Fix #31573, prevent ARM64 SymmQgemm int16 overflow - #32057
Draft
Sylvester Kaczmarek (sylvesterkaczmarek) wants to merge 1 commit into
Draft
Fix #31573, prevent ARM64 SymmQgemm int16 overflow#32057Sylvester Kaczmarek (sylvesterkaczmarek) wants to merge 1 commit into
Sylvester Kaczmarek (sylvesterkaczmarek) wants to merge 1 commit into
Conversation
Widen each 8-lane int8 product group into the int32 accumulators before multiplying the second half of the packed K block. This avoids the signed int16 overflow that occurs when two -128 * -128 products share a halfword lane. Enable the existing signed-input regression coverage on non-dotprod ARM64 now that the plain NEON path is corrected.
|
Azure Pipelines: There may be pipelines that require an authorized user to comment /azp run to run. |
Contributor
|
Sylvester Kaczmarek (@sylvesterkaczmarek) please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Widen each 8-lane int8 product group into the int32 accumulators before multiplying the second half of the packed K block. This avoids the signed int16 overflow that occurs when two -128 * -128 products share a halfword lane.
Enable the existing signed-input regression coverage on non-dotprod ARM64 now that the plain NEON path is corrected.
Description
Motivation and Context