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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+f -target-abi=lp64f \
; RUN: | FileCheck %s --check-prefixes=CHECK,RV64I
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
; RUN: | FileCheck %s --check-prefixes=CHECK,RV64ZBB
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
; RUN: -riscv-disable-sextw-removal | FileCheck %s --check-prefix=NOREMOVAL
define void @test1(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: mv s0, a1
; CHECK-NEXT: sraw s1, a0, a1
; CHECK-NEXT: .LBB0_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mv a0, s1
; CHECK-NEXT: call bar@plt
; CHECK-NEXT: sllw s1, s1, s0
; CHECK-NEXT: bnez a0, .LBB0_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test1:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -32
; NOREMOVAL-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: mv s0, a1
; NOREMOVAL-NEXT: sraw s1, a0, a1
; NOREMOVAL-NEXT: .LBB0_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, s1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: sllw s1, s1, s0
; NOREMOVAL-NEXT: bnez a0, .LBB0_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 32
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = shl i32 %i3, %arg1
%i6 = icmp eq i32 %i4, 0
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare signext i32 @bar(i32 signext)
; The load here will be an anyext load in isel and sext.w will be emitted for
; the ret. Make sure we can look through logic ops to prove the sext.w is
; unnecessary.
define signext i32 @test2(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test2:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: not a1, a1
; RV64I-NEXT: and a0, a1, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test2:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, -2
; RV64ZBB-NEXT: rolw a1, a2, a1
; RV64ZBB-NEXT: and a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test2:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, -2
; NOREMOVAL-NEXT: rolw a1, a2, a1
; NOREMOVAL-NEXT: and a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = and i32 %neg, %a
ret i32 %and1
}
define signext i32 @test3(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test3:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: not a1, a1
; RV64I-NEXT: or a0, a1, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test3:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, -2
; RV64ZBB-NEXT: rolw a1, a2, a1
; RV64ZBB-NEXT: or a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test3:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, -2
; NOREMOVAL-NEXT: rolw a1, a2, a1
; NOREMOVAL-NEXT: or a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = or i32 %neg, %a
ret i32 %and1
}
define signext i32 @test4(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test4:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: xor a0, a1, a0
; RV64I-NEXT: not a0, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test4:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, 1
; RV64ZBB-NEXT: sllw a1, a2, a1
; RV64ZBB-NEXT: xnor a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test4:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, 1
; NOREMOVAL-NEXT: sllw a1, a2, a1
; NOREMOVAL-NEXT: xnor a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = xor i32 %neg, %a
ret i32 %and1
}
; Make sure we don't put a sext.w before bar when using cpopw.
define void @test5(i32 signext %arg, i32 signext %arg1) nounwind {
; RV64I-LABEL: test5:
; RV64I: # %bb.0: # %bb
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sraw a0, a0, a1
; RV64I-NEXT: lui a1, 349525
; RV64I-NEXT: addiw s0, a1, 1365
; RV64I-NEXT: lui a1, 209715
; RV64I-NEXT: addiw s1, a1, 819
; RV64I-NEXT: lui a1, 61681
; RV64I-NEXT: addiw s2, a1, -241
; RV64I-NEXT: lui a1, 4112
; RV64I-NEXT: addiw s3, a1, 257
; RV64I-NEXT: .LBB4_1: # %bb2
; RV64I-NEXT: # =>This Inner Loop Header: Depth=1
; RV64I-NEXT: call bar@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: srli a0, a0, 1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: subw a0, a1, a0
; RV64I-NEXT: and a2, a0, s1
; RV64I-NEXT: srli a0, a0, 2
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: add a0, a2, a0
; RV64I-NEXT: srli a2, a0, 4
; RV64I-NEXT: add a0, a0, a2
; RV64I-NEXT: and a0, a0, s2
; RV64I-NEXT: mulw a0, a0, s3
; RV64I-NEXT: srliw a0, a0, 24
; RV64I-NEXT: bnez a1, .LBB4_1
; RV64I-NEXT: # %bb.2: # %bb7
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test5:
; RV64ZBB: # %bb.0: # %bb
; RV64ZBB-NEXT: addi sp, sp, -16
; RV64ZBB-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64ZBB-NEXT: sraw a0, a0, a1
; RV64ZBB-NEXT: .LBB4_1: # %bb2
; RV64ZBB-NEXT: # =>This Inner Loop Header: Depth=1
; RV64ZBB-NEXT: call bar@plt
; RV64ZBB-NEXT: mv a1, a0
