[refactor] [CUDA] Add traced_records_ for KernelProfilerBase, refactoring KernelProfilerCUDA::sync() #2909
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
…ring KernelProfilerCUDA::sync()
|
/format |
|
FYI, most of the changes are in |
k-ye
approved these changes
Sep 10, 2021
| struct KernelProfileRecord { | ||
| struct KernelProfileTracedRecord { | ||
| std::string name; | ||
| float kernel_elapsed_time_in_ms{0.0}; |
There was a problem hiding this comment.
TODO: In the future we can use a more accurate type to denote time and duration, e.g. std::chrono::duration
|
/format |
This was referenced Sep 11, 2021
Merged
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Outdated suggestions cannot be applied.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.
Related issue = #2902
Concisely describe the proposed feature
Taichi counts profiling records and stores the results in
KernelProfileRecorddirectly (StatisticalResult).But didn't allocate space to store raw data (TracedRecord).
Code in
KernelProfilerCUDA::sync()is somewhat complicatedDescribe the solution you'd like
Add a new structure,
KernelProfileTracedRecordto store traced records.Rename the old structure from
KernelProfileRecordtoKernelProfileStatisticalResultDecouple the code in
KernelProfilerCUDA::sync()into 5 parts: