[LLVMdev] Upstream PTX backend that uses target independent code generator if possible

Michael Spencer bigcheesegs at gmail.com
Sat Aug 7 02:57:08 PDT 2010

On Fri, Aug 6, 2010 at 6:47 PM, Che-Liang Chiou <clchiou at gmail.com> wrote:
> Hi there,
> I have a working prototype of PTX backend, and I would like to
> upstream it if possible.  This backend is implemented by LLVM's target
> independent code generator framework; I think this will make it easier
> to maintain.
> I have tested this backend to translate a work-efficient parallel scan
> kernel ( http://http.developer.nvidia.com/GPUGems3/gpugems3_ch39.html
> ) into PTX code.  The generated PTX code was then executed on real
> hardware, and the result is correct.
> So far I have to hack clang to generate bitcode for this backend, but
> I will try to patch clang to parse CUDA (or OpenCL) while I am
> upstreaming this backend.

Clang already has an OpenCL front end, but I don't know what it would
take to make it work with your backend (I'm assuming there're quite a
few intrinsics that have to be dealt with).

> I am new to LLVM.  Any comments are welcome.

The GPU and multiprocessor possibilities are one of the many things
that have interested me in LLVM, and it's great to see someone working
on that.

I'm rather new here my self, so really the only other question I have
is is the code currently hosted anywhere to look at?

> Regards,
> Che-Liang

More information about the llvm-dev mailing list