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
|
// Tests CUDA compilation pipeline construction in Driver.
// REQUIRES: clang-driver
// REQUIRES: x86-registered-target
// REQUIRES: nvptx-registered-target
// Simple compilation case. Compile device-side to PTX assembly and make sure
// we use it on the host side.
// RUN: %clang -### -target x86_64-linux-gnu -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix NOLINK %s
// Typical compilation + link case.
// RUN: %clang -### -target x86_64-linux-gnu %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
// Verify that --cuda-host-only disables device-side compilation, but doesn't
// disable host-side compilation/linking.
// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
// Verify that --cuda-device-only disables host-side compilation and linking.
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
// Check that the last of --cuda-compile-host-device, --cuda-host-only, and
// --cuda-device-only wins.
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-host-only %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device \
// RUN: --cuda-host-only %s 2>&1 \
// RUN: | FileCheck -check-prefix NODEVICE -check-prefix HOST \
// RUN: -check-prefix NOINCLUDES-DEVICE -check-prefix LINK %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only \
// RUN: --cuda-device-only %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-compile-host-device \
// RUN: --cuda-device-only %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix NOHOST -check-prefix NOLINK %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-host-only \
// RUN: --cuda-compile-host-device %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-compile-host-device %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix INCLUDES-DEVICE \
// RUN: -check-prefix LINK %s
// Verify that --cuda-gpu-arch option passes the correct GPU architecture to
// device compilation.
// RUN: %clang -### -target x86_64-linux-gnu --cuda-gpu-arch=sm_30 -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix DEVICE-SM30 -check-prefix HOST \
// RUN: -check-prefix INCLUDES-DEVICE -check-prefix NOLINK %s
// Verify that there is one device-side compilation per --cuda-gpu-arch args
// and that all results are included on the host side.
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes DEVICE,DEVICE-NOSAVE,DEVICE2 \
// RUN: -check-prefixes DEVICE-SM30,DEVICE2-SM35 \
// RUN: -check-prefixes INCLUDES-DEVICE,INCLUDES-DEVICE2 \
// RUN: -check-prefixes HOST,HOST-NOSAVE,NOLINK %s
// Verify that device-side results are passed to the correct tool when
// -save-temps is used.
// RUN: %clang -### -target x86_64-linux-gnu -save-temps -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-SAVE \
// RUN: -check-prefix HOST -check-prefix HOST-SAVE -check-prefix NOLINK %s
// Verify that device-side results are passed to the correct tool when
// -fno-integrated-as is used.
// RUN: %clang -### -target x86_64-linux-gnu -fno-integrated-as -c %s 2>&1 \
// RUN: | FileCheck -check-prefix DEVICE -check-prefix DEVICE-NOSAVE \
// RUN: -check-prefix HOST -check-prefix HOST-NOSAVE \
// RUN: -check-prefix HOST-AS -check-prefix NOLINK %s
// Verify that --[no-]cuda-gpu-arch arguments are handled correctly.
// a) --no-cuda-gpu-arch=X negates preceding --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-gpu-arch=sm_50 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
// b) --no-cuda-gpu-arch=X negates more than one preceding --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-gpu-arch=sm_50 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,NOARCH-SM50 %s
// c) if --no-cuda-gpu-arch=X negates all preceding --cuda-gpu-arch=X
// we default to sm_35 -- same as if no --cuda-gpu-arch were passed.
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-gpu-arch=sm_50 --no-cuda-gpu-arch=sm_30 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes NOARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
// d) --no-cuda-gpu-arch=X is a no-op if there's no preceding --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30\
// RUN: --no-cuda-gpu-arch=sm_50 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes ARCH-SM30,ARCH-SM35,NOARCH-SM50 %s
// e) --no-cuda-gpu-arch=X does not affect following --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --no-cuda-gpu-arch=sm_50 --no-cuda-gpu-arch=sm_30 \
// RUN: --cuda-gpu-arch=sm_50 --cuda-gpu-arch=sm_30 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes ARCH-SM30,NOARCH-SM35,ARCH-SM50 %s
// f) --no-cuda-gpu-arch=all negates all preceding --cuda-gpu-arch=X
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-gpu-arch=all \
// RUN: --cuda-gpu-arch=sm_50 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes NOARCH-SM30,NOARCH-SM35,ARCH-SM50 %s
// g) There's no --cuda-gpu-arch=all
// RUN: %clang -### -target x86_64-linux-gnu --cuda-device-only \
// RUN: --cuda-gpu-arch=all \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefix ARCHALLERROR %s
// Verify that --[no-]cuda-include-ptx arguments are handled correctly.
// a) by default we're including PTX for all GPUs.
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
// b) --no-cuda-include-ptx=all disables PTX inclusion for all GPUs
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,NOPTX-SM30 %s
// c) --no-cuda-include-ptx=sm_XX disables PTX inclusion for that GPU only.
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-include-ptx=sm_35 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,NOPTX-SM35,PTX-SM30 %s
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-include-ptx=sm_30 \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,NOPTX-SM30 %s
// d) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=all
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-include-ptx=all --cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
// e) --cuda-include-ptx=all overrides preceding --no-cuda-include-ptx=sm_XX
// RUN: %clang -### -target x86_64-linux-gnu \
// RUN: --cuda-gpu-arch=sm_35 --cuda-gpu-arch=sm_30 \
// RUN: --no-cuda-include-ptx=sm_30 --cuda-include-ptx=all \
// RUN: -c %s 2>&1 \
// RUN: | FileCheck -check-prefixes FATBIN-COMMON,PTX-SM35,PTX-SM30 %s
// Verify -flto=thin -fwhole-program-vtables handling. This should result in
// both options being passed to the host compilation, with neither passed to
// the device compilation.
// RUN: %clang -### -target x86_64-linux-gnu -c -flto=thin -fwhole-program-vtables %s 2>&1 \
// RUN: | FileCheck -check-prefixes DEVICE,DEVICE-NOSAVE,HOST,INCLUDES-DEVICE,NOLINK,THINLTOWPD %s
// THINLTOWPD-NOT: error: invalid argument '-fwhole-program-vtables' only allowed with '-flto'
// ARCH-SM30: "-cc1"{{.*}}"-target-cpu" "sm_30"
// NOARCH-SM30-NOT: "-cc1"{{.*}}"-target-cpu" "sm_30"
// ARCH-SM35: "-cc1"{{.*}}"-target-cpu" "sm_35"
// NOARCH-SM35-NOT: "-cc1"{{.*}}"-target-cpu" "sm_35"
// ARCH-SM50: "-cc1"{{.*}}"-target-cpu" "sm_50"
// NOARCH-SM50-NOT: "-cc1"{{.*}}"-target-cpu" "sm_50"
// ARCHALLERROR: error: unsupported CUDA gpu architecture: all
// Match device-side preprocessor and compiler phases with -save-temps.
// DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// DEVICE-SAVE-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// DEVICE-SAVE-SAME: "-fcuda-is-device"
// DEVICE-SAVE-SAME: "-x" "cuda"
// DEVICE-SAVE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// DEVICE-SAVE-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// DEVICE-SAVE-SAME: "-fcuda-is-device"
// DEVICE-SAVE-SAME: "-x" "cuda-cpp-output"
// Match the job that produces PTX assembly.
// DEVICE: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// DEVICE-NOSAVE-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// THINLTOWPD-NOT: "-flto=thin"
// DEVICE-SAME: "-fcuda-is-device"
// DEVICE-SM30-SAME: "-target-cpu" "sm_30"
// THINLTOWPD-NOT: "-fwhole-program-vtables"
// DEVICE-SAME: "-o" "[[PTXFILE:[^"]*]]"
// DEVICE-NOSAVE-SAME: "-x" "cuda"
// DEVICE-SAVE-SAME: "-x" "ir"
// Match the call to ptxas (which assembles PTX to SASS).
// DEVICE:ptxas
// DEVICE-SM30-DAG: "--gpu-name" "sm_30"
// DEVICE-DAG: "--output-file" "[[CUBINFILE:[^"]*]]"
// DEVICE-DAG: "[[PTXFILE]]"
// Match another device-side compilation.
// DEVICE2: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// DEVICE2-SAME: "-aux-triple" "x86_64-unknown-linux-gnu"
// DEVICE2-SAME: "-fcuda-is-device"
// DEVICE2-SM35-SAME: "-target-cpu" "sm_35"
// DEVICE2-SAME: "-o" "[[PTXFILE2:[^"]*]]"
// DEVICE2-SAME: "-x" "cuda"
// Match another call to ptxas.
// DEVICE2: ptxas
// DEVICE2-SM35-DAG: "--gpu-name" "sm_35"
// DEVICE2-DAG: "--output-file" "[[CUBINFILE2:[^"]*]]"
// DEVICE2-DAG: "[[PTXFILE2]]"
// Match no device-side compilation.
// NODEVICE-NOT: "-cc1" "-triple" "nvptx64-nvidia-cuda"
// NODEVICE-NOT: "-fcuda-is-device"
// INCLUDES-DEVICE:fatbinary
// INCLUDES-DEVICE-DAG: "--create" "[[FATBINARY:[^"]*]]"
// INCLUDES-DEVICE-DAG: "--image=profile=sm_{{[0-9]+}},file=[[CUBINFILE]]"
// INCLUDES-DEVICE-DAG: "--image=profile=compute_{{[0-9]+}},file=[[PTXFILE]]"
// INCLUDES-DEVICE2-DAG: "--image=profile=sm_{{[0-9]+}},file=[[CUBINFILE2]]"
// INCLUDES-DEVICE2-DAG: "--image=profile=compute_{{[0-9]+}},file=[[PTXFILE2]]"
// Match host-side preprocessor job with -save-temps.
// HOST-SAVE: "-cc1" "-triple" "x86_64-unknown-linux-gnu"
// HOST-SAVE-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
// HOST-SAVE-NOT: "-fcuda-is-device"
// HOST-SAVE-SAME: "-x" "cuda"
// Match host-side compilation.
// HOST: "-cc1" "-triple" "x86_64-unknown-linux-gnu"
// HOST-SAME: "-aux-triple" "nvptx64-nvidia-cuda"
// THINLTOWPD-SAME: "-flto=thin"
// HOST-NOT: "-fcuda-is-device"
// There is only one GPU binary after combining it with fatbinary!
// INCLUDES-DEVICE2-NOT: "-fcuda-include-gpubinary"
// INCLUDES-DEVICE-SAME: "-fcuda-include-gpubinary" "[[FATBINARY]]"
// There is only one GPU binary after combining it with fatbinary.
// INCLUDES-DEVICE2-NOT: "-fcuda-include-gpubinary"
// THINLTOWPD-SAME: "-fwhole-program-vtables"
// HOST-SAME: "-o" "[[HOSTOUTPUT:[^"]*]]"
// HOST-NOSAVE-SAME: "-x" "cuda"
// HOST-SAVE-SAME: "-x" "cuda-cpp-output"
// Match external assembler that uses compilation output.
// HOST-AS: "-o" "{{.*}}.o" "[[HOSTOUTPUT]]"
// Match no GPU code inclusion.
// NOINCLUDES-DEVICE-NOT: "-fcuda-include-gpubinary"
// Match no host compilation.
// NOHOST-NOT: "-cc1" "-triple"
// NOHOST-NOT: "-x" "cuda"
// Match linker.
// LINK: "{{.*}}{{ld|link}}{{(.exe)?}}"
// LINK-SAME: "[[HOSTOUTPUT]]"
// Match no linker.
// NOLINK-NOT: "{{.*}}{{ld|link}}{{(.exe)?}}"
// FATBIN-COMMON:fatbinary
// FATBIN-COMMON: "--create" "[[FATBINARY:[^"]*]]"
// FATBIN-COMMON: "--image=profile=sm_30,file=
// PTX-SM30: "--image=profile=compute_30,file=
// NOPTX-SM30-NOT: "--image=profile=compute_30,file=
// FATBIN-COMMON: "--image=profile=sm_35,file=
// PTX-SM35: "--image=profile=compute_35,file=
// NOPTX-SM35-NOT: "--image=profile=compute_35,file=
|
