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
| // RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +sse4.1 -emit-llvm -o - -Wall -Werror | FileCheck %s
// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +sse4.1 -fno-signed-char -emit-llvm -o - -Wall -Werror | FileCheck %s
#include <immintrin.h>
// NOTE: This should match the tests in llvm/test/CodeGen/X86/sse41-intrinsics-fast-isel.ll
__m128i test_mm_blend_epi16(__m128i V1, __m128i V2) {
// CHECK-LABEL: test_mm_blend_epi16
// CHECK: shufflevector <8 x i16> %{{.*}}, <8 x i16> %{{.*}}, <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 7>
return _mm_blend_epi16(V1, V2, 42);
}
__m128d test_mm_blend_pd(__m128d V1, __m128d V2) {
// CHECK-LABEL: test_mm_blend_pd
// CHECK: shufflevector <2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x i32> <i32 0, i32 3>
return _mm_blend_pd(V1, V2, 2);
}
__m128 test_mm_blend_ps(__m128 V1, __m128 V2) {
// CHECK-LABEL: test_mm_blend_ps
// CHECK: shufflevector <4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x i32> <i32 0, i32 5, i32 6, i32 3>
return _mm_blend_ps(V1, V2, 6);
}
__m128i test_mm_blendv_epi8(__m128i V1, __m128i V2, __m128i V3) {
// CHECK-LABEL: test_mm_blendv_epi8
// CHECK: call <16 x i8> @llvm.x86.sse41.pblendvb(<16 x i8> %{{.*}}, <16 x i8> %{{.*}}, <16 x i8> %{{.*}})
return _mm_blendv_epi8(V1, V2, V3);
}
__m128d test_mm_blendv_pd(__m128d V1, __m128d V2, __m128d V3) {
// CHECK-LABEL: test_mm_blendv_pd
// CHECK: call <2 x double> @llvm.x86.sse41.blendvpd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
return _mm_blendv_pd(V1, V2, V3);
}
__m128 test_mm_blendv_ps(__m128 V1, __m128 V2, __m128 V3) {
// CHECK-LABEL: test_mm_blendv_ps
// CHECK: call <4 x float> @llvm.x86.sse41.blendvps(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
return _mm_blendv_ps(V1, V2, V3);
}
__m128d test_mm_ceil_pd(__m128d x) {
// CHECK-LABEL: test_mm_ceil_pd
// CHECK: call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %{{.*}}, i32 2)
return _mm_ceil_pd(x);
}
__m128 test_mm_ceil_ps(__m128 x) {
// CHECK-LABEL: test_mm_ceil_ps
// CHECK: call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %{{.*}}, i32 2)
return _mm_ceil_ps(x);
}
__m128d test_mm_ceil_sd(__m128d x, __m128d y) {
// CHECK-LABEL: test_mm_ceil_sd
// CHECK: call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i32 2)
return _mm_ceil_sd(x, y);
}
__m128 test_mm_ceil_ss(__m128 x, __m128 y) {
// CHECK-LABEL: test_mm_ceil_ss
// CHECK: call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i32 2)
return _mm_ceil_ss(x, y);
}
__m128i test_mm_cmpeq_epi64(__m128i A, __m128i B) {
// CHECK-LABEL: test_mm_cmpeq_epi64
// CHECK: icmp eq <2 x i64>
// CHECK: sext <2 x i1> %{{.*}} to <2 x i64>
return _mm_cmpeq_epi64(A, B);
}
__m128i test_mm_cvtepi8_epi16(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi16
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
// CHECK: sext <8 x i8> {{.*}} to <8 x i16>
return _mm_cvtepi8_epi16(a);
}
__m128i test_mm_cvtepi8_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi32
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: sext <4 x i8> {{.*}} to <4 x i32>
return _mm_cvtepi8_epi32(a);
}
__m128i test_mm_cvtepi8_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi8_epi64
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: sext <2 x i8> {{.*}} to <2 x i64>
return _mm_cvtepi8_epi64(a);
}
__m128i test_mm_cvtepi16_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi16_epi32
// CHECK: shufflevector <8 x i16> {{.*}}, <8 x i16> {{.*}}, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: sext <4 x i16> {{.*}} to <4 x i32>
return _mm_cvtepi16_epi32(a);
}
__m128i test_mm_cvtepi16_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi16_epi64
// CHECK: shufflevector <8 x i16> {{.*}}, <8 x i16> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: sext <2 x i16> {{.*}} to <2 x i64>
return _mm_cvtepi16_epi64(a);
}
__m128i test_mm_cvtepi32_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepi32_epi64
// CHECK: shufflevector <4 x i32> {{.*}}, <4 x i32> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: sext <2 x i32> {{.*}} to <2 x i64>
return _mm_cvtepi32_epi64(a);
}
__m128i test_mm_cvtepu8_epi16(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu8_epi16
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
// CHECK: zext <8 x i8> {{.*}} to <8 x i16>
return _mm_cvtepu8_epi16(a);
}
__m128i test_mm_cvtepu8_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu8_epi32
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: zext <4 x i8> {{.*}} to <4 x i32>
return _mm_cvtepu8_epi32(a);
}
__m128i test_mm_cvtepu8_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu8_epi64
// CHECK: shufflevector <16 x i8> {{.*}}, <16 x i8> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: zext <2 x i8> {{.*}} to <2 x i64>
return _mm_cvtepu8_epi64(a);
}
__m128i test_mm_cvtepu16_epi32(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu16_epi32
// CHECK: shufflevector <8 x i16> {{.*}}, <8 x i16> {{.*}}, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// CHECK: zext <4 x i16> {{.*}} to <4 x i32>
return _mm_cvtepu16_epi32(a);
}
__m128i test_mm_cvtepu16_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu16_epi64
// CHECK: shufflevector <8 x i16> {{.*}}, <8 x i16> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: zext <2 x i16> {{.*}} to <2 x i64>
return _mm_cvtepu16_epi64(a);
}
__m128i test_mm_cvtepu32_epi64(__m128i a) {
// CHECK-LABEL: test_mm_cvtepu32_epi64
// CHECK: shufflevector <4 x i32> {{.*}}, <4 x i32> {{.*}}, <2 x i32> <i32 0, i32 1>
// CHECK: zext <2 x i32> {{.*}} to <2 x i64>
return _mm_cvtepu32_epi64(a);
}
__m128d test_mm_dp_pd(__m128d x, __m128d y) {
// CHECK-LABEL: test_mm_dp_pd
// CHECK: call <2 x double> @llvm.x86.sse41.dppd(<2 x double> {{.*}}, <2 x double> {{.*}}, i8 7)
return _mm_dp_pd(x, y, 7);
}
__m128 test_mm_dp_ps(__m128 x, __m128 y) {
// CHECK-LABEL: test_mm_dp_ps
// CHECK: call <4 x float> @llvm.x86.sse41.dpps(<4 x float> {{.*}}, <4 x float> {{.*}}, i8 7)
return _mm_dp_ps(x, y, 7);
}
int test_mm_extract_epi8(__m128i x) {
// CHECK-LABEL: test_mm_extract_epi8
// CHECK: extractelement <16 x i8> %{{.*}}, {{i32|i64}} 1
// CHECK: zext i8 %{{.*}} to i32
return _mm_extract_epi8(x, 1);
}
int test_mm_extract_epi32(__m128i x) {
// CHECK-LABEL: test_mm_extract_epi32
// CHECK: extractelement <4 x i32> %{{.*}}, {{i32|i64}} 1
return _mm_extract_epi32(x, 1);
}
#ifdef __x86_64__
long long test_mm_extract_epi64(__m128i x) {
// CHECK-LABEL: test_mm_extract_epi64
// CHECK: extractelement <2 x i64> %{{.*}}, {{i32|i64}} 1
return _mm_extract_epi64(x, 1);
}
#endif
int test_mm_extract_ps(__m128 x) {
// CHECK-LABEL: test_mm_extract_ps
// CHECK: extractelement <4 x float> %{{.*}}, {{i32|i64}} 1
return _mm_extract_ps(x, 1);
}
__m128d test_mm_floor_pd(__m128d x) {
// CHECK-LABEL: test_mm_floor_pd
// CHECK: call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %{{.*}}, i32 1)
