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
|
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-- -target-cpu tahiti -O0 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -O0 -emit-llvm -verify -o - %s | FileCheck -check-prefix=X86 %s
__attribute__((amdgpu_flat_work_group_size(0, 0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0() {}
__attribute__((amdgpu_waves_per_eu(0))) // expected-no-diagnostics
kernel void waves_per_eu_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0() {}
__attribute__((amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void num_sgpr0() {}
__attribute__((amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void num_vgpr0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_num_vgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_num_sgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_num_vgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0_num_sgpr_0() {}
__attribute__((amdgpu_waves_per_eu(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void waves_per_eu_0_0_num_vgpr_0() {}
__attribute__((amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_sgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0), amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(0, 0), amdgpu_waves_per_eu(0, 0), amdgpu_num_sgpr(0), amdgpu_num_vgpr(0))) // expected-no-diagnostics
kernel void flat_work_group_size_0_0_waves_per_eu_0_0_num_sgpr_0_num_vgpr_0() {}
__attribute__((amdgpu_flat_work_group_size(32, 64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64() [[FLAT_WORK_GROUP_SIZE_32_64:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2))) // expected-no-diagnostics
kernel void waves_per_eu_2() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2() [[WAVES_PER_EU_2:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2, 4))) // expected-no-diagnostics
kernel void waves_per_eu_2_4() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4() [[WAVES_PER_EU_2_4:#[0-9]+]]
}
__attribute__((amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @num_sgpr_32() [[NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @num_vgpr_64() [[NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_4() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void waves_per_eu_2_num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_num_sgpr_32() [[WAVES_PER_EU_2_NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void waves_per_eu_2_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_num_vgpr_64() [[WAVES_PER_EU_2_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32))) // expected-no-diagnostics
kernel void waves_per_eu_2_4_num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4_num_sgpr_32() [[WAVES_PER_EU_2_4_NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_waves_per_eu(2, 4), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void waves_per_eu_2_4_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @waves_per_eu_2_4_num_vgpr_64() [[WAVES_PER_EU_2_4_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void num_sgpr_32_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @num_sgpr_32_num_vgpr_64() [[NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_vgpr(64)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_vgpr(64)))
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2), amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_num_sgpr_32_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((amdgpu_flat_work_group_size(32, 64), amdgpu_waves_per_eu(2, 4), amdgpu_num_sgpr(32), amdgpu_num_vgpr(64))) // expected-no-diagnostics
kernel void flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32_num_vgpr_64() {
// CHECK: define{{.*}} amdgpu_kernel void @flat_work_group_size_32_64_waves_per_eu_2_4_num_sgpr_32_num_vgpr_64() [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64:#[0-9]+]]
}
__attribute__((reqd_work_group_size(32, 2, 1))) // expected-no-diagnostics
kernel void reqd_work_group_size_32_2_1() {
// CHECK: define{{.*}} amdgpu_kernel void @reqd_work_group_size_32_2_1() [[FLAT_WORK_GROUP_SIZE_64_64:#[0-9]+]]
}
__attribute__((reqd_work_group_size(32, 2, 1), amdgpu_flat_work_group_size(16, 128))) // expected-no-diagnostics
kernel void reqd_work_group_size_32_2_1_flat_work_group_size_16_128() {
// CHECK: define{{.*}} amdgpu_kernel void @reqd_work_group_size_32_2_1_flat_work_group_size_16_128() [[FLAT_WORK_GROUP_SIZE_16_128:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(1, 1, 1))) // expected-no-diagnostics
kernel void max_num_work_groups_1_1_1() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_1_1_1() [[MAX_NUM_WORK_GROUPS_1_1_1:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(32, 1, 1))) // expected-no-diagnostics
kernel void max_num_work_groups_32_1_1() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_32_1_1() [[MAX_NUM_WORK_GROUPS_32_1_1:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(32, 8, 1))) // expected-no-diagnostics
kernel void max_num_work_groups_32_8_1() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_32_8_1() [[MAX_NUM_WORK_GROUPS_32_8_1:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(1, 1, 32))) // expected-no-diagnostics
kernel void max_num_work_groups_1_1_32() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_1_1_32() [[MAX_NUM_WORK_GROUPS_1_1_32:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(1, 8, 32))) // expected-no-diagnostics
kernel void max_num_work_groups_1_8_32() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_1_8_32() [[MAX_NUM_WORK_GROUPS_1_8_32:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(4, 8, 32))) // expected-no-diagnostics
kernel void max_num_work_groups_4_8_32() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_4_8_32() [[MAX_NUM_WORK_GROUPS_4_8_32:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(32))) // expected-no-diagnostics
kernel void max_num_work_groups_32() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_32() [[MAX_NUM_WORK_GROUPS_32_1_1:#[0-9]+]]
}
__attribute__((amdgpu_max_num_work_groups(32,1))) // expected-no-diagnostics
kernel void max_num_work_groups_32_1() {
// CHECK: define{{.*}} amdgpu_kernel void @max_num_work_groups_32_1() [[MAX_NUM_WORK_GROUPS_32_1_1:#[0-9]+]]
}
void a_function() {
// CHECK: define{{.*}} void @a_function() [[A_FUNCTION:#[0-9]+]]
}
kernel void default_kernel() {
// CHECK: define{{.*}} amdgpu_kernel void @default_kernel() [[DEFAULT_KERNEL_ATTRS:#[0-9]+]]
}
// Make sure this is silently accepted on other targets.
// X86-NOT: "amdgpu-flat-work-group-size"
// X86-NOT: "amdgpu-waves-per-eu"
// X86-NOT: "amdgpu-num-vgpr"
// X86-NOT: "amdgpu-num-sgpr"
// CHECK-NOT: "amdgpu-implicitarg-num-bytes"
// CHECK-NOT: "amdgpu-flat-work-group-size"="0,0"
// CHECK-NOT: "amdgpu-waves-per-eu"="0"
// CHECK-NOT: "amdgpu-waves-per-eu"="0,0"
// CHECK-NOT: "amdgpu-num-sgpr"="0"
// CHECK-NOT: "amdgpu-num-vgpr"="0"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_64_64]] = {{.*}} "amdgpu-flat-work-group-size"="64,64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_16_128]] = {{.*}} "amdgpu-flat-work-group-size"="16,128"
// CHECK-DAG: attributes [[WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32"
// CHECK-DAG: attributes [[NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="1,256" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2"
// CHECK-DAG: attributes [[FLAT_WORK_GROUP_SIZE_32_64_WAVES_PER_EU_2_4_NUM_SGPR_32_NUM_VGPR_64]] = {{.*}} "amdgpu-flat-work-group-size"="32,64" "amdgpu-num-sgpr"="32" "amdgpu-num-vgpr"="64" "amdgpu-waves-per-eu"="2,4"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_1_1_1]] = {{.*}} "amdgpu-max-num-workgroups"="1,1,1"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_32_1_1]] = {{.*}} "amdgpu-max-num-workgroups"="32,1,1"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_32_8_1]] = {{.*}} "amdgpu-max-num-workgroups"="32,8,1"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_1_1_32]] = {{.*}} "amdgpu-max-num-workgroups"="1,1,32"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_1_8_32]] = {{.*}} "amdgpu-max-num-workgroups"="1,8,32"
// CHECK-DAG: attributes [[MAX_NUM_WORK_GROUPS_4_8_32]] = {{.*}} "amdgpu-max-num-workgroups"="4,8,32"
// CHECK-DAG: attributes [[A_FUNCTION]] = {{.*}}
// CHECK-DAG: attributes [[DEFAULT_KERNEL_ATTRS]] = {{.*}} "amdgpu-flat-work-group-size"="1,256"
|
