[ET-VK][ez] Fix to codegen caching mechanism #12272
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
## Changes * Fixed a bug with caching the generated GLSL file too early in `gen_vulkan_spv.py` ## Context Currently, the `gen_vulkan_spv.py` script saves the generated GLSL file to the cache immediately after generation. Then, when compiling the GLSL to SPIR-V, it checks the current generated GLSL file against the one in the cache. However, because of the early caching, this check will always pass, even when the GLSL template was updated and a SPIR-V recompilation is needed. The fix is to only store the generated GLSL file after the SPIR-V compilation succeeds. Differential Revision: [D77933112](https://our.internmc.facebook.com/intern/diff/D77933112/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Jul 8, 2025
## Changes * Fixed a bug with caching the generated GLSL file too early in `gen_vulkan_spv.py` ## Context Currently, the `gen_vulkan_spv.py` script saves the generated GLSL file to the cache immediately after generation. Then, when compiling the GLSL to SPIR-V, it checks the current generated GLSL file against the one in the cache. However, because of the early caching, this check will always pass, even when the GLSL template was updated and a SPIR-V recompilation is needed. The fix is to only store the generated GLSL file after the SPIR-V compilation succeeds. Differential Revision: [D77933112](https://our.internmc.facebook.com/intern/diff/D77933112/) ghstack-source-id: 294852284 Pull Request resolved: #12272
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12272
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit f800e41 with merge base ba19c75 ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D77933112 |
This PR needs a
|
kimishpatel
approved these changes
Jul 8, 2025
facebook-github-bot
merged commit 62ed54b
into
gh/SS-JIA/253/base
96 of 101 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
psiddh
pushed a commit
that referenced
this pull request
Jul 8, 2025
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #12272 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/253/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/253/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/253/orig @diff-train-skip-merge Co-authored-by: Stephen Jia <ssjia@meta.com>
Tanish2101
pushed a commit
to Tanish2101/executorch
that referenced
this pull request
Jul 9, 2025
This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: pytorch#12272 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/253/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/253/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/253/orig @diff-train-skip-merge Co-authored-by: Stephen Jia <ssjia@meta.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Stack from ghstack (oldest at bottom):
Changes
gen_vulkan_spv.pyContext
Currently, the
gen_vulkan_spv.pyscript saves the generated GLSL file to the cache immediately after generation.Then, when compiling the GLSL to SPIR-V, it checks the current generated GLSL file against the one in the cache. However, because of the early caching, this check will always pass, even when the GLSL template was updated and a SPIR-V recompilation is needed.
The fix is to only store the generated GLSL file after the SPIR-V compilation succeeds.
Differential Revision: D77933112