Fujitsu Unveiled NVIDIA GPU-Accelerated Servers to the Masses
NVIDIA recently announced the availability of its Tesla GPUs in Fujitsu's PRIMERGY CX400 S1 servers, offering high-performance GPU-accelerated computing to Fujitsu’s large installed base of customers.
Fujitsu designed the PRIMERGY CX400 S1 server for high performance in a compact form factor by using half-wide, two-socket server nodes – doubling 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.
“Fujitsu is a leader in high-performance computing (HPC),” said Sumit Gupta, senior director of the Tesla business at NVIDIA. “Its new GPU-equipped servers provide supercomputing performance to the broad base of researchers and engineers at universities, enterprise and government research laboratories.”
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. The GPU-accelerated Fujitsu system is designed to address complex computational processing challenges inherent in HPC applications.
“With support for NVIDIA GPUs, the system dramatically increases computational performance, while reducing costs and power consumption. This combination is exactly what today’s HPC customers are looking for,” said Jens-Peter Seick, senior vice president of Product Development Group at Fujitsu Technology Solutions.