Add copy_back_func for DaCe GPU framework to fix validation #41
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
This commit adds a copy_back_func() method to the DaceFramework class to properly convert CuPy arrays back to NumPy arrays during validation. Previously, GPU arrays were not being converted, causing validation failures when comparing against NumPy reference implementations. The fix ensures that when running with dace_gpu framework, results are properly copied from GPU to CPU using cupy.asnumpy() before validation comparison. Fixes validation errors in GPU benchmarks by ensuring proper data transfer from device to host memory before numpy comparison.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Problem
The DaCe GPU framework was experiencing validation failures when comparing GPU results against NumPy reference implementations.
Root Cause
The
DaceFrameworkclass was missing acopy_back_func()method to convert CuPy GPU arrays back to NumPy CPU arrays before validation. Whilecopy_func()properly transferred data to GPU, there was no corresponding method to transfer results back to CPU for comparison.Solution
Added a
copy_back_func()method that:dace_gpucupy.asnumpy()to convert GPU arrays to NumPy arraysTesting
Changes
npbench/infrastructure/dace_framework.pycopy_back_func()method (lines 45-55)