[ET-VK] Replace Uniform buffers with push constants for view op #7319
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
…ta in DispatchNode. Pull Request resolved: #7223 This diff adds a new class called `PushConstantDataInfo` to the `DispatchNode` class in the Vulkan backend for Executorch. This class represents a push constant data entry, which can either be a shared pointer to a tensor's uniform data with an attribute or data with a maximum size of 16 bytes. The `write` method is also added to this class, which writes the data to a destination buffer. ghstack-source-id: 257899587 @exported-using-ghexport Differential Revision: [D66796049](https://our.internmc.facebook.com/intern/diff/D66796049/)
…tantDataInfo for various attributes of a tensor. Pull Request resolved: #7224 This diff adds convenience functions in the Compute graph to get PushConstantDataInfo for various attributes of a tensor. ghstack-source-id: 257899588 @exported-using-ghexport Differential Revision: [D66853502](https://our.internmc.facebook.com/intern/diff/D66853502/)
Pull Request resolved: #7229 This diff replaces uniform buffers with push constants for view op in the Vulkan backend of Executorch. The changes include updating the GLSL code to use push constants instead of uniform buffers and updating the C++ code to pass the sizes as push constants to the shader. ghstack-source-id: 257899594 @exported-using-ghexport Differential Revision: [D66733658](https://our.internmc.facebook.com/intern/diff/D66733658/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7319
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit b005b8c with merge base de74961 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kirklandsign
approved these changes
Dec 16, 2024
kirklandsign
added
the
release notes: backends [DO NOT USE]
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: #7229
^ 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/trivedivivek/24/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/24/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/trivedivivek/23/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/trivedivivek/24/orig
@diff-train-skip-merge