Skip to content
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

[SYCL-PTX] Add _Float16 as native type #1848

Merged
merged 2 commits into from
Jun 11, 2020

Conversation

Naghasan
Copy link
Contributor

@Naghasan Naghasan commented Jun 9, 2020

The NVPTX backend supports half and handle the insertion of conversion operations when required.

Resolves #1799

Signed-off-by: Victor Lomuller [email protected]

Copy link
Contributor

@premanandrao premanandrao left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please fix the code format errors.

Copy link
Contributor

@Fznamznon Fznamznon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you please also revert a4f4fa9 ?

@Naghasan Naghasan force-pushed the cuda_native_float_16 branch 2 times, most recently from 96b3e79 to b1ffe4a Compare June 10, 2020 16:48
Fznamznon
Fznamznon previously approved these changes Jun 10, 2020
Copy link
Contributor

@Fznamznon Fznamznon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM, thanks!

@bader
Copy link
Contributor

bader commented Jun 11, 2020

@Naghasan, could you apply clang-format to the patch, please?

Naghasan added 2 commits June 11, 2020 09:48
The NVPTX backend supports half and handle the insertion of conversion operations when required.

Signed-off-by: Victor Lomuller <[email protected]>
This reverts commit a4f4fa9.

Signed-off-by: Victor Lomuller <[email protected]>
Copy link
Contributor

@bader bader left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we should submit this patch to the community.
@Naghasan, could you do that, please?

@bader bader added the cuda CUDA back-end label Jun 11, 2020
@bader bader merged commit bc5be46 into intel:sycl Jun 11, 2020
KornevNikita pushed a commit to KornevNikita/llvm that referenced this pull request Feb 20, 2023
This specifies the right operand types for GetKernelWorkGroupSize,
GetKernelPreferredWorkGroupSizeMultiple,
GetKernelNDrangeMaxSubGroupSize,
and GetKernelNDrangeSubGroupCount to fix a function signature mismatch
bug on reverse translation.

Original commit:
KhronosGroup/SPIRV-LLVM-Translator@f0366a6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
cuda CUDA back-end
Projects
None yet
Development

Successfully merging this pull request may close these issues.

FP16 types are reported as unsupported for CUDA BE on compile time after cf6cc662
4 participants