-
Notifications
You must be signed in to change notification settings - Fork 797
[SYCL][COMPAT] First sycl_ext_oneapi_compat implementation #9755
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
Conversation
We think that we should refactor our tests from Our tests are built upon
|
Extensions should have docs. ( llvm/sycl/extensions/experimental/* ) , especially one as extensive as this. Also, I'd like to better understand the exact use cases. The code here seems fine, but what with wrapping atomics, kernels, and even dimensions, I'd like to get a clear understanding of what this is and how/when a user would use it. |
I think we shouldn't. Not because it's an external dependency, but because both LIT and GTest are testing frameworks and it's a bad idea to mix usage of two. I think what you're looking for is Update:
But also ignore the entire |
Co-Authored-By: Gordon Brown <[email protected]> Co-Authored-By: Joe Todd <[email protected]> Co-Authored-By: Pietro Ghiglio <[email protected]> Co-Authored-By: Ruyman Reyes <[email protected]>
880ebc8
to
ea344df
Compare
Co-authored-by: tomflinda <[email protected]>
@cperkinsintel The docs are available in #9646. The extension contains quite a bit of code so we divided it in two. I think you will find there an answer for the topics you have brought up. |
We were advised to refactor the code and split it up in multiple PRs: #9976 is the first. |
This is an implementation of the experimental extension proposed in #9646.
The compat extension has two primary goals:
Improve the adoption of SYCL. The compat extension is designed to provide a familiar programming interface that resembles other popular heterogeneous programming models. By reducing the learning curve, it enables developers to leverage SYCL's power and features more easily.
Source-to-Source Translation Support. compat is also designed to facilitate automatic source-to-source translation from other heterogeneous programming models to SYCL and offer a more standardized and consistent programming interface. This feature can significantly streamline the migration and integration of existing codebases into the SYCL ecosystem.
The PR also includes testing for the
compat
extension.As we stated in the proposal PR, we are open to any suggestions, concerns, or improvements you may have, so please, let us know if you have any.