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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+avx512bw,+avx512vl | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512VL
define <2 x i64> @insert_v2i64_x1(<2 x i64> %a) {
; SSE2-LABEL: insert_v2i64_x1:
; SSE2: # %bb.0:
; SSE2-NEXT: movlpd {{.*#+}} xmm0 = mem[0],xmm0[1]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v2i64_x1:
; SSE3: # %bb.0:
; SSE3-NEXT: movlpd {{.*#+}} xmm0 = mem[0],xmm0[1]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v2i64_x1:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movlpd {{.*#+}} xmm0 = mem[0],xmm0[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v2i64_x1:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v2i64_x1:
; AVX1: # %bb.0:
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v2i64_x1:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v2i64_x1:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX512-NEXT: vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
; AVX512-NEXT: retq
%1 = insertelement <2 x i64> %a, i64 -1, i32 0
ret <2 x i64> %1
}
define <4 x i64> @insert_v4i64_01x3(<4 x i64> %a) {
; SSE2-LABEL: insert_v4i64_01x3:
; SSE2: # %bb.0:
; SSE2-NEXT: movlpd {{.*#+}} xmm1 = mem[0],xmm1[1]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v4i64_01x3:
; SSE3: # %bb.0:
; SSE3-NEXT: movlpd {{.*#+}} xmm1 = mem[0],xmm1[1]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v4i64_01x3:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movlpd {{.*#+}} xmm1 = mem[0],xmm1[1]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v4i64_01x3:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm2[0,1,2,3],xmm1[4,5,6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v4i64_01x3:
; AVX1: # %bb.0:
; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vcmptrueps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v4i64_01x3:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v4i64_01x3:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
; AVX512-NEXT: retq
%1 = insertelement <4 x i64> %a, i64 -1, i32 2
ret <4 x i64> %1
}
define <4 x i32> @insert_v4i32_01x3(<4 x i32> %a) {
; SSE2-LABEL: insert_v4i32_01x3:
; SSE2: # %bb.0:
; SSE2-NEXT: movl $-1, %eax
; SSE2-NEXT: movd %eax, %xmm1
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSE2-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v4i32_01x3:
; SSE3: # %bb.0:
; SSE3-NEXT: movl $-1, %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v4i32_01x3:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movl $-1, %eax
; SSSE3-NEXT: movd %eax, %xmm1
; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[3,0]
; SSSE3-NEXT: shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v4i32_01x3:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v4i32_01x3:
; AVX1: # %bb.0:
; AVX1-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v4i32_01x3:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v4i32_01x3:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX512-NEXT: vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2],xmm0[3]
; AVX512-NEXT: retq
%1 = insertelement <4 x i32> %a, i32 -1, i32 2
ret <4 x i32> %1
}
define <8 x i32> @insert_v8i32_x12345x7(<8 x i32> %a) {
; SSE2-LABEL: insert_v8i32_x12345x7:
; SSE2: # %bb.0:
; SSE2-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE2-NEXT: movss {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3]
; SSE2-NEXT: movl $-1, %eax
; SSE2-NEXT: movd %eax, %xmm2
; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm1[3,0]
; SSE2-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm2[0,2]
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v8i32_x12345x7:
; SSE3: # %bb.0:
; SSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE3-NEXT: movss {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3]
; SSE3-NEXT: movl $-1, %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm1[3,0]
; SSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm2[0,2]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v8i32_x12345x7:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSSE3-NEXT: movss {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3]
; SSSE3-NEXT: movl $-1, %eax
; SSSE3-NEXT: movd %eax, %xmm2
; SSSE3-NEXT: shufps {{.*#+}} xmm2 = xmm2[0,0],xmm1[3,0]
; SSSE3-NEXT: shufps {{.*#+}} xmm1 = xmm1[0,1],xmm2[0,2]
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v8i32_x12345x7:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm2[0,1],xmm0[2,3,4,5,6,7]
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm2[4,5],xmm1[6,7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v8i32_x12345x7:
; AVX1: # %bb.0:
; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
; AVX1-NEXT: vcmptrueps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5],ymm1[6],ymm0[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v8i32_x12345x7:
; AVX2: # %bb.0:
; AVX2-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5],ymm1[6],ymm0[7]
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v8i32_x12345x7:
; AVX512: # %bb.0:
; AVX512-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5],ymm1[6],ymm0[7]
; AVX512-NEXT: retq
%1 = insertelement <8 x i32> %a, i32 -1, i32 0
%2 = insertelement <8 x i32> %1, i32 -1, i32 6
ret <8 x i32> %2
}
define <8 x i16> @insert_v8i16_x12345x7(<8 x i16> %a) {
; SSE2-LABEL: insert_v8i16_x12345x7:
; SSE2: # %bb.0:
; SSE2-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSE2-NEXT: pinsrw $0, %eax, %xmm0
; SSE2-NEXT: pinsrw $6, %eax, %xmm0
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v8i16_x12345x7:
; SSE3: # %bb.0:
; SSE3-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSE3-NEXT: pinsrw $0, %eax, %xmm0
; SSE3-NEXT: pinsrw $6, %eax, %xmm0
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v8i16_x12345x7:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSSE3-NEXT: pinsrw $0, %eax, %xmm0
; SSSE3-NEXT: pinsrw $6, %eax, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v8i16_x12345x7:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm1, %xmm1
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3,4,5],xmm1[6],xmm0[7]
; SSE41-NEXT: retq
;
; AVX-LABEL: insert_v8i16_x12345x7:
; AVX: # %bb.0:
; AVX-NEXT: vpcmpeqd %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpblendw {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3,4,5],xmm1[6],xmm0[7]
; AVX-NEXT: retq
%1 = insertelement <8 x i16> %a, i16 -1, i32 0
%2 = insertelement <8 x i16> %1, i16 -1, i32 6
ret <8 x i16> %2
}
define <16 x i16> @insert_v16i16_x12345x789ABCDEx(<16 x i16> %a) {
; SSE2-LABEL: insert_v16i16_x12345x789ABCDEx:
; SSE2: # %bb.0:
; SSE2-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSE2-NEXT: pinsrw $0, %eax, %xmm0
; SSE2-NEXT: pinsrw $6, %eax, %xmm0
; SSE2-NEXT: pinsrw $7, %eax, %xmm1
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v16i16_x12345x789ABCDEx:
; SSE3: # %bb.0:
; SSE3-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSE3-NEXT: pinsrw $0, %eax, %xmm0
; SSE3-NEXT: pinsrw $6, %eax, %xmm0
; SSE3-NEXT: pinsrw $7, %eax, %xmm1
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v16i16_x12345x789ABCDEx:
; SSSE3: # %bb.0:
; SSSE3-NEXT: movl $65535, %eax # imm = 0xFFFF
; SSSE3-NEXT: pinsrw $0, %eax, %xmm0
; SSSE3-NEXT: pinsrw $6, %eax, %xmm0
; SSSE3-NEXT: pinsrw $7, %eax, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v16i16_x12345x789ABCDEx:
; SSE41: # %bb.0:
; SSE41-NEXT: pcmpeqd %xmm2, %xmm2
; SSE41-NEXT: pblendw {{.*#+}} xmm0 = xmm2[0],xmm0[1,2,3,4,5],xmm2[6],xmm0[7]
; SSE41-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,5,6],xmm2[7]
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v16i16_x12345x789ABCDEx:
; AVX1: # %bb.0:
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vorps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vorps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vandps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: vorps {{.*}}(%rip), %ymm0, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v16i16_x12345x789ABCDEx:
; AVX2: # %bb.0:
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpcmpeqd %ymm2, %ymm2, %ymm2
; AVX2-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX2-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,0]
; AVX2-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX2-NEXT: retq
;
; AVX512F-LABEL: insert_v16i16_x12345x789ABCDEx:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX512F-NEXT: vpcmpeqd %ymm2, %ymm2, %ymm2
; AVX512F-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; AVX512F-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX512F-NEXT: vmovdqa {{.*#+}} ymm1 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,0]
; AVX512F-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX512F-NEXT: retq
;
; AVX512VL-LABEL: insert_v16i16_x12345x789ABCDEx:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpcmpeqd %ymm1, %ymm1, %ymm1
; AVX512VL-NEXT: movw $1, %ax
; AVX512VL-NEXT: kmovd %eax, %k1
; AVX512VL-NEXT: vmovdqu16 %ymm1, %ymm0 {%k1}
; AVX512VL-NEXT: movw $64, %ax
; AVX512VL-NEXT: kmovd %eax, %k1
; AVX512VL-NEXT: vmovdqu16 %ymm1, %ymm0 {%k1}
; AVX512VL-NEXT: movw $-32768, %ax # imm = 0x8000
; AVX512VL-NEXT: kmovd %eax, %k1
; AVX512VL-NEXT: vmovdqu16 %ymm1, %ymm0 {%k1}
; AVX512VL-NEXT: retq
%1 = insertelement <16 x i16> %a, i16 -1, i32 0
%2 = insertelement <16 x i16> %1, i16 -1, i32 6
%3 = insertelement <16 x i16> %2, i16 -1, i32 15
ret <16 x i16> %3
}
define <16 x i8> @insert_v16i8_x123456789ABCDEx(<16 x i8> %a) {
; SSE2-LABEL: insert_v16i8_x123456789ABCDEx:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm1 = [0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm1, %xmm0
; SSE2-NEXT: movl $255, %eax
; SSE2-NEXT: movd %eax, %xmm2
; SSE2-NEXT: pandn %xmm2, %xmm1
; SSE2-NEXT: por %xmm1, %xmm0
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0]
; SSE2-NEXT: por %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v16i8_x123456789ABCDEx:
; SSE3: # %bb.0:
; SSE3-NEXT: movdqa {{.*#+}} xmm1 = [0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; SSE3-NEXT: pand %xmm1, %xmm0
; SSE3-NEXT: movl $255, %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: pandn %xmm2, %xmm1
; SSE3-NEXT: por %xmm1, %xmm0
; SSE3-NEXT: pand {{.*}}(%rip), %xmm0
; SSE3-NEXT: pslldq {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0]
; SSE3-NEXT: por %xmm2, %xmm0
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v16i8_x123456789ABCDEx:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = zero,xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
; SSSE3-NEXT: movl $255, %eax
; SSSE3-NEXT: movd %eax, %xmm1
; SSSE3-NEXT: movdqa %xmm1, %xmm2
; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = xmm2[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: por %xmm2, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14],zero
; SSSE3-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0]
; SSSE3-NEXT: por %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v16i8_x123456789ABCDEx:
; SSE41: # %bb.0:
; SSE41-NEXT: movl $255, %eax
; SSE41-NEXT: pinsrb $0, %eax, %xmm0
; SSE41-NEXT: pinsrb $15, %eax, %xmm0
; SSE41-NEXT: retq
;
; AVX-LABEL: insert_v16i8_x123456789ABCDEx:
; AVX: # %bb.0:
; AVX-NEXT: movl $255, %eax
; AVX-NEXT: vpinsrb $0, %eax, %xmm0, %xmm0
; AVX-NEXT: vpinsrb $15, %eax, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = insertelement <16 x i8> %a, i8 -1, i32 0
%2 = insertelement <16 x i8> %1, i8 -1, i32 15
ret <16 x i8> %2
}
define <32 x i8> @insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx(<32 x i8> %a) {
; SSE2-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; SSE2: # %bb.0:
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: movl $255, %eax
; SSE2-NEXT: movd %eax, %xmm3
; SSE2-NEXT: pandn %xmm3, %xmm2
; SSE2-NEXT: por %xmm2, %xmm0
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0]
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: movdqa %xmm3, %xmm4
; SSE2-NEXT: pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0]
; SSE2-NEXT: por %xmm4, %xmm0
; SSE2-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255]
; SSE2-NEXT: pand %xmm5, %xmm1
; SSE2-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1]
; SSE2-NEXT: pandn %xmm3, %xmm5
; SSE2-NEXT: por %xmm5, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: por %xmm4, %xmm1
; SSE2-NEXT: retq
;
; SSE3-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; SSE3: # %bb.0:
; SSE3-NEXT: movdqa {{.*#+}} xmm2 = [0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
; SSE3-NEXT: pand %xmm2, %xmm0
; SSE3-NEXT: movl $255, %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: pandn %xmm3, %xmm2
; SSE3-NEXT: por %xmm2, %xmm0
; SSE3-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0]
; SSE3-NEXT: pand %xmm2, %xmm0
; SSE3-NEXT: movdqa %xmm3, %xmm4
; SSE3-NEXT: pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0]
; SSE3-NEXT: por %xmm4, %xmm0
; SSE3-NEXT: movdqa {{.*#+}} xmm5 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,255]
; SSE3-NEXT: pand %xmm5, %xmm1
; SSE3-NEXT: pslldq {{.*#+}} xmm3 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm3[0,1]
; SSE3-NEXT: pandn %xmm3, %xmm5
; SSE3-NEXT: por %xmm5, %xmm1
; SSE3-NEXT: pand %xmm2, %xmm1
; SSE3-NEXT: por %xmm4, %xmm1
; SSE3-NEXT: retq
;
; SSSE3-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = zero,xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
; SSSE3-NEXT: movl $255, %eax
; SSSE3-NEXT: movd %eax, %xmm2
; SSSE3-NEXT: movdqa %xmm2, %xmm3
; SSSE3-NEXT: pshufb {{.*#+}} xmm3 = xmm3[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: por %xmm3, %xmm0
; SSSE3-NEXT: movdqa {{.*#+}} xmm3 = [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,128]
; SSSE3-NEXT: pshufb %xmm3, %xmm0
; SSSE3-NEXT: movdqa %xmm2, %xmm4
; SSSE3-NEXT: pslldq {{.*#+}} xmm4 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm4[0]
; SSSE3-NEXT: por %xmm4, %xmm0
; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[0,1,2,3,4,5,6,7,8,9,10,11,12,13],zero,xmm1[15]
; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0],zero
; SSSE3-NEXT: por %xmm2, %xmm1
; SSSE3-NEXT: pshufb %xmm3, %xmm1
; SSSE3-NEXT: por %xmm4, %xmm1
; SSSE3-NEXT: retq
;
; SSE41-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; SSE41: # %bb.0:
; SSE41-NEXT: movl $255, %eax
; SSE41-NEXT: pinsrb $0, %eax, %xmm0
; SSE41-NEXT: pinsrb $15, %eax, %xmm0
; SSE41-NEXT: pinsrb $14, %eax, %xmm1
; SSE41-NEXT: pinsrb $15, %eax, %xmm1
; SSE41-NEXT: retq
;
; AVX1-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; AVX1: # %bb.0:
; AVX1-NEXT: movl $255, %eax
; AVX1-NEXT: vpinsrb $0, %eax, %xmm0, %xmm1
; AVX1-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; AVX1-NEXT: vblendps {{.*#+}} ymm1 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
; AVX1-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
; AVX1-NEXT: vpinsrb $15, %eax, %xmm0, %xmm0
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; AVX2: # %bb.0:
; AVX2-NEXT: movl $255, %eax
; AVX2-NEXT: vpinsrb $0, %eax, %xmm0, %xmm1
; AVX2-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; AVX2-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX2-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
; AVX2-NEXT: vpinsrb $15, %eax, %xmm0, %xmm0
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX2-NEXT: retq
;
; AVX512-LABEL: insert_v32i8_x123456789ABCDEzGHIJKLMNOPQRSTxx:
; AVX512: # %bb.0:
; AVX512-NEXT: movl $255, %eax
; AVX512-NEXT: vpinsrb $0, %eax, %xmm0, %xmm1
; AVX512-NEXT: vpinsrb $15, %eax, %xmm1, %xmm1
; AVX512-NEXT: vpblendd {{.*#+}} ymm1 = ymm1[0,1,2,3],ymm0[4,5,6,7]
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm0
; AVX512-NEXT: vpinsrb $14, %eax, %xmm0, %xmm0
; AVX512-NEXT: vpinsrb $15, %eax, %xmm0, %xmm0
; AVX512-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX512-NEXT: retq
%1 = insertelement <32 x i8> %a, i8 -1, i32 0
%2 = insertelement <32 x i8> %1, i8 -1, i32 15
%3 = insertelement <32 x i8> %2, i8 -1, i32 30
%4 = insertelement <32 x i8> %3, i8 -1, i32 31
ret <32 x i8> %4
}
|
