aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp
blob: a27da047bfd39cd4745b8084abe53851155b4d9a (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
///===- SimpleLoopUnswitch.cpp - Hoist loop-invariant control flow ---------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/SimpleLoopUnswitch.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Sequence.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CFG.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/GuardUtils.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LoopAnalysisManager.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopIterator.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/MemorySSAUpdater.h"
#include "llvm/Analysis/MustExecute.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/IR/Use.h"
#include "llvm/IR/Value.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/GenericDomTree.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/ValueMapper.h"
#include <algorithm>
#include <cassert>
#include <iterator>
#include <numeric>
#include <utility>

#define DEBUG_TYPE "simple-loop-unswitch"

using namespace llvm;
using namespace llvm::PatternMatch;

STATISTIC(NumBranches, "Number of branches unswitched");
STATISTIC(NumSwitches, "Number of switches unswitched");
STATISTIC(NumGuards, "Number of guards turned into branches for unswitching");
STATISTIC(NumTrivial, "Number of unswitches that are trivial");
STATISTIC(
    NumCostMultiplierSkipped,
    "Number of unswitch candidates that had their cost multiplier skipped");

static cl::opt<bool> EnableNonTrivialUnswitch(
    "enable-nontrivial-unswitch", cl::init(false), cl::Hidden,
    cl::desc("Forcibly enables non-trivial loop unswitching rather than "
             "following the configuration passed into the pass."));

static cl::opt<int>
    UnswitchThreshold("unswitch-threshold", cl::init(50), cl::Hidden,
                      cl::ZeroOrMore,
                      cl::desc("The cost threshold for unswitching a loop."));

static cl::opt<bool> EnableUnswitchCostMultiplier(
    "enable-unswitch-cost-multiplier", cl::init(true), cl::Hidden,
    cl::desc("Enable unswitch cost multiplier that prohibits exponential "
             "explosion in nontrivial unswitch."));
static cl::opt<int> UnswitchSiblingsToplevelDiv(
    "unswitch-siblings-toplevel-div", cl::init(2), cl::Hidden,
    cl::desc("Toplevel siblings divisor for cost multiplier."));
static cl::opt<int> UnswitchNumInitialUnscaledCandidates(
    "unswitch-num-initial-unscaled-candidates", cl::init(8), cl::Hidden,
    cl::desc("Number of unswitch candidates that are ignored when calculating "
             "cost multiplier."));
static cl::opt<bool> UnswitchGuards(
    "simple-loop-unswitch-guards", cl::init(true), cl::Hidden,
    cl::desc("If enabled, simple loop unswitching will also consider "
             "llvm.experimental.guard intrinsics as unswitch candidates."));
static cl::opt<bool> DropNonTrivialImplicitNullChecks(
    "simple-loop-unswitch-drop-non-trivial-implicit-null-checks",
    cl::init(false), cl::Hidden,
    cl::desc("If enabled, drop make.implicit metadata in unswitched implicit "
             "null checks to save time analyzing if we can keep it."));
static cl::opt<unsigned>
    MSSAThreshold("simple-loop-unswitch-memoryssa-threshold",
                  cl::desc("Max number of memory uses to explore during "
                           "partial unswitching analysis"),
                  cl::init(100), cl::Hidden);
static cl::opt<bool> FreezeLoopUnswitchCond(
    "freeze-loop-unswitch-cond", cl::init(false), cl::Hidden,
    cl::desc("If enabled, the freeze instruction will be added to condition "
             "of loop unswitch to prevent miscompilation."));

/// Collect all of the loop invariant input values transitively used by the
/// homogeneous instruction graph from a given root.
///
/// This essentially walks from a root recursively through loop variant operands
/// which have the exact same opcode and finds all inputs which are loop
/// invariant. For some operations these can be re-associated and unswitched out
/// of the loop entirely.
static TinyPtrVector<Value *>
collectHomogenousInstGraphLoopInvariants(Loop &L, Instruction &Root,
                                         LoopInfo &LI) {
  assert(!L.isLoopInvariant(&Root) &&
         "Only need to walk the graph if root itself is not invariant.");
  TinyPtrVector<Value *> Invariants;

  bool IsRootAnd = match(&Root, m_LogicalAnd());
  bool IsRootOr  = match(&Root, m_LogicalOr());

  // Build a worklist and recurse through operators collecting invariants.
  SmallVector<Instruction *, 4> Worklist;
  SmallPtrSet<Instruction *, 8> Visited;
  Worklist.push_back(&Root);
  Visited.insert(&Root);
  do {
    Instruction &I = *Worklist.pop_back_val();
    for (Value *OpV : I.operand_values()) {
      // Skip constants as unswitching isn't interesting for them.
      if (isa<Constant>(OpV))
        continue;

      // Add it to our result if loop invariant.
      if (L.isLoopInvariant(OpV)) {
        Invariants.push_back(OpV);
        continue;
      }

      // If not an instruction with the same opcode, nothing we can do.
      Instruction *OpI = dyn_cast<Instruction>(OpV);

      if (OpI && ((IsRootAnd && match(OpI, m_LogicalAnd())) ||
                  (IsRootOr  && match(OpI, m_LogicalOr())))) {
        // Visit this operand.
        if (Visited.insert(OpI).second)
          Worklist.push_back(OpI);
      }
    }
  } while (!Worklist.empty());

  return Invariants;
}

static void replaceLoopInvariantUses(Loop &L, Value *Invariant,
                                     Constant &Replacement) {
  assert(!isa<Constant>(Invariant) && "Why are we unswitching on a constant?");

  // Replace uses of LIC in the loop with the given constant.
  // We use make_early_inc_range as set invalidates the iterator.
  for (Use &U : llvm::make_early_inc_range(Invariant->uses())) {
    Instruction *UserI = dyn_cast<Instruction>(U.getUser());

    // Replace this use within the loop body.
    if (UserI && L.contains(UserI))
      U.set(&Replacement);
  }
}

/// Check that all the LCSSA PHI nodes in the loop exit block have trivial
/// incoming values along this edge.
static bool areLoopExitPHIsLoopInvariant(Loop &L, BasicBlock &ExitingBB,
                                         BasicBlock &ExitBB) {
  for (Instruction &I : ExitBB) {
    auto *PN = dyn_cast<PHINode>(&I);
    if (!PN)
      // No more PHIs to check.
      return true;

    // If the incoming value for this edge isn't loop invariant the unswitch
    // won't be trivial.
    if (!L.isLoopInvariant(PN->getIncomingValueForBlock(&ExitingBB)))
      return false;
  }
  llvm_unreachable("Basic blocks should never be empty!");
}

/// Copy a set of loop invariant values \p ToDuplicate and insert them at the
/// end of \p BB and conditionally branch on the copied condition. We only
/// branch on a single value.
static void buildPartialUnswitchConditionalBranch(
    BasicBlock &BB, ArrayRef<Value *> Invariants, bool Direction,
    BasicBlock &UnswitchedSucc, BasicBlock &NormalSucc, bool InsertFreeze) {
  IRBuilder<> IRB(&BB);

  Value *Cond = Direction ? IRB.CreateOr(Invariants) :
    IRB.CreateAnd(Invariants);
  if (InsertFreeze)
    Cond = IRB.CreateFreeze(Cond, Cond->getName() + ".fr");
  IRB.CreateCondBr(Cond, Direction ? &UnswitchedSucc : &NormalSucc,
                   Direction ? &NormalSucc : &UnswitchedSucc);
}

/// Copy a set of loop invariant values, and conditionally branch on them.
static void buildPartialInvariantUnswitchConditionalBranch(
    BasicBlock &BB, ArrayRef<Value *> ToDuplicate, bool Direction,
    BasicBlock &UnswitchedSucc, BasicBlock &NormalSucc, Loop &L,
    MemorySSAUpdater *MSSAU) {
  ValueToValueMapTy VMap;
  for (auto *Val : reverse(ToDuplicate)) {
    Instruction *Inst = cast<Instruction>(Val);
    Instruction *NewInst = Inst->clone();
    BB.getInstList().insert(BB.end(), NewInst);
    RemapInstruction(NewInst, VMap,
                     RF_NoModuleLevelChanges | RF_IgnoreMissingLocals);
    VMap[Val] = NewInst;

    if (!MSSAU)
      continue;

    MemorySSA *MSSA = MSSAU->getMemorySSA();
    if (auto *MemUse =
            dyn_cast_or_null<MemoryUse>(MSSA->getMemoryAccess(Inst))) {
      auto *DefiningAccess = MemUse->getDefiningAccess();
      // Get the first defining access before the loop.
      while (L.contains(DefiningAccess->getBlock())) {
        // If the defining access is a MemoryPhi, get the incoming
        // value for the pre-header as defining access.
        if (auto *MemPhi = dyn_cast<MemoryPhi>(DefiningAccess))
          DefiningAccess =
              MemPhi->getIncomingValueForBlock(L.getLoopPreheader());
        else
          DefiningAccess = cast<MemoryDef>(DefiningAccess)->getDefiningAccess();
      }
      MSSAU->createMemoryAccessInBB(NewInst, DefiningAccess,
                                    NewInst->getParent(),
                                    MemorySSA::BeforeTerminator);
    }
  }

  IRBuilder<> IRB(&BB);
  Value *Cond = VMap[ToDuplicate[0]];
  IRB.CreateCondBr(Cond, Direction ? &UnswitchedSucc : &NormalSucc,
                   Direction ? &NormalSucc : &UnswitchedSucc);
}

/// Rewrite the PHI nodes in an unswitched loop exit basic block.
///
/// Requires that the loop exit and unswitched basic block are the same, and
/// that the exiting block was a unique predecessor of that block. Rewrites the
/// PHI nodes in that block such that what were LCSSA PHI nodes become trivial
/// PHI nodes from the old preheader that now contains the unswitched
/// terminator.
static void rewritePHINodesForUnswitchedExitBlock(BasicBlock &UnswitchedBB,
                                                  BasicBlock &OldExitingBB,
                                                  BasicBlock &OldPH) {
  for (PHINode &PN : UnswitchedBB.phis()) {
    // When the loop exit is directly unswitched we just need to update the
    // incoming basic block. We loop to handle weird cases with repeated
    // incoming blocks, but expect to typically only have one operand here.
    for (auto i : seq<int>(0, PN.getNumOperands())) {
      assert(PN.getIncomingBlock(i) == &OldExitingBB &&
             "Found incoming block different from unique predecessor!");
      PN.setIncomingBlock(i, &OldPH);
    }
  }
}

/// Rewrite the PHI nodes in the loop exit basic block and the split off
/// unswitched block.
///
/// Because the exit block remains an exit from the loop, this rewrites the
/// LCSSA PHI nodes in it to remove the unswitched edge and introduces PHI
/// nodes into the unswitched basic block to select between the value in the
/// old preheader and the loop exit.
static void rewritePHINodesForExitAndUnswitchedBlocks(BasicBlock &ExitBB,
                                                      BasicBlock &UnswitchedBB,
                                                      BasicBlock &OldExitingBB,
                                                      BasicBlock &OldPH,
                                                      bool FullUnswitch) {
  assert(&ExitBB != &UnswitchedBB &&
         "Must have different loop exit and unswitched blocks!");
  Instruction *InsertPt = &*UnswitchedBB.begin();
  for (PHINode &PN : ExitBB.phis()) {
    auto *NewPN = PHINode::Create(PN.getType(), /*NumReservedValues*/ 2,
                                  PN.getName() + ".split", InsertPt);

    // Walk backwards over the old PHI node's inputs to minimize the cost of
    // removing each one. We have to do this weird loop manually so that we
    // create the same number of new incoming edges in the new PHI as we expect
    // each case-based edge to be included in the unswitched switch in some
    // cases.
    // FIXME: This is really, really gross. It would be much cleaner if LLVM
    // allowed us to create a single entry for a predecessor block without
    // having separate entries for each "edge" even though these edges are
    // required to produce identical results.
    for (int i = PN.getNumIncomingValues() - 1; i >= 0; --i) {
      if (PN.getIncomingBlock(i) != &OldExitingBB)
        continue;

      Value *Incoming = PN.getIncomingValue(i);
      if (FullUnswitch)
        // No more edge from the old exiting block to the exit block.
        PN.removeIncomingValue(i);

      NewPN->addIncoming(Incoming, &OldPH);
    }

    // Now replace the old PHI with the new one and wire the old one in as an
    // input to the new one.
    PN.replaceAllUsesWith(NewPN);
    NewPN->addIncoming(&PN, &ExitBB);
  }
}

/// Hoist the current loop up to the innermost loop containing a remaining exit.
///
/// Because we've removed an exit from the loop, we may have changed the set of
/// loops reachable and need to move the current loop up the loop nest or even
/// to an entirely separate nest.
static void hoistLoopToNewParent(Loop &L, BasicBlock &Preheader,
                                 DominatorTree &DT, LoopInfo &LI,
                                 MemorySSAUpdater *MSSAU, ScalarEvolution *SE) {
  // If the loop is already at the top level, we can't hoist it anywhere.
  Loop *OldParentL = L.getParentLoop();
  if (!OldParentL)
    return;

  SmallVector<BasicBlock *, 4> Exits;
  L.getExitBlocks(Exits);
  Loop *NewParentL = nullptr;
  for (auto *ExitBB : Exits)
    if (Loop *ExitL = LI.getLoopFor(ExitBB))
      if (!NewParentL || NewParentL->contains(ExitL))
        NewParentL = ExitL;

  if (NewParentL == OldParentL)
    return;

  // The new parent loop (if different) should always contain the old one.
  if (NewParentL)
    assert(NewParentL->contains(OldParentL) &&
           "Can only hoist this loop up the nest!");

  // The preheader will need to move with the body of this loop. However,
  // because it isn't in this loop we also need to update the primary loop map.
  assert(OldParentL == LI.getLoopFor(&Preheader) &&
         "Parent loop of this loop should contain this loop's preheader!");
  LI.changeLoopFor(&Preheader, NewParentL);

  // Remove this loop from its old parent.
  OldParentL->removeChildLoop(&L);

  // Add the loop either to the new parent or as a top-level loop.
  if (NewParentL)
    NewParentL->addChildLoop(&L);
  else
    LI.addTopLevelLoop(&L);

  // Remove this loops blocks from the old parent and every other loop up the
  // nest until reaching the new parent. Also update all of these
  // no-longer-containing loops to reflect the nesting change.
  for (Loop *OldContainingL = OldParentL; OldContainingL != NewParentL;
       OldContainingL = OldContainingL->getParentLoop()) {
    llvm::erase_if(OldContainingL->getBlocksVector(),
                   [&](const BasicBlock *BB) {
                     return BB == &Preheader || L.contains(BB);
                   });

    OldContainingL->getBlocksSet().erase(&Preheader);
    for (BasicBlock *BB : L.blocks())
      OldContainingL->getBlocksSet().erase(BB);

    // Because we just hoisted a loop out of this one, we have essentially
    // created new exit paths from it. That means we need to form LCSSA PHI
    // nodes for values used in the no-longer-nested loop.
    formLCSSA(*OldContainingL, DT, &LI, SE);

    // We shouldn't need to form dedicated exits because the exit introduced
    // here is the (just split by unswitching) preheader. However, after trivial
    // unswitching it is possible to get new non-dedicated exits out of parent
    // loop so let's conservatively form dedicated exit blocks and figure out
    // if we can optimize later.
    formDedicatedExitBlocks(OldContainingL, &DT, &LI, MSSAU,
                            /*PreserveLCSSA*/ true);
  }
}

// Return the top-most loop containing ExitBB and having ExitBB as exiting block
// or the loop containing ExitBB, if there is no parent loop containing ExitBB
// as exiting block.
static Loop *getTopMostExitingLoop(BasicBlock *ExitBB, LoopInfo &LI) {
  Loop *TopMost = LI.getLoopFor(ExitBB);
  Loop *Current = TopMost;
  while (Current) {
    if (Current->isLoopExiting(ExitBB))
      TopMost = Current;
    Current = Current->getParentLoop();
  }
  return TopMost;
}

/// Unswitch a trivial branch if the condition is loop invariant.
///
/// This routine should only be called when loop code leading to the branch has
/// been validated as trivial (no side effects). This routine checks if the
/// condition is invariant and one of the successors is a loop exit. This
/// allows us to unswitch without duplicating the loop, making it trivial.
///
/// If this routine fails to unswitch the branch it returns false.
///
/// If the branch can be unswitched, this routine splits the preheader and
/// hoists the branch above that split. Preserves loop simplified form
/// (splitting the exit block as necessary). It simplifies the branch within
/// the loop to an unconditional branch but doesn't remove it entirely. Further
/// cleanup can be done with some simplifycfg like pass.
///
/// If `SE` is not null, it will be updated based on the potential loop SCEVs
/// invalidated by this.
static bool unswitchTrivialBranch(Loop &L, BranchInst &BI, DominatorTree &DT,
                                  LoopInfo &LI, ScalarEvolution *SE,
                                  MemorySSAUpdater *MSSAU) {
  assert(BI.isConditional() && "Can only unswitch a conditional branch!");
  LLVM_DEBUG(dbgs() << "  Trying to unswitch branch: " << BI << "\n");

  // The loop invariant values that we want to unswitch.
  TinyPtrVector<Value *> Invariants;

  // When true, we're fully unswitching the branch rather than just unswitching
  // some input conditions to the branch.
  bool FullUnswitch = false;

  if (L.isLoopInvariant(BI.getCondition())) {
    Invariants.push_back(BI.getCondition());
    FullUnswitch = true;
  } else {
    if (auto *CondInst = dyn_cast<Instruction>(BI.getCondition()))
      Invariants = collectHomogenousInstGraphLoopInvariants(L, *CondInst, LI);
    if (Invariants.empty()) {
      LLVM_DEBUG(dbgs() << "   Couldn't find invariant inputs!\n");
      return false;
    }
  }

  // Check that one of the branch's successors exits, and which one.
  bool ExitDirection = true;
  int LoopExitSuccIdx = 0;
  auto *LoopExitBB = BI.getSuccessor(0);
  if (L.contains(LoopExitBB)) {
    ExitDirection = false;
    LoopExitSuccIdx = 1;
    LoopExitBB = BI.getSuccessor(1);
    if (L.contains(LoopExitBB)) {
      LLVM_DEBUG(dbgs() << "   Branch doesn't exit the loop!\n");
      return false;
    }
  }
  auto *ContinueBB = BI.getSuccessor(1 - LoopExitSuccIdx);
  auto *ParentBB = BI.getParent();
  if (!areLoopExitPHIsLoopInvariant(L, *ParentBB, *LoopExitBB)) {
    LLVM_DEBUG(dbgs() << "   Loop exit PHI's aren't loop-invariant!\n");
    return false;
  }

  // When unswitching only part of the branch's condition, we need the exit
  // block to be reached directly from the partially unswitched input. This can
  // be done when the exit block is along the true edge and the branch condition
  // is a graph of `or` operations, or the exit block is along the false edge
  // and the condition is a graph of `and` operations.
  if (!FullUnswitch) {
    if (ExitDirection ? !match(BI.getCondition(), m_LogicalOr())
                      : !match(BI.getCondition(), m_LogicalAnd())) {
      LLVM_DEBUG(dbgs() << "   Branch condition is in improper form for "
                           "non-full unswitch!\n");
      return false;
    }
  }

  LLVM_DEBUG({
    dbgs() << "    unswitching trivial invariant conditions for: " << BI
           << "\n";
    for (Value *Invariant : Invariants) {
      dbgs() << "      " << *Invariant << " == true";
      if (Invariant != Invariants.back())
        dbgs() << " ||";
      dbgs() << "\n";
    }
  });

  // If we have scalar evolutions, we need to invalidate them including this
  // loop, the loop containing the exit block and the topmost parent loop
  // exiting via LoopExitBB.
  if (SE) {
    if (Loop *ExitL = getTopMostExitingLoop(LoopExitBB, LI))
      SE->forgetLoop(ExitL);
    else
      // Forget the entire nest as this exits the entire nest.
      SE->forgetTopmostLoop(&L);
  }

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // Split the preheader, so that we know that there is a safe place to insert
  // the conditional branch. We will change the preheader to have a conditional
  // branch on LoopCond.
  BasicBlock *OldPH = L.getLoopPreheader();
  BasicBlock *NewPH = SplitEdge(OldPH, L.getHeader(), &DT, &LI, MSSAU);

  // Now that we have a place to insert the conditional branch, create a place
  // to branch to: this is the exit block out of the loop that we are
  // unswitching. We need to split this if there are other loop predecessors.
  // Because the loop is in simplified form, *any* other predecessor is enough.
  BasicBlock *UnswitchedBB;
  if (FullUnswitch && LoopExitBB->getUniquePredecessor()) {
    assert(LoopExitBB->getUniquePredecessor() == BI.getParent() &&
           "A branch's parent isn't a predecessor!");
    UnswitchedBB = LoopExitBB;
  } else {
    UnswitchedBB =
        SplitBlock(LoopExitBB, &LoopExitBB->front(), &DT, &LI, MSSAU);
  }

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // Actually move the invariant uses into the unswitched position. If possible,
  // we do this by moving the instructions, but when doing partial unswitching
  // we do it by building a new merge of the values in the unswitched position.
  OldPH->getTerminator()->eraseFromParent();
  if (FullUnswitch) {
    // If fully unswitching, we can use the existing branch instruction.
    // Splice it into the old PH to gate reaching the new preheader and re-point
    // its successors.
    OldPH->getInstList().splice(OldPH->end(), BI.getParent()->getInstList(),
                                BI);
    if (MSSAU) {
      // Temporarily clone the terminator, to make MSSA update cheaper by
      // separating "insert edge" updates from "remove edge" ones.
      ParentBB->getInstList().push_back(BI.clone());
    } else {
      // Create a new unconditional branch that will continue the loop as a new
      // terminator.
      BranchInst::Create(ContinueBB, ParentBB);
    }
    BI.setSuccessor(LoopExitSuccIdx, UnswitchedBB);
    BI.setSuccessor(1 - LoopExitSuccIdx, NewPH);
  } else {
    // Only unswitching a subset of inputs to the condition, so we will need to
    // build a new branch that merges the invariant inputs.
    if (ExitDirection)
      assert(match(BI.getCondition(), m_LogicalOr()) &&
             "Must have an `or` of `i1`s or `select i1 X, true, Y`s for the "
             "condition!");
    else
      assert(match(BI.getCondition(), m_LogicalAnd()) &&
             "Must have an `and` of `i1`s or `select i1 X, Y, false`s for the"
             " condition!");
    buildPartialUnswitchConditionalBranch(*OldPH, Invariants, ExitDirection,
                                          *UnswitchedBB, *NewPH, false);
  }

  // Update the dominator tree with the added edge.
  DT.insertEdge(OldPH, UnswitchedBB);

  // After the dominator tree was updated with the added edge, update MemorySSA
  // if available.
  if (MSSAU) {
    SmallVector<CFGUpdate, 1> Updates;
    Updates.push_back({cfg::UpdateKind::Insert, OldPH, UnswitchedBB});
    MSSAU->applyInsertUpdates(Updates, DT);
  }

  // Finish updating dominator tree and memory ssa for full unswitch.
  if (FullUnswitch) {
    if (MSSAU) {
      // Remove the cloned branch instruction.
      ParentBB->getTerminator()->eraseFromParent();
      // Create unconditional branch now.
      BranchInst::Create(ContinueBB, ParentBB);
      MSSAU->removeEdge(ParentBB, LoopExitBB);
    }
    DT.deleteEdge(ParentBB, LoopExitBB);
  }

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // Rewrite the relevant PHI nodes.
  if (UnswitchedBB == LoopExitBB)
    rewritePHINodesForUnswitchedExitBlock(*UnswitchedBB, *ParentBB, *OldPH);
  else
    rewritePHINodesForExitAndUnswitchedBlocks(*LoopExitBB, *UnswitchedBB,
                                              *ParentBB, *OldPH, FullUnswitch);

  // The constant we can replace all of our invariants with inside the loop
  // body. If any of the invariants have a value other than this the loop won't
  // be entered.
  ConstantInt *Replacement = ExitDirection
                                 ? ConstantInt::getFalse(BI.getContext())
                                 : ConstantInt::getTrue(BI.getContext());

  // Since this is an i1 condition we can also trivially replace uses of it
  // within the loop with a constant.
  for (Value *Invariant : Invariants)
    replaceLoopInvariantUses(L, Invariant, *Replacement);

  // If this was full unswitching, we may have changed the nesting relationship
  // for this loop so hoist it to its correct parent if needed.
  if (FullUnswitch)
    hoistLoopToNewParent(L, *NewPH, DT, LI, MSSAU, SE);

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  LLVM_DEBUG(dbgs() << "    done: unswitching trivial branch...\n");
  ++NumTrivial;
  ++NumBranches;
  return true;
}

/// Unswitch a trivial switch if the condition is loop invariant.
///
/// This routine should only be called when loop code leading to the switch has
/// been validated as trivial (no side effects). This routine checks if the
/// condition is invariant and that at least one of the successors is a loop
/// exit. This allows us to unswitch without duplicating the loop, making it
/// trivial.
///
/// If this routine fails to unswitch the switch it returns false.
///
/// If the switch can be unswitched, this routine splits the preheader and
/// copies the switch above that split. If the default case is one of the
/// exiting cases, it copies the non-exiting cases and points them at the new
/// preheader. If the default case is not exiting, it copies the exiting cases
/// and points the default at the preheader. It preserves loop simplified form
/// (splitting the exit blocks as necessary). It simplifies the switch within
/// the loop by removing now-dead cases. If the default case is one of those
/// unswitched, it replaces its destination with a new basic block containing
/// only unreachable. Such basic blocks, while technically loop exits, are not
/// considered for unswitching so this is a stable transform and the same
/// switch will not be revisited. If after unswitching there is only a single
/// in-loop successor, the switch is further simplified to an unconditional
/// branch. Still more cleanup can be done with some simplifycfg like pass.
///
/// If `SE` is not null, it will be updated based on the potential loop SCEVs
/// invalidated by this.
static bool unswitchTrivialSwitch(Loop &L, SwitchInst &SI, DominatorTree &DT,
                                  LoopInfo &LI, ScalarEvolution *SE,
                                  MemorySSAUpdater *MSSAU) {
  LLVM_DEBUG(dbgs() << "  Trying to unswitch switch: " << SI << "\n");
  Value *LoopCond = SI.getCondition();

  // If this isn't switching on an invariant condition, we can't unswitch it.
  if (!L.isLoopInvariant(LoopCond))
    return false;

  auto *ParentBB = SI.getParent();

  // The same check must be used both for the default and the exit cases. We
  // should never leave edges from the switch instruction to a basic block that
  // we are unswitching, hence the condition used to determine the default case
  // needs to also be used to populate ExitCaseIndices, which is then used to
  // remove cases from the switch.
  auto IsTriviallyUnswitchableExitBlock = [&](BasicBlock &BBToCheck) {
    // BBToCheck is not an exit block if it is inside loop L.
    if (L.contains(&BBToCheck))
      return false;
    // BBToCheck is not trivial to unswitch if its phis aren't loop invariant.
    if (!areLoopExitPHIsLoopInvariant(L, *ParentBB, BBToCheck))
      return false;
    // We do not unswitch a block that only has an unreachable statement, as
    // it's possible this is a previously unswitched block. Only unswitch if
    // either the terminator is not unreachable, or, if it is, it's not the only
    // instruction in the block.
    auto *TI = BBToCheck.getTerminator();
    bool isUnreachable = isa<UnreachableInst>(TI);
    return !isUnreachable ||
           (isUnreachable && (BBToCheck.getFirstNonPHIOrDbg() != TI));
  };

  SmallVector<int, 4> ExitCaseIndices;
  for (auto Case : SI.cases())
    if (IsTriviallyUnswitchableExitBlock(*Case.getCaseSuccessor()))
      ExitCaseIndices.push_back(Case.getCaseIndex());
  BasicBlock *DefaultExitBB = nullptr;
  SwitchInstProfUpdateWrapper::CaseWeightOpt DefaultCaseWeight =
      SwitchInstProfUpdateWrapper::getSuccessorWeight(SI, 0);
  if (IsTriviallyUnswitchableExitBlock(*SI.getDefaultDest())) {
    DefaultExitBB = SI.getDefaultDest();
  } else if (ExitCaseIndices.empty())
    return false;

  LLVM_DEBUG(dbgs() << "    unswitching trivial switch...\n");

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // We may need to invalidate SCEVs for the outermost loop reached by any of
  // the exits.
  Loop *OuterL = &L;

  if (DefaultExitBB) {
    // Clear out the default destination temporarily to allow accurate
    // predecessor lists to be examined below.
    SI.setDefaultDest(nullptr);
    // Check the loop containing this exit.
    Loop *ExitL = LI.getLoopFor(DefaultExitBB);
    if (!ExitL || ExitL->contains(OuterL))
      OuterL = ExitL;
  }

  // Store the exit cases into a separate data structure and remove them from
  // the switch.
  SmallVector<std::tuple<ConstantInt *, BasicBlock *,
                         SwitchInstProfUpdateWrapper::CaseWeightOpt>,
              4> ExitCases;
  ExitCases.reserve(ExitCaseIndices.size());
  SwitchInstProfUpdateWrapper SIW(SI);
  // We walk the case indices backwards so that we remove the last case first
  // and don't disrupt the earlier indices.
  for (unsigned Index : reverse(ExitCaseIndices)) {
    auto CaseI = SI.case_begin() + Index;
    // Compute the outer loop from this exit.
    Loop *ExitL = LI.getLoopFor(CaseI->getCaseSuccessor());
    if (!ExitL || ExitL->contains(OuterL))
      OuterL = ExitL;
    // Save the value of this case.
    auto W = SIW.getSuccessorWeight(CaseI->getSuccessorIndex());
    ExitCases.emplace_back(CaseI->getCaseValue(), CaseI->getCaseSuccessor(), W);
    // Delete the unswitched cases.
    SIW.removeCase(CaseI);
  }

  if (SE) {
    if (OuterL)
      SE->forgetLoop(OuterL);
    else
      SE->forgetTopmostLoop(&L);
  }

  // Check if after this all of the remaining cases point at the same
  // successor.
  BasicBlock *CommonSuccBB = nullptr;
  if (SI.getNumCases() > 0 &&
      all_of(drop_begin(SI.cases()), [&SI](const SwitchInst::CaseHandle &Case) {
        return Case.getCaseSuccessor() == SI.case_begin()->getCaseSuccessor();
      }))
    CommonSuccBB = SI.case_begin()->getCaseSuccessor();
  if (!DefaultExitBB) {
    // If we're not unswitching the default, we need it to match any cases to
    // have a common successor or if we have no cases it is the common
    // successor.
    if (SI.getNumCases() == 0)
      CommonSuccBB = SI.getDefaultDest();
    else if (SI.getDefaultDest() != CommonSuccBB)
      CommonSuccBB = nullptr;
  }

  // Split the preheader, so that we know that there is a safe place to insert
  // the switch.
  BasicBlock *OldPH = L.getLoopPreheader();
  BasicBlock *NewPH = SplitEdge(OldPH, L.getHeader(), &DT, &LI, MSSAU);
  OldPH->getTerminator()->eraseFromParent();

  // Now add the unswitched switch.
  auto *NewSI = SwitchInst::Create(LoopCond, NewPH, ExitCases.size(), OldPH);
  SwitchInstProfUpdateWrapper NewSIW(*NewSI);

  // Rewrite the IR for the unswitched basic blocks. This requires two steps.
  // First, we split any exit blocks with remaining in-loop predecessors. Then
  // we update the PHIs in one of two ways depending on if there was a split.
  // We walk in reverse so that we split in the same order as the cases
  // appeared. This is purely for convenience of reading the resulting IR, but
  // it doesn't cost anything really.
  SmallPtrSet<BasicBlock *, 2> UnswitchedExitBBs;
  SmallDenseMap<BasicBlock *, BasicBlock *, 2> SplitExitBBMap;
  // Handle the default exit if necessary.
  // FIXME: It'd be great if we could merge this with the loop below but LLVM's
  // ranges aren't quite powerful enough yet.
  if (DefaultExitBB) {
    if (pred_empty(DefaultExitBB)) {
      UnswitchedExitBBs.insert(DefaultExitBB);
      rewritePHINodesForUnswitchedExitBlock(*DefaultExitBB, *ParentBB, *OldPH);
    } else {
      auto *SplitBB =
          SplitBlock(DefaultExitBB, &DefaultExitBB->front(), &DT, &LI, MSSAU);
      rewritePHINodesForExitAndUnswitchedBlocks(*DefaultExitBB, *SplitBB,
                                                *ParentBB, *OldPH,
                                                /*FullUnswitch*/ true);
      DefaultExitBB = SplitExitBBMap[DefaultExitBB] = SplitBB;
    }
  }
  // Note that we must use a reference in the for loop so that we update the
  // container.
  for (auto &ExitCase : reverse(ExitCases)) {
    // Grab a reference to the exit block in the pair so that we can update it.
    BasicBlock *ExitBB = std::get<1>(ExitCase);

    // If this case is the last edge into the exit block, we can simply reuse it
    // as it will no longer be a loop exit. No mapping necessary.
    if (pred_empty(ExitBB)) {
      // Only rewrite once.
      if (UnswitchedExitBBs.insert(ExitBB).second)
        rewritePHINodesForUnswitchedExitBlock(*ExitBB, *ParentBB, *OldPH);
      continue;
    }

    // Otherwise we need to split the exit block so that we retain an exit
    // block from the loop and a target for the unswitched condition.
    BasicBlock *&SplitExitBB = SplitExitBBMap[ExitBB];
    if (!SplitExitBB) {
      // If this is the first time we see this, do the split and remember it.
      SplitExitBB = SplitBlock(ExitBB, &ExitBB->front(), &DT, &LI, MSSAU);
      rewritePHINodesForExitAndUnswitchedBlocks(*ExitBB, *SplitExitBB,
                                                *ParentBB, *OldPH,
                                                /*FullUnswitch*/ true);
    }
    // Update the case pair to point to the split block.
    std::get<1>(ExitCase) = SplitExitBB;
  }

  // Now add the unswitched cases. We do this in reverse order as we built them
  // in reverse order.
  for (auto &ExitCase : reverse(ExitCases)) {
    ConstantInt *CaseVal = std::get<0>(ExitCase);
    BasicBlock *UnswitchedBB = std::get<1>(ExitCase);

    NewSIW.addCase(CaseVal, UnswitchedBB, std::get<2>(ExitCase));
  }

  // If the default was unswitched, re-point it and add explicit cases for
  // entering the loop.
  if (DefaultExitBB) {
    NewSIW->setDefaultDest(DefaultExitBB);
    NewSIW.setSuccessorWeight(0, DefaultCaseWeight);

    // We removed all the exit cases, so we just copy the cases to the
    // unswitched switch.
    for (const auto &Case : SI.cases())
      NewSIW.addCase(Case.getCaseValue(), NewPH,
                     SIW.getSuccessorWeight(Case.getSuccessorIndex()));
  } else if (DefaultCaseWeight) {
    // We have to set branch weight of the default case.
    uint64_t SW = *DefaultCaseWeight;
    for (const auto &Case : SI.cases()) {
      auto W = SIW.getSuccessorWeight(Case.getSuccessorIndex());
      assert(W &&
             "case weight must be defined as default case weight is defined");
      SW += *W;
    }
    NewSIW.setSuccessorWeight(0, SW);
  }

  // If we ended up with a common successor for every path through the switch
  // after unswitching, rewrite it to an unconditional branch to make it easy
  // to recognize. Otherwise we potentially have to recognize the default case
  // pointing at unreachable and other complexity.
  if (CommonSuccBB) {
    BasicBlock *BB = SI.getParent();
    // We may have had multiple edges to this common successor block, so remove
    // them as predecessors. We skip the first one, either the default or the
    // actual first case.
    bool SkippedFirst = DefaultExitBB == nullptr;
    for (auto Case : SI.cases()) {
      assert(Case.getCaseSuccessor() == CommonSuccBB &&
             "Non-common successor!");
      (void)Case;
      if (!SkippedFirst) {
        SkippedFirst = true;
        continue;
      }
      CommonSuccBB->removePredecessor(BB,
                                      /*KeepOneInputPHIs*/ true);
    }
    // Now nuke the switch and replace it with a direct branch.
    SIW.eraseFromParent();
    BranchInst::Create(CommonSuccBB, BB);
  } else if (DefaultExitBB) {
    assert(SI.getNumCases() > 0 &&
           "If we had no cases we'd have a common successor!");
    // Move the last case to the default successor. This is valid as if the
    // default got unswitched it cannot be reached. This has the advantage of
    // being simple and keeping the number of edges from this switch to
    // successors the same, and avoiding any PHI update complexity.
    auto LastCaseI = std::prev(SI.case_end());

    SI.setDefaultDest(LastCaseI->getCaseSuccessor());
    SIW.setSuccessorWeight(
        0, SIW.getSuccessorWeight(LastCaseI->getSuccessorIndex()));
    SIW.removeCase(LastCaseI);
  }

  // Walk the unswitched exit blocks and the unswitched split blocks and update
  // the dominator tree based on the CFG edits. While we are walking unordered
  // containers here, the API for applyUpdates takes an unordered list of
  // updates and requires them to not contain duplicates.
  SmallVector<DominatorTree::UpdateType, 4> DTUpdates;
  for (auto *UnswitchedExitBB : UnswitchedExitBBs) {
    DTUpdates.push_back({DT.Delete, ParentBB, UnswitchedExitBB});
    DTUpdates.push_back({DT.Insert, OldPH, UnswitchedExitBB});
  }
  for (auto SplitUnswitchedPair : SplitExitBBMap) {
    DTUpdates.push_back({DT.Delete, ParentBB, SplitUnswitchedPair.first});
    DTUpdates.push_back({DT.Insert, OldPH, SplitUnswitchedPair.second});
  }

  if (MSSAU) {
    MSSAU->applyUpdates(DTUpdates, DT, /*UpdateDT=*/true);
    if (VerifyMemorySSA)
      MSSAU->getMemorySSA()->verifyMemorySSA();
  } else {
    DT.applyUpdates(DTUpdates);
  }

  assert(DT.verify(DominatorTree::VerificationLevel::Fast));

  // We may have changed the nesting relationship for this loop so hoist it to
  // its correct parent if needed.
  hoistLoopToNewParent(L, *NewPH, DT, LI, MSSAU, SE);

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  ++NumTrivial;
  ++NumSwitches;
  LLVM_DEBUG(dbgs() << "    done: unswitching trivial switch...\n");
  return true;
}

/// This routine scans the loop to find a branch or switch which occurs before
/// any side effects occur. These can potentially be unswitched without
/// duplicating the loop. If a branch or switch is successfully unswitched the
/// scanning continues to see if subsequent branches or switches have become
/// trivial. Once all trivial candidates have been unswitched, this routine
/// returns.
///
/// The return value indicates whether anything was unswitched (and therefore
/// changed).
///
/// If `SE` is not null, it will be updated based on the potential loop SCEVs
/// invalidated by this.
static bool unswitchAllTrivialConditions(Loop &L, DominatorTree &DT,
                                         LoopInfo &LI, ScalarEvolution *SE,
                                         MemorySSAUpdater *MSSAU) {
  bool Changed = false;

  // If loop header has only one reachable successor we should keep looking for
  // trivial condition candidates in the successor as well. An alternative is
  // to constant fold conditions and merge successors into loop header (then we
  // only need to check header's terminator). The reason for not doing this in
  // LoopUnswitch pass is that it could potentially break LoopPassManager's
  // invariants. Folding dead branches could either eliminate the current loop
  // or make other loops unreachable. LCSSA form might also not be preserved
  // after deleting branches. The following code keeps traversing loop header's
  // successors until it finds the trivial condition candidate (condition that
  // is not a constant). Since unswitching generates branches with constant
  // conditions, this scenario could be very common in practice.
  BasicBlock *CurrentBB = L.getHeader();
  SmallPtrSet<BasicBlock *, 8> Visited;
  Visited.insert(CurrentBB);
  do {
    // Check if there are any side-effecting instructions (e.g. stores, calls,
    // volatile loads) in the part of the loop that the code *would* execute
    // without unswitching.
    if (MSSAU) // Possible early exit with MSSA
      if (auto *Defs = MSSAU->getMemorySSA()->getBlockDefs(CurrentBB))
        if (!isa<MemoryPhi>(*Defs->begin()) || (++Defs->begin() != Defs->end()))
          return Changed;
    if (llvm::any_of(*CurrentBB,
                     [](Instruction &I) { return I.mayHaveSideEffects(); }))
      return Changed;

    Instruction *CurrentTerm = CurrentBB->getTerminator();

    if (auto *SI = dyn_cast<SwitchInst>(CurrentTerm)) {
      // Don't bother trying to unswitch past a switch with a constant
      // condition. This should be removed prior to running this pass by
      // simplifycfg.
      if (isa<Constant>(SI->getCondition()))
        return Changed;

      if (!unswitchTrivialSwitch(L, *SI, DT, LI, SE, MSSAU))
        // Couldn't unswitch this one so we're done.
        return Changed;

      // Mark that we managed to unswitch something.
      Changed = true;

      // If unswitching turned the terminator into an unconditional branch then
      // we can continue. The unswitching logic specifically works to fold any
      // cases it can into an unconditional branch to make it easier to
      // recognize here.
      auto *BI = dyn_cast<BranchInst>(CurrentBB->getTerminator());
      if (!BI || BI->isConditional())
        return Changed;

      CurrentBB = BI->getSuccessor(0);
      continue;
    }

    auto *BI = dyn_cast<BranchInst>(CurrentTerm);
    if (!BI)
      // We do not understand other terminator instructions.
      return Changed;

    // Don't bother trying to unswitch past an unconditional branch or a branch
    // with a constant value. These should be removed by simplifycfg prior to
    // running this pass.
    if (!BI->isConditional() || isa<Constant>(BI->getCondition()))
      return Changed;

    // Found a trivial condition candidate: non-foldable conditional branch. If
    // we fail to unswitch this, we can't do anything else that is trivial.
    if (!unswitchTrivialBranch(L, *BI, DT, LI, SE, MSSAU))
      return Changed;

    // Mark that we managed to unswitch something.
    Changed = true;

    // If we only unswitched some of the conditions feeding the branch, we won't
    // have collapsed it to a single successor.
    BI = cast<BranchInst>(CurrentBB->getTerminator());
    if (BI->isConditional())
      return Changed;

    // Follow the newly unconditional branch into its successor.
    CurrentBB = BI->getSuccessor(0);

    // When continuing, if we exit the loop or reach a previous visited block,
    // then we can not reach any trivial condition candidates (unfoldable
    // branch instructions or switch instructions) and no unswitch can happen.
  } while (L.contains(CurrentBB) && Visited.insert(CurrentBB).second);

  return Changed;
}

/// Build the cloned blocks for an unswitched copy of the given loop.
///
/// The cloned blocks are inserted before the loop preheader (`LoopPH`) and
/// after the split block (`SplitBB`) that will be used to select between the
/// cloned and original loop.
///
/// This routine handles cloning all of the necessary loop blocks and exit
/// blocks including rewriting their instructions and the relevant PHI nodes.
/// Any loop blocks or exit blocks which are dominated by a different successor
/// than the one for this clone of the loop blocks can be trivially skipped. We
/// use the `DominatingSucc` map to determine whether a block satisfies that
/// property with a simple map lookup.
///
/// It also correctly creates the unconditional branch in the cloned
/// unswitched parent block to only point at the unswitched successor.
///
/// This does not handle most of the necessary updates to `LoopInfo`. Only exit
/// block splitting is correctly reflected in `LoopInfo`, essentially all of
/// the cloned blocks (and their loops) are left without full `LoopInfo`
/// updates. This also doesn't fully update `DominatorTree`. It adds the cloned
/// blocks to them but doesn't create the cloned `DominatorTree` structure and
/// instead the caller must recompute an accurate DT. It *does* correctly
/// update the `AssumptionCache` provided in `AC`.
static BasicBlock *buildClonedLoopBlocks(
    Loop &L, BasicBlock *LoopPH, BasicBlock *SplitBB,
    ArrayRef<BasicBlock *> ExitBlocks, BasicBlock *ParentBB,
    BasicBlock *UnswitchedSuccBB, BasicBlock *ContinueSuccBB,
    const SmallDenseMap<BasicBlock *, BasicBlock *, 16> &DominatingSucc,
    ValueToValueMapTy &VMap,
    SmallVectorImpl<DominatorTree::UpdateType> &DTUpdates, AssumptionCache &AC,
    DominatorTree &DT, LoopInfo &LI, MemorySSAUpdater *MSSAU) {
  SmallVector<BasicBlock *, 4> NewBlocks;
  NewBlocks.reserve(L.getNumBlocks() + ExitBlocks.size());

  // We will need to clone a bunch of blocks, wrap up the clone operation in
  // a helper.
  auto CloneBlock = [&](BasicBlock *OldBB) {
    // Clone the basic block and insert it before the new preheader.
    BasicBlock *NewBB = CloneBasicBlock(OldBB, VMap, ".us", OldBB->getParent());
    NewBB->moveBefore(LoopPH);

    // Record this block and the mapping.
    NewBlocks.push_back(NewBB);
    VMap[OldBB] = NewBB;

    return NewBB;
  };

  // We skip cloning blocks when they have a dominating succ that is not the
  // succ we are cloning for.
  auto SkipBlock = [&](BasicBlock *BB) {
    auto It = DominatingSucc.find(BB);
    return It != DominatingSucc.end() && It->second != UnswitchedSuccBB;
  };

  // First, clone the preheader.
  auto *ClonedPH = CloneBlock(LoopPH);

  // Then clone all the loop blocks, skipping the ones that aren't necessary.
  for (auto *LoopBB : L.blocks())
    if (!SkipBlock(LoopBB))
      CloneBlock(LoopBB);

  // Split all the loop exit edges so that when we clone the exit blocks, if
  // any of the exit blocks are *also* a preheader for some other loop, we
  // don't create multiple predecessors entering the loop header.
  for (auto *ExitBB : ExitBlocks) {
    if (SkipBlock(ExitBB))
      continue;

    // When we are going to clone an exit, we don't need to clone all the
    // instructions in the exit block and we want to ensure we have an easy
    // place to merge the CFG, so split the exit first. This is always safe to
    // do because there cannot be any non-loop predecessors of a loop exit in
    // loop simplified form.
    auto *MergeBB = SplitBlock(ExitBB, &ExitBB->front(), &DT, &LI, MSSAU);

    // Rearrange the names to make it easier to write test cases by having the
    // exit block carry the suffix rather than the merge block carrying the
    // suffix.
    MergeBB->takeName(ExitBB);
    ExitBB->setName(Twine(MergeBB->getName()) + ".split");

    // Now clone the original exit block.
    auto *ClonedExitBB = CloneBlock(ExitBB);
    assert(ClonedExitBB->getTerminator()->getNumSuccessors() == 1 &&
           "Exit block should have been split to have one successor!");
    assert(ClonedExitBB->getTerminator()->getSuccessor(0) == MergeBB &&
           "Cloned exit block has the wrong successor!");

    // Remap any cloned instructions and create a merge phi node for them.
    for (auto ZippedInsts : llvm::zip_first(
             llvm::make_range(ExitBB->begin(), std::prev(ExitBB->end())),
             llvm::make_range(ClonedExitBB->begin(),
                              std::prev(ClonedExitBB->end())))) {
      Instruction &I = std::get<0>(ZippedInsts);
      Instruction &ClonedI = std::get<1>(ZippedInsts);

      // The only instructions in the exit block should be PHI nodes and
      // potentially a landing pad.
      assert(
          (isa<PHINode>(I) || isa<LandingPadInst>(I) || isa<CatchPadInst>(I)) &&
          "Bad instruction in exit block!");
      // We should have a value map between the instruction and its clone.
      assert(VMap.lookup(&I) == &ClonedI && "Mismatch in the value map!");

      auto *MergePN =
          PHINode::Create(I.getType(), /*NumReservedValues*/ 2, ".us-phi",
                          &*MergeBB->getFirstInsertionPt());
      I.replaceAllUsesWith(MergePN);
      MergePN->addIncoming(&I, ExitBB);
      MergePN->addIncoming(&ClonedI, ClonedExitBB);
    }
  }

  // Rewrite the instructions in the cloned blocks to refer to the instructions
  // in the cloned blocks. We have to do this as a second pass so that we have
  // everything available. Also, we have inserted new instructions which may
  // include assume intrinsics, so we update the assumption cache while
  // processing this.
  for (auto *ClonedBB : NewBlocks)
    for (Instruction &I : *ClonedBB) {
      RemapInstruction(&I, VMap,
                       RF_NoModuleLevelChanges | RF_IgnoreMissingLocals);
      if (auto *II = dyn_cast<AssumeInst>(&I))
        AC.registerAssumption(II);
    }

  // Update any PHI nodes in the cloned successors of the skipped blocks to not
  // have spurious incoming values.
  for (auto *LoopBB : L.blocks())
    if (SkipBlock(LoopBB))
      for (auto *SuccBB : successors(LoopBB))
        if (auto *ClonedSuccBB = cast_or_null<BasicBlock>(VMap.lookup(SuccBB)))
          for (PHINode &PN : ClonedSuccBB->phis())
            PN.removeIncomingValue(LoopBB, /*DeletePHIIfEmpty*/ false);

  // Remove the cloned parent as a predecessor of any successor we ended up
  // cloning other than the unswitched one.
  auto *ClonedParentBB = cast<BasicBlock>(VMap.lookup(ParentBB));
  for (auto *SuccBB : successors(ParentBB)) {
    if (SuccBB == UnswitchedSuccBB)
      continue;

    auto *ClonedSuccBB = cast_or_null<BasicBlock>(VMap.lookup(SuccBB));
    if (!ClonedSuccBB)
      continue;

    ClonedSuccBB->removePredecessor(ClonedParentBB,
                                    /*KeepOneInputPHIs*/ true);
  }

  // Replace the cloned branch with an unconditional branch to the cloned
  // unswitched successor.
  auto *ClonedSuccBB = cast<BasicBlock>(VMap.lookup(UnswitchedSuccBB));
  Instruction *ClonedTerminator = ClonedParentBB->getTerminator();
  // Trivial Simplification. If Terminator is a conditional branch and
  // condition becomes dead - erase it.
  Value *ClonedConditionToErase = nullptr;
  if (auto *BI = dyn_cast<BranchInst>(ClonedTerminator))
    ClonedConditionToErase = BI->getCondition();
  else if (auto *SI = dyn_cast<SwitchInst>(ClonedTerminator))
    ClonedConditionToErase = SI->getCondition();

  ClonedTerminator->eraseFromParent();
  BranchInst::Create(ClonedSuccBB, ClonedParentBB);

  if (ClonedConditionToErase)
    RecursivelyDeleteTriviallyDeadInstructions(ClonedConditionToErase, nullptr,
                                               MSSAU);

  // If there are duplicate entries in the PHI nodes because of multiple edges
  // to the unswitched successor, we need to nuke all but one as we replaced it
  // with a direct branch.
  for (PHINode &PN : ClonedSuccBB->phis()) {
    bool Found = false;
    // Loop over the incoming operands backwards so we can easily delete as we
    // go without invalidating the index.
    for (int i = PN.getNumOperands() - 1; i >= 0; --i) {
      if (PN.getIncomingBlock(i) != ClonedParentBB)
        continue;
      if (!Found) {
        Found = true;
        continue;
      }
      PN.removeIncomingValue(i, /*DeletePHIIfEmpty*/ false);
    }
  }

  // Record the domtree updates for the new blocks.
  SmallPtrSet<BasicBlock *, 4> SuccSet;
  for (auto *ClonedBB : NewBlocks) {
    for (auto *SuccBB : successors(ClonedBB))
      if (SuccSet.insert(SuccBB).second)
        DTUpdates.push_back({DominatorTree::Insert, ClonedBB, SuccBB});
    SuccSet.clear();
  }

  return ClonedPH;
}

/// Recursively clone the specified loop and all of its children.
///
/// The target parent loop for the clone should be provided, or can be null if
/// the clone is a top-level loop. While cloning, all the blocks are mapped
/// with the provided value map. The entire original loop must be present in
/// the value map. The cloned loop is returned.
static Loop *cloneLoopNest(Loop &OrigRootL, Loop *RootParentL,
                           const ValueToValueMapTy &VMap, LoopInfo &LI) {
  auto AddClonedBlocksToLoop = [&](Loop &OrigL, Loop &ClonedL) {
    assert(ClonedL.getBlocks().empty() && "Must start with an empty loop!");
    ClonedL.reserveBlocks(OrigL.getNumBlocks());
    for (auto *BB : OrigL.blocks()) {
      auto *ClonedBB = cast<BasicBlock>(VMap.lookup(BB));
      ClonedL.addBlockEntry(ClonedBB);
      if (LI.getLoopFor(BB) == &OrigL)
        LI.changeLoopFor(ClonedBB, &ClonedL);
    }
  };

  // We specially handle the first loop because it may get cloned into
  // a different parent and because we most commonly are cloning leaf loops.
  Loop *ClonedRootL = LI.AllocateLoop();
  if (RootParentL)
    RootParentL->addChildLoop(ClonedRootL);
  else
    LI.addTopLevelLoop(ClonedRootL);
  AddClonedBlocksToLoop(OrigRootL, *ClonedRootL);

  if (OrigRootL.isInnermost())
    return ClonedRootL;

  // If we have a nest, we can quickly clone the entire loop nest using an
  // iterative approach because it is a tree. We keep the cloned parent in the
  // data structure to avoid repeatedly querying through a map to find it.
  SmallVector<std::pair<Loop *, Loop *>, 16> LoopsToClone;
  // Build up the loops to clone in reverse order as we'll clone them from the
  // back.
  for (Loop *ChildL : llvm::reverse(OrigRootL))
    LoopsToClone.push_back({ClonedRootL, ChildL});
  do {
    Loop *ClonedParentL, *L;
    std::tie(ClonedParentL, L) = LoopsToClone.pop_back_val();
    Loop *ClonedL = LI.AllocateLoop();
    ClonedParentL->addChildLoop(ClonedL);
    AddClonedBlocksToLoop(*L, *ClonedL);
    for (Loop *ChildL : llvm::reverse(*L))
      LoopsToClone.push_back({ClonedL, ChildL});
  } while (!LoopsToClone.empty());

  return ClonedRootL;
}

/// Build the cloned loops of an original loop from unswitching.
///
/// Because unswitching simplifies the CFG of the loop, this isn't a trivial
/// operation. We need to re-verify that there even is a loop (as the backedge
/// may not have been cloned), and even if there are remaining backedges the
/// backedge set may be different. However, we know that each child loop is
/// undisturbed, we only need to find where to place each child loop within
/// either any parent loop or within a cloned version of the original loop.
///
/// Because child loops may end up cloned outside of any cloned version of the
/// original loop, multiple cloned sibling loops may be created. All of them
/// are returned so that the newly introduced loop nest roots can be
/// identified.
static void buildClonedLoops(Loop &OrigL, ArrayRef<BasicBlock *> ExitBlocks,
                             const ValueToValueMapTy &VMap, LoopInfo &LI,
                             SmallVectorImpl<Loop *> &NonChildClonedLoops) {
  Loop *ClonedL = nullptr;

  auto *OrigPH = OrigL.getLoopPreheader();
  auto *OrigHeader = OrigL.getHeader();

  auto *ClonedPH = cast<BasicBlock>(VMap.lookup(OrigPH));
  auto *ClonedHeader = cast<BasicBlock>(VMap.lookup(OrigHeader));

  // We need to know the loops of the cloned exit blocks to even compute the
  // accurate parent loop. If we only clone exits to some parent of the
  // original parent, we want to clone into that outer loop. We also keep track
  // of the loops that our cloned exit blocks participate in.
  Loop *ParentL = nullptr;
  SmallVector<BasicBlock *, 4> ClonedExitsInLoops;
  SmallDenseMap<BasicBlock *, Loop *, 16> ExitLoopMap;
  ClonedExitsInLoops.reserve(ExitBlocks.size());
  for (auto *ExitBB : ExitBlocks)
    if (auto *ClonedExitBB = cast_or_null<BasicBlock>(VMap.lookup(ExitBB)))
      if (Loop *ExitL = LI.getLoopFor(ExitBB)) {
        ExitLoopMap[ClonedExitBB] = ExitL;
        ClonedExitsInLoops.push_back(ClonedExitBB);
        if (!ParentL || (ParentL != ExitL && ParentL->contains(ExitL)))
          ParentL = ExitL;
      }
  assert((!ParentL || ParentL == OrigL.getParentLoop() ||
          ParentL->contains(OrigL.getParentLoop())) &&
         "The computed parent loop should always contain (or be) the parent of "
         "the original loop.");

  // We build the set of blocks dominated by the cloned header from the set of
  // cloned blocks out of the original loop. While not all of these will
  // necessarily be in the cloned loop, it is enough to establish that they
  // aren't in unreachable cycles, etc.
  SmallSetVector<BasicBlock *, 16> ClonedLoopBlocks;
  for (auto *BB : OrigL.blocks())
    if (auto *ClonedBB = cast_or_null<BasicBlock>(VMap.lookup(BB)))
      ClonedLoopBlocks.insert(ClonedBB);

  // Rebuild the set of blocks that will end up in the cloned loop. We may have
  // skipped cloning some region of this loop which can in turn skip some of
  // the backedges so we have to rebuild the blocks in the loop based on the
  // backedges that remain after cloning.
  SmallVector<BasicBlock *, 16> Worklist;
  SmallPtrSet<BasicBlock *, 16> BlocksInClonedLoop;
  for (auto *Pred : predecessors(ClonedHeader)) {
    // The only possible non-loop header predecessor is the preheader because
    // we know we cloned the loop in simplified form.
    if (Pred == ClonedPH)
      continue;

    // Because the loop was in simplified form, the only non-loop predecessor
    // should be the preheader.
    assert(ClonedLoopBlocks.count(Pred) && "Found a predecessor of the loop "
                                           "header other than the preheader "
                                           "that is not part of the loop!");

    // Insert this block into the loop set and on the first visit (and if it
    // isn't the header we're currently walking) put it into the worklist to
    // recurse through.
    if (BlocksInClonedLoop.insert(Pred).second && Pred != ClonedHeader)
      Worklist.push_back(Pred);
  }

  // If we had any backedges then there *is* a cloned loop. Put the header into
  // the loop set and then walk the worklist backwards to find all the blocks
  // that remain within the loop after cloning.
  if (!BlocksInClonedLoop.empty()) {
    BlocksInClonedLoop.insert(ClonedHeader);

    while (!Worklist.empty()) {
      BasicBlock *BB = Worklist.pop_back_val();
      assert(BlocksInClonedLoop.count(BB) &&
             "Didn't put block into the loop set!");

      // Insert any predecessors that are in the possible set into the cloned
      // set, and if the insert is successful, add them to the worklist. Note
      // that we filter on the blocks that are definitely reachable via the
      // backedge to the loop header so we may prune out dead code within the
      // cloned loop.
      for (auto *Pred : predecessors(BB))
        if (ClonedLoopBlocks.count(Pred) &&
            BlocksInClonedLoop.insert(Pred).second)
          Worklist.push_back(Pred);
    }

    ClonedL = LI.AllocateLoop();
    if (ParentL) {
      ParentL->addBasicBlockToLoop(ClonedPH, LI);
      ParentL->addChildLoop(ClonedL);
    } else {
      LI.addTopLevelLoop(ClonedL);
    }
    NonChildClonedLoops.push_back(ClonedL);

    ClonedL->reserveBlocks(BlocksInClonedLoop.size());
    // We don't want to just add the cloned loop blocks based on how we
    // discovered them. The original order of blocks was carefully built in
    // a way that doesn't rely on predecessor ordering. Rather than re-invent
    // that logic, we just re-walk the original blocks (and those of the child
    // loops) and filter them as we add them into the cloned loop.
    for (auto *BB : OrigL.blocks()) {
      auto *ClonedBB = cast_or_null<BasicBlock>(VMap.lookup(BB));
      if (!ClonedBB || !BlocksInClonedLoop.count(ClonedBB))
        continue;

      // Directly add the blocks that are only in this loop.
      if (LI.getLoopFor(BB) == &OrigL) {
        ClonedL->addBasicBlockToLoop(ClonedBB, LI);
        continue;
      }

      // We want to manually add it to this loop and parents.
      // Registering it with LoopInfo will happen when we clone the top
      // loop for this block.
      for (Loop *PL = ClonedL; PL; PL = PL->getParentLoop())
        PL->addBlockEntry(ClonedBB);
    }

    // Now add each child loop whose header remains within the cloned loop. All
    // of the blocks within the loop must satisfy the same constraints as the
    // header so once we pass the header checks we can just clone the entire
    // child loop nest.
    for (Loop *ChildL : OrigL) {
      auto *ClonedChildHeader =
          cast_or_null<BasicBlock>(VMap.lookup(ChildL->getHeader()));
      if (!ClonedChildHeader || !BlocksInClonedLoop.count(ClonedChildHeader))
        continue;

#ifndef NDEBUG
      // We should never have a cloned child loop header but fail to have
      // all of the blocks for that child loop.
      for (auto *ChildLoopBB : ChildL->blocks())
        assert(BlocksInClonedLoop.count(
                   cast<BasicBlock>(VMap.lookup(ChildLoopBB))) &&
               "Child cloned loop has a header within the cloned outer "
               "loop but not all of its blocks!");
#endif

      cloneLoopNest(*ChildL, ClonedL, VMap, LI);
    }
  }

  // Now that we've handled all the components of the original loop that were
  // cloned into a new loop, we still need to handle anything from the original
  // loop that wasn't in a cloned loop.

  // Figure out what blocks are left to place within any loop nest containing
  // the unswitched loop. If we never formed a loop, the cloned PH is one of
  // them.
  SmallPtrSet<BasicBlock *, 16> UnloopedBlockSet;
  if (BlocksInClonedLoop.empty())
    UnloopedBlockSet.insert(ClonedPH);
  for (auto *ClonedBB : ClonedLoopBlocks)
    if (!BlocksInClonedLoop.count(ClonedBB))
      UnloopedBlockSet.insert(ClonedBB);

  // Copy the cloned exits and sort them in ascending loop depth, we'll work
  // backwards across these to process them inside out. The order shouldn't
  // matter as we're just trying to build up the map from inside-out; we use
  // the map in a more stably ordered way below.
  auto OrderedClonedExitsInLoops = ClonedExitsInLoops;
  llvm::sort(OrderedClonedExitsInLoops, [&](BasicBlock *LHS, BasicBlock *RHS) {
    return ExitLoopMap.lookup(LHS)->getLoopDepth() <
           ExitLoopMap.lookup(RHS)->getLoopDepth();
  });

  // Populate the existing ExitLoopMap with everything reachable from each
  // exit, starting from the inner most exit.
  while (!UnloopedBlockSet.empty() && !OrderedClonedExitsInLoops.empty()) {
    assert(Worklist.empty() && "Didn't clear worklist!");

    BasicBlock *ExitBB = OrderedClonedExitsInLoops.pop_back_val();
    Loop *ExitL = ExitLoopMap.lookup(ExitBB);

    // Walk the CFG back until we hit the cloned PH adding everything reachable
    // and in the unlooped set to this exit block's loop.
    Worklist.push_back(ExitBB);
    do {
      BasicBlock *BB = Worklist.pop_back_val();
      // We can stop recursing at the cloned preheader (if we get there).
      if (BB == ClonedPH)
        continue;

      for (BasicBlock *PredBB : predecessors(BB)) {
        // If this pred has already been moved to our set or is part of some
        // (inner) loop, no update needed.
        if (!UnloopedBlockSet.erase(PredBB)) {
          assert(
              (BlocksInClonedLoop.count(PredBB) || ExitLoopMap.count(PredBB)) &&
              "Predecessor not mapped to a loop!");
          continue;
        }

        // We just insert into the loop set here. We'll add these blocks to the
        // exit loop after we build up the set in an order that doesn't rely on
        // predecessor order (which in turn relies on use list order).
        bool Inserted = ExitLoopMap.insert({PredBB, ExitL}).second;
        (void)Inserted;
        assert(Inserted && "Should only visit an unlooped block once!");

        // And recurse through to its predecessors.
        Worklist.push_back(PredBB);
      }
    } while (!Worklist.empty());
  }

  // Now that the ExitLoopMap gives as  mapping for all the non-looping cloned
  // blocks to their outer loops, walk the cloned blocks and the cloned exits
  // in their original order adding them to the correct loop.

  // We need a stable insertion order. We use the order of the original loop
  // order and map into the correct parent loop.
  for (auto *BB : llvm::concat<BasicBlock *const>(
           makeArrayRef(ClonedPH), ClonedLoopBlocks, ClonedExitsInLoops))
    if (Loop *OuterL = ExitLoopMap.lookup(BB))
      OuterL->addBasicBlockToLoop(BB, LI);

#ifndef NDEBUG
  for (auto &BBAndL : ExitLoopMap) {
    auto *BB = BBAndL.first;
    auto *OuterL = BBAndL.second;
    assert(LI.getLoopFor(BB) == OuterL &&
           "Failed to put all blocks into outer loops!");
  }
#endif

  // Now that all the blocks are placed into the correct containing loop in the
  // absence of child loops, find all the potentially cloned child loops and
  // clone them into whatever outer loop we placed their header into.
  for (Loop *ChildL : OrigL) {
    auto *ClonedChildHeader =
        cast_or_null<BasicBlock>(VMap.lookup(ChildL->getHeader()));
    if (!ClonedChildHeader || BlocksInClonedLoop.count(ClonedChildHeader))
      continue;

#ifndef NDEBUG
    for (auto *ChildLoopBB : ChildL->blocks())
      assert(VMap.count(ChildLoopBB) &&
             "Cloned a child loop header but not all of that loops blocks!");
#endif

    NonChildClonedLoops.push_back(cloneLoopNest(
        *ChildL, ExitLoopMap.lookup(ClonedChildHeader), VMap, LI));
  }
}

static void
deleteDeadClonedBlocks(Loop &L, ArrayRef<BasicBlock *> ExitBlocks,
                       ArrayRef<std::unique_ptr<ValueToValueMapTy>> VMaps,
                       DominatorTree &DT, MemorySSAUpdater *MSSAU) {
  // Find all the dead clones, and remove them from their successors.
  SmallVector<BasicBlock *, 16> DeadBlocks;
  for (BasicBlock *BB : llvm::concat<BasicBlock *const>(L.blocks(), ExitBlocks))
    for (auto &VMap : VMaps)
      if (BasicBlock *ClonedBB = cast_or_null<BasicBlock>(VMap->lookup(BB)))
        if (!DT.isReachableFromEntry(ClonedBB)) {
          for (BasicBlock *SuccBB : successors(ClonedBB))
            SuccBB->removePredecessor(ClonedBB);
          DeadBlocks.push_back(ClonedBB);
        }

  // Remove all MemorySSA in the dead blocks
  if (MSSAU) {
    SmallSetVector<BasicBlock *, 8> DeadBlockSet(DeadBlocks.begin(),
                                                 DeadBlocks.end());
    MSSAU->removeBlocks(DeadBlockSet);
  }

  // Drop any remaining references to break cycles.
  for (BasicBlock *BB : DeadBlocks)
    BB->dropAllReferences();
  // Erase them from the IR.
  for (BasicBlock *BB : DeadBlocks)
    BB->eraseFromParent();
}

static void
deleteDeadBlocksFromLoop(Loop &L,
                         SmallVectorImpl<BasicBlock *> &ExitBlocks,
                         DominatorTree &DT, LoopInfo &LI,
                         MemorySSAUpdater *MSSAU,
                         function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
  // Find all the dead blocks tied to this loop, and remove them from their
  // successors.
  SmallSetVector<BasicBlock *, 8> DeadBlockSet;

  // Start with loop/exit blocks and get a transitive closure of reachable dead
  // blocks.
  SmallVector<BasicBlock *, 16> DeathCandidates(ExitBlocks.begin(),
                                                ExitBlocks.end());
  DeathCandidates.append(L.blocks().begin(), L.blocks().end());
  while (!DeathCandidates.empty()) {
    auto *BB = DeathCandidates.pop_back_val();
    if (!DeadBlockSet.count(BB) && !DT.isReachableFromEntry(BB)) {
      for (BasicBlock *SuccBB : successors(BB)) {
        SuccBB->removePredecessor(BB);
        DeathCandidates.push_back(SuccBB);
      }
      DeadBlockSet.insert(BB);
    }
  }

  // Remove all MemorySSA in the dead blocks
  if (MSSAU)
    MSSAU->removeBlocks(DeadBlockSet);

  // Filter out the dead blocks from the exit blocks list so that it can be
  // used in the caller.
  llvm::erase_if(ExitBlocks,
                 [&](BasicBlock *BB) { return DeadBlockSet.count(BB); });

