fma4-builtins.c
13 KB
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
// RUN: %clang_cc1 -ffreestanding %s -triple=x86_64-apple-darwin -target-feature +fma4 -emit-llvm -o - -Wall -Werror | FileCheck %s
#include <x86intrin.h>
__m128 test_mm_macc_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_macc_ps
// CHECK: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
return _mm_macc_ps(a, b, c);
}
__m128d test_mm_macc_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_macc_pd
// CHECK: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
return _mm_macc_pd(a, b, c);
}
__m128 test_mm_macc_ss(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_macc_ss
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float %{{.*}}, float %{{.*}})
// CHECK: insertelement <4 x float> zeroinitializer, float %{{.*}}, i64 0
return _mm_macc_ss(a, b, c);
}
__m128d test_mm_macc_sd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_macc_sd
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double %{{.*}}, double %{{.*}})
// CHECK: insertelement <2 x double> zeroinitializer, double %{{.*}}, i64 0
return _mm_macc_sd(a, b, c);
}
__m128 test_mm_msub_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_msub_ps
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
return _mm_msub_ps(a, b, c);
}
__m128d test_mm_msub_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_msub_pd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
return _mm_msub_pd(a, b, c);
}
__m128 test_mm_msub_ss(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_msub_ss
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: [[C:%.+]] = extractelement <4 x float> [[NEG]], i64 0
// CHECK: call float @llvm.fma.f32(float %{{.*}}, float %{{.*}}, float [[C]])
// CHECK: insertelement <4 x float> zeroinitializer, float %{{.*}}, i64 0
return _mm_msub_ss(a, b, c);
}
__m128d test_mm_msub_sd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_msub_sd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: [[C:%.+]] = extractelement <2 x double> [[NEG]], i64 0
// CHECK: call double @llvm.fma.f64(double %{{.*}}, double %{{.*}}, double [[C]])
// CHECK: insertelement <2 x double> zeroinitializer, double %{{.*}}, i64 0
return _mm_msub_sd(a, b, c);
}
__m128 test_mm_nmacc_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_nmacc_ps
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
return _mm_nmacc_ps(a, b, c);
}
__m128d test_mm_nmacc_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_nmacc_pd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
return _mm_nmacc_pd(a, b, c);
}
__m128 test_mm_nmacc_ss(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_nmacc_ss
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[A:%.+]] = extractelement <4 x float> [[NEG]], i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: call float @llvm.fma.f32(float [[A]], float %{{.*}}, float %{{.*}})
// CHECK: insertelement <4 x float> zeroinitializer, float %{{.*}}, i64 0
return _mm_nmacc_ss(a, b, c);
}
__m128d test_mm_nmacc_sd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_nmacc_sd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[A:%.+]] = extractelement <2 x double> [[NEG]], i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: call double @llvm.fma.f64(double [[A]], double %{{.*}}, double %{{.*}})
// CHECK: insertelement <2 x double> zeroinitializer, double %{{.*}}, i64 0
return _mm_nmacc_sd(a, b, c);
}
__m128 test_mm_nmsub_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_nmsub_ps
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[NEG2:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
return _mm_nmsub_ps(a, b, c);
}
__m128d test_mm_nmsub_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_nmsub_pd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[NEG2:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
return _mm_nmsub_pd(a, b, c);
}
__m128 test_mm_nmsub_ss(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_nmsub_ss
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[NEG2:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[A:%.+]] = extractelement <4 x float> [[NEG]], i64 0
// CHECK: extractelement <4 x float> %{{.*}}, i64 0
// CHECK: [[C:%.+]] = extractelement <4 x float> [[NEG2]], i64 0
// CHECK: call float @llvm.fma.f32(float [[A]], float %{{.*}}, float [[C]])
// CHECK: insertelement <4 x float> zeroinitializer, float %{{.*}}, i64 0
return _mm_nmsub_ss(a, b, c);
}
__m128d test_mm_nmsub_sd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_nmsub_sd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[NEG2:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[A:%.+]] = extractelement <2 x double> [[NEG]], i64 0
// CHECK: extractelement <2 x double> %{{.*}}, i64 0
// CHECK: [[C:%.+]] = extractelement <2 x double> [[NEG2]], i64 0
// CHECK: call double @llvm.fma.f64(double [[A]], double %{{.*}}, double [[C]])
// CHECK: insertelement <2 x double> zeroinitializer, double %{{.*}}, i64 0
return _mm_nmsub_sd(a, b, c);
}
__m128 test_mm_maddsub_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_maddsub_ps
// CHECK: [[ADD:%.+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[SUB:%.+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[NEG]]
