[Unity][Disco] Use default stream in disco #15827
Merged
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
|
cc: @junrushao @tqchen |
junrushao
approved these changes
Sep 27, 2023
junrushao
reviewed
Oct 4, 2023
Comment on lines
-148
to
-153
| deviceStream_t GetDefaultStream() { | ||
| const auto* func = tvm::runtime::Registry::Get("runtime.get_" TVM_DISCO_DEVICE_NAME "_stream"); | ||
| ICHECK(func != nullptr); | ||
| deviceStream_t stream = static_cast<deviceStream_t>((*func)().operator void*()); | ||
| return stream == nullptr ? default_stream : stream; | ||
| } |
There was a problem hiding this comment.
it seems to break cudagraph integration because cudagraph provides a default stream
junrushao
added a commit
to junrushao/tvm
that referenced
this pull request
Oct 4, 2023
This PR fixed a bug introduced in apache#15827 since which the cudagraph's stream is discarded.
junrushao
added a commit
to junrushao/tvm
that referenced
this pull request
Oct 4, 2023
This PR fixed a bug introduced in apache#15827 since which the cudagraph's stream is discarded.
jinhongyii
pushed a commit
that referenced
this pull request
Oct 5, 2023
This PR fixed a bug introduced in #15827 since which the cudagraph's stream is discarded.
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Outdated suggestions cannot be applied.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.
running on default stream and synchronizing with it is significantly faster on amd gpu than running on other stream and synchronizing that stream, so we switch to using default stream in init_ccl.
I also tested on nvidia gpu and confirmed that there's no perf regression.