-
Notifications
You must be signed in to change notification settings - Fork 787
[SYCL] Enable useful (not random) output from stream #737
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
+328
−112
Merged
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This function is weird.. Why do we allocate 80% of local size? In what situation we can exceed 80% of local size and what happens in this case? If we lose some data, can a perfectly legal SYCL code hit this?
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Because I think it is not good to allocate 100% of local mem, then it will not be possible to use local mem for other purposes inside the kernel. If [# work items running in parallel] * [flush buffer size provided by user] exceeds 80% of local memory then data for work items that don't have flush buffer will not be printed. But as far as I know maximum number of work items in work group for each device is defined, so this number could not be too big. Theoretically user can provide any flush buffer size, but I am not sure that any implementation can handle any input provided by user. Probably we can write an error message if user provided too big flush buffer size ( if allocated local memory is not enough).
This design (to use local memory) was discussed with @rolandschulz and @dbabokin.
@rolandschulz @dbabokin Could you please also provide your input regarding this question?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you defer this computation somehow till after the run-time has chosen the wg-size? Or do we always choose max WG-size/GlobalSize so this matches?
We should throw an exception if the flush buffer is too big.