Fix counter collection inconsistency with rocprofv3 #589
+5
−4
Conversation
This file contains 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
* Fix post analysis gui in standalone binary * Add post analysis gui assets and required server libraries for GUI server and web page * Add port forwarding to docker test compose * Update README me to use `docker compose up` instead of `docker compose run` to run containers with port forwarding and to leverage other functionalities of docker compose
ywang103-amd
approved these changes
Mar 10, 2025
vedithal-amd
approved these changes
Mar 10, 2025
src/rocprof_compute_soc/soc_base.py
Outdated
| def using_v3(): | ||
| return "ROCPROF" in os.environ.keys() and os.environ["ROCPROF"] == "rocprofv3" | ||
| return "ROCPROF" in os.environ.keys() and "rocprofv3" in os.environ["ROCPROF"] |
There was a problem hiding this comment.
Just curious as to why does this hack do substring match?
There was a problem hiding this comment.
I get it now, ROCPROF env. var. will contain the path to rocprofv3, in that case should we use os.environ["ROCPROF"].endswith("rocprofv3")
| @@ -209,7 +209,8 @@ def create_single_df_pmc(raw_data_dir, node_name, kernel_verbose, verbose): | |||
| dfs.append(tmp_df) | |||
| coll_levels.append(f[:-4]) | |||
|
|
|||
| final_df = pd.concat(dfs, keys=coll_levels, axis=1, copy=False) | |||
| # TODO: double check the case if all tmp_df.shape[0] are not on the same page | |||
| final_df = pd.concat(dfs, keys=coll_levels, axis=1, join="inner", copy=False) | |||
There was a problem hiding this comment.
As discussed in the meeting, inner join based on index is the only option we have since kernel name and dispatch ids might be non-deterministic
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.
For some case, we noticed collected total row numbers are not the same across all perfmon csv files:
pmc_perf.csv, SQ_IFETCH_LEVEL.csv, SQ_INST_LEVEL_LDS.csv, SQ_INST_LEVEL_SMEM.csv, SQ_INST_LEVEL_VMEM.csv.
The quick solution is: inner join if collected csv are not on the same page.
We might need to dig into and check the root reason.