Add NEON optimizations of SynetConvolution32fNhwcGroupedBlock1x2 - #806
Merged
Conversation
Port the SSE4.1 NhwcGroupedBlock1x2 algorithm to NEON, wire Neon dispatch, extend AutoTest coverage for unaligned srcC, and document the change in release 7.2.165. Co-authored-by: Ihar Yermalayeu <ermig1979@gmail.com>
ermig1979
marked this pull request as ready for review
August 3, 2026 14:08
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
SynetConvolution32fNhwcGroupedBlock1x2inSimdNeonSynetConvolution32fNhwcGrouped.cpp, based on the existing SSE4.1 algorithm (vectorized grouped 1x2 convolution with fused bias/activation).SimdNeonSynetConvolution32f.cppand declare the class inSimdSynetConvolution32f.h.prj/vs2022/Neon.vcxproj/ filters, extendSynetConvolution32fAutoTest coverage for unalignedsrcC, and document the change under release 7.2.165 indocs/2026.html.Test plan
SynetConvolution32fAutoTest (SSE/AVX paths) including the new grouped cases../Test "-r=.." -fi=SynetConvolution32fand confirm NeonNhwcGroupedBlock1x2is selected forgroup == srcC && dstC == 2 * srcC.