IBM and Nvidia have been awarded $425 million by the US Department of Energy to build two brand-new supercomputers that leverage IBM’s Power8 CPUs and Nvidia’s upcoming Volta GPUs. The two computers — Summit, which will be built at Oak Ridge National Laboratory, and Sierra, built at Lawrence Livermore — will have peak performance of around 150 petaflops when they’re completed in 2017-2018. This should make them the most powerful supercomputers in the world, though I wouldn’t be surprised if China is working on something even faster to retain its supercomputing crown.
Today, the USA’s fastest supercomputers are Titan at ORNL and Sequoia at LLNL, both capable of around 17 petaflops, and placed second and third in the world respectively. Both of these supercomputers are actually quite new (completed in the last couple of years), so I’m not sure if Summit and Sierra will replace them, or if all four supercomputers will exist at the same time (which would be awesome, but would require a ridiculous amount of power — about 50 megawatts). At this point, we only know the loosest of hardware specifications for the new supercomputers. Primarily there will be thousands of IBM Power8 CPUs running the show.
Attached to those Power8 chips, via the new CAPI interface, will be thousands of Nvidia Volta GPUs. We don’t know a whole lot about Volta, except that it will feature “stacked DRAM” — DRAM stacked on top of the GPU using through-silicon vias (TSVs) — with memory bandwidth around 1TB/sec and very low latency. Nvidia’s current GPU accelerators (the K40, K20, etc.) are based on the Kepler core; Volta is the core after Maxwell.
Great useful article. Most of the information is really helpful to me. Thanks for sharing this article .
ReplyDeletehp setup 6964 driver