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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=CHECK --check-prefix=SSE --check-prefix=SSE-RECIP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX-RECIP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx,+fma | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=FMA-RECIP
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=BTVER2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=SANDY
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=haswell -mattr=-fma | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=HASWELL-NO-FMA
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=knl -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=KNL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=skx -print-schedule | FileCheck %s --check-prefix=CHECK --check-prefix=AVX --check-prefix=AVX512 --check-prefix=SKX
; If the target's divss/divps instructions are substantially
; slower than rcpss/rcpps with a Newton-Raphson refinement,
; we should generate the estimate sequence.
; See PR21385 ( http://llvm.org/bugs/show_bug.cgi?id=21385 )
; for details about the accuracy, speed, and implementation
; differences of x86 reciprocal estimates.
define float @f32_no_estimate(float %x) #0 {
; SSE-LABEL: f32_no_estimate:
; SSE: # BB#0:
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: divss %xmm0, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: f32_no_estimate:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-RECIP-NEXT: vdivss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: f32_no_estimate:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; FMA-RECIP-NEXT: vdivss %xmm0, %xmm1, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: f32_no_estimate:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [5:1.00]
; BTVER2-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [19:19.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: f32_no_estimate:
; SANDY: # BB#0:
; SANDY-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [6:0.50]
; SANDY-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [14:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: f32_no_estimate:
; HASWELL: # BB#0:
; HASWELL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [1:0.50]
; HASWELL-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: f32_no_estimate:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; HASWELL-NO-FMA-NEXT: vdivss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: f32_no_estimate:
; KNL: # BB#0:
; KNL-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [1:0.50]
; KNL-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: f32_no_estimate:
; SKX: # BB#0:
; SKX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero sched: [5:0.50]
; SKX-NEXT: vdivss %xmm0, %xmm1, %xmm0 # sched: [11:1.00]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast float 1.0, %x
ret float %div
}
define float @f32_one_step(float %x) #1 {
; SSE-LABEL: f32_one_step:
; SSE: # BB#0:
; SSE-NEXT: rcpss %xmm0, %xmm2
; SSE-NEXT: mulss %xmm2, %xmm0
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: subss %xmm0, %xmm1
; SSE-NEXT: mulss %xmm2, %xmm1
; SSE-NEXT: addss %xmm2, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: f32_one_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-RECIP-NEXT: vsubss %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: vaddss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: f32_one_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; FMA-RECIP-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0
; FMA-RECIP-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: f32_one_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:1.00]
; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [2:1.00]
; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: f32_one_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [6:0.50]
; SANDY-NEXT: vsubss %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: f32_one_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
; HASWELL-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: f32_one_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: f32_one_step:
; KNL: # BB#0:
; KNL-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1
