aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Transforms/Scalar/JumpThreading.cpp
blob: a3efad104ca6caafd8b2abed15421ded4e23b21c (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
//===- JumpThreading.cpp - Thread control through conditional blocks ------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements the Jump Threading pass.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/JumpThreading.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/Optional.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/BlockFrequencyInfo.h"
#include "llvm/Analysis/BranchProbabilityInfo.h"
#include "llvm/Analysis/CFG.h"
#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/Analysis/DomTreeUpdater.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/GuardUtils.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LazyValueInfo.h"
#include "llvm/Analysis/Loads.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/MemoryLocation.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/CFG.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/ConstantRange.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/MDBuilder.h"
#include "llvm/IR/Metadata.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Use.h"
#include "llvm/IR/User.h"
#include "llvm/IR/Value.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/BlockFrequency.h"
#include "llvm/Support/BranchProbability.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/BasicBlockUtils.h"
#include "llvm/Transforms/Utils/Cloning.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/SSAUpdater.h"
#include "llvm/Transforms/Utils/ValueMapper.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <iterator>
#include <memory>
#include <utility>

using namespace llvm;
using namespace jumpthreading;

#define DEBUG_TYPE "jump-threading"

STATISTIC(NumThreads, "Number of jumps threaded");
STATISTIC(NumFolds,   "Number of terminators folded");
STATISTIC(NumDupes,   "Number of branch blocks duplicated to eliminate phi");

static cl::opt<unsigned>
BBDuplicateThreshold("jump-threading-threshold",
          cl::desc("Max block size to duplicate for jump threading"),
          cl::init(6), cl::Hidden);

static cl::opt<unsigned>
ImplicationSearchThreshold(
  "jump-threading-implication-search-threshold",
  cl::desc("The number of predecessors to search for a stronger "
           "condition to use to thread over a weaker condition"),
  cl::init(3), cl::Hidden);

static cl::opt<bool> PrintLVIAfterJumpThreading(
    "print-lvi-after-jump-threading",
    cl::desc("Print the LazyValueInfo cache after JumpThreading"), cl::init(false),
    cl::Hidden);

static cl::opt<bool> JumpThreadingFreezeSelectCond(
    "jump-threading-freeze-select-cond",
    cl::desc("Freeze the condition when unfolding select"), cl::init(false),
    cl::Hidden);

static cl::opt<bool> ThreadAcrossLoopHeaders(
    "jump-threading-across-loop-headers",
    cl::desc("Allow JumpThreading to thread across loop headers, for testing"),
    cl::init(false), cl::Hidden);


namespace {

  /// This pass performs 'jump threading', which looks at blocks that have
  /// multiple predecessors and multiple successors.  If one or more of the
  /// predecessors of the block can be proven to always jump to one of the
  /// successors, we forward the edge from the predecessor to the successor by
  /// duplicating the contents of this block.
  ///
  /// An example of when this can occur is code like this:
  ///
  ///   if () { ...
  ///     X = 4;
  ///   }
  ///   if (X < 3) {
  ///
  /// In this case, the unconditional branch at the end of the first if can be
  /// revectored to the false side of the second if.
  class JumpThreading : public FunctionPass {
    JumpThreadingPass Impl;

  public:
    static char ID; // Pass identification

    JumpThreading(bool InsertFreezeWhenUnfoldingSelect = false, int T = -1)
        : FunctionPass(ID), Impl(InsertFreezeWhenUnfoldingSelect, T) {
      initializeJumpThreadingPass(*PassRegistry::getPassRegistry());
    }

    bool runOnFunction(Function &F) override;

    void getAnalysisUsage(AnalysisUsage &AU) const override {
      AU.addRequired<DominatorTreeWrapperPass>();
      AU.addPreserved<DominatorTreeWrapperPass>();
      AU.addRequired<AAResultsWrapperPass>();
      AU.addRequired<LazyValueInfoWrapperPass>();
      AU.addPreserved<LazyValueInfoWrapperPass>();
      AU.addPreserved<GlobalsAAWrapperPass>();
      AU.addRequired<TargetLibraryInfoWrapperPass>();
      AU.addRequired<TargetTransformInfoWrapperPass>();
    }

    void releaseMemory() override { Impl.releaseMemory(); }
  };

} // end anonymous namespace

char JumpThreading::ID = 0;

INITIALIZE_PASS_BEGIN(JumpThreading, "jump-threading",
                "Jump Threading", false, false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LazyValueInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
INITIALIZE_PASS_END(JumpThreading, "jump-threading",
                "Jump Threading", false, false)

// Public interface to the Jump Threading pass
FunctionPass *llvm::createJumpThreadingPass(bool InsertFr, int Threshold) {
  return new JumpThreading(InsertFr, Threshold);
}

JumpThreadingPass::JumpThreadingPass(bool InsertFr, int T) {
  InsertFreezeWhenUnfoldingSelect = JumpThreadingFreezeSelectCond | InsertFr;
  DefaultBBDupThreshold = (T == -1) ? BBDuplicateThreshold : unsigned(T);
}

// Update branch probability information according to conditional
// branch probability. This is usually made possible for cloned branches
// in inline instances by the context specific profile in the caller.
// For instance,
//
//  [Block PredBB]
//  [Branch PredBr]
//  if (t) {
//     Block A;
//  } else {
//     Block B;
//  }
//
//  [Block BB]
//  cond = PN([true, %A], [..., %B]); // PHI node
//  [Branch CondBr]
//  if (cond) {
//    ...  // P(cond == true) = 1%
//  }
//
//  Here we know that when block A is taken, cond must be true, which means
//      P(cond == true | A) = 1
//
//  Given that P(cond == true) = P(cond == true | A) * P(A) +
//                               P(cond == true | B) * P(B)
//  we get:
//     P(cond == true ) = P(A) + P(cond == true | B) * P(B)
//
//  which gives us:
//     P(A) is less than P(cond == true), i.e.
//     P(t == true) <= P(cond == true)
//
//  In other words, if we know P(cond == true) is unlikely, we know
//  that P(t == true) is also unlikely.
//
static void updatePredecessorProfileMetadata(PHINode *PN, BasicBlock *BB) {
  BranchInst *CondBr = dyn_cast<BranchInst>(BB->getTerminator());
  if (!CondBr)
    return;

  uint64_t TrueWeight, FalseWeight;
  if (!CondBr->extractProfMetadata(TrueWeight, FalseWeight))
    return;

  if (TrueWeight + FalseWeight == 0)
    // Zero branch_weights do not give a hint for getting branch probabilities.
    // Technically it would result in division by zero denominator, which is
    // TrueWeight + FalseWeight.
    return;

  // Returns the outgoing edge of the dominating predecessor block
  // that leads to the PhiNode's incoming block:
  auto GetPredOutEdge =
      [](BasicBlock *IncomingBB,
         BasicBlock *PhiBB) -> std::pair<BasicBlock *, BasicBlock *> {
    auto *PredBB = IncomingBB;
    auto *SuccBB = PhiBB;
    SmallPtrSet<BasicBlock *, 16> Visited;
    while (true) {
      BranchInst *PredBr = dyn_cast<BranchInst>(PredBB->getTerminator());
      if (PredBr && PredBr->isConditional())
        return {PredBB, SuccBB};
      Visited.insert(PredBB);
      auto *SinglePredBB = PredBB->getSinglePredecessor();
      if (!SinglePredBB)
        return {nullptr, nullptr};

      // Stop searching when SinglePredBB has been visited. It means we see
      // an unreachable loop.
      if (Visited.count(SinglePredBB))
        return {nullptr, nullptr};

      SuccBB = PredBB;
      PredBB = SinglePredBB;
    }
  };

  for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
    Value *PhiOpnd = PN->getIncomingValue(i);
    ConstantInt *CI = dyn_cast<ConstantInt>(PhiOpnd);

    if (!CI || !CI->getType()->isIntegerTy(1))
      continue;

    BranchProbability BP =
        (CI->isOne() ? BranchProbability::getBranchProbability(
                           TrueWeight, TrueWeight + FalseWeight)
                     : BranchProbability::getBranchProbability(
                           FalseWeight, TrueWeight + FalseWeight));

    auto PredOutEdge = GetPredOutEdge(PN->getIncomingBlock(i), BB);
    if (!PredOutEdge.first)
      return;

    BasicBlock *PredBB = PredOutEdge.first;
    BranchInst *PredBr = dyn_cast<BranchInst>(PredBB->getTerminator());
    if (!PredBr)
      return;

    uint64_t PredTrueWeight, PredFalseWeight;
    // FIXME: We currently only set the profile data when it is missing.
    // With PGO, this can be used to refine even existing profile data with
    // context information. This needs to be done after more performance
    // testing.
    if (PredBr->extractProfMetadata(PredTrueWeight, PredFalseWeight))
      continue;

    // We can not infer anything useful when BP >= 50%, because BP is the
    // upper bound probability value.
    if (BP >= BranchProbability(50, 100))
      continue;

    SmallVector<uint32_t, 2> Weights;
    if (PredBr->getSuccessor(0) == PredOutEdge.second) {
      Weights.push_back(BP.getNumerator());
      Weights.push_back(BP.getCompl().getNumerator());
    } else {
      Weights.push_back(BP.getCompl().getNumerator());
      Weights.push_back(BP.getNumerator());
    }
    PredBr->setMetadata(LLVMContext::MD_prof,
                        MDBuilder(PredBr->getParent()->getContext())
                            .createBranchWeights(Weights));
  }
}

/// runOnFunction - Toplevel algorithm.
bool JumpThreading::runOnFunction(Function &F) {
  if (skipFunction(F))
    return false;
  auto TTI = &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(F);
  // Jump Threading has no sense for the targets with divergent CF
  if (TTI->hasBranchDivergence())
    return false;
  auto TLI = &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
  auto DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
  auto LVI = &getAnalysis<LazyValueInfoWrapperPass>().getLVI();
  auto AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
  DomTreeUpdater DTU(*DT, DomTreeUpdater::UpdateStrategy::Lazy);
  std::unique_ptr<BlockFrequencyInfo> BFI;
  std::unique_ptr<BranchProbabilityInfo> BPI;
  if (F.hasProfileData()) {
    LoopInfo LI{DominatorTree(F)};
    BPI.reset(new BranchProbabilityInfo(F, LI, TLI));
    BFI.reset(new BlockFrequencyInfo(F, *BPI, LI));
  }

  bool Changed = Impl.runImpl(F, TLI, TTI, LVI, AA, &DTU, F.hasProfileData(),
                              std::move(BFI), std::move(BPI));
  if (PrintLVIAfterJumpThreading) {
    dbgs() << "LVI for function '" << F.getName() << "':\n";
    LVI->printLVI(F, DTU.getDomTree(), dbgs());
  }
  return Changed;
}

PreservedAnalyses JumpThreadingPass::run(Function &F,
                                         FunctionAnalysisManager &AM) {
  auto &TTI = AM.getResult<TargetIRAnalysis>(F);
  // Jump Threading has no sense for the targets with divergent CF
  if (TTI.hasBranchDivergence())
    return PreservedAnalyses::all();
  auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
  auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
  auto &LVI = AM.getResult<LazyValueAnalysis>(F);
  auto &AA = AM.getResult<AAManager>(F);
  DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Lazy);

  std::unique_ptr<BlockFrequencyInfo> BFI;
  std::unique_ptr<BranchProbabilityInfo> BPI;
  if (F.hasProfileData()) {
    LoopInfo LI{DominatorTree(F)};
    BPI.reset(new BranchProbabilityInfo(F, LI, &TLI));
    BFI.reset(new BlockFrequencyInfo(F, *BPI, LI));
  }

  bool Changed = runImpl(F, &TLI, &TTI, &LVI, &AA, &DTU, F.hasProfileData(),
                         std::move(BFI), std::move(BPI));

  if (PrintLVIAfterJumpThreading) {
    dbgs() << "LVI for function '" << F.getName() << "':\n";
    LVI.printLVI(F, DTU.getDomTree(), dbgs());
  }

  if (!Changed)
    return PreservedAnalyses::all();
  PreservedAnalyses PA;
  PA.preserve<DominatorTreeAnalysis>();
  PA.preserve<LazyValueAnalysis>();
  return PA;
}

bool JumpThreadingPass::runImpl(Function &F, TargetLibraryInfo *TLI_,
                                TargetTransformInfo *TTI_, LazyValueInfo *LVI_,
                                AliasAnalysis *AA_, DomTreeUpdater *DTU_,
                                bool HasProfileData_,
                                std::unique_ptr<BlockFrequencyInfo> BFI_,
                                std::unique_ptr<BranchProbabilityInfo> BPI_) {
  LLVM_DEBUG(dbgs() << "Jump threading on function '" << F.getName() << "'\n");
  TLI = TLI_;
  TTI = TTI_;
  LVI = LVI_;
  AA = AA_;
  DTU = DTU_;
  BFI.reset();
  BPI.reset();
  // When profile data is available, we need to update edge weights after
  // successful jump threading, which requires both BPI and BFI being available.
  HasProfileData = HasProfileData_;
  auto *GuardDecl = F.getParent()->getFunction(
      Intrinsic::getName(Intrinsic::experimental_guard));
  HasGuards = GuardDecl && !GuardDecl->use_empty();
  if (HasProfileData) {
    BPI = std::move(BPI_);
    BFI = std::move(BFI_);
  }

  // Reduce the number of instructions duplicated when optimizing strictly for
  // size.
  if (BBDuplicateThreshold.getNumOccurrences())
    BBDupThreshold = BBDuplicateThreshold;
  else if (F.hasFnAttribute(Attribute::MinSize))
    BBDupThreshold = 3;
  else
    BBDupThreshold = DefaultBBDupThreshold;

  // JumpThreading must not processes blocks unreachable from entry. It's a
  // waste of compute time and can potentially lead to hangs.
  SmallPtrSet<BasicBlock *, 16> Unreachable;
  assert(DTU && "DTU isn't passed into JumpThreading before using it.");
  assert(DTU->hasDomTree() && "JumpThreading relies on DomTree to proceed.");
  DominatorTree &DT = DTU->getDomTree();
  for (auto &BB : F)
    if (!DT.isReachableFromEntry(&BB))
      Unreachable.insert(&BB);

  if (!ThreadAcrossLoopHeaders)
    findLoopHeaders(F);

  bool EverChanged = false;
  bool Changed;
  do {
    Changed = false;
    for (auto &BB : F) {
      if (Unreachable.count(&BB))
        continue;
      while (processBlock(&BB)) // Thread all of the branches we can over BB.
        Changed = true;

      // Jump threading may have introduced redundant debug values into BB
      // which should be removed.
      if (Changed)
        RemoveRedundantDbgInstrs(&BB);

      // Stop processing BB if it's the entry or is now deleted. The following
      // routines attempt to eliminate BB and locating a suitable replacement
      // for the entry is non-trivial.
      if (&BB == &F.getEntryBlock() || DTU->isBBPendingDeletion(&BB))
        continue;

      if (pred_empty(&BB)) {
        // When processBlock makes BB unreachable it doesn't bother to fix up
        // the instructions in it. We must remove BB to prevent invalid IR.
        LLVM_DEBUG(dbgs() << "  JT: Deleting dead block '" << BB.getName()
                          << "' with terminator: " << *BB.getTerminator()
                          << '\n');
        LoopHeaders.erase(&BB);
        LVI->eraseBlock(&BB);
        DeleteDeadBlock(&BB, DTU);
        Changed = true;
        continue;
      }

      // processBlock doesn't thread BBs with unconditional TIs. However, if BB
      // is "almost empty", we attempt to merge BB with its sole successor.
      auto *BI = dyn_cast<BranchInst>(BB.getTerminator());
      if (BI && BI->isUnconditional()) {
        BasicBlock *Succ = BI->getSuccessor(0);
        if (
            // The terminator must be the only non-phi instruction in BB.
            BB.getFirstNonPHIOrDbg(true)->isTerminator() &&
            // Don't alter Loop headers and latches to ensure another pass can
            // detect and transform nested loops later.
            !LoopHeaders.count(&BB) && !LoopHeaders.count(Succ) &&
            TryToSimplifyUncondBranchFromEmptyBlock(&BB, DTU)) {
          RemoveRedundantDbgInstrs(Succ);
          // BB is valid for cleanup here because we passed in DTU. F remains
          // BB's parent until a DTU->getDomTree() event.
          LVI->eraseBlock(&BB);
          Changed = true;
        }
      }
    }
    EverChanged |= Changed;
  } while (Changed);

  LoopHeaders.clear();
  return EverChanged;
}

// Replace uses of Cond with ToVal when safe to do so. If all uses are
// replaced, we can remove Cond. We cannot blindly replace all uses of Cond
// because we may incorrectly replace uses when guards/assumes are uses of
// of `Cond` and we used the guards/assume to reason about the `Cond` value
// at the end of block. RAUW unconditionally replaces all uses
// including the guards/assumes themselves and the uses before the
// guard/assume.
static void replaceFoldableUses(Instruction *Cond, Value *ToVal) {
  assert(Cond->getType() == ToVal->getType());
  auto *BB = Cond->getParent();
  // We can unconditionally replace all uses in non-local blocks (i.e. uses
  // strictly dominated by BB), since LVI information is true from the
  // terminator of BB.
  replaceNonLocalUsesWith(Cond, ToVal);
  for (Instruction &I : reverse(*BB)) {
    // Reached the Cond whose uses we are trying to replace, so there are no
    // more uses.
    if (&I == Cond)
      break;
    // We only replace uses in instructions that are guaranteed to reach the end
    // of BB, where we know Cond is ToVal.
    if (!isGuaranteedToTransferExecutionToSuccessor(&I))
      break;
    I.replaceUsesOfWith(Cond, ToVal);
  }
  if (Cond->use_empty() && !Cond->mayHaveSideEffects())
    Cond->eraseFromParent();
}

/// Return the cost of duplicating a piece of this block from first non-phi
/// and before StopAt instruction to thread across it. Stop scanning the block
/// when exceeding the threshold. If duplication is impossible, returns ~0U.
static unsigned getJumpThreadDuplicationCost(const TargetTransformInfo *TTI,
                                             BasicBlock *BB,
                                             Instruction *StopAt,
                                             unsigned Threshold) {
  assert(StopAt->getParent() == BB && "Not an instruction from proper BB?");
  /// Ignore PHI nodes, these will be flattened when duplication happens.
  BasicBlock::const_iterator I(BB->getFirstNonPHI());

  // FIXME: THREADING will delete values that are just used to compute the
  // branch, so they shouldn't count against the duplication cost.

  unsigned Bonus = 0;
  if (BB->getTerminator() == StopAt) {
    // Threading through a switch statement is particularly profitable.  If this
    // block ends in a switch, decrease its cost to make it more likely to
    // happen.
    if (isa<SwitchInst>(StopAt))
      Bonus = 6;

    // The same holds for indirect branches, but slightly more so.
    if (isa<IndirectBrInst>(StopAt))
      Bonus = 8;
  }

  // Bump the threshold up so the early exit from the loop doesn't skip the
  // terminator-based Size adjustment at the end.
  Threshold += Bonus;

  // Sum up the cost of each instruction until we get to the terminator.  Don't
  // include the terminator because the copy won't include it.
  unsigned Size = 0;
  for (; &*I != StopAt; ++I) {

    // Stop scanning the block if we've reached the threshold.
    if (Size > Threshold)
      return Size;

    // Bail out if this instruction gives back a token type, it is not possible
    // to duplicate it if it is used outside this BB.
    if (I->getType()->isTokenTy() && I->isUsedOutsideOfBlock(BB))
      return ~0U;

    // Blocks with NoDuplicate are modelled as having infinite cost, so they
    // are never duplicated.
    if (const CallInst *CI = dyn_cast<CallInst>(I))
      if (CI->cannotDuplicate() || CI->isConvergent())
        return ~0U;

    if (TTI->getUserCost(&*I, TargetTransformInfo::TCK_SizeAndLatency)
            == TargetTransformInfo::TCC_Free)
      continue;

    // All other instructions count for at least one unit.
    ++Size;

    // Calls are more expensive.  If they are non-intrinsic calls, we model them
    // as having cost of 4.  If they are a non-vector intrinsic, we model them
    // as having cost of 2 total, and if they are a vector intrinsic, we model
    // them as having cost 1.
    if (const CallInst *CI = dyn_cast<CallInst>(I)) {
      if (!isa<IntrinsicInst>(CI))
        Size += 3;
      else if (!CI->getType()->isVectorTy())
        Size += 1;
    }
  }

  return Size > Bonus ? Size - Bonus : 0;
}

/// findLoopHeaders - We do not want jump threading to turn proper loop
/// structures into irreducible loops.  Doing this breaks up the loop nesting
/// hierarchy and pessimizes later transformations.  To prevent this from
/// happening, we first have to find the loop headers.  Here we approximate this
/// by finding targets of backedges in the CFG.
///
/// Note that there definitely are cases when we want to allow threading of
/// edges across a loop header.  For example, threading a jump from outside the
/// loop (the preheader) to an exit block of the loop is definitely profitable.
/// It is also almost always profitable to thread backedges from within the loop
/// to exit blocks, and is often profitable to thread backedges to other blocks
/// within the loop (forming a nested loop).  This simple analysis is not rich
/// enough to track all of these properties and keep it up-to-date as the CFG
/// mutates, so we don't allow any of these transformations.
void JumpThreadingPass::findLoopHeaders(Function &F) {
  SmallVector<std::pair<const BasicBlock*,const BasicBlock*>, 32> Edges;
  FindFunctionBackedges(F, Edges);

  for (const auto &Edge : Edges)
    LoopHeaders.insert(Edge.second);
}

/// getKnownConstant - Helper method to determine if we can thread over a
/// terminator with the given value as its condition, and if so what value to
/// use for that. What kind of value this is depends on whether we want an
/// integer or a block address, but an undef is always accepted.
/// Returns null if Val is null or not an appropriate constant.
static Constant *getKnownConstant(Value *Val, ConstantPreference Preference) {
  if (!Val)
    return nullptr;

  // Undef is "known" enough.
  if (UndefValue *U = dyn_cast<UndefValue>(Val))
    return U;

  if (Preference == WantBlockAddress)
    return dyn_cast<BlockAddress>(Val->stripPointerCasts());

  return dyn_cast<ConstantInt>(Val);
}

/// computeValueKnownInPredecessors - Given a basic block BB and a value V, see
/// if we can infer that the value is a known ConstantInt/BlockAddress or undef
/// in any of our predecessors.  If so, return the known list of value and pred
/// BB in the result vector.
///
/// This returns true if there were any known values.
bool JumpThreadingPass::computeValueKnownInPredecessorsImpl(
    Value *V, BasicBlock *BB, PredValueInfo &Result,
    ConstantPreference Preference, DenseSet<Value *> &RecursionSet,
    Instruction *CxtI) {
  // This method walks up use-def chains recursively.  Because of this, we could
  // get into an infinite loop going around loops in the use-def chain.  To
  // prevent this, keep track of what (value, block) pairs we've already visited
  // and terminate the search if we loop back to them
  if (!RecursionSet.insert(V).second)
    return false;

  // If V is a constant, then it is known in all predecessors.
  if (Constant *KC = getKnownConstant(V, Preference)) {
    for (BasicBlock *Pred : predecessors(BB))
      Result.emplace_back(KC, Pred);

    return !Result.empty();
  }

  // If V is a non-instruction value, or an instruction in a different block,
  // then it can't be derived from a PHI.
  Instruction *I = dyn_cast<Instruction>(V);
  if (!I || I->getParent() != BB) {

    // Okay, if this is a live-in value, see if it has a known value at the end
    // of any of our predecessors.
    //
    // FIXME: This should be an edge property, not a block end property.
    /// TODO: Per PR2563, we could infer value range information about a
    /// predecessor based on its terminator.
    //
    // FIXME: change this to use the more-rich 'getPredicateOnEdge' method if
    // "I" is a non-local compare-with-a-constant instruction.  This would be
    // able to handle value inequalities better, for example if the compare is
    // "X < 4" and "X < 3" is known true but "X < 4" itself is not available.
    // Perhaps getConstantOnEdge should be smart enough to do this?
    for (BasicBlock *P : predecessors(BB)) {
      // If the value is known by LazyValueInfo to be a constant in a
      // predecessor, use that information to try to thread this block.
      Constant *PredCst = LVI->getConstantOnEdge(V, P, BB, CxtI);
      if (Constant *KC = getKnownConstant(PredCst, Preference))
        Result.emplace_back(KC, P);
    }

    return !Result.empty();
  }

  /// If I is a PHI node, then we know the incoming values for any constants.
  if (PHINode *PN = dyn_cast<PHINode>(I)) {
    for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
      Value *InVal = PN->getIncomingValue(i);
      if (Constant *KC = getKnownConstant(InVal, Preference)) {
        Result.emplace_back(KC, PN->getIncomingBlock(i));
      } else {
        Constant *CI = LVI->getConstantOnEdge(InVal,
                                              PN->getIncomingBlock(i),
                                              BB, CxtI);
        if (Constant *KC = getKnownConstant(CI, Preference))
          Result.emplace_back(KC, PN->getIncomingBlock(i));
      }
    }

    return !Result.empty();
  }

  // Handle Cast instructions.
  if (CastInst *CI = dyn_cast<CastInst>(I)) {
    Value *Source = CI->getOperand(0);
    computeValueKnownInPredecessorsImpl(Source, BB, Result, Preference,
                                        RecursionSet, CxtI);
    if (Result.empty())
      return false;

    // Convert the known values.
    for (auto &R : Result)
      R.first = ConstantExpr::getCast(CI->getOpcode(), R.first, CI->getType());

    return true;
  }

  if (FreezeInst *FI = dyn_cast<FreezeInst>(I)) {
    Value *Source = FI->getOperand(0);
    computeValueKnownInPredecessorsImpl(Source, BB, Result, Preference,
                                        RecursionSet, CxtI);

    erase_if(Result, [](auto &Pair) {
      return !isGuaranteedNotToBeUndefOrPoison(Pair.first);
    });

    return !Result.empty();
  }

  // Handle some boolean conditions.
  if (I->getType()->getPrimitiveSizeInBits() == 1) {
    using namespace PatternMatch;
    if (Preference != WantInteger)
      return false;
    // X | true -> true
    // X & false -> false
    Value *Op0, *Op1;
    if (match(I, m_LogicalOr(m_Value(Op0), m_Value(Op1))) ||
        match(I, m_LogicalAnd(m_Value(Op0), m_Value(Op1)))) {
      PredValueInfoTy LHSVals, RHSVals;

      computeValueKnownInPredecessorsImpl(Op0, BB, LHSVals, WantInteger,
                                          RecursionSet, CxtI);
      computeValueKnownInPredecessorsImpl(Op1, BB, RHSVals, WantInteger,
                                          RecursionSet, CxtI);

      if (LHSVals.empty() && RHSVals.empty())
        return false;

      ConstantInt *InterestingVal;
      if (match(I, m_LogicalOr()))
        InterestingVal = ConstantInt::getTrue(I->getContext());
      else
        InterestingVal = ConstantInt::getFalse(I->getContext());

      SmallPtrSet<BasicBlock*, 4> LHSKnownBBs;

      // Scan for the sentinel.  If we find an undef, force it to the
      // interesting value: x|undef -> true and x&undef -> false.
      for (const auto &LHSVal : LHSVals)
        if (LHSVal.first == InterestingVal || isa<UndefValue>(LHSVal.first)) {
          Result.emplace_back(InterestingVal, LHSVal.second);
          LHSKnownBBs.insert(LHSVal.second);
        }
      for (const auto &RHSVal : RHSVals)
        if (RHSVal.first == InterestingVal || isa<UndefValue>(RHSVal.first)) {
          // If we already inferred a value for this block on the LHS, don't
          // re-add it.
          if (!LHSKnownBBs.count(RHSVal.second))
            Result.emplace_back(InterestingVal, RHSVal.second);
        }

      return !Result.empty();
    }

    // Handle the NOT form of XOR.
    if (I->getOpcode() == Instruction::Xor &&
        isa<ConstantInt>(I->getOperand(1)) &&
        cast<ConstantInt>(I->getOperand(1))->isOne()) {
      computeValueKnownInPredecessorsImpl(I->getOperand(0), BB, Result,
                                          WantInteger, RecursionSet, CxtI);
      if (Result.empty())
        return false;

      // Invert the known values.
      for (auto &R : Result)
        R.first = ConstantExpr::getNot(R.first);

      return true;
    }

  // Try to simplify some other binary operator values.
  } else if (BinaryOperator *BO = dyn_cast<BinaryOperator>(I)) {
    if (Preference != WantInteger)
      return false;
    if (ConstantInt *CI = dyn_cast<ConstantInt>(BO->getOperand(1))) {
      PredValueInfoTy LHSVals;
      computeValueKnownInPredecessorsImpl(BO->getOperand(0), BB, LHSVals,
                                          WantInteger, RecursionSet, CxtI);

      // Try to use constant folding to simplify the binary operator.
      for (const auto &LHSVal : LHSVals) {
        Constant *V = LHSVal.first;
        Constant *Folded = ConstantExpr::get(BO->getOpcode(), V, CI);

        if (Constant *KC = getKnownConstant(Folded, WantInteger))
          Result.emplace_back(KC, LHSVal.second);
      }
    }

    return !Result.empty();
  }

  // Handle compare with phi operand, where the PHI is defined in this block.
  if (CmpInst *Cmp = dyn_cast<CmpInst>(I)) {
    if (Preference != WantInteger)
      return false;
    Type *CmpType = Cmp->getType();
    Value *CmpLHS = Cmp->getOperand(0);
    Value *CmpRHS = Cmp->getOperand(1);
    CmpInst::Predicate Pred = Cmp->getPredicate();

    PHINode *PN = dyn_cast<PHINode>(CmpLHS);
    if (!PN)
      PN = dyn_cast<PHINode>(CmpRHS);
    if (PN && PN->getParent() == BB) {
      const DataLayout &DL = PN->getModule()->getDataLayout();
      // We can do this simplification if any comparisons fold to true or false.
      // See if any do.
      for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
        BasicBlock *PredBB = PN->getIncomingBlock(i);
        Value *LHS, *RHS;
        if (PN == CmpLHS) {
          LHS = PN->getIncomingValue(i);
          RHS = CmpRHS->DoPHITranslation(BB, PredBB);
        } else {
          LHS = CmpLHS->DoPHITranslation(BB, PredBB);
          RHS = PN->getIncomingValue(i);
        }
        Value *Res = SimplifyCmpInst(Pred, LHS, RHS, {DL});
        if (!Res) {
          if (!isa<Constant>(RHS))
            continue;

          // getPredicateOnEdge call will make no sense if LHS is defined in BB.
          auto LHSInst = dyn_cast<Instruction>(LHS);
          if (LHSInst && LHSInst->getParent() == BB)
            continue;

          LazyValueInfo::Tristate
            ResT = LVI->getPredicateOnEdge(Pred, LHS,
                                           cast<Constant>(RHS), PredBB, BB,
                                           CxtI ? CxtI : Cmp);
          if (ResT == LazyValueInfo::Unknown)
            continue;
          Res = ConstantInt::get(Type::getInt1Ty(LHS->getContext()), ResT);
        }

        if (Constant *KC = getKnownConstant(Res, WantInteger))
          Result.emplace_back(KC, PredBB);
      }

      return !Result.empty();
    }

    // If comparing a live-in value against a constant, see if we know the
    // live-in value on any predecessors.
    if (isa<Constant>(CmpRHS) && !CmpType->isVectorTy()) {
      Constant *CmpConst = cast<Constant>(CmpRHS);

      if (!isa<Instruction>(CmpLHS) ||
          cast<Instruction>(CmpLHS)->getParent() != BB) {
        for (BasicBlock *P : predecessors(BB)) {
          // If the value is known by LazyValueInfo to be a constant in a
          // predecessor, use that information to try to thread this block.
          LazyValueInfo::Tristate Res =
            LVI->getPredicateOnEdge(Pred, CmpLHS,
                                    CmpConst, P, BB, CxtI ? CxtI : Cmp);
          if (Res == LazyValueInfo::Unknown)
            continue;

          Constant *ResC = ConstantInt::get(CmpType, Res);
          Result.emplace_back(ResC, P);
        }

        return !Result.empty();
      }

      // InstCombine can fold some forms of constant range checks into
      // (icmp (add (x, C1)), C2). See if we have we have such a thing with
      // x as a live-in.
      {
        using namespace PatternMatch;

        Value *AddLHS;
        ConstantInt *AddConst;
        if (isa<ConstantInt>(CmpConst) &&
            match(CmpLHS, m_Add(m_Value(AddLHS), m_ConstantInt(AddConst)))) {
          if (!isa<Instruction>(AddLHS) ||
              cast<Instruction>(AddLHS)->getParent() != BB) {
            for (BasicBlock *P : predecessors(BB)) {
              // If the value is known by LazyValueInfo to be a ConstantRange in
              // a predecessor, use that information to try to thread this
              // block.
              ConstantRange CR = LVI->getConstantRangeOnEdge(
                  AddLHS, P, BB, CxtI ? CxtI : cast<Instruction>(CmpLHS));
              // Propagate the range through the addition.
              CR = CR.add(AddConst->getValue());

              // Get the range where the compare returns true.
              ConstantRange CmpRange = ConstantRange::makeExactICmpRegion(
                  Pred, cast<ConstantInt>(CmpConst)->getValue());

              Constant *ResC;
              if (CmpRange.contains(CR))
                ResC = ConstantInt::getTrue(CmpType);
              else if (CmpRange.inverse().contains(CR))
                ResC = ConstantInt::getFalse(CmpType);
              else
                continue;

              Result.emplace_back(ResC, P);
            }

            return !Result.empty();
          }
        }
      }

      // Try to find a constant value for the LHS of a comparison,
      // and evaluate it statically if we can.
      PredValueInfoTy LHSVals;
      computeValueKnownInPredecessorsImpl(I->getOperand(0), BB, LHSVals,
                                          WantInteger, RecursionSet, CxtI);

      for (const auto &LHSVal : LHSVals) {
        Constant *V = LHSVal.first;
        Constant *Folded = ConstantExpr::getCompare(Pred, V, CmpConst);
        if (Constant *KC = getKnownConstant(Folded, WantInteger))
          Result.emplace_back(KC, LHSVal.second);
      }

      return !Result.empty();
    }
  }

  if (SelectInst *SI = dyn_cast<SelectInst>(I)) {
    // Handle select instructions where at least one operand is a known constant
    // and we can figure out the condition value for any predecessor block.
    Constant *TrueVal = getKnownConstant(SI->getTrueValue(), Preference);
    Constant *FalseVal = getKnownConstant(SI->getFalseValue(), Preference);
    PredValueInfoTy Conds;
    if ((TrueVal || FalseVal) &&
        computeValueKnownInPredecessorsImpl(SI->getCondition(), BB, Conds,
                                            WantInteger, RecursionSet, CxtI)) {
      for (auto &C : Conds) {
        Constant *Cond = C.first;

        // Figure out what value to use for the condition.
        bool KnownCond;
        if (ConstantInt *CI = dyn_cast<ConstantInt>(Cond)) {
          // A known boolean.
          KnownCond = CI->isOne();
        } else {
          assert(isa<UndefValue>(Cond) && "Unexpected condition value");
          // Either operand will do, so be sure to pick the one that's a known
          // constant.
          // FIXME: Do this more cleverly if both values are known constants?
          KnownCond = (TrueVal != nullptr);
        }

        // See if the select has a known constant value for this predecessor.
        if (Constant *Val = KnownCond ? TrueVal : FalseVal)
          Result.emplace_back(Val, C.second);
      }

      return !Result.empty();
    }
  }

  // If all else fails, see if LVI can figure out a constant value for us.
  assert(CxtI->getParent() == BB && "CxtI should be in BB");
  Constant *CI = LVI->getConstant(V, CxtI);
  if (Constant *KC = getKnownConstant(CI, Preference)) {
    for (BasicBlock *Pred : predecessors(BB))
      Result.emplace_back(KC, Pred);
  }

  return !Result.empty();
}

/// GetBestDestForBranchOnUndef - If we determine that the specified block ends
/// in an undefined jump, decide which block is best to revector to.
///
/// Since we can pick an arbitrary destination, we pick the successor with the
/// fewest predecessors.  This should reduce the in-degree of the others.
static unsigned getBestDestForJumpOnUndef(BasicBlock *BB) {
  Instruction *BBTerm = BB->getTerminator();
  unsigned MinSucc = 0;
  BasicBlock *TestBB = BBTerm->getSuccessor(MinSucc);
  // Compute the successor with the minimum number of predecessors.
  unsigned MinNumPreds = pred_size(TestBB);
  for (unsigned i = 1, e = BBTerm->getNumSuccessors(); i != e; ++i) {
    TestBB = BBTerm->getSuccessor(i);
    unsigned NumPreds = pred_size(TestBB);
    if (NumPreds < MinNumPreds) {
      MinSucc = i;
      MinNumPreds = NumPreds;
    }
  }

  return MinSucc;
}

static bool hasAddressTakenAndUsed(BasicBlock *BB) {
  if (!BB->hasAddressTaken()) return false;

  // If the block has its address taken, it may be a tree of dead constants
  // hanging off of it.  These shouldn't keep the block alive.
  BlockAddress *BA = BlockAddress::get(BB);
  BA->removeDeadConstantUsers();
  return !BA->use_empty();
}

/// processBlock - If there are any predecessors whose control can be threaded
/// through to a successor, transform them now.
bool JumpThreadingPass::processBlock(BasicBlock *BB) {
  // If the block is trivially dead, just return and let the caller nuke it.
  // This simplifies other transformations.
  if (DTU->isBBPendingDeletion(BB) ||
      (pred_empty(BB) && BB != &BB->getParent()->getEntryBlock()))
    return false;

  // If this block has a single predecessor, and if that pred has a single
  // successor, merge the blocks.  This encourages recursive jump threading
  // because now the condition in this block can be threaded through
  // predecessors of our predecessor block.
  if (maybeMergeBasicBlockIntoOnlyPred(BB))
    return true;

  if (tryToUnfoldSelectInCurrBB(BB))
    return true;

  // Look if we can propagate guards to predecessors.
  if (HasGuards && processGuards(BB))
    return true;

  // What kind of constant we're looking for.
  ConstantPreference Preference = WantInteger;

  // Look to see if the terminator is a conditional branch, switch or indirect
  // branch, if not we can't thread it.
  Value *Condition;
  Instruction *Terminator = BB->getTerminator();
  if (BranchInst *BI = dyn_cast<BranchInst>(Terminator)) {
    // Can't thread an unconditional jump.
    if (BI->isUnconditional()) return false;
    Condition = BI->getCondition();
  } else if (SwitchInst *SI = dyn_cast<SwitchInst>(Terminator)) {
    Condition = SI->getCondition();
  } else if (IndirectBrInst *IB = dyn_cast<IndirectBrInst>(Terminator)) {
    // Can't thread indirect branch with no successors.
    if (IB->getNumSuccessors() == 0) return false;
    Condition = IB->getAddress()->stripPointerCasts();
    Preference = WantBlockAddress;
  } else {
    return false; // Must be an invoke or callbr.
  }

  // Keep track if we constant folded the condition in this invocation.
  bool ConstantFolded = false;

  // Run constant folding to see if we can reduce the condition to a simple
  // constant.
  if (Instruction *I = dyn_cast<Instruction>(Condition)) {
    Value *SimpleVal =
        ConstantFoldInstruction(I, BB->getModule()->getDataLayout(), TLI);
    if (SimpleVal) {
      I->replaceAllUsesWith(SimpleVal);
      if (isInstructionTriviallyDead(I, TLI))
        I->eraseFromParent();
      Condition = SimpleVal;
      ConstantFolded = true;
    }
  }

  // If the terminator is branching on an undef or freeze undef, we can pick any
  // of the successors to branch to.  Let getBestDestForJumpOnUndef decide.
  auto *FI = dyn_cast<FreezeInst>(Condition);
  if (isa<UndefValue>(Condition) ||
      (FI && isa<UndefValue>(FI->getOperand(0)) && FI->hasOneUse())) {
    unsigned BestSucc = getBestDestForJumpOnUndef(BB);
    std::vector<DominatorTree::UpdateType> Updates;

    // Fold the branch/switch.
    Instruction *BBTerm = BB->getTerminator();
    Updates.reserve(BBTerm->getNumSuccessors());
    for (unsigned i = 0, e = BBTerm->getNumSuccessors(); i != e; ++i) {
      if (i == BestSucc) continue;
      BasicBlock *Succ = BBTerm->getSuccessor(i);
      Succ->removePredecessor(BB, true);
      Updates.push_back({DominatorTree::Delete, BB, Succ});
    }

    LLVM_DEBUG(dbgs() << "  In block '" << BB->getName()
                      << "' folding undef terminator: " << *BBTerm << '\n');
    BranchInst::Create(BBTerm->getSuccessor(BestSucc), BBTerm);
    ++NumFolds;
    BBTerm->eraseFromParent();
    DTU->applyUpdatesPermissive(Updates);
    if (FI)
      FI->eraseFromParent();
    return true;
  }

  // If the terminator of this block is branching on a constant, simplify the
  // terminator to an unconditional branch.  This can occur due to threading in
  // other blocks.
  if (getKnownConstant(Condition, Preference)) {
    LLVM_DEBUG(dbgs() << "  In block '" << BB->getName()
                      << "' folding terminator: " << *BB->getTerminator()
                      << '\n');
    ++NumFolds;
    ConstantFoldTerminator(BB, true, nullptr, DTU);
    if (HasProfileData)
      BPI->eraseBlock(BB);
    return true;
  }

  Instruction *CondInst = dyn_cast<Instruction>(Condition);

  // All the rest of our checks depend on the condition being an instruction.
  if (!CondInst) {
    // FIXME: Unify this with code below.
    if (processThreadableEdges(Condition, BB, Preference, Terminator))
      return true;
    return ConstantFolded;
  }

  if (CmpInst *CondCmp = dyn_cast<CmpInst>(CondInst)) {
    // If we're branching on a conditional, LVI might be able to determine
    // it's value at the branch instruction.  We only handle comparisons
    // against a constant at this time.
    // TODO: This should be extended to handle switches as well.
    BranchInst *CondBr = dyn_cast<BranchInst>(BB->getTerminator());
    Constant *CondConst = dyn_cast<Constant>(CondCmp->getOperand(1));
    if (CondBr && CondConst) {
      // We should have returned as soon as we turn a conditional branch to
      // unconditional. Because its no longer interesting as far as jump
      // threading is concerned.
      assert(CondBr->isConditional() && "Threading on unconditional terminator");

      LazyValueInfo::Tristate Ret =
          LVI->getPredicateAt(CondCmp->getPredicate(), CondCmp->getOperand(0),
                              CondConst, CondBr, /*UseBlockValue=*/false);
      if (Ret != LazyValueInfo::Unknown) {
        unsigned ToRemove = Ret == LazyValueInfo::True ? 1 : 0;
        unsigned ToKeep = Ret == LazyValueInfo::True ? 0 : 1;
        BasicBlock *ToRemoveSucc = CondBr->getSuccessor(ToRemove);
        ToRemoveSucc->removePredecessor(BB, true);
        BranchInst *UncondBr =
          BranchInst::Create(CondBr->getSuccessor(ToKeep), CondBr);
        UncondBr->setDebugLoc(CondBr->getDebugLoc());
        ++NumFolds;
        CondBr->eraseFromParent();
        if (CondCmp->use_empty())
          CondCmp->eraseFromParent();
        // We can safely replace *some* uses of the CondInst if it has
        // exactly one value as returned by LVI. RAUW is incorrect in the
        // presence of guards and assumes, that have the `Cond` as the use. This
        // is because we use the guards/assume to reason about the `Cond` value
        // at the end of block, but RAUW unconditionally replaces all uses
        // including the guards/assumes themselves and the uses before the
        // guard/assume.
        else if (CondCmp->getParent() == BB) {
          auto *CI = Ret == LazyValueInfo::True ?
            ConstantInt::getTrue(CondCmp->getType()) :
            ConstantInt::getFalse(CondCmp->getType());
          replaceFoldableUses(CondCmp, CI);
        }
        DTU->applyUpdatesPermissive(
            {{DominatorTree::Delete, BB, ToRemoveSucc}});
        if (HasProfileData)
          BPI->eraseBlock(BB);
        return true;
      }

      // We did not manage to simplify this branch, try to see whether
      // CondCmp depends on a known phi-select pattern.
      if (tryToUnfoldSelect(CondCmp, BB))
        return true;
    }
  }

  if (SwitchInst *SI = dyn_cast<SwitchInst>(BB->getTerminator()))
    if (tryToUnfoldSelect(SI, BB))
      return true;

  // Check for some cases that are worth simplifying.  Right now we want to look
  // for loads that are used by a switch or by the condition for the branch.  If
  // we see one, check to see if it's partially redundant.  If so, insert a PHI
  // which can then be used to thread the values.
  Value *SimplifyValue = CondInst;

  if (auto *FI = dyn_cast<FreezeInst>(SimplifyValue))
    // Look into freeze's operand
    SimplifyValue = FI->getOperand(0);

  if (CmpInst *CondCmp = dyn_cast<CmpInst>(SimplifyValue))
    if (isa<Constant>(CondCmp->getOperand(1)))
      SimplifyValue = CondCmp->getOperand(0);

  // TODO: There are other places where load PRE would be profitable, such as
  // more complex comparisons.
  if (LoadInst *LoadI = dyn_cast<LoadInst>(SimplifyValue))
    if (simplifyPartiallyRedundantLoad(LoadI))
      return true;

  // Before threading, try to propagate profile data backwards:
  if (PHINode *PN = dyn_cast<PHINode>(CondInst))
    if (PN->getParent() == BB && isa<BranchInst>(BB->getTerminator()))
      updatePredecessorProfileMetadata(PN, BB);

  // Handle a variety of cases where we are branching on something derived from
  // a PHI node in the current block.  If we can prove that any predecessors
  // compute a predictable value based on a PHI node, thread those predecessors.
  if (processThreadableEdges(CondInst, BB, Preference, Terminator))
    return true;

  // If this is an otherwise-unfoldable branch on a phi node or freeze(phi) in
  // the current block, see if we can simplify.
  PHINode *PN = dyn_cast<PHINode>(
      isa<FreezeInst>(CondInst) ? cast<FreezeInst>(CondInst)->getOperand(0)
                                : CondInst);

  if (PN && PN->getParent() == BB && isa<BranchInst>(BB->getTerminator()))
    return processBranchOnPHI(PN);

  // If this is an otherwise-unfoldable branch on a XOR, see if we can simplify.
  if (CondInst->getOpcode() == Instruction::Xor &&
      CondInst->getParent() == BB && isa<BranchInst>(BB->getTerminator()))
    return processBranchOnXOR(cast<BinaryOperator>(CondInst));

  // Search for a stronger dominating condition that can be used to simplify a
  // conditional branch leaving BB.
  if (processImpliedCondition(BB))
    return true;

  return false;
}

bool JumpThreadingPass::processImpliedCondition(BasicBlock *BB) {
  auto *BI = dyn_cast<BranchInst>(BB->getTerminator());
  if (!BI || !BI->isConditional())
    return false;

  Value *Cond = BI->getCondition();
  BasicBlock *CurrentBB = BB;
  BasicBlock *CurrentPred = BB->getSinglePredecessor();
  unsigned Iter = 0;

  auto &DL = BB->getModule()->getDataLayout();

  while (CurrentPred && Iter++ < ImplicationSearchThreshold) {
    auto *PBI = dyn_cast<BranchInst>(CurrentPred->getTerminator());
    if (!PBI || !PBI->isConditional())
      return false;
    if (PBI->getSuccessor(0) != CurrentBB && PBI->getSuccessor(1) != CurrentBB)
      return false;

    bool CondIsTrue = PBI->getSuccessor(0) == CurrentBB;
    Optional<bool> Implication =
        isImpliedCondition(PBI->getCondition(), Cond, DL, CondIsTrue);
    if (Implication) {
      BasicBlock *KeepSucc = BI->getSuccessor(*Implication ? 0 : 1);
      BasicBlock *RemoveSucc = BI->getSuccessor(*Implication ? 1 : 0);
      RemoveSucc->removePredecessor(BB);
      BranchInst *UncondBI = BranchInst::Create(KeepSucc, BI);
      UncondBI->setDebugLoc(BI->getDebugLoc());
      ++NumFolds;
      BI->eraseFromParent();
      DTU->applyUpdatesPermissive({{DominatorTree::Delete, BB, RemoveSucc}});
      if (HasProfileData)
        BPI->eraseBlock(BB);
      return true;
    }
    CurrentBB = CurrentPred;
    CurrentPred = CurrentBB->getSinglePredecessor();
  }

  return false;
}

/// Return true if Op is an instruction defined in the given block.
static bool isOpDefinedInBlock(Value *Op, BasicBlock *BB) {
  if (Instruction *OpInst = dyn_cast<Instruction>(Op))
    if (OpInst->getParent() == BB)
      return true;
  return false;
}

/// simplifyPartiallyRedundantLoad - If LoadI is an obviously partially
/// redundant load instruction, eliminate it by replacing it with a PHI node.
/// This is an important optimization that encourages jump threading, and needs
/// to be run interlaced with other jump threading tasks.
bool JumpThreadingPass::simplifyPartiallyRedundantLoad(LoadInst *LoadI) {
  // Don't hack volatile and ordered loads.
  if (!LoadI->isUnordered()) return false;

  // If the load is defined in a block with exactly one predecessor, it can't be
  // partially redundant.
  BasicBlock *LoadBB = LoadI->getParent();
  if (LoadBB->getSinglePredecessor())
    return false;

  // If the load is defined in an EH pad, it can't be partially redundant,
  // because the edges between the invoke and the EH pad cannot have other
  // instructions between them.
  if (LoadBB->isEHPad())
    return false;

  Value *LoadedPtr = LoadI->getOperand(0);

  // If the loaded operand is defined in the LoadBB and its not a phi,
  // it can't be available in predecessors.
  if (isOpDefinedInBlock(LoadedPtr, LoadBB) && !isa<PHINode>(LoadedPtr))
    return false;

  // Scan a few instructions up from the load, to see if it is obviously live at
  // the entry to its block.
  BasicBlock::iterator BBIt(LoadI);
  bool IsLoadCSE;
  if (Value *AvailableVal = FindAvailableLoadedValue(
          LoadI, LoadBB, BBIt, DefMaxInstsToScan, AA, &IsLoadCSE)) {
    // If the value of the load is locally available within the block, just use
    // it.  This frequently occurs for reg2mem'd allocas.

    if (IsLoadCSE) {
      LoadInst *NLoadI = cast<LoadInst>(AvailableVal);
      combineMetadataForCSE(NLoadI, LoadI, false);
    };

    // If the returned value is the load itself, replace with an undef. This can
    // only happen in dead loops.
    if (AvailableVal == LoadI)
      AvailableVal = UndefValue::get(LoadI->getType());
    if (AvailableVal->getType() != LoadI->getType())
      AvailableVal = CastInst::CreateBitOrPointerCast(
          AvailableVal, LoadI->getType(), "", LoadI);
    LoadI->replaceAllUsesWith(AvailableVal);
    LoadI->eraseFromParent();
    return true;
  }

  // Otherwise, if we scanned the whole block and got to the top of the block,
  // we know the block is locally transparent to the load.  If not, something
  // might clobber its value.
  if (BBIt != LoadBB->begin())
    return false;

  // If all of the loads and stores that feed the value have the same AA tags,
  // then we can propagate them onto any newly inserted loads.
  AAMDNodes AATags = LoadI->getAAMetadata();

  SmallPtrSet<BasicBlock*, 8> PredsScanned;

  using AvailablePredsTy = SmallVector<std::pair<BasicBlock *, Value *>, 8>;

  AvailablePredsTy AvailablePreds;
  BasicBlock *OneUnavailablePred = nullptr;
  SmallVector<LoadInst*, 8> CSELoads;

  // If we got here, the loaded value is transparent through to the start of the
  // block.  Check to see if it is available in any of the predecessor blocks.
  for (BasicBlock *PredBB : predecessors(LoadBB)) {
    // If we already scanned this predecessor, skip it.
    if (!PredsScanned.insert(PredBB).second)
      continue;

    BBIt = PredBB->end();
    unsigned NumScanedInst = 0;
    Value *PredAvailable = nullptr;
    // NOTE: We don't CSE load that is volatile or anything stronger than
    // unordered, that should have been checked when we entered the function.
    assert(LoadI->isUnordered() &&
           "Attempting to CSE volatile or atomic loads");
    // If this is a load on a phi pointer, phi-translate it and search
    // for available load/store to the pointer in predecessors.
    Type *AccessTy = LoadI->getType();
    const auto &DL = LoadI->getModule()->getDataLayout();
    MemoryLocation Loc(LoadedPtr->DoPHITranslation(LoadBB, PredBB),
                       LocationSize::precise(DL.getTypeStoreSize(AccessTy)),
                       AATags);
    PredAvailable = findAvailablePtrLoadStore(Loc, AccessTy, LoadI->isAtomic(),
                                              PredBB, BBIt, DefMaxInstsToScan,
                                              AA, &IsLoadCSE, &NumScanedInst);

    // If PredBB has a single predecessor, continue scanning through the
    // single predecessor.
    BasicBlock *SinglePredBB = PredBB;
    while (!PredAvailable && SinglePredBB && BBIt == SinglePredBB->begin() &&
           NumScanedInst < DefMaxInstsToScan) {
      SinglePredBB = SinglePredBB->getSinglePredecessor();
      if (SinglePredBB) {
        BBIt = SinglePredBB->end();
        PredAvailable = findAvailablePtrLoadStore(
            Loc, AccessTy, LoadI->isAtomic(), SinglePredBB, BBIt,
            (DefMaxInstsToScan - NumScanedInst), AA, &IsLoadCSE,
            &NumScanedInst);
      }
    }

    if (!PredAvailable) {
      OneUnavailablePred = PredBB;
      continue;
    }

    if (IsLoadCSE)
      CSELoads.push_back(cast<LoadInst>(PredAvailable));

    // If so, this load is partially redundant.  Remember this info so that we
    // can create a PHI node.
    AvailablePreds.emplace_back(PredBB, PredAvailable);
  }

  // If the loaded value isn't available in any predecessor, it isn't partially
  // redundant.
  if (AvailablePreds.empty()) return false;

  // Okay, the loaded value is available in at least one (and maybe all!)
  // predecessors.  If the value is unavailable in more than one unique
  // predecessor, we want to insert a merge block for those common predecessors.
  // This ensures that we only have to insert one reload, thus not increasing
  // code size.
  BasicBlock *UnavailablePred = nullptr;

  // If the value is unavailable in one of predecessors, we will end up
  // inserting a new instruction into them. It is only valid if all the
  // instructions before LoadI are guaranteed to pass execution to its
  // successor, or if LoadI is safe to speculate.
  // TODO: If this logic becomes more complex, and we will perform PRE insertion
  // farther than to a predecessor, we need to reuse the code from GVN's PRE.
  // It requires domination tree analysis, so for this simple case it is an
  // overkill.
  if (PredsScanned.size() != AvailablePreds.size() &&
      !isSafeToSpeculativelyExecute(LoadI))
    for (auto I = LoadBB->begin(); &*I != LoadI; ++I)
      if (!isGuaranteedToTransferExecutionToSuccessor(&*I))
        return false;

  // If there is exactly one predecessor where the value is unavailable, the
  // already computed 'OneUnavailablePred' block is it.  If it ends in an
  // unconditional branch, we know that it isn't a critical edge.
  if (PredsScanned.size() == AvailablePreds.size()+1 &&
      OneUnavailablePred->getTerminator()->getNumSuccessors() == 1) {
    UnavailablePred = OneUnavailablePred;
  } else if (PredsScanned.size() != AvailablePreds.size()) {
    // Otherwise, we had multiple unavailable predecessors or we had a critical
    // edge from the one.
    SmallVector<BasicBlock*, 8> PredsToSplit;
    SmallPtrSet<BasicBlock*, 8> AvailablePredSet;

    for (const auto &AvailablePred : AvailablePreds)
      AvailablePredSet.insert(AvailablePred.first);

    // Add all the unavailable predecessors to the PredsToSplit list.
    for (BasicBlock *P : predecessors(LoadBB)) {
      // If the predecessor is an indirect goto, we can't split the edge.
      // Same for CallBr.
      if (isa<IndirectBrInst>(P->getTerminator()) ||
          isa<CallBrInst>(P->getTerminator()))
        return false;

      if (!AvailablePredSet.count(P))
        PredsToSplit.push_back(P);
    }

    // Split them out to their own block.
    UnavailablePred = splitBlockPreds(LoadBB, PredsToSplit, "thread-pre-split");
  }

  // If the value isn't available in all predecessors, then there will be
  // exactly one where it isn't available.  Insert a load on that edge and add
  // it to the AvailablePreds list.
  if (UnavailablePred) {
    assert(UnavailablePred->getTerminator()->getNumSuccessors() == 1 &&
           "Can't handle critical edge here!");
    LoadInst *NewVal = new LoadInst(
        LoadI->getType(), LoadedPtr->DoPHITranslation(LoadBB, UnavailablePred),
        LoadI->getName() + ".pr", false, LoadI->getAlign(),
        LoadI->getOrdering(), LoadI->getSyncScopeID(),
        UnavailablePred->getTerminator());
    NewVal->setDebugLoc(LoadI->getDebugLoc());
    if (AATags)
      NewVal->setAAMetadata(AATags);

    AvailablePreds.emplace_back(UnavailablePred, NewVal);
  }

  // Now we know that each predecessor of this block has a value in
  // AvailablePreds, sort them for efficient access as we're walking the preds.
  array_pod_sort(AvailablePreds.begin(), AvailablePreds.end());

  // Create a PHI node at the start of the block for the PRE'd load value.
  pred_iterator PB = pred_begin(LoadBB), PE = pred_end(LoadBB);
  PHINode *PN = PHINode::Create(LoadI->getType(), std::distance(PB, PE), "",
                                &LoadBB->front());
  PN->takeName(LoadI);
  PN->setDebugLoc(LoadI->getDebugLoc());

  // Insert new entries into the PHI for each predecessor.  A single block may
  // have multiple entries here.
  for (pred_iterator PI = PB; PI != PE; ++PI) {
    BasicBlock *P = *PI;
    AvailablePredsTy::iterator I =
        llvm::lower_bound(AvailablePreds, std::make_pair(P, (Value *)nullptr));

    assert(I != AvailablePreds.end() && I->first == P &&
           "Didn't find entry for predecessor!");

    // If we have an available predecessor but it requires casting, insert the
    // cast in the predecessor and use the cast. Note that we have to update the
    // AvailablePreds vector as we go so that all of the PHI entries for this
    // predecessor use the same bitcast.
    Value *&PredV = I->second;
    if (PredV->getType() != LoadI->getType())
      PredV = CastInst::CreateBitOrPointerCast(PredV, LoadI->getType(), "",
                                               P->getTerminator());

    PN->addIncoming(PredV, I->first);
  }

  for (LoadInst *PredLoadI : CSELoads) {
    combineMetadataForCSE(PredLoadI, LoadI, true);
  }

  LoadI->replaceAllUsesWith(PN);
  LoadI->eraseFromParent();

  return true;
}

/// findMostPopularDest - The specified list contains multiple possible
/// threadable destinations.  Pick the one that occurs the most frequently in
/// the list.
static BasicBlock *
findMostPopularDest(BasicBlock *BB,
                    const SmallVectorImpl<std::pair<BasicBlock *,
                                          BasicBlock *>> &PredToDestList) {
  assert(!PredToDestList.empty());

  // Determine popularity.  If there are multiple possible destinations, we
  // explicitly choose to ignore 'undef' destinations.  We prefer to thread
  // blocks with known and real destinations to threading undef.  We'll handle
  // them later if interesting.
  MapVector<BasicBlock *, unsigned> DestPopularity;

  // Populate DestPopularity with the successors in the order they appear in the
  // successor list.  This way, we ensure determinism by iterating it in the
  // same order in std::max_element below.  We map nullptr to 0 so that we can
  // return nullptr when PredToDestList contains nullptr only.
  DestPopularity[nullptr] = 0;
  for (auto *SuccBB : successors(BB))
    DestPopularity[SuccBB] = 0;

  for (const auto &PredToDest : PredToDestList)
    if (PredToDest.second)
      DestPopularity[PredToDest.second]++;

  // Find the most popular dest.
  using VT = decltype(DestPopularity)::value_type;
  auto MostPopular = std::max_element(
      DestPopularity.begin(), DestPopularity.end(),
      [](const VT &L, const VT &R) { return L.second < R.second; });

  // Okay, we have finally picked the most popular destination.
  return MostPopular->first;
}

// Try to evaluate the value of V when the control flows from PredPredBB to
// BB->getSinglePredecessor() and then on to BB.
Constant *JumpThreadingPass::evaluateOnPredecessorEdge(BasicBlock *BB,
                                                       BasicBlock *PredPredBB,
                                                       Value *V) {
  BasicBlock *PredBB = BB->getSinglePredecessor();
  assert(PredBB && "Expected a single predecessor");

  if (Constant *Cst = dyn_cast<Constant>(V)) {
    return Cst;
  }

  // Consult LVI if V is not an instruction in BB or PredBB.
  Instruction *I = dyn_cast<Instruction>(V);
  if (!I || (I->getParent() != BB && I->getParent() != PredBB)) {
    return LVI->getConstantOnEdge(V, PredPredBB, PredBB, nullptr);
  }

  // Look into a PHI argument.
  if (PHINode *PHI = dyn_cast<PHINode>(V)) {
    if (PHI->getParent() == PredBB)
      return dyn_cast<Constant>(PHI->getIncomingValueForBlock(PredPredBB));
    return nullptr;
  }

  // If we have a CmpInst, try to fold it for each incoming edge into PredBB.
  if (CmpInst *CondCmp = dyn_cast<CmpInst>(V)) {
    if (CondCmp->getParent() == BB) {
      Constant *Op0 =
          evaluateOnPredecessorEdge(BB, PredPredBB, CondCmp->getOperand(0));
      Constant *Op1 =
          evaluateOnPredecessorEdge(BB, PredPredBB, CondCmp->getOperand(1));
      if (Op0 && Op1) {
        return ConstantExpr::getCompare(CondCmp->getPredicate(), Op0, Op1);
      }
    }
    return nullptr;
  }

  return nullptr;
}

bool JumpThreadingPass::processThreadableEdges(Value *Cond, BasicBlock *BB,
                                               ConstantPreference Preference,
                                               Instruction *CxtI) {
  // If threading this would thread across a loop header, don't even try to
  // thread the edge.
  if (LoopHeaders.count(BB))
    return false;

  PredValueInfoTy PredValues;
  if (!computeValueKnownInPredecessors(Cond, BB, PredValues, Preference,
                                       CxtI)) {
    // We don't have known values in predecessors.  See if we can thread through
    // BB and its sole predecessor.
    return maybethreadThroughTwoBasicBlocks(BB, Cond);
  }

  assert(!PredValues.empty() &&
         "computeValueKnownInPredecessors returned true with no values");

  LLVM_DEBUG(dbgs() << "IN BB: " << *BB;
             for (const auto &PredValue : PredValues) {
               dbgs() << "  BB '" << BB->getName()
                      << "': FOUND condition = " << *PredValue.first
                      << " for pred '" << PredValue.second->getName() << "'.\n";
  });

  // Decide what we want to thread through.  Convert our list of known values to
  // a list of known destinations for each pred.  This also discards duplicate
  // predecessors and keeps track of the undefined inputs (which are represented
  // as a null dest in the PredToDestList).
  SmallPtrSet<BasicBlock*, 16> SeenPreds;
  SmallVector<std::pair<BasicBlock*, BasicBlock*>, 16> PredToDestList;

  BasicBlock *OnlyDest = nullptr;
  BasicBlock *MultipleDestSentinel = (BasicBlock*)(intptr_t)~0ULL;
  Constant *OnlyVal = nullptr;
  Constant *MultipleVal = (Constant *)(intptr_t)~0ULL;

  for (const auto &PredValue : PredValues) {
    BasicBlock *Pred = PredValue.second;
    if (!SeenPreds.insert(Pred).second)
      continue;  // Duplicate predecessor entry.

    Constant *Val = PredValue.first;

    BasicBlock *DestBB;
    if (isa<UndefValue>(Val))
      DestBB = nullptr;
    else if (BranchInst *BI = dyn_cast<BranchInst>(BB->getTerminator())) {
      assert(isa<ConstantInt>(Val) && "Expecting a constant integer");
      DestBB = BI->getSuccessor(cast<ConstantInt>(Val)->isZero());
    } else if (SwitchInst *SI = dyn_cast<SwitchInst>(BB->getTerminator())) {
      assert(isa<ConstantInt>(Val) && "Expecting a constant integer");
      DestBB = SI->findCaseValue(cast<ConstantInt>(Val))->getCaseSuccessor();
    } else {
      assert(isa<IndirectBrInst>(BB->getTerminator())
              && "Unexpected terminator");
      assert(isa<BlockAddress>(Val) && "Expecting a constant blockaddress");
      DestBB = cast<BlockAddress>(Val)->getBasicBlock();
    }

    // If we have exactly one destination, remember it for efficiency below.
    if (PredToDestList.empty()) {
      OnlyDest = DestBB;
      OnlyVal = Val;
    } else {
      if (OnlyDest != DestBB)
        OnlyDest = MultipleDestSentinel;
      // It possible we have same destination, but different value, e.g. default
      // case in switchinst.
      if (Val != OnlyVal)
        OnlyVal = MultipleVal;
    }

    // If the predecessor ends with an indirect goto, we can't change its
    // destination. Same for CallBr.
    if (isa<IndirectBrInst>(Pred->getTerminator()) ||
        isa<CallBrInst>(Pred->getTerminator()))
      continue;

    PredToDestList.emplace_back(Pred, DestBB);
  }

  // If all edges were unthreadable, we fail.
  if (PredToDestList.empty())
    return false;

  // If all the predecessors go to a single known successor, we want to fold,
  // not thread. By doing so, we do not need to duplicate the current block and
  // also miss potential opportunities in case we dont/cant duplicate.
  if (OnlyDest && OnlyDest != MultipleDestSentinel) {
    if (BB->hasNPredecessors(PredToDestList.size())) {
      bool SeenFirstBranchToOnlyDest = false;
      std::vector <DominatorTree::UpdateType> Updates;
      Updates.reserve(BB->getTerminator()->getNumSuccessors() - 1);
      for (BasicBlock *SuccBB : successors(BB)) {
        if (SuccBB == OnlyDest && !SeenFirstBranchToOnlyDest) {
          SeenFirstBranchToOnlyDest = true; // Don't modify the first branch.
        } else {
          SuccBB->removePredecessor(BB, true); // This is unreachable successor.
          Updates.push_back({DominatorTree::Delete, BB, SuccBB});
        }
      }

      // Finally update the terminator.
      Instruction *Term = BB->getTerminator();
      BranchInst::Create(OnlyDest, Term);
      ++NumFolds;
      Term->eraseFromParent();
      DTU->applyUpdatesPermissive(Updates);
      if (HasProfileData)
        BPI->eraseBlock(BB);

      // If the condition is now dead due to the removal of the old terminator,
      // erase it.
      if (auto *CondInst = dyn_cast<Instruction>(Cond)) {
        if (CondInst->use_empty() && !CondInst->mayHaveSideEffects())
          CondInst->eraseFromParent();
        // We can safely replace *some* uses of the CondInst if it has
        // exactly one value as returned by LVI. RAUW is incorrect in the
        // presence of guards and assumes, that have the `Cond` as the use. This
        // is because we use the guards/assume to reason about the `Cond` value
        // at the end of block, but RAUW unconditionally replaces all uses
        // including the guards/assumes themselves and the uses before the
        // guard/assume.
        else if (OnlyVal && OnlyVal != MultipleVal &&
                 CondInst->getParent() == BB)
          replaceFoldableUses(CondInst, OnlyVal);
      }
      return true;
    }
  }

  // Determine which is the most common successor.  If we have many inputs and
  // this block is a switch, we want to start by threading the batch that goes
  // to the most popular destination first.  If we only know about one
  // threadable destination (the common case) we can avoid this.
  BasicBlock *MostPopularDest = OnlyDest;

  if (MostPopularDest == MultipleDestSentinel) {
    // Remove any loop headers from the Dest list, threadEdge conservatively
    // won't process them, but we might have other destination that are eligible
    // and we still want to process.
    erase_if(PredToDestList,
             [&](const std::pair<BasicBlock *, BasicBlock *> &PredToDest) {
               return LoopHeaders.contains(PredToDest.second);
             });

    if (PredToDestList.empty())
      return false;

    MostPopularDest = findMostPopularDest(BB, PredToDestList);
  }

  // Now that we know what the most popular destination is, factor all
  // predecessors that will jump to it into a single predecessor.
  SmallVector<BasicBlock*, 16> PredsToFactor;
  for (const auto &PredToDest : PredToDestList)
    if (PredToDest.second == MostPopularDest) {
      BasicBlock *Pred = PredToDest.first;

      // This predecessor may be a switch or something else that has multiple
      // edges to the block.  Factor each of these edges by listing them
      // according to # occurrences in PredsToFactor.
      for (BasicBlock *Succ : successors(Pred))
        if (Succ == BB)
          PredsToFactor.push_back(Pred);
    }

  // If the threadable edges are branching on an undefined value, we get to pick
  // the destination that these predecessors should get to.
  if (!MostPopularDest)
    MostPopularDest = BB->getTerminator()->
                            getSuccessor(getBestDestForJumpOnUndef(BB));

  // Ok, try to thread it!
  return tryThreadEdge(BB, PredsToFactor, MostPopularDest);
}

/// processBranchOnPHI - We have an otherwise unthreadable conditional branch on
/// a PHI node (or freeze PHI) in the current block.  See if there are any
/// simplifications we can do based on inputs to the phi node.
bool JumpThreadingPass::processBranchOnPHI(PHINode *PN) {
  BasicBlock *BB = PN->getParent();

  // TODO: We could make use of this to do it once for blocks with common PHI
  // values.
  SmallVector<BasicBlock*, 1> PredBBs;
  PredBBs.resize(1);

  // If any of the predecessor blocks end in an unconditional branch, we can
  // *duplicate* the conditional branch into that block in order to further
  // encourage jump threading and to eliminate cases where we have branch on a
  // phi of an icmp (branch on icmp is much better).
  // This is still beneficial when a frozen phi is used as the branch condition
  // because it allows CodeGenPrepare to further canonicalize br(freeze(icmp))
  // to br(icmp(freeze ...)).
  for (unsigned i = 0, e = PN->getNumIncomingValues(); i != e; ++i) {
    BasicBlock *PredBB = PN->getIncomingBlock(i);
    if (BranchInst *PredBr = dyn_cast<BranchInst>(PredBB->getTerminator()))
      if (PredBr->isUnconditional()) {
        PredBBs[0] = PredBB;
        // Try to duplicate BB into PredBB.
        if (duplicateCondBranchOnPHIIntoPred(BB, PredBBs))
          return true;
      }
  }

  return false;
}

/// processBranchOnXOR - We have an otherwise unthreadable conditional branch on
/// a xor instruction in the current block.  See if there are any
/// simplifications we can do based on inputs to the xor.
bool JumpThreadingPass::processBranchOnXOR(BinaryOperator *BO) {
  BasicBlock *BB = BO->getParent();

  // If either the LHS or RHS of the xor is a constant, don't do this
  // optimization.
  if (isa<ConstantInt>(BO->getOperand(0)) ||
      isa<ConstantInt>(BO->getOperand(1)))
    return false;

  // If the first instruction in BB isn't a phi, we won't be able to infer
  // anything special about any particular predecessor.
  if (!isa<PHINode>(BB->front()))
    return false;

  // If this BB is a landing pad, we won't be able to split the edge into it.
  if (BB->isEHPad())
    return false;

  // If we have a xor as the branch input to this block, and we know that the
  // LHS or RHS of the xor in any predecessor is true/false, then we can clone
  // the condition into the predecessor and fix that value to true, saving some
  // logical ops on that path and encouraging other paths to simplify.
  //
  // This copies something like this:
  //
  //  BB:
  //    %X = phi i1 [1],  [%X']
  //    %Y = icmp eq i32 %A, %B
  //    %Z = xor i1 %X, %Y
  //    br i1 %Z, ...
  //
  // Into:
  //  BB':
  //    %Y = icmp ne i32 %A, %B
  //    br i1 %Y, ...

  PredValueInfoTy XorOpValues;
  bool isLHS = true;
  if (!computeValueKnownInPredecessors(BO->getOperand(0), BB, XorOpValues,
                                       WantInteger, BO)) {
    assert(XorOpValues.empty());
    if (!computeValueKnownInPredecessors(BO->getOperand(1), BB, XorOpValues,
                                         WantInteger, BO))
      return false;
    isLHS = false;
  }

  assert(!XorOpValues.empty() &&
         "computeValueKnownInPredecessors returned true with no values");

  // Scan the information to see which is most popular: true or false.  The
  // predecessors can be of the set true, false, or undef.
  unsigned NumTrue = 0, NumFalse = 0;
  for (const auto &XorOpValue : XorOpValues) {
    if (isa<UndefValue>(XorOpValue.first))
      // Ignore undefs for the count.
      continue;
    if (cast<ConstantInt>(XorOpValue.first)->isZero())
      ++NumFalse;
    else
      ++NumTrue;
  }

  // Determine which value to split on, true, false, or undef if neither.
  ConstantInt *SplitVal = nullptr;
  if (NumTrue > NumFalse)
    SplitVal = ConstantInt::getTrue(BB->getContext());
  else if (NumTrue != 0 || NumFalse != 0)
    SplitVal = ConstantInt::getFalse(BB->getContext());

  // Collect all of the blocks that this can be folded into so that we can
  // factor this once and clone it once.
  SmallVector<BasicBlock*, 8> BlocksToFoldInto;
  for (const auto &XorOpValue : XorOpValues) {
    if (XorOpValue.first != SplitVal && !isa<UndefValue>(XorOpValue.first))
      continue;

    BlocksToFoldInto.push_back(XorOpValue.second);
  }

  // If we inferred a value for all of the predecessors, then duplication won't
  // help us.  However, we can just replace the LHS or RHS with the constant.
  if (BlocksToFoldInto.size() ==
      cast<PHINode>(BB->front()).getNumIncomingValues()) {
    if (!SplitVal) {
      // If all preds provide undef, just nuke the xor, because it is undef too.
      BO->replaceAllUsesWith(UndefValue::get(BO->getType()));
      BO->eraseFromParent();
    } else if (SplitVal->isZero()) {
      // If all preds provide 0, replace the xor with the other input.
      BO->replaceAllUsesWith(BO->getOperand(isLHS));
      BO->eraseFromParent();
    } else {
      // If all preds provide 1, set the computed value to 1.
      BO->setOperand(!isLHS, SplitVal);
    }

    return true;
  }

  // If any of predecessors end with an indirect goto, we can't change its
  // destination. Same for CallBr.
  if (any_of(BlocksToFoldInto, [](BasicBlock *Pred) {
        return isa<IndirectBrInst>(Pred->getTerminator()) ||
               isa<CallBrInst>(Pred->getTerminator());
      }))
    return false;

  // Try to duplicate BB into PredBB.
  return duplicateCondBranchOnPHIIntoPred(BB, BlocksToFoldInto);
}

/// addPHINodeEntriesForMappedBlock - We're adding 'NewPred' as a new
/// predecessor to the PHIBB block.  If it has PHI nodes, add entries for
/// NewPred using the entries from OldPred (suitably mapped).
static void addPHINodeEntriesForMappedBlock(BasicBlock *PHIBB,
                                            BasicBlock *OldPred,
                                            BasicBlock *NewPred,
                                     DenseMap<Instruction*, Value*> &ValueMap) {
  for (PHINode &PN : PHIBB->phis()) {
    // Ok, we have a PHI node.  Figure out what the incoming value was for the
    // DestBlock.
    Value *IV = PN.getIncomingValueForBlock(OldPred);

    // Remap the value if necessary.
    if (Instruction *Inst = dyn_cast<Instruction>(IV)) {
      DenseMap<Instruction*, Value*>::iterator I = ValueMap.find(Inst);
      if (I != ValueMap.end())
        IV = I->second;
    }

    PN.addIncoming(IV, NewPred);
  }
}

/// Merge basic block BB into its sole predecessor if possible.
bool JumpThreadingPass::maybeMergeBasicBlockIntoOnlyPred(BasicBlock *BB) {
  BasicBlock *SinglePred = BB->getSinglePredecessor();
  if (!SinglePred)
    return false;

  const Instruction *TI = SinglePred->getTerminator();
  if (TI->isExceptionalTerminator() || TI->getNumSuccessors() != 1 ||
      SinglePred == BB || hasAddressTakenAndUsed(BB))
    return false;

  // If SinglePred was a loop header, BB becomes one.
  if (LoopHeaders.erase(SinglePred))
    LoopHeaders.insert(BB);

  LVI->eraseBlock(SinglePred);
  MergeBasicBlockIntoOnlyPred(BB, DTU);

  // Now that BB is merged into SinglePred (i.e. SinglePred code followed by
  // BB code within one basic block `BB`), we need to invalidate the LVI
  // information associated with BB, because the LVI information need not be
  // true for all of BB after the merge. For example,
  // Before the merge, LVI info and code is as follows:
  // SinglePred: <LVI info1 for %p val>
  // %y = use of %p
  // call @exit() // need not transfer execution to successor.
  // assume(%p) // from this point on %p is true
  // br label %BB
  // BB: <LVI info2 for %p val, i.e. %p is true>
  // %x = use of %p
  // br label exit
  //
  // Note that this LVI info for blocks BB and SinglPred is correct for %p
  // (info2 and info1 respectively). After the merge and the deletion of the
  // LVI info1 for SinglePred. We have the following code:
  // BB: <LVI info2 for %p val>
  // %y = use of %p
  // call @exit()
  // assume(%p)
  // %x = use of %p <-- LVI info2 is correct from here onwards.
  // br label exit
  // LVI info2 for BB is incorrect at the beginning of BB.

  // Invalidate LVI information for BB if the LVI is not provably true for
  // all of BB.
  if (!isGuaranteedToTransferExecutionToSuccessor(BB))
    LVI->eraseBlock(BB);
  return true;
}

/// Update the SSA form.  NewBB contains instructions that are copied from BB.
/// ValueMapping maps old values in BB to new ones in NewBB.
void JumpThreadingPass::updateSSA(
    BasicBlock *BB, BasicBlock *NewBB,
    DenseMap<Instruction *, Value *> &ValueMapping) {
  // If there were values defined in BB that are used outside the block, then we
  // now have to update all uses of the value to use either the original value,
  // the cloned value, or some PHI derived value.  This can require arbitrary
  // PHI insertion, of which we are prepared to do, clean these up now.
  SSAUpdater SSAUpdate;
  SmallVector<Use *, 16> UsesToRename;

  for (Instruction &I : *BB) {
    // Scan all uses of this instruction to see if it is used outside of its
    // block, and if so, record them in UsesToRename.
    for (Use &U : I.uses()) {
      Instruction *User = cast<Instruction>(U.getUser());
      if (PHINode *UserPN = dyn_cast<PHINode>(User)) {
        if (UserPN->getIncomingBlock(U) == BB)
          continue;
      } else if (User->getParent() == BB)
        continue;

      UsesToRename.push_back(&U);
    }

    // If there are no uses outside the block, we're done with this instruction.
    if (UsesToRename.empty())
      continue;
    LLVM_DEBUG(dbgs() << "JT: Renaming non-local uses of: " << I << "\n");

    // We found a use of I outside of BB.  Rename all uses of I that are outside
    // its block to be uses of the appropriate PHI node etc.  See ValuesInBlocks
    // with the two values we know.
    SSAUpdate.Initialize(I.getType(), I.getName());
    SSAUpdate.AddAvailableValue(BB, &I);
    SSAUpdate.AddAvailableValue(NewBB, ValueMapping[&I]);

    while (!UsesToRename.empty())
      SSAUpdate.RewriteUse(*UsesToRename.pop_back_val());
    LLVM_DEBUG(dbgs() << "\n");
  }
}

/// Clone instructions in range [BI, BE) to NewBB.  For PHI nodes, we only clone
/// arguments that come from PredBB.  Return the map from the variables in the
/// source basic block to the variables in the newly created basic block.
DenseMap<Instruction *, Value *>
JumpThreadingPass::cloneInstructions(BasicBlock::iterator BI,
                                     BasicBlock::iterator BE, BasicBlock *NewBB,
                                     BasicBlock *PredBB) {
  // We are going to have to map operands from the source basic block to the new
  // copy of the block 'NewBB'.  If there are PHI nodes in the source basic
  // block, evaluate them to account for entry from PredBB.
  DenseMap<Instruction *, Value *> ValueMapping;

  // Clone the phi nodes of the source basic block into NewBB.  The resulting
  // phi nodes are trivial since NewBB only has one predecessor, but SSAUpdater
  // might need to rewrite the operand of the cloned phi.
  for (; PHINode *PN = dyn_cast<PHINode>(BI); ++BI) {
    PHINode *NewPN = PHINode::Create(PN->getType(), 1, PN->getName(), NewBB);
    NewPN->addIncoming(PN->getIncomingValueForBlock(PredBB), PredBB);
    ValueMapping[PN] = NewPN;
  }

  // Clone noalias scope declarations in the threaded block. When threading a
  // loop exit, we would otherwise end up with two idential scope declarations
  // visible at the same time.
  SmallVector<MDNode *> NoAliasScopes;
  DenseMap<MDNode *, MDNode *> ClonedScopes;
  LLVMContext &Context = PredBB->getContext();
  identifyNoAliasScopesToClone(BI, BE, NoAliasScopes);
  cloneNoAliasScopes(NoAliasScopes, ClonedScopes, "thread", Context);

  // Clone the non-phi instructions of the source basic block into NewBB,
  // keeping track of the mapping and using it to remap operands in the cloned
  // instructions.
  for (; BI != BE; ++BI) {
    Instruction *New = BI->clone();
    New->setName(BI->getName());
    NewBB->getInstList().push_back(New);
    ValueMapping[&*BI] = New;
    adaptNoAliasScopes(New, ClonedScopes, Context);

    // Remap operands to patch up intra-block references.
    for (unsigned i = 0, e = New->getNumOperands(); i != e; ++i)
      if (Instruction *Inst = dyn_cast<Instruction>(New->getOperand(i))) {
        DenseMap<Instruction *, Value *>::iterator I = ValueMapping.find(Inst);
        if (I != ValueMapping.end())
          New->setOperand(i, I->second);
      }
  }

  return ValueMapping;
}

/// Attempt to thread through two successive basic blocks.
bool JumpThreadingPass::maybethreadThroughTwoBasicBlocks(BasicBlock *BB,
                                                         Value *Cond) {
  // Consider:
  //
  // PredBB:
  //   %var = phi i32* [ null, %bb1 ], [ @a, %bb2 ]
  //   %tobool = icmp eq i32 %cond, 0
  //   br i1 %tobool, label %BB, label ...
  //
  // BB:
  //   %cmp = icmp eq i32* %var, null
  //   br i1 %cmp, label ..., label ...
  //
  // We don't know the value of %var at BB even if we know which incoming edge
  // we take to BB.  However, once we duplicate PredBB for each of its incoming
  // edges (say, PredBB1 and PredBB2), we know the value of %var in each copy of
  // PredBB.  Then we can thread edges PredBB1->BB and PredBB2->BB through BB.

  // Require that BB end with a Branch for simplicity.
  BranchInst *CondBr = dyn_cast<BranchInst>(BB->getTerminator());
  if (!CondBr)
    return false;

  // BB must have exactly one predecessor.
  BasicBlock *PredBB = BB->getSinglePredecessor();
  if (!PredBB)
    return false;

  // Require that PredBB end with a conditional Branch. If PredBB ends with an
  // unconditional branch, we should be merging PredBB and BB instead. For
  // simplicity, we don't deal with a switch.
  BranchInst *PredBBBranch = dyn_cast<BranchInst>(PredBB->getTerminator());
  if (!PredBBBranch || PredBBBranch->isUnconditional())
    return false;

  // If PredBB has exactly one incoming edge, we don't gain anything by copying
  // PredBB.
  if (PredBB->getSinglePredecessor())
    return false;

  // Don't thread through PredBB if it contains a successor edge to itself, in
  // which case we would infinite loop.  Suppose we are threading an edge from
  // PredPredBB through PredBB and BB to SuccBB with PredBB containing a
  // successor edge to itself.  If we allowed jump threading in this case, we
  // could duplicate PredBB and BB as, say, PredBB.thread and BB.thread.  Since
  // PredBB.thread has a successor edge to PredBB, we would immediately come up
  // with another jump threading opportunity from PredBB.thread through PredBB
  // and BB to SuccBB.  This jump threading would repeatedly occur.  That is, we
  // would keep peeling one iteration from PredBB.
  if (llvm::is_contained(successors(PredBB), PredBB))
    return false;

  // Don't thread across a loop header.
  if (LoopHeaders.count(PredBB))
    return false;

  // Avoid complication with duplicating EH pads.
  if (PredBB->isEHPad())
    return false;

  // Find a predecessor that we can thread.  For simplicity, we only consider a
  // successor edge out of BB to which we thread exactly one incoming edge into
  // PredBB.
  unsigned ZeroCount = 0;
  unsigned OneCount = 0;
  BasicBlock *ZeroPred = nullptr;
  BasicBlock *OnePred = nullptr;
  for (BasicBlock *P : predecessors(PredBB)) {
    if (ConstantInt *CI = dyn_cast_or_null<ConstantInt>(
            evaluateOnPredecessorEdge(BB, P, Cond))) {
      if (CI->isZero()) {
        ZeroCount++;
        ZeroPred = P;
      } else if (CI->isOne()) {
        OneCount++;
        OnePred = P;
      }
    }
  }

  // Disregard complicated cases where we have to thread multiple edges.
  BasicBlock *PredPredBB;
  if (ZeroCount == 1) {
    PredPredBB = ZeroPred;
  } else if (OneCount == 1) {
    PredPredBB = OnePred;
  } else {
    return false;
  }

  BasicBlock *SuccBB = CondBr->getSuccessor(PredPredBB == ZeroPred);

  // If threading to the same block as we come from, we would infinite loop.
  if (SuccBB == BB) {
    LLVM_DEBUG(dbgs() << "  Not threading across BB '" << BB->getName()
                      << "' - would thread to self!\n");
    return false;
  }

  // If threading this would thread across a loop header, don't thread the edge.
  // See the comments above findLoopHeaders for justifications and caveats.
  if (LoopHeaders.count(BB) || LoopHeaders.count(SuccBB)) {
    LLVM_DEBUG({
      bool BBIsHeader = LoopHeaders.count(BB);
      bool SuccIsHeader = LoopHeaders.count(SuccBB);
      dbgs() << "  Not threading across "
             << (BBIsHeader ? "loop header BB '" : "block BB '")
             << BB->getName() << "' to dest "
             << (SuccIsHeader ? "loop header BB '" : "block BB '")
             << SuccBB->getName()
             << "' - it might create an irreducible loop!\n";
    });
    return false;
  }

  // Compute the cost of duplicating BB and PredBB.
  unsigned BBCost = getJumpThreadDuplicationCost(
      TTI, BB, BB->getTerminator(), BBDupThreshold);
  unsigned PredBBCost = getJumpThreadDuplicationCost(
      TTI, PredBB, PredBB->getTerminator(), BBDupThreshold);

  // Give up if costs are too high.  We need to check BBCost and PredBBCost
  // individually before checking their sum because getJumpThreadDuplicationCost
  // return (unsigned)~0 for those basic blocks that cannot be duplicated.
  if (BBCost > BBDupThreshold || PredBBCost > BBDupThreshold ||
      BBCost + PredBBCost > BBDupThreshold) {
    LLVM_DEBUG(dbgs() << "  Not threading BB '" << BB->getName()
                      << "' - Cost is too high: " << PredBBCost
                      << " for PredBB, " << BBCost << "for BB\n");
    return false;
  }

  // Now we are ready to duplicate PredBB.
  threadThroughTwoBasicBlocks(PredPredBB, PredBB, BB, SuccBB);
  return true;
}

void JumpThreadingPass::threadThroughTwoBasicBlocks(BasicBlock *PredPredBB,
                                                    BasicBlock *PredBB,
                                                    BasicBlock *BB,
                                                    BasicBlock *SuccBB) {
  LLVM_DEBUG(dbgs() << "  Threading through '" << PredBB->getName() << "' and '"
                    << BB->getName() << "'\n");

  BranchInst *CondBr = cast<BranchInst>(BB->getTerminator());
  BranchInst *PredBBBranch = cast<BranchInst>(PredBB->getTerminator());

  BasicBlock *NewBB =
      BasicBlock::Create(PredBB->getContext(), PredBB->getName() + ".thread",
                         PredBB->getParent(), PredBB);
  NewBB->moveAfter(PredBB);

  // Set the block frequency of NewBB.
  if (HasProfileData) {
    auto NewBBFreq = BFI->getBlockFreq(PredPredBB) *
                     BPI->getEdgeProbability(PredPredBB, PredBB);
    BFI->setBlockFreq(NewBB, NewBBFreq.getFrequency());
  }

  // We are going to have to map operands from the original BB block to the new
  // copy of the block 'NewBB'.  If there are PHI nodes in PredBB, evaluate them
  // to account for entry from PredPredBB.
  DenseMap<Instruction *, Value *> ValueMapping =
      cloneInstructions(PredBB->begin(), PredBB->end(), NewBB, PredPredBB);

  // Copy the edge probabilities from PredBB to NewBB.
  if (HasProfileData)
    BPI->copyEdgeProbabilities(PredBB, NewBB);

  // Update the terminator of PredPredBB to jump to NewBB instead of PredBB.
  // This eliminates predecessors from PredPredBB, which requires us to simplify
  // any PHI nodes in PredBB.
  Instruction *PredPredTerm = PredPredBB->getTerminator();
  for (unsigned i = 0, e = PredPredTerm->getNumSuccessors(); i != e; ++i)
    if (PredPredTerm->getSuccessor(i) == PredBB) {
      PredBB->removePredecessor(PredPredBB, true);
      PredPredTerm->setSuccessor(i, NewBB);
    }

  addPHINodeEntriesForMappedBlock(PredBBBranch->getSuccessor(0), PredBB, NewBB,
                                  ValueMapping);
  addPHINodeEntriesForMappedBlock(PredBBBranch->getSuccessor(1), PredBB, NewBB,
                                  ValueMapping);

  DTU->applyUpdatesPermissive(
      {{DominatorTree::Insert, NewBB, CondBr->getSuccessor(0)},
       {DominatorTree::Insert, NewBB, CondBr->getSuccessor(1)},
       {DominatorTree::Insert, PredPredBB, NewBB},
       {DominatorTree::Delete, PredPredBB, PredBB}});

  updateSSA(PredBB, NewBB, ValueMapping);

  // Clean up things like PHI nodes with single operands, dead instructions,
  // etc.
  SimplifyInstructionsInBlock(NewBB, TLI);
  SimplifyInstructionsInBlock(PredBB, TLI);

  SmallVector<BasicBlock *, 1> PredsToFactor;
  PredsToFactor.push_back(NewBB);
  threadEdge(BB, PredsToFactor, SuccBB);
}

/// tryThreadEdge - Thread an edge if it's safe and profitable to do so.
bool JumpThreadingPass::tryThreadEdge(
    BasicBlock *BB, const SmallVectorImpl<BasicBlock *> &PredBBs,
    BasicBlock *SuccBB) {
  // If threading to the same block as we come from, we would infinite loop.
  if (SuccBB == BB) {
    LLVM_DEBUG(dbgs() << "  Not threading across BB '" << BB->getName()
                      << "' - would thread to self!\n");
    return false;
  }

  // If threading this would thread across a loop header, don't thread the edge.
  // See the comments above findLoopHeaders for justifications and caveats.
  if (LoopHeaders.count(BB) || LoopHeaders.count(SuccBB)) {
    LLVM_DEBUG({
      bool BBIsHeader = LoopHeaders.count(BB);
      bool SuccIsHeader = LoopHeaders.count(SuccBB);
      dbgs() << "  Not threading across "
          << (BBIsHeader ? "loop header BB '" : "block BB '") << BB->getName()
          << "' to dest " << (SuccIsHeader ? "loop header BB '" : "block BB '")
          << SuccBB->getName() << "' - it might create an irreducible loop!\n";
    });
    return false;
  }

  unsigned JumpThreadCost = getJumpThreadDuplicationCost(
      TTI, BB, BB->getTerminator(), BBDupThreshold);
  if (JumpThreadCost > BBDupThreshold) {
    LLVM_DEBUG(dbgs() << "  Not threading BB '" << BB->getName()
                      << "' - Cost is too high: " << JumpThreadCost << "\n");
    return false;
  }

  threadEdge(BB, PredBBs, SuccBB);
  return true;
}

/// threadEdge - We have decided that it is safe and profitable to factor the
/// blocks in PredBBs to one predecessor, then thread an edge from it to SuccBB
/// across BB.  Transform the IR to reflect this change.
void JumpThreadingPass::threadEdge(BasicBlock *BB,
                                   const SmallVectorImpl<BasicBlock *> &PredBBs,
                                   BasicBlock *SuccBB) {
  assert(SuccBB != BB && "Don't create an infinite loop");

  assert(!LoopHeaders.count(BB) && !LoopHeaders.count(SuccBB) &&
         "Don't thread across loop headers");

