inline-memcpy.mir
12.9 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
269
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=aarch64 -run-pass=aarch64-prelegalizer-combiner -verify-machineinstrs %s -o - | FileCheck %s
--- |
target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-darwin"
define void @test_memcpy1(i32* nocapture %dst, i32* nocapture readonly %src, i64 %len) local_unnamed_addr #0 {
entry:
%0 = bitcast i32* %dst to i8*
%1 = bitcast i32* %src to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 %len, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i1 immarg) #1
define void @test_memcpy2_const(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #0 {
entry:
%0 = bitcast i32* %dst to i8*
%1 = bitcast i32* %src to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
ret void
}
define void @test_memcpy2_const_optsize(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #2 {
entry:
%0 = bitcast i32* %dst to i8*
%1 = bitcast i32* %src to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
ret void
}
define void @test_memcpy2_const_minsize(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #3 {
entry:
%0 = bitcast i32* %dst to i8*
%1 = bitcast i32* %src to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 72, i1 false)
ret void
}
define void @test_memcpy3_const_arrays_unaligned(i32* nocapture %dst, i32* nocapture readonly %src) local_unnamed_addr #0 {
entry:
%0 = bitcast i32* %dst to i8*
%1 = bitcast i32* %src to i8*
tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 %0, i8* align 4 %1, i64 143, i1 false)
ret void
}
attributes #0 = { nounwind ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "min-legal-vector-width"="0" "frame-pointer"="all" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="cyclone" "target-features"="+aes,+crypto,+fp-armv8,+neon,+sha2,+zcm,+zcz" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { argmemonly nounwind }
attributes #2 = { optsize }
attributes #3 = { minsize }
...
---
name: test_memcpy1
alignment: 4
tracksRegLiveness: true
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
machineFunctionInfo: {}
body: |
bb.1.entry:
liveins: $x0, $x1, $x2
; CHECK-LABEL: name: test_memcpy1
; CHECK: liveins: $x0, $x1, $x2
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $x2
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), [[COPY]](p0), [[COPY1]](p0), [[COPY2]](s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
; CHECK: RET_ReallyLR
%0:_(p0) = COPY $x0
%1:_(p0) = COPY $x1
%2:_(s64) = COPY $x2
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
RET_ReallyLR
...
---
name: test_memcpy2_const
alignment: 4
tracksRegLiveness: true
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
machineFunctionInfo: {}
body: |
bb.1.entry:
liveins: $x0, $x1
; CHECK-LABEL: name: test_memcpy2_const
; CHECK: liveins: $x0, $x1
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
; CHECK: [[LOAD4:%[0-9]+]]:_(s64) = G_LOAD [[GEP6]](p0) :: (load 8 from %ir.1 + 64, align 4)
; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
; CHECK: G_STORE [[LOAD4]](s64), [[GEP7]](p0) :: (store 8 into %ir.0 + 64, align 4)
; CHECK: RET_ReallyLR
%0:_(p0) = COPY $x0
%1:_(p0) = COPY $x1
%2:_(s64) = G_CONSTANT i64 72
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
RET_ReallyLR
...
---
name: test_memcpy2_const_optsize
alignment: 4
tracksRegLiveness: true
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
machineFunctionInfo: {}
body: |
bb.1.entry:
liveins: $x0, $x1
; CHECK-LABEL: name: test_memcpy2_const_optsize
; CHECK: liveins: $x0, $x1
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
; CHECK: [[LOAD4:%[0-9]+]]:_(s64) = G_LOAD [[GEP6]](p0) :: (load 8 from %ir.1 + 64, align 4)
; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
; CHECK: G_STORE [[LOAD4]](s64), [[GEP7]](p0) :: (store 8 into %ir.0 + 64, align 4)
; CHECK: RET_ReallyLR
%0:_(p0) = COPY $x0
%1:_(p0) = COPY $x1
%2:_(s64) = G_CONSTANT i64 72
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
RET_ReallyLR
...
---
name: test_memcpy2_const_minsize
alignment: 4
tracksRegLiveness: true
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
machineFunctionInfo: {}
body: |
bb.1.entry:
liveins: $x0, $x1
; CHECK-LABEL: name: test_memcpy2_const_minsize
; CHECK: liveins: $x0, $x1
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 72
; CHECK: G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), [[COPY]](p0), [[COPY1]](p0), [[C]](s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
; CHECK: RET_ReallyLR
%0:_(p0) = COPY $x0
%1:_(p0) = COPY $x1
%2:_(s64) = G_CONSTANT i64 72
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
RET_ReallyLR
...
