Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
EE Times-Asia > Processors/DSPs

Nvidia GPUs drive Fujitsu servers

Posted: 19 Jun 2012 ?? ?Print Version ?Bookmark and Share

Keywords:Tesla GPU? multicore CPU? parallel processing cores?

Nvidia Corp.'s Tesla GPUs are enabling GPU-accelerated performance in Fujitsu's Primergy CX400 S1 servers, benefiting Fujitsu's customers in Japan and Europe.

The Primergy CX400 S1 server comes in a compact form factor using half-wide, two-socket server nodesdoubling the number of cores per unit height. The system houses either four 1U hot-plug Primergy CX250 S1 server nodes with two CPUs per node, or two 2U hot-plug CX270 S1 server nodes with two CPUs and one NVIDIA Tesla GPU per node.

Combining a multicore CPU with the hundreds of parallel processing cores of an Nvidia GPU has enabled a new GPU-accelerated computing model for the HPC industry. This combination shifts complex parallel computing tasks to the GPU and keeps program logic aligned with the CPU, enabling dramatically higher levels of performance than CPU-only systems, while significantly reducing power consumption.

The GPU-accelerated Fujitsu system is designed to address complex computational processing challenges inherent in HPC applications, including structural mechanics, fluid dynamics, seismic modeling and imaging, bioinformatics, molecular dynamics, and computational finance and data mining. The automotive industry is also rapidly deploying GPU technology for crash simulations and CAE design based on its ability to significantly reduce simulation runtimes and computational costs.

Fujitsu Primergy CX400 S1 Multi-Node systems are available now from Fujitsu and its channel partners.

Article Comments - Nvidia GPUs drive Fujitsu servers
*? You can enter [0] more charecters.
*Verify code:


Visit Asia Webinars to learn about the latest in technology and get practical design tips.

Back to Top