JIT: Optimize pmovmaskb with a named vector constant #3497
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
I was looking at some other JIT overheads and this cropped up as some overhead. Instead of materializing a constant using mov+movk+movk+movk, load it from the named vector constant array. In a micro-benchmark this improved performance by 34%. In bytemark this improved on subbench by 0.82%
Sonicadvance1
force-pushed
the
movmaskb_constant
branch
from
ade3792 to
20da1e4
Compare
alyssarosenzweig
approved these changes
Mar 18, 2024
|
I can't think of a good way to do that in NEON either. SVE does have the INDEX instruction, but even with that, generating the 64-bit constant would take three instructions. So it doesn't seem like it would be better than this PR's approach. |
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Outdated suggestions cannot be applied.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.
I was looking at some other JIT overheads and this cropped up as some
overhead. Instead of materializing a constant using mov+movk+movk+movk,
load it from the named vector constant array.
In a micro-benchmark this improved performance by 34%.
In bytemark this improved on subbench by 0.82%