  // Walk from this loop up through its parents removing all of the dead blocks.
  for (Loop *ParentL = &L; ParentL; ParentL = ParentL->getParentLoop()) {
    for (auto *BB : DeadBlockSet)
      ParentL->getBlocksSet().erase(BB);
    llvm::erase_if(ParentL->getBlocksVector(),
                   [&](BasicBlock *BB) { return DeadBlockSet.count(BB); });
  }

  // Now delete the dead child loops. This raw delete will clear them
  // recursively.
  llvm::erase_if(L.getSubLoopsVector(), [&](Loop *ChildL) {
    if (!DeadBlockSet.count(ChildL->getHeader()))
      return false;

    assert(llvm::all_of(ChildL->blocks(),
                        [&](BasicBlock *ChildBB) {
                          return DeadBlockSet.count(ChildBB);
                        }) &&
           "If the child loop header is dead all blocks in the child loop must "
           "be dead as well!");
    DestroyLoopCB(*ChildL, ChildL->getName());
    LI.destroy(ChildL);
    return true;
  });

  // Remove the loop mappings for the dead blocks and drop all the references
  // from these blocks to others to handle cyclic references as we start
  // deleting the blocks themselves.
  for (auto *BB : DeadBlockSet) {
    // Check that the dominator tree has already been updated.
    assert(!DT.getNode(BB) && "Should already have cleared domtree!");
    LI.changeLoopFor(BB, nullptr);
    // Drop all uses of the instructions to make sure we won't have dangling
    // uses in other blocks.
    for (auto &I : *BB)
      if (!I.use_empty())
        I.replaceAllUsesWith(UndefValue::get(I.getType()));
    BB->dropAllReferences();
  }

  // Actually delete the blocks now that they've been fully unhooked from the
  // IR.
  for (auto *BB : DeadBlockSet)
    BB->eraseFromParent();
}

/// Recompute the set of blocks in a loop after unswitching.
///
/// This walks from the original headers predecessors to rebuild the loop. We
/// take advantage of the fact that new blocks can't have been added, and so we
/// filter by the original loop's blocks. This also handles potentially
/// unreachable code that we don't want to explore but might be found examining
/// the predecessors of the header.
///
/// If the original loop is no longer a loop, this will return an empty set. If
/// it remains a loop, all the blocks within it will be added to the set
/// (including those blocks in inner loops).
static SmallPtrSet<const BasicBlock *, 16> recomputeLoopBlockSet(Loop &L,
                                                                 LoopInfo &LI) {
  SmallPtrSet<const BasicBlock *, 16> LoopBlockSet;

  auto *PH = L.getLoopPreheader();
  auto *Header = L.getHeader();

  // A worklist to use while walking backwards from the header.
  SmallVector<BasicBlock *, 16> Worklist;

  // First walk the predecessors of the header to find the backedges. This will
  // form the basis of our walk.
  for (auto *Pred : predecessors(Header)) {
    // Skip the preheader.
    if (Pred == PH)
      continue;

    // Because the loop was in simplified form, the only non-loop predecessor
    // is the preheader.
    assert(L.contains(Pred) && "Found a predecessor of the loop header other "
                               "than the preheader that is not part of the "
                               "loop!");

    // Insert this block into the loop set and on the first visit and, if it
    // isn't the header we're currently walking, put it into the worklist to
    // recurse through.
    if (LoopBlockSet.insert(Pred).second && Pred != Header)
      Worklist.push_back(Pred);
  }

  // If no backedges were found, we're done.
  if (LoopBlockSet.empty())
    return LoopBlockSet;

  // We found backedges, recurse through them to identify the loop blocks.
  while (!Worklist.empty()) {
    BasicBlock *BB = Worklist.pop_back_val();
    assert(LoopBlockSet.count(BB) && "Didn't put block into the loop set!");

    // No need to walk past the header.
    if (BB == Header)
      continue;

    // Because we know the inner loop structure remains valid we can use the
    // loop structure to jump immediately across the entire nested loop.
    // Further, because it is in loop simplified form, we can directly jump
    // to its preheader afterward.
    if (Loop *InnerL = LI.getLoopFor(BB))
      if (InnerL != &L) {
        assert(L.contains(InnerL) &&
               "Should not reach a loop *outside* this loop!");
        // The preheader is the only possible predecessor of the loop so
        // insert it into the set and check whether it was already handled.
        auto *InnerPH = InnerL->getLoopPreheader();
        assert(L.contains(InnerPH) && "Cannot contain an inner loop block "
                                      "but not contain the inner loop "
                                      "preheader!");
        if (!LoopBlockSet.insert(InnerPH).second)
          // The only way to reach the preheader is through the loop body
          // itself so if it has been visited the loop is already handled.
          continue;

        // Insert all of the blocks (other than those already present) into
        // the loop set. We expect at least the block that led us to find the
        // inner loop to be in the block set, but we may also have other loop
        // blocks if they were already enqueued as predecessors of some other
        // outer loop block.
        for (auto *InnerBB : InnerL->blocks()) {
          if (InnerBB == BB) {
            assert(LoopBlockSet.count(InnerBB) &&
                   "Block should already be in the set!");
            continue;
          }

          LoopBlockSet.insert(InnerBB);
        }

        // Add the preheader to the worklist so we will continue past the
        // loop body.
        Worklist.push_back(InnerPH);
        continue;
      }

    // Insert any predecessors that were in the original loop into the new
    // set, and if the insert is successful, add them to the worklist.
    for (auto *Pred : predecessors(BB))
      if (L.contains(Pred) && LoopBlockSet.insert(Pred).second)
        Worklist.push_back(Pred);
  }

  assert(LoopBlockSet.count(Header) && "Cannot fail to add the header!");

  // We've found all the blocks participating in the loop, return our completed
  // set.
  return LoopBlockSet;
}

/// Rebuild a loop after unswitching removes some subset of blocks and edges.
///
/// The removal may have removed some child loops entirely but cannot have
/// disturbed any remaining child loops. However, they may need to be hoisted
/// to the parent loop (or to be top-level loops). The original loop may be
/// completely removed.
///
/// The sibling loops resulting from this update are returned. If the original
/// loop remains a valid loop, it will be the first entry in this list with all
/// of the newly sibling loops following it.
///
/// Returns true if the loop remains a loop after unswitching, and false if it
/// is no longer a loop after unswitching (and should not continue to be
/// referenced).
static bool rebuildLoopAfterUnswitch(Loop &L, ArrayRef<BasicBlock *> ExitBlocks,
                                     LoopInfo &LI,
                                     SmallVectorImpl<Loop *> &HoistedLoops) {
  auto *PH = L.getLoopPreheader();

  // Compute the actual parent loop from the exit blocks. Because we may have
  // pruned some exits the loop may be different from the original parent.
  Loop *ParentL = nullptr;
  SmallVector<Loop *, 4> ExitLoops;
  SmallVector<BasicBlock *, 4> ExitsInLoops;
  ExitsInLoops.reserve(ExitBlocks.size());
  for (auto *ExitBB : ExitBlocks)
    if (Loop *ExitL = LI.getLoopFor(ExitBB)) {
      ExitLoops.push_back(ExitL);
      ExitsInLoops.push_back(ExitBB);
      if (!ParentL || (ParentL != ExitL && ParentL->contains(ExitL)))
        ParentL = ExitL;
    }

  // Recompute the blocks participating in this loop. This may be empty if it
  // is no longer a loop.
  auto LoopBlockSet = recomputeLoopBlockSet(L, LI);

  // If we still have a loop, we need to re-set the loop's parent as the exit
  // block set changing may have moved it within the loop nest. Note that this
  // can only happen when this loop has a parent as it can only hoist the loop
  // *up* the nest.
  if (!LoopBlockSet.empty() && L.getParentLoop() != ParentL) {
    // Remove this loop's (original) blocks from all of the intervening loops.
    for (Loop *IL = L.getParentLoop(); IL != ParentL;
         IL = IL->getParentLoop()) {
      IL->getBlocksSet().erase(PH);
      for (auto *BB : L.blocks())
        IL->getBlocksSet().erase(BB);
      llvm::erase_if(IL->getBlocksVector(), [&](BasicBlock *BB) {
        return BB == PH || L.contains(BB);
      });
    }

    LI.changeLoopFor(PH, ParentL);
    L.getParentLoop()->removeChildLoop(&L);
    if (ParentL)
      ParentL->addChildLoop(&L);
    else
      LI.addTopLevelLoop(&L);
  }

  // Now we update all the blocks which are no longer within the loop.
  auto &Blocks = L.getBlocksVector();
  auto BlocksSplitI =
      LoopBlockSet.empty()
          ? Blocks.begin()
          : std::stable_partition(
                Blocks.begin(), Blocks.end(),
                [&](BasicBlock *BB) { return LoopBlockSet.count(BB); });

  // Before we erase the list of unlooped blocks, build a set of them.
  SmallPtrSet<BasicBlock *, 16> UnloopedBlocks(BlocksSplitI, Blocks.end());
  if (LoopBlockSet.empty())
    UnloopedBlocks.insert(PH);

  // Now erase these blocks from the loop.
  for (auto *BB : make_range(BlocksSplitI, Blocks.end()))
    L.getBlocksSet().erase(BB);
  Blocks.erase(BlocksSplitI, Blocks.end());

  // Sort the exits in ascending loop depth, we'll work backwards across these
  // to process them inside out.
  llvm::stable_sort(ExitsInLoops, [&](BasicBlock *LHS, BasicBlock *RHS) {
    return LI.getLoopDepth(LHS) < LI.getLoopDepth(RHS);
  });

  // We'll build up a set for each exit loop.
  SmallPtrSet<BasicBlock *, 16> NewExitLoopBlocks;
  Loop *PrevExitL = L.getParentLoop(); // The deepest possible exit loop.

  auto RemoveUnloopedBlocksFromLoop =
      [](Loop &L, SmallPtrSetImpl<BasicBlock *> &UnloopedBlocks) {
        for (auto *BB : UnloopedBlocks)
          L.getBlocksSet().erase(BB);
        llvm::erase_if(L.getBlocksVector(), [&](BasicBlock *BB) {
          return UnloopedBlocks.count(BB);
        });
      };

  SmallVector<BasicBlock *, 16> Worklist;
  while (!UnloopedBlocks.empty() && !ExitsInLoops.empty()) {
    assert(Worklist.empty() && "Didn't clear worklist!");
    assert(NewExitLoopBlocks.empty() && "Didn't clear loop set!");

    // Grab the next exit block, in decreasing loop depth order.
    BasicBlock *ExitBB = ExitsInLoops.pop_back_val();
    Loop &ExitL = *LI.getLoopFor(ExitBB);
    assert(ExitL.contains(&L) && "Exit loop must contain the inner loop!");

    // Erase all of the unlooped blocks from the loops between the previous
    // exit loop and this exit loop. This works because the ExitInLoops list is
    // sorted in increasing order of loop depth and thus we visit loops in
    // decreasing order of loop depth.
    for (; PrevExitL != &ExitL; PrevExitL = PrevExitL->getParentLoop())
      RemoveUnloopedBlocksFromLoop(*PrevExitL, UnloopedBlocks);

    // Walk the CFG back until we hit the cloned PH adding everything reachable
    // and in the unlooped set to this exit block's loop.
    Worklist.push_back(ExitBB);
    do {
      BasicBlock *BB = Worklist.pop_back_val();
      // We can stop recursing at the cloned preheader (if we get there).
      if (BB == PH)
        continue;

      for (BasicBlock *PredBB : predecessors(BB)) {
        // If this pred has already been moved to our set or is part of some
        // (inner) loop, no update needed.
        if (!UnloopedBlocks.erase(PredBB)) {
          assert((NewExitLoopBlocks.count(PredBB) ||
                  ExitL.contains(LI.getLoopFor(PredBB))) &&
                 "Predecessor not in a nested loop (or already visited)!");
          continue;
        }

        // We just insert into the loop set here. We'll add these blocks to the
        // exit loop after we build up the set in a deterministic order rather
        // than the predecessor-influenced visit order.
        bool Inserted = NewExitLoopBlocks.insert(PredBB).second;
        (void)Inserted;
        assert(Inserted && "Should only visit an unlooped block once!");

        // And recurse through to its predecessors.
        Worklist.push_back(PredBB);
      }
    } while (!Worklist.empty());

    // If blocks in this exit loop were directly part of the original loop (as
    // opposed to a child loop) update the map to point to this exit loop. This
    // just updates a map and so the fact that the order is unstable is fine.
    for (auto *BB : NewExitLoopBlocks)
      if (Loop *BBL = LI.getLoopFor(BB))
        if (BBL == &L || !L.contains(BBL))
          LI.changeLoopFor(BB, &ExitL);

    // We will remove the remaining unlooped blocks from this loop in the next
    // iteration or below.
    NewExitLoopBlocks.clear();
  }

  // Any remaining unlooped blocks are no longer part of any loop unless they
  // are part of some child loop.
  for (; PrevExitL; PrevExitL = PrevExitL->getParentLoop())
    RemoveUnloopedBlocksFromLoop(*PrevExitL, UnloopedBlocks);
  for (auto *BB : UnloopedBlocks)
    if (Loop *BBL = LI.getLoopFor(BB))
      if (BBL == &L || !L.contains(BBL))
        LI.changeLoopFor(BB, nullptr);

  // Sink all the child loops whose headers are no longer in the loop set to
  // the parent (or to be top level loops). We reach into the loop and directly
  // update its subloop vector to make this batch update efficient.
  auto &SubLoops = L.getSubLoopsVector();
  auto SubLoopsSplitI =
      LoopBlockSet.empty()
          ? SubLoops.begin()
          : std::stable_partition(
                SubLoops.begin(), SubLoops.end(), [&](Loop *SubL) {
                  return LoopBlockSet.count(SubL->getHeader());
                });
  for (auto *HoistedL : make_range(SubLoopsSplitI, SubLoops.end())) {
    HoistedLoops.push_back(HoistedL);
    HoistedL->setParentLoop(nullptr);

    // To compute the new parent of this hoisted loop we look at where we
    // placed the preheader above. We can't lookup the header itself because we
    // retained the mapping from the header to the hoisted loop. But the
    // preheader and header should have the exact same new parent computed
    // based on the set of exit blocks from the original loop as the preheader
    // is a predecessor of the header and so reached in the reverse walk. And
    // because the loops were all in simplified form the preheader of the
    // hoisted loop can't be part of some *other* loop.
    if (auto *NewParentL = LI.getLoopFor(HoistedL->getLoopPreheader()))
      NewParentL->addChildLoop(HoistedL);
    else
      LI.addTopLevelLoop(HoistedL);
  }
  SubLoops.erase(SubLoopsSplitI, SubLoops.end());

  // Actually delete the loop if nothing remained within it.
  if (Blocks.empty()) {
    assert(SubLoops.empty() &&
           "Failed to remove all subloops from the original loop!");
    if (Loop *ParentL = L.getParentLoop())
      ParentL->removeChildLoop(llvm::find(*ParentL, &L));
    else
      LI.removeLoop(llvm::find(LI, &L));
    // markLoopAsDeleted for L should be triggered by the caller (it is typically
    // done by using the UnswitchCB callback).
    LI.destroy(&L);
    return false;
  }

  return true;
}

/// Helper to visit a dominator subtree, invoking a callable on each node.
///
/// Returning false at any point will stop walking past that node of the tree.
template <typename CallableT>
void visitDomSubTree(DominatorTree &DT, BasicBlock *BB, CallableT Callable) {
  SmallVector<DomTreeNode *, 4> DomWorklist;
  DomWorklist.push_back(DT[BB]);
#ifndef NDEBUG
  SmallPtrSet<DomTreeNode *, 4> Visited;
  Visited.insert(DT[BB]);
#endif
  do {
    DomTreeNode *N = DomWorklist.pop_back_val();

    // Visit this node.
    if (!Callable(N->getBlock()))
      continue;

    // Accumulate the child nodes.
    for (DomTreeNode *ChildN : *N) {
      assert(Visited.insert(ChildN).second &&
             "Cannot visit a node twice when walking a tree!");
      DomWorklist.push_back(ChildN);
    }
  } while (!DomWorklist.empty());
}

static void unswitchNontrivialInvariants(
    Loop &L, Instruction &TI, ArrayRef<Value *> Invariants,
    SmallVectorImpl<BasicBlock *> &ExitBlocks, IVConditionInfo &PartialIVInfo,
    DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
    function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
    ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
    function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
  auto *ParentBB = TI.getParent();
  BranchInst *BI = dyn_cast<BranchInst>(&TI);
  SwitchInst *SI = BI ? nullptr : cast<SwitchInst>(&TI);

  // We can only unswitch switches, conditional branches with an invariant
  // condition, or combining invariant conditions with an instruction or
  // partially invariant instructions.
  assert((SI || (BI && BI->isConditional())) &&
         "Can only unswitch switches and conditional branch!");
  bool PartiallyInvariant = !PartialIVInfo.InstToDuplicate.empty();
  bool FullUnswitch =
      SI || (BI->getCondition() == Invariants[0] && !PartiallyInvariant);
  if (FullUnswitch)
    assert(Invariants.size() == 1 &&
           "Cannot have other invariants with full unswitching!");
  else
    assert(isa<Instruction>(BI->getCondition()) &&
           "Partial unswitching requires an instruction as the condition!");

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // Constant and BBs tracking the cloned and continuing successor. When we are
  // unswitching the entire condition, this can just be trivially chosen to
  // unswitch towards `true`. However, when we are unswitching a set of
  // invariants combined with `and` or `or` or partially invariant instructions,
  // the combining operation determines the best direction to unswitch: we want
  // to unswitch the direction that will collapse the branch.
  bool Direction = true;
  int ClonedSucc = 0;
  if (!FullUnswitch) {
    Value *Cond = BI->getCondition();
    (void)Cond;
    assert(((match(Cond, m_LogicalAnd()) ^ match(Cond, m_LogicalOr())) ||
            PartiallyInvariant) &&
           "Only `or`, `and`, an `select`, partially invariant instructions "
           "can combine invariants being unswitched.");
    if (!match(BI->getCondition(), m_LogicalOr())) {
      if (match(BI->getCondition(), m_LogicalAnd()) ||
          (PartiallyInvariant && !PartialIVInfo.KnownValue->isOneValue())) {
        Direction = false;
        ClonedSucc = 1;
      }
    }
  }

  BasicBlock *RetainedSuccBB =
      BI ? BI->getSuccessor(1 - ClonedSucc) : SI->getDefaultDest();
  SmallSetVector<BasicBlock *, 4> UnswitchedSuccBBs;
  if (BI)
    UnswitchedSuccBBs.insert(BI->getSuccessor(ClonedSucc));
  else
    for (auto Case : SI->cases())
      if (Case.getCaseSuccessor() != RetainedSuccBB)
        UnswitchedSuccBBs.insert(Case.getCaseSuccessor());

  assert(!UnswitchedSuccBBs.count(RetainedSuccBB) &&
         "Should not unswitch the same successor we are retaining!");

  // The branch should be in this exact loop. Any inner loop's invariant branch
  // should be handled by unswitching that inner loop. The caller of this
  // routine should filter out any candidates that remain (but were skipped for
  // whatever reason).
  assert(LI.getLoopFor(ParentBB) == &L && "Branch in an inner loop!");

  // Compute the parent loop now before we start hacking on things.
  Loop *ParentL = L.getParentLoop();
  // Get blocks in RPO order for MSSA update, before changing the CFG.
  LoopBlocksRPO LBRPO(&L);
  if (MSSAU)
    LBRPO.perform(&LI);

  // Compute the outer-most loop containing one of our exit blocks. This is the
  // furthest up our loopnest which can be mutated, which we will use below to
  // update things.
  Loop *OuterExitL = &L;
  for (auto *ExitBB : ExitBlocks) {
    Loop *NewOuterExitL = LI.getLoopFor(ExitBB);
    if (!NewOuterExitL) {
      // We exited the entire nest with this block, so we're done.
      OuterExitL = nullptr;
      break;
    }
    if (NewOuterExitL != OuterExitL && NewOuterExitL->contains(OuterExitL))
      OuterExitL = NewOuterExitL;
  }

  // At this point, we're definitely going to unswitch something so invalidate
  // any cached information in ScalarEvolution for the outer most loop
  // containing an exit block and all nested loops.
  if (SE) {
    if (OuterExitL)
      SE->forgetLoop(OuterExitL);
    else
      SE->forgetTopmostLoop(&L);
  }

  bool InsertFreeze = false;
  if (FreezeLoopUnswitchCond) {
    ICFLoopSafetyInfo SafetyInfo;
    SafetyInfo.computeLoopSafetyInfo(&L);
    InsertFreeze = !SafetyInfo.isGuaranteedToExecute(TI, &DT, &L);
  }

  // If the edge from this terminator to a successor dominates that successor,
  // store a map from each block in its dominator subtree to it. This lets us
  // tell when cloning for a particular successor if a block is dominated by
  // some *other* successor with a single data structure. We use this to
  // significantly reduce cloning.
  SmallDenseMap<BasicBlock *, BasicBlock *, 16> DominatingSucc;
  for (auto *SuccBB : llvm::concat<BasicBlock *const>(
           makeArrayRef(RetainedSuccBB), UnswitchedSuccBBs))
    if (SuccBB->getUniquePredecessor() ||
        llvm::all_of(predecessors(SuccBB), [&](BasicBlock *PredBB) {
          return PredBB == ParentBB || DT.dominates(SuccBB, PredBB);
        }))
      visitDomSubTree(DT, SuccBB, [&](BasicBlock *BB) {
        DominatingSucc[BB] = SuccBB;
        return true;
      });

  // Split the preheader, so that we know that there is a safe place to insert
  // the conditional branch. We will change the preheader to have a conditional
  // branch on LoopCond. The original preheader will become the split point
  // between the unswitched versions, and we will have a new preheader for the
  // original loop.
  BasicBlock *SplitBB = L.getLoopPreheader();
  BasicBlock *LoopPH = SplitEdge(SplitBB, L.getHeader(), &DT, &LI, MSSAU);

  // Keep track of the dominator tree updates needed.
  SmallVector<DominatorTree::UpdateType, 4> DTUpdates;

  // Clone the loop for each unswitched successor.
  SmallVector<std::unique_ptr<ValueToValueMapTy>, 4> VMaps;
  VMaps.reserve(UnswitchedSuccBBs.size());
  SmallDenseMap<BasicBlock *, BasicBlock *, 4> ClonedPHs;
  for (auto *SuccBB : UnswitchedSuccBBs) {
    VMaps.emplace_back(new ValueToValueMapTy());
    ClonedPHs[SuccBB] = buildClonedLoopBlocks(
        L, LoopPH, SplitBB, ExitBlocks, ParentBB, SuccBB, RetainedSuccBB,
        DominatingSucc, *VMaps.back(), DTUpdates, AC, DT, LI, MSSAU);
  }

  // Drop metadata if we may break its semantics by moving this instr into the
  // split block.
  if (TI.getMetadata(LLVMContext::MD_make_implicit)) {
    if (DropNonTrivialImplicitNullChecks)
      // Do not spend time trying to understand if we can keep it, just drop it
      // to save compile time.
      TI.setMetadata(LLVMContext::MD_make_implicit, nullptr);
    else {
      // It is only legal to preserve make.implicit metadata if we are
      // guaranteed no reach implicit null check after following this branch.
      ICFLoopSafetyInfo SafetyInfo;
      SafetyInfo.computeLoopSafetyInfo(&L);
      if (!SafetyInfo.isGuaranteedToExecute(TI, &DT, &L))
        TI.setMetadata(LLVMContext::MD_make_implicit, nullptr);
    }
  }

  // The stitching of the branched code back together depends on whether we're
  // doing full unswitching or not with the exception that we always want to
  // nuke the initial terminator placed in the split block.
  SplitBB->getTerminator()->eraseFromParent();
  if (FullUnswitch) {
    // Splice the terminator from the original loop and rewrite its
    // successors.
    SplitBB->getInstList().splice(SplitBB->end(), ParentBB->getInstList(), TI);

    // Keep a clone of the terminator for MSSA updates.
    Instruction *NewTI = TI.clone();
    ParentBB->getInstList().push_back(NewTI);

    // First wire up the moved terminator to the preheaders.
    if (BI) {
      BasicBlock *ClonedPH = ClonedPHs.begin()->second;
      BI->setSuccessor(ClonedSucc, ClonedPH);
      BI->setSuccessor(1 - ClonedSucc, LoopPH);
      if (InsertFreeze) {
        auto Cond = BI->getCondition();
        if (!isGuaranteedNotToBeUndefOrPoison(Cond, &AC, BI, &DT))
          BI->setCondition(new FreezeInst(Cond, Cond->getName() + ".fr", BI));
      }
      DTUpdates.push_back({DominatorTree::Insert, SplitBB, ClonedPH});
    } else {
      assert(SI && "Must either be a branch or switch!");

      // Walk the cases and directly update their successors.
      assert(SI->getDefaultDest() == RetainedSuccBB &&
             "Not retaining default successor!");
      SI->setDefaultDest(LoopPH);
      for (auto &Case : SI->cases())
        if (Case.getCaseSuccessor() == RetainedSuccBB)
          Case.setSuccessor(LoopPH);
        else
          Case.setSuccessor(ClonedPHs.find(Case.getCaseSuccessor())->second);

      if (InsertFreeze) {
        auto Cond = SI->getCondition();
        if (!isGuaranteedNotToBeUndefOrPoison(Cond, &AC, SI, &DT))
          SI->setCondition(new FreezeInst(Cond, Cond->getName() + ".fr", SI));
      }
      // We need to use the set to populate domtree updates as even when there
      // are multiple cases pointing at the same successor we only want to
      // remove and insert one edge in the domtree.
      for (BasicBlock *SuccBB : UnswitchedSuccBBs)
        DTUpdates.push_back(
            {DominatorTree::Insert, SplitBB, ClonedPHs.find(SuccBB)->second});
    }

    if (MSSAU) {
      DT.applyUpdates(DTUpdates);
      DTUpdates.clear();

      // Remove all but one edge to the retained block and all unswitched
      // blocks. This is to avoid having duplicate entries in the cloned Phis,
      // when we know we only keep a single edge for each case.
      MSSAU->removeDuplicatePhiEdgesBetween(ParentBB, RetainedSuccBB);
      for (BasicBlock *SuccBB : UnswitchedSuccBBs)
        MSSAU->removeDuplicatePhiEdgesBetween(ParentBB, SuccBB);

      for (auto &VMap : VMaps)
        MSSAU->updateForClonedLoop(LBRPO, ExitBlocks, *VMap,
                                   /*IgnoreIncomingWithNoClones=*/true);
      MSSAU->updateExitBlocksForClonedLoop(ExitBlocks, VMaps, DT);

      // Remove all edges to unswitched blocks.
      for (BasicBlock *SuccBB : UnswitchedSuccBBs)
        MSSAU->removeEdge(ParentBB, SuccBB);
    }

    // Now unhook the successor relationship as we'll be replacing
    // the terminator with a direct branch. This is much simpler for branches
    // than switches so we handle those first.
    if (BI) {
      // Remove the parent as a predecessor of the unswitched successor.
      assert(UnswitchedSuccBBs.size() == 1 &&
             "Only one possible unswitched block for a branch!");
      BasicBlock *UnswitchedSuccBB = *UnswitchedSuccBBs.begin();
      UnswitchedSuccBB->removePredecessor(ParentBB,
                                          /*KeepOneInputPHIs*/ true);
      DTUpdates.push_back({DominatorTree::Delete, ParentBB, UnswitchedSuccBB});
    } else {
      // Note that we actually want to remove the parent block as a predecessor
      // of *every* case successor. The case successor is either unswitched,
      // completely eliminating an edge from the parent to that successor, or it
      // is a duplicate edge to the retained successor as the retained successor
      // is always the default successor and as we'll replace this with a direct
      // branch we no longer need the duplicate entries in the PHI nodes.
      SwitchInst *NewSI = cast<SwitchInst>(NewTI);
      assert(NewSI->getDefaultDest() == RetainedSuccBB &&
             "Not retaining default successor!");
      for (auto &Case : NewSI->cases())
        Case.getCaseSuccessor()->removePredecessor(
            ParentBB,
            /*KeepOneInputPHIs*/ true);

      // We need to use the set to populate domtree updates as even when there
      // are multiple cases pointing at the same successor we only want to
      // remove and insert one edge in the domtree.
      for (BasicBlock *SuccBB : UnswitchedSuccBBs)
        DTUpdates.push_back({DominatorTree::Delete, ParentBB, SuccBB});
    }

    // After MSSAU update, remove the cloned terminator instruction NewTI.
    ParentBB->getTerminator()->eraseFromParent();

    // Create a new unconditional branch to the continuing block (as opposed to
    // the one cloned).
    BranchInst::Create(RetainedSuccBB, ParentBB);
  } else {
    assert(BI && "Only branches have partial unswitching.");
    assert(UnswitchedSuccBBs.size() == 1 &&
           "Only one possible unswitched block for a branch!");
    BasicBlock *ClonedPH = ClonedPHs.begin()->second;
    // When doing a partial unswitch, we have to do a bit more work to build up
    // the branch in the split block.
    if (PartiallyInvariant)
      buildPartialInvariantUnswitchConditionalBranch(
          *SplitBB, Invariants, Direction, *ClonedPH, *LoopPH, L, MSSAU);
    else
      buildPartialUnswitchConditionalBranch(*SplitBB, Invariants, Direction,
                                            *ClonedPH, *LoopPH, InsertFreeze);
    DTUpdates.push_back({DominatorTree::Insert, SplitBB, ClonedPH});

    if (MSSAU) {
      DT.applyUpdates(DTUpdates);
      DTUpdates.clear();

      // Perform MSSA cloning updates.
      for (auto &VMap : VMaps)
        MSSAU->updateForClonedLoop(LBRPO, ExitBlocks, *VMap,
                                   /*IgnoreIncomingWithNoClones=*/true);
      MSSAU->updateExitBlocksForClonedLoop(ExitBlocks, VMaps, DT);
    }
  }

  // Apply the updates accumulated above to get an up-to-date dominator tree.
  DT.applyUpdates(DTUpdates);

  // Now that we have an accurate dominator tree, first delete the dead cloned
  // blocks so that we can accurately build any cloned loops. It is important to
  // not delete the blocks from the original loop yet because we still want to
  // reference the original loop to understand the cloned loop's structure.
  deleteDeadClonedBlocks(L, ExitBlocks, VMaps, DT, MSSAU);

  // Build the cloned loop structure itself. This may be substantially
  // different from the original structure due to the simplified CFG. This also
  // handles inserting all the cloned blocks into the correct loops.
  SmallVector<Loop *, 4> NonChildClonedLoops;
  for (std::unique_ptr<ValueToValueMapTy> &VMap : VMaps)
    buildClonedLoops(L, ExitBlocks, *VMap, LI, NonChildClonedLoops);

  // Now that our cloned loops have been built, we can update the original loop.
  // First we delete the dead blocks from it and then we rebuild the loop
  // structure taking these deletions into account.
  deleteDeadBlocksFromLoop(L, ExitBlocks, DT, LI, MSSAU, DestroyLoopCB);

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  SmallVector<Loop *, 4> HoistedLoops;
  bool IsStillLoop = rebuildLoopAfterUnswitch(L, ExitBlocks, LI, HoistedLoops);

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  // This transformation has a high risk of corrupting the dominator tree, and
  // the below steps to rebuild loop structures will result in hard to debug
  // errors in that case so verify that the dominator tree is sane first.
  // FIXME: Remove this when the bugs stop showing up and rely on existing
  // verification steps.
  assert(DT.verify(DominatorTree::VerificationLevel::Fast));

  if (BI && !PartiallyInvariant) {
    // If we unswitched a branch which collapses the condition to a known
    // constant we want to replace all the uses of the invariants within both
    // the original and cloned blocks. We do this here so that we can use the
    // now updated dominator tree to identify which side the users are on.
    assert(UnswitchedSuccBBs.size() == 1 &&
           "Only one possible unswitched block for a branch!");
    BasicBlock *ClonedPH = ClonedPHs.begin()->second;

    // When considering multiple partially-unswitched invariants
    // we cant just go replace them with constants in both branches.
    //
    // For 'AND' we infer that true branch ("continue") means true
    // for each invariant operand.
    // For 'OR' we can infer that false branch ("continue") means false
    // for each invariant operand.
    // So it happens that for multiple-partial case we dont replace
    // in the unswitched branch.
    bool ReplaceUnswitched =
        FullUnswitch || (Invariants.size() == 1) || PartiallyInvariant;

    ConstantInt *UnswitchedReplacement =
        Direction ? ConstantInt::getTrue(BI->getContext())
                  : ConstantInt::getFalse(BI->getContext());
    ConstantInt *ContinueReplacement =
        Direction ? ConstantInt::getFalse(BI->getContext())
                  : ConstantInt::getTrue(BI->getContext());
    for (Value *Invariant : Invariants) {
      assert(!isa<Constant>(Invariant) &&
             "Should not be replacing constant values!");
      // Use make_early_inc_range here as set invalidates the iterator.
      for (Use &U : llvm::make_early_inc_range(Invariant->uses())) {
        Instruction *UserI = dyn_cast<Instruction>(U.getUser());
        if (!UserI)
          continue;

        // Replace it with the 'continue' side if in the main loop body, and the
        // unswitched if in the cloned blocks.
        if (DT.dominates(LoopPH, UserI->getParent()))
          U.set(ContinueReplacement);
        else if (ReplaceUnswitched &&
                 DT.dominates(ClonedPH, UserI->getParent()))
          U.set(UnswitchedReplacement);
      }
    }
  }

  // We can change which blocks are exit blocks of all the cloned sibling
  // loops, the current loop, and any parent loops which shared exit blocks
  // with the current loop. As a consequence, we need to re-form LCSSA for
  // them. But we shouldn't need to re-form LCSSA for any child loops.
  // FIXME: This could be made more efficient by tracking which exit blocks are
  // new, and focusing on them, but that isn't likely to be necessary.
  //
  // In order to reasonably rebuild LCSSA we need to walk inside-out across the
  // loop nest and update every loop that could have had its exits changed. We
  // also need to cover any intervening loops. We add all of these loops to
  // a list and sort them by loop depth to achieve this without updating
  // unnecessary loops.
  auto UpdateLoop = [&](Loop &UpdateL) {
#ifndef NDEBUG
    UpdateL.verifyLoop();
    for (Loop *ChildL : UpdateL) {
      ChildL->verifyLoop();
      assert(ChildL->isRecursivelyLCSSAForm(DT, LI) &&
             "Perturbed a child loop's LCSSA form!");
    }
#endif
    // First build LCSSA for this loop so that we can preserve it when
    // forming dedicated exits. We don't want to perturb some other loop's
    // LCSSA while doing that CFG edit.
    formLCSSA(UpdateL, DT, &LI, SE);

