lib/x86/adler32: refactor and improve implementations #348
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
ebiggers
force-pushed
the
dev
branch
2 times, most recently
from
c57ef9e to
4fa0398
Compare
- Increase size of test file to 250 MB for more accurate results - Disable x86-32 test by default - Support specifying extra cmake flags - Code cleanups
ebiggers
force-pushed
the
dev
branch
2 times, most recently
from
ad667b2 to
2a07d53
Compare
- Refactor the x86 implementations of Adler-32 to be organized like the x86 implementations of CRC-32, where there's an x86-specific template that expands into the different implementations. - Add an AVX512VNNI implementation using 256-bit vectors. - Increase the number of vectors processed per iteration of the inner loop of the AVX512VNNI implementations from 2 to 4. - Handle small amounts of data more efficiently. If the length is small, don't bother aligning the pointer at the beginning. Also optimize the handling of any bytes left over after the inner loop. Also avoid doing redundant reductions mod 65521. - Make the AVX-VNNI implementation dot with 1's so that all VNNI implementations use the same strategy. - Put "_x86" in the name of the functions, like what is done for CRC-32.
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Outdated suggestions cannot be applied.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.
No description provided.