Server featuring Tesla GPUsSanta Clara, California-based NVIDIA and Supermicro have just announced the availability of a new SuperServer 6016T-GF-TM2 based on NVIDIA's Tesla GPU architecture. Designed in a single 1U rack-mountable chassis, this new server system is said to be capable of providing enterprise-class users with up to 12 times the performance that can be achieved with a single, traditional quad-core CPU-based 1U server. Following the official introduction, Supermicros is expected to showcase the new server during the Computex 2009 show kicking off tomorrow.
“Our new Tesla GPU-based SuperServer 6016T-GF Series delivers a much higher performance-per-watt and per-rack than any other 1U solution in the market today,” stated Don Clegg, vice president of marketing, Supermicro. “This 2-Teraflop SuperServer meets the most demanding enterprise data center requirements for reliability and manageability.”
The new SuperServer 6016T-GF-TM2 server system has been designed using the same NVIDIA CUDA architecture that is available for other Tesla GPU-based solutions. CUDA can enable enterprise-class users to tap into the massively parallel computing capabilities of the NVIDIA GPU, consequently improving the performance of the server system. The GPU also allows for a better management of the entire system, thanks to its capability to connect to the remote monitoring capabilities of the server.
“With our GPU cluster we are getting performance improvements of 5x to 20x over our traditional multi-core CPU-based cluster,” said Neiva Zago, geophysical technology manager, Petrobras. “We expect that the continued use of GPUs in our business will result in significant reduction in processing time as well as savings in power consumption and datacenter floor space.”
According to NVIDIA, the new solution from Supermicro, can boost the performance of a 1U server system by as much as 12 times that of a traditional quad-core CPU-based server.