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
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
|
///
/// Perform several driver tests for OpenMP offloading
///
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: powerpc-registered-target
// REQUIRES: nvptx-registered-target
// REQUIRES: amdgpu-registered-target
// UNSUPPORTED: aix
/// ###########################################################################
/// Check -Xopenmp-target uses one of the archs provided when several archs are used.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 -Xopenmp-target -march=sm_60 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-ARCHS %s
// CHK-FOPENMP-TARGET-ARCHS: ptxas{{.*}}" "--gpu-name" "sm_60"
// CHK-FOPENMP-TARGET-ARCHS: nvlink{{.*}}" "-arch" "sm_60"
/// ###########################################################################
/// Check -Xopenmp-target -march=sm_35 works as expected when two triples are present.
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp \
// RUN: -fopenmp-targets=powerpc64le-ibm-linux-gnu,nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target=nvptx64-nvidia-cuda -march=sm_35 %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FOPENMP-TARGET-COMPILATION %s
// CHK-FOPENMP-TARGET-COMPILATION: ptxas{{.*}}" "--gpu-name" "sm_35"
// CHK-FOPENMP-TARGET-COMPILATION: nvlink{{.*}}" "-arch" "sm_35"
/// ###########################################################################
/// Check cubin file generation and usage by nvlink
// RUN: %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda -save-temps %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUBIN-NVLINK %s
// CHK-CUBIN-NVLINK: clang{{.*}}" {{.*}}"-fopenmp-is-device" {{.*}}"-o" "[[PTX:.*\.s]]"
// CHK-CUBIN-NVLINK-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
// CHK-CUBIN-NVLINK-NEXT: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
/// ###########################################################################
/// Check unbundlink of assembly file, cubin file generation and usage by nvlink
// RUN: touch %t.s
// RUN: %clang -### -target powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -no-canonical-prefixes -save-temps %t.s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK %s
/// Use DAG to ensure that assembly file has been unbundled.
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX:.*\.s]]"
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=s" {{.*}}"-outputs={{.*}}[[PTX]]
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK-DAG-SAME: "-unbundle"
// CHK-UNBUNDLING-PTXAS-CUBIN-NVLINK: nvlink{{.*}}" {{.*}}"[[CUBIN]]"
/// ###########################################################################
/// Check cubin file generation and bundling
// RUN: %clang -### -target powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -no-canonical-prefixes -save-temps %s -c 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-CUBIN-BUNDLING %s
// CHK-PTXAS-CUBIN-BUNDLING: clang{{.*}}" "-o" "[[PTX:.*\.s]]"
// CHK-PTXAS-CUBIN-BUNDLING-NEXT: ptxas{{.*}}" "--output-file" "[[CUBIN:.*\.cubin]]" {{.*}}"[[PTX]]"
// CHK-PTXAS-CUBIN-BUNDLING: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-inputs={{.*}}[[CUBIN]]
/// ###########################################################################
/// Check cubin file unbundling and usage by nvlink
// RUN: touch %t.o
// RUN: %clang -### -target powerpc64le-unknown-linux-gnu -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -no-canonical-prefixes -save-temps %t.o %S/Inputs/in.so 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUBIN-UNBUNDLING-NVLINK %s
/// Use DAG to ensure that cubin file has been unbundled.
// CHK-CUBIN-UNBUNDLING-NVLINK-NOT: clang-offload-bundler{{.*}}" "-type=o"{{.*}}in.so
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: nvlink{{.*}}" {{.*}}"[[CUBIN:.*\.cubin]]"
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG: clang-offload-bundler{{.*}}" "-type=o" {{.*}}"-outputs={{.*}}[[CUBIN]]
// CHK-CUBIN-UNBUNDLING-NVLINK-DAG-SAME: "-unbundle"
// CHK-CUBIN-UNBUNDLING-NVLINK-NOT: clang-offload-bundler{{.*}}" "-type=o"{{.*}}in.so
/// ###########################################################################
/// Check cubin file generation and usage by nvlink
// RUN: touch %t1.o
// RUN: touch %t2.o
// RUN: %clang -### -no-canonical-prefixes -target powerpc64le-unknown-linux-gnu -fopenmp=libomp \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN %s
/// Check cubin file generation and usage by nvlink when toolchain has BindArchAction
// RUN: %clang -### -no-canonical-prefixes -target x86_64-apple-darwin17.0.0 -fopenmp=libomp \
// RUN: -fopenmp-targets=nvptx64-nvidia-cuda %t1.o %t2.o 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-TWOCUBIN %s
// CHK-TWOCUBIN: nvlink{{.*}}openmp-offload-{{.*}}.cubin" "{{.*}}openmp-offload-{{.*}}.cubin"
/// ###########################################################################
/// Check PTXAS is passed -c flag when offloading to an NVIDIA device using OpenMP.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-DEFAULT %s
// CHK-PTXAS-DEFAULT: ptxas{{.*}}" "-c"
/// ###########################################################################
/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP - disable it.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fnoopenmp-relocatable-target \
// RUN: -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-NORELO %s
// CHK-PTXAS-NORELO-NOT: ptxas{{.*}}" "-c"
/// ###########################################################################
/// PTXAS is passed -c flag by default when offloading to an NVIDIA device using OpenMP
/// Check that the flag is passed when -fopenmp-relocatable-target is used.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -fopenmp-relocatable-target \
// RUN: -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-PTXAS-RELO %s
// CHK-PTXAS-RELO: ptxas{{.*}}" "-c"
/// ###########################################################################
/// Check that error is not thrown by toolchain when no cuda lib flag is used.
/// Check that the flag is passed when -fopenmp-relocatable-target is used.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 \
// RUN: -nocudalib -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-FLAG-NOLIBDEVICE %s
// CHK-FLAG-NOLIBDEVICE-NOT: error:{{.*}}sm_60
/// ###########################################################################
/// Check that error is not thrown by toolchain when no cuda lib device is found when using -S.
/// Check that the flag is passed when -fopenmp-relocatable-target is used.
// RUN: %clang -### -S -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-NOLIBDEVICE %s
// CHK-NOLIBDEVICE-NOT: error:{{.*}}sm_60
/// ###########################################################################
/// Check that the runtime bitcode library is part of the compile line.
/// Create a bogus bitcode library and specify it with libomptarget-nvptx-bc-path
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-nvptx-test.bc \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -fopenmp-target-new-runtime -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB %s
/// Specify the directory containing the bitcode lib, check clang picks the right one
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -fno-openmp-target-new-runtime -save-temps \
// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-BCLIB-DIR %s
/// Check with the new runtime enabled
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -fopenmp-target-new-runtime \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc \
// RUN: -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB-NEW %s
/// Check with new runtime and specifying the directory
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -fopenmp-target-new-runtime \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget -save-temps \
// RUN: -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB-NEW-DIR %s
/// Create a bogus bitcode library and find it with LIBRARY_PATH
// RUN: env LIBRARY_PATH=%S/Inputs/libomptarget/subdir %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -fno-openmp-target-new-runtime -save-temps \
// RUN: -no-canonical-prefixes %s 2>&1 | FileCheck -check-prefix=CHK-ENV-BCLIB %s
// CHK-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-nvptx-test.bc
// CHK-BCLIB-DIR: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget{{/|\\\\}}libomptarget-nvptx-sm_35.bc
// CHK-BCLIB-NEW: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget-new-nvptx-test.bc
// CHK-BCLIB-NEW-DIR: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}libomptarget{{/|\\\\}}libomptarget-new-nvptx-sm_35.bc
// CHK-ENV-BCLIB: clang{{.*}}-triple{{.*}}nvptx64-nvidia-cuda{{.*}}-mlink-builtin-bitcode{{.*}}subdir{{/|\\\\}}libomptarget-nvptx-sm_35.bc
// CHK-BCLIB-NOT: {{error:|warning:}}
/// ###########################################################################
/// Check that the warning is thrown when the libomptarget bitcode library is not found.
