Activate the cuBLAS workaround by checking the cuBLAS version at runtime (ported to 22.05)#246
Merged
magnatelee merged 1 commit intonv-legate:branch-22.05from Mar 30, 2022
Conversation
ipdemes
pushed a commit
to ipdemes/cunumeric
that referenced
this pull request
Jun 7, 2022
* Utility methods to construct futures from buffers or cdata * Use NVML to check if the CUDA driver has a fix for GH nv-legate#374 * Use barriers at the beginning of NCCL tasks to work around a driver bug * Install Legion C util as it's now used by the core * Rename the parameter to match the definition * Use a CUDA driver call for the version check * Add some note on what the barrier is intended to do
manopapad
pushed a commit
that referenced
this pull request
Nov 17, 2024
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR is to use the cuBLAS version at runtime to activate the workaround for a known matrix-vector multiplication bug in cuBLAS. Previously, the workaround was guarded by a macro, which works only when cuNumeric was built from source on the target environment.