Earlier today we carried the news that SuperMicro and Nvidia have partnered to bring a 1U 2TeraFlop system to market, with integrated Tesla & CPU onboard. John West at InsideHPC talked to Andy Walsh at NVidia about the details of the system.
The new 1U server packs two S1070-class GPUs, for 2 TFLOPS of GPU goodness, into a single rackmount enclosure with 2 quadcore CPUs. The result is a self-contained building block for large systems. This is the same compute density as the previously announced Tesla Preconfigured Clusters, which interleaved a single 1U NVIDIA box with 4 S1070s (4 TFLOPS) with a 1U CPU server box that serves as the host for the S1070s. That’s 4 TFLOPS in 2U, with cables in between.
The CPU part of the SuperServer today is a dual socket quadcore Nehalem system capable of supporting 96 GB (less than the maximum, but still healthy). NVIDIA and Supermicro are careful to talk about the “enterprise” features of this unit, by which they mean that the unit is IPMI 2.0 compliant so its fits into your management stack, and that it has other features like high efficiency power supplies that make it fit well in large configurations.
via NVIDIA and Supermicro announce 1U supercomputer building block | insideHPC.com.
