-
Notifications
You must be signed in to change notification settings - Fork 779
[SYCL][Devicelib] Implement cmath rintf wrapper with __spirv_ocl_rint #18857
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
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, we could probably remove the NVPTX/AMDGCN specific path and use the __spirv_ocl_rint
path for them as well, but we can look at that in a different patch.
In general, there is no point in adding |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Could you add a test please.
Could you point me to the wrapper that implements This PR is to support use of |
Hi, @bader and @wenju-he |
done, thanks. |
It's not actually ready yet, but I've been working on that in #18706 which will address this rint issue once completed, but it needs more work and is currently only tested for CUDA/HIP. So I think it's fine to go ahead with this PR until the header solution is ready. |
|
This PR is to support the use of std::rint in device code. Currently it
is resolved to rintf symbol. With this PR, the rintf symbol is resolved
by libdevice.