; KNL-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: f32_one_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1 # sched: [4:1.00]
; SKX-NEXT: vfnmadd213ss {{.*}}(%rip), %xmm1, %xmm0 # sched: [9:0.50]
; SKX-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast float 1.0, %x
ret float %div
}
define float @f32_two_step(float %x) #2 {
; SSE-LABEL: f32_two_step:
; SSE: # BB#0:
; SSE-NEXT: rcpss %xmm0, %xmm2
; SSE-NEXT: movaps %xmm0, %xmm3
; SSE-NEXT: mulss %xmm2, %xmm3
; SSE-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE-NEXT: movaps %xmm1, %xmm4
; SSE-NEXT: subss %xmm3, %xmm4
; SSE-NEXT: mulss %xmm2, %xmm4
; SSE-NEXT: addss %xmm2, %xmm4
; SSE-NEXT: mulss %xmm4, %xmm0
; SSE-NEXT: subss %xmm0, %xmm1
; SSE-NEXT: mulss %xmm4, %xmm1
; SSE-NEXT: addss %xmm4, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: f32_two_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm2
; AVX-RECIP-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; AVX-RECIP-NEXT: vsubss %xmm2, %xmm3, %xmm2
; AVX-RECIP-NEXT: vmulss %xmm2, %xmm1, %xmm2
; AVX-RECIP-NEXT: vaddss %xmm2, %xmm1, %xmm1
; AVX-RECIP-NEXT: vmulss %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT: vsubss %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT: vmulss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: vaddss %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: f32_two_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; FMA-RECIP-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; FMA-RECIP-NEXT: vmovaps %xmm1, %xmm3
; FMA-RECIP-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3
; FMA-RECIP-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0
; FMA-RECIP-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: f32_two_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero sched: [5:1.00]
; BTVER2-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [2:1.00]
; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm2 # sched: [2:1.00]
; BTVER2-NEXT: vsubss %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
; BTVER2-NEXT: vmulss %xmm2, %xmm1, %xmm2 # sched: [2:1.00]
; BTVER2-NEXT: vaddss %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
; BTVER2-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vsubss %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: f32_two_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm2 # sched: [5:1.00]
; SANDY-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero sched: [6:0.50]
; SANDY-NEXT: vsubss %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
; SANDY-NEXT: vmulss %xmm2, %xmm1, %xmm2 # sched: [5:1.00]
; SANDY-NEXT: vaddss %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
; SANDY-NEXT: vmulss %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vsubss %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: vmulss %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vaddss %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: f32_two_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpss %xmm0, %xmm0, %xmm1 # sched: [5:1.00]
; HASWELL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [1:0.50]
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; HASWELL-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
; HASWELL-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: f32_two_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm2
; HASWELL-NO-FMA-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; HASWELL-NO-FMA-NEXT: vsubss %xmm2, %xmm3, %xmm2
; HASWELL-NO-FMA-NEXT: vmulss %xmm2, %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT: vaddss %xmm2, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT: vmulss %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT: vsubss %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT: vmulss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: vaddss %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: f32_two_step:
; KNL: # BB#0:
; KNL-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1
; KNL-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [1:0.50]
; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; KNL-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
; KNL-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: f32_two_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ss %xmm0, %xmm0, %xmm1 # sched: [4:1.00]
; SKX-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero sched: [5:0.50]
; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; SKX-NEXT: vfnmadd213ss %xmm2, %xmm0, %xmm3 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ss %xmm1, %xmm1, %xmm3 # sched: [4:0.33]
; SKX-NEXT: vfnmadd213ss %xmm2, %xmm3, %xmm0 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ss %xmm3, %xmm3, %xmm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast float 1.0, %x
ret float %div
}
define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 {
; SSE-LABEL: v4f32_no_estimate:
; SSE: # BB#0:
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: divps %xmm0, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v4f32_no_estimate:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v4f32_no_estimate:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; FMA-RECIP-NEXT: vdivps %xmm0, %xmm1, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v4f32_no_estimate:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [19:19.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v4f32_no_estimate:
; SANDY: # BB#0:
; SANDY-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [6:0.50]
; SANDY-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [14:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v4f32_no_estimate:
; HASWELL: # BB#0:
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v4f32_no_estimate:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1]
; HASWELL-NO-FMA-NEXT: vdivps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v4f32_no_estimate:
; KNL: # BB#0:
; KNL-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [13:1.00]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v4f32_no_estimate:
; SKX: # BB#0:
; SKX-NEXT: vbroadcastss {{.*#+}} xmm1 = [1,1,1,1] sched: [6:0.50]
; SKX-NEXT: vdivps %xmm0, %xmm1, %xmm0 # sched: [11:1.00]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
; SSE-LABEL: v4f32_one_step:
; SSE: # BB#0:
; SSE-NEXT: rcpps %xmm0, %xmm2
; SSE-NEXT: mulps %xmm2, %xmm0
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: subps %xmm0, %xmm1
; SSE-NEXT: mulps %xmm2, %xmm1
; SSE-NEXT: addps %xmm2, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v4f32_one_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpps %xmm0, %xmm1
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vsubps %xmm0, %xmm2, %xmm0
; AVX-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v4f32_one_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpps %xmm0, %xmm1
; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %xmm1, %xmm0
; FMA-RECIP-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v4f32_one_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vrcpps %xmm0, %xmm1 # sched: [2:1.00]
; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v4f32_one_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [6:0.50]
; SANDY-NEXT: vsubps %xmm0, %xmm2, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v4f32_one_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v4f32_one_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1]
; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm2, %xmm0
; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v4f32_one_step:
; KNL: # BB#0:
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm1, %xmm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v4f32_one_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ps %xmm0, %xmm1 # sched: [4:1.00]
; SKX-NEXT: vfnmadd213ps {{.*}}(%rip){1to4}, %xmm1, %xmm0 # sched: [10:0.50]
; SKX-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <4 x float> @v4f32_two_step(<4 x float> %x) #2 {
; SSE-LABEL: v4f32_two_step:
; SSE: # BB#0:
; SSE-NEXT: rcpps %xmm0, %xmm2
; SSE-NEXT: movaps %xmm0, %xmm3
; SSE-NEXT: mulps %xmm2, %xmm3
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: movaps %xmm1, %xmm4
; SSE-NEXT: subps %xmm3, %xmm4
; SSE-NEXT: mulps %xmm2, %xmm4
; SSE-NEXT: addps %xmm2, %xmm4
; SSE-NEXT: mulps %xmm4, %xmm0
; SSE-NEXT: subps %xmm0, %xmm1
; SSE-NEXT: mulps %xmm4, %xmm1
; SSE-NEXT: addps %xmm4, %xmm1
; SSE-NEXT: movaps %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v4f32_two_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpps %xmm0, %xmm1
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm2
; AVX-RECIP-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vsubps %xmm2, %xmm3, %xmm2
