SWDEV-537865 - Don't return zero for platforms with only a single CU #625
+12
−12
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
12 tasks
ammallya
pushed a commit
that referenced
this pull request
Nov 17, 2025
…625) Increased the AMDSMI_MAX_DEVICES to 64 to accomodate all devices in CPX mode. The link type has been modified in amd-smi to match with rocm-smi types, updated the same for drm tests. --------- Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
ammallya
pushed a commit
that referenced
this pull request
Nov 18, 2025
…625) Increased the AMDSMI_MAX_DEVICES to 64 to accomodate all devices in CPX mode. The link type has been modified in amd-smi to match with rocm-smi types, updated the same for drm tests. --------- Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com> [ROCm/amdsmi commit: 6715c5a]
ammallya
pushed a commit
that referenced
this pull request
Nov 21, 2025
…625) Increased the AMDSMI_MAX_DEVICES to 64 to accomodate all devices in CPX mode. The link type has been modified in amd-smi to match with rocm-smi types, updated the same for drm tests. --------- Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com> [ROCm/amdsmi commit: 6715c5a]
sruscica
force-pushed
the
import/develop/gnifAMD_hip-tests/SWDEV-537865
branch
from
432bb47 to
6cb93ce
Compare
gandryey
approved these changes
Jan 20, 2026
sruscica
force-pushed
the
import/develop/gnifAMD_hip-tests/SWDEV-537865
branch
2 times, most recently
from
e38f057 to
30632df
Compare
This can occur on platforms that operates in WGP (work group processor) mode in which the CUs are grouped in pairs so there are effectively half as many multiprocessing units.
sruscica
force-pushed
the
import/develop/gnifAMD_hip-tests/SWDEV-537865
branch
from
30632df to
d73f82e
Compare
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 can occur on platforms that operates in WGP (work group processor) mode in which the CUs are grouped in pairs so there are effectively half as many multiprocessing units.
Associated JIRA ticket number/Github issue number
Fixes SWDEV-537865
What type of PR is this? (check all applicable)
What were the changes?
Clamp the results from
GenerateThreadDimensions,GenerateBlockDimensions,GenerateThreadDimensionsForShuffleandGenerateBlockDimensionsForShuffleto prevent invalid zero values whenmultiProcessorCountreturns 1.Why are these changes needed?
Fixes divide by zero errors and invalid parameter errors.
Updated CHANGELOG?
Added/Updated documentation?
Additional Checks
🔁 Imported from ROCm/hip-tests#477
🧑💻 Originally authored by @gnifAMD