June 17, 2008
64 GPU solution extends Acceleware's acceleration platform to provide unmatched scalability and performance
DRESDEN, Germany, June 17 -- At the International Supercomputing Conference, Acceleware Corp., a leading developer of high performance computing (HPC) solutions, today released the world's first commercially available GPU-based cluster solution, the C30-16. 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.
"The processing capability of the GPU hardware combined with Acceleware's software to eliminate the complexity of parallel processing from our software partners, allows them to quickly deliver powerful accelerated cluster solutions to their end-users," said Ryan Schneider, Acceleware's CTO. "Delivering a solution of this power is a significant milestone for Acceleware, demonstrating the scalability of our platform for the large and complex computing problems our customers face."
Acceleware's enterprise customers, ranging from innovators of high-tech products to oil exploration firms operating in complex geological locations, require specialized solutions to address their difficult computational requirements. Acceleware's vertical domain expertise in building designed-for-parallel, performance tuned software combined with GPU clustering experience, results in leading edge application performance previously unattainable on conventional hardware clusters. This solution brings together all the advantages of clustering -- scalable commodity performance, enterprise-class computing capacity -- with the advantages of GPU acceleration -- compelling performance gains, higher compute densities and lower total cost of ownership from superior power, cooling and space utilization.
"There is a clear market opportunity for high performance solutions that incorporate significant processing power beyond the commodity microprocessor, either because the application cannot effectively take advantage of the multiple cores in today's processors or because the processors and memory required would consume too much power," said Addison Snell, VP of Tabor Research. "GPU-based solutions offer an alternative for finding cost-effective performance for computationally intensive problems."
"Tesla GPUs offer compelling performance for many applications, when using single or multiple GPUs in one system," says Andy Keane, NVIDIA's general manager of GPU Computing." The cluster technology in Acceleware's Platform software takes this compelling performance to the next level, by connecting several hosts together, allowing customers to scale their simulation and data processing problems taking advantage of the performance and memory available on NVIDIA's current and future Tesla, datacenter products."
The GPU cluster solution combined with Acceleware's computational algorithms was benchmarked with data provided by end users, confirming processing power capable of solving problems billions of cells in size with speeds approaching 14 Gigacells per second for electronic design customers. At these processing speeds, Acceleware's C30-16 is competitive against traditional, more expensive clusters of around 1,000 cores. For seismic customers using techniques like Reverse Time Migration, problem sets in the range of billions of cells over thousands of square kilometers found in large marine surveys will now be commercially possible with the Acceleware solution.
Based on NVIDIA Tesla GPU computing technology, Acceleware's new cluster solution is available in four pre-defined 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) datacenter form-factor coupled with host server nodes that incorporate high-speed Infiniband interconnect.
Acceleware will also be demonstrating the cluster solution at IEEE IMS-MTT 2008 in Atlanta, Georgia, June 17–20.
The Acceleware GPU based cluster solutions are available for purchase.
Acceleware develops and markets solutions that enable software vendors to leverage heterogeneous, multi-core processing hardware without rewriting their applications for parallel computing. This acceleration middