GIM 9.1.0.K: re-vendor smi lib + wire UBB node power in GIM path#78
Merged
Conversation
Re-vendor third-party/rocm/gim_amd_smi_lib to 9.1.0.K (libgim_amd_smi.so RHEL9-built GLIBC 2.34, 9.1 header, version.txt). Wire UBB node power in the GIM host-side walker, mirroring the non-GIM amdsmi path: stats->ubb_power from power_info.ubb_power, and ubb_power_cap from npm_info.ubb_power_threshold (9.1.0.K added the ubb_power_threshold field to amdsmi_npm_info_t and ubb_power to amdsmi_power_info_t). Decodes to 0 on GPUs that don't expose it (pre-MI350X). amdsmi_metric_name_t expands 73 -> 171 entries (additive); the positional metric-stream walker recompiles against the new header, unhandled entries fall through to the existing default (sentinel).
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Re-vendor third-party/rocm/gim_amd_smi_lib to 9.1.0.K (libgim_amd_smi.so RHEL9-built GLIBC 2.34, 9.1 header, version.txt).
Wire UBB node power in the GIM host-side walker, mirroring the non-GIM amdsmi path: stats->ubb_power from power_info.ubb_power, and ubb_power_cap from npm_info.ubb_power_threshold (9.1.0.K added the ubb_power_threshold field to amdsmi_npm_info_t and ubb_power to amdsmi_power_info_t). Decodes to 0 on GPUs that don't expose it (pre-MI350X).
amdsmi_metric_name_t expands 73 -> 171 entries (additive); the positional metric-stream walker recompiles against the new header, unhandled entries fall through to the existing default (sentinel).
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist