Enable auto-vectorization of add/mul reduction loops on NEON hardware#63
Draft
raneashay wants to merge 1 commit intomicrosoft:mainfrom
Draft
Enable auto-vectorization of add/mul reduction loops on NEON hardware#63raneashay wants to merge 1 commit intomicrosoft:mainfrom
raneashay wants to merge 1 commit intomicrosoft:mainfrom
Conversation
raneashay
force-pushed
the
ashay/improve-auto-vectorization
branch
from
5ca717d to
6c4c75d
Compare
raneashay
changed the title
On NEON, this patch enables auto-vectorization of sum and product
reduction loops, thus enabling vectorization of several BLAS functions.
In particular, this patch adds strict-order NEON reduction instructions
for `{Add|Mul}ReductionV{F|D}` operations. Prior to this change,
`match_rule_supported_auto_vectorization()` blocked these operations,
preventing vectorization of reduction loops that are common in dot
products, matrix-vector multiplications, and matrix-matrix
multiplications. Additionally, this patch also adds UseSVE guards to
existing SVE reduction predicates so that they're not matched on
NEON-only hardware.
raneashay
force-pushed
the
ashay/improve-auto-vectorization
branch
from
6c4c75d to
a3491b4
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
On NEON, this patch enables auto-vectorization of sum and product
reduction loops, thus enabling vectorization of several BLAS functions.
In particular, this patch adds strict-order NEON reduction instructions
for
{Add|Mul}ReductionV{F|D}operations. Prior to this change,match_rule_supported_auto_vectorization()blocked these operations,preventing vectorization of reduction loops that are common in dot
products, matrix-vector multiplications, and matrix-matrix
multiplications. Additionally, this patch also adds UseSVE guards to
existing SVE reduction predicates so that they're not matched on
NEON-only hardware.