Intel GPU: Enable SYCL building system #1671
Draft
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 is the programming solution dominated by Intel. SYCL has been adopted widely to enable compute kernels for Intel GPUs, such as PyTorch. CUDA has been a supported language in CMAKE, e.g. enable_langauge(CUDA). Unlike CUDA, SYCL requires more CMAKE codes to enable building system. The SYCL building system in the commit is the general part ported from PyTorch. Usage: 1. mkdir build && cd build 2. cmake -DCOMPUTE_BACKEND=xpu [-DBUILD_TEST_SYCL=1] .. && make BUILD_TEST_SYCL is an option for testing SYCL building system. Signed-off-by: Feng Yuan <[email protected]>
|
Are there any particular kernels we expect to implement in SYCL directly in this repo? I haven't been expecting that we'd build SYCL code for XPU here, and instead would use ops exposed in IPEX, kernels in Triton, or plain PyTorch. |
matthewdouglas
added
Low Priority
Hi @matthewdouglas , Thanks for comments. |
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Outdated suggestions cannot be applied.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.
SYCL is the programming solution dominated by Intel. SYCL has been adopted widely to enable compute kernels for Intel GPUs, such as PyTorch. CUDA has been a supported language in CMAKE, e.g. enable_langauge(CUDA). Unlike CUDA, SYCL requires more CMAKE codes to enable building system. The SYCL building system in the commit is the general part ported from PyTorch.
Usage:
BUILD_TEST_SYCL is an option for testing SYCL building system.