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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=knl -mattr=+avx512dq | FileCheck %s
declare <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvt_pd2qq_512(<8 x double> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_pd2qq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtpd2qq {ru-sae}, %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtpd2qq {rn-sae}, %zmm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvt_pd2uqq_512(<8 x double> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_pd2uqq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtpd2uqq {ru-sae}, %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtpd2uqq {rn-sae}, %zmm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvt_ps2qq_512(<8 x float> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ps2qq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtps2qq {ru-sae}, %ymm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtps2qq {rn-sae}, %ymm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvt_ps2uqq_512(<8 x float> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_ps2uqq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtps2uqq {ru-sae}, %ymm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtps2uqq {rn-sae}, %ymm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 2)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 0)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64>, <8 x double>, i8, i32)
define <8 x double>@test_int_x86_avx512_mask_cvt_qq2pd_512(<8 x i64> %x0, <8 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_qq2pd_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtqq2pd %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtqq2pd {rn-sae}, %zmm0, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 %x2, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 0)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
declare <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64>, <8 x float>, i8, i32)
define <8 x float>@test_int_x86_avx512_mask_cvt_qq2ps_512(<8 x i64> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_qq2ps_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtqq2ps %zmm0, %ymm1 {%k1}
; CHECK-NEXT: vcvtqq2ps {rn-sae}, %zmm0, %ymm0
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%res = call <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 %x2, i32 4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 0)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvttpd2qq.512(<8 x double>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvtt_pd2qq_512(<8 x double> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_pd2qq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvttpd2qq %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvttpd2qq {sae}, %zmm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvttpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 4)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvttpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvttpd2uqq.512(<8 x double>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvtt_pd2uqq_512(<8 x double> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_pd2uqq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvttpd2uqq %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvttpd2uqq {sae}, %zmm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvttpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, i32 4)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvttpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvttps2qq.512(<8 x float>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvtt_ps2qq_512(<8 x float> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_ps2qq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvttps2qq %ymm0, %zmm1 {%k1}
; CHECK-NEXT: vcvttps2qq {sae}, %ymm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvttps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 4)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvttps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x i64> @llvm.x86.avx512.mask.cvttps2uqq.512(<8 x float>, <8 x i64>, i8, i32)
define <8 x i64>@test_int_x86_avx512_mask_cvtt_ps2uqq_512(<8 x float> %x0, <8 x i64> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvtt_ps2uqq_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvttps2uqq %ymm0, %zmm1 {%k1}
; CHECK-NEXT: vcvttps2uqq {sae}, %ymm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x i64> @llvm.x86.avx512.mask.cvttps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i32 4)
%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvttps2uqq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i32 8)
%res2 = add <8 x i64> %res, %res1
ret <8 x i64> %res2
}
declare <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64>, <8 x double>, i8, i32)
define <8 x double>@test_int_x86_avx512_mask_cvt_uqq2pd_512(<8 x i64> %x0, <8 x double> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_uqq2pd_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtuqq2pd %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vcvtuqq2pd {rn-sae}, %zmm0, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 %x2, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.cvtuqq2pd.512(<8 x i64> %x0, <8 x double> %x1, i8 -1, i32 0)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
declare <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64>, <8 x float>, i8, i32)
define <8 x float>@test_int_x86_avx512_mask_cvt_uqq2ps_512(<8 x i64> %x0, <8 x float> %x1, i8 %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask_cvt_uqq2ps_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vcvtuqq2ps %zmm0, %ymm1 {%k1}
; CHECK-NEXT: vcvtuqq2ps {rn-sae}, %zmm0, %ymm0
; CHECK-NEXT: vaddps %ymm0, %ymm1, %ymm0
; CHECK-NEXT: retq
%res = call <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 %x2, i32 4)
%res1 = call <8 x float> @llvm.x86.avx512.mask.cvtuqq2ps.512(<8 x i64> %x0, <8 x float> %x1, i8 -1, i32 0)
%res2 = fadd <8 x float> %res, %res1
ret <8 x float> %res2
}
declare <8 x double> @llvm.x86.avx512.mask.reduce.pd.512(<8 x double>, i32, <8 x double>, i8, i32)
define <8 x double>@test_int_x86_avx512_mask_reduce_pd_512(<8 x double> %x0, <8 x double> %x2, i8 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_reduce_pd_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vreducepd $8, %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vreducepd $4, {sae}, %zmm0, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.reduce.pd.512(<8 x double> %x0, i32 8, <8 x double> %x2, i8 %x3, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.reduce.pd.512(<8 x double> %x0, i32 4, <8 x double> %x2, i8 -1, i32 8)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
declare <16 x float> @llvm.x86.avx512.mask.reduce.ps.512(<16 x float>, i32, <16 x float>, i16, i32)
define <16 x float>@test_int_x86_avx512_mask_reduce_ps_512(<16 x float> %x0, <16 x float> %x2, i16 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_reduce_ps_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vreduceps $44, {sae}, %zmm0, %zmm1 {%k1}
; CHECK-NEXT: vreduceps $11, %zmm0, %zmm0
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.reduce.ps.512(<16 x float> %x0, i32 44, <16 x float> %x2, i16 %x3, i32 8)
%res1 = call <16 x float> @llvm.x86.avx512.mask.reduce.ps.512(<16 x float> %x0, i32 11, <16 x float> %x2, i16 -1, i32 4)
%res2 = fadd <16 x float> %res, %res1
ret <16 x float> %res2
}
declare <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double>, <8 x double>, i32, <8 x double>, i8, i32)
define <8 x double>@test_int_x86_avx512_mask_range_pd_512(<8 x double> %x0, <8 x double> %x1, <8 x double> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_range_pd_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vrangepd $8, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT: vrangepd $4, {sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res = call <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double> %x0, <8 x double> %x1, i32 8, <8 x double> %x3, i8 %x4, i32 4)
%res1 = call <8 x double> @llvm.x86.avx512.mask.range.pd.512(<8 x double> %x0, <8 x double> %x1, i32 4, <8 x double> %x3, i8 -1, i32 8)
%res2 = fadd <8 x double> %res, %res1
ret <8 x double> %res2
}
declare <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float>, <16 x float>, i32, <16 x float>, i16, i32)
define <16 x float>@test_int_x86_avx512_mask_range_ps_512(<16 x float> %x0, <16 x float> %x1, <16 x float> %x3, i16 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_range_ps_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vrangeps $88, %zmm1, %zmm0, %zmm2 {%k1}
; CHECK-NEXT: vrangeps $4, {sae}, %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float> %x0, <16 x float> %x1, i32 88, <16 x float> %x3, i16 %x4, i32 4)
%res1 = call <16 x float> @llvm.x86.avx512.mask.range.ps.512(<16 x float> %x0, <16 x float> %x1, i32 4, <16 x float> %x3, i16 -1, i32 8)
%res2 = fadd <16 x float> %res, %res1
ret <16 x float> %res2
}
declare <4 x float> @llvm.x86.avx512.mask.reduce.ss(<4 x float>, <4 x float>,<4 x float>, i8, i32, i32)
define <4 x float>@test_int_x86_avx512_mask_reduce_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_reduce_ss:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vreducess $4, %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT: vreducess $4, {sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask.reduce.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 %x4, i32 4, i32 4)
%res1 = call <4 x float> @llvm.x86.avx512.mask.reduce.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 -1, i32 4, i32 8)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
}
declare <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float>, <4 x float>,<4 x float>, i8, i32, i32)
define <4 x float>@test_int_x86_avx512_mask_range_ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_range_ss:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vrangess $4, {sae}, %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT: vrangess $4, {sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vaddps %xmm0, %xmm2, %xmm0
; CHECK-NEXT: retq
%res = call <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 %x4, i32 4, i32 8)
%res1 = call <4 x float> @llvm.x86.avx512.mask.range.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x3, i8 -1, i32 4, i32 8)
%res2 = fadd <4 x float> %res, %res1
ret <4 x float> %res2
}
declare <2 x double> @llvm.x86.avx512.mask.reduce.sd(<2 x double>, <2 x double>,<2 x double>, i8, i32, i32)
define <2 x double>@test_int_x86_avx512_mask_reduce_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_reduce_sd:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vreducesd $4, %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT: vreducesd $4, {sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vaddpd %xmm0, %xmm2, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask.reduce.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 %x4, i32 4, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.reduce.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 -1, i32 4, i32 8)
%res2 = fadd <2 x double> %res, %res1
ret <2 x double> %res2
}
declare <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double>, <2 x double>,<2 x double>, i8, i32, i32)
define <2 x double>@test_int_x86_avx512_mask_range_sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 %x4) {
; CHECK-LABEL: test_int_x86_avx512_mask_range_sd:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vrangesd $4, %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT: vrangesd $4, {sae}, %xmm1, %xmm0, %xmm0
; CHECK-NEXT: vaddpd %xmm0, %xmm2, %xmm0
; CHECK-NEXT: retq
%res = call <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 %x4, i32 4, i32 4)
%res1 = call <2 x double> @llvm.x86.avx512.mask.range.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x3, i8 -1, i32 4, i32 8)
%res2 = fadd <2 x double> %res, %res1
ret <2 x double> %res2
}
declare i8 @llvm.x86.avx512.mask.fpclass.pd.512(<8 x double>, i32, i8)
define i8 @test_int_x86_avx512_mask_fpclass_pd_512(<8 x double> %x0, i8 %x1) {
; CHECK-LABEL: test_int_x86_avx512_mask_fpclass_pd_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfpclasspd $2, %zmm0, %k0 {%k1}
; CHECK-NEXT: kmovw %k0, %ecx
; CHECK-NEXT: vfpclasspd $4, %zmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: addb %cl, %al
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i8 @llvm.x86.avx512.mask.fpclass.pd.512(<8 x double> %x0, i32 2, i8 %x1)
%res1 = call i8 @llvm.x86.avx512.mask.fpclass.pd.512(<8 x double> %x0, i32 4, i8 -1)
%res2 = add i8 %res, %res1
ret i8 %res2
}
declare i16 @llvm.x86.avx512.mask.fpclass.ps.512(<16 x float>, i32, i16)
define i16@test_int_x86_avx512_mask_fpclass_ps_512(<16 x float> %x0, i16 %x1) {
; CHECK-LABEL: test_int_x86_avx512_mask_fpclass_ps_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfpclassps $4, %zmm0, %k0 {%k1}
; CHECK-NEXT: kmovw %k0, %ecx
; CHECK-NEXT: vfpclassps $4, %zmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: addl %ecx, %eax
; CHECK-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i16 @llvm.x86.avx512.mask.fpclass.ps.512(<16 x float> %x0, i32 4, i16 %x1)
%res1 = call i16 @llvm.x86.avx512.mask.fpclass.ps.512(<16 x float> %x0, i32 4, i16 -1)
%res2 = add i16 %res, %res1
ret i16 %res2
}
declare i8 @llvm.x86.avx512.mask.fpclass.sd(<2 x double>, i32, i8)
define i8 @test_int_x86_avx512_mask_fpclass_sd(<2 x double> %x0, i8 %x1) {
; CHECK-LABEL: test_int_x86_avx512_mask_fpclass_sd:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfpclasssd $2, %xmm0, %k0 {%k1}
; CHECK-NEXT: kmovw %k0, %ecx
; CHECK-NEXT: andl $1, %ecx
; CHECK-NEXT: vfpclasssd $4, %xmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: andl $1, %eax
; CHECK-NEXT: addb %cl, %al
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i8 @llvm.x86.avx512.mask.fpclass.sd(<2 x double> %x0, i32 2, i8 %x1)
%res1 = call i8 @llvm.x86.avx512.mask.fpclass.sd(<2 x double> %x0, i32 4, i8 -1)
%res2 = add i8 %res, %res1
ret i8 %res2
}
declare i8 @llvm.x86.avx512.mask.fpclass.ss(<4 x float>, i32, i8)
define i8 @test_int_x86_avx512_mask_fpclass_ss(<4 x float> %x0, i8 %x1) {
; CHECK-LABEL: test_int_x86_avx512_mask_fpclass_ss:
; CHECK: ## BB#0:
; CHECK-NEXT: andl $1, %edi
