summaryrefslogtreecommitdiffstats
path: root/tcg/optimize.c
blob: c447062ab1ef2c9c26a73de01b4e806ca3e7c623 (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
/*
 * Optimizations for Tiny Code Generator for QEMU
 *
 * Copyright (c) 2010 Samsung Electronics.
 * Contributed by Kirill Batuzov <batuzovk@ispras.ru>
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

#include "config.h"

#include <stdlib.h>
#include <stdio.h>

#include "qemu-common.h"
#include "tcg-op.h"

#define CASE_OP_32_64(x)                        \
        glue(glue(case INDEX_op_, x), _i32):    \
        glue(glue(case INDEX_op_, x), _i64)

typedef enum {
    TCG_TEMP_UNDEF = 0,
    TCG_TEMP_CONST,
    TCG_TEMP_COPY,
} tcg_temp_state;

struct tcg_temp_info {
    tcg_temp_state state;
    uint16_t prev_copy;
    uint16_t next_copy;
    tcg_target_ulong val;
    tcg_target_ulong mask;
};

static struct tcg_temp_info temps[TCG_MAX_TEMPS];

/* Reset TEMP's state to TCG_TEMP_UNDEF.  If TEMP only had one copy, remove
   the copy flag from the left temp.  */
static void reset_temp(TCGArg temp)
{
    if (temps[temp].state == TCG_TEMP_COPY) {
        if (temps[temp].prev_copy == temps[temp].next_copy) {
            temps[temps[temp].next_copy].state = TCG_TEMP_UNDEF;
        } else {
            temps[temps[temp].next_copy].prev_copy = temps[temp].prev_copy;
            temps[temps[temp].prev_copy].next_copy = temps[temp].next_copy;
        }
    }
    temps[temp].state = TCG_TEMP_UNDEF;
    temps[temp].mask = -1;
}

/* Reset all temporaries, given that there are NB_TEMPS of them.  */
static void reset_all_temps(int nb_temps)
{
    int i;
    for (i = 0; i < nb_temps; i++) {
        temps[i].state = TCG_TEMP_UNDEF;
        temps[i].mask = -1;
    }
}

static int op_bits(TCGOpcode op)
{
    const TCGOpDef *def = &tcg_op_defs[op];
    return def->flags & TCG_OPF_64BIT ? 64 : 32;
}

static TCGOpcode op_to_movi(TCGOpcode op)
{
    switch (op_bits(op)) {
    case 32:
        return INDEX_op_movi_i32;
    case 64:
        return INDEX_op_movi_i64;
    default:
        fprintf(stderr, "op_to_movi: unexpected return value of "
                "function op_bits.\n");
        tcg_abort();
    }
}

static TCGArg find_better_copy(TCGContext *s, TCGArg temp)
{
    TCGArg i;

    /* If this is already a global, we can't do better. */
    if (temp < s->nb_globals) {
        return temp;
    }

    /* Search for a global first. */
    for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
        if (i < s->nb_globals) {
            return i;
        }
    }

    /* If it is a temp, search for a temp local. */
    if (!s->temps[temp].temp_local) {
        for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
            if (s->temps[i].temp_local) {
                return i;
            }
        }
    }

    /* Failure to find a better representation, return the same temp. */
    return temp;
}

static bool temps_are_copies(TCGArg arg1, TCGArg arg2)
{
    TCGArg i;

    if (arg1 == arg2) {
        return true;
    }

    if (temps[arg1].state != TCG_TEMP_COPY
        || temps[arg2].state != TCG_TEMP_COPY) {
        return false;
    }

    for (i = temps[arg1].next_copy ; i != arg1 ; i = temps[i].next_copy) {
        if (i == arg2) {
            return true;
        }
    }

    return false;
}

static void tcg_opt_gen_mov(TCGContext *s, TCGArg *gen_args,
                            TCGArg dst, TCGArg src)
{
    reset_temp(dst);
    temps[dst].mask = temps[src].mask;
    assert(temps[src].state != TCG_TEMP_CONST);

    if (s->temps[src].type == s->temps[dst].type) {
        if (temps[src].state != TCG_TEMP_COPY) {
            temps[src].state = TCG_TEMP_COPY;
            temps[src].next_copy = src;
            temps[src].prev_copy = src;
        }
        temps[dst].state = TCG_TEMP_COPY;
        temps[dst].next_copy = temps[src].next_copy;
        temps[dst].prev_copy = src;
        temps[temps[dst].next_copy].prev_copy = dst;
        temps[src].next_copy = dst;
    }

    gen_args[0] = dst;
    gen_args[1] = src;
}

static void tcg_opt_gen_movi(TCGArg *gen_args, TCGArg dst, TCGArg val)
{
    reset_temp(dst);
    temps[dst].state = TCG_TEMP_CONST;
    temps[dst].val = val;
    temps[dst].mask = val;
    gen_args[0] = dst;
    gen_args[1] = val;
}

static TCGOpcode op_to_mov(TCGOpcode op)
{
    switch (op_bits(op)) {
    case 32:
        return INDEX_op_mov_i32;
    case 64:
        return INDEX_op_mov_i64;
    default:
        fprintf(stderr, "op_to_mov: unexpected return value of "
                "function op_bits.\n");
        tcg_abort();
    }
}

static TCGArg do_constant_folding_2(TCGOpcode op, TCGArg x, TCGArg y)
{
    uint64_t l64, h64;

    switch (op) {
    CASE_OP_32_64(add):
        return x + y;

    CASE_OP_32_64(sub):
        return x - y;

    CASE_OP_32_64(mul):
        return x * y;

    CASE_OP_32_64(and):
        return x & y;

    CASE_OP_32_64(or):
        return x | y;

    CASE_OP_32_64(xor):
        return x ^ y;

    case INDEX_op_shl_i32:
        return (uint32_t)x << (y & 31);

    case INDEX_op_shl_i64:
        return (uint64_t)x << (y & 63);

    case INDEX_op_shr_i32:
        return (uint32_t)x >> (y & 31);

    case INDEX_op_shr_i64:
        return (uint64_t)x >> (y & 63);

    case INDEX_op_sar_i32:
        return (int32_t)x >> (y & 31);

    case INDEX_op_sar_i64:
        return (int64_t)x >> (y & 63);

    case INDEX_op_rotr_i32:
        return ror32(x, y & 31);

    case INDEX_op_rotr_i64:
        return ror64(x, y & 63);

    case INDEX_op_rotl_i32:
        return rol32(x, y & 31);

    case INDEX_op_rotl_i64:
        return rol64(x, y & 63);

    CASE_OP_32_64(not):
        return ~x;

    CASE_OP_32_64(neg):
        return -x;

    CASE_OP_32_64(andc):
        return x & ~y;

    CASE_OP_32_64(orc):
        return x | ~y;

    CASE_OP_32_64(eqv):
        return ~(x ^ y);

    CASE_OP_32_64(nand):
        return ~(x & y);

    CASE_OP_32_64(nor):
        return ~(x | y);

    CASE_OP_32_64(ext8s):
        return (int8_t)x;

    CASE_OP_32_64(ext16s):
        return (int16_t)x;

    CASE_OP_32_64(ext8u):
        return (uint8_t)x;

    CASE_OP_32_64(ext16u):
        return (uint16_t)x;

    case INDEX_op_ext32s_i64:
        return (int32_t)x;

    case INDEX_op_ext32u_i64:
        return (uint32_t)x;

    case INDEX_op_muluh_i32:
        return ((uint64_t)(uint32_t)x * (uint32_t)y) >> 32;
    case INDEX_op_mulsh_i32:
        return ((int64_t)(int32_t)x * (int32_t)y) >> 32;

    case INDEX_op_muluh_i64:
        mulu64(&l64, &h64, x, y);
        return h64;
    case INDEX_op_mulsh_i64:
        muls64(&l64, &h64, x, y);
        return h64;

    case INDEX_op_div_i32:
        /* Avoid crashing on divide by zero, otherwise undefined.  */
        return (int32_t)x / ((int32_t)y ? : 1);
    case INDEX_op_divu_i32:
        return (uint32_t)x / ((uint32_t)y ? : 1);
    case INDEX_op_div_i64:
        return (int64_t)x / ((int64_t)y ? : 1);
    case INDEX_op_divu_i64:
        return (uint64_t)x / ((uint64_t)y ? : 1);

    case INDEX_op_rem_i32:
        return (int32_t)x % ((int32_t)y ? : 1);
    case INDEX_op_remu_i32:
        return (uint32_t)x % ((uint32_t)y ? : 1);
    case INDEX_op_rem_i64:
        return (int64_t)x % ((int64_t)y ? : 1);
    case INDEX_op_remu_i64:
        return (uint64_t)x % ((uint64_t)y ? : 1);

    default:
        fprintf(stderr,
                "Unrecognized operation %d in do_constant_folding.\n", op);
        tcg_abort();
    }
}

static TCGArg do_constant_folding(TCGOpcode op, TCGArg x, TCGArg y)
{
    TCGArg res = do_constant_folding_2(op, x, y);
    if (op_bits(op) == 32) {
        res &= 0xffffffff;
    }
    return res;
}

static bool do_constant_folding_cond_32(uint32_t x, uint32_t y, TCGCond c)
{
    switch (c) {
    case TCG_COND_EQ:
        return x == y;
    case TCG_COND_NE:
        return x != y;
    case TCG_COND_LT:
        return (int32_t)x < (int32_t)y;
    case TCG_COND_GE:
        return (int32_t)x >= (int32_t)y;
    case TCG_COND_LE:
        return (int32_t)x <= (int32_t)y;
    case TCG_COND_GT:
        return (int32_t)x > (int32_t)y;
    case TCG_COND_LTU:
        return x < y;
    case TCG_COND_GEU:
        return x >= y;
    case TCG_COND_LEU:
        return x <= y;
    case TCG_COND_GTU:
        return x > y;
    default:
        tcg_abort();
    }
}

static bool do_constant_folding_cond_64(uint64_t x, uint64_t y, TCGCond c)
{
    switch (c) {
    case TCG_COND_EQ:
        return x == y;
    case TCG_COND_NE:
        return x != y;
    case TCG_COND_LT:
        return (int64_t)x < (int64_t)y;
    case TCG_COND_GE:
        return (int64_t)x >= (int64_t)y;
    case TCG_COND_LE:
        return (int64_t)x <= (int64_t)y;
    case TCG_COND_GT:
        return (int64_t)x > (int64_t)y;
    case TCG_COND_LTU:
        return x < y;
    case TCG_COND_GEU:
        return x >= y;
    case TCG_COND_LEU:
        return x <= y;
    case TCG_COND_GTU:
        return x > y;
    default:
        tcg_abort();
    }
}

static bool do_constant_folding_cond_eq(TCGCond c)
{
    switch (c) {
    case TCG_COND_GT:
    case TCG_COND_LTU:
    case TCG_COND_LT:
    case TCG_COND_GTU:
    case TCG_COND_NE:
        return 0;
    case TCG_COND_GE:
    case TCG_COND_GEU:
    case TCG_COND_LE:
    case TCG_COND_LEU:
    case TCG_COND_EQ:
        return 1;
    default:
        tcg_abort();
    }
}

/* Return 2 if the condition can't be simplified, and the result
   of the condition (0 or 1) if it can */
static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
                                       TCGArg y, TCGCond c)
{
    if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) {
        switch (op_bits(op)) {
        case 32:
            return do_constant_folding_cond_32(temps[x].val, temps[y].val, c);
        case 64:
            return do_constant_folding_cond_64(temps[x].val, temps[y].val, c);
        default:
            tcg_abort();
        }
    } else if (temps_are_copies(x, y)) {
        return do_constant_folding_cond_eq(c);
    } else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) {
        switch (c) {
        case TCG_COND_LTU:
            return 0;
        case TCG_COND_GEU:
            return 1;
        default:
            return 2;
        }
    } else {
        return 2;
    }
}

/* Return 2 if the condition can't be simplified, and the result
   of the condition (0 or 1) if it can */
static TCGArg do_constant_folding_cond2(TCGArg *p1, TCGArg *p2, TCGCond c)
{
    TCGArg al = p1[0], ah = p1[1];
    TCGArg bl = p2[0], bh = p2[1];

    if (temps[bl].state == TCG_TEMP_CONST
        && temps[bh].state == TCG_TEMP_CONST) {
        uint64_t b = ((uint64_t)temps[bh].val << 32) | (uint32_t)temps[bl].val;

        if (temps[al].state == TCG_TEMP_CONST
            && temps[ah].state == TCG_TEMP_CONST) {
            uint64_t a;
            a = ((uint64_t)temps[ah].val << 32) | (uint32_t)temps[al].val;
            return do_constant_folding_cond_64(a, b, c);
        }
        if (b == 0) {
            switch (c) {
            case TCG_COND_LTU:
                return 0;
            case TCG_COND_GEU:
                return 1;
            default:
                break;
            }
        }
    }
    if (temps_are_copies(al, bl) && temps_are_copies(ah, bh)) {
        return do_constant_folding_cond_eq(c);
    }
    return 2;
}

static bool swap_commutative(TCGArg dest, TCGArg *p1, TCGArg *p2)
{
    TCGArg a1 = *p1, a2 = *p2;
    int sum = 0;
    sum += temps[a1].state == TCG_TEMP_CONST;
    sum -= temps[a2].state == TCG_TEMP_CONST;

    /* Prefer the constant in second argument, and then the form
       op a, a, b, which is better handled on non-RISC hosts. */
    if (sum > 0 || (sum == 0 && dest == a2)) {
        *p1 = a2;
        *p2 = a1;
        return true;
    }
    return false;
}

static bool swap_commutative2(TCGArg *p1, TCGArg *p2)
{
    int sum = 0;
    sum += temps[p1[0]].state == TCG_TEMP_CONST;
    sum += temps[p1[1]].state == TCG_TEMP_CONST;
    sum -= temps[p2[0]].state == TCG_TEMP_CONST;
    sum -= temps[p2[1]].state == TCG_TEMP_CONST;
    if (sum > 0) {
        TCGArg t;
        t = p1[0], p1[0] = p2[0], p2[0] = t;
        t = p1[1], p1[1] = p2[1], p2[1] = t;
        return true;
    }
    return false;
}

/* Propagate constants and copies, fold constant expressions. */
static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
                                    TCGArg *args, TCGOpDef *tcg_op_defs)
{
    int i, nb_ops, op_index, nb_temps, nb_globals, nb_call_args;
    tcg_target_ulong mask, affected;
    TCGOpcode op;
    const TCGOpDef *def;
    TCGArg *gen_args;
    TCGArg tmp;

