[ET-VK][ez] Restrict batch norm operator to 4D input tensors only #16460
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
added 2 commits
January 5, 2026 10:53
…exels Pull Request resolved: #16419 When the packed dimension size is not a multiple of 4, texture-backed tensors have padding elements in the last texel. For division operations, these padding regions contain 0/0 = NaN, which propagates through subsequent reduction operations and corrupts results. This fix adds conditional padding masking logic to binary_op shaders: - Introduced MASK_PADDING codegen variable to binary_op.yaml - Enabled MASK_PADDING=1 for binary_div and binary_floor_divide ops - Added GLSL preprocessor macro definition in binary_op.glsl - Implemented padding masking logic using modulo arithmetic to correctly identify last texels in batch concatenation scenarios - Padding elements are explicitly zeroed out to prevent NaN propagation The implementation follows GLSL best practices by using Python preprocessing only for macro definition, keeping core shader logic as pure GLSL with standard #ifdef directives. ghstack-source-id: 331920706 Differential Revision: [D89935220](https://our.internmc.facebook.com/intern/diff/D89935220/)
Pull Request resolved: #16420 Batch normalization is typically used with 4D tensors (batch, channels, height, width) in convolutional neural networks. This change adds input validation to ensure batch norm is only lowered to the Vulkan backend when the input tensor is 4-dimensional. For other input shapes, the operator will fall back to other backends. The implementation follows the same pattern as the convolution operator, using an `are_node_inputs_supported_fn` callback to validate input shapes during graph partitioning. This prevents potential issues with batch norm on unsupported tensor shapes and makes the operator requirements explicit. ghstack-source-id: 331920708 @exported-using-ghexport Differential Revision: [D89935219](https://our.internmc.facebook.com/intern/diff/D89935219/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16460
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 2 New Failures, 24 PendingAs of commit aac499f with merge base c730feb ( NEW FAILURES - The following jobs have failed:
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
SS-JIA
approved these changes
Jan 5, 2026
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: #16420 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/391/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/391/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/390/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/391/orig
Differential Revision: D89935219
@diff-train-skip-merge