[SYCL] Fix AMD GPU architecture detection#22670
Open
zjin-lcf wants to merge 1 commit into
Open
Conversation
get_architecture() stripped the feature-suffix (e.g. ":sramecc+:xnack-")
from the device version string using string_view::substr, but then passed
the view's .data() to a helper taking a const char*. Since .data() points
into the original, non-truncated buffer, the lookup compared against the
full "gfx942:sramecc+:xnack-" string and never matched, yielding
architecture::unknown for AMD GPUs whose gcnArchName carries feature flags.
NVIDIA is unaffected because its version string ("7.5" style) has no ':'
to truncate. Take a std::string_view in the helper and pass the bounded
substring so the comparison respects the truncation.
Co-authored-by: Cursor <cursoragent@cursor.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
get_architecture() stripped the feature-suffix (e.g. ":sramecc+:xnack-") from the device version string using string_view::substr, but then passed the view's .data() to a helper taking a const char*. Since .data() points into the original, non-truncated buffer, the lookup compared against the full "gfx942:sramecc+:xnack-" string and never matched, yielding architecture::unknown for AMD GPUs whose gcnArchName carries feature flags.