Add support for fixed-width 128-bit SVE implementation #503
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
markbarnett-arm
requested changes
Sep 10, 2024
markbarnett-arm
approved these changes
Sep 11, 2024
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Outdated suggestions cannot be applied.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.
This PR adds basic support for a 128-bit SVE implementation, which is implemented as an enhanced version of the NEON SIMD library rather than as a dedicated pure SVE implementation.
Note that the NEON code was added as part of the 256-bit SVE port, so this change is purely build infrastructure to expose the new build type with the correct compiler settings.
On Neoverse V2 performance is 5% better for 4x4 blocks, improving to 10% better for 12x12 blocks. This is 1/3 from compiler-injected code, and 2/3 from using native gathers.