NVIDIA Announces Several Developments at SC08

By DE Editors

One of six announcements made at SC08 (Austin, TX) by NVIDIA included the demonstration of a Lenovo ThinkStation equipped with Tesla C1060 GPU Computing processing technology that showed cluster-class performance of complex seismic imaging data being generated on a single workstation.

Lenovo is already shipping the D10 ThinkStation equipped with Tesla C870, which uses the Tesla C1060 GPU Computing Processor based on the NVIDIA CUDA parallel computing architecture. CUDA enables developers and researchers to harness the massively parallel computational power of Tesla through industry standard C.

In a second announcement, NVIDIA Tesla made personal supercomputing a reality as the Tesla GPUs enable cluster class performance on the desktop at 1/10th the power, read the release. Scientific research is carried out on supercomputing clusters, a shared resource that consumes hundreds of kilowatts of power and costs millions of dollars to build and maintain. For more information on workstation-based NVIDIA Tesla GPU Computing solutions, contact NVIDIA.

The next day at SC08, NVIDIA announced it was partnering with Bull (Les Clayes-sous-Bois, France),  a supplier of high performance computing (HPC) technologies, to provide the Tesla S1070 GPU Computing System as the accelerator option for their HPC solutions. This enables HPC customers in Europe to get integrated solutions and services from Bull that combine Tesla GPU Computing solutions with Bull’s range of other products for HPC. For information on NVIDIA Tesla S1070, visit NVIDIA.

NVIDIA also announced that the Tesla S1070 Computing System is now being offered in the highly successful range of HP (Palo Alto, CA) ProLiant servers. Several Tesla GPU based systems are already installed and are transforming a wide range of industries. Acceleware (Calgary,  Alberta), a company that specializes in enabling software vendors to leverage parallel processing architectures, has been working with Kodak to deliver a solution of clustered Tesla GPU servers for accelerating their large engineering simulations. For more information on HP accelerators, visit HP.

Next, NVIDIA and Cray (Seattle,  WA) announced the availability of NVIDIA Tesla C1060 GPU Computing processors in the new Cray CX1 line of supercomputers. With ease of use and the ability to fit into a standard office setting, the Cray CX1 product reflects NVIDIA and Cray’s goal to drive high productivity computing solutions into an array of markets including financial services, oil and gas, life sciences, government,  and academia. Each Tesla processor has hundreds of processor cores that deliver nearly one teraflop of peak computing performance. The Cray CX1 Supercomputer delivers up to four teraflops of performance, right at the deskside, when configured with four Tesla processors.

Last NVIDIA announced collaboration with NEC (Tokyo, Japan) to integrate NVIDIA Tesla GPUs into its systems for the high performance computing (HPC) industry. The first customer to leverage this collaboration is the Global Scientific Information and Computing Center (GSIC) at Tokyo Institute of Technology, whose TSUBAME supercomputer has lead the supercomputing scene both in Japan and globally for the past 2.5 years. TSUBAME was upgraded in Oct 2008 with 680 NVIDIA Tesla GPUs, while the system remained in operation. The newly upgraded system recorded 77.48 Teraflops in Linpack, ranking it high in the global Top 500 supercomputer listing.

For more details, please visit NVIDIA.

For previous DE coverage, see “NVIDIA Tesla Transforms Seismic Modeling,” (Nov. 2008).

Sources:  Press materials received from the company and additional information gleaned from the company’s website.