// CHECK: shufflevector <4 x float> [[SUB]], <4 x float> [[ADD]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
return _mm_maddsub_ps(a, b, c);
}
__m128d test_mm_maddsub_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_maddsub_pd
// CHECK: [[ADD:%.+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[SUB:%.+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[NEG]]
// CHECK: shufflevector <2 x double> [[SUB]], <2 x double> [[ADD]], <2 x i32> <i32 0, i32 3>
return _mm_maddsub_pd(a, b, c);
}
__m128 test_mm_msubadd_ps(__m128 a, __m128 b, __m128 c) {
// CHECK-LABEL: test_mm_msubadd_ps
// CHECK: [[NEG:%.+]] = fneg <4 x float> %{{.+}}
// CHECK: [[SUB:%.+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> [[NEG]]
// CHECK: [[ADD:%.+]] = call <4 x float> @llvm.fma.v4f32(<4 x float> %{{.*}}, <4 x float> %{{.*}}, <4 x float> %{{.*}})
// CHECK: shufflevector <4 x float> [[ADD]], <4 x float> [[SUB]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
return _mm_msubadd_ps(a, b, c);
}
__m128d test_mm_msubadd_pd(__m128d a, __m128d b, __m128d c) {
// CHECK-LABEL: test_mm_msubadd_pd
// CHECK: [[NEG:%.+]] = fneg <2 x double> %{{.+}}
// CHECK: [[SUB:%.+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> [[NEG]]
// CHECK: [[ADD:%.+]] = call <2 x double> @llvm.fma.v2f64(<2 x double> %{{.*}}, <2 x double> %{{.*}}, <2 x double> %{{.*}})
// CHECK: shufflevector <2 x double> [[ADD]], <2 x double> [[SUB]], <2 x i32> <i32 0, i32 3>
return _mm_msubadd_pd(a, b, c);
}
__m256 test_mm256_macc_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_macc_ps
// CHECK: call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
return _mm256_macc_ps(a, b, c);
}
__m256d test_mm256_macc_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_macc_pd
// CHECK: call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
return _mm256_macc_pd(a, b, c);
}
__m256 test_mm256_msub_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_msub_ps
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
return _mm256_msub_ps(a, b, c);
}
__m256d test_mm256_msub_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_msub_pd
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
// CHECK: call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
return _mm256_msub_pd(a, b, c);
}
__m256 test_mm256_nmacc_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_nmacc_ps
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
return _mm256_nmacc_ps(a, b, c);
}
__m256d test_mm256_nmacc_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_nmacc_pd
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
// CHECK: call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
return _mm256_nmacc_pd(a, b, c);
}
__m256 test_mm256_nmsub_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_nmsub_ps
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: [[NEG2:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
return _mm256_nmsub_ps(a, b, c);
}
__m256d test_mm256_nmsub_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_nmsub_pd
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
// CHECK: [[NEG2:%.+]] = fneg <4 x double> %{{.+}}
// CHECK: call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
return _mm256_nmsub_pd(a, b, c);
}
__m256 test_mm256_maddsub_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_maddsub_ps
// CHECK: [[ADD:%.+]] = call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: [[SUB:%.+]] = call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> [[NEG]]
// CHECK: shufflevector <8 x float> [[SUB]], <8 x float> [[ADD]], <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
return _mm256_maddsub_ps(a, b, c);
}
__m256d test_mm256_maddsub_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_maddsub_pd
// CHECK: [[ADD:%.+]] = call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
// CHECK: [[NEG:%.+]] = fneg <4 x double> %{{.+}}
// CHECK: [[SUB:%.+]] = call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
// CHECK: shufflevector <4 x double> [[SUB]], <4 x double> [[ADD]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
return _mm256_maddsub_pd(a, b, c);
}
__m256 test_mm256_msubadd_ps(__m256 a, __m256 b, __m256 c) {
// CHECK-LABEL: test_mm256_msubadd_ps
// CHECK: [[NEG:%.+]] = fneg <8 x float> %{{.*}}
// CHECK: [[SUB:%.+]] = call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> [[NEG]]
// CHECK: [[ADD:%.+]] = call <8 x float> @llvm.fma.v8f32(<8 x float> %{{.*}}, <8 x float> %{{.*}}, <8 x float> %{{.*}})
// CHECK: shufflevector <8 x float> [[ADD]], <8 x float> [[SUB]], <8 x i32> <i32 0, i32 9, i32 2, i32 11, i32 4, i32 13, i32 6, i32 15>
return _mm256_msubadd_ps(a, b, c);
}
__m256d test_mm256_msubadd_pd(__m256d a, __m256d b, __m256d c) {
// CHECK-LABEL: test_mm256_msubadd_pd
// CHECK: [[NEG:%.+]] = fneg <4 x double> {{.+}}
// CHECK: [[SUB:%.+]] = call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> [[NEG]]
// CHECK: [[ADD:%.+]] = call <4 x double> @llvm.fma.v4f64(<4 x double> %{{.*}}, <4 x double> %{{.*}}, <4 x double> %{{.*}})
// CHECK: shufflevector <4 x double> [[ADD]], <4 x double> [[SUB]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
return _mm256_msubadd_pd(a, b, c);
}