Skip to content

[ET-VK] Create Pipeline layouts with push constant ranges when required #7483

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

Merged
merged 2 commits into from
Jan 3, 2025

Conversation

pytorchbot
Copy link
Collaborator

This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #7479
^ 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/160/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/160/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/159/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/160/orig
@diff-train-skip-merge

SS-JIA added 2 commits January 2, 2025 13:05
…ructor

## Context

I discovered this bug when trying to execute the `vulkan_compute_api_test` binary on Windows. Almost all the tests were failing, with compute shaders producing incorrect results. After bisecting the change, it turns out the culprit is #7015. The diff introduced an alternative templated constructor for `ParamsBuffer` which would initialize an empty UBO with a specified size instead of wrapping a pre-existing object.

The issue is that these constructors are ambiguous because they both are template constructors and both only accept one argument. Therefore, the original constructor would be called when certain callsites intended to call the new constructor. This results in a UBO being created with an incorrect size, and resulted in the tensor's metadata being passed incorrectly into a compute shader.

To fix, I added a dummy argument into the new constructor for disambiguation purposes. I also changed it so that it's not templated, since there's no reason for it to be templated.

Differential Revision: [D67770791](https://our.internmc.facebook.com/intern/diff/D67770791/)

ghstack-source-id: 260031108
Pull Request resolved: #7478
## Context

#7223 added the ability to use push constants in shaders. However, one thing the diff missed was not specifying that the compute pipeline layout needed to include a push constant upon creation. The Vulkan validation layers warns against this, and on certain GPUs such as the integrated Intel GPU on my windows laptop compute shaders will produce incorrect output.

This diff makes the change such that the compute pipeline layout will be created with a push constant block if necessary.

## Solution

Change the key of the pipeline layout cache to accept an additional push constant size field. The push constant size will be used to create the pipeline layout with a push constant block of the specified size.

Differential Revision: [D67770793](https://our.internmc.facebook.com/intern/diff/D67770793/)

ghstack-source-id: 260031109
Pull Request resolved: #7479
Copy link

pytorch-bot bot commented Jan 3, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7483

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

⏳ No Failures, 5 Pending

As of commit bd59382 with merge base d3e58b0 (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 Jan 3, 2025
Base automatically changed from gh/SS-JIA/159/orig to main January 3, 2025 00:53
@SS-JIA SS-JIA merged commit 7001ac7 into main Jan 3, 2025
43 checks passed
@SS-JIA SS-JIA deleted the gh/SS-JIA/160/orig branch January 3, 2025 00:53
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.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants