Acceleware Announces GPU-Based Cluster Solution

By DE Editors

Acceleware Corp. (Munich, Germany), developer of high performance computing (HPC) solutions, released its GPU-based cluster solution, the C30-16, at the International Supercomputing Conference in Dresden, Germany. Calling it the “the world’s first commercially available,” the company says this solution combines Acceleware’s new clustering technology with its portfolio of designed-for-parallel computational algorithms to harness the power of 64 GPUs, delivering “unprecedented” performance and scalability for enterprise customers. Acceleware’s C30-16 is competitive against traditional, more expensive clusters of around 1000 cores. Based on NVIDIA Tesla GPU computing technology, Acceleware’s new cluster solution is available in four predefined configurations, allowing for customers to match their processing needs. The cluster solutions start with a 16 GPU configuration and progresses through 32, 48 and up to 64 GPUs. The NVIDIA GPU nodes come packaged in a 1U (four GPU) data center form-factor coupled with host server nodes that incorporate high-speed Infiniband interconnect.

In a simultaneous announcement, Acceleware and Vector Fields (Aurora, IL) announced a partnership to accelerate microwave design, allowing electromagnetic equipment designers to simulate performance up to 20x faster by combining Vector Fields’ Concerto automation software package with Acceleware’s FDTD Accelerator solution.

For recent DEcoverage on Vector Fields, read “Video Shows New Possibilities in EM Design,” (April 2008).

In a third announcement, Acceleware Corp. will enable acceleration of matrix equation solvers found in simulation and data processing software that is used for scientific and industrial applications. New methods extend the problem solving capability of the Acceleware Platform, allowing a broad range of application providers the opportunity to deliver the compelling performance of multi-core and hardware accelerators to their technical computing customers. With these matrix methods added into the Acceleware Platform, end users of these advanced techniques can benefit by solving their linear equation problems up to 20x faster.

For more information, please visit Acceleware.

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