---
name: test_memcpy3_const_arrays_unaligned
alignment: 4
tracksRegLiveness: true
registers:
- { id: 0, class: _ }
- { id: 1, class: _ }
- { id: 2, class: _ }
machineFunctionInfo: {}
body: |
bb.1.entry:
liveins: $x0, $x1
; CHECK-LABEL: name: test_memcpy3_const_arrays_unaligned
; CHECK: liveins: $x0, $x1
; CHECK: [[COPY:%[0-9]+]]:_(p0) = COPY $x0
; CHECK: [[COPY1:%[0-9]+]]:_(p0) = COPY $x1
; CHECK: [[LOAD:%[0-9]+]]:_(s128) = G_LOAD [[COPY1]](p0) :: (load 16 from %ir.1, align 4)
; CHECK: G_STORE [[LOAD]](s128), [[COPY]](p0) :: (store 16 into %ir.0, align 4)
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 16
; CHECK: [[GEP:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C]](s64)
; CHECK: [[LOAD1:%[0-9]+]]:_(s128) = G_LOAD [[GEP]](p0) :: (load 16 from %ir.1 + 16, align 4)
; CHECK: [[GEP1:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C]](s64)
; CHECK: G_STORE [[LOAD1]](s128), [[GEP1]](p0) :: (store 16 into %ir.0 + 16, align 4)
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 32
; CHECK: [[GEP2:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C1]](s64)
; CHECK: [[LOAD2:%[0-9]+]]:_(s128) = G_LOAD [[GEP2]](p0) :: (load 16 from %ir.1 + 32, align 4)
; CHECK: [[GEP3:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C1]](s64)
; CHECK: G_STORE [[LOAD2]](s128), [[GEP3]](p0) :: (store 16 into %ir.0 + 32, align 4)
; CHECK: [[C2:%[0-9]+]]:_(s64) = G_CONSTANT i64 48
; CHECK: [[GEP4:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C2]](s64)
; CHECK: [[LOAD3:%[0-9]+]]:_(s128) = G_LOAD [[GEP4]](p0) :: (load 16 from %ir.1 + 48, align 4)
; CHECK: [[GEP5:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C2]](s64)
; CHECK: G_STORE [[LOAD3]](s128), [[GEP5]](p0) :: (store 16 into %ir.0 + 48, align 4)
; CHECK: [[C3:%[0-9]+]]:_(s64) = G_CONSTANT i64 64
; CHECK: [[GEP6:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C3]](s64)
; CHECK: [[LOAD4:%[0-9]+]]:_(s128) = G_LOAD [[GEP6]](p0) :: (load 16 from %ir.1 + 64, align 4)
; CHECK: [[GEP7:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C3]](s64)
; CHECK: G_STORE [[LOAD4]](s128), [[GEP7]](p0) :: (store 16 into %ir.0 + 64, align 4)
; CHECK: [[C4:%[0-9]+]]:_(s64) = G_CONSTANT i64 80
; CHECK: [[GEP8:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C4]](s64)
; CHECK: [[LOAD5:%[0-9]+]]:_(s128) = G_LOAD [[GEP8]](p0) :: (load 16 from %ir.1 + 80, align 4)
; CHECK: [[GEP9:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C4]](s64)
; CHECK: G_STORE [[LOAD5]](s128), [[GEP9]](p0) :: (store 16 into %ir.0 + 80, align 4)
; CHECK: [[C5:%[0-9]+]]:_(s64) = G_CONSTANT i64 96
; CHECK: [[GEP10:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C5]](s64)
; CHECK: [[LOAD6:%[0-9]+]]:_(s128) = G_LOAD [[GEP10]](p0) :: (load 16 from %ir.1 + 96, align 4)
; CHECK: [[GEP11:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C5]](s64)
; CHECK: G_STORE [[LOAD6]](s128), [[GEP11]](p0) :: (store 16 into %ir.0 + 96, align 4)
; CHECK: [[C6:%[0-9]+]]:_(s64) = G_CONSTANT i64 112
; CHECK: [[GEP12:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C6]](s64)
; CHECK: [[LOAD7:%[0-9]+]]:_(s128) = G_LOAD [[GEP12]](p0) :: (load 16 from %ir.1 + 112, align 4)
; CHECK: [[GEP13:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C6]](s64)
; CHECK: G_STORE [[LOAD7]](s128), [[GEP13]](p0) :: (store 16 into %ir.0 + 112, align 4)
; CHECK: [[C7:%[0-9]+]]:_(s64) = G_CONSTANT i64 127
; CHECK: [[GEP14:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY1]], [[C7]](s64)
; CHECK: [[LOAD8:%[0-9]+]]:_(s128) = G_LOAD [[GEP14]](p0) :: (load 16 from %ir.1 + 127, align 4)
; CHECK: [[GEP15:%[0-9]+]]:_(p0) = G_PTR_ADD [[COPY]], [[C7]](s64)
; CHECK: G_STORE [[LOAD8]](s128), [[GEP15]](p0) :: (store 16 into %ir.0 + 127, align 4)
; CHECK: RET_ReallyLR
%0:_(p0) = COPY $x0
%1:_(p0) = COPY $x1
%2:_(s64) = G_CONSTANT i64 143
G_INTRINSIC_W_SIDE_EFFECTS intrinsic(@llvm.memcpy), %0(p0), %1(p0), %2(s64), 1 :: (store 1 into %ir.0, align 4), (load 1 from %ir.1, align 4)
RET_ReallyLR
...