Skip to content

[ET-VK][Ops] aten.convolution (Transpose) #2883

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from

Conversation

jorgep31415
Copy link
Contributor

@jorgep31415 jorgep31415 commented Apr 5, 2024

Stack from ghstack (oldest at bottom):

Summary (cases handled)

We introduce support for the convolution cases covered by ATen-VK's transpose implementation. This is achieved by

We also include resizing support for dynamic shapes. Note that only height and width of the input can vary.

Cases not handled

The implementation is on-par with ATen-VK's Transpose. This means the following cases are missing:

  1. Groups G > 1.
  2. Batch (input) N > 1.
  3. Dilation > 1.

Differential Revision: D55667336

## Summary (cases handled)

We introduce support for the convolution cases covered by ATen-VK's transpose implementation. This is achieved by
- reusing the existing [`conv_transpose2d.glsl`](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/glsl/conv_transpose2d.glsl), and
- [moving special weights prepacking from CPU](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/ops/Convolution.cpp#L134-L235) to the GPU in `conv_transpose2d_prepack_weights.glsl`.

We also include resizing support for dynamic shapes. Note that only height and width of the input can vary.

## Cases not handled

The implementation is on-par with ATen-VK's Transpose. This means the following cases are missing:
1. **Groups G > 1.**
2. **Batch (input) N > 1.**
3. **Dilation > 1.**

Differential Revision: [D55667336](https://our.internmc.facebook.com/intern/diff/D55667336/)

[ghstack-poisoned]
Copy link

pytorch-bot bot commented Apr 5, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/2883

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 37e6160 with merge base d3326a2 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 5, 2024
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D55667336

## Summary (cases handled)

We introduce support for the convolution cases covered by ATen-VK's transpose implementation. This is achieved by
- reusing the existing [`conv_transpose2d.glsl`](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/glsl/conv_transpose2d.glsl), and
- [moving special weights prepacking from CPU](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/ops/Convolution.cpp#L134-L235) to the GPU in `conv_transpose2d_prepack_weights.glsl`.

We also include resizing support for dynamic shapes. Note that only height and width of the input can vary.

## Cases not handled

The implementation is on-par with ATen-VK's Transpose. This means the following cases are missing:
1. **Groups G > 1.**
2. **Batch (input) N > 1.**
3. **Dilation > 1.**

Differential Revision: [D55667336](https://our.internmc.facebook.com/intern/diff/D55667336/)

[ghstack-poisoned]
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D55667336

jorgep31415 added a commit that referenced this pull request Apr 8, 2024
Pull Request resolved: #2883

## Summary (cases handled)

We introduce support for the convolution cases covered by ATen-VK's transpose implementation. This is achieved by
- reusing the existing [`conv_transpose2d.glsl`](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/glsl/conv_transpose2d.glsl), and
- [moving special weights prepacking from CPU](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/ops/Convolution.cpp#L134-L235) to the GPU in `conv_transpose2d_prepack_weights.glsl`.

We also include resizing support for dynamic shapes. Note that only height and width of the input can vary.

## Cases not handled

The implementation is on-par with ATen-VK's Transpose. This means the following cases are missing:
1. **Groups G > 1.**
2. **Batch (input) N > 1.**
3. **Dilation > 1.**
ghstack-source-id: 221721754
@exported-using-ghexport

Differential Revision: [D55667336](https://our.internmc.facebook.com/intern/diff/D55667336/)
@SS-JIA SS-JIA self-requested a review April 9, 2024 18:56
@facebook-github-bot
Copy link
Contributor

This pull request has been merged in 8a6427e.

@mergennachin mergennachin mentioned this pull request Apr 26, 2024
kedarnath03 pushed a commit to kedarnath03/executorch that referenced this pull request Jun 25, 2025
## Summary (cases handled)

We introduce support for the convolution cases covered by ATen-VK's transpose implementation. This is achieved by
- reusing the existing [`conv_transpose2d.glsl`](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/glsl/conv_transpose2d.glsl), and
- [moving special weights prepacking from CPU](https://github.com/pytorch/pytorch/blob/09c72eaa3f69f90402c86a30abf4fc621298578c/aten/src/ATen/native/vulkan/ops/Convolution.cpp#L134-L235) to the GPU in `conv_transpose2d_prepack_weights.glsl`.

We also include resizing support for dynamic shapes. Note that only height and width of the input can vary.

## Cases not handled

The implementation is on-par with ATen-VK's Transpose. This means the following cases are missing:
1. **Groups G > 1.**
2. **Batch (input) N > 1.**
3. **Dilation > 1.**

Differential Revision: [D55667336](https://our.internmc.facebook.com/intern/diff/D55667336/)

ghstack-source-id: 221526248
Pull Request resolved: pytorch/executorch#2883
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported Merged
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants