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
| // RUN: %clang_cc1 -ffreestanding %s -O3 -triple=x86_64-apple-darwin -target-feature +avx -emit-llvm -o - | FileCheck %s
// FIXME: This is testing optimized generation of shuffle instructions and should be fixed.
#include <immintrin.h>
//
// Test LLVM IR codegen of shuffle instructions
//
__m256 x(__m256 a, __m256 b) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 3, i32 2, i32 8, i32 11, i32 7, i32 6, i32 12, i32 15>
return _mm256_shuffle_ps(a, b, 203);
}
__m128d test_mm_permute_pd(__m128d a) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 1, i32 0>
return _mm_permute_pd(a, 1);
}
__m256d test_mm256_permute_pd(__m256d a) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 1, i32 0, i32 3, i32 2>
return _mm256_permute_pd(a, 5);
}
__m128 test_mm_permute_ps(__m128 a) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 3, i32 2, i32 1, i32 0>
return _mm_permute_ps(a, 0x1b);
}
// Test case for PR12401
__m128 test_mm_permute_ps2(__m128 a) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 2, i32 1, i32 2, i32 3>
return _mm_permute_ps(a, 0xe6);
}
__m256 test_mm256_permute_ps(__m256 a) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
return _mm256_permute_ps(a, 0x1b);
}
__m256d test_mm256_permute2f128_pd(__m256d a, __m256d b) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 2, i32 3, i32 6, i32 7>
return _mm256_permute2f128_pd(a, b, 0x31);
}
__m256 test_mm256_permute2f128_ps(__m256 a, __m256 b) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}}<i32 4, i32 5, i32 6, i32 7, i32 12, i32 13, i32 14, i32 15>
return _mm256_permute2f128_ps(a, b, 0x13);
}
__m256i test_mm256_permute2f128_si256(__m256i a, __m256i b) {
// Check if the mask is correct
// CHECK: shufflevector{{.*}} <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
return _mm256_permute2f128_si256(a, b, 0x20);
}
__m128
test_mm_broadcast_ss(float const *__a) {
// CHECK-LABEL: @test_mm_broadcast_ss
// CHECK: insertelement <4 x float> {{.*}}, i32 0
// CHECK: shufflevector <4 x float> {{.*}}, <4 x float> undef, <4 x i32> zeroinitializer
return _mm_broadcast_ss(__a);
}
__m256d
test_mm256_broadcast_sd(double const *__a) {
// CHECK-LABEL: @test_mm256_broadcast_sd
// CHECK: insertelement <4 x double> {{.*}}, i32 0
// CHECK: shufflevector <4 x double> {{.*}}, <4 x double> undef, <4 x i32> zeroinitializer
return _mm256_broadcast_sd(__a);
}
__m256
test_mm256_broadcast_ss(float const *__a) {
// CHECK-LABEL: @test_mm256_broadcast_ss
// CHECK: insertelement <8 x float> {{.*}}, i32 0
// CHECK: shufflevector <8 x float> {{.*}}, <8 x float> undef, <8 x i32> zeroinitializer
return _mm256_broadcast_ss(__a);
}
// Make sure we have the correct mask for each insertf128 case.
__m256 test_mm256_insertf128_ps_0(__m256 a, __m128 b) {
// CHECK-LABEL: @test_mm256_insertf128_ps_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
return _mm256_insertf128_ps(a, b, 0);
}
__m256d test_mm256_insertf128_pd_0(__m256d a, __m128d b) {
// CHECK-LABEL: @test_mm256_insertf128_pd_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 6, i32 7>
return _mm256_insertf128_pd(a, b, 0);
}
__m256i test_mm256_insertf128_si256_0(__m256i a, __m128i b) {
// CHECK-LABEL: @test_mm256_insertf128_si256_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 12, i32 13, i32 14, i32 15>
return _mm256_insertf128_si256(a, b, 0);
}
__m256 test_mm256_insertf128_ps_1(__m256 a, __m128 b) {
// CHECK-LABEL: @test_mm256_insertf128_ps_1
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
return _mm256_insertf128_ps(a, b, 1);
}
__m256d test_mm256_insertf128_pd_1(__m256d a, __m128d b) {
// CHECK-LABEL: @test_mm256_insertf128_pd_1
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 4, i32 5>
return _mm256_insertf128_pd(a, b, 1);
}
__m256i test_mm256_insertf128_si256_1(__m256i a, __m128i b) {
// CHECK-LABEL: @test_mm256_insertf128_si256_1
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 8, i32 9, i32 10, i32 11>
return _mm256_insertf128_si256(a, b, 1);
}
// Make sure we have the correct mask for each extractf128 case.
__m128 test_mm256_extractf128_ps_0(__m256 a) {
// CHECK-LABEL: @test_mm256_extractf128_ps_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_extractf128_ps(a, 0);
}
__m128d test_mm256_extractf128_pd_0(__m256d a) {
// CHECK-LABEL: @test_mm256_extractf128_pd_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1>
return _mm256_extractf128_pd(a, 0);
}
__m128i test_mm256_extractf128_si256_0(__m256i a) {
// CHECK-LABEL: @test_mm256_extractf128_si256_0
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_extractf128_si256(a, 0);
}
__m128 test_mm256_extractf128_ps_1(__m256 a) {
// CHECK-LABEL: @test_mm256_extractf128_ps_1
// CHECK: shufflevector{{.*}}<i32 4, i32 5, i32 6, i32 7>
return _mm256_extractf128_ps(a, 1);
}
__m128d test_mm256_extractf128_pd_1(__m256d a) {
// CHECK-LABEL: @test_mm256_extractf128_pd_1
// CHECK: shufflevector{{.*}}<i32 2, i32 3>
return _mm256_extractf128_pd(a, 1);
}
__m128i test_mm256_extractf128_si256_1(__m256i a) {
// CHECK-LABEL: @test_mm256_extractf128_si256_1
// CHECK: shufflevector{{.*}}<i32 4, i32 5, i32 6, i32 7>
return _mm256_extractf128_si256(a, 1);
}
__m256 test_mm256_set_m128(__m128 hi, __m128 lo) {
// CHECK-LABEL: @test_mm256_set_m128
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return _mm256_set_m128(hi, lo);
}
__m256d test_mm256_set_m128d(__m128d hi, __m128d lo) {
// CHECK-LABEL: @test_mm256_set_m128d
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_set_m128d(hi, lo);
}
__m256i test_mm256_set_m128i(__m128i hi, __m128i lo) {
// CHECK-LABEL: @test_mm256_set_m128i
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_set_m128i(hi, lo);
}
__m256 test_mm256_setr_m128(__m128 hi, __m128 lo) {
// CHECK-LABEL: @test_mm256_setr_m128
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
return _mm256_setr_m128(lo, hi);
}
__m256d test_mm256_setr_m128d(__m128d hi, __m128d lo) {
// CHECK-LABEL: @test_mm256_setr_m128d
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_setr_m128d(lo, hi);
}
__m256i test_mm256_setr_m128i(__m128i hi, __m128i lo) {
// CHECK-LABEL: @test_mm256_setr_m128i
// CHECK: shufflevector{{.*}}<i32 0, i32 1, i32 2, i32 3>
return _mm256_setr_m128i(lo, hi);
}
|