Fence callbacks support in nvprof-focused connector #178
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
Note that the tool-induced fences need to be filtered out for the fence callbacks. Also, the environment variable of KOKKOSTOOLS_GLOBALFENCES needs to be accomodated for. This will coming soon.
crtrott
requested changes
Apr 20, 2023
| void kokkosp_begin_fence(const uint64_t kID) { | ||
| *kID = nextKernelID++; | ||
| currentKernel = getFocusedConnectorInfo(name, FENCE); | ||
| focusedConnectorExecuteStart(); |
There was a problem hiding this comment.
this is not necessary. What this does is turning nvtx profiling on and off. But this is only a fence anyway, so likely no CUDA operation will happen
|
I am closing this draft issue based on discussion |
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Outdated suggestions cannot be applied.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.
Fix #177.
I have added the fence callbacks in the Kokkos tool connector.
Note that the tool-induced fences need to be filtered out for the fence callbacks. Also, the environment variable of KOKKOSTOOLS_GLOBALFENCES needs to be accomodated for. This is a draft PR and I will do this soon.