return _mm_floor_pd(x);
}
__m128 test_mm_floor_ps(__m128 x) {
// CHECK-LABEL: test_mm_floor_ps
// CHECK: call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %{{.*}}, i32 1)
return _mm_floor_ps(x);
}
__m128d test_mm_floor_sd(__m128d x, __m128d y) {
// CHECK-LABEL: test_mm_floor_sd
// CHECK: call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i32 1)
return _mm_floor_sd(x, y);
}
__m128 test_mm_floor_ss(__m128 x, __m128 y) {
// CHECK-LABEL: test_mm_floor_ss
// CHECK: call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i32 1)
return _mm_floor_ss(x, y);
}
__m128i test_mm_insert_epi8(__m128i x, char b) {
// CHECK-LABEL: test_mm_insert_epi8
// CHECK: insertelement <16 x i8> %{{.*}}, i8 %{{.*}}, {{i32|i64}} 1
return _mm_insert_epi8(x, b, 1);
}
__m128i test_mm_insert_epi32(__m128i x, int b) {
// CHECK-LABEL: test_mm_insert_epi32
// CHECK: insertelement <4 x i32> %{{.*}}, i32 %{{.*}}, {{i32|i64}} 1
return _mm_insert_epi32(x, b, 1);
}
#ifdef __x86_64__
__m128i test_mm_insert_epi64(__m128i x, long long b) {
// CHECK-LABEL: test_mm_insert_epi64
// CHECK: insertelement <2 x i64> %{{.*}}, i64 %{{.*}}, {{i32|i64}} 1
return _mm_insert_epi64(x, b, 1);
}
#endif
__m128 test_mm_insert_ps(__m128 x, __m128 y) {
// CHECK-LABEL: test_mm_insert_ps
// CHECK: call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i8 4)
return _mm_insert_ps(x, y, 4);
}
__m128i test_mm_max_epi8(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_max_epi8
// CHECK: [[CMP:%.*]] = icmp sgt <16 x i8> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <16 x i1> [[CMP]], <16 x i8> [[X]], <16 x i8> [[Y]]
return _mm_max_epi8(x, y);
}
__m128i test_mm_max_epi32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_max_epi32
// CHECK: [[CMP:%.*]] = icmp sgt <4 x i32> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <4 x i1> [[CMP]], <4 x i32> [[X]], <4 x i32> [[Y]]
return _mm_max_epi32(x, y);
}
__m128i test_mm_max_epu16(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_max_epu16
// CHECK: [[CMP:%.*]] = icmp ugt <8 x i16> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <8 x i1> [[CMP]], <8 x i16> [[X]], <8 x i16> [[Y]]
return _mm_max_epu16(x, y);
}
__m128i test_mm_max_epu32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_max_epu32
// CHECK: [[CMP:%.*]] = icmp ugt <4 x i32> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <4 x i1> [[CMP]], <4 x i32> [[X]], <4 x i32> [[Y]]
return _mm_max_epu32(x, y);
}
__m128i test_mm_min_epi8(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_min_epi8
// CHECK: [[CMP:%.*]] = icmp slt <16 x i8> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <16 x i1> [[CMP]], <16 x i8> [[X]], <16 x i8> [[Y]]
return _mm_min_epi8(x, y);
}
__m128i test_mm_min_epi32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_min_epi32
// CHECK: [[CMP:%.*]] = icmp slt <4 x i32> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <4 x i1> [[CMP]], <4 x i32> [[X]], <4 x i32> [[Y]]
return _mm_min_epi32(x, y);
}
__m128i test_mm_min_epu16(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_min_epu16
// CHECK: [[CMP:%.*]] = icmp ult <8 x i16> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <8 x i1> [[CMP]], <8 x i16> [[X]], <8 x i16> [[Y]]
return _mm_min_epu16(x, y);
}
__m128i test_mm_min_epu32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_min_epu32
// CHECK: [[CMP:%.*]] = icmp ult <4 x i32> [[X:%.*]], [[Y:%.*]]
