Intel this week announced that its processors, compute accelerators, and Optane DC persistent memory modules will power Aurora, the first supercomputer in the US projected to feature a performance of one exaFLOP. The system is expected to be delivered in about two years, and goes beyond its initial Xeon Phi specification released in 2014.
Back in 2016 when NVIDIA launched the Pascal GP100 GPU and associated Tesla cards, one of the consequences of their increased server focus for Pascal was that interconnect bandwidth...22 by Ryan Smith on 3/27/2018
PathForward: US Dept. of Energy Awards $258M in Research Contracts To Develop Exascale Supercomputer Technology
Even though the major US national laboratories are just now starting to take delivery of the supercomputers they ordered a few years back, due to the long and complex...22 by Ryan Smith on 6/15/2017
For a few years now, NVIDIA has been flirting with the server business as a means of driving the growth of datacenter sales of their products. A combination of...30 by Ryan Smith & Ian Cutress on 4/6/2016
The typical view of a cluster or supercomputer that uses a GPU, an FPGA or a Xeon Phi type device is that each node in the system requires one...8 by Ian Cutress on 12/21/2015