aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/EarlyCSE/AArch64/intrinsics.ll
blob: d166ff1e10921d7cf54d9a9d8e16d89f0ca9f732 (plain)
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
; RUN: opt < %s -S -mtriple=aarch64-none-linux-gnu -mattr=+neon -early-cse | FileCheck %s
; RUN: opt < %s -S -mtriple=aarch64-none-linux-gnu -mattr=+neon -passes=early-cse | FileCheck %s

define <4 x i32> @test_cse(i32* %a, [2 x <4 x i32>] %s.coerce, i32 %n) {
entry:
; Check that @llvm.aarch64.neon.ld2 is optimized away by Early CSE.
; CHECK-LABEL: @test_cse
; CHECK-NOT: call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %1 = bitcast <4 x i32> %s.coerce.fca.0.extract to <16 x i8>
  %2 = bitcast <4 x i32> %s.coerce.fca.1.extract to <16 x i8>
  %3 = bitcast <16 x i8> %1 to <4 x i32>
  %4 = bitcast <16 x i8> %2 to <4 x i32>
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %4, i8* %0)
  %5 = bitcast i32* %a to i8*
  %vld2 = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8* %5)
  %vld2.fca.0.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 0
  %vld2.fca.1.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 1
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld2.fca.0.extract, <4 x i32> %vld2.fca.0.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}

define <4 x i32> @test_cse2(i32* %a, [2 x <4 x i32>] %s.coerce, i32 %n) {
entry:
; Check that the first @llvm.aarch64.neon.st2 is optimized away by Early CSE.
; CHECK-LABEL: @test_cse2
; CHECK-NOT: call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %3, i8* %0)
; CHECK: call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %4, i8* %0)
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %1 = bitcast <4 x i32> %s.coerce.fca.0.extract to <16 x i8>
  %2 = bitcast <4 x i32> %s.coerce.fca.1.extract to <16 x i8>
  %3 = bitcast <16 x i8> %1 to <4 x i32>
  %4 = bitcast <16 x i8> %2 to <4 x i32>
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %3, i8* %0)
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %4, i8* %0)
  %5 = bitcast i32* %a to i8*
  %vld2 = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8* %5)
  %vld2.fca.0.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 0
  %vld2.fca.1.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 1
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld2.fca.0.extract, <4 x i32> %vld2.fca.0.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}

define <4 x i32> @test_cse3(i32* %a, [2 x <4 x i32>] %s.coerce, i32 %n) #0 {
entry:
; Check that the first @llvm.aarch64.neon.ld2 is optimized away by Early CSE.
; CHECK-LABEL: @test_cse3
; CHECK: call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8
; CHECK-NOT: call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %vld2 = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8* %0)
  %vld2.fca.0.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 0
  %vld2.fca.1.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 1
  %1 = bitcast i32* %a to i8*
  %vld22 = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8* %1)
  %vld22.fca.0.extract = extractvalue { <4 x i32>, <4 x i32> } %vld22, 0
  %vld22.fca.1.extract = extractvalue { <4 x i32>, <4 x i32> } %vld22, 1
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld2.fca.0.extract, <4 x i32> %vld22.fca.0.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}


define <4 x i32> @test_nocse(i32* %a, i32* %b, [2 x <4 x i32>] %s.coerce, i32 %n) {
entry:
; Check that the store prevents @llvm.aarch64.neon.ld2 from being optimized
; away by Early CSE.
; CHECK-LABEL: @test_nocse
; CHECK: call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %1 = bitcast <4 x i32> %s.coerce.fca.0.extract to <16 x i8>
  %2 = bitcast <4 x i32> %s.coerce.fca.1.extract to <16 x i8>
  %3 = bitcast <16 x i8> %1 to <4 x i32>
  %4 = bitcast <16 x i8> %2 to <4 x i32>
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %4, i8* %0)
  store i32 0, i32* %b, align 4
  %5 = bitcast i32* %a to i8*
  %vld2 = call { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8* %5)
  %vld2.fca.0.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 0
  %vld2.fca.1.extract = extractvalue { <4 x i32>, <4 x i32> } %vld2, 1
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld2.fca.0.extract, <4 x i32> %vld2.fca.0.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}

define <4 x i32> @test_nocse2(i32* %a, [2 x <4 x i32>] %s.coerce, i32 %n) {
entry:
; Check that @llvm.aarch64.neon.ld3 is not optimized away by Early CSE due
; to mismatch between st2 and ld3.
; CHECK-LABEL: @test_nocse2
; CHECK: call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0i8
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %1 = bitcast <4 x i32> %s.coerce.fca.0.extract to <16 x i8>
  %2 = bitcast <4 x i32> %s.coerce.fca.1.extract to <16 x i8>
  %3 = bitcast <16 x i8> %1 to <4 x i32>
  %4 = bitcast <16 x i8> %2 to <4 x i32>
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %4, i8* %0)
  %5 = bitcast i32* %a to i8*
  %vld3 = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0i8(i8* %5)
  %vld3.fca.0.extract = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } %vld3, 0
  %vld3.fca.2.extract = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } %vld3, 2
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld3.fca.0.extract, <4 x i32> %vld3.fca.2.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}

define <4 x i32> @test_nocse3(i32* %a, [2 x <4 x i32>] %s.coerce, i32 %n) {
entry:
; Check that @llvm.aarch64.neon.st3 is not optimized away by Early CSE due to
; mismatch between st2 and st3.
; CHECK-LABEL: @test_nocse3
; CHECK: call void @llvm.aarch64.neon.st3.v4i32.p0i8
; CHECK: call void @llvm.aarch64.neon.st2.v4i32.p0i8
  %s.coerce.fca.0.extract = extractvalue [2 x <4 x i32>] %s.coerce, 0
  %s.coerce.fca.1.extract = extractvalue [2 x <4 x i32>] %s.coerce, 1
  br label %for.cond

for.cond:                                         ; preds = %for.body, %entry
  %i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
  %res.0 = phi <4 x i32> [ undef, %entry ], [ %call, %for.body ]
  %cmp = icmp slt i32 %i.0, %n
  br i1 %cmp, label %for.body, label %for.end

for.body:                                         ; preds = %for.cond
  %0 = bitcast i32* %a to i8*
  %1 = bitcast <4 x i32> %s.coerce.fca.0.extract to <16 x i8>
  %2 = bitcast <4 x i32> %s.coerce.fca.1.extract to <16 x i8>
  %3 = bitcast <16 x i8> %1 to <4 x i32>
  %4 = bitcast <16 x i8> %2 to <4 x i32>
  call void @llvm.aarch64.neon.st3.v4i32.p0i8(<4 x i32> %4, <4 x i32> %3, <4 x i32> %3, i8* %0)
  call void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32> %3, <4 x i32> %3, i8* %0)
  %5 = bitcast i32* %a to i8*
  %vld3 = call { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0i8(i8* %5)
  %vld3.fca.0.extract = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } %vld3, 0
  %vld3.fca.1.extract = extractvalue { <4 x i32>, <4 x i32>, <4 x i32> } %vld3, 1
  %call = call <4 x i32> @vaddq_s32(<4 x i32> %vld3.fca.0.extract, <4 x i32> %vld3.fca.0.extract)
  %inc = add nsw i32 %i.0, 1
  br label %for.cond

for.end:                                          ; preds = %for.cond
  ret <4 x i32> %res.0
}

; Function Attrs: nounwind
declare void @llvm.aarch64.neon.st2.v4i32.p0i8(<4 x i32>, <4 x i32>, i8* nocapture)

; Function Attrs: nounwind
declare void @llvm.aarch64.neon.st3.v4i32.p0i8(<4 x i32>, <4 x i32>, <4 x i32>, i8* nocapture)

; Function Attrs: nounwind readonly
declare { <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld2.v4i32.p0i8(i8*)

; Function Attrs: nounwind readonly
declare { <4 x i32>, <4 x i32>, <4 x i32> } @llvm.aarch64.neon.ld3.v4i32.p0i8(i8*)

define internal fastcc <4 x i32> @vaddq_s32(<4 x i32> %__p0, <4 x i32> %__p1) {
entry:
  %add = add <4 x i32> %__p0, %__p1
  ret <4 x i32> %add
}