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
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-globals --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" --global-value-regex "\![0-9]+"
// RUN: %clang_cc1 -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-host.bc
// RUN: %clang_cc1 -internal-isystem %S/../../lib/Headers/openmp_wrappers -include __clang_openmp_device_functions.h -internal-isystem %S/../../lib/Headers/openmp_wrappers -internal-isystem %S/Inputs/include -x c++ -fopenmp -triple amdgcn-amd-amdhsa -aux-triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-host.bc -o - | FileCheck %s
#ifdef __cplusplus
#include <cmath>
#else
#include <math.h>
#endif
#pragma omp begin declare target
const float constexpr_fabsf_f32 = fabsf(-2.0f);
const float constexpr_fabs_f32 = fabs(-2.0f);
const float constexpr_sinf_f32 = sinf(-2.0f);
const float constexpr_sin_f32 = sin(-2.0f);
const float constexpr_cosf_f32 = cosf(-2.0f);
const float constexpr_cos_f32 = cos(-2.0f);
const float constexpr_fmaf_f32 = fmaf(2.0f, 4.0f, 1.0f);
const float constexpr_fma_f32 = fma(2.0f, 4.0f, 1.0f);
const float constexpr_min_f32 = min(2.0f, -4.0f);
const float constexpr_max_f32 = max(2.0f, -4.0f);
const float constexpr_fmin_f32 = fmin(2.0f, -4.0f);
const float constexpr_fmax_f32 = fmax(2.0f, -4.0f);
const float constexpr_fminf_f32 = fminf(2.0f, -4.0f);
const float constexpr_fmaxf_f32 = fmaxf(2.0f, -4.0f);
#pragma omp end declare target
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fabsf_f32_l14_ctor
// CHECK-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = call float @llvm.fabs.f32(float [[TMP0]])
// CHECK-NEXT: store float [[TMP1]], ptr addrspacecast (ptr addrspace(1) @_ZL19constexpr_fabsf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fabs_f32_l15_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[RETVAL_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I_I]] to ptr
// CHECK-NEXT: store float [[TMP0]], ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.fabs.f32(float [[TMP1]])
// CHECK-NEXT: store float [[TMP2]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_fabs_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_sinf_f32_l17_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[CALL_I:%.*]] = call float @__ocml_sin_f32(float noundef [[TMP0]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: store float [[CALL_I]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_sinf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_sin_f32_l18_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[RETVAL_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I_I]] to ptr
// CHECK-NEXT: store float [[TMP0]], ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[CALL_I_I:%.*]] = call float @__ocml_sin_f32(float noundef [[TMP1]]) #[[ATTR3]]
// CHECK-NEXT: store float [[CALL_I_I]], ptr addrspacecast (ptr addrspace(1) @_ZL17constexpr_sin_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_cosf_f32_l20_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[CALL_I:%.*]] = call float @__ocml_cos_f32(float noundef [[TMP0]]) #[[ATTR3]]
// CHECK-NEXT: store float [[CALL_I]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_cosf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_cos_f32_l21_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: store float -2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[RETVAL_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I_I]] to ptr
// CHECK-NEXT: store float [[TMP0]], ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[CALL_I_I:%.*]] = call float @__ocml_cos_f32(float noundef [[TMP1]]) #[[ATTR3]]
// CHECK-NEXT: store float [[CALL_I_I]], ptr addrspacecast (ptr addrspace(1) @_ZL17constexpr_cos_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fmaf_f32_l23_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Z_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: [[__Z_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Z_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float 4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float 1.000000e+00, ptr [[__Z_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[__Z_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = call float @llvm.fma.f32(float [[TMP0]], float [[TMP1]], float [[TMP2]])
// CHECK-NEXT: store float [[TMP3]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_fmaf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fma_f32_l24_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Z_ADDR_I_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Z_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: [[__Z_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Z_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float 4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float 1.000000e+00, ptr [[__Z_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load float, ptr [[__Z_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[RETVAL_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I_I]] to ptr
// CHECK-NEXT: [[__Z_ADDR_ASCAST_I_I:%.*]] = addrspacecast ptr addrspace(5) [[__Z_ADDR_I_I]] to ptr
// CHECK-NEXT: store float [[TMP0]], ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: store float [[TMP1]], ptr [[__Y_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: store float [[TMP2]], ptr [[__Z_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP5:%.*]] = load float, ptr [[__Z_ADDR_ASCAST_I_I]], align 4
// CHECK-NEXT: [[TMP6:%.*]] = call float @llvm.fma.f32(float [[TMP3]], float [[TMP4]], float [[TMP5]])
// CHECK-NEXT: store float [[TMP6]], ptr addrspacecast (ptr addrspace(1) @_ZL17constexpr_fma_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_min_f32_l27_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float -4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.minnum.f32(float [[TMP0]], float [[TMP1]])
// CHECK-NEXT: store float [[TMP2]], ptr addrspacecast (ptr addrspace(1) @_ZL17constexpr_min_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_max_f32_l28_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float -4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.maxnum.f32(float [[TMP0]], float [[TMP1]])
// CHECK-NEXT: store float [[TMP2]], ptr addrspacecast (ptr addrspace(1) @_ZL17constexpr_max_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fmin_f32_l30_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = call noundef float @_Z4fminff(float noundef 2.000000e+00, float noundef -4.000000e+00) #[[ATTR4:[0-9]+]]
// CHECK-NEXT: store float [[CALL]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_fmin_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fmax_f32_l31_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = call noundef float @_Z4fmaxff(float noundef 2.000000e+00, float noundef -4.000000e+00) #[[ATTR4]]
// CHECK-NEXT: store float [[CALL]], ptr addrspacecast (ptr addrspace(1) @_ZL18constexpr_fmax_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fminf_f32_l33_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float -4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.minnum.f32(float [[TMP0]], float [[TMP1]])
// CHECK-NEXT: store float [[TMP2]], ptr addrspacecast (ptr addrspace(1) @_ZL19constexpr_fminf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_constexpr_fmaxf_f32_l34_ctor
// CHECK-SAME: () #[[ATTR0]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[RETVAL_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__X_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[__Y_ADDR_I:%.*]] = alloca float, align 4, addrspace(5)
// CHECK-NEXT: [[RETVAL_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[RETVAL_I]] to ptr
// CHECK-NEXT: [[__X_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__X_ADDR_I]] to ptr
// CHECK-NEXT: [[__Y_ADDR_ASCAST_I:%.*]] = addrspacecast ptr addrspace(5) [[__Y_ADDR_I]] to ptr
// CHECK-NEXT: store float 2.000000e+00, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: store float -4.000000e+00, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[__X_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load float, ptr [[__Y_ADDR_ASCAST_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = call float @llvm.maxnum.f32(float [[TMP0]], float [[TMP1]])
// CHECK-NEXT: store float [[TMP2]], ptr addrspacecast (ptr addrspace(1) @_ZL19constexpr_fmaxf_f32 to ptr), align 4
// CHECK-NEXT: ret void
//
|
