Howto pass flag to nvcc compiler in CMAKE
I have a C project in Cmake in which I have embedded cuda kernel module.
I want to pass --ptxas-options=-v only to nvcc in-order to view
Number of registers usage per thread and
shared Memory usage per block.
By searching on howto pass flags to nvcc in Cmake, I came across a solution
add_compile_options(myprog
PRIVATE
$<$<COMPILE_LANGUAGE:C>:-Wall>
$<$<COMPILE_LANGUAGE:CUDA>:-arch=sm_20 -ptxas-options=-v>
)
but this didn't show me the above properties. I think these flags aren't passed to nvcc properly.
How can I pass --ptxas-options=-v to my nvcc compiler ?
cmake cuda nvcc
asked Nov 12 '18 at 5:33
Nouman Tajik
319
add a comment |
I have a C project in Cmake in which I have embedded cuda kernel module.
I want to pass --ptxas-options=-v only to nvcc in-order to view
Number of registers usage per thread and
shared Memory usage per block.
By searching on howto pass flags to nvcc in Cmake, I came across a solution
add_compile_options(myprog
PRIVATE
$<$<COMPILE_LANGUAGE:C>:-Wall>
$<$<COMPILE_LANGUAGE:CUDA>:-arch=sm_20 -ptxas-options=-v>
)
but this didn't show me the above properties. I think these flags aren't passed to nvcc properly.
How can I pass --ptxas-options=-v to my nvcc compiler ?
cmake cuda nvcc
asked Nov 12 '18 at 5:33
Nouman Tajik
319
1
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02
add a comment |
I have a C project in Cmake in which I have embedded cuda kernel module.
I want to pass --ptxas-options=-v only to nvcc in-order to view
Number of registers usage per thread and
shared Memory usage per block.
By searching on howto pass flags to nvcc in Cmake, I came across a solution
add_compile_options(myprog
PRIVATE
$<$<COMPILE_LANGUAGE:C>:-Wall>
$<$<COMPILE_LANGUAGE:CUDA>:-arch=sm_20 -ptxas-options=-v>
)
but this didn't show me the above properties. I think these flags aren't passed to nvcc properly.
How can I pass --ptxas-options=-v to my nvcc compiler ?
cmake cuda nvcc
asked Nov 12 '18 at 5:33
Nouman Tajik
319
I have a C project in Cmake in which I have embedded cuda kernel module.
I want to pass --ptxas-options=-v only to nvcc in-order to view
Number of registers usage per thread and
shared Memory usage per block.
By searching on howto pass flags to nvcc in Cmake, I came across a solution
add_compile_options(myprog
PRIVATE
$<$<COMPILE_LANGUAGE:C>:-Wall>
$<$<COMPILE_LANGUAGE:CUDA>:-arch=sm_20 -ptxas-options=-v>
)
but this didn't show me the above properties. I think these flags aren't passed to nvcc properly.
How can I pass --ptxas-options=-v to my nvcc compiler ?
cmake cuda nvcc
cmake cuda nvcc
asked Nov 12 '18 at 5:33
Nouman Tajik
319
asked Nov 12 '18 at 5:33
Nouman Tajik
319
edited Nov 15 '18 at 10:52
asked Nov 12 '18 at 5:33
Nouman Tajik
319
asked Nov 12 '18 at 5:33
Nouman Tajik
319
asked Nov 12 '18 at 5:33
Nouman Tajik
319
319
1
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02
add a comment |
1
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02
1
1
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02
add a comment |
3 Answers
3
active
oldest
votes
The newer approach of cmake cuda sets some other variables. Check the docs here.
What we need is to set CMAKE_<LANG>_FLAGS, which actually CMAKE_CUDA_FLAGS here.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --ptxas-options=-v")
answered Nov 13 '18 at 8:50
halfelf
6,46993146
add a comment |
The proper way to set CUDA flags only on a target is
target_compile_options(<my_target> PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:my_cuda_option>)
This will set the option, via the generator expression, only for files which are compiled for the CUDA language.
Using CMAKE_CUDA_FLAGS as suggested by the other answer sets a global property for all targets, which might or might not be the right approach depending on the use-case.
answered Nov 15 '18 at 9:05
havogt
1,53011321
add a comment |
How about?...
find_package( CUDA REQUIRED )
set( CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "--ptxas-options=-v" )
include_directories( ${CUDA_INCLUDE_DIRS} )
cuda_add_library( kernel_lib ${sources} )
You can check also the CMake CUDA documentation online... https://cmake.org/cmake/help/latest/module/FindCUDA.html
answered Nov 12 '18 at 8:31
KlingonJoe
508414
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
add a comment |
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);
StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});
function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});
}
});
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53256405%2fhowto-pass-flag-to-nvcc-compiler-in-cmake%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
3 Answers
3
active
oldest
votes
3 Answers
3
active
oldest
votes
active
oldest
votes
active
oldest
votes
The newer approach of cmake cuda sets some other variables. Check the docs here.
What we need is to set CMAKE_<LANG>_FLAGS, which actually CMAKE_CUDA_FLAGS here.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --ptxas-options=-v")
answered Nov 13 '18 at 8:50
halfelf
6,46993146
add a comment |
The newer approach of cmake cuda sets some other variables. Check the docs here.
What we need is to set CMAKE_<LANG>_FLAGS, which actually CMAKE_CUDA_FLAGS here.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --ptxas-options=-v")
answered Nov 13 '18 at 8:50
halfelf
6,46993146
add a comment |
The newer approach of cmake cuda sets some other variables. Check the docs here.
What we need is to set CMAKE_<LANG>_FLAGS, which actually CMAKE_CUDA_FLAGS here.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --ptxas-options=-v")
answered Nov 13 '18 at 8:50
halfelf
6,46993146
The newer approach of cmake cuda sets some other variables. Check the docs here.
What we need is to set CMAKE_<LANG>_FLAGS, which actually CMAKE_CUDA_FLAGS here.
set(CMAKE_CUDA_FLAGS "${CMAKE_CUDA_FLAGS} --ptxas-options=-v")
answered Nov 13 '18 at 8:50
halfelf
6,46993146
edited Nov 19 '18 at 5:47
answered Nov 13 '18 at 8:50
halfelf
6,46993146
answered Nov 13 '18 at 8:50
halfelf
6,46993146
answered Nov 13 '18 at 8:50
halfelf
6,46993146
6,46993146
add a comment |
add a comment |
The proper way to set CUDA flags only on a target is
target_compile_options(<my_target> PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:my_cuda_option>)
This will set the option, via the generator expression, only for files which are compiled for the CUDA language.
Using CMAKE_CUDA_FLAGS as suggested by the other answer sets a global property for all targets, which might or might not be the right approach depending on the use-case.
answered Nov 15 '18 at 9:05
havogt
1,53011321
add a comment |
The proper way to set CUDA flags only on a target is
target_compile_options(<my_target> PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:my_cuda_option>)
This will set the option, via the generator expression, only for files which are compiled for the CUDA language.
Using CMAKE_CUDA_FLAGS as suggested by the other answer sets a global property for all targets, which might or might not be the right approach depending on the use-case.
answered Nov 15 '18 at 9:05
havogt
1,53011321
add a comment |
The proper way to set CUDA flags only on a target is
target_compile_options(<my_target> PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:my_cuda_option>)
This will set the option, via the generator expression, only for files which are compiled for the CUDA language.
Using CMAKE_CUDA_FLAGS as suggested by the other answer sets a global property for all targets, which might or might not be the right approach depending on the use-case.
answered Nov 15 '18 at 9:05
havogt
1,53011321
The proper way to set CUDA flags only on a target is
target_compile_options(<my_target> PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:my_cuda_option>)
This will set the option, via the generator expression, only for files which are compiled for the CUDA language.
Using CMAKE_CUDA_FLAGS as suggested by the other answer sets a global property for all targets, which might or might not be the right approach depending on the use-case.
answered Nov 15 '18 at 9:05
havogt
1,53011321
answered Nov 15 '18 at 9:05
havogt
1,53011321
answered Nov 15 '18 at 9:05
havogt
1,53011321
answered Nov 15 '18 at 9:05
havogt
1,53011321
1,53011321
add a comment |
add a comment |
How about?...
find_package( CUDA REQUIRED )
set( CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "--ptxas-options=-v" )
include_directories( ${CUDA_INCLUDE_DIRS} )
cuda_add_library( kernel_lib ${sources} )
You can check also the CMake CUDA documentation online... https://cmake.org/cmake/help/latest/module/FindCUDA.html
answered Nov 12 '18 at 8:31
KlingonJoe
508414
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
add a comment |
How about?...
find_package( CUDA REQUIRED )
set( CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "--ptxas-options=-v" )
include_directories( ${CUDA_INCLUDE_DIRS} )
cuda_add_library( kernel_lib ${sources} )
You can check also the CMake CUDA documentation online... https://cmake.org/cmake/help/latest/module/FindCUDA.html
answered Nov 12 '18 at 8:31
KlingonJoe
508414
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
add a comment |
How about?...
find_package( CUDA REQUIRED )
set( CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "--ptxas-options=-v" )
include_directories( ${CUDA_INCLUDE_DIRS} )
cuda_add_library( kernel_lib ${sources} )
You can check also the CMake CUDA documentation online... https://cmake.org/cmake/help/latest/module/FindCUDA.html
answered Nov 12 '18 at 8:31
KlingonJoe
508414
How about?...
find_package( CUDA REQUIRED )
set( CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "--ptxas-options=-v" )
include_directories( ${CUDA_INCLUDE_DIRS} )
cuda_add_library( kernel_lib ${sources} )
You can check also the CMake CUDA documentation online... https://cmake.org/cmake/help/latest/module/FindCUDA.html
answered Nov 12 '18 at 8:31
KlingonJoe
508414
edited Nov 13 '18 at 4:54
answered Nov 12 '18 at 8:31
KlingonJoe
508414
answered Nov 12 '18 at 8:31
KlingonJoe
508414
answered Nov 12 '18 at 8:31
KlingonJoe
508414
508414
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
add a comment |
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Tried that but didn't worked.
– Nouman Tajik
Nov 12 '18 at 8:54
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
Make sure you are compiling with the cuda__add ... target commands.
– KlingonJoe
Nov 12 '18 at 9:39
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
You should also think about breaking up your CMakeLists.txt file. You have a lot of stuff in there. Consider sending some stuff to /config directory, and adding subdirectory - separating the C and CUDA code into separate directories is a good idea here.
– KlingonJoe
Nov 12 '18 at 9:46
1
1
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
I downvoted as the modern way is using the built-in CUDA language support, which the OP already uses.
– havogt
Nov 12 '18 at 21:36
add a comment |
Thanks for contributing an answer to Stack Overflow!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53256405%2fhowto-pass-flag-to-nvcc-compiler-in-cmake%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
1
I think you are looking for target_compile_options, not add_compile_options.
– havogt
Nov 12 '18 at 21:46
target_compile_options(myprog PUBLIC $<$<COMPILE_LANGUAGE:CUDA>:--ptxas-options=-v>) worked. Thank you.
– Nouman Tajik
Nov 13 '18 at 4:02