    /* Array VALS has an element for each temp.
       If this temp holds a constant then its value is kept in VALS' element.
       If this temp is a copy of other ones then the other copies are
       available through the doubly linked circular list. */

    nb_temps = s->nb_temps;
    nb_globals = s->nb_globals;
    reset_all_temps(nb_temps);

    nb_ops = tcg_opc_ptr - s->gen_opc_buf;
    gen_args = args;
    for (op_index = 0; op_index < nb_ops; op_index++) {
        op = s->gen_opc_buf[op_index];
        def = &tcg_op_defs[op];
        /* Do copy propagation */
        if (op == INDEX_op_call) {
            int nb_oargs = args[0] >> 16;
            int nb_iargs = args[0] & 0xffff;
            for (i = nb_oargs + 1; i < nb_oargs + nb_iargs + 1; i++) {
                if (temps[args[i]].state == TCG_TEMP_COPY) {
                    args[i] = find_better_copy(s, args[i]);
                }
            }
        } else {
            for (i = def->nb_oargs; i < def->nb_oargs + def->nb_iargs; i++) {
                if (temps[args[i]].state == TCG_TEMP_COPY) {
                    args[i] = find_better_copy(s, args[i]);
                }
            }
        }

        /* For commutative operations make constant second argument */
        switch (op) {
        CASE_OP_32_64(add):
        CASE_OP_32_64(mul):
        CASE_OP_32_64(and):
        CASE_OP_32_64(or):
        CASE_OP_32_64(xor):
        CASE_OP_32_64(eqv):
        CASE_OP_32_64(nand):
        CASE_OP_32_64(nor):
        CASE_OP_32_64(muluh):
        CASE_OP_32_64(mulsh):
            swap_commutative(args[0], &args[1], &args[2]);
            break;
        CASE_OP_32_64(brcond):
            if (swap_commutative(-1, &args[0], &args[1])) {
                args[2] = tcg_swap_cond(args[2]);
            }
            break;
        CASE_OP_32_64(setcond):
            if (swap_commutative(args[0], &args[1], &args[2])) {
                args[3] = tcg_swap_cond(args[3]);
            }
            break;
        CASE_OP_32_64(movcond):
            if (swap_commutative(-1, &args[1], &args[2])) {
                args[5] = tcg_swap_cond(args[5]);
            }
            /* For movcond, we canonicalize the "false" input reg to match
               the destination reg so that the tcg backend can implement
               a "move if true" operation.  */
            if (swap_commutative(args[0], &args[4], &args[3])) {
                args[5] = tcg_invert_cond(args[5]);
            }
            break;
        CASE_OP_32_64(add2):
            swap_commutative(args[0], &args[2], &args[4]);
            swap_commutative(args[1], &args[3], &args[5]);
            break;
        CASE_OP_32_64(mulu2):
        CASE_OP_32_64(muls2):
            swap_commutative(args[0], &args[2], &args[3]);
            break;
        case INDEX_op_brcond2_i32:
            if (swap_commutative2(&args[0], &args[2])) {
                args[4] = tcg_swap_cond(args[4]);
            }
            break;
        case INDEX_op_setcond2_i32:
            if (swap_commutative2(&args[1], &args[3])) {
                args[5] = tcg_swap_cond(args[5]);
            }
            break;
        default:
            break;
        }

        /* Simplify expressions for "shift/rot r, 0, a => movi r, 0",
           and "sub r, 0, a => neg r, a" case.  */
        switch (op) {
        CASE_OP_32_64(shl):
        CASE_OP_32_64(shr):
        CASE_OP_32_64(sar):
        CASE_OP_32_64(rotl):
        CASE_OP_32_64(rotr):
            if (temps[args[1]].state == TCG_TEMP_CONST
                && temps[args[1]].val == 0) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tcg_opt_gen_movi(gen_args, args[0], 0);
                args += 3;
                gen_args += 2;
                continue;
            }
            break;
        CASE_OP_32_64(sub):
            {
                TCGOpcode neg_op;
                bool have_neg;

                if (temps[args[2]].state == TCG_TEMP_CONST) {
                    /* Proceed with possible constant folding. */
                    break;
                }
                if (op == INDEX_op_sub_i32) {
                    neg_op = INDEX_op_neg_i32;
                    have_neg = TCG_TARGET_HAS_neg_i32;
                } else {
                    neg_op = INDEX_op_neg_i64;
                    have_neg = TCG_TARGET_HAS_neg_i64;
                }
                if (!have_neg) {
                    break;
                }
                if (temps[args[1]].state == TCG_TEMP_CONST
                    && temps[args[1]].val == 0) {
                    s->gen_opc_buf[op_index] = neg_op;
                    reset_temp(args[0]);
                    gen_args[0] = args[0];
                    gen_args[1] = args[2];
                    args += 3;
                    gen_args += 2;
                    continue;
                }
            }
            break;
        CASE_OP_32_64(xor):
        CASE_OP_32_64(nand):
            if (temps[args[1]].state != TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[2]].val == -1) {
                i = 1;
                goto try_not;
            }
            break;
        CASE_OP_32_64(nor):
            if (temps[args[1]].state != TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[2]].val == 0) {
                i = 1;
                goto try_not;
            }
            break;
        CASE_OP_32_64(andc):
            if (temps[args[2]].state != TCG_TEMP_CONST
                && temps[args[1]].state == TCG_TEMP_CONST
                && temps[args[1]].val == -1) {
                i = 2;
                goto try_not;
            }
            break;
        CASE_OP_32_64(orc):
        CASE_OP_32_64(eqv):
            if (temps[args[2]].state != TCG_TEMP_CONST
                && temps[args[1]].state == TCG_TEMP_CONST
                && temps[args[1]].val == 0) {
                i = 2;
                goto try_not;
            }
            break;
        try_not:
            {
                TCGOpcode not_op;
                bool have_not;

