[GEMM] [Tuning] Add waves_per_eu to gemm tuning
#362
Merged
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
zhanglx13
force-pushed
the
add-waves-per-eu-to-gemm-tuning
branch
from
3e77212
to
d806234
Compare
zhanglx13
force-pushed
the
add-waves-per-eu-to-gemm-tuning
branch
from
b36ec13
to
bd61bcf
Compare
jayfurmanek
approved these changes
Oct 16, 2023
scxiao
pushed a commit
that referenced
this pull request
Oct 20, 2023
* Add waves_per_eu in the tuning space * Do not allocate tensor on device during kernel compilation step * Add breakdown elapsed time * Parallelize the post-processing step * Parallelize the profile step with --ngpus * Better timing info printout
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Outdated suggestions cannot be applied.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.
And reduce tuning time by fixing a bug in the pre-compile step
More details:
Previously, the pre-compiled step is done in parallel. However, the compiled kernels are not cached. Therefore, at the tuning step, we still pay the overhead of kernel compilation.