[SYCL][CUDA] Add experimental cuda interop with queue #6290
Conversation
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
sycl/plugins/cuda/pi_cuda.cpp
Outdated
| "Creation of PI queue from native handle not implemented"); | ||
| return {}; | ||
|
|
||
| assert(ownNativeHandle == 1); |
There was a problem hiding this comment.
Suggested change
| assert(ownNativeHandle == 1); | |
| assert(ownNativeHandle); |
Also, cuda_piextContextCreateWithNativeHandle asserts this parameter to be false. What is the difference here?
There was a problem hiding this comment.
So this should be false for the cuda backend. make_queue was passing this as true due to the level_zero backend defaults to transferring control of the object.
I have fixed this by asserting this parameter to false, and specialising make_queue for the experimental cuda interop.
This change will also need to be made in #6288. I will make the change to that PR if this approach works for you.
|
/verify with intel/llvm-test-suite#1054 |
pvchupin
pushed a commit
to intel/llvm-test-suite
that referenced
this pull request
Jun 15, 2022
This PR add testing of the CUDA backend experimental queue interop. It checks that valid types are returned and that the created SYCL objects can be used to do work. It additionally creates a queue from an already existing sycl queue's native handle and makes sure it and the original work. Depends on: intel/llvm#6290
aelovikov-intel
pushed a commit
to aelovikov-intel/llvm
that referenced
this pull request
Mar 27, 2023
…t-suite#1054) This PR add testing of the CUDA backend experimental queue interop. It checks that valid types are returned and that the created SYCL objects can be used to do work. It additionally creates a queue from an already existing sycl queue's native handle and makes sure it and the original work. Depends on: intel#6290
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 is adds part of the CUDA-backend spec interop proposed in KhronosGroup/SYCL-Docs#197. The changes work with the CUDA CTS interop checks KhronosGroup/SYCL-CTS#336.
This PR just adds the queue interop.
llvm-test-suite: intel/llvm-test-suite#1054