[libclc] Implement erf/erfc vector function with loop since scalar function is large #157055
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
…nction is large This PR reduces amdgcn--amdhsa.bc size by 3% and nvptx64--nvidiacl.bc size by 4%. Loop trip count is constant and backend can decide whether to unroll.
There was a problem hiding this comment.
Pull Request Overview
This PR optimizes the erf and erfc vector functions in libclc by switching from scalarization to a loop-based implementation. The change aims to reduce binary size by 3-4% for AMD and NVIDIA targets while maintaining functionality.
- Replaces scalarized vector implementations with loop-based ones for erf/erfc functions
- Introduces a new shared header for loop-based unary function scalarization
- Allows backend compilers to decide on loop unrolling for optimal performance
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| libclc/clc/lib/generic/math/clc_erfc.cl | Switches from scalarized to loop-based vector implementation |
| libclc/clc/lib/generic/math/clc_erf.cl | Switches from scalarized to loop-based vector implementation |
| libclc/clc/include/clc/shared/unary_def_scalarize_loop.inc | New shared header implementing loop-based vector scalarization |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
arsenm
approved these changes
Sep 5, 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Outdated suggestions cannot be applied.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.
This PR reduces amdgcn--amdhsa.bc size by 1.8% and nvptx64--nvidiacl.bc size by 4%.
Loop trip count is constant and backend can decide whether to unroll.