prefer-avx256-mask-extend.ll
10.9 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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,+prefer-256-bit | FileCheck %s --check-prefix=CHECK --check-prefix=AVX256
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vl,-prefer-256-bit | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512VL
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,+prefer-256-bit | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f,-prefer-256-bit | FileCheck %s --check-prefix=CHECK --check-prefix=AVX512 --check-prefix=AVX512F
define <8 x i16> @testv8i1_sext_v8i16(<8 x i32>* %p) {
; AVX256-LABEL: testv8i1_sext_v8i16:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vzeroupper
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv8i1_sext_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv8i1_sext_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT: vpcmpeqd (%rdi), %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%ext = sext <8 x i1> %cmp to <8 x i16>
ret <8 x i16> %ext
}
define <16 x i8> @testv16i1_sext_v16i8(<8 x i32>* %p, <8 x i32>* %q) {
; AVX256-LABEL: testv16i1_sext_v16i8:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vmovdqa (%rsi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k2
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm1 {%k2} {z}
; AVX256-NEXT: vpmovdw %ymm1, %xmm1
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vpacksswb %xmm1, %xmm0, %xmm0
; AVX256-NEXT: vzeroupper
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv16i1_sext_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: vmovdqa (%rsi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: kunpckbw %k0, %k1, %k1
; AVX512VL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv16i1_sext_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: vmovdqa (%rsi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: kunpckbw %k0, %k1, %k1
; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%in2 = load <8 x i32>, <8 x i32>* %q
%cmp2 = icmp eq <8 x i32> %in2, zeroinitializer
%concat = shufflevector <8 x i1> %cmp, <8 x i1> %cmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%ext = sext <16 x i1> %concat to <16 x i8>
ret <16 x i8> %ext
}
define <16 x i16> @testv16i1_sext_v16i16(<8 x i32>* %p, <8 x i32>* %q) {
; AVX256-LABEL: testv16i1_sext_v16i16:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vmovdqa (%rsi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k2
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm1 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm1, %xmm1
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k2} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv16i1_sext_v16i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: vmovdqa (%rsi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: kunpckbw %k0, %k1, %k1
; AVX512VL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdw %zmm0, %ymm0
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv16i1_sext_v16i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: vmovdqa (%rsi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: kunpckbw %k0, %k1, %k1
; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%in2 = load <8 x i32>, <8 x i32>* %q
%cmp2 = icmp eq <8 x i32> %in2, zeroinitializer
%concat = shufflevector <8 x i1> %cmp, <8 x i1> %cmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%ext = sext <16 x i1> %concat to <16 x i16>
ret <16 x i16> %ext
}
define <8 x i16> @testv8i1_zext_v8i16(<8 x i32>* %p) {
; AVX256-LABEL: testv8i1_zext_v8i16:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vpsrlw $15, %xmm0, %xmm0
; AVX256-NEXT: vzeroupper
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv8i1_zext_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX512VL-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdw %ymm0, %xmm0
; AVX512VL-NEXT: vpsrlw $15, %xmm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv8i1_zext_v8i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vpxor %xmm0, %xmm0, %xmm0
; AVX512F-NEXT: vpcmpeqd (%rdi), %ymm0, %ymm0
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpsrlw $15, %xmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%ext = zext <8 x i1> %cmp to <8 x i16>
ret <8 x i16> %ext
}
define <16 x i8> @testv16i1_zext_v16i8(<8 x i32>* %p, <8 x i32>* %q) {
; AVX256-LABEL: testv16i1_zext_v16i8:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vmovdqa (%rsi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k2
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm1 {%k2} {z}
; AVX256-NEXT: vpmovdw %ymm1, %xmm1
; AVX256-NEXT: vpsrlw $15, %xmm1, %xmm1
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vpsrlw $15, %xmm0, %xmm0
; AVX256-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
; AVX256-NEXT: vzeroupper
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv16i1_zext_v16i8:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: vmovdqa (%rsi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: kunpckbw %k0, %k1, %k1
; AVX512VL-NEXT: vpbroadcastd {{.*}}(%rip), %zmm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdb %zmm0, %xmm0
; AVX512VL-NEXT: vzeroupper
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv16i1_zext_v16i8:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: vmovdqa (%rsi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: kunpckbw %k0, %k1, %k1
; AVX512F-NEXT: vpbroadcastd {{.*}}(%rip), %zmm0 {%k1} {z}
; AVX512F-NEXT: vpmovdb %zmm0, %xmm0
; AVX512F-NEXT: vzeroupper
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%in2 = load <8 x i32>, <8 x i32>* %q
%cmp2 = icmp eq <8 x i32> %in2, zeroinitializer
%concat = shufflevector <8 x i1> %cmp, <8 x i1> %cmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%ext = zext <16 x i1> %concat to <16 x i8>
ret <16 x i8> %ext
}
define <16 x i16> @testv16i1_zext_v16i16(<8 x i32>* %p, <8 x i32>* %q) {
; AVX256-LABEL: testv16i1_zext_v16i16:
; AVX256: # %bb.0:
; AVX256-NEXT: vmovdqa (%rdi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX256-NEXT: vmovdqa (%rsi), %ymm0
; AVX256-NEXT: vptestnmd %ymm0, %ymm0, %k2
; AVX256-NEXT: vpcmpeqd %ymm0, %ymm0, %ymm0
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm1 {%k1} {z}
; AVX256-NEXT: vpmovdw %ymm1, %xmm1
; AVX256-NEXT: vmovdqa32 %ymm0, %ymm0 {%k2} {z}
; AVX256-NEXT: vpmovdw %ymm0, %xmm0
; AVX256-NEXT: vinserti128 $1, %xmm0, %ymm1, %ymm0
; AVX256-NEXT: vpsrlw $15, %ymm0, %ymm0
; AVX256-NEXT: retq
;
; AVX512VL-LABEL: testv16i1_zext_v16i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vmovdqa (%rdi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k0
; AVX512VL-NEXT: vmovdqa (%rsi), %ymm0
; AVX512VL-NEXT: vptestnmd %ymm0, %ymm0, %k1
; AVX512VL-NEXT: kunpckbw %k0, %k1, %k1
; AVX512VL-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512VL-NEXT: vpmovdw %zmm0, %ymm0
; AVX512VL-NEXT: vpsrlw $15, %ymm0, %ymm0
; AVX512VL-NEXT: retq
;
; AVX512F-LABEL: testv16i1_zext_v16i16:
; AVX512F: # %bb.0:
; AVX512F-NEXT: vmovdqa (%rdi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k0
; AVX512F-NEXT: vmovdqa (%rsi), %ymm0
; AVX512F-NEXT: vptestnmd %zmm0, %zmm0, %k1
; AVX512F-NEXT: kunpckbw %k0, %k1, %k1
; AVX512F-NEXT: vpternlogd $255, %zmm0, %zmm0, %zmm0 {%k1} {z}
; AVX512F-NEXT: vpmovdw %zmm0, %ymm0
; AVX512F-NEXT: vpsrlw $15, %ymm0, %ymm0
; AVX512F-NEXT: retq
%in = load <8 x i32>, <8 x i32>* %p
%cmp = icmp eq <8 x i32> %in, zeroinitializer
%in2 = load <8 x i32>, <8 x i32>* %q
%cmp2 = icmp eq <8 x i32> %in2, zeroinitializer
%concat = shufflevector <8 x i1> %cmp, <8 x i1> %cmp2, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
%ext = zext <16 x i1> %concat to <16 x i16>
ret <16 x i16> %ext
}