GPU accelerated high-frequency trading

Quote from Equalizer:

My point exactly. I just don't buy the prediction that Intel's new releases will be the end for CUDA and/or NVIDIA. OpenCL, maybe, but for our specific applications which map nicely (and which I can't get into on a public forum), I just can't see how, say, using even a 64-core machine (multi-core-multi-CPU) can beat a GPU/multi-GPU solution.
it's not a question of performance, it's a question of economics. they will beat them with low-end marketshare, not with hpc cores.

intel's sandy bridge architecture is going to meld cpu/gpu on a single chip. targeted to medium to low-end users this will add some HEAVY competition to nvidia's core product line. the same product line that subsidizes cool things like tesla/cuda/fermi. eliminate or significantly reduce the subsidy, and bye-bye cheap supercomputing for the masses. it may or may not disappear altogether, but the days of highly competitvely priced hpc cards are numbered.

... that is, until the next co-processor design makes an inroad. but, like all before them, they will be integrated into the core tech, and prices will revert to their mean (high premium for performance).
 
Back
Top