Consistent gemm tests #16
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
roversch
approved these changes
Aug 5, 2024
mkatliar
force-pushed
the
panel_gemm
branch
2 times, most recently
from
e7c50aa to
d53768d
Compare
|
@roversch please re-check that |
roversch
reviewed
Aug 12, 2024
roversch
reviewed
Aug 12, 2024
Comment on lines
+55
to
+60
| randomize(a); | ||
| randomize(b); | ||
| randomize(c); | ||
|
|
||
| // libxsmm behaves upredictably with alpha != 1. || beta != 1. | ||
| Real const alpha = 1., beta = 1.; |
There was a problem hiding this comment.
Quite some duplication. I would refactor into its own setup function or so.
There was a problem hiding this comment.
Yes, there is a lot of duplicated code in benchmarks, not only here. I have created the issue #25 to address this problem later.
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Outdated suggestions cannot be applied.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.
Made
gemmtests consistent:D = alpha * op1(A) * op2(B) + beta * Cis used or implementations that support out-of-placegemmC = alpha * op1(A) * op2(B) + beta * Cis used or implementations that support in-placegemmonlyop1andop2are chosen as "transpose" or "don't transpose" depending on what we think is fastest for each implementationalpha = 1.andbeta = 1.forlibxsmm, because otherwise it either crashes or returns in 0 time.