                if (def->flags & TCG_OPF_64BIT) {
                    not_op = INDEX_op_not_i64;
                    have_not = TCG_TARGET_HAS_not_i64;
                } else {
                    not_op = INDEX_op_not_i32;
                    have_not = TCG_TARGET_HAS_not_i32;
                }
                if (!have_not) {
                    break;
                }
                s->gen_opc_buf[op_index] = not_op;
                reset_temp(args[0]);
                gen_args[0] = args[0];
                gen_args[1] = args[i];
                args += 3;
                gen_args += 2;
                continue;
            }
        default:
            break;
        }

        /* Simplify expression for "op r, a, const => mov r, a" cases */
        switch (op) {
        CASE_OP_32_64(add):
        CASE_OP_32_64(sub):
        CASE_OP_32_64(shl):
        CASE_OP_32_64(shr):
        CASE_OP_32_64(sar):
        CASE_OP_32_64(rotl):
        CASE_OP_32_64(rotr):
        CASE_OP_32_64(or):
        CASE_OP_32_64(xor):
        CASE_OP_32_64(andc):
            if (temps[args[1]].state != TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[2]].val == 0) {
                goto do_mov3;
            }
            break;
        CASE_OP_32_64(and):
        CASE_OP_32_64(orc):
        CASE_OP_32_64(eqv):
            if (temps[args[1]].state != TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[2]].val == -1) {
                goto do_mov3;
            }
            break;
        do_mov3:
            if (temps_are_copies(args[0], args[1])) {
                s->gen_opc_buf[op_index] = INDEX_op_nop;
            } else {
                s->gen_opc_buf[op_index] = op_to_mov(op);
                tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
                gen_args += 2;
            }
            args += 3;
            continue;
        default:
            break;
        }

        /* Simplify using known-zero bits. Currently only ops with a single
           output argument is supported. */
        mask = -1;
        affected = -1;
        switch (op) {
        CASE_OP_32_64(ext8s):
            if ((temps[args[1]].mask & 0x80) != 0) {
                break;
            }
        CASE_OP_32_64(ext8u):
            mask = 0xff;
            goto and_const;
        CASE_OP_32_64(ext16s):
            if ((temps[args[1]].mask & 0x8000) != 0) {
                break;
            }
        CASE_OP_32_64(ext16u):
            mask = 0xffff;
            goto and_const;
        case INDEX_op_ext32s_i64:
            if ((temps[args[1]].mask & 0x80000000) != 0) {
                break;
            }
        case INDEX_op_ext32u_i64:
            mask = 0xffffffffU;
            goto and_const;

        CASE_OP_32_64(and):
            mask = temps[args[2]].mask;
            if (temps[args[2]].state == TCG_TEMP_CONST) {
        and_const:
                affected = temps[args[1]].mask & ~mask;
            }
            mask = temps[args[1]].mask & mask;
            break;

        CASE_OP_32_64(andc):
            /* Known-zeros does not imply known-ones.  Therefore unless
               args[2] is constant, we can't infer anything from it.  */
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                mask = ~temps[args[2]].mask;
                goto and_const;
            }
            /* But we certainly know nothing outside args[1] may be set. */
            mask = temps[args[1]].mask;
            break;

        case INDEX_op_sar_i32:
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                tmp = temps[args[2]].val & 31;
                mask = (int32_t)temps[args[1]].mask >> tmp;
            }
            break;
        case INDEX_op_sar_i64:
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                tmp = temps[args[2]].val & 63;
                mask = (int64_t)temps[args[1]].mask >> tmp;
            }
            break;

        case INDEX_op_shr_i32:
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                tmp = temps[args[2]].val & 31;
                mask = (uint32_t)temps[args[1]].mask >> tmp;
            }
            break;
        case INDEX_op_shr_i64:
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                tmp = temps[args[2]].val & 63;
                mask = (uint64_t)temps[args[1]].mask >> tmp;
            }
            break;

        CASE_OP_32_64(shl):
            if (temps[args[2]].state == TCG_TEMP_CONST) {
                tmp = temps[args[2]].val & (TCG_TARGET_REG_BITS - 1);
                mask = temps[args[1]].mask << tmp;
            }
            break;

        CASE_OP_32_64(neg):
            /* Set to 1 all bits to the left of the rightmost.  */
            mask = -(temps[args[1]].mask & -temps[args[1]].mask);
            break;

        CASE_OP_32_64(deposit):
            mask = deposit64(temps[args[1]].mask, args[3], args[4],
                             temps[args[2]].mask);
            break;

        CASE_OP_32_64(or):
        CASE_OP_32_64(xor):
            mask = temps[args[1]].mask | temps[args[2]].mask;
            break;

        CASE_OP_32_64(setcond):
            mask = 1;
            break;

        CASE_OP_32_64(movcond):
            mask = temps[args[3]].mask | temps[args[4]].mask;
            break;

        CASE_OP_32_64(ld8u):
        case INDEX_op_qemu_ld8u:
            mask = 0xff;
            break;
        CASE_OP_32_64(ld16u):
        case INDEX_op_qemu_ld16u:
            mask = 0xffff;
            break;
        case INDEX_op_ld32u_i64:
#if TCG_TARGET_REG_BITS == 64
        case INDEX_op_qemu_ld32u:
#endif
            mask = 0xffffffffu;
            break;

        CASE_OP_32_64(qemu_ld):
            {
                TCGMemOp mop = args[def->nb_oargs + def->nb_iargs];
                if (!(mop & MO_SIGN)) {
                    mask = (2ULL << ((8 << (mop & MO_SIZE)) - 1)) - 1;
                }
            }
            break;

        default:
            break;
        }

        /* 32-bit ops (non 64-bit ops and non load/store ops) generate 32-bit
           results */
        if (!(def->flags & (TCG_OPF_CALL_CLOBBER | TCG_OPF_64BIT))) {
            mask &= 0xffffffffu;
        }

        if (mask == 0) {
            assert(def->nb_oargs == 1);
            s->gen_opc_buf[op_index] = op_to_movi(op);
            tcg_opt_gen_movi(gen_args, args[0], 0);
            args += def->nb_oargs + def->nb_iargs + def->nb_cargs;
            gen_args += 2;
            continue;
        }
        if (affected == 0) {
            assert(def->nb_oargs == 1);
            if (temps_are_copies(args[0], args[1])) {
                s->gen_opc_buf[op_index] = INDEX_op_nop;
            } else if (temps[args[1]].state != TCG_TEMP_CONST) {
                s->gen_opc_buf[op_index] = op_to_mov(op);
                tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
                gen_args += 2;
            } else {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tcg_opt_gen_movi(gen_args, args[0], temps[args[1]].val);
                gen_args += 2;
            }
            args += def->nb_iargs + 1;
            continue;
        }

        /* Simplify expression for "op r, a, 0 => movi r, 0" cases */
        switch (op) {
        CASE_OP_32_64(and):
        CASE_OP_32_64(mul):
        CASE_OP_32_64(muluh):
        CASE_OP_32_64(mulsh):
            if ((temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[2]].val == 0)) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tcg_opt_gen_movi(gen_args, args[0], 0);
                args += 3;
                gen_args += 2;
                continue;
            }
            break;
        default:
            break;
        }

        /* Simplify expression for "op r, a, a => mov r, a" cases */
        switch (op) {
        CASE_OP_32_64(or):
        CASE_OP_32_64(and):
            if (temps_are_copies(args[1], args[2])) {
                if (temps_are_copies(args[0], args[1])) {
                    s->gen_opc_buf[op_index] = INDEX_op_nop;
                } else {
                    s->gen_opc_buf[op_index] = op_to_mov(op);
                    tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
                    gen_args += 2;
                }
                args += 3;
                continue;
            }
            break;
        default:
            break;
        }

        /* Simplify expression for "op r, a, a => movi r, 0" cases */
        switch (op) {
        CASE_OP_32_64(andc):
        CASE_OP_32_64(sub):
        CASE_OP_32_64(xor):
            if (temps_are_copies(args[1], args[2])) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tcg_opt_gen_movi(gen_args, args[0], 0);
                gen_args += 2;
                args += 3;
                continue;
            }
            break;
        default:
            break;
        }

        /* Propagate constants through copy operations and do constant
           folding.  Constants will be substituted to arguments by register
           allocator where needed and possible.  Also detect copies. */
        switch (op) {
        CASE_OP_32_64(mov):
            if (temps_are_copies(args[0], args[1])) {
                args += 2;
                s->gen_opc_buf[op_index] = INDEX_op_nop;
                break;
            }
            if (temps[args[1]].state != TCG_TEMP_CONST) {
                tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
                gen_args += 2;
                args += 2;
                break;
            }
            /* Source argument is constant.  Rewrite the operation and
               let movi case handle it. */
            op = op_to_movi(op);
            s->gen_opc_buf[op_index] = op;
            args[1] = temps[args[1]].val;
            /* fallthrough */
        CASE_OP_32_64(movi):
            tcg_opt_gen_movi(gen_args, args[0], args[1]);
            gen_args += 2;
            args += 2;
            break;

        CASE_OP_32_64(not):
        CASE_OP_32_64(neg):
        CASE_OP_32_64(ext8s):
        CASE_OP_32_64(ext8u):
        CASE_OP_32_64(ext16s):
        CASE_OP_32_64(ext16u):
        case INDEX_op_ext32s_i64:
        case INDEX_op_ext32u_i64:
            if (temps[args[1]].state == TCG_TEMP_CONST) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tmp = do_constant_folding(op, temps[args[1]].val, 0);
                tcg_opt_gen_movi(gen_args, args[0], tmp);
                gen_args += 2;
                args += 2;
                break;
            }
            goto do_default;

        CASE_OP_32_64(add):
        CASE_OP_32_64(sub):
        CASE_OP_32_64(mul):
        CASE_OP_32_64(or):
        CASE_OP_32_64(and):
        CASE_OP_32_64(xor):
        CASE_OP_32_64(shl):
        CASE_OP_32_64(shr):
        CASE_OP_32_64(sar):
        CASE_OP_32_64(rotl):
        CASE_OP_32_64(rotr):
        CASE_OP_32_64(andc):
        CASE_OP_32_64(orc):
        CASE_OP_32_64(eqv):
        CASE_OP_32_64(nand):
        CASE_OP_32_64(nor):
        CASE_OP_32_64(muluh):
        CASE_OP_32_64(mulsh):
        CASE_OP_32_64(div):
        CASE_OP_32_64(divu):
        CASE_OP_32_64(rem):
        CASE_OP_32_64(remu):
            if (temps[args[1]].state == TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tmp = do_constant_folding(op, temps[args[1]].val,
                                          temps[args[2]].val);
                tcg_opt_gen_movi(gen_args, args[0], tmp);
                gen_args += 2;
                args += 3;
                break;
            }
            goto do_default;

        CASE_OP_32_64(deposit):
            if (temps[args[1]].state == TCG_TEMP_CONST
                && temps[args[2]].state == TCG_TEMP_CONST) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tmp = deposit64(temps[args[1]].val, args[3], args[4],
                                temps[args[2]].val);
                tcg_opt_gen_movi(gen_args, args[0], tmp);
                gen_args += 2;
                args += 5;
                break;
            }
            goto do_default;

        CASE_OP_32_64(setcond):
            tmp = do_constant_folding_cond(op, args[1], args[2], args[3]);
            if (tmp != 2) {
                s->gen_opc_buf[op_index] = op_to_movi(op);
                tcg_opt_gen_movi(gen_args, args[0], tmp);
                gen_args += 2;
                args += 4;
                break;
            }
            goto do_default;

        CASE_OP_32_64(brcond):
            tmp = do_constant_folding_cond(op, args[0], args[1], args[2]);
            if (tmp != 2) {
                if (tmp) {
                    reset_all_temps(nb_temps);
                    s->gen_opc_buf[op_index] = INDEX_op_br;
                    gen_args[0] = args[3];
                    gen_args += 1;
                } else {
                    s->gen_opc_buf[op_index] = INDEX_op_nop;
                }
                args += 4;
                break;
            }
            goto do_default;

        CASE_OP_32_64(movcond):
            tmp = do_constant_folding_cond(op, args[1], args[2], args[5]);
            if (tmp != 2) {
                if (temps_are_copies(args[0], args[4-tmp])) {
                    s->gen_opc_buf[op_index] = INDEX_op_nop;
                } else if (temps[args[4-tmp]].state == TCG_TEMP_CONST) {
                    s->gen_opc_buf[op_index] = op_to_movi(op);
                    tcg_opt_gen_movi(gen_args, args[0], temps[args[4-tmp]].val);
                    gen_args += 2;
                } else {
                    s->gen_opc_buf[op_index] = op_to_mov(op);
                    tcg_opt_gen_mov(s, gen_args, args[0], args[4-tmp]);
                    gen_args += 2;
                }
                args += 6;
                break;
            }
            goto do_default;

        case INDEX_op_add2_i32:
        case INDEX_op_sub2_i32:
            if (temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[3]].state == TCG_TEMP_CONST
                && temps[args[4]].state == TCG_TEMP_CONST
                && temps[args[5]].state == TCG_TEMP_CONST) {
                uint32_t al = temps[args[2]].val;
                uint32_t ah = temps[args[3]].val;
                uint32_t bl = temps[args[4]].val;
                uint32_t bh = temps[args[5]].val;
                uint64_t a = ((uint64_t)ah << 32) | al;
                uint64_t b = ((uint64_t)bh << 32) | bl;
                TCGArg rl, rh;

                if (op == INDEX_op_add2_i32) {
                    a += b;
                } else {
                    a -= b;
                }

