legalize-add-v512.mir
13.2 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
277
278
279
280
281
282
283
284
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX1
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512F
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx512f,+avx512bw -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX512BW
--- |
define void @test_add_v64i8() {
%ret = add <64 x i8> undef, undef
ret void
}
define void @test_add_v32i16() {
%ret = add <32 x i16> undef, undef
ret void
}
define void @test_add_v16i32() {
%ret = add <16 x i32> undef, undef
ret void
}
define void @test_add_v8i64() {
%ret = add <8 x i64> undef, undef
ret void
}
define <64 x i8> @test_add_v64i8_2(<64 x i8> %arg1, <64 x i8> %arg2) #0 {
%ret = add <64 x i8> %arg1, %arg2
ret <64 x i8> %ret
}
...
---
name: test_add_v64i8
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $zmm0, $zmm1
; AVX1-LABEL: name: test_add_v64i8
; AVX1: [[DEF:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>), [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<64 x s8>)
; AVX1: [[UV4:%[0-9]+]]:_(<16 x s8>), [[UV5:%[0-9]+]]:_(<16 x s8>), [[UV6:%[0-9]+]]:_(<16 x s8>), [[UV7:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<64 x s8>)
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV4]]
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV5]]
; AVX1: [[ADD2:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV2]], [[UV6]]
; AVX1: [[ADD3:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV3]], [[UV7]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<64 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>), [[ADD2]](<16 x s8>), [[ADD3]](<16 x s8>)
; AVX1: $zmm0 = COPY [[CONCAT_VECTORS]](<64 x s8>)
; AVX1: RET 0
; AVX512F-LABEL: name: test_add_v64i8
; AVX512F: [[DEF:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX512F: [[DEF1:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX512F: [[UV:%[0-9]+]]:_(<32 x s8>), [[UV1:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[DEF]](<64 x s8>)
; AVX512F: [[UV2:%[0-9]+]]:_(<32 x s8>), [[UV3:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[DEF1]](<64 x s8>)
; AVX512F: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[UV]], [[UV2]]
; AVX512F: [[ADD1:%[0-9]+]]:_(<32 x s8>) = G_ADD [[UV1]], [[UV3]]
; AVX512F: [[CONCAT_VECTORS:%[0-9]+]]:_(<64 x s8>) = G_CONCAT_VECTORS [[ADD]](<32 x s8>), [[ADD1]](<32 x s8>)
; AVX512F: $zmm0 = COPY [[CONCAT_VECTORS]](<64 x s8>)
; AVX512F: RET 0
; AVX512BW-LABEL: name: test_add_v64i8
; AVX512BW: [[DEF:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX512BW: [[DEF1:%[0-9]+]]:_(<64 x s8>) = IMPLICIT_DEF
; AVX512BW: [[ADD:%[0-9]+]]:_(<64 x s8>) = G_ADD [[DEF]], [[DEF1]]
; AVX512BW: $zmm0 = COPY [[ADD]](<64 x s8>)
; AVX512BW: RET 0
%0(<64 x s8>) = IMPLICIT_DEF
%1(<64 x s8>) = IMPLICIT_DEF
%2(<64 x s8>) = G_ADD %0, %1
$zmm0 = COPY %2
RET 0
...
---
name: test_add_v32i16
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $zmm0, $zmm1
; AVX1-LABEL: name: test_add_v32i16
; AVX1: [[DEF:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>), [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<32 x s16>)
; AVX1: [[UV4:%[0-9]+]]:_(<8 x s16>), [[UV5:%[0-9]+]]:_(<8 x s16>), [[UV6:%[0-9]+]]:_(<8 x s16>), [[UV7:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<32 x s16>)
; AVX1: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV4]]
; AVX1: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV5]]
; AVX1: [[ADD2:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV2]], [[UV6]]
; AVX1: [[ADD3:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV3]], [[UV7]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s16>) = G_CONCAT_VECTORS [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>), [[ADD2]](<8 x s16>), [[ADD3]](<8 x s16>)
; AVX1: $zmm0 = COPY [[CONCAT_VECTORS]](<32 x s16>)
; AVX1: RET 0
; AVX512F-LABEL: name: test_add_v32i16
; AVX512F: [[DEF:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX512F: [[DEF1:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX512F: [[UV:%[0-9]+]]:_(<16 x s16>), [[UV1:%[0-9]+]]:_(<16 x s16>) = G_UNMERGE_VALUES [[DEF]](<32 x s16>)
; AVX512F: [[UV2:%[0-9]+]]:_(<16 x s16>), [[UV3:%[0-9]+]]:_(<16 x s16>) = G_UNMERGE_VALUES [[DEF1]](<32 x s16>)
; AVX512F: [[ADD:%[0-9]+]]:_(<16 x s16>) = G_ADD [[UV]], [[UV2]]
; AVX512F: [[ADD1:%[0-9]+]]:_(<16 x s16>) = G_ADD [[UV1]], [[UV3]]
; AVX512F: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s16>) = G_CONCAT_VECTORS [[ADD]](<16 x s16>), [[ADD1]](<16 x s16>)
; AVX512F: $zmm0 = COPY [[CONCAT_VECTORS]](<32 x s16>)
; AVX512F: RET 0
; AVX512BW-LABEL: name: test_add_v32i16
; AVX512BW: [[DEF:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX512BW: [[DEF1:%[0-9]+]]:_(<32 x s16>) = IMPLICIT_DEF
; AVX512BW: [[ADD:%[0-9]+]]:_(<32 x s16>) = G_ADD [[DEF]], [[DEF1]]
; AVX512BW: $zmm0 = COPY [[ADD]](<32 x s16>)
; AVX512BW: RET 0
%0(<32 x s16>) = IMPLICIT_DEF
%1(<32 x s16>) = IMPLICIT_DEF
%2(<32 x s16>) = G_ADD %0, %1
$zmm0 = COPY %2
RET 0
...
---
name: test_add_v16i32
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $zmm0, $zmm1
; AVX1-LABEL: name: test_add_v16i32
; AVX1: [[DEF:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>), [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<16 x s32>)
; AVX1: [[UV4:%[0-9]+]]:_(<4 x s32>), [[UV5:%[0-9]+]]:_(<4 x s32>), [[UV6:%[0-9]+]]:_(<4 x s32>), [[UV7:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<16 x s32>)
; AVX1: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV4]]
; AVX1: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV5]]
; AVX1: [[ADD2:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV2]], [[UV6]]
; AVX1: [[ADD3:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV3]], [[UV7]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s32>) = G_CONCAT_VECTORS [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>), [[ADD2]](<4 x s32>), [[ADD3]](<4 x s32>)
; AVX1: $zmm0 = COPY [[CONCAT_VECTORS]](<16 x s32>)
; AVX1: RET 0
; AVX512F-LABEL: name: test_add_v16i32
; AVX512F: [[DEF:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX512F: [[DEF1:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX512F: [[ADD:%[0-9]+]]:_(<16 x s32>) = G_ADD [[DEF]], [[DEF1]]
; AVX512F: $zmm0 = COPY [[ADD]](<16 x s32>)
; AVX512F: RET 0
; AVX512BW-LABEL: name: test_add_v16i32
; AVX512BW: [[DEF:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX512BW: [[DEF1:%[0-9]+]]:_(<16 x s32>) = IMPLICIT_DEF
; AVX512BW: [[ADD:%[0-9]+]]:_(<16 x s32>) = G_ADD [[DEF]], [[DEF1]]
; AVX512BW: $zmm0 = COPY [[ADD]](<16 x s32>)
; AVX512BW: RET 0
%0(<16 x s32>) = IMPLICIT_DEF
%1(<16 x s32>) = IMPLICIT_DEF
%2(<16 x s32>) = G_ADD %0, %1
$zmm0 = COPY %2
RET 0
...
---
name: test_add_v8i64
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $zmm0, $zmm1
; AVX1-LABEL: name: test_add_v8i64
; AVX1: [[DEF:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>), [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<8 x s64>)
; AVX1: [[UV4:%[0-9]+]]:_(<2 x s64>), [[UV5:%[0-9]+]]:_(<2 x s64>), [[UV6:%[0-9]+]]:_(<2 x s64>), [[UV7:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<8 x s64>)
; AVX1: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV4]]
; AVX1: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV5]]
; AVX1: [[ADD2:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV2]], [[UV6]]
; AVX1: [[ADD3:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV3]], [[UV7]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s64>) = G_CONCAT_VECTORS [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>), [[ADD2]](<2 x s64>), [[ADD3]](<2 x s64>)
; AVX1: $zmm0 = COPY [[CONCAT_VECTORS]](<8 x s64>)
; AVX1: RET 0
; AVX512F-LABEL: name: test_add_v8i64
; AVX512F: [[DEF:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX512F: [[DEF1:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX512F: [[ADD:%[0-9]+]]:_(<8 x s64>) = G_ADD [[DEF]], [[DEF1]]
; AVX512F: $zmm0 = COPY [[ADD]](<8 x s64>)
; AVX512F: RET 0
; AVX512BW-LABEL: name: test_add_v8i64
; AVX512BW: [[DEF:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX512BW: [[DEF1:%[0-9]+]]:_(<8 x s64>) = IMPLICIT_DEF
; AVX512BW: [[ADD:%[0-9]+]]:_(<8 x s64>) = G_ADD [[DEF]], [[DEF1]]
; AVX512BW: $zmm0 = COPY [[ADD]](<8 x s64>)
; AVX512BW: RET 0
%0(<8 x s64>) = IMPLICIT_DEF
%1(<8 x s64>) = IMPLICIT_DEF
%2(<8 x s64>) = G_ADD %0, %1
$zmm0 = COPY %2
RET 0
...
