Mellanox Technologies, Ltd. Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Mellanox Technologies, Ltd.

MLNX 124.89

0.0%

Apr 27 5:00 PM EST

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

From: PaulAquino	11/15/2016 4:45:44 AM
	of 954

How Nvidia’s Own Saturn V DGX-1 Cluster Stacks Up nextplatform.com November 14, 2016 Timothy Prickett Morgan (Excerpt): Some other things to contemplate. Here’s the fun bit to contemplate. Nvidia has demonstrated it can deliver 42.5 teraflops of peak performance and about 28.7 teraflops of sustained performance in a 4U server node. That is about 10.6 teraflops per 1U of rack form factor space. IBM, Nvidia, and Mellanox are working to get more than 40 teraflops of capacity into a 2U “Witherspoon” system next year with the “Summit” supercomputing they are building for the US Department of Energy facility at Oak Ridge National Laboratory. To our way of thinking, that means the future “Volta” GV100 accelerator cards should have about twice the performance of the Pascal GP100 cards currently shipping, if IBM sticks with the 2U form factor and only puts four GPU accelerators into the Witherspoon box alongside a pair of 24-core Power9 chips as we expect. And by this time next year, Nvidia might be able to build a DGX-2 system sporting Intel “Skylake” Xeon E5 v5 processors paired with eight Voltas and delivering as much as 85 teraflops double precision in a 4U chassis – the same performance density as the Summit machines at the peak level. We still think the Witherspoon node used in the Summit machine could have a slight advantage in harnessing that floating point oomph across four Volta cards for HPC workloads. If AMD supports NVLink ports on the future “Zen” 16-core Opteron processors, this would be a very interesting development indeed. But that seems unlikely, considering how AMD has joined the CCIX, OpenCAPI, and Gen Z consortiums. That said, it could happen, and that would mean customers wanting to tightly couple CPUs and GPUs in a fat node could have an X86 option that had many of the same benefits that IBM is bringing with Power8 and Power9 chips.

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next