Enable arm64 convolution for fbgemm through the reference convolution APIs #5126
Conversation
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
Contributor
mcfi
added a commit
to mcfi/FBGEMM
that referenced
this pull request
Nov 14, 2025
… APIs (pytorch#5126) Summary: X-link: facebookresearch/FBGEMM#2128 This diff adds convolution support to arm64 fbgemm by reusing existing reference implementations. 1. Introduced conv_requant_ref that invokes the reference conv_ref and requantize_u8acc32_ref and added it in places where only x86 conv implementations are available. 2. Changed weights matrix packing to basically do nothing or call transposeConvWeights. This diff unblocks fbgemm users' convolution code on Arm64. We plan to add follow-up diffs to optimize each kind of convolution (e.g., depthwise, directconv, etc.) Differential Revision: D86548699
mcfi
force-pushed
the
export-D86548699
branch
from
9291333 to
f3e4f2a
Compare
mcfi
added a commit
to mcfi/FBGEMM
that referenced
this pull request
Nov 14, 2025
… APIs (pytorch#5126) Summary: X-link: facebookresearch/FBGEMM#2128 This diff adds convolution support to arm64 fbgemm by reusing existing reference implementations. 1. Introduced conv_requant_ref that invokes the reference conv_ref and requantize_u8acc32_ref and added it in places where only x86 conv implementations are available. 2. Changed weights matrix packing to basically do nothing or call transposeConvWeights. This diff unblocks fbgemm users' convolution code on Arm64. We plan to add follow-up diffs to optimize each kind of convolution (e.g., depthwise, directconv, etc.) Differential Revision: D86548699
mcfi
force-pushed
the
export-D86548699
branch
from
f3e4f2a to
53747f5
Compare
mcfi
added a commit
to mcfi/FBGEMM
that referenced
this pull request
Nov 15, 2025
… APIs (pytorch#5126) Summary: X-link: facebookresearch/FBGEMM#2128 This diff adds convolution support to arm64 fbgemm by reusing existing reference implementations. 1. Introduced conv_requant_ref that invokes the reference conv_ref and requantize_u8acc32_ref and added it in places where only x86 conv implementations are available. 2. Changed weights matrix packing to basically do nothing or call transposeConvWeights. This diff unblocks fbgemm users' convolution code on Arm64. We plan to add follow-up diffs to optimize each kind of convolution (e.g., depthwise, directconv, etc.) Differential Revision: D86548699
mcfi
force-pushed
the
export-D86548699
branch
from
53747f5 to
a189d92
Compare
… APIs (pytorch#5126) Summary: X-link: facebookresearch/FBGEMM#2128 This diff adds convolution support to arm64 fbgemm by reusing existing reference implementations. 1. Introduced conv_requant_ref that invokes the reference conv_ref and requantize_u8acc32_ref and added it in places where only x86 conv implementations are available. 2. Changed weights matrix packing to basically do nothing or call transposeConvWeights. This diff unblocks fbgemm users' convolution code on Arm64. We plan to add follow-up diffs to optimize each kind of convolution (e.g., depthwise, directconv, etc.) Differential Revision: D86548699
mcfi
force-pushed
the
export-D86548699
branch
from
a189d92 to
7be0f35
Compare
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.
Summary:
This diff adds convolution support to arm64 fbgemm by reusing existing reference implementations.
This diff unblocks fbgemm users' convolution code on Arm64. We plan to add follow-up diffs to optimize each kind of convolution (e.g., depthwise, directconv, etc.)
Differential Revision: D86548699