---
name: test_add_v64i8_2
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
- { id: 3, class: _ }
- { id: 4, class: _ }
- { id: 5, class: _ }
- { id: 6, class: _ }
- { id: 7, class: _ }
- { id: 8, class: _ }
#
#
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1, $ymm2, $ymm3
; AVX1-LABEL: name: test_add_v64i8_2
; AVX1: [[COPY:%[0-9]+]]:_(<32 x s8>) = COPY $ymm0
; AVX1: [[COPY1:%[0-9]+]]:_(<32 x s8>) = COPY $ymm1
; AVX1: [[COPY2:%[0-9]+]]:_(<32 x s8>) = COPY $ymm2
; AVX1: [[COPY3:%[0-9]+]]:_(<32 x s8>) = COPY $ymm3
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY]](<32 x s8>)
; AVX1: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY1]](<32 x s8>)
; AVX1: [[UV4:%[0-9]+]]:_(<16 x s8>), [[UV5:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY2]](<32 x s8>)
; AVX1: [[UV6:%[0-9]+]]:_(<16 x s8>), [[UV7:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[COPY3]](<32 x s8>)
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV4]]
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV5]]
; AVX1: [[ADD2:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV2]], [[UV6]]
; AVX1: [[ADD3:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV3]], [[UV7]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
; AVX1: [[CONCAT_VECTORS1:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD2]](<16 x s8>), [[ADD3]](<16 x s8>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<32 x s8>)
; AVX1: $ymm1 = COPY [[CONCAT_VECTORS1]](<32 x s8>)
; AVX1: RET 0, implicit $ymm0, implicit $ymm1
; AVX512F-LABEL: name: test_add_v64i8_2
; AVX512F: [[COPY:%[0-9]+]]:_(<32 x s8>) = COPY $ymm0
; AVX512F: [[COPY1:%[0-9]+]]:_(<32 x s8>) = COPY $ymm1
; AVX512F: [[COPY2:%[0-9]+]]:_(<32 x s8>) = COPY $ymm2
; AVX512F: [[COPY3:%[0-9]+]]:_(<32 x s8>) = COPY $ymm3
; AVX512F: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[COPY]], [[COPY2]]
; AVX512F: [[ADD1:%[0-9]+]]:_(<32 x s8>) = G_ADD [[COPY1]], [[COPY3]]
; AVX512F: $ymm0 = COPY [[ADD]](<32 x s8>)
; AVX512F: $ymm1 = COPY [[ADD1]](<32 x s8>)
; AVX512F: RET 0, implicit $ymm0, implicit $ymm1
; AVX512BW-LABEL: name: test_add_v64i8_2
; AVX512BW: [[COPY:%[0-9]+]]:_(<32 x s8>) = COPY $ymm0
; AVX512BW: [[COPY1:%[0-9]+]]:_(<32 x s8>) = COPY $ymm1
; AVX512BW: [[COPY2:%[0-9]+]]:_(<32 x s8>) = COPY $ymm2
; AVX512BW: [[COPY3:%[0-9]+]]:_(<32 x s8>) = COPY $ymm3
; AVX512BW: [[CONCAT_VECTORS:%[0-9]+]]:_(<64 x s8>) = G_CONCAT_VECTORS [[COPY]](<32 x s8>), [[COPY1]](<32 x s8>)
; AVX512BW: [[CONCAT_VECTORS1:%[0-9]+]]:_(<64 x s8>) = G_CONCAT_VECTORS [[COPY2]](<32 x s8>), [[COPY3]](<32 x s8>)
; AVX512BW: [[ADD:%[0-9]+]]:_(<64 x s8>) = G_ADD [[CONCAT_VECTORS]], [[CONCAT_VECTORS1]]
; AVX512BW: [[UV:%[0-9]+]]:_(<32 x s8>), [[UV1:%[0-9]+]]:_(<32 x s8>) = G_UNMERGE_VALUES [[ADD]](<64 x s8>)
; AVX512BW: $ymm0 = COPY [[UV]](<32 x s8>)
; AVX512BW: $ymm1 = COPY [[UV1]](<32 x s8>)
; AVX512BW: RET 0, implicit $ymm0, implicit $ymm1
%2(<32 x s8>) = COPY $ymm0
%3(<32 x s8>) = COPY $ymm1
%4(<32 x s8>) = COPY $ymm2
%5(<32 x s8>) = COPY $ymm3
%0(<64 x s8>) = G_CONCAT_VECTORS %2(<32 x s8>), %3(<32 x s8>)
%1(<64 x s8>) = G_CONCAT_VECTORS %4(<32 x s8>), %5(<32 x s8>)
%6(<64 x s8>) = G_ADD %0, %1
%7(<32 x s8>), %8(<32 x s8>) = G_UNMERGE_VALUES %6(<64 x s8>)
$ymm0 = COPY %7(<32 x s8>)
$ymm1 = COPY %8(<32 x s8>)
RET 0, implicit $ymm0, implicit $ymm1
...