Enable Windows Support for ROCm Libraries Benchmarks#2697
Merged
Conversation
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Remove Unicode characters (✓, ✗, ⚠, →, ∞) from log messages that cause UnicodeEncodeError on Windows (CP1252 encoding). Replace with ASCII text to ensure cross-platform compatibility. Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
- multiprocessing.cpu_count() for CPU core count - wmic commands for detailed CPU information (model, speed, cache, RAM) Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
To match with other benchmarks and to support windows binary files. Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Remove benchmark_runs_on parameter from ci.yml to prevent Windows benchmarks from running on PRs. Benchmarks now only execute during scheduled nightly runs (ci_nightly.yml) for both Linux and Windows. Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
geomin12
reviewed
Jan 2, 2026
Contributor
geomin12
left a comment
There was a problem hiding this comment.
looks good, just some housekeeping comments
Link TODO comments for dedicated benchmark-runs-on runners to tracking issue. Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
geomin12
reviewed
Jan 5, 2026
Contributor
geomin12
left a comment
There was a problem hiding this comment.
two more comments, then it looks good to land
Comment on lines
112
to
115
| **GPU Family Support:** | ||
|
|
||
| - **Linux:** gfx94x (MI300X/MI325X) | ||
| - **Windows:** gfx1151 (RDNA3.5) |
Contributor
There was a problem hiding this comment.
can we add the expected GPU family support for benchmarks? (if known)
Contributor
Author
There was a problem hiding this comment.
Done! Updated README.md with table showing GPU family support for benchmarks.
- Added table showing GPU family support for benchmarks across platforms - Documents which families are enabled in CI (gfx94x Linux, gfx1151 Windows) - Lists architecture-agnostic support for gfx950, gfx110x, gfx120x, gfx90x - Increased rocrand_bench timeout from 60 to 90 minutes Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
Signed-off-by: Lenine Ajagappane <Lenine.Ajagappane@amd.com>
geomin12
approved these changes
Jan 6, 2026
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
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 enables benchmark testing on Windows runners for
gfx1151, extending the existing Linux-only benchmark infrastructure to support cross-platform execution.Motivation
Currently, TheRock benchmark tests only run on Linux runners. To ensure comprehensive performance validation across all supported platforms, we need to enable benchmark testing on Windows as well. This PR extends the benchmark framework to support Windows execution, specifically targeting
gfx1151Windows runners.Technical Details
test_windows_benchmarksjob to.github/workflows/ci_windows.ymlthat mirrors the Linux benchmark implementationUnicodeEncodeErroron Windows (CP1252 encoding)test_rocrand_benchmark.pygfx1151inamdgpu_family_matrix.pyTest Plan
gfx1151Test Result
Windows Build and Benchmark Execution verified on Nightly-CI (
gfx1151).https://github.com/ROCm/TheRock/actions/runs/20466255467