                /* We emit the extra nop when we emit the add2/sub2.  */
                assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);

                rl = args[0];
                rh = args[1];
                s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
                s->gen_opc_buf[++op_index] = INDEX_op_movi_i32;
                tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)a);
                tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(a >> 32));
                gen_args += 4;
                args += 6;
                break;
            }
            goto do_default;

        case INDEX_op_mulu2_i32:
            if (temps[args[2]].state == TCG_TEMP_CONST
                && temps[args[3]].state == TCG_TEMP_CONST) {
                uint32_t a = temps[args[2]].val;
                uint32_t b = temps[args[3]].val;
                uint64_t r = (uint64_t)a * b;
                TCGArg rl, rh;

                /* We emit the extra nop when we emit the mulu2.  */
                assert(s->gen_opc_buf[op_index + 1] == INDEX_op_nop);

                rl = args[0];
                rh = args[1];
                s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
                s->gen_opc_buf[++op_index] = INDEX_op_movi_i32;
                tcg_opt_gen_movi(&gen_args[0], rl, (uint32_t)r);
                tcg_opt_gen_movi(&gen_args[2], rh, (uint32_t)(r >> 32));
                gen_args += 4;
                args += 4;
                break;
            }
            goto do_default;

        case INDEX_op_brcond2_i32:
            tmp = do_constant_folding_cond2(&args[0], &args[2], args[4]);
            if (tmp != 2) {
                if (tmp) {
                    reset_all_temps(nb_temps);
                    s->gen_opc_buf[op_index] = INDEX_op_br;
                    gen_args[0] = args[5];
                    gen_args += 1;
                } else {
                    s->gen_opc_buf[op_index] = INDEX_op_nop;
                }
            } else if ((args[4] == TCG_COND_LT || args[4] == TCG_COND_GE)
                       && temps[args[2]].state == TCG_TEMP_CONST
                       && temps[args[3]].state == TCG_TEMP_CONST
                       && temps[args[2]].val == 0
                       && temps[args[3]].val == 0) {
                /* Simplify LT/GE comparisons vs zero to a single compare
                   vs the high word of the input.  */
                reset_all_temps(nb_temps);
                s->gen_opc_buf[op_index] = INDEX_op_brcond_i32;
                gen_args[0] = args[1];
                gen_args[1] = args[3];
                gen_args[2] = args[4];
                gen_args[3] = args[5];
                gen_args += 4;
            } else {
                goto do_default;
            }
            args += 6;
            break;

        case INDEX_op_setcond2_i32:
            tmp = do_constant_folding_cond2(&args[1], &args[3], args[5]);
            if (tmp != 2) {
                s->gen_opc_buf[op_index] = INDEX_op_movi_i32;
                tcg_opt_gen_movi(gen_args, args[0], tmp);
                gen_args += 2;
            } else if ((args[5] == TCG_COND_LT || args[5] == TCG_COND_GE)
                       && temps[args[3]].state == TCG_TEMP_CONST
                       && temps[args[4]].state == TCG_TEMP_CONST
                       && temps[args[3]].val == 0
                       && temps[args[4]].val == 0) {
                /* Simplify LT/GE comparisons vs zero to a single compare
                   vs the high word of the input.  */
                s->gen_opc_buf[op_index] = INDEX_op_setcond_i32;
                reset_temp(args[0]);
                gen_args[0] = args[0];
                gen_args[1] = args[2];
                gen_args[2] = args[4];
                gen_args[3] = args[5];
                gen_args += 4;
            } else {
                goto do_default;
            }
            args += 6;
            break;

        case INDEX_op_call:
            nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
            if (!(args[nb_call_args + 1] & (TCG_CALL_NO_READ_GLOBALS |
                                            TCG_CALL_NO_WRITE_GLOBALS))) {
                for (i = 0; i < nb_globals; i++) {
                    reset_temp(i);
                }
            }
            for (i = 0; i < (args[0] >> 16); i++) {
                reset_temp(args[i + 1]);
            }
            i = nb_call_args + 3;
            while (i) {
                *gen_args = *args;
                args++;
                gen_args++;
                i--;
            }
            break;

        default:
        do_default:
            /* Default case: we know nothing about operation (or were unable
               to compute the operation result) so no propagation is done.
               We trash everything if the operation is the end of a basic
               block, otherwise we only trash the output args.  "mask" is
               the non-zero bits mask for the first output arg.  */
            if (def->flags & TCG_OPF_BB_END) {
                reset_all_temps(nb_temps);
            } else {
                for (i = 0; i < def->nb_oargs; i++) {
                    reset_temp(args[i]);
                    /* Save the corresponding known-zero bits mask for the
                       first output argument (only one supported so far). */
                    if (i == 0) {
                        temps[args[i]].mask = mask;
                    }
                }
            }
            for (i = 0; i < def->nb_args; i++) {
                gen_args[i] = args[i];
            }
            args += def->nb_args;
            gen_args += def->nb_args;
            break;
        }
    }

    return gen_args;
}

TCGArg *tcg_optimize(TCGContext *s, uint16_t *tcg_opc_ptr,
        TCGArg *args, TCGOpDef *tcg_op_defs)
{
    TCGArg *res;
    res = tcg_constant_folding(s, tcg_opc_ptr, args, tcg_op_defs);
    return res;
}