2 Replies Latest reply on Nov 10, 2008 3:29 PM by MicahVillmow

    GPUware C 0.5 test release

    macdonc

      The GPUware C compiler allows one to code in a C-like language to construct AMD GPU kernel calls. It allows one to program with AMD's CAL, to produce high performance software, and still code kernels in a high level language. The AMD IL produced by the compiler is very readable, and can be easily modified by hand.

      www.gpuware.com

        • GPUware C 0.5 test release
          sgratton

          Dear macdonc,

          This seems like a really good idea that might be able to fill a gap between brook+ and il. Having finally gotten a particular IL program going I was thinking that there must be some simplifications possible, allowing e.g. names with array notation to be used instead of r100,r101,r110,r111 for a matrix etc.; I should try your compiler!

          Another tool in this vein I'd love to see from AMD (or anybody!) would be a "simple" IL to gpuisa compiler or "translator" that doesn't attempt any optimization or anything, for example mapping vector il registers directly to vector gpu registers. I've noticed some il code ends up as isa code that uses many more actual registers than I think it should and has suboptimal burst-writing (I think this may be down to trying to use the "t" unit as much as possible), and would like to know whether a "simpler" version would actually perform better.

          Good luck for your project,
          Steven.


          • GPUware C 0.5 test release
            MicahVillmow
            Macdonc,
            That looks really nice, I'll look at it later today and check it out. Thanks for posting the link.

            Steven,
            Currently there is no way to tell the cal compiler not to use optimizations, but it is something we are looking at and may show up in the future.