Standalone: New kernels #116
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
Float32 kernel optimized for Cortex-A55r1. uint8->uint32 kernel using Armv8.2 dot product extension with generic optimizations. uint8->uint32 kernel using Armv8.2 dot product extension, optimized for Cortex-A55r1.
bjacob
added a commit
that referenced
this pull request
Oct 16, 2018
instructions (UDOT) available on newer CPUs such as Cortex-A76. This particular kernel is not tuned for one particular CPU; it does well on Cortex-A76 in particular. ARM had contributed another kernel more specifically optimized for Cortex-A55r1; it would have to be imported separately. Context: for ARM's contributions, see #116 Notice that the new kernel is not automatically enabled when the instructions are present: the user is required to also define a preprocessor token, GEMMLOWP_DOTPROD_KERNEL, to opt in to using that kernel. Rationale: avoid worsening the ODR-violations situations with more inline symbols having different definitions based on preprocessor tokens. Conveniently, this will also allow in the future to have multiple such kernels coexist, behind separate opt-in tokens.
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Outdated suggestions cannot be applied.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 pull request adds three new kernels to the standalone benchmark:
Float32 kernel optimized for Cortex-A55r1.
uint8->uint32 kernel using Armv8.2 dot product extension with generic optimizations.
uint8->uint32 kernel using Armv8.2 dot product extension, optimized for Cortex-A55r1.