On May 27, 5:01 pm, newgeekorder <[email protected]> wrote:
[ . . . ]
> More specifically I'm deciding between Java bindings to openCL  v's
> jcuda ?
> And is there any way  that JSR 166 can also be applied to GPU
> computing?

My initial prejudice would be to prefer OpenCL over CUDA because it is
a standard applicable to more than one vendor's products.  On the
other hand if all your equipment is from that vendor then perhaps CUDA
is more efficient.  I have no data as yet.

As far as I am aware JSR166 provides no direct support for any GPU
computing.  The parallel arrays feature in JSR166 extras is possibly
the only real entry point, but then there is a computational model
conflict between CPU and GPU that means a separate but consistent API
is probably the right thing.

The GPars project (http://gpars.codehaus.org) should probably look at
providing easy access to these bindings so that Groovy can be used as
the coordination language for GPU as well as actor, dataflow and
Communicating Sequential Process (CSP) based systems.

-- 
You received this message because you are subscribed to the Google Groups "The 
Java Posse" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/javaposse?hl=en.

Reply via email to