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.
