Supermicro today launched their second generation of server systems with integrated NVIDIA Tesla GPU silicon. The new generation includes NVIDIA’s 20-series Tesla GPUs, nicknamed “Fermi.” The product line includes a 1U server, a 4U tower and a 2U twin server.
To meet our customers’ strong demand, we have made the world’s fastest servers even faster by optimizing our HPC product line to support the latest Tesla 20-series GPUs,” said Charles Liang, CEO and president of Supermicro. “Our dual-GPU 1U SuperServer now delivers up to 1 teraflops double-precision performance, making it suitable for a far wider range of high-performance computing applications where more complex data calculations can be performed faster.”
Supermicro systems optimized for the new NVIDIA Tesla M2050 GPU computing module enable seamless integration of GPUs into large, scale-out deployments in commercial and scientific computing datacenters,” said Andy Keane, general manager, Tesla business at NVIDIA. “Servers with Tesla GPUs provide maximum compute-density for the datacenter, delivering the same compute performance as a CPU-only cluster at 1/10th the cost and 1/20th the power consumption with the ability to scale to thousands of nodes.”
The respective product lines support both Intel 5600 series [Westmere] processors and AMD Opteron 6100 [Socket G34] processors. The various system configurations include the traditional set of management, monitoring and datacenter features. They also include X16 PCIe support with full non-blocking version 2.0 capability.
For more info on the new digs from Supermicro, read the full release here.