Hi, there is an OpenCL / Haskell thread floating around the ML, mostly it's a dew ppl talking about merging the 5 (or so) bindings to the OpenCL api and getting spiffy multi-threaded haskell-awesomeness out of that.  i think they are discussing the benefits/drawbacks of a pure-ish api conversion or a more haskell-ish conversion, or some combination thereof.

either way, it exsists, and it's happening (though i'm not so sure about CUDA bindings...  but OpenCL will work on Nvidia & ATI cards the same)

hex



On Thu, Oct 27, 2011 at 3:45 PM, Rafael Gustavo da Cunha Pereira Pinto <RafaelGCPP.Linux@gmail.com> wrote:


Hi folks,

I just bought a NVidia Fermi-based card and remembered reading a few months (years?) ago about some effort to accelerate array processing in Haskell using GPUs.

How is this going on? Any progresses? Do we have GPU based DPH already? (the last one is a joke...)

I keep thinking on the advantages of such GPU data processing on the signal processing field.

Best regards,

Rafael Gustavo da Cunha Pereira Pinto


_______________________________________________
Haskell-Cafe mailing list
Haskell-Cafe@haskell.org
http://www.haskell.org/mailman/listinfo/haskell-cafe




--
*  my blog is cooler than yours: http://serialhex.github.com
*  The wise man said: "Never argue with an idiot. They bring you down to their level and beat you with experience."
*  As a programmer, it is your job to put yourself out of business. What you do today can be automated tomorrow. ~Doug McIlroy
---
CFO: “What happens if we train people and they leave?”
CTO: “What if we don’t and they stay?”