    // For loops reached by this loop's original exit blocks we may
    // introduced new, non-dedicated exits. At least try to re-form dedicated
    // exits for these loops. This may fail if they couldn't have dedicated
    // exits to start with.
    formDedicatedExitBlocks(&UpdateL, &DT, &LI, MSSAU, /*PreserveLCSSA*/ true);
  };

  // For non-child cloned loops and hoisted loops, we just need to update LCSSA
  // and we can do it in any order as they don't nest relative to each other.
  //
  // Also check if any of the loops we have updated have become top-level loops
  // as that will necessitate widening the outer loop scope.
  for (Loop *UpdatedL :
       llvm::concat<Loop *>(NonChildClonedLoops, HoistedLoops)) {
    UpdateLoop(*UpdatedL);
    if (UpdatedL->isOutermost())
      OuterExitL = nullptr;
  }
  if (IsStillLoop) {
    UpdateLoop(L);
    if (L.isOutermost())
      OuterExitL = nullptr;
  }

  // If the original loop had exit blocks, walk up through the outer most loop
  // of those exit blocks to update LCSSA and form updated dedicated exits.
  if (OuterExitL != &L)
    for (Loop *OuterL = ParentL; OuterL != OuterExitL;
         OuterL = OuterL->getParentLoop())
      UpdateLoop(*OuterL);

#ifndef NDEBUG
  // Verify the entire loop structure to catch any incorrect updates before we
  // progress in the pass pipeline.
  LI.verify(DT);
#endif

  // Now that we've unswitched something, make callbacks to report the changes.
  // For that we need to merge together the updated loops and the cloned loops
  // and check whether the original loop survived.
  SmallVector<Loop *, 4> SibLoops;
  for (Loop *UpdatedL : llvm::concat<Loop *>(NonChildClonedLoops, HoistedLoops))
    if (UpdatedL->getParentLoop() == ParentL)
      SibLoops.push_back(UpdatedL);
  UnswitchCB(IsStillLoop, PartiallyInvariant, SibLoops);

  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();

  if (BI)
    ++NumBranches;
  else
    ++NumSwitches;
}

/// Recursively compute the cost of a dominator subtree based on the per-block
/// cost map provided.
///
/// The recursive computation is memozied into the provided DT-indexed cost map
/// to allow querying it for most nodes in the domtree without it becoming
/// quadratic.
static InstructionCost computeDomSubtreeCost(
    DomTreeNode &N,
    const SmallDenseMap<BasicBlock *, InstructionCost, 4> &BBCostMap,
    SmallDenseMap<DomTreeNode *, InstructionCost, 4> &DTCostMap) {
  // Don't accumulate cost (or recurse through) blocks not in our block cost
  // map and thus not part of the duplication cost being considered.
  auto BBCostIt = BBCostMap.find(N.getBlock());
  if (BBCostIt == BBCostMap.end())
    return 0;

  // Lookup this node to see if we already computed its cost.
  auto DTCostIt = DTCostMap.find(&N);
  if (DTCostIt != DTCostMap.end())
    return DTCostIt->second;

  // If not, we have to compute it. We can't use insert above and update
  // because computing the cost may insert more things into the map.
  InstructionCost Cost = std::accumulate(
      N.begin(), N.end(), BBCostIt->second,
      [&](InstructionCost Sum, DomTreeNode *ChildN) -> InstructionCost {
        return Sum + computeDomSubtreeCost(*ChildN, BBCostMap, DTCostMap);
      });
  bool Inserted = DTCostMap.insert({&N, Cost}).second;
  (void)Inserted;
  assert(Inserted && "Should not insert a node while visiting children!");
  return Cost;
}

/// Turns a llvm.experimental.guard intrinsic into implicit control flow branch,
/// making the following replacement:
///
///   --code before guard--
///   call void (i1, ...) @llvm.experimental.guard(i1 %cond) [ "deopt"() ]
///   --code after guard--
///
/// into
///
///   --code before guard--
///   br i1 %cond, label %guarded, label %deopt
///
/// guarded:
///   --code after guard--
///
/// deopt:
///   call void (i1, ...) @llvm.experimental.guard(i1 false) [ "deopt"() ]
///   unreachable
///
/// It also makes all relevant DT and LI updates, so that all structures are in
/// valid state after this transform.
static BranchInst *
turnGuardIntoBranch(IntrinsicInst *GI, Loop &L,
                    SmallVectorImpl<BasicBlock *> &ExitBlocks,
                    DominatorTree &DT, LoopInfo &LI, MemorySSAUpdater *MSSAU) {
  SmallVector<DominatorTree::UpdateType, 4> DTUpdates;
  LLVM_DEBUG(dbgs() << "Turning " << *GI << " into a branch.\n");
  BasicBlock *CheckBB = GI->getParent();

  if (MSSAU && VerifyMemorySSA)
     MSSAU->getMemorySSA()->verifyMemorySSA();

  // Remove all CheckBB's successors from DomTree. A block can be seen among
  // successors more than once, but for DomTree it should be added only once.
  SmallPtrSet<BasicBlock *, 4> Successors;
  for (auto *Succ : successors(CheckBB))
    if (Successors.insert(Succ).second)
      DTUpdates.push_back({DominatorTree::Delete, CheckBB, Succ});

  Instruction *DeoptBlockTerm =
      SplitBlockAndInsertIfThen(GI->getArgOperand(0), GI, true);
  BranchInst *CheckBI = cast<BranchInst>(CheckBB->getTerminator());
  // SplitBlockAndInsertIfThen inserts control flow that branches to
  // DeoptBlockTerm if the condition is true.  We want the opposite.
  CheckBI->swapSuccessors();

  BasicBlock *GuardedBlock = CheckBI->getSuccessor(0);
  GuardedBlock->setName("guarded");
  CheckBI->getSuccessor(1)->setName("deopt");
  BasicBlock *DeoptBlock = CheckBI->getSuccessor(1);

  // We now have a new exit block.
  ExitBlocks.push_back(CheckBI->getSuccessor(1));

  if (MSSAU)
    MSSAU->moveAllAfterSpliceBlocks(CheckBB, GuardedBlock, GI);

  GI->moveBefore(DeoptBlockTerm);
  GI->setArgOperand(0, ConstantInt::getFalse(GI->getContext()));

  // Add new successors of CheckBB into DomTree.
  for (auto *Succ : successors(CheckBB))
    DTUpdates.push_back({DominatorTree::Insert, CheckBB, Succ});

  // Now the blocks that used to be CheckBB's successors are GuardedBlock's
  // successors.
  for (auto *Succ : Successors)
    DTUpdates.push_back({DominatorTree::Insert, GuardedBlock, Succ});

  // Make proper changes to DT.
  DT.applyUpdates(DTUpdates);
  // Inform LI of a new loop block.
  L.addBasicBlockToLoop(GuardedBlock, LI);

  if (MSSAU) {
    MemoryDef *MD = cast<MemoryDef>(MSSAU->getMemorySSA()->getMemoryAccess(GI));
    MSSAU->moveToPlace(MD, DeoptBlock, MemorySSA::BeforeTerminator);
    if (VerifyMemorySSA)
      MSSAU->getMemorySSA()->verifyMemorySSA();
  }

  ++NumGuards;
  return CheckBI;
}

/// Cost multiplier is a way to limit potentially exponential behavior
/// of loop-unswitch. Cost is multipied in proportion of 2^number of unswitch
/// candidates available. Also accounting for the number of "sibling" loops with
/// the idea to account for previous unswitches that already happened on this
/// cluster of loops. There was an attempt to keep this formula simple,
/// just enough to limit the worst case behavior. Even if it is not that simple
/// now it is still not an attempt to provide a detailed heuristic size
/// prediction.
///
/// TODO: Make a proper accounting of "explosion" effect for all kinds of
/// unswitch candidates, making adequate predictions instead of wild guesses.
/// That requires knowing not just the number of "remaining" candidates but
/// also costs of unswitching for each of these candidates.
static int CalculateUnswitchCostMultiplier(
    Instruction &TI, Loop &L, LoopInfo &LI, DominatorTree &DT,
    ArrayRef<std::pair<Instruction *, TinyPtrVector<Value *>>>
        UnswitchCandidates) {

  // Guards and other exiting conditions do not contribute to exponential
  // explosion as soon as they dominate the latch (otherwise there might be
  // another path to the latch remaining that does not allow to eliminate the
  // loop copy on unswitch).
  BasicBlock *Latch = L.getLoopLatch();
  BasicBlock *CondBlock = TI.getParent();
  if (DT.dominates(CondBlock, Latch) &&
      (isGuard(&TI) ||
       llvm::count_if(successors(&TI), [&L](BasicBlock *SuccBB) {
         return L.contains(SuccBB);
       }) <= 1)) {
    NumCostMultiplierSkipped++;
    return 1;
  }

  auto *ParentL = L.getParentLoop();
  int SiblingsCount = (ParentL ? ParentL->getSubLoopsVector().size()
                               : std::distance(LI.begin(), LI.end()));
  // Count amount of clones that all the candidates might cause during
  // unswitching. Branch/guard counts as 1, switch counts as log2 of its cases.
  int UnswitchedClones = 0;
  for (auto Candidate : UnswitchCandidates) {
    Instruction *CI = Candidate.first;
    BasicBlock *CondBlock = CI->getParent();
    bool SkipExitingSuccessors = DT.dominates(CondBlock, Latch);
    if (isGuard(CI)) {
      if (!SkipExitingSuccessors)
        UnswitchedClones++;
      continue;
    }
    int NonExitingSuccessors = llvm::count_if(
        successors(CondBlock), [SkipExitingSuccessors, &L](BasicBlock *SuccBB) {
          return !SkipExitingSuccessors || L.contains(SuccBB);
        });
    UnswitchedClones += Log2_32(NonExitingSuccessors);
  }

  // Ignore up to the "unscaled candidates" number of unswitch candidates
  // when calculating the power-of-two scaling of the cost. The main idea
  // with this control is to allow a small number of unswitches to happen
  // and rely more on siblings multiplier (see below) when the number
  // of candidates is small.
  unsigned ClonesPower =
      std::max(UnswitchedClones - (int)UnswitchNumInitialUnscaledCandidates, 0);

  // Allowing top-level loops to spread a bit more than nested ones.
  int SiblingsMultiplier =
      std::max((ParentL ? SiblingsCount
                        : SiblingsCount / (int)UnswitchSiblingsToplevelDiv),
               1);
  // Compute the cost multiplier in a way that won't overflow by saturating
  // at an upper bound.
  int CostMultiplier;
  if (ClonesPower > Log2_32(UnswitchThreshold) ||
      SiblingsMultiplier > UnswitchThreshold)
    CostMultiplier = UnswitchThreshold;
  else
    CostMultiplier = std::min(SiblingsMultiplier * (1 << ClonesPower),
                              (int)UnswitchThreshold);

  LLVM_DEBUG(dbgs() << "  Computed multiplier  " << CostMultiplier
                    << " (siblings " << SiblingsMultiplier << " * clones "
                    << (1 << ClonesPower) << ")"
                    << " for unswitch candidate: " << TI << "\n");
  return CostMultiplier;
}

static bool unswitchBestCondition(
    Loop &L, DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
    AAResults &AA, TargetTransformInfo &TTI,
    function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
    ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
    function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
  // Collect all invariant conditions within this loop (as opposed to an inner
  // loop which would be handled when visiting that inner loop).
  SmallVector<std::pair<Instruction *, TinyPtrVector<Value *>>, 4>
      UnswitchCandidates;

  // Whether or not we should also collect guards in the loop.
  bool CollectGuards = false;
  if (UnswitchGuards) {
    auto *GuardDecl = L.getHeader()->getParent()->getParent()->getFunction(
        Intrinsic::getName(Intrinsic::experimental_guard));
    if (GuardDecl && !GuardDecl->use_empty())
      CollectGuards = true;
  }

  IVConditionInfo PartialIVInfo;
  for (auto *BB : L.blocks()) {
    if (LI.getLoopFor(BB) != &L)
      continue;

    if (CollectGuards)
      for (auto &I : *BB)
        if (isGuard(&I)) {
          auto *Cond = cast<IntrinsicInst>(&I)->getArgOperand(0);
          // TODO: Support AND, OR conditions and partial unswitching.
          if (!isa<Constant>(Cond) && L.isLoopInvariant(Cond))
            UnswitchCandidates.push_back({&I, {Cond}});
        }

    if (auto *SI = dyn_cast<SwitchInst>(BB->getTerminator())) {
      // We can only consider fully loop-invariant switch conditions as we need
      // to completely eliminate the switch after unswitching.
      if (!isa<Constant>(SI->getCondition()) &&
          L.isLoopInvariant(SI->getCondition()) && !BB->getUniqueSuccessor())
        UnswitchCandidates.push_back({SI, {SI->getCondition()}});
      continue;
    }

    auto *BI = dyn_cast<BranchInst>(BB->getTerminator());
    if (!BI || !BI->isConditional() || isa<Constant>(BI->getCondition()) ||
        BI->getSuccessor(0) == BI->getSuccessor(1))
      continue;

    // If BI's condition is 'select _, true, false', simplify it to confuse
    // matchers
    Value *Cond = BI->getCondition(), *CondNext;
    while (match(Cond, m_Select(m_Value(CondNext), m_One(), m_Zero())))
      Cond = CondNext;
    BI->setCondition(Cond);

    if (isa<Constant>(Cond))
      continue;

    if (L.isLoopInvariant(BI->getCondition())) {
      UnswitchCandidates.push_back({BI, {BI->getCondition()}});
      continue;
    }

    Instruction &CondI = *cast<Instruction>(BI->getCondition());
    if (match(&CondI, m_CombineOr(m_LogicalAnd(), m_LogicalOr()))) {
      TinyPtrVector<Value *> Invariants =
          collectHomogenousInstGraphLoopInvariants(L, CondI, LI);
      if (Invariants.empty())
        continue;

      UnswitchCandidates.push_back({BI, std::move(Invariants)});
      continue;
    }
  }

  Instruction *PartialIVCondBranch = nullptr;
  if (MSSAU && !findOptionMDForLoop(&L, "llvm.loop.unswitch.partial.disable") &&
      !any_of(UnswitchCandidates, [&L](auto &TerminatorAndInvariants) {
        return TerminatorAndInvariants.first == L.getHeader()->getTerminator();
      })) {
    MemorySSA *MSSA = MSSAU->getMemorySSA();
    if (auto Info = hasPartialIVCondition(L, MSSAThreshold, *MSSA, AA)) {
      LLVM_DEBUG(
          dbgs() << "simple-loop-unswitch: Found partially invariant condition "
                 << *Info->InstToDuplicate[0] << "\n");
      PartialIVInfo = *Info;
      PartialIVCondBranch = L.getHeader()->getTerminator();
      TinyPtrVector<Value *> ValsToDuplicate;
      for (auto *Inst : Info->InstToDuplicate)
        ValsToDuplicate.push_back(Inst);
      UnswitchCandidates.push_back(
          {L.getHeader()->getTerminator(), std::move(ValsToDuplicate)});
    }
  }

  // If we didn't find any candidates, we're done.
  if (UnswitchCandidates.empty())
    return false;

  // Check if there are irreducible CFG cycles in this loop. If so, we cannot
  // easily unswitch non-trivial edges out of the loop. Doing so might turn the
  // irreducible control flow into reducible control flow and introduce new
  // loops "out of thin air". If we ever discover important use cases for doing
  // this, we can add support to loop unswitch, but it is a lot of complexity
  // for what seems little or no real world benefit.
  LoopBlocksRPO RPOT(&L);
  RPOT.perform(&LI);
  if (containsIrreducibleCFG<const BasicBlock *>(RPOT, LI))
    return false;

  SmallVector<BasicBlock *, 4> ExitBlocks;
  L.getUniqueExitBlocks(ExitBlocks);

  // We cannot unswitch if exit blocks contain a cleanuppad/catchswitch
  // instruction as we don't know how to split those exit blocks.
  // FIXME: We should teach SplitBlock to handle this and remove this
  // restriction.
  for (auto *ExitBB : ExitBlocks) {
    auto *I = ExitBB->getFirstNonPHI();
    if (isa<CleanupPadInst>(I) || isa<CatchSwitchInst>(I)) {
      LLVM_DEBUG(dbgs() << "Cannot unswitch because of cleanuppad/catchswitch "
                           "in exit block\n");
      return false;
    }
  }

  LLVM_DEBUG(
      dbgs() << "Considering " << UnswitchCandidates.size()
             << " non-trivial loop invariant conditions for unswitching.\n");

  // Given that unswitching these terminators will require duplicating parts of
  // the loop, so we need to be able to model that cost. Compute the ephemeral
  // values and set up a data structure to hold per-BB costs. We cache each
  // block's cost so that we don't recompute this when considering different
  // subsets of the loop for duplication during unswitching.
  SmallPtrSet<const Value *, 4> EphValues;
  CodeMetrics::collectEphemeralValues(&L, &AC, EphValues);
  SmallDenseMap<BasicBlock *, InstructionCost, 4> BBCostMap;