  // And finally, do it!  Start by factoring the predecessors if needed.
  BasicBlock *PredBB;
  if (PredBBs.size() == 1)
    PredBB = PredBBs[0];
  else {
    LLVM_DEBUG(dbgs() << "  Factoring out " << PredBBs.size()
                      << " common predecessors.\n");
    PredBB = splitBlockPreds(BB, PredBBs, ".thr_comm");
  }

  // And finally, do it!
  LLVM_DEBUG(dbgs() << "  Threading edge from '" << PredBB->getName()
                    << "' to '" << SuccBB->getName()
                    << ", across block:\n    " << *BB << "\n");

  LVI->threadEdge(PredBB, BB, SuccBB);

  BasicBlock *NewBB = BasicBlock::Create(BB->getContext(),
                                         BB->getName()+".thread",
                                         BB->getParent(), BB);
  NewBB->moveAfter(PredBB);

  // Set the block frequency of NewBB.
  if (HasProfileData) {
    auto NewBBFreq =
        BFI->getBlockFreq(PredBB) * BPI->getEdgeProbability(PredBB, BB);
    BFI->setBlockFreq(NewBB, NewBBFreq.getFrequency());
  }

  // Copy all the instructions from BB to NewBB except the terminator.
  DenseMap<Instruction *, Value *> ValueMapping =
      cloneInstructions(BB->begin(), std::prev(BB->end()), NewBB, PredBB);

  // We didn't copy the terminator from BB over to NewBB, because there is now
  // an unconditional jump to SuccBB.  Insert the unconditional jump.
  BranchInst *NewBI = BranchInst::Create(SuccBB, NewBB);
  NewBI->setDebugLoc(BB->getTerminator()->getDebugLoc());

  // Check to see if SuccBB has PHI nodes. If so, we need to add entries to the
  // PHI nodes for NewBB now.
  addPHINodeEntriesForMappedBlock(SuccBB, BB, NewBB, ValueMapping);

  // Update the terminator of PredBB to jump to NewBB instead of BB.  This
  // eliminates predecessors from BB, which requires us to simplify any PHI
  // nodes in BB.
  Instruction *PredTerm = PredBB->getTerminator();
  for (unsigned i = 0, e = PredTerm->getNumSuccessors(); i != e; ++i)
    if (PredTerm->getSuccessor(i) == BB) {
      BB->removePredecessor(PredBB, true);
      PredTerm->setSuccessor(i, NewBB);
    }

  // Enqueue required DT updates.
  DTU->applyUpdatesPermissive({{DominatorTree::Insert, NewBB, SuccBB},
                               {DominatorTree::Insert, PredBB, NewBB},
                               {DominatorTree::Delete, PredBB, BB}});

  updateSSA(BB, NewBB, ValueMapping);

  // At this point, the IR is fully up to date and consistent.  Do a quick scan
  // over the new instructions and zap any that are constants or dead.  This
  // frequently happens because of phi translation.
  SimplifyInstructionsInBlock(NewBB, TLI);

  // Update the edge weight from BB to SuccBB, which should be less than before.
  updateBlockFreqAndEdgeWeight(PredBB, BB, NewBB, SuccBB);

  // Threaded an edge!
  ++NumThreads;
}

/// Create a new basic block that will be the predecessor of BB and successor of
/// all blocks in Preds. When profile data is available, update the frequency of
/// this new block.
BasicBlock *JumpThreadingPass::splitBlockPreds(BasicBlock *BB,
                                               ArrayRef<BasicBlock *> Preds,
                                               const char *Suffix) {
  SmallVector<BasicBlock *, 2> NewBBs;

  // Collect the frequencies of all predecessors of BB, which will be used to
  // update the edge weight of the result of splitting predecessors.
  DenseMap<BasicBlock *, BlockFrequency> FreqMap;
  if (HasProfileData)
    for (auto Pred : Preds)
      FreqMap.insert(std::make_pair(
          Pred, BFI->getBlockFreq(Pred) * BPI->getEdgeProbability(Pred, BB)));

  // In the case when BB is a LandingPad block we create 2 new predecessors
  // instead of just one.
  if (BB->isLandingPad()) {
    std::string NewName = std::string(Suffix) + ".split-lp";
    SplitLandingPadPredecessors(BB, Preds, Suffix, NewName.c_str(), NewBBs);
  } else {
    NewBBs.push_back(SplitBlockPredecessors(BB, Preds, Suffix));
  }

  std::vector<DominatorTree::UpdateType> Updates;
  Updates.reserve((2 * Preds.size()) + NewBBs.size());
  for (auto NewBB : NewBBs) {
    BlockFrequency NewBBFreq(0);
    Updates.push_back({DominatorTree::Insert, NewBB, BB});
    for (auto Pred : predecessors(NewBB)) {
      Updates.push_back({DominatorTree::Delete, Pred, BB});
      Updates.push_back({DominatorTree::Insert, Pred, NewBB});
      if (HasProfileData) // Update frequencies between Pred -> NewBB.
        NewBBFreq += FreqMap.lookup(Pred);
    }
    if (HasProfileData) // Apply the summed frequency to NewBB.
      BFI->setBlockFreq(NewBB, NewBBFreq.getFrequency());
  }

  DTU->applyUpdatesPermissive(Updates);
  return NewBBs[0];
}

bool JumpThreadingPass::doesBlockHaveProfileData(BasicBlock *BB) {
  const Instruction *TI = BB->getTerminator();
  assert(TI->getNumSuccessors() > 1 && "not a split");

  MDNode *WeightsNode = TI->getMetadata(LLVMContext::MD_prof);
  if (!WeightsNode)
    return false;

  MDString *MDName = cast<MDString>(WeightsNode->getOperand(0));
  if (MDName->getString() != "branch_weights")
    return false;

  // Ensure there are weights for all of the successors. Note that the first
  // operand to the metadata node is a name, not a weight.
  return WeightsNode->getNumOperands() == TI->getNumSuccessors() + 1;
}

/// Update the block frequency of BB and branch weight and the metadata on the
/// edge BB->SuccBB. This is done by scaling the weight of BB->SuccBB by 1 -
/// Freq(PredBB->BB) / Freq(BB->SuccBB).
void JumpThreadingPass::updateBlockFreqAndEdgeWeight(BasicBlock *PredBB,
                                                     BasicBlock *BB,
                                                     BasicBlock *NewBB,
                                                     BasicBlock *SuccBB) {
  if (!HasProfileData)
    return;

  assert(BFI && BPI && "BFI & BPI should have been created here");

  // As the edge from PredBB to BB is deleted, we have to update the block
  // frequency of BB.
  auto BBOrigFreq = BFI->getBlockFreq(BB);
  auto NewBBFreq = BFI->getBlockFreq(NewBB);
  auto BB2SuccBBFreq = BBOrigFreq * BPI->getEdgeProbability(BB, SuccBB);
  auto BBNewFreq = BBOrigFreq - NewBBFreq;
  BFI->setBlockFreq(BB, BBNewFreq.getFrequency());

  // Collect updated outgoing edges' frequencies from BB and use them to update
  // edge probabilities.
  SmallVector<uint64_t, 4> BBSuccFreq;
  for (BasicBlock *Succ : successors(BB)) {
    auto SuccFreq = (Succ == SuccBB)
                        ? BB2SuccBBFreq - NewBBFreq
                        : BBOrigFreq * BPI->getEdgeProbability(BB, Succ);
    BBSuccFreq.push_back(SuccFreq.getFrequency());
  }

  uint64_t MaxBBSuccFreq =
      *std::max_element(BBSuccFreq.begin(), BBSuccFreq.end());

  SmallVector<BranchProbability, 4> BBSuccProbs;
  if (MaxBBSuccFreq == 0)
    BBSuccProbs.assign(BBSuccFreq.size(),
                       {1, static_cast<unsigned>(BBSuccFreq.size())});
  else {
    for (uint64_t Freq : BBSuccFreq)
      BBSuccProbs.push_back(
          BranchProbability::getBranchProbability(Freq, MaxBBSuccFreq));
    // Normalize edge probabilities so that they sum up to one.
    BranchProbability::normalizeProbabilities(BBSuccProbs.begin(),
                                              BBSuccProbs.end());
  }

  // Update edge probabilities in BPI.
  BPI->setEdgeProbability(BB, BBSuccProbs);

  // Update the profile metadata as well.
  //
  // Don't do this if the profile of the transformed blocks was statically
  // estimated.  (This could occur despite the function having an entry
  // frequency in completely cold parts of the CFG.)
  //
  // In this case we don't want to suggest to subsequent passes that the
  // calculated weights are fully consistent.  Consider this graph:
  //
  //                 check_1
  //             50% /  |
  //             eq_1   | 50%
  //                 \  |
  //                 check_2
  //             50% /  |
  //             eq_2   | 50%
  //                 \  |
  //                 check_3
  //             50% /  |
  //             eq_3   | 50%
  //                 \  |
  //
  // Assuming the blocks check_* all compare the same value against 1, 2 and 3,
  // the overall probabilities are inconsistent; the total probability that the
  // value is either 1, 2 or 3 is 150%.
  //
  // As a consequence if we thread eq_1 -> check_2 to check_3, check_2->check_3
  // becomes 0%.  This is even worse if the edge whose probability becomes 0% is
  // the loop exit edge.  Then based solely on static estimation we would assume
  // the loop was extremely hot.
  //
  // FIXME this locally as well so that BPI and BFI are consistent as well.  We
  // shouldn't make edges extremely likely or unlikely based solely on static
  // estimation.
  if (BBSuccProbs.size() >= 2 && doesBlockHaveProfileData(BB)) {
    SmallVector<uint32_t, 4> Weights;
    for (auto Prob : BBSuccProbs)
      Weights.push_back(Prob.getNumerator());

    auto TI = BB->getTerminator();
    TI->setMetadata(
        LLVMContext::MD_prof,
        MDBuilder(TI->getParent()->getContext()).createBranchWeights(Weights));
  }
}

/// duplicateCondBranchOnPHIIntoPred - PredBB contains an unconditional branch
/// to BB which contains an i1 PHI node and a conditional branch on that PHI.
/// If we can duplicate the contents of BB up into PredBB do so now, this
/// improves the odds that the branch will be on an analyzable instruction like
/// a compare.
bool JumpThreadingPass::duplicateCondBranchOnPHIIntoPred(
    BasicBlock *BB, const SmallVectorImpl<BasicBlock *> &PredBBs) {
  assert(!PredBBs.empty() && "Can't handle an empty set");

  // If BB is a loop header, then duplicating this block outside the loop would
  // cause us to transform this into an irreducible loop, don't do this.
  // See the comments above findLoopHeaders for justifications and caveats.
  if (LoopHeaders.count(BB)) {
    LLVM_DEBUG(dbgs() << "  Not duplicating loop header '" << BB->getName()
                      << "' into predecessor block '" << PredBBs[0]->getName()
                      << "' - it might create an irreducible loop!\n");
    return false;
  }

  unsigned DuplicationCost = getJumpThreadDuplicationCost(
      TTI, BB, BB->getTerminator(), BBDupThreshold);
  if (DuplicationCost > BBDupThreshold) {
    LLVM_DEBUG(dbgs() << "  Not duplicating BB '" << BB->getName()
                      << "' - Cost is too high: " << DuplicationCost << "\n");
    return false;
  }

  // And finally, do it!  Start by factoring the predecessors if needed.
  std::vector<DominatorTree::UpdateType> Updates;
  BasicBlock *PredBB;
  if (PredBBs.size() == 1)
    PredBB = PredBBs[0];
  else {
    LLVM_DEBUG(dbgs() << "  Factoring out " << PredBBs.size()
                      << " common predecessors.\n");
    PredBB = splitBlockPreds(BB, PredBBs, ".thr_comm");
  }
  Updates.push_back({DominatorTree::Delete, PredBB, BB});

  // Okay, we decided to do this!  Clone all the instructions in BB onto the end
  // of PredBB.
  LLVM_DEBUG(dbgs() << "  Duplicating block '" << BB->getName()
                    << "' into end of '" << PredBB->getName()
                    << "' to eliminate branch on phi.  Cost: "
                    << DuplicationCost << " block is:" << *BB << "\n");

  // Unless PredBB ends with an unconditional branch, split the edge so that we
  // can just clone the bits from BB into the end of the new PredBB.
  BranchInst *OldPredBranch = dyn_cast<BranchInst>(PredBB->getTerminator());

  if (!OldPredBranch || !OldPredBranch->isUnconditional()) {
    BasicBlock *OldPredBB = PredBB;
    PredBB = SplitEdge(OldPredBB, BB);
    Updates.push_back({DominatorTree::Insert, OldPredBB, PredBB});
    Updates.push_back({DominatorTree::Insert, PredBB, BB});
    Updates.push_back({DominatorTree::Delete, OldPredBB, BB});
    OldPredBranch = cast<BranchInst>(PredBB->getTerminator());
  }

  // We are going to have to map operands from the original BB block into the
  // PredBB block.  Evaluate PHI nodes in BB.
  DenseMap<Instruction*, Value*> ValueMapping;

  BasicBlock::iterator BI = BB->begin();
  for (; PHINode *PN = dyn_cast<PHINode>(BI); ++BI)
    ValueMapping[PN] = PN->getIncomingValueForBlock(PredBB);
  // Clone the non-phi instructions of BB into PredBB, keeping track of the
  // mapping and using it to remap operands in the cloned instructions.
  for (; BI != BB->end(); ++BI) {
    Instruction *New = BI->clone();

    // Remap operands to patch up intra-block references.
    for (unsigned i = 0, e = New->getNumOperands(); i != e; ++i)
      if (Instruction *Inst = dyn_cast<Instruction>(New->getOperand(i))) {
        DenseMap<Instruction*, Value*>::iterator I = ValueMapping.find(Inst);
        if (I != ValueMapping.end())
          New->setOperand(i, I->second);
      }

    // If this instruction can be simplified after the operands are updated,
    // just use the simplified value instead.  This frequently happens due to
    // phi translation.
    if (Value *IV = SimplifyInstruction(
            New,
            {BB->getModule()->getDataLayout(), TLI, nullptr, nullptr, New})) {
      ValueMapping[&*BI] = IV;
      if (!New->mayHaveSideEffects()) {
        New->deleteValue();
        New = nullptr;
      }
    } else {
      ValueMapping[&*BI] = New;
    }
    if (New) {
      // Otherwise, insert the new instruction into the block.
      New->setName(BI->getName());
      PredBB->getInstList().insert(OldPredBranch->getIterator(), New);
      // Update Dominance from simplified New instruction operands.
      for (unsigned i = 0, e = New->getNumOperands(); i != e; ++i)
        if (BasicBlock *SuccBB = dyn_cast<BasicBlock>(New->getOperand(i)))
          Updates.push_back({DominatorTree::Insert, PredBB, SuccBB});
    }
  }

  // Check to see if the targets of the branch had PHI nodes. If so, we need to
  // add entries to the PHI nodes for branch from PredBB now.
  BranchInst *BBBranch = cast<BranchInst>(BB->getTerminator());
  addPHINodeEntriesForMappedBlock(BBBranch->getSuccessor(0), BB, PredBB,
                                  ValueMapping);
  addPHINodeEntriesForMappedBlock(BBBranch->getSuccessor(1), BB, PredBB,
                                  ValueMapping);

  updateSSA(BB, PredBB, ValueMapping);

  // PredBB no longer jumps to BB, remove entries in the PHI node for the edge
  // that we nuked.
  BB->removePredecessor(PredBB, true);

