Relion 2808GT

Penguin Computing, which provides high performance, enterprise and cloud solutions, introduced its Relion 2808GT with rack DCLC solution by CoolIT at the Nvidia GPU Tech Conference. Penguin Computing’s partnership with CoolIT addresses power and cooling of high-density configurations.

The Relion 2808GT was designed to deliver maximum compute power with a minimal datacentre footprint. The system supports eight GPUs or coprocessors in two rack units. Configured with eight Nvidia GPUs or eight Intel Xeon Phi co-processors, a single Relion 2808GT can achieve over 8 TFLOPs of double-precision peak performance.

The system’s eight GPUs or coprocessors are supported by a dual socket platform based on Intel’s Xeon E5-2600v2 product family. The system can be configured with up to 512GB of ECC memory and features an on-board dual 10GbE BASE-T controller and optional support for two 10GbE SFP+ ports. Serviceability features include a dedicated LAN port for server management as well as support for IPMI 2.0 and remote KVM. For maximum power efficiency, the Relion 2808GT features a dual 1600W power supply that has been certified at the 80 PLUS Gold level.

It acts as al platform for running scientific and engineering applications that support GPUs or coprocessors such as Matlab, Amber, or Abaqus, as well as ‘home grown’ and open source applications that can be ported to support GPUs or coprocessors.

CoolIT’s rack DCLC Solution provides direct-to-chip liquid cooling to both of the Intel Xeon Processors along with eight NVIDIA K40 GPUs. This addresses 86 per cent of total server heat while facility air cooling requirement is substantially reduced to 14 per cent.

By reducing the air cooling requirement, an increased number of servers per rack is possible as well as decreasing data centre rack footprint.


For functionality and security for externalised research, software providers have turned to the cloud, writes Sophia Ktori


Robert Roe looks at the latest simulation techniques used in the design of industrial and commercial vehicles


Robert Roe investigates the growth in cloud technology which is being driven by scientific, engineering and HPC workflows through application specific hardware


Robert Roe learns that the NASA advanced supercomputing division (NAS) is optimising energy efficiency and water usage to maximise the facility’s potential to deliver computing services to its user community


Robert Roe investigates the use of technologies in HPC that could help shape the design of future supercomputers