// CHECK-NEXT: select <4 x i1> [[CMP]], <4 x i32> [[X]], <4 x i32> [[Y]]
return _mm_min_epu32(x, y);
}
__m128i test_mm_minpos_epu16(__m128i x) {
// CHECK-LABEL: test_mm_minpos_epu16
// CHECK: call <8 x i16> @llvm.x86.sse41.phminposuw(<8 x i16> %{{.*}})
return _mm_minpos_epu16(x);
}
__m128i test_mm_mpsadbw_epu8(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_mpsadbw_epu8
// CHECK: call <8 x i16> @llvm.x86.sse41.mpsadbw(<16 x i8> %{{.*}}, <16 x i8> %{{.*}}, i8 1)
return _mm_mpsadbw_epu8(x, y, 1);
}
__m128i test_mm_mul_epi32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_mul_epi32
// CHECK: shl <2 x i64> %{{.*}}, <i64 32, i64 32>
// CHECK: ashr <2 x i64> %{{.*}}, <i64 32, i64 32>
// CHECK: shl <2 x i64> %{{.*}}, <i64 32, i64 32>
// CHECK: ashr <2 x i64> %{{.*}}, <i64 32, i64 32>
// CHECK: mul <2 x i64> %{{.*}}, %{{.*}}
return _mm_mul_epi32(x, y);
}
__m128i test_mm_mullo_epi32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_mullo_epi32
// CHECK: mul <4 x i32>
return _mm_mullo_epi32(x, y);
}
__m128i test_mm_packus_epi32(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_packus_epi32
// CHECK: call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %{{.*}}, <4 x i32> %{{.*}})
return _mm_packus_epi32(x, y);
}
__m128d test_mm_round_pd(__m128d x) {
// CHECK-LABEL: test_mm_round_pd
// CHECK: call <2 x double> @llvm.x86.sse41.round.pd(<2 x double> %{{.*}}, i32 4)
return _mm_round_pd(x, 4);
}
__m128 test_mm_round_ps(__m128 x) {
// CHECK-LABEL: test_mm_round_ps
// CHECK: call <4 x float> @llvm.x86.sse41.round.ps(<4 x float> %{{.*}}, i32 4)
return _mm_round_ps(x, 4);
}
__m128d test_mm_round_sd(__m128d x, __m128d y) {
// CHECK-LABEL: test_mm_round_sd
// CHECK: call <2 x double> @llvm.x86.sse41.round.sd(<2 x double> %{{.*}}, <2 x double> %{{.*}}, i32 4)
return _mm_round_sd(x, y, 4);
}
__m128 test_mm_round_ss(__m128 x, __m128 y) {
// CHECK-LABEL: test_mm_round_ss
// CHECK: call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %{{.*}}, <4 x float> %{{.*}}, i32 4)
return _mm_round_ss(x, y, 4);
}
__m128i test_mm_stream_load_si128(__m128i const *a) {
// CHECK-LABEL: test_mm_stream_load_si128
// CHECK: load <2 x i64>, <2 x i64>* %{{.*}}, align 16, !nontemporal
return _mm_stream_load_si128(a);
}
int test_mm_test_all_ones(__m128i x) {
// CHECK-LABEL: test_mm_test_all_ones
// CHECK: call i32 @llvm.x86.sse41.ptestc(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_test_all_ones(x);
}
int test_mm_test_all_zeros(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_test_all_zeros
// CHECK: call i32 @llvm.x86.sse41.ptestz(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_test_all_zeros(x, y);
}
int test_mm_test_mix_ones_zeros(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_test_mix_ones_zeros
// CHECK: call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_test_mix_ones_zeros(x, y);
}
int test_mm_testc_si128(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_testc_si128
// CHECK: call i32 @llvm.x86.sse41.ptestc(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_testc_si128(x, y);
}
int test_mm_testnzc_si128(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_testnzc_si128
// CHECK: call i32 @llvm.x86.sse41.ptestnzc(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_testnzc_si128(x, y);
}
int test_mm_testz_si128(__m128i x, __m128i y) {
// CHECK-LABEL: test_mm_testz_si128
// CHECK: call i32 @llvm.x86.sse41.ptestz(<2 x i64> %{{.*}}, <2 x i64> %{{.*}})
return _mm_testz_si128(x, y);
}
|