GPUOP-880: SR-IOV GIM host-side metric coverage (Phase A 8.7 + Phase …#76
Open
bhatturu wants to merge 1 commit into
Open
GPUOP-880: SR-IOV GIM host-side metric coverage (Phase A 8.7 + Phase …#76bhatturu wants to merge 1 commit into
bhatturu wants to merge 1 commit into
Conversation
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
from
eb9df44 to
5266a98
Compare
spraveenio
reviewed
Jul 7, 2026
| std::unique_ptr<amdsmi_metric_t[]> *heap, | ||
| amdsmi_metric_t **out_buf, uint32_t *out_count) | ||
| { | ||
| amdsmi_status_t amdsmi_ret; |
Contributor
There was a problem hiding this comment.
follow ascending len declaration uint32_t count = 0; to the top
| amdsmi_metric_t buf_stack[kStackMax]; | ||
| std::unique_ptr<amdsmi_metric_t[]> buf_heap; | ||
| amdsmi_metric_t *buf = nullptr; | ||
| uint32_t count = 0; |
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
from
5266a98 to
bf8969a
Compare
rsrikanth86
reviewed
Jul 7, 2026
| amdsmi_gpu_metrics_t metrics_info = {}; | ||
| amdsmi_gpu_metrics_t cached_metrics = {}; | ||
| amdsmi_power_info_t power_info = {}; | ||
| amdsmi_node_handle node_handle = {}; |
Contributor
There was a problem hiding this comment.
Variables should be in increasing order of line width
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
6 times, most recently
from
f1a906a to
e0e461f
Compare
rsrikanth86
reviewed
Jul 10, 2026
| amdsmi_power_info_t power_info = {}; | ||
| amdsmi_engine_usage_t usage_info = {}; | ||
| amdsmi_node_handle node_handle = {}; | ||
| amdsmi_npm_info_t npm_info = {}; |
Contributor
There was a problem hiding this comment.
variable ordering is incorrect
rsrikanth86
reviewed
Jul 10, 2026
| gpu_handle, amdsmi_ret); | ||
| return amdsmi_ret_to_sdk_ret(amdsmi_ret); | ||
| } | ||
| if (count > AGA_GIM_MAX_METRICS) { |
Contributor
There was a problem hiding this comment.
do we need this check again? Does the count get set when metrics list is not null?
rsrikanth86
reviewed
Jul 10, 2026
| idx = m.res_instance; | ||
|
|
||
| if (unlikely(debug)) { | ||
| AGA_TRACE_ERR("gim_metrics GPU {} name {} val {} flags {} inst {}", |
Contributor
There was a problem hiding this comment.
Why do we need an env variable? Can't we make it a VERBOSE log?
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
from
e0e461f to
2b64c9a
Compare
rsrikanth86
reviewed
Jul 10, 2026
| /// \return SDK_RET_OK or error code | ||
| static sdk_ret_t | ||
| smi_walk_gpu_metrics (aga_gpu_handle_t gpu_handle, | ||
| aga_gpu_stats_t *stats) |
Contributor
There was a problem hiding this comment.
can be moved to previous line
rsrikanth86
reviewed
Jul 10, 2026
| is_inst = (m.flags & AMDSMI_METRIC_TYPE_INST); | ||
| idx = m.res_instance; | ||
|
|
||
| AGA_TRACE_DEBUG("gim_metrics GPU {} name {} val {} flags {} inst {}", |
Contributor
There was a problem hiding this comment.
Make this VERBOSE. Also make the log more readable, we cannot have _ and is the last field in the log supposed to be instantaneous or index? Make the log something like "GPU {} metrics name {} value {} flags {} ..."
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
from
2b64c9a to
ed0b469
Compare
bhatturu
force-pushed
the
feat/gpuop-880-sriov-gim-coverage
branch
from
ed0b469 to
52132fc
Compare
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
3 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.
…B 9.0.0.K)
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist