legalize-add-v256.mir
8.87 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
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+sse2 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NOT_AVX2 --check-prefix=SSE2
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=NOT_AVX2 --check-prefix=AVX1
# RUN: llc -mtriple=x86_64-linux-gnu -mattr=+avx2 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=ALL --check-prefix=AVX2
--- |
define void @test_add_v32i8() {
%ret = add <32 x i8> undef, undef
ret void
}
define void @test_add_v16i16() {
%ret = add <16 x i16> undef, undef
ret void
}
define void @test_add_v8i32() {
%ret = add <8 x i32> undef, undef
ret void
}
define void @test_add_v4i64() {
%ret = add <4 x i64> undef, undef
ret void
}
...
---
name: test_add_v32i8
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v32i8
; SSE2: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<32 x s8>)
; SSE2: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<32 x s8>)
; SSE2: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<32 x s8>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v32i8
; AVX1: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<16 x s8>), [[UV1:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF]](<32 x s8>)
; AVX1: [[UV2:%[0-9]+]]:_(<16 x s8>), [[UV3:%[0-9]+]]:_(<16 x s8>) = G_UNMERGE_VALUES [[DEF1]](<32 x s8>)
; AVX1: [[ADD:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<16 x s8>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<32 x s8>) = G_CONCAT_VECTORS [[ADD]](<16 x s8>), [[ADD1]](<16 x s8>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<32 x s8>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v32i8
; AVX2: [[DEF:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<32 x s8>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<32 x s8>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<32 x s8>)
; AVX2: RET 0
%0(<32 x s8>) = IMPLICIT_DEF
%1(<32 x s8>) = IMPLICIT_DEF
%2(<32 x s8>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v16i16
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v16i16
; SSE2: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<16 x s16>)
; SSE2: [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<16 x s16>)
; SSE2: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s16>) = G_CONCAT_VECTORS [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<16 x s16>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v16i16
; AVX1: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<8 x s16>), [[UV1:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF]](<16 x s16>)
; AVX1: [[UV2:%[0-9]+]]:_(<8 x s16>), [[UV3:%[0-9]+]]:_(<8 x s16>) = G_UNMERGE_VALUES [[DEF1]](<16 x s16>)
; AVX1: [[ADD:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<8 x s16>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<16 x s16>) = G_CONCAT_VECTORS [[ADD]](<8 x s16>), [[ADD1]](<8 x s16>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<16 x s16>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v16i16
; AVX2: [[DEF:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<16 x s16>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<16 x s16>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<16 x s16>)
; AVX2: RET 0
%0(<16 x s16>) = IMPLICIT_DEF
%1(<16 x s16>) = IMPLICIT_DEF
%2(<16 x s16>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v8i32
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v8i32
; SSE2: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<8 x s32>)
; SSE2: [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<8 x s32>)
; SSE2: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<8 x s32>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v8i32
; AVX1: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<4 x s32>), [[UV1:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF]](<8 x s32>)
; AVX1: [[UV2:%[0-9]+]]:_(<4 x s32>), [[UV3:%[0-9]+]]:_(<4 x s32>) = G_UNMERGE_VALUES [[DEF1]](<8 x s32>)
; AVX1: [[ADD:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<4 x s32>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<8 x s32>) = G_CONCAT_VECTORS [[ADD]](<4 x s32>), [[ADD1]](<4 x s32>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<8 x s32>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v8i32
; AVX2: [[DEF:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<8 x s32>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<8 x s32>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<8 x s32>)
; AVX2: RET 0
%0(<8 x s32>) = IMPLICIT_DEF
%1(<8 x s32>) = IMPLICIT_DEF
%2(<8 x s32>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...
---
name: test_add_v4i64
alignment: 16
legalized: false
regBankSelected: false
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
body: |
bb.1 (%ir-block.0):
liveins: $ymm0, $ymm1
; SSE2-LABEL: name: test_add_v4i64
; SSE2: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; SSE2: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; SSE2: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<4 x s64>)
; SSE2: [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<4 x s64>)
; SSE2: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV2]]
; SSE2: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV3]]
; SSE2: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>)
; SSE2: $ymm0 = COPY [[CONCAT_VECTORS]](<4 x s64>)
; SSE2: RET 0
; AVX1-LABEL: name: test_add_v4i64
; AVX1: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX1: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX1: [[UV:%[0-9]+]]:_(<2 x s64>), [[UV1:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF]](<4 x s64>)
; AVX1: [[UV2:%[0-9]+]]:_(<2 x s64>), [[UV3:%[0-9]+]]:_(<2 x s64>) = G_UNMERGE_VALUES [[DEF1]](<4 x s64>)
; AVX1: [[ADD:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV]], [[UV2]]
; AVX1: [[ADD1:%[0-9]+]]:_(<2 x s64>) = G_ADD [[UV1]], [[UV3]]
; AVX1: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s64>) = G_CONCAT_VECTORS [[ADD]](<2 x s64>), [[ADD1]](<2 x s64>)
; AVX1: $ymm0 = COPY [[CONCAT_VECTORS]](<4 x s64>)
; AVX1: RET 0
; AVX2-LABEL: name: test_add_v4i64
; AVX2: [[DEF:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX2: [[DEF1:%[0-9]+]]:_(<4 x s64>) = IMPLICIT_DEF
; AVX2: [[ADD:%[0-9]+]]:_(<4 x s64>) = G_ADD [[DEF]], [[DEF1]]
; AVX2: $ymm0 = COPY [[ADD]](<4 x s64>)
; AVX2: RET 0
%0(<4 x s64>) = IMPLICIT_DEF
%1(<4 x s64>) = IMPLICIT_DEF
%2(<4 x s64>) = G_ADD %0, %1
$ymm0 = COPY %2
RET 0
...