; AVX-RECIP-NEXT: vmulps %xmm2, %xmm1, %xmm2
; AVX-RECIP-NEXT: vaddps %xmm2, %xmm1, %xmm1
; AVX-RECIP-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX-RECIP-NEXT: vsubps %xmm0, %xmm3, %xmm0
; AVX-RECIP-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v4f32_two_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpps %xmm0, %xmm1
; FMA-RECIP-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; FMA-RECIP-NEXT: vmovaps %xmm1, %xmm3
; FMA-RECIP-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3
; FMA-RECIP-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3
; FMA-RECIP-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0
; FMA-RECIP-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v4f32_two_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vrcpps %xmm0, %xmm1 # sched: [2:1.00]
; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm2 # sched: [2:1.00]
; BTVER2-NEXT: vsubps %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
; BTVER2-NEXT: vmulps %xmm2, %xmm1, %xmm2 # sched: [2:1.00]
; BTVER2-NEXT: vaddps %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
; BTVER2-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vsubps %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [2:1.00]
; BTVER2-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v4f32_two_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm2 # sched: [5:1.00]
; SANDY-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [6:0.50]
; SANDY-NEXT: vsubps %xmm2, %xmm3, %xmm2 # sched: [3:1.00]
; SANDY-NEXT: vmulps %xmm2, %xmm1, %xmm2 # sched: [5:1.00]
; SANDY-NEXT: vaddps %xmm2, %xmm1, %xmm1 # sched: [3:1.00]
; SANDY-NEXT: vmulps %xmm1, %xmm0, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vsubps %xmm0, %xmm3, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: vmulps %xmm0, %xmm1, %xmm0 # sched: [5:1.00]
; SANDY-NEXT: vaddps %xmm0, %xmm1, %xmm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v4f32_two_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; HASWELL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
; HASWELL-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v4f32_two_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpps %xmm0, %xmm1
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm2
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} xmm3 = [1,1,1,1]
; HASWELL-NO-FMA-NEXT: vsubps %xmm2, %xmm3, %xmm2
; HASWELL-NO-FMA-NEXT: vmulps %xmm2, %xmm1, %xmm2
; HASWELL-NO-FMA-NEXT: vaddps %xmm2, %xmm1, %xmm1
; HASWELL-NO-FMA-NEXT: vmulps %xmm1, %xmm0, %xmm0
; HASWELL-NO-FMA-NEXT: vsubps %xmm0, %xmm3, %xmm0
; HASWELL-NO-FMA-NEXT: vmulps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: vaddps %xmm0, %xmm1, %xmm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v4f32_two_step:
; KNL: # BB#0:
; KNL-NEXT: vrcpps %xmm0, %xmm1 # sched: [5:1.00]
; KNL-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [5:0.50]
; KNL-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v4f32_two_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ps %xmm0, %xmm1 # sched: [4:1.00]
; SKX-NEXT: vbroadcastss {{.*#+}} xmm2 = [1,1,1,1] sched: [6:0.50]
; SKX-NEXT: vmovaps %xmm1, %xmm3 # sched: [1:1.00]
; SKX-NEXT: vfnmadd213ps %xmm2, %xmm0, %xmm3 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ps %xmm1, %xmm1, %xmm3 # sched: [4:0.33]
; SKX-NEXT: vfnmadd213ps %xmm2, %xmm3, %xmm0 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ps %xmm3, %xmm3, %xmm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
; SSE-LABEL: v8f32_no_estimate:
; SSE: # BB#0:
; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: movaps %xmm2, %xmm3
; SSE-NEXT: divps %xmm0, %xmm3
; SSE-NEXT: divps %xmm1, %xmm2
; SSE-NEXT: movaps %xmm3, %xmm0
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v8f32_no_estimate:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vdivps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v8f32_no_estimate:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; FMA-RECIP-NEXT: vdivps %ymm0, %ymm1, %ymm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v8f32_no_estimate:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [38:38.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v8f32_no_estimate:
; SANDY: # BB#0:
; SANDY-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [7:0.50]