/// Libomptarget requires sm_35 or newer so an sm_35 bitcode library should never exist.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB-WARN %s
// CHK-BCLIB-WARN: no library 'libomptarget-new-nvptx-sm_35.bc' found in the default clang lib directory or in LIBRARY_PATH; use '--libomptarget-nvptx-bc-path' to specify nvptx bitcode library
/// ###########################################################################
/// Check that the error is thrown when the libomptarget bitcode library does not exist.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_102/usr/local/cuda \
// RUN: --libomptarget-nvptx-bc-path=not-exist.bc \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-BCLIB-ERROR %s
// CHK-BCLIB-ERROR: bitcode library 'not-exist.bc' does not exist
/// ###########################################################################
/// Check that the error is thrown when CUDA 9.1 or lower version is used.
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -Xopenmp-target -march=sm_35 --cuda-path=%S/Inputs/CUDA_90/usr/local/cuda \
// RUN: -fopenmp-relocatable-target -save-temps -no-canonical-prefixes %s 2>&1 \
// RUN: | FileCheck -check-prefix=CHK-CUDA-VERSION-ERROR %s
// CHK-CUDA-VERSION-ERROR: NVPTX target requires CUDA 9.2 or above; CUDA 9.0 detected
/// Check that debug info is emitted in dwarf-2
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O1 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g0 2>&1 \
// RUN: | FileCheck -check-prefix=NO_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb0 -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=NO_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-directives-only 2>&1 \
// RUN: | FileCheck -check-prefix=DEBUG_DIRECTIVES %s
// DEBUG_DIRECTIVES-NOT: warning: debug
// NO_DEBUG-NOT: warning: debug
// NO_DEBUG: "-fopenmp-is-device"
// NO_DEBUG-NOT: "-debug-info-kind=
// NO_DEBUG: ptxas
// DEBUG_DIRECTIVES: "-triple" "nvptx64-nvidia-cuda"
// DEBUG_DIRECTIVES-SAME: "-debug-info-kind=line-directives-only"
// DEBUG_DIRECTIVES-SAME: "-fopenmp-is-device"
// DEBUG_DIRECTIVES: ptxas
// DEBUG_DIRECTIVES: "-lineinfo"
// NO_DEBUG-NOT: "-g"
// NO_DEBUG: nvlink
// NO_DEBUG-NOT: "-g"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --no-cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O0 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g2 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb2 -O0 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -g3 -O3 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb3 -O2 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -gline-tables-only 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -ggdb1 -O2 --cuda-noopt-device-debug 2>&1 \
// RUN: | FileCheck -check-prefix=HAS_DEBUG %s
// HAS_DEBUG-NOT: warning: debug
// HAS_DEBUG: "-triple" "nvptx64-nvidia-cuda"
// HAS_DEBUG-SAME: "-debug-info-kind={{constructor|line-tables-only}}"
// HAS_DEBUG-SAME: "-dwarf-version=2"
// HAS_DEBUG-SAME: "-fopenmp-is-device"
// HAS_DEBUG: ptxas
// HAS_DEBUG-SAME: "-g"
// HAS_DEBUG-SAME: "--dont-merge-basicblocks"
// HAS_DEBUG-SAME: "--return-at-end"
// HAS_DEBUG: nvlink
// HAS_DEBUG-SAME: "-g"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-mode -fopenmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_MODE %s
// CUDA_MODE: clang{{.*}}"-cc1"{{.*}}"-triple" "{{nvptx64-nvidia-cuda|amdgcn-amd-amdhsa}}"
