[llvm-dev] [AMDGPU] non-hsa intrinsic with hsa target

[李弘宇 via llvm-dev]

Hi,

Thank you for your prompt response. I'll see the implementation in the hcc.

Li

On Sun, Mar 6, 2016 at 6:28 AM, Matt Arsenault <arsenm2 at gmail.com> wrote:

>
> On Mar 5, 2016, at 09:46, Liu Xin via llvm-dev <llvm-dev at lists.llvm.org>
> wrote:
>
> I never worked on OpenCL+HSA. I just wonder if libclc supports HSA.
>
>
> It does not currently, and only supports Clover’s ABI. The reason there
> are still r600 related intrinsics being used for workitems is mostly
> because I haven’t gotten around to fixing it. Clover should be reading
> these from an offset from the kernel argument pointer rather than having
> special case intrinsics, or it could start putting arguments somewhere else.
>
>
> HSA RT uses 'hsa_kernel_dispatch_packet_t' to get know workgroup size and
> grid size. so far, I didn't see hsa-specific implementation appears in
> libclc.
>
>
> The Mesa ABI reads items out of a hidden kernel argument area before the
> true arguments, while HSA reads from the dispatch packet pointer, which has
> an intrinsic for it. You can see how these are implemented here:
>
> https://bitbucket.org/multicoreware/hcc/src/33432be0ab37668e55f1f534294d7525587518a4/lib/hsail-amdgpu-wrapper.ll?at=master&fileviewer=file-view-default
>
> -Matt
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20160306/db1965d6/attachment.html>