Query out and use local size set in program IL in CL adapter. #2160
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
The CL spec wording on this is kind of fuzzy but every CL driver I tested (across intel, amd, nvidia cpu + gpu) returns an error when you have a local size set in the program source/IL and you don't specify any local size in your clEnqueueNDRangeKernel call (i.e. you leave it as NULL). Our spec does allow you to leave local size as null if you have a size specified in your program, so this change adds some logic to query out the size set in the program and passes it to the enqueue call. Initially I was concerned this might impact performance of current users but it looks like SYCL always passes a local size when calling urEnqueueKernelLaunch so it won't hit the path with the extra query.
|
LLVM PR intel/llvm#15571 |
kbenzie
approved these changes
Oct 2, 2024
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Outdated suggestions cannot be applied.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.
The CL spec wording on this is kind of fuzzy but every CL driver I tested (across intel, amd, nvidia cpu + gpu) returns an error when you have a local size set in the program source/IL and you don't specify any local size in your clEnqueueNDRangeKernel call (i.e. you leave it as NULL).
Our spec does allow you to leave local size as null if you have a size specified in your program, so this change adds some logic to query out the size set in the program and passes it to the enqueue call.
Initially I was concerned this might impact performance of current users but it looks like SYCL always passes a local size when calling urEnqueueKernelLaunch so it won't hit the path with the extra query.