  // Compute the cost of each block, as well as the total loop cost. Also, bail
  // out if we see instructions which are incompatible with loop unswitching
  // (convergent, noduplicate, or cross-basic-block tokens).
  // FIXME: We might be able to safely handle some of these in non-duplicated
  // regions.
  TargetTransformInfo::TargetCostKind CostKind =
      L.getHeader()->getParent()->hasMinSize()
      ? TargetTransformInfo::TCK_CodeSize
      : TargetTransformInfo::TCK_SizeAndLatency;
  InstructionCost LoopCost = 0;
  for (auto *BB : L.blocks()) {
    InstructionCost Cost = 0;
    for (auto &I : *BB) {
      if (EphValues.count(&I))
        continue;

      if (I.getType()->isTokenTy() && I.isUsedOutsideOfBlock(BB))
        return false;
      if (auto *CB = dyn_cast<CallBase>(&I))
        if (CB->isConvergent() || CB->cannotDuplicate())
          return false;

      Cost += TTI.getUserCost(&I, CostKind);
    }
    assert(Cost >= 0 && "Must not have negative costs!");
    LoopCost += Cost;
    assert(LoopCost >= 0 && "Must not have negative loop costs!");
    BBCostMap[BB] = Cost;
  }
  LLVM_DEBUG(dbgs() << "  Total loop cost: " << LoopCost << "\n");

  // Now we find the best candidate by searching for the one with the following
  // properties in order:
  //
  // 1) An unswitching cost below the threshold
  // 2) The smallest number of duplicated unswitch candidates (to avoid
  //    creating redundant subsequent unswitching)
  // 3) The smallest cost after unswitching.
  //
  // We prioritize reducing fanout of unswitch candidates provided the cost
  // remains below the threshold because this has a multiplicative effect.
  //
  // This requires memoizing each dominator subtree to avoid redundant work.
  //
  // FIXME: Need to actually do the number of candidates part above.
  SmallDenseMap<DomTreeNode *, InstructionCost, 4> DTCostMap;
  // Given a terminator which might be unswitched, computes the non-duplicated
  // cost for that terminator.
  auto ComputeUnswitchedCost = [&](Instruction &TI,
                                   bool FullUnswitch) -> InstructionCost {
    BasicBlock &BB = *TI.getParent();
    SmallPtrSet<BasicBlock *, 4> Visited;

    InstructionCost Cost = 0;
    for (BasicBlock *SuccBB : successors(&BB)) {
      // Don't count successors more than once.
      if (!Visited.insert(SuccBB).second)
        continue;

      // If this is a partial unswitch candidate, then it must be a conditional
      // branch with a condition of either `or`, `and`, their corresponding
      // select forms or partially invariant instructions. In that case, one of
      // the successors is necessarily duplicated, so don't even try to remove
      // its cost.
      if (!FullUnswitch) {
        auto &BI = cast<BranchInst>(TI);
        if (match(BI.getCondition(), m_LogicalAnd())) {
          if (SuccBB == BI.getSuccessor(1))
            continue;
        } else if (match(BI.getCondition(), m_LogicalOr())) {
          if (SuccBB == BI.getSuccessor(0))
            continue;
        } else if ((PartialIVInfo.KnownValue->isOneValue() &&
                    SuccBB == BI.getSuccessor(0)) ||
                   (!PartialIVInfo.KnownValue->isOneValue() &&
                    SuccBB == BI.getSuccessor(1)))
          continue;
      }

      // This successor's domtree will not need to be duplicated after
      // unswitching if the edge to the successor dominates it (and thus the
      // entire tree). This essentially means there is no other path into this
      // subtree and so it will end up live in only one clone of the loop.
      if (SuccBB->getUniquePredecessor() ||
          llvm::all_of(predecessors(SuccBB), [&](BasicBlock *PredBB) {
            return PredBB == &BB || DT.dominates(SuccBB, PredBB);
          })) {
        Cost += computeDomSubtreeCost(*DT[SuccBB], BBCostMap, DTCostMap);
        assert(Cost <= LoopCost &&
               "Non-duplicated cost should never exceed total loop cost!");
      }
    }

    // Now scale the cost by the number of unique successors minus one. We
    // subtract one because there is already at least one copy of the entire
    // loop. This is computing the new cost of unswitching a condition.
    // Note that guards always have 2 unique successors that are implicit and
    // will be materialized if we decide to unswitch it.
    int SuccessorsCount = isGuard(&TI) ? 2 : Visited.size();
    assert(SuccessorsCount > 1 &&
           "Cannot unswitch a condition without multiple distinct successors!");
    return (LoopCost - Cost) * (SuccessorsCount - 1);
  };
  Instruction *BestUnswitchTI = nullptr;
  InstructionCost BestUnswitchCost = 0;
  ArrayRef<Value *> BestUnswitchInvariants;
  for (auto &TerminatorAndInvariants : UnswitchCandidates) {
    Instruction &TI = *TerminatorAndInvariants.first;
    ArrayRef<Value *> Invariants = TerminatorAndInvariants.second;
    BranchInst *BI = dyn_cast<BranchInst>(&TI);
    InstructionCost CandidateCost = ComputeUnswitchedCost(
        TI, /*FullUnswitch*/ !BI || (Invariants.size() == 1 &&
                                     Invariants[0] == BI->getCondition()));
    // Calculate cost multiplier which is a tool to limit potentially
    // exponential behavior of loop-unswitch.
    if (EnableUnswitchCostMultiplier) {
      int CostMultiplier =
          CalculateUnswitchCostMultiplier(TI, L, LI, DT, UnswitchCandidates);
      assert(
          (CostMultiplier > 0 && CostMultiplier <= UnswitchThreshold) &&
          "cost multiplier needs to be in the range of 1..UnswitchThreshold");
      CandidateCost *= CostMultiplier;
      LLVM_DEBUG(dbgs() << "  Computed cost of " << CandidateCost
                        << " (multiplier: " << CostMultiplier << ")"
                        << " for unswitch candidate: " << TI << "\n");
    } else {
      LLVM_DEBUG(dbgs() << "  Computed cost of " << CandidateCost
                        << " for unswitch candidate: " << TI << "\n");
    }

    if (!BestUnswitchTI || CandidateCost < BestUnswitchCost) {
      BestUnswitchTI = &TI;
      BestUnswitchCost = CandidateCost;
      BestUnswitchInvariants = Invariants;
    }
  }
  assert(BestUnswitchTI && "Failed to find loop unswitch candidate");

  if (BestUnswitchCost >= UnswitchThreshold) {
    LLVM_DEBUG(dbgs() << "Cannot unswitch, lowest cost found: "
                      << BestUnswitchCost << "\n");
    return false;
  }

  if (BestUnswitchTI != PartialIVCondBranch)
    PartialIVInfo.InstToDuplicate.clear();

  // If the best candidate is a guard, turn it into a branch.
  if (isGuard(BestUnswitchTI))
    BestUnswitchTI = turnGuardIntoBranch(cast<IntrinsicInst>(BestUnswitchTI), L,
                                         ExitBlocks, DT, LI, MSSAU);

  LLVM_DEBUG(dbgs() << "  Unswitching non-trivial (cost = "
                    << BestUnswitchCost << ") terminator: " << *BestUnswitchTI
                    << "\n");
  unswitchNontrivialInvariants(L, *BestUnswitchTI, BestUnswitchInvariants,
                               ExitBlocks, PartialIVInfo, DT, LI, AC,
                               UnswitchCB, SE, MSSAU, DestroyLoopCB);
  return true;
}

/// Unswitch control flow predicated on loop invariant conditions.
///
/// This first hoists all branches or switches which are trivial (IE, do not
/// require duplicating any part of the loop) out of the loop body. It then
/// looks at other loop invariant control flows and tries to unswitch those as
/// well by cloning the loop if the result is small enough.
///
/// The `DT`, `LI`, `AC`, `AA`, `TTI` parameters are required analyses that are
/// also updated based on the unswitch. The `MSSA` analysis is also updated if
/// valid (i.e. its use is enabled).
///
/// If either `NonTrivial` is true or the flag `EnableNonTrivialUnswitch` is
/// true, we will attempt to do non-trivial unswitching as well as trivial
/// unswitching.
///
/// The `UnswitchCB` callback provided will be run after unswitching is
/// complete, with the first parameter set to `true` if the provided loop
/// remains a loop, and a list of new sibling loops created.
///
/// If `SE` is non-null, we will update that analysis based on the unswitching
/// done.
static bool
unswitchLoop(Loop &L, DominatorTree &DT, LoopInfo &LI, AssumptionCache &AC,
             AAResults &AA, TargetTransformInfo &TTI, bool Trivial,
             bool NonTrivial,
             function_ref<void(bool, bool, ArrayRef<Loop *>)> UnswitchCB,
             ScalarEvolution *SE, MemorySSAUpdater *MSSAU,
             function_ref<void(Loop &, StringRef)> DestroyLoopCB) {
  assert(L.isRecursivelyLCSSAForm(DT, LI) &&
         "Loops must be in LCSSA form before unswitching.");

  // Must be in loop simplified form: we need a preheader and dedicated exits.
  if (!L.isLoopSimplifyForm())
    return false;

  // Try trivial unswitch first before loop over other basic blocks in the loop.
  if (Trivial && unswitchAllTrivialConditions(L, DT, LI, SE, MSSAU)) {
    // If we unswitched successfully we will want to clean up the loop before
    // processing it further so just mark it as unswitched and return.
    UnswitchCB(/*CurrentLoopValid*/ true, false, {});
    return true;
  }

  // Check whether we should continue with non-trivial conditions.
  // EnableNonTrivialUnswitch: Global variable that forces non-trivial
  //                           unswitching for testing and debugging.
  // NonTrivial: Parameter that enables non-trivial unswitching for this
  //             invocation of the transform. But this should be allowed only
  //             for targets without branch divergence.
  //
  // FIXME: If divergence analysis becomes available to a loop
  // transform, we should allow unswitching for non-trivial uniform
  // branches even on targets that have divergence.
  // https://bugs.llvm.org/show_bug.cgi?id=48819
  bool ContinueWithNonTrivial =
      EnableNonTrivialUnswitch || (NonTrivial && !TTI.hasBranchDivergence());
  if (!ContinueWithNonTrivial)
    return false;

  // Skip non-trivial unswitching for optsize functions.
  if (L.getHeader()->getParent()->hasOptSize())
    return false;

  // Skip non-trivial unswitching for loops that cannot be cloned.
  if (!L.isSafeToClone())
    return false;

  // For non-trivial unswitching, because it often creates new loops, we rely on
  // the pass manager to iterate on the loops rather than trying to immediately
  // reach a fixed point. There is no substantial advantage to iterating
  // internally, and if any of the new loops are simplified enough to contain
  // trivial unswitching we want to prefer those.

  // Try to unswitch the best invariant condition. We prefer this full unswitch to
  // a partial unswitch when possible below the threshold.
  if (unswitchBestCondition(L, DT, LI, AC, AA, TTI, UnswitchCB, SE, MSSAU,
                            DestroyLoopCB))
    return true;

  // No other opportunities to unswitch.
  return false;
}

PreservedAnalyses SimpleLoopUnswitchPass::run(Loop &L, LoopAnalysisManager &AM,
                                              LoopStandardAnalysisResults &AR,
                                              LPMUpdater &U) {
  Function &F = *L.getHeader()->getParent();
  (void)F;

  LLVM_DEBUG(dbgs() << "Unswitching loop in " << F.getName() << ": " << L
                    << "\n");

  // Save the current loop name in a variable so that we can report it even
  // after it has been deleted.
  std::string LoopName = std::string(L.getName());

  auto UnswitchCB = [&L, &U, &LoopName](bool CurrentLoopValid,
                                        bool PartiallyInvariant,
                                        ArrayRef<Loop *> NewLoops) {
    // If we did a non-trivial unswitch, we have added new (cloned) loops.
    if (!NewLoops.empty())
      U.addSiblingLoops(NewLoops);

    // If the current loop remains valid, we should revisit it to catch any
    // other unswitch opportunities. Otherwise, we need to mark it as deleted.
    if (CurrentLoopValid) {
      if (PartiallyInvariant) {
        // Mark the new loop as partially unswitched, to avoid unswitching on
        // the same condition again.
        auto &Context = L.getHeader()->getContext();
        MDNode *DisableUnswitchMD = MDNode::get(
            Context,
            MDString::get(Context, "llvm.loop.unswitch.partial.disable"));
        MDNode *NewLoopID = makePostTransformationMetadata(
            Context, L.getLoopID(), {"llvm.loop.unswitch.partial"},
            {DisableUnswitchMD});
        L.setLoopID(NewLoopID);
      } else
        U.revisitCurrentLoop();
    } else
      U.markLoopAsDeleted(L, LoopName);
  };

  auto DestroyLoopCB = [&U](Loop &L, StringRef Name) {
    U.markLoopAsDeleted(L, Name);
  };

  Optional<MemorySSAUpdater> MSSAU;
  if (AR.MSSA) {
    MSSAU = MemorySSAUpdater(AR.MSSA);
    if (VerifyMemorySSA)
      AR.MSSA->verifyMemorySSA();
  }
  if (!unswitchLoop(L, AR.DT, AR.LI, AR.AC, AR.AA, AR.TTI, Trivial, NonTrivial,
                    UnswitchCB, &AR.SE,
                    MSSAU.hasValue() ? MSSAU.getPointer() : nullptr,
                    DestroyLoopCB))
    return PreservedAnalyses::all();

  if (AR.MSSA && VerifyMemorySSA)
    AR.MSSA->verifyMemorySSA();

  // Historically this pass has had issues with the dominator tree so verify it
  // in asserts builds.
  assert(AR.DT.verify(DominatorTree::VerificationLevel::Fast));

  auto PA = getLoopPassPreservedAnalyses();
  if (AR.MSSA)
    PA.preserve<MemorySSAAnalysis>();
  return PA;
}

void SimpleLoopUnswitchPass::printPipeline(
    raw_ostream &OS, function_ref<StringRef(StringRef)> MapClassName2PassName) {
  static_cast<PassInfoMixin<SimpleLoopUnswitchPass> *>(this)->printPipeline(
      OS, MapClassName2PassName);

  OS << "<";
  OS << (NonTrivial ? "" : "no-") << "nontrivial;";
  OS << (Trivial ? "" : "no-") << "trivial";
  OS << ">";
}

namespace {

class SimpleLoopUnswitchLegacyPass : public LoopPass {
  bool NonTrivial;

public:
  static char ID; // Pass ID, replacement for typeid

  explicit SimpleLoopUnswitchLegacyPass(bool NonTrivial = false)
      : LoopPass(ID), NonTrivial(NonTrivial) {
    initializeSimpleLoopUnswitchLegacyPassPass(
        *PassRegistry::getPassRegistry());
  }

  bool runOnLoop(Loop *L, LPPassManager &LPM) override;

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<AssumptionCacheTracker>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    AU.addRequired<MemorySSAWrapperPass>();
    AU.addPreserved<MemorySSAWrapperPass>();
    getLoopAnalysisUsage(AU);
  }
};

} // end anonymous namespace

bool SimpleLoopUnswitchLegacyPass::runOnLoop(Loop *L, LPPassManager &LPM) {
  if (skipLoop(L))
    return false;

  Function &F = *L->getHeader()->getParent();

  LLVM_DEBUG(dbgs() << "Unswitching loop in " << F.getName() << ": " << *L
                    << "\n");

  auto &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  auto &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
  auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(F);
  auto &AA = getAnalysis<AAResultsWrapperPass>().getAAResults();
  auto &TTI = getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
  MemorySSA *MSSA = &getAnalysis<MemorySSAWrapperPass>().getMSSA();
  MemorySSAUpdater MSSAU(MSSA);

  auto *SEWP = getAnalysisIfAvailable<ScalarEvolutionWrapperPass>();
  auto *SE = SEWP ? &SEWP->getSE() : nullptr;

  auto UnswitchCB = [&L, &LPM](bool CurrentLoopValid, bool PartiallyInvariant,
                               ArrayRef<Loop *> NewLoops) {
    // If we did a non-trivial unswitch, we have added new (cloned) loops.
    for (auto *NewL : NewLoops)
      LPM.addLoop(*NewL);

    // If the current loop remains valid, re-add it to the queue. This is
    // a little wasteful as we'll finish processing the current loop as well,
    // but it is the best we can do in the old PM.
    if (CurrentLoopValid) {
      // If the current loop has been unswitched using a partially invariant
      // condition, we should not re-add the current loop to avoid unswitching
      // on the same condition again.
      if (!PartiallyInvariant)
        LPM.addLoop(*L);
    } else
      LPM.markLoopAsDeleted(*L);
  };

  auto DestroyLoopCB = [&LPM](Loop &L, StringRef /* Name */) {
    LPM.markLoopAsDeleted(L);
  };

  if (VerifyMemorySSA)
    MSSA->verifyMemorySSA();

  bool Changed = unswitchLoop(*L, DT, LI, AC, AA, TTI, true, NonTrivial,
                              UnswitchCB, SE, &MSSAU, DestroyLoopCB);

  if (VerifyMemorySSA)
    MSSA->verifyMemorySSA();

  // Historically this pass has had issues with the dominator tree so verify it
  // in asserts builds.
  assert(DT.verify(DominatorTree::VerificationLevel::Fast));

  return Changed;
}

char SimpleLoopUnswitchLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(SimpleLoopUnswitchLegacyPass, "simple-loop-unswitch",
                      "Simple unswitch loops", false, false)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_END(SimpleLoopUnswitchLegacyPass, "simple-loop-unswitch",
                    "Simple unswitch loops", false, false)

Pass *llvm::createSimpleLoopUnswitchLegacyPass(bool NonTrivial) {
  return new SimpleLoopUnswitchLegacyPass(NonTrivial);
}