Small update to gpu compiler flags to support compute capabilities 8.0 and 8.6 as well. #113
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Added complier flags for ampere gpus.
|
Thanks! Those are some extensive changes. Did you change the file yourself or you used some other file (e.g. by NVIDIA) as template? |
|
Apologies for my delayed reply. It is mostly copied from the FindCUDA module of the CMAKE github and as given by nvidia cuda documentation. I didn't write it. I tried it out on our A100 gpu which are with compute capabilities 8.0. On average it only speed up by 1.01 using the above code. |
|
Some of the changes I don't understand. Does it work on older architectures as well? |
|
The oldest GPU I have access to is GTX1080 and it works on it. But not sure about even older gpus. |
lorenzo-rovigatti
added a commit
that referenced
this pull request
Aug 30, 2024
The bug would prevent compilation with `-DCUDA=On -D -DCUDA_COMMON_ARCH=OFF`
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This adds compiler flags for Ampere gpu with compute capabilities 8.0 and 8.6 as provided in https://github.com/Kitware/CMake/blob/master/Modules/FindCUDA/select_compute_arch.cmake.