Detect Nvidia arch automatically also for multiple GPUs #1063
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
…ith right flags and forward compatibility
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Outdated suggestions cannot be applied.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.
This fixes #1060.
If the user does not provide
MADGRAPH_CUDA_ARCHITECTUREas a comma-separated list, we detect it usingnvidia-smi(this queries all the GPUs in the system).The output (in either case) is a comma-separated list of numbers.
We then build against each one of them (
sm_*), and also for the highest PTX, to ensure forward compatibility.In this way the makefile automatically adapts to the GPUs present in the system, even if they are of different compute capability, the binary would be able to run on those, and if CUDA will ever drop a certain compute capability, there would be no need to change the makefile.
We default to
70(V100) in case of any error incurring during detection (with logs explaining that we weren't able to detect the arch automatically).Possible enhancements: consider check for the presence of
CUDA_VISIBLE_DEVICESand selects the arch only of those visible GPUs.