Fix gamma accuracy gap compared to scipy #1608
Open
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
There was a problem hiding this comment.
Pull Request Overview
This PR aims to resolve the gamma accuracy gap compared to scipy by adjusting two key parameters in the XPU distributions.
- Reduced the max threads per block for the gamma kernel from 512 to 256.
- Changed the seed parameter for the random engine in launch_gamma_kernel from 42 to 10.
Comments suppressed due to low confidence (1)
src/ATen/native/xpu/sycl/Distributions.cpp:176
- Reducing the max_threads_per_block from 512 to 256 may affect kernel performance; please ensure this change is validated across different XPU configurations.
/*max_threads_per_block=*/256
EikanWang
requested changes
Apr 26, 2025
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Outdated suggestions cannot be applied.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.
Resolve #1163. This PR aims to resolve the gamma accuracy gap compared to scipy by adjusting two key parameters in the XPU distributions. Motivation: Misaligned key parameters can cause computation differences with CUDA, which may lead to failures in CUDA bias cases. We have decided to follow these parameters.