; RV64ZBB-NEXT: cpopw a0, a0
; RV64ZBB-NEXT: bnez a1, .LBB4_1
; RV64ZBB-NEXT: # %bb.2: # %bb7
; RV64ZBB-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64ZBB-NEXT: addi sp, sp, 16
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test5:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a1, a0, a1
; NOREMOVAL-NEXT: .LBB4_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: cpopw a1, a0
; NOREMOVAL-NEXT: bnez a0, .LBB4_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = tail call i32 @llvm.ctpop.i32(i32 %i4)
%i6 = icmp eq i32 %i4, 0
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i32 @llvm.ctpop.i32(i32)
define void @test6(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: fmv.w.x fs0, zero
; CHECK-NEXT: .LBB5_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call baz@plt
; CHECK-NEXT: feq.s a1, fa0, fs0
; CHECK-NEXT: fcvt.w.s a0, fa0, rtz
; CHECK-NEXT: beqz a1, .LBB5_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test6:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: fmv.w.x fs0, zero
; NOREMOVAL-NEXT: .LBB5_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call baz@plt
; NOREMOVAL-NEXT: feq.s a1, fa0, fs0
; NOREMOVAL-NEXT: fcvt.w.s a0, fa0, rtz
; NOREMOVAL-NEXT: beqz a1, .LBB5_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call float @baz(i32 signext %i3)
%i5 = fptosi float %i4 to i32
%i6 = fcmp oeq float %i4, zeroinitializer
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare float @baz(i32 signext %i3)
define void @test7(i32 signext %arg, i32 signext %arg1) nounwind {
; RV64I-LABEL: test7:
; RV64I: # %bb.0: # %bb
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lui a2, %hi(.LCPI6_0)
; RV64I-NEXT: ld s0, %lo(.LCPI6_0)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_1)
; RV64I-NEXT: ld s1, %lo(.LCPI6_1)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_2)
; RV64I-NEXT: ld s2, %lo(.LCPI6_2)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_3)
; RV64I-NEXT: ld s3, %lo(.LCPI6_3)(a2)
; RV64I-NEXT: sraw a0, a0, a1
; RV64I-NEXT: .LBB6_1: # %bb2
; RV64I-NEXT: # =>This Inner Loop Header: Depth=1
; RV64I-NEXT: call foo@plt
; RV64I-NEXT: srli a1, a0, 1
; RV64I-NEXT: and a1, a1, s0
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: and a1, a0, s1
; RV64I-NEXT: srli a0, a0, 2
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: srli a1, a0, 4
; RV64I-NEXT: add a0, a0, a1
; RV64I-NEXT: and a0, a0, s2
; RV64I-NEXT: mul a0, a0, s3
; RV64I-NEXT: srli a0, a0, 56
; RV64I-NEXT: bnez a0, .LBB6_1
; RV64I-NEXT: # %bb.2: # %bb7
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test7:
; RV64ZBB: # %bb.0: # %bb
; RV64ZBB-NEXT: addi sp, sp, -16
; RV64ZBB-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64ZBB-NEXT: sraw a0, a0, a1
; RV64ZBB-NEXT: .LBB6_1: # %bb2
; RV64ZBB-NEXT: # =>This Inner Loop Header: Depth=1
; RV64ZBB-NEXT: call foo@plt
; RV64ZBB-NEXT: cpop a0, a0
; RV64ZBB-NEXT: bnez a0, .LBB6_1
; RV64ZBB-NEXT: # %bb.2: # %bb7
; RV64ZBB-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64ZBB-NEXT: addi sp, sp, 16
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test7:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: .LBB6_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call foo@plt
; NOREMOVAL-NEXT: cpop a0, a0
; NOREMOVAL-NEXT: bnez a0, .LBB6_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i6, %bb2 ]
%i4 = tail call signext i64 @foo(i32 signext %i3)
%i5 = tail call i64 @llvm.ctpop.i64(i64 %i4)
%i6 = trunc i64 %i5 to i32
%i7 = icmp eq i32 %i6, 0
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i64 @llvm.ctpop.i64(i64)
define void @test8(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test8:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: .LBB7_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call foo@plt
; CHECK-NEXT: ori a0, a0, -256
; CHECK-NEXT: bnez a0, .LBB7_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test8:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: .LBB7_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call foo@plt
; NOREMOVAL-NEXT: ori a0, a0, -256
; NOREMOVAL-NEXT: bnez a0, .LBB7_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i6, %bb2 ]
%i4 = tail call signext i64 @foo(i32 signext %i3)
%i5 = or i64 %i4, -256
%i6 = trunc i64 %i5 to i32
%i7 = icmp eq i32 %i6, 0
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i64 @foo(i32 signext)
define void @test9(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test9:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: li s0, 254
; CHECK-NEXT: .LBB8_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call bar@plt
; CHECK-NEXT: mv a1, a0
; CHECK-NEXT: slti a0, a0, 255
; CHECK-NEXT: blt s0, a1, .LBB8_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test9:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a1, a0, a1
