Mailinglist Archive: radeonhd (353 mails)

[Zack Rusin <zack@xxxxxxx>]

On Tuesday 08 April 2008 07:24:40 pm Jerome Glisse wrote:
> I just want to be sure that you are aware of the limitation of GPU
> hw, it should not be seen as CPU and so not be tackle like a CPU.
> Compiler we are aiming for should be able to translate TGSI in
> GPU opcode. I am yet not sure on win we could get from using llvm
> too for producing the byte code.

There really isn't one. Realistically the point of interest for us are the 
optimization passes. Code generation and multi-lingual input being side 
considerations that realistically haven't been proven yet. LLVM simply packs 
it all into one, integrated and document framework which, given the 
complexity of it all, is highly desirable.

z
-- 
To unsubscribe, e-mail: radeonhd+unsubscribe@xxxxxxxxxxxx
For additional commands, e-mail: radeonhd+help@xxxxxxxxxxxx