; SANDY-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [29:2.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v8f32_no_estimate:
; HASWELL: # BB#0:
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [21:2.00]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v8f32_no_estimate:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1]
; HASWELL-NO-FMA-NEXT: vdivps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v8f32_no_estimate:
; KNL: # BB#0:
; KNL-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [21:2.00]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v8f32_no_estimate:
; SKX: # BB#0:
; SKX-NEXT: vbroadcastss {{.*#+}} ymm1 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
; SKX-NEXT: vdivps %ymm0, %ymm1, %ymm0 # sched: [11:1.00]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
; SSE-LABEL: v8f32_one_step:
; SSE: # BB#0:
; SSE-NEXT: rcpps %xmm0, %xmm4
; SSE-NEXT: mulps %xmm4, %xmm0
; SSE-NEXT: movaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: movaps %xmm2, %xmm3
; SSE-NEXT: subps %xmm0, %xmm3
; SSE-NEXT: mulps %xmm4, %xmm3
; SSE-NEXT: addps %xmm4, %xmm3
; SSE-NEXT: rcpps %xmm1, %xmm0
; SSE-NEXT: mulps %xmm0, %xmm1
; SSE-NEXT: subps %xmm1, %xmm2
; SSE-NEXT: mulps %xmm0, %xmm2
; SSE-NEXT: addps %xmm0, %xmm2
; SSE-NEXT: movaps %xmm3, %xmm0
; SSE-NEXT: movaps %xmm2, %xmm1
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v8f32_one_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpps %ymm0, %ymm1
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vsubps %ymm0, %ymm2, %ymm0
; AVX-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT: vaddps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v8f32_one_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm1
; FMA-RECIP-NEXT: vfnmadd213ps {{.*}}(%rip), %ymm1, %ymm0
; FMA-RECIP-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v8f32_one_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vrcpps %ymm0, %ymm1 # sched: [2:2.00]
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:2.00]
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v8f32_one_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
; SANDY-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [7:0.50]
; SANDY-NEXT: vsubps %ymm0, %ymm2, %ymm0 # sched: [3:1.00]
; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
; SANDY-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v8f32_one_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v8f32_one_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1]
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm2, %ymm0
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v8f32_one_step:
; KNL: # BB#0:
; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm1, %ymm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v8f32_one_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ps %ymm0, %ymm1 # sched: [4:1.00]
; SKX-NEXT: vfnmadd213ps {{.*}}(%rip){1to8}, %ymm1, %ymm0 # sched: [11:0.50]
; SKX-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
define <8 x float> @v8f32_two_step(<8 x float> %x) #2 {
; SSE-LABEL: v8f32_two_step:
; SSE: # BB#0:
; SSE-NEXT: movaps %xmm1, %xmm2
; SSE-NEXT: rcpps %xmm0, %xmm3
; SSE-NEXT: movaps %xmm0, %xmm4
; SSE-NEXT: mulps %xmm3, %xmm4
; SSE-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; SSE-NEXT: movaps %xmm1, %xmm5
; SSE-NEXT: subps %xmm4, %xmm5
; SSE-NEXT: mulps %xmm3, %xmm5
; SSE-NEXT: addps %xmm3, %xmm5
; SSE-NEXT: mulps %xmm5, %xmm0
; SSE-NEXT: movaps %xmm1, %xmm3
; SSE-NEXT: subps %xmm0, %xmm3
; SSE-NEXT: mulps %xmm5, %xmm3
; SSE-NEXT: addps %xmm5, %xmm3
; SSE-NEXT: rcpps %xmm2, %xmm0
; SSE-NEXT: movaps %xmm2, %xmm4
; SSE-NEXT: mulps %xmm0, %xmm4
; SSE-NEXT: movaps %xmm1, %xmm5
; SSE-NEXT: subps %xmm4, %xmm5
; SSE-NEXT: mulps %xmm0, %xmm5
; SSE-NEXT: addps %xmm0, %xmm5
; SSE-NEXT: mulps %xmm5, %xmm2
; SSE-NEXT: subps %xmm2, %xmm1
; SSE-NEXT: mulps %xmm5, %xmm1
; SSE-NEXT: addps %xmm5, %xmm1
; SSE-NEXT: movaps %xmm3, %xmm0
; SSE-NEXT: retq
;
; AVX-RECIP-LABEL: v8f32_two_step:
; AVX-RECIP: # BB#0:
; AVX-RECIP-NEXT: vrcpps %ymm0, %ymm1
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm2
; AVX-RECIP-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-RECIP-NEXT: vsubps %ymm2, %ymm3, %ymm2
; AVX-RECIP-NEXT: vmulps %ymm2, %ymm1, %ymm2
; AVX-RECIP-NEXT: vaddps %ymm2, %ymm1, %ymm1