// CUDA_MODE-SAME: "-fopenmp-cuda-mode"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=NO_CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-mode -fno-openmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=NO_CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=NO_CUDA_MODE %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-mode -fno-openmp-cuda-mode 2>&1 \
// RUN: | FileCheck -check-prefix=NO_CUDA_MODE %s
// NO_CUDA_MODE-NOT: "-{{fno-|f}}openmp-cuda-mode"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-force-full-runtime -fopenmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-force-full-runtime -fopenmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=FULL_RUNTIME %s
// FULL_RUNTIME: clang{{.*}}"-cc1"{{.*}}"-triple" "{{nvptx64-nvidia-cuda|amdgcn-amd-amdhsa}}"
// FULL_RUNTIME-SAME: "-fopenmp-cuda-force-full-runtime"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fno-openmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=NO_FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-force-full-runtime -fno-openmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=NO_FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fno-openmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=NO_FULL_RUNTIME %s
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=amdgcn-amd-amdhsa -Xopenmp-target -march=gfx906 %s -fopenmp-cuda-force-full-runtime -fno-openmp-cuda-force-full-runtime 2>&1 \
// RUN: | FileCheck -check-prefix=NO_FULL_RUNTIME %s
// NO_FULL_RUNTIME-NOT: "-{{fno-|f}}openmp-cuda-force-full-runtime"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-teams-reduction-recs-num=2048 2>&1 \
// RUN: | FileCheck -check-prefix=CUDA_RED_RECS %s
// CUDA_RED_RECS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
// CUDA_RED_RECS-SAME: "-fopenmp-cuda-teams-reduction-recs-num=2048"
// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda %s 2>&1 \
// RUN: | FileCheck -check-prefix=OPENMP_NVPTX_WRAPPERS %s
// OPENMP_NVPTX_WRAPPERS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda"
// OPENMP_NVPTX_WRAPPERS-SAME: "-internal-isystem" "{{.*}}openmp_wrappers"
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -save-temps -no-canonical-prefixes -ccc-print-bindings %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=SAVE_TEMPS_NAMES %s
// SAVE_TEMPS_NAMES-NOT: "GNU::Linker"{{.*}}["[[SAVE_TEMPS_INPUT1:.*\.o]]", "[[SAVE_TEMPS_INPUT1]]"]
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64 -Xopenmp-target=nvptx64 -march=sm_35 \
// RUN: -save-temps -no-canonical-prefixes %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=TRIPLE %s
// TRIPLE: "-triple" "nvptx64-nvidia-cuda"
// TRIPLE: "-target-cpu" "sm_35"
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda \
// RUN: -fopenmp-new-driver -no-canonical-prefixes -ccc-print-bindings %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=NEW_DRIVER %s
// NEW_DRIVER: "[[HOST_TRIPLE:.+]]" - "clang", inputs: ["[[HOST_INPUT:.+]]"], output: "[[HOST_BC:.+]]"
// NEW_DRIVER: "nvptx64-nvidia-cuda" - "clang", inputs: ["[[DEVICE_INPUT:.+]]", "[[HOST_BC]]"], output: "[[DEVICE_ASM:.+]]"
// NEW_DRIVER: "nvptx64-nvidia-cuda" - "NVPTX::Assembler", inputs: ["[[DEVICE_ASM]]"], output: "[[DEVICE_OBJ:.+]]"
// RUN: %clang -### -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target=nvptx64-nvida-cuda -march=sm_70 \
// RUN: --libomptarget-nvptx-bc-path=%S/Inputs/libomptarget/libomptarget-new-nvptx-test.bc \
// RUN: -fopenmp-new-driver -no-canonical-prefixes -nogpulib %s -o openmp-offload-gpu 2>&1 \
// RUN: | FileCheck -check-prefix=NEW_DRIVER_EMBEDDING %s
// NEW_DRIVER_EMBEDDING: -fembed-offload-object=[[CUBIN:.*\.cubin]],nvptx64-nvidia-cuda.sm_70
|
