[ET-VK] Store weights transposed for int8 linear #9803
Merged
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
Pull Request resolved: #9765 ## Context The weight tensor of a linear layer is usually stored in a transposed manner, such that when computing the matrix multiplication, the reduction traverses along the rows of the weight tensor as opposed to the columns. This results in a better memory access pattern for CPUs. However, for GPUs, I have found that "un-transposing" the weight tensors result in better performance. This is likely due to the fact since GPUs can compute multiple output elements in parallel, reading along the columns allows for coalescing memory loads among threads in a work group. ## Changes * Introduce the ability to transpose height and weight dims when transferring tensor data to the GPU. * Prepackthe weight tensor "un-transposed" for the int8 quantized linear operator ghstack-source-id: 275180033 @exported-using-ghexport Differential Revision: [D72066588](https://our.internmc.facebook.com/intern/diff/D72066588/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9803
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 13 PendingAs of commit de2aab6 with merge base 2aa7748 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This PR needs a
|
SS-JIA
approved these changes
Apr 1, 2025
kirklandsign
pushed a commit
that referenced
this pull request
Apr 11, 2025
## Context The weight tensor of a linear layer is usually stored in a transposed manner, such that when computing the matrix multiplication, the reduction traverses along the rows of the weight tensor as opposed to the columns. This results in a better memory access pattern for CPUs. However, for GPUs, I have found that "un-transposing" the weight tensors result in better performance. This is likely due to the fact since GPUs can compute multiple output elements in parallel, reading along the columns allows for coalescing memory loads among threads in a work group. ## Changes * Introduce the ability to transpose height and weight dims when transferring tensor data to the GPU. * Prepackthe weight tensor "un-transposed" for the int8 quantized linear operator Differential Revision: [D72066588](https://our.internmc.facebook.com/intern/diff/D72066588/)
This was referenced Apr 14, 2025
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #9765 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/204/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/204/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/204/orig
@diff-train-skip-merge