Nvidia packs 2 petaflops of performance in a single compact server

At its GPU Technology Conference this week, Nvidia took the wraps off a new DGX-2 system it claims is the first to offer multi-petaflop performance in a single server, thus greatly reducing the footprint to get to true high-performance computing (HPC).

DGX-2 comes just seven months after the DGX-1 was introduced, although it won’t ship until the third quarter. However, Nvidia claims it has 10 times the compute power as the previous generation thanks to twice the number of GPUs, much more memory per GPU, faster memory, and a faster GPU interconnect.

The DGX-2 uses a Tesla V100 CPU, the top of the line for Nvidia’s HPC and artificial intelligence-based cards. With the DGX-2, it has doubled the on-board memory to 32GB. Nvidia claims the DGX-2 is the world’s first single physical server with enough computing power to deliver two petaflops, a level of performance usually delivered by hundreds of servers networked into clusters.

How DGX-2 compares to Intel’s Skylake Xeon

By way of comparison, Nvidia said, to get similar performance out of Intel’s latest Skylake Xeon generation, you would need a $3 million system consisting of 15 racks of servers and 300 CPUs. DGX-2 starts at $399,000 and is 60 times smaller and 18 times more power efficient than the Skylake setup, the company said.