The DGX-2, which sports performance of 1920 TFLOPs (Tensor processing); 480 TFLOPs of FP16; half again that value at 240 TFLOPs for FP32 workloads; and 120 TFLOPs on FP64.
https://blogs.nvidia...le-datacenters/
https://www.techpowe...ry-for-usd-400k
Edited by theone, 03 April 2018 - 09:22 PM.