  // Remove the unconditional branch at the end of the PredBB block.
  OldPredBranch->eraseFromParent();
  if (HasProfileData)
    BPI->copyEdgeProbabilities(BB, PredBB);
  DTU->applyUpdatesPermissive(Updates);

  ++NumDupes;
  return true;
}

// Pred is a predecessor of BB with an unconditional branch to BB. SI is
// a Select instruction in Pred. BB has other predecessors and SI is used in
// a PHI node in BB. SI has no other use.
// A new basic block, NewBB, is created and SI is converted to compare and 
// conditional branch. SI is erased from parent.
void JumpThreadingPass::unfoldSelectInstr(BasicBlock *Pred, BasicBlock *BB,
                                          SelectInst *SI, PHINode *SIUse,
                                          unsigned Idx) {
  // Expand the select.
  //
  // Pred --
  //  |    v
  //  |  NewBB
  //  |    |
  //  |-----
  //  v
  // BB
  BranchInst *PredTerm = cast<BranchInst>(Pred->getTerminator());
  BasicBlock *NewBB = BasicBlock::Create(BB->getContext(), "select.unfold",
                                         BB->getParent(), BB);
  // Move the unconditional branch to NewBB.
  PredTerm->removeFromParent();
  NewBB->getInstList().insert(NewBB->end(), PredTerm);
  // Create a conditional branch and update PHI nodes.
  auto *BI = BranchInst::Create(NewBB, BB, SI->getCondition(), Pred);
  BI->applyMergedLocation(PredTerm->getDebugLoc(), SI->getDebugLoc());
  SIUse->setIncomingValue(Idx, SI->getFalseValue());
  SIUse->addIncoming(SI->getTrueValue(), NewBB);

  // The select is now dead.
  SI->eraseFromParent();
  DTU->applyUpdatesPermissive({{DominatorTree::Insert, NewBB, BB},
                               {DominatorTree::Insert, Pred, NewBB}});

  // Update any other PHI nodes in BB.
  for (BasicBlock::iterator BI = BB->begin();
       PHINode *Phi = dyn_cast<PHINode>(BI); ++BI)
    if (Phi != SIUse)
      Phi->addIncoming(Phi->getIncomingValueForBlock(Pred), NewBB);
}

bool JumpThreadingPass::tryToUnfoldSelect(SwitchInst *SI, BasicBlock *BB) {
  PHINode *CondPHI = dyn_cast<PHINode>(SI->getCondition());

  if (!CondPHI || CondPHI->getParent() != BB)
    return false;

  for (unsigned I = 0, E = CondPHI->getNumIncomingValues(); I != E; ++I) {
    BasicBlock *Pred = CondPHI->getIncomingBlock(I);
    SelectInst *PredSI = dyn_cast<SelectInst>(CondPHI->getIncomingValue(I));

    // The second and third condition can be potentially relaxed. Currently
    // the conditions help to simplify the code and allow us to reuse existing
    // code, developed for tryToUnfoldSelect(CmpInst *, BasicBlock *)
    if (!PredSI || PredSI->getParent() != Pred || !PredSI->hasOneUse())
      continue;

    BranchInst *PredTerm = dyn_cast<BranchInst>(Pred->getTerminator());
    if (!PredTerm || !PredTerm->isUnconditional())
      continue;

    unfoldSelectInstr(Pred, BB, PredSI, CondPHI, I);
    return true;
  }
  return false;
}

/// tryToUnfoldSelect - Look for blocks of the form
/// bb1:
///   %a = select
///   br bb2
///
/// bb2:
///   %p = phi [%a, %bb1] ...
///   %c = icmp %p
///   br i1 %c
///
/// And expand the select into a branch structure if one of its arms allows %c
/// to be folded. This later enables threading from bb1 over bb2.
bool JumpThreadingPass::tryToUnfoldSelect(CmpInst *CondCmp, BasicBlock *BB) {
  BranchInst *CondBr = dyn_cast<BranchInst>(BB->getTerminator());
  PHINode *CondLHS = dyn_cast<PHINode>(CondCmp->getOperand(0));
  Constant *CondRHS = cast<Constant>(CondCmp->getOperand(1));

  if (!CondBr || !CondBr->isConditional() || !CondLHS ||
      CondLHS->getParent() != BB)
    return false;

  for (unsigned I = 0, E = CondLHS->getNumIncomingValues(); I != E; ++I) {
    BasicBlock *Pred = CondLHS->getIncomingBlock(I);
    SelectInst *SI = dyn_cast<SelectInst>(CondLHS->getIncomingValue(I));

    // Look if one of the incoming values is a select in the corresponding
    // predecessor.
    if (!SI || SI->getParent() != Pred || !SI->hasOneUse())
      continue;

    BranchInst *PredTerm = dyn_cast<BranchInst>(Pred->getTerminator());
    if (!PredTerm || !PredTerm->isUnconditional())
      continue;

    // Now check if one of the select values would allow us to constant fold the
    // terminator in BB. We don't do the transform if both sides fold, those
    // cases will be threaded in any case.
    LazyValueInfo::Tristate LHSFolds =
        LVI->getPredicateOnEdge(CondCmp->getPredicate(), SI->getOperand(1),
                                CondRHS, Pred, BB, CondCmp);
    LazyValueInfo::Tristate RHSFolds =
        LVI->getPredicateOnEdge(CondCmp->getPredicate(), SI->getOperand(2),
                                CondRHS, Pred, BB, CondCmp);
    if ((LHSFolds != LazyValueInfo::Unknown ||
         RHSFolds != LazyValueInfo::Unknown) &&
        LHSFolds != RHSFolds) {
      unfoldSelectInstr(Pred, BB, SI, CondLHS, I);
      return true;
    }
  }
  return false;
}

/// tryToUnfoldSelectInCurrBB - Look for PHI/Select or PHI/CMP/Select in the
/// same BB in the form
/// bb:
///   %p = phi [false, %bb1], [true, %bb2], [false, %bb3], [true, %bb4], ...
///   %s = select %p, trueval, falseval
///
/// or
///
/// bb:
///   %p = phi [0, %bb1], [1, %bb2], [0, %bb3], [1, %bb4], ...
///   %c = cmp %p, 0
///   %s = select %c, trueval, falseval
///
/// And expand the select into a branch structure. This later enables
/// jump-threading over bb in this pass.
///
/// Using the similar approach of SimplifyCFG::FoldCondBranchOnPHI(), unfold
/// select if the associated PHI has at least one constant.  If the unfolded
/// select is not jump-threaded, it will be folded again in the later
/// optimizations.
bool JumpThreadingPass::tryToUnfoldSelectInCurrBB(BasicBlock *BB) {
  // This transform would reduce the quality of msan diagnostics.
  // Disable this transform under MemorySanitizer.
  if (BB->getParent()->hasFnAttribute(Attribute::SanitizeMemory))
    return false;

  // If threading this would thread across a loop header, don't thread the edge.
  // See the comments above findLoopHeaders for justifications and caveats.
  if (LoopHeaders.count(BB))
    return false;

  for (BasicBlock::iterator BI = BB->begin();
       PHINode *PN = dyn_cast<PHINode>(BI); ++BI) {
    // Look for a Phi having at least one constant incoming value.
    if (llvm::all_of(PN->incoming_values(),
                     [](Value *V) { return !isa<ConstantInt>(V); }))
      continue;

    auto isUnfoldCandidate = [BB](SelectInst *SI, Value *V) {
      using namespace PatternMatch;

      // Check if SI is in BB and use V as condition.
      if (SI->getParent() != BB)
        return false;
      Value *Cond = SI->getCondition();
      bool IsAndOr = match(SI, m_CombineOr(m_LogicalAnd(), m_LogicalOr()));
      return Cond && Cond == V && Cond->getType()->isIntegerTy(1) && !IsAndOr;
    };

    SelectInst *SI = nullptr;
    for (Use &U : PN->uses()) {
      if (ICmpInst *Cmp = dyn_cast<ICmpInst>(U.getUser())) {
        // Look for a ICmp in BB that compares PN with a constant and is the
        // condition of a Select.
        if (Cmp->getParent() == BB && Cmp->hasOneUse() &&
            isa<ConstantInt>(Cmp->getOperand(1 - U.getOperandNo())))
          if (SelectInst *SelectI = dyn_cast<SelectInst>(Cmp->user_back()))
            if (isUnfoldCandidate(SelectI, Cmp->use_begin()->get())) {
              SI = SelectI;
              break;
            }
      } else if (SelectInst *SelectI = dyn_cast<SelectInst>(U.getUser())) {
        // Look for a Select in BB that uses PN as condition.
        if (isUnfoldCandidate(SelectI, U.get())) {
          SI = SelectI;
          break;
        }
      }
    }

    if (!SI)
      continue;
    // Expand the select.
    Value *Cond = SI->getCondition();
    if (InsertFreezeWhenUnfoldingSelect &&
        !isGuaranteedNotToBeUndefOrPoison(Cond, nullptr, SI,
                                          &DTU->getDomTree()))
      Cond = new FreezeInst(Cond, "cond.fr", SI);
    Instruction *Term = SplitBlockAndInsertIfThen(Cond, SI, false);
    BasicBlock *SplitBB = SI->getParent();
    BasicBlock *NewBB = Term->getParent();
    PHINode *NewPN = PHINode::Create(SI->getType(), 2, "", SI);
    NewPN->addIncoming(SI->getTrueValue(), Term->getParent());
    NewPN->addIncoming(SI->getFalseValue(), BB);
    SI->replaceAllUsesWith(NewPN);
    SI->eraseFromParent();
    // NewBB and SplitBB are newly created blocks which require insertion.
    std::vector<DominatorTree::UpdateType> Updates;
    Updates.reserve((2 * SplitBB->getTerminator()->getNumSuccessors()) + 3);
    Updates.push_back({DominatorTree::Insert, BB, SplitBB});
    Updates.push_back({DominatorTree::Insert, BB, NewBB});
    Updates.push_back({DominatorTree::Insert, NewBB, SplitBB});
    // BB's successors were moved to SplitBB, update DTU accordingly.
    for (auto *Succ : successors(SplitBB)) {
      Updates.push_back({DominatorTree::Delete, BB, Succ});
      Updates.push_back({DominatorTree::Insert, SplitBB, Succ});
    }
    DTU->applyUpdatesPermissive(Updates);
    return true;
  }
  return false;
}

/// Try to propagate a guard from the current BB into one of its predecessors
/// in case if another branch of execution implies that the condition of this
/// guard is always true. Currently we only process the simplest case that
/// looks like:
///
/// Start:
///   %cond = ...
///   br i1 %cond, label %T1, label %F1
/// T1:
///   br label %Merge
/// F1:
///   br label %Merge
/// Merge:
///   %condGuard = ...
///   call void(i1, ...) @llvm.experimental.guard( i1 %condGuard )[ "deopt"() ]
///
/// And cond either implies condGuard or !condGuard. In this case all the
/// instructions before the guard can be duplicated in both branches, and the
/// guard is then threaded to one of them.
bool JumpThreadingPass::processGuards(BasicBlock *BB) {
  using namespace PatternMatch;

  // We only want to deal with two predecessors.
  BasicBlock *Pred1, *Pred2;
  auto PI = pred_begin(BB), PE = pred_end(BB);
  if (PI == PE)
    return false;
  Pred1 = *PI++;
  if (PI == PE)
    return false;
  Pred2 = *PI++;
  if (PI != PE)
    return false;
  if (Pred1 == Pred2)
    return false;

  // Try to thread one of the guards of the block.
  // TODO: Look up deeper than to immediate predecessor?
  auto *Parent = Pred1->getSinglePredecessor();
  if (!Parent || Parent != Pred2->getSinglePredecessor())
    return false;

  if (auto *BI = dyn_cast<BranchInst>(Parent->getTerminator()))
    for (auto &I : *BB)
      if (isGuard(&I) && threadGuard(BB, cast<IntrinsicInst>(&I), BI))
        return true;

  return false;
}

/// Try to propagate the guard from BB which is the lower block of a diamond
/// to one of its branches, in case if diamond's condition implies guard's
/// condition.
bool JumpThreadingPass::threadGuard(BasicBlock *BB, IntrinsicInst *Guard,
                                    BranchInst *BI) {
  assert(BI->getNumSuccessors() == 2 && "Wrong number of successors?");
  assert(BI->isConditional() && "Unconditional branch has 2 successors?");
  Value *GuardCond = Guard->getArgOperand(0);
  Value *BranchCond = BI->getCondition();
  BasicBlock *TrueDest = BI->getSuccessor(0);
  BasicBlock *FalseDest = BI->getSuccessor(1);

  auto &DL = BB->getModule()->getDataLayout();
  bool TrueDestIsSafe = false;
  bool FalseDestIsSafe = false;

  // True dest is safe if BranchCond => GuardCond.
  auto Impl = isImpliedCondition(BranchCond, GuardCond, DL);
  if (Impl && *Impl)
    TrueDestIsSafe = true;
  else {
    // False dest is safe if !BranchCond => GuardCond.
    Impl = isImpliedCondition(BranchCond, GuardCond, DL, /* LHSIsTrue */ false);
    if (Impl && *Impl)
      FalseDestIsSafe = true;
  }

  if (!TrueDestIsSafe && !FalseDestIsSafe)
    return false;

  BasicBlock *PredUnguardedBlock = TrueDestIsSafe ? TrueDest : FalseDest;
  BasicBlock *PredGuardedBlock = FalseDestIsSafe ? TrueDest : FalseDest;

  ValueToValueMapTy UnguardedMapping, GuardedMapping;
  Instruction *AfterGuard = Guard->getNextNode();
  unsigned Cost =
      getJumpThreadDuplicationCost(TTI, BB, AfterGuard, BBDupThreshold);
  if (Cost > BBDupThreshold)
    return false;
  // Duplicate all instructions before the guard and the guard itself to the
  // branch where implication is not proved.
  BasicBlock *GuardedBlock = DuplicateInstructionsInSplitBetween(
      BB, PredGuardedBlock, AfterGuard, GuardedMapping, *DTU);
  assert(GuardedBlock && "Could not create the guarded block?");
  // Duplicate all instructions before the guard in the unguarded branch.
  // Since we have successfully duplicated the guarded block and this block
  // has fewer instructions, we expect it to succeed.
  BasicBlock *UnguardedBlock = DuplicateInstructionsInSplitBetween(
      BB, PredUnguardedBlock, Guard, UnguardedMapping, *DTU);
  assert(UnguardedBlock && "Could not create the unguarded block?");
  LLVM_DEBUG(dbgs() << "Moved guard " << *Guard << " to block "
                    << GuardedBlock->getName() << "\n");
  // Some instructions before the guard may still have uses. For them, we need
  // to create Phi nodes merging their copies in both guarded and unguarded
  // branches. Those instructions that have no uses can be just removed.
  SmallVector<Instruction *, 4> ToRemove;
  for (auto BI = BB->begin(); &*BI != AfterGuard; ++BI)
    if (!isa<PHINode>(&*BI))
      ToRemove.push_back(&*BI);

  Instruction *InsertionPoint = &*BB->getFirstInsertionPt();
  assert(InsertionPoint && "Empty block?");
  // Substitute with Phis & remove.
  for (auto *Inst : reverse(ToRemove)) {
    if (!Inst->use_empty()) {
      PHINode *NewPN = PHINode::Create(Inst->getType(), 2);
      NewPN->addIncoming(UnguardedMapping[Inst], UnguardedBlock);
      NewPN->addIncoming(GuardedMapping[Inst], GuardedBlock);
      NewPN->insertBefore(InsertionPoint);
      Inst->replaceAllUsesWith(NewPN);
    }
    Inst->eraseFromParent();
  }
  return true;
}