[smoke-limbo] mix_hipmemset_omp: verify through a host copy - #2406
Merged
Conversation
The test read the omp_target_alloc'd buffer directly from host code, but that pointer refers to device memory. Whether such a read works depends on the PCIe Resizable BAR setting, so the test passed on machines where the CPU can map all of GPU memory and segfaulted where only the legacy 256MB window is visible. Two gfx1030 machines differing only in that setting disagreed, which is what surfaced it. Copy the buffer back with omp_target_memcpy before checking it. The HIP side of the test is unchanged.
abidh
requested review from
carlobertolli,
estewart08,
gregrodgers and
zGoldthorpe
as code owners
August 6, 2026 11:16
ronlieb
approved these changes
Aug 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The test read the omp_target_alloc'd buffer directly from host code, but that pointer refers to device memory. Whether such a read works depends on the PCIe Resizable BAR setting, so the test passed on machines where the CPU can map all of GPU memory and segfaulted where only the legacy 256MB window is visible. Two gfx1030 machines differing only in that setting disagreed, which is what surfaced it.
Copy the buffer back with omp_target_memcpy before checking it. The HIP side of the test is unchanged.