[SYCL][NATIVECPU] Add Native CPU specific property mechanism and nd_range property #16152
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
PietroGhg
had a problem deploying
to
WindowsCILock
GitHub Actions
Failure
PietroGhg
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
elizabethandrews
approved these changes
Nov 21, 2024
PietroGhg
had a problem deploying
to
WindowsCILock
GitHub Actions
Error
PietroGhg
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
PietroGhg
temporarily deployed
to
WindowsCILock
GitHub Actions
Inactive
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Outdated suggestions cannot be applied.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.
This PR adds a mechanism to process Native CPU-specific kernel properties, and uses that mechanism to process a kernel property to check whether or not a kernel uses features provided by
sycl::nd_range(e.g.get_local_id, local memory,workgroup_barrier).This information is employed when enqueueing the kernel: if the kernel doesn't use
nd_rangefeatures, we can restructure the nd_range, allowing us to pack more work items into a work group, which plays well with the vectorization/scheduling process used by Native CPU.In particular this PR:
CheckNDRangeSYCLNativeCPUpass which checks if the kernels uses features from annd_rangeSYCL/native cpu propertiessection in the properties file, which will contain kernel properties specific to Native CPU.UR PR: oneapi-src/unified-runtime#2367