBlock::iterator I = EntryBB.begin(), E = std::prev(EntryBB.end());
       I != E; ++I) {
    if (AllocaInst *AI = dyn_cast<AllocaInst>(I))
      Worklist.insert(AI);
  }

  bool Changed = false;
  // A set of deleted alloca instruction pointers which should be removed from
  // the list of promotable allocas.
  SmallPtrSet<AllocaInst *, 4> DeletedAllocas;

  do {
    while (!Worklist.empty()) {
      Changed |= runOnAlloca(*Worklist.pop_back_val());
      deleteDeadInstructions(DeletedAllocas);

      // Remove the deleted allocas from various lists so that we don't try to
      // continue processing them.
      if (!DeletedAllocas.empty()) {
        auto IsInSet = [&](AllocaInst *AI) { return DeletedAllocas.count(AI); };
        Worklist.remove_if(IsInSet);
        PostPromotionWorklist.remove_if(IsInSet);
        PromotableAllocas.erase(std::remove_if(PromotableAllocas.begin(),
                                               PromotableAllocas.end(),
                                               IsInSet),
                                PromotableAllocas.end());
        DeletedAllocas.clear();
      }
    }

    Changed |= promoteAllocas(F);

    Worklist = PostPromotionWorklist;
    PostPromotionWorklist.clear();
  } while (!Worklist.empty());

  return Changed;
}

void SROA::getAnalysisUsage(AnalysisUsage &AU) const {
  AU.addRequired<AssumptionCacheTracker>();
  if (RequiresDomTree)
    AU.addRequired<DominatorTreeWrapperPass>();
  AU.setPreservesCFG();
}