> > > A (GP)GPU can just be seen as an SIMD co-processor. No doubt we'll come to > take them for granted as time passes, and expect full language support. > Just as we did for floating-point operations. I also imagine that other > specialisations will become common as the computing world becomes > increasingly parallel. > > And no, I'm not aware of any system ever running purely on coprocessors, > although there are several blades and dedicated boxes now available, such as > Nvidia's Tesla range. > > Have you ever looked at the MMX instruction set ? I would be v interested how an add instruction that does 8 simulatenous bytes can be used to run java programs.
I think its fairly reasonable to say that the NVidia CG language and GPUs are what can be considered the leader in this area: http://en.wikipedia.org/wiki/Cg_%28programming_language%29 http://http.developer.nvidia.com/CgTutorial/cg_tutorial_chapter01.html DEFINE LUMINANCE = {0.299, 0.587, 0.114, 0.0}; TEX H0, f[TEX0], TEX4, 2D; TEX H1, f[TEX2], TEX5, CUBE; DP3X H1.xyz, H1, LUMINANCE; MULX H0.w, H0.w, LUMINANCE.w; MULX H1.w, H1.x, Given that a Nvidia GPu is fast at processing maths, textures, graphics, im not sure how that helps execute bytecode. Yes it can do normal stuff found in most cpus, but how well. My guess is that is nothign stellar as someone would have built a general purpose computing device ontop iof them instead of buying chips from Intel. The impressive processing is only in the area of graphics and not general purpose computing which is quite different and "boring". Please call Nvidia and tell them to update their cores to do x86 and kill intel w/ their gpu technology, apparently nobody has told them... -- 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.
