fix: Avoid SVE codegen in SME wrapper - #1308
Open
morgolock wants to merge 1 commit into
Open
Conversation
The arm_gemm SME interleave wrappers are instantiated from the SVE source bucket so explicit SME and Streaming-SVE assembly can be assembled. That also allowed the compiler to auto-vectorize ordinary C++ wrapper code into non-streaming SVE instructions, which is invalid on CPUs that expose SME/SME2 without normal SVE. Split the affected wrapper into a protected SVE bucket. It keeps the existing SVE assembler target but disables compiler vectorization for the ordinary wrapper code. Normal SVE and SVE2 buckets stay unchanged, so multi-ISA builds still carry their runtime-dispatched implementations. Resolves MLCE-2015 Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com> Change-Id: Idea17eef5a0cd422c2510ba4dbe6882f33120591
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The arm_gemm SME interleave wrappers are instantiated from the SVE source bucket so explicit SME and Streaming-SVE assembly can be assembled. That also allowed the compiler to auto-vectorize ordinary C++ wrapper code into non-streaming SVE instructions, which is invalid on CPUs that expose SME/SME2 without normal SVE.
Split the affected wrapper into a protected SVE bucket. It keeps the existing SVE assembler target but disables compiler vectorization for the ordinary wrapper code. Normal SVE and SVE2 buckets stay unchanged, so multi-ISA builds still carry their runtime-dispatched implementations.
Resolves MLCE-2015
Change-Id: Idea17eef5a0cd422c2510ba4dbe6882f33120591