[cfe-dev] [llvm-dev] [Openmp-dev] RFC: Proposing an LLVM subproject for parallelism runtime and support libraries

[Chandler Carruth via cfe-dev]

On Mon, Mar 28, 2016 at 10:12 AM Mehdi Amini <mehdi.amini at apple.com> wrote:

> Hi Jason,
>
> This is probably because I'm not aware of the details, but it was claimed
> in this thread that liboffload can target Xeon Phi and Nvidia GPUs. Adding
> a new library that the compiler has to be aware of has to bring significant
> benefit.
> So it is not clear to me yet why the compiler should target two different
> runtime libraries that seems to have large chunk of overlapping
> functionalities.
> On a high-level view, these libraries seems to have the same goals with
> respect to what they provide to the compiler.
>

I think there are at least two issues:

1) Provide a high level C++ stream-based API that integrates cleanly with
compiler-generated kernel dispatch (CUDA or OpenCL, or...)

2) Support the necessary APIs for being a runtime backend for CUDA code.

I think both of these are really important and not really covered at all by
liboffload in its current form.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/cfe-dev/attachments/20160328/f19f0d8b/attachment.html>