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vfpclassss $4, %xmm0, %k0 {%k1}
; CHECK-NEXT: kmovw %k0, %ecx
; CHECK-NEXT: andl $1, %ecx
; CHECK-NEXT: vfpclassss $4, %xmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: andl $1, %eax
; CHECK-NEXT: addb %cl, %al
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i8 @llvm.x86.avx512.mask.fpclass.ss(<4 x float> %x0, i32 4, i8 %x1)
%res1 = call i8 @llvm.x86.avx512.mask.fpclass.ss(<4 x float> %x0, i32 4, i8 -1)
%res2 = add i8 %res, %res1
ret i8 %res2
}
declare <16 x float> @llvm.x86.avx512.mask.broadcastf32x2.512(<4 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_broadcastf32x2_512(<4 x float> %x0, <16 x float> %x2, i16 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf32x2_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vbroadcastf32x2 {{.*#+}} zmm1 {%k1} = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vbroadcastf32x2 {{.*#+}} zmm2 {%k1} {z} = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vaddps %zmm2, %zmm1, %zmm1
; CHECK-NEXT: vbroadcastf32x2 {{.*#+}} zmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vaddps %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x2.512(<4 x float> %x0, <16 x float> %x2, i16 %x3)
%res1 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x2.512(<4 x float> %x0, <16 x float> zeroinitializer, i16 %x3)
%res2 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x2.512(<4 x float> %x0, <16 x float> %x2, i16 -1)
%res3 = fadd <16 x float> %res, %res1
%res4 = fadd <16 x float> %res3, %res2
ret <16 x float> %res4
}
declare <16 x i32> @llvm.x86.avx512.mask.broadcasti32x2.512(<4 x i32>, <16 x i32>, i16)
define <16 x i32>@test_int_x86_avx512_mask_broadcasti32x2_512(<4 x i32> %x0, <16 x i32> %x2, i16 %x3) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti32x2_512:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vbroadcasti32x2 {{.*#+}} zmm1 {%k1} = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vbroadcasti32x2 {{.*#+}} zmm2 {%k1} {z} = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vpaddd %zmm2, %zmm1, %zmm1
; CHECK-NEXT: vbroadcasti32x2 {{.*#+}} zmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
; CHECK-NEXT: vpaddd %zmm0, %zmm1, %zmm0
; CHECK-NEXT: retq
%res = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x2.512(<4 x i32> %x0, <16 x i32> %x2, i16 %x3)
%res1 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x2.512(<4 x i32> %x0, <16 x i32> zeroinitializer, i16 %x3)
%res2 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x2.512(<4 x i32> %x0, <16 x i32> %x2, i16 -1)
%res3 = add <16 x i32> %res, %res1
%res4 = add <16 x i32> %res3, %res2
ret <16 x i32> %res4
}
declare i16 @llvm.x86.avx512.cvtd2mask.512(<16 x i32>)
define i16@test_int_x86_avx512_cvtd2mask_512(<16 x i32> %x0) {
; CHECK-LABEL: test_int_x86_avx512_cvtd2mask_512:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmovd2m %zmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i16 @llvm.x86.avx512.cvtd2mask.512(<16 x i32> %x0)
ret i16 %res
}
declare i8 @llvm.x86.avx512.cvtq2mask.512(<8 x i64>)
define i8@test_int_x86_avx512_cvtq2mask_512(<8 x i64> %x0) {
; CHECK-LABEL: test_int_x86_avx512_cvtq2mask_512:
; CHECK: ## BB#0:
; CHECK-NEXT: vpmovq2m %zmm0, %k0
; CHECK-NEXT: kmovw %k0, %eax
; CHECK-NEXT: ## kill: %AL<def> %AL<kill> %EAX<kill>
; CHECK-NEXT: retq
%res = call i8 @llvm.x86.avx512.cvtq2mask.512(<8 x i64> %x0)
ret i8 %res
}
declare <16 x float> @llvm.x86.avx512.mask.broadcastf32x8.512(<8 x float>, <16 x float>, i16)
define <16 x float>@test_int_x86_avx512_mask_broadcastf32x8_512(<8 x float> %x0, <16 x float> %x2, i16 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf32x8_512:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm0 = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vaddps %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vaddps %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res1 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x8.512(<8 x float> %x0, <16 x float> %x2, i16 -1)
%res2 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x8.512(<8 x float> %x0, <16 x float> %x2, i16 %mask)
%res3 = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x8.512(<8 x float> %x0, <16 x float> zeroinitializer, i16 %mask)
%res4 = fadd <16 x float> %res1, %res2
%res5 = fadd <16 x float> %res3, %res4
ret <16 x float> %res5
}
define <16 x float>@test_int_x86_avx512_mask_broadcastf32x8_512_load(<8 x float>* %x0ptr, <16 x float> %x2, i16 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf32x8_512_load:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1
; CHECK-NEXT: vmovaps (%rdi), %ymm1
; CHECK-NEXT: vshuff32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: retq
%x0 = load <8 x float>, <8 x float>* %x0ptr
%res = call <16 x float> @llvm.x86.avx512.mask.broadcastf32x8.512(<8 x float> %x0, <16 x float> %x2, i16 %mask)
ret <16 x float> %res
}
declare <8 x double> @llvm.x86.avx512.mask.broadcastf64x2.512(<2 x double>, <8 x double>, i8)
define <8 x double>@test_int_x86_avx512_mask_broadcastf64x2_512(<2 x double> %x0, <8 x double> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf64x2_512:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm1 {%k1} = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm0 = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vaddpd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vaddpd %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res1 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x2.512(<2 x double> %x0, <8 x double> %x2, i8 -1)
%res2 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x2.512(<2 x double> %x0, <8 x double> %x2, i8 %mask)
%res3 = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x2.512(<2 x double> %x0, <8 x double> zeroinitializer, i8 %mask)
%res4 = fadd <8 x double> %res1, %res2
%res5 = fadd <8 x double> %res3, %res4
ret <8 x double> %res5
}
define <8 x double>@test_int_x86_avx512_mask_broadcastf64x2_512_load(<2 x double>* %x0ptr, <8 x double> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcastf64x2_512_load:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1
; CHECK-NEXT: vmovapd (%rdi), %xmm1
; CHECK-NEXT: vshuff64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,0,1,0,1,0,1]
; CHECK-NEXT: retq
%x0 = load <2 x double>, <2 x double>* %x0ptr
%res = call <8 x double> @llvm.x86.avx512.mask.broadcastf64x2.512(<2 x double> %x0, <8 x double> %x2, i8 %mask)
ret <8 x double> %res
}
declare <16 x i32> @llvm.x86.avx512.mask.broadcasti32x8.512(<8 x i32>, <16 x i32>, i16)
define <16 x i32>@test_int_x86_avx512_mask_broadcasti32x8_512(<8 x i32> %x0, <16 x i32> %x2, i16 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti32x8_512:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %YMM0<def> %YMM0<kill> %ZMM0<def>
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm1 {%k1} = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm0 = zmm0[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpaddd %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res1 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x8.512(<8 x i32> %x0, <16 x i32> %x2, i16 -1)
%res2 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x8.512(<8 x i32> %x0, <16 x i32> %x2, i16 %mask)
%res3 = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x8.512(<8 x i32> %x0, <16 x i32> zeroinitializer, i16 %mask)
%res4 = add <16 x i32> %res1, %res2
%res5 = add <16 x i32> %res3, %res4
ret <16 x i32> %res5
}
define <16 x i32>@test_int_x86_avx512_mask_broadcasti32x8_512_load(<8 x i32>* %x0ptr, <16 x i32> %x2, i16 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti32x8_512_load:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1
; CHECK-NEXT: vmovdqa (%rdi), %ymm1
; CHECK-NEXT: vshufi32x4 {{.*#+}} zmm0 {%k1} = zmm1[0,1,2,3,4,5,6,7,0,1,2,3,4,5,6,7]
; CHECK-NEXT: retq
%x0 = load <8 x i32>, <8 x i32>* %x0ptr
%res = call <16 x i32> @llvm.x86.avx512.mask.broadcasti32x8.512(<8 x i32> %x0, <16 x i32> %x2, i16 %mask)
ret <16 x i32> %res
}
declare <8 x i64> @llvm.x86.avx512.mask.broadcasti64x2.512(<2 x i64>, <8 x i64>, i8)
define <8 x i64>@test_int_x86_avx512_mask_broadcasti64x2_512(<2 x i64> %x0, <8 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti64x2_512:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; CHECK-NEXT: kmovw %edi, %k1
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm2 {%k1} {z} = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm1 {%k1} = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm0 = zmm0[0,1,0,1,0,1,0,1]
; CHECK-NEXT: vpaddq %zmm1, %zmm0, %zmm0
; CHECK-NEXT: vpaddq %zmm0, %zmm2, %zmm0
; CHECK-NEXT: retq
%res1 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x2.512(<2 x i64> %x0, <8 x i64> %x2, i8 -1)
%res2 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x2.512(<2 x i64> %x0, <8 x i64> %x2, i8 %mask)
%res3 = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x2.512(<2 x i64> %x0, <8 x i64> zeroinitializer, i8 %mask)
%res4 = add <8 x i64> %res1, %res2
%res5 = add <8 x i64> %res3, %res4
ret <8 x i64> %res5
}
define <8 x i64>@test_int_x86_avx512_mask_broadcasti64x2_512_load(<2 x i64>* %x0ptr, <8 x i64> %x2, i8 %mask) {
; CHECK-LABEL: test_int_x86_avx512_mask_broadcasti64x2_512_load:
; CHECK: ## BB#0:
; CHECK-NEXT: kmovw %esi, %k1
; CHECK-NEXT: vmovdqa (%rdi), %xmm1
; CHECK-NEXT: vshufi64x2 {{.*#+}} zmm0 {%k1} = zmm1[0,1,0,1,0,1,0,1]
; CHECK-NEXT: retq
%x0 = load <2 x i64>, <2 x i64>* %x0ptr
%res = call <8 x i64> @llvm.x86.avx512.mask.broadcasti64x2.512(<2 x i64> %x0, <8 x i64> %x2, i8 %mask)
ret <8 x i64> %res
}
|
