Power-efficiency, GPUs push exascale computing

"Power is the main challenge on the path to exascale computing," affirmed Anthony Kenisky of Appro. Chuck Moore, AMD corporate fellow and technology group CTO, said those looking to achieve exascale would have to factor in a million dollars per megawatt. "As good as Bulldozer, or Interlagos is, they are not good enough. They're not going to get us there."

Moore predicted it may take AMD until at least 2019 or 2020 before its chips would offer a level of programmability sufficient to take customers to exascale level, noting that GPUs would factor heavily into the equation. Indeed, GPUs in supercomputers is becoming an integral part of the segment's forward momentum, though the consensus was that CPUs would in no way become redundant in the space as a result.

"GPUs are a very important part of heterogeneous computing in terms of alleviating the bottlenecks," said Clegg, adding that graphics processing was "right on the cusp" of becoming accepted as the predominant way to get heterogeneous computing going. While that was a significant achievement for the GPU space, however, Clegg was quick to temper his comments with caution. "Will the space become 100 percent heterogeneous and GPU based? I don't think so, because there are some applications that are suited to it and some that are not."

"GPU is in vogue in HPC at the moment," added Charles Wuischpard, president and CEO of Penguin Computing. "For our larger systems, everything we're doing involves a GPU but for the mass market, not so much."

GPU supercomputing will continue
"GPU supercomputing is here to stay," agreed Cray's Williams, saying her firm—which builds some of the world's fastest supercomputing systems—saw an increasing role for GPUs moving forward. In May, Cray unveiled its XK6 hybrid supercomputer, which combines AMD's multicore scalar processors with Nvidia's many-core GPGPU processors to achieve 50 petaflops of peak performance, and Williams said the firm is now working to upgrade its Jaguar System to add in GPUs too.

The question, Williams said, is whether the industry can make it easier for application programmers to access the GPUs and harness all of that power effectively. "Applications will continue to drive the sweet spot as to where GPUs will be applicable," concurred Appro's Kenisky, noting that though the firm is seeing a growing interest in GPU technology and a demand in the space, the firm still did not see it becoming a dominant player.

?? 1???2???3??