Nvidia Joins Open Compute Project With HGX-1 Hyperscale GPU Accelerator

[heirdeux]

Nvidia partnered with Microsoft to include the GPU accelerator into Microsoft's Project Olympus design.

Nvidia Joins Open Compute Project With HGX-1 Hyperscale GPU Accelerator : Read more

 

[WhyAreYou]

Sounds good, lets see

 

[Wisecracker]

Sounds good, lets see

The MI8 is the "Radeon Instinct" - aka R9 Nano @ "<175w," available in 8X clusters. The Mi25 is presumed to be Vega with AMD announcing it as the "Falcon Radeon Instinct Cluster with 16X Radeon Instinct MI25 @ 400 Teraflops." I suspect nVidia likely went with their 32X cluster to top the "Falcon Radeon Instinct Cluster." Last year AMD said '1H-2017' for availability --- likely to coincide with the release of the Naples enterprise platform.

Not sure how Chipzilla will respond with the "Phi" as they are unlikely to stand-pat with their "competition" BUT they do seem to be lagging in FP16 ...