; NOREMOVAL-NEXT: li s0, 254
; NOREMOVAL-NEXT: .LBB8_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: slti a1, a0, 255
; NOREMOVAL-NEXT: blt s0, a0, .LBB8_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i7, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = icmp slt i32 %i4, 255
%i6 = sext i1 %i5 to i32
%i7 = sub i32 0, %i6
br i1 %i5, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
define void @test10(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test10:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: fmv.w.x fs0, zero
; CHECK-NEXT: .LBB9_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call baz@plt
; CHECK-NEXT: feq.s a1, fa0, fs0
; CHECK-NEXT: fmv.x.w a0, fa0
; CHECK-NEXT: beqz a1, .LBB9_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test10:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: fmv.w.x fs0, zero
; NOREMOVAL-NEXT: .LBB9_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call baz@plt
; NOREMOVAL-NEXT: feq.s a1, fa0, fs0
; NOREMOVAL-NEXT: fmv.x.w a0, fa0
; NOREMOVAL-NEXT: beqz a1, .LBB9_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call float @baz(i32 signext %i3)
%i5 = bitcast float %i4 to i32
%i6 = fcmp oeq float %i4, zeroinitializer
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
; simple test for forward-searching. (and 1234) only uses lower word of input
define signext i32 @test11(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test11:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a2, a2, -1
; CHECK-NEXT: li a3, 256
; CHECK-NEXT: .LBB10_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: andi a0, a0, 1234
; CHECK-NEXT: addi a2, a2, 1
; CHECK-NEXT: addw a0, a0, a1
; CHECK-NEXT: bltu a2, a3, .LBB10_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test11:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB10_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: andi a0, a0, 1234
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a0, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB10_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i5, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = and i64 %i1, 1234
%i5 = add i64 %i4, %arg2
%i6 = icmp ugt i64 %i2, 255
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
%i7 = trunc i64 %i5 to i32
ret i32 %i7
}
; circular use-dependency and multiple transformations.
define signext i32 @test12(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test12:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a3, a2, -1
; CHECK-NEXT: li a4, 256
; CHECK-NEXT: .LBB11_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xor a0, a0, a1
; CHECK-NEXT: mulw a2, a0, a1
; CHECK-NEXT: addw a0, a0, a2
; CHECK-NEXT: and a2, a2, a0
; CHECK-NEXT: addi a3, a3, 1
; CHECK-NEXT: add a0, a2, a1
; CHECK-NEXT: bltu a3, a4, .LBB11_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: mv a0, a2
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test12:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB11_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: xor a0, a0, a1
; NOREMOVAL-NEXT: mul a4, a0, a1
; NOREMOVAL-NEXT: add a0, a0, a4
; NOREMOVAL-NEXT: and a4, a4, a0
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a4, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB11_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a4
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i6, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = xor i64 %i1, %arg2
%i5 = mul i64 %i4, %arg2
%i9 = add i64 %i4, %i5
%i8 = and i64 %i5, %i9
%i6 = add i64 %i8, %arg2
%i7 = icmp ugt i64 %i2, 255
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
%r = trunc i64 %i8 to i32
ret i32 %r
}
; Not optimized. sdiv doesn't only use lower word
define signext i32 @test13(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test13:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a2, a2, -1
; CHECK-NEXT: li a3, 256
; CHECK-NEXT: .LBB12_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: div a0, a0, a1
; CHECK-NEXT: addi a2, a2, 1
; CHECK-NEXT: add a0, a0, a1
; CHECK-NEXT: bltu a2, a3, .LBB12_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: sext.w a0, a0
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test13:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB12_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: div a0, a0, a1
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a0, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB12_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i5, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = sdiv i64 %i1, %arg2
%i5 = add i64 %i4, %arg2
%i6 = icmp ugt i64 %i2, 255
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
%i8 = trunc i64 %i5 to i32
ret i32 %i8
}
|
