llvm.org GIT mirror llvm / release_37 test / CodeGen / X86 / vector-popcnt-128.ll
release_37

Tree @release_37 (Download .tar.gz)

vector-popcnt-128.ll @release_37raw · history · blame

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2

target triple = "x86_64-unknown-unknown"

define <2 x i64> @testv2i64(<2 x i64> %in) {
; SSE2-LABEL: testv2i64:
; SSE2:       # BB#0:
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlq $1, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    psubq %xmm1, %xmm0
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [3689348814741910323,3689348814741910323]
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    pand %xmm1, %xmm2
; SSE2-NEXT:    psrlq $2, %xmm0
; SSE2-NEXT:    pand %xmm1, %xmm0
; SSE2-NEXT:    paddq %xmm2, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlq $4, %xmm1
; SSE2-NEXT:    paddq %xmm0, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    psadbw %xmm0, %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSE3-LABEL: testv2i64:
; SSE3:       # BB#0:
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlq $1, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    psubq %xmm1, %xmm0
; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [3689348814741910323,3689348814741910323]
; SSE3-NEXT:    movdqa %xmm0, %xmm2
; SSE3-NEXT:    pand %xmm1, %xmm2
; SSE3-NEXT:    psrlq $2, %xmm0
; SSE3-NEXT:    pand %xmm1, %xmm0
; SSE3-NEXT:    paddq %xmm2, %xmm0
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlq $4, %xmm1
; SSE3-NEXT:    paddq %xmm0, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    pxor %xmm0, %xmm0
; SSE3-NEXT:    psadbw %xmm0, %xmm1
; SSE3-NEXT:    movdqa %xmm1, %xmm0
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: testv2i64:
; SSSE3:       # BB#0:
; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSSE3-NEXT:    movdqa %xmm0, %xmm2
; SSSE3-NEXT:    pand %xmm1, %xmm2
; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSSE3-NEXT:    movdqa %xmm3, %xmm4
; SSSE3-NEXT:    pshufb %xmm2, %xmm4
; SSSE3-NEXT:    psrlw $4, %xmm0
; SSSE3-NEXT:    pand %xmm1, %xmm0
; SSSE3-NEXT:    pshufb %xmm0, %xmm3
; SSSE3-NEXT:    paddb %xmm4, %xmm3
; SSSE3-NEXT:    pxor %xmm0, %xmm0
; SSSE3-NEXT:    psadbw %xmm3, %xmm0
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: testv2i64:
; SSE41:       # BB#0:
; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE41-NEXT:    movdqa %xmm0, %xmm2
; SSE41-NEXT:    pand %xmm1, %xmm2
; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSE41-NEXT:    movdqa %xmm3, %xmm4
; SSE41-NEXT:    pshufb %xmm2, %xmm4
; SSE41-NEXT:    psrlw $4, %xmm0
; SSE41-NEXT:    pand %xmm1, %xmm0
; SSE41-NEXT:    pshufb %xmm0, %xmm3
; SSE41-NEXT:    paddb %xmm4, %xmm3
; SSE41-NEXT:    pxor %xmm0, %xmm0
; SSE41-NEXT:    psadbw %xmm3, %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: testv2i64:
; AVX:       # BB#0:
; AVX-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
; AVX-NEXT:    vpsrlw $4, %xmm0, %xmm0
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vpsadbw %xmm0, %xmm1, %xmm0
; AVX-NEXT:    retq
  %out = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %in)
  ret <2 x i64> %out
}

define <4 x i32> @testv4i32(<4 x i32> %in) {
; SSE2-LABEL: testv4i32:
; SSE2:       # BB#0:
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrld $1, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    psubd %xmm1, %xmm0
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [858993459,858993459,858993459,858993459]
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    pand %xmm1, %xmm2
; SSE2-NEXT:    psrld $2, %xmm0
; SSE2-NEXT:    pand %xmm1, %xmm0
; SSE2-NEXT:    paddd %xmm2, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrld $4, %xmm1
; SSE2-NEXT:    paddd %xmm0, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    pxor %xmm0, %xmm0
; SSE2-NEXT:    movdqa %xmm1, %xmm2
; SSE2-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE2-NEXT:    psadbw %xmm0, %xmm2
; SSE2-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE2-NEXT:    psadbw %xmm0, %xmm1
; SSE2-NEXT:    packuswb %xmm2, %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSE3-LABEL: testv4i32:
; SSE3:       # BB#0:
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrld $1, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    psubd %xmm1, %xmm0
; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [858993459,858993459,858993459,858993459]
; SSE3-NEXT:    movdqa %xmm0, %xmm2
; SSE3-NEXT:    pand %xmm1, %xmm2
; SSE3-NEXT:    psrld $2, %xmm0
; SSE3-NEXT:    pand %xmm1, %xmm0
; SSE3-NEXT:    paddd %xmm2, %xmm0
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrld $4, %xmm1
; SSE3-NEXT:    paddd %xmm0, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    pxor %xmm0, %xmm0
; SSE3-NEXT:    movdqa %xmm1, %xmm2
; SSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE3-NEXT:    psadbw %xmm0, %xmm2
; SSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT:    psadbw %xmm0, %xmm1
; SSE3-NEXT:    packuswb %xmm2, %xmm1
; SSE3-NEXT:    movdqa %xmm1, %xmm0
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: testv4i32:
; SSSE3:       # BB#0:
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSSE3-NEXT:    movdqa %xmm0, %xmm3
; SSSE3-NEXT:    pand %xmm2, %xmm3
; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSSE3-NEXT:    movdqa %xmm1, %xmm4
; SSSE3-NEXT:    pshufb %xmm3, %xmm4
; SSSE3-NEXT:    psrlw $4, %xmm0
; SSSE3-NEXT:    pand %xmm2, %xmm0
; SSSE3-NEXT:    pshufb %xmm0, %xmm1
; SSSE3-NEXT:    paddb %xmm4, %xmm1
; SSSE3-NEXT:    pxor %xmm0, %xmm0
; SSSE3-NEXT:    movdqa %xmm1, %xmm2
; SSSE3-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSSE3-NEXT:    psadbw %xmm0, %xmm2
; SSSE3-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSSE3-NEXT:    psadbw %xmm0, %xmm1
; SSSE3-NEXT:    packuswb %xmm2, %xmm1
; SSSE3-NEXT:    movdqa %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: testv4i32:
; SSE41:       # BB#0:
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE41-NEXT:    movdqa %xmm0, %xmm3
; SSE41-NEXT:    pand %xmm2, %xmm3
; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSE41-NEXT:    movdqa %xmm1, %xmm4
; SSE41-NEXT:    pshufb %xmm3, %xmm4
; SSE41-NEXT:    psrlw $4, %xmm0
; SSE41-NEXT:    pand %xmm2, %xmm0
; SSE41-NEXT:    pshufb %xmm0, %xmm1
; SSE41-NEXT:    paddb %xmm4, %xmm1
; SSE41-NEXT:    pxor %xmm0, %xmm0
; SSE41-NEXT:    movdqa %xmm1, %xmm2
; SSE41-NEXT:    punpckhdq {{.*#+}} xmm2 = xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE41-NEXT:    psadbw %xmm0, %xmm2
; SSE41-NEXT:    punpckldq {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE41-NEXT:    psadbw %xmm0, %xmm1
; SSE41-NEXT:    packuswb %xmm2, %xmm1
; SSE41-NEXT:    movdqa %xmm1, %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: testv4i32:
; AVX:       # BB#0:
; AVX-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
; AVX-NEXT:    vpsrlw $4, %xmm0, %xmm0
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vpunpckhdq {{.*#+}} xmm2 = xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; AVX-NEXT:    vpsadbw %xmm2, %xmm1, %xmm2
; AVX-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX-NEXT:    vpsadbw %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vpackuswb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    retq
  %out = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> %in)
  ret <4 x i32> %out
}

define <8 x i16> @testv8i16(<8 x i16> %in) {
; SSE2-LABEL: testv8i16:
; SSE2:       # BB#0:
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlw $1, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    psubw %xmm1, %xmm0
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [13107,13107,13107,13107,13107,13107,13107,13107]
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    pand %xmm1, %xmm2
; SSE2-NEXT:    psrlw $2, %xmm0
; SSE2-NEXT:    pand %xmm1, %xmm0
; SSE2-NEXT:    paddw %xmm2, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlw $4, %xmm1
; SSE2-NEXT:    paddw %xmm0, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    psllw $8, %xmm0
; SSE2-NEXT:    paddb %xmm1, %xmm0
; SSE2-NEXT:    psrlw $8, %xmm0
; SSE2-NEXT:    retq
;
; SSE3-LABEL: testv8i16:
; SSE3:       # BB#0:
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlw $1, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    psubw %xmm1, %xmm0
; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [13107,13107,13107,13107,13107,13107,13107,13107]
; SSE3-NEXT:    movdqa %xmm0, %xmm2
; SSE3-NEXT:    pand %xmm1, %xmm2
; SSE3-NEXT:    psrlw $2, %xmm0
; SSE3-NEXT:    pand %xmm1, %xmm0
; SSE3-NEXT:    paddw %xmm2, %xmm0
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlw $4, %xmm1
; SSE3-NEXT:    paddw %xmm0, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    movdqa %xmm1, %xmm0
; SSE3-NEXT:    psllw $8, %xmm0
; SSE3-NEXT:    paddb %xmm1, %xmm0
; SSE3-NEXT:    psrlw $8, %xmm0
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: testv8i16:
; SSSE3:       # BB#0:
; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSSE3-NEXT:    movdqa %xmm0, %xmm2
; SSSE3-NEXT:    pand %xmm1, %xmm2
; SSSE3-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSSE3-NEXT:    movdqa %xmm3, %xmm4
; SSSE3-NEXT:    pshufb %xmm2, %xmm4
; SSSE3-NEXT:    psrlw $4, %xmm0
; SSSE3-NEXT:    pand %xmm1, %xmm0
; SSSE3-NEXT:    pshufb %xmm0, %xmm3
; SSSE3-NEXT:    paddb %xmm4, %xmm3
; SSSE3-NEXT:    movdqa %xmm3, %xmm0
; SSSE3-NEXT:    psllw $8, %xmm0
; SSSE3-NEXT:    paddb %xmm3, %xmm0
; SSSE3-NEXT:    psrlw $8, %xmm0
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: testv8i16:
; SSE41:       # BB#0:
; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE41-NEXT:    movdqa %xmm0, %xmm2
; SSE41-NEXT:    pand %xmm1, %xmm2
; SSE41-NEXT:    movdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSE41-NEXT:    movdqa %xmm3, %xmm4
; SSE41-NEXT:    pshufb %xmm2, %xmm4
; SSE41-NEXT:    psrlw $4, %xmm0
; SSE41-NEXT:    pand %xmm1, %xmm0
; SSE41-NEXT:    pshufb %xmm0, %xmm3
; SSE41-NEXT:    paddb %xmm4, %xmm3
; SSE41-NEXT:    movdqa %xmm3, %xmm0
; SSE41-NEXT:    psllw $8, %xmm0
; SSE41-NEXT:    paddb %xmm3, %xmm0
; SSE41-NEXT:    psrlw $8, %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: testv8i16:
; AVX:       # BB#0:
; AVX-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
; AVX-NEXT:    vpsrlw $4, %xmm0, %xmm0
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    vpsllw $8, %xmm0, %xmm1
; AVX-NEXT:    vpaddb %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vpsrlw $8, %xmm0, %xmm0
; AVX-NEXT:    retq
  %out = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> %in)
  ret <8 x i16> %out
}

define <16 x i8> @testv16i8(<16 x i8> %in) {
; SSE2-LABEL: testv16i8:
; SSE2:       # BB#0:
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlw $1, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    psubb %xmm1, %xmm0
; SSE2-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; SSE2-NEXT:    movdqa %xmm0, %xmm2
; SSE2-NEXT:    pand %xmm1, %xmm2
; SSE2-NEXT:    psrlw $2, %xmm0
; SSE2-NEXT:    pand %xmm1, %xmm0
; SSE2-NEXT:    paddb %xmm2, %xmm0
; SSE2-NEXT:    movdqa %xmm0, %xmm1
; SSE2-NEXT:    psrlw $4, %xmm1
; SSE2-NEXT:    paddb %xmm0, %xmm1
; SSE2-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE2-NEXT:    movdqa %xmm1, %xmm0
; SSE2-NEXT:    retq
;
; SSE3-LABEL: testv16i8:
; SSE3:       # BB#0:
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlw $1, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    psubb %xmm1, %xmm0
; SSE3-NEXT:    movdqa {{.*#+}} xmm1 = [51,51,51,51,51,51,51,51,51,51,51,51,51,51,51,51]
; SSE3-NEXT:    movdqa %xmm0, %xmm2
; SSE3-NEXT:    pand %xmm1, %xmm2
; SSE3-NEXT:    psrlw $2, %xmm0
; SSE3-NEXT:    pand %xmm1, %xmm0
; SSE3-NEXT:    paddb %xmm2, %xmm0
; SSE3-NEXT:    movdqa %xmm0, %xmm1
; SSE3-NEXT:    psrlw $4, %xmm1
; SSE3-NEXT:    paddb %xmm0, %xmm1
; SSE3-NEXT:    pand {{.*}}(%rip), %xmm1
; SSE3-NEXT:    movdqa %xmm1, %xmm0
; SSE3-NEXT:    retq
;
; SSSE3-LABEL: testv16i8:
; SSSE3:       # BB#0:
; SSSE3-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSSE3-NEXT:    movdqa %xmm0, %xmm3
; SSSE3-NEXT:    pand %xmm2, %xmm3
; SSSE3-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSSE3-NEXT:    movdqa %xmm1, %xmm4
; SSSE3-NEXT:    pshufb %xmm3, %xmm4
; SSSE3-NEXT:    psrlw $4, %xmm0
; SSSE3-NEXT:    pand %xmm2, %xmm0
; SSSE3-NEXT:    pshufb %xmm0, %xmm1
; SSSE3-NEXT:    paddb %xmm4, %xmm1
; SSSE3-NEXT:    movdqa %xmm1, %xmm0
; SSSE3-NEXT:    retq
;
; SSE41-LABEL: testv16i8:
; SSE41:       # BB#0:
; SSE41-NEXT:    movdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; SSE41-NEXT:    movdqa %xmm0, %xmm3
; SSE41-NEXT:    pand %xmm2, %xmm3
; SSE41-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; SSE41-NEXT:    movdqa %xmm1, %xmm4
; SSE41-NEXT:    pshufb %xmm3, %xmm4
; SSE41-NEXT:    psrlw $4, %xmm0
; SSE41-NEXT:    pand %xmm2, %xmm0
; SSE41-NEXT:    pshufb %xmm0, %xmm1
; SSE41-NEXT:    paddb %xmm4, %xmm1
; SSE41-NEXT:    movdqa %xmm1, %xmm0
; SSE41-NEXT:    retq
;
; AVX-LABEL: testv16i8:
; AVX:       # BB#0:
; AVX-NEXT:    vmovdqa {{.*#+}} xmm1 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm2
; AVX-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,1,2,1,2,2,3,1,2,2,3,2,3,3,4]
; AVX-NEXT:    vpshufb %xmm2, %xmm3, %xmm2
; AVX-NEXT:    vpsrlw $4, %xmm0, %xmm0
; AVX-NEXT:    vpand %xmm1, %xmm0, %xmm0
; AVX-NEXT:    vpshufb %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vpaddb %xmm2, %xmm0, %xmm0
; AVX-NEXT:    retq
  %out = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> %in)
  ret <16 x i8> %out
}

define <2 x i64> @foldv2i64() {
; SSE-LABEL: foldv2i64:
; SSE:       # BB#0:
; SSE-NEXT:    movaps {{.*#+}} xmm0 = [1,64]
; SSE-NEXT:    retq
;
; AVX-LABEL: foldv2i64:
; AVX:       # BB#0:
; AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [1,64]
; AVX-NEXT:    retq
  %out = call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> <i64 256, i64 -1>)
  ret <2 x i64> %out
}

define <4 x i32> @foldv4i32() {
; SSE-LABEL: foldv4i32:
; SSE:       # BB#0:
; SSE-NEXT:    movaps {{.*#+}} xmm0 = [1,32,0,8]
; SSE-NEXT:    retq
;
; AVX-LABEL: foldv4i32:
; AVX:       # BB#0:
; AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [1,32,0,8]
; AVX-NEXT:    retq
  %out = call <4 x i32> @llvm.ctpop.v4i32(<4 x i32> <i32 256, i32 -1, i32 0, i32 255>)
  ret <4 x i32> %out
}

define <8 x i16> @foldv8i16() {
; SSE-LABEL: foldv8i16:
; SSE:       # BB#0:
; SSE-NEXT:    movaps {{.*#+}} xmm0 = [1,16,0,8,0,3,2,3]
; SSE-NEXT:    retq
;
; AVX-LABEL: foldv8i16:
; AVX:       # BB#0:
; AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [1,16,0,8,0,3,2,3]
; AVX-NEXT:    retq
  %out = call <8 x i16> @llvm.ctpop.v8i16(<8 x i16> <i16 256, i16 -1, i16 0, i16 255, i16 -65536, i16 7, i16 24, i16 88>)
  ret <8 x i16> %out
}

define <16 x i8> @foldv16i8() {
; SSE-LABEL: foldv16i8:
; SSE:       # BB#0:
; SSE-NEXT:    movaps {{.*#+}} xmm0 = [0,8,0,8,0,3,2,3,7,7,1,1,1,1,1,1]
; SSE-NEXT:    retq
;
; AVX-LABEL: foldv16i8:
; AVX:       # BB#0:
; AVX-NEXT:    vmovaps {{.*#+}} xmm0 = [0,8,0,8,0,3,2,3,7,7,1,1,1,1,1,1]
; AVX-NEXT:    retq
  %out = call <16 x i8> @llvm.ctpop.v16i8(<16 x i8> <i8 256, i8 -1, i8 0, i8 255, i8 -65536, i8 7, i8 24, i8 88, i8 -2, i8 254, i8 1, i8 2, i8 4, i8 8, i8 16, i8 32>)
  ret <16 x i8> %out
}

declare <2 x i64> @llvm.ctpop.v2i64(<2 x i64>)
declare <4 x i32> @llvm.ctpop.v4i32(<4 x i32>)
declare <8 x i16> @llvm.ctpop.v8i16(<8 x i16>)
declare <16 x i8> @llvm.ctpop.v16i8(<16 x i8>)