; AVX-RECIP-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX-RECIP-NEXT: vsubps %ymm0, %ymm3, %ymm0
; AVX-RECIP-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT: vaddps %ymm0, %ymm1, %ymm0
; AVX-RECIP-NEXT: retq
;
; FMA-RECIP-LABEL: v8f32_two_step:
; FMA-RECIP: # BB#0:
; FMA-RECIP-NEXT: vrcpps %ymm0, %ymm1
; FMA-RECIP-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; FMA-RECIP-NEXT: vmovaps %ymm1, %ymm3
; FMA-RECIP-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3
; FMA-RECIP-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3
; FMA-RECIP-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0
; FMA-RECIP-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0
; FMA-RECIP-NEXT: retq
;
; BTVER2-LABEL: v8f32_two_step:
; BTVER2: # BB#0:
; BTVER2-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [5:1.00]
; BTVER2-NEXT: vrcpps %ymm0, %ymm1 # sched: [2:2.00]
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [2:2.00]
; BTVER2-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:2.00]
; BTVER2-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [2:2.00]
; BTVER2-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:2.00]
; BTVER2-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:2.00]
; BTVER2-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [2:2.00]
; BTVER2-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:2.00]
; BTVER2-NEXT: retq # sched: [4:1.00]
;
; SANDY-LABEL: v8f32_two_step:
; SANDY: # BB#0:
; SANDY-NEXT: vrcpps %ymm0, %ymm1 # sched: [7:2.00]
; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm2 # sched: [5:1.00]
; SANDY-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00] sched: [7:0.50]
; SANDY-NEXT: vsubps %ymm2, %ymm3, %ymm2 # sched: [3:1.00]
; SANDY-NEXT: vmulps %ymm2, %ymm1, %ymm2 # sched: [5:1.00]
; SANDY-NEXT: vaddps %ymm2, %ymm1, %ymm1 # sched: [3:1.00]
; SANDY-NEXT: vmulps %ymm1, %ymm0, %ymm0 # sched: [5:1.00]
; SANDY-NEXT: vsubps %ymm0, %ymm3, %ymm0 # sched: [3:1.00]
; SANDY-NEXT: vmulps %ymm0, %ymm1, %ymm0 # sched: [5:1.00]
; SANDY-NEXT: vaddps %ymm0, %ymm1, %ymm0 # sched: [3:1.00]
; SANDY-NEXT: retq # sched: [1:1.00]
;
; HASWELL-LABEL: v8f32_two_step:
; HASWELL: # BB#0:
; HASWELL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
; HASWELL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; HASWELL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [5:0.50]
; HASWELL-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [5:0.50]
; HASWELL-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [5:0.50]
; HASWELL-NEXT: retq # sched: [2:1.00]
;
; HASWELL-NO-FMA-LABEL: v8f32_two_step:
; HASWELL-NO-FMA: # BB#0:
; HASWELL-NO-FMA-NEXT: vrcpps %ymm0, %ymm1
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm2
; HASWELL-NO-FMA-NEXT: vbroadcastss {{.*#+}} ymm3 = [1,1,1,1,1,1,1,1]
; HASWELL-NO-FMA-NEXT: vsubps %ymm2, %ymm3, %ymm2
; HASWELL-NO-FMA-NEXT: vmulps %ymm2, %ymm1, %ymm2
; HASWELL-NO-FMA-NEXT: vaddps %ymm2, %ymm1, %ymm1
; HASWELL-NO-FMA-NEXT: vmulps %ymm1, %ymm0, %ymm0
; HASWELL-NO-FMA-NEXT: vsubps %ymm0, %ymm3, %ymm0
; HASWELL-NO-FMA-NEXT: vmulps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT: vaddps %ymm0, %ymm1, %ymm0
; HASWELL-NO-FMA-NEXT: retq
;
; KNL-LABEL: v8f32_two_step:
; KNL: # BB#0:
; KNL-NEXT: vrcpps %ymm0, %ymm1 # sched: [11:2.00]
; KNL-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [1:0.50]
; KNL-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [5:0.50]
; KNL-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [5:0.50]
; KNL-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [5:0.50]
; KNL-NEXT: retq # sched: [2:1.00]
;
; SKX-LABEL: v8f32_two_step:
; SKX: # BB#0:
; SKX-NEXT: vrcp14ps %ymm0, %ymm1 # sched: [4:1.00]
; SKX-NEXT: vbroadcastss {{.*#+}} ymm2 = [1,1,1,1,1,1,1,1] sched: [7:0.50]
; SKX-NEXT: vmovaps %ymm1, %ymm3 # sched: [1:1.00]
; SKX-NEXT: vfnmadd213ps %ymm2, %ymm0, %ymm3 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ps %ymm1, %ymm1, %ymm3 # sched: [4:0.33]
; SKX-NEXT: vfnmadd213ps %ymm2, %ymm3, %ymm0 # sched: [4:0.33]
; SKX-NEXT: vfmadd132ps %ymm3, %ymm3, %ymm0 # sched: [4:0.33]
; SKX-NEXT: retq # sched: [7:1.00]
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!divf,!vec-divf" }
attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }
attributes #2 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:2,vec-divf:2" }
|
