Made it possible to disable GPU detection#2424
Open
philip-paul-mueller wants to merge 2 commits into
Open
Conversation
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Currently DaCe will always compile and run a test program to determine the CUDA/HIP architecture.
This is problematic because this will create a CUDA-Context and prevents parallel compilations.
The solution proposed by this PR is to introduce the
compiler.cuda.no_gpu_arch_detectionconfig variable.This key instructs CMake to not perform this inference and instead only use
compiler.cuda.{hip,cuda}_argch.An alternative solution, that would not be backwards compatible, is to repurpose
compiler.cuda.{hip,cuda}_argch.If it is given, then no auto detection will take place and the code is compiled only for the architectures listed there.
Furthermore, PR changes the defaults of
compiler.cuda.{hip,cuda}_argchwhich are now empty.This has the effect that the code is not always compiled for
60regardless if it is there or not.