private-element-size.ll
14.6 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
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-16 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=ELT16 -check-prefix=HSA -check-prefix=HSA-ELT16 -check-prefix=ALL -check-prefix=HSA_ELTGE8 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-8 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=ELT8 -check-prefix=HSA -check-prefix=HSA-ELT8 -check-prefix=ALL -check-prefix=HSA-ELTGE8 %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-4 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap -check-prefix=ELT4 -check-prefix=HSA -check-prefix=HSA-ELT4 -check-prefix=ALL %s
; ALL-LABEL: {{^}}private_elt_size_v4i32:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
define amdgpu_kernel void @private_elt_size_v4i32(<4 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <4 x i32>], align 16, addrspace(5)
%gep0 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>] addrspace(5)* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>] addrspace(5)* %alloca, i32 0, i32 1
store <4 x i32> zeroinitializer, <4 x i32> addrspace(5)* %gep0
store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, <4 x i32> addrspace(5)* %gep1
%gep2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>] addrspace(5)* %alloca, i32 0, i32 %index
%load = load <4 x i32>, <4 x i32> addrspace(5)* %gep2
store <4 x i32> %load, <4 x i32> addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_v8i32:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:48
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:64
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:80
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:48
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:56
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:88
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:80
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:72
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:64
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:48{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:52{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:56{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:60{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:64{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:68{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:72{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:76{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:80{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:84{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:88{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:92{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:16{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:20{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:24{{$}}
; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:28{{$}}
define amdgpu_kernel void @private_elt_size_v8i32(<8 x i32> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <8 x i32>], align 32, addrspace(5)
%gep0 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>] addrspace(5)* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>] addrspace(5)* %alloca, i32 0, i32 1
store <8 x i32> zeroinitializer, <8 x i32> addrspace(5)* %gep0
store <8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>, <8 x i32> addrspace(5)* %gep1
%gep2 = getelementptr inbounds [2 x <8 x i32>], [2 x <8 x i32>] addrspace(5)* %alloca, i32 0, i32 %index
%load = load <8 x i32>, <8 x i32> addrspace(5)* %gep2
store <8 x i32> %load, <8 x i32> addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_i64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], 0 offset:1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], 0 offset:2
; HSA-ELTGE8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
define amdgpu_kernel void @private_elt_size_i64(i64 addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x i64], align 16, addrspace(5)
%gep0 = getelementptr inbounds [2 x i64], [2 x i64] addrspace(5)* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x i64], [2 x i64] addrspace(5)* %alloca, i32 0, i32 1
store i64 0, i64 addrspace(5)* %gep0
store i64 34359738602, i64 addrspace(5)* %gep1
%gep2 = getelementptr inbounds [2 x i64], [2 x i64] addrspace(5)* %alloca, i32 0, i32 %index
%load = load i64, i64 addrspace(5)* %gep2
store i64 %load, i64 addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_f64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24
; HSA-ELTGE8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
define amdgpu_kernel void @private_elt_size_f64(double addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x double], align 16, addrspace(5)
%gep0 = getelementptr inbounds [2 x double], [2 x double] addrspace(5)* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x double], [2 x double] addrspace(5)* %alloca, i32 0, i32 1
store double 0.0, double addrspace(5)* %gep0
store double 4.0, double addrspace(5)* %gep1
%gep2 = getelementptr inbounds [2 x double], [2 x double] addrspace(5)* %alloca, i32 0, i32 %index
%load = load double, double addrspace(5)* %gep2
store double %load, double addrspace(1)* %out
ret void
}
; ALL-LABEL: {{^}}private_elt_size_v2i64:
; HSA-ELT16: private_element_size = 3
; HSA-ELT8: private_element_size = 2
; HSA-ELT4: private_element_size = 1
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16{{$}}
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
define amdgpu_kernel void @private_elt_size_v2i64(<2 x i64> addrspace(1)* %out, i32 addrspace(1)* %index.array) #0 {
entry:
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.index = getelementptr inbounds i32, i32 addrspace(1)* %index.array, i64 %idxprom
%index.load = load i32, i32 addrspace(1)* %gep.index
%index = and i32 %index.load, 2
%alloca = alloca [2 x <2 x i64>], align 16, addrspace(5)
%gep0 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>] addrspace(5)* %alloca, i32 0, i32 0
%gep1 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>] addrspace(5)* %alloca, i32 0, i32 1
store <2 x i64> zeroinitializer, <2 x i64> addrspace(5)* %gep0
store <2 x i64> <i64 1, i64 2>, <2 x i64> addrspace(5)* %gep1
%gep2 = getelementptr inbounds [2 x <2 x i64>], [2 x <2 x i64>] addrspace(5)* %alloca, i32 0, i32 %index
%load = load <2 x i64>, <2 x i64> addrspace(5)* %gep2
store <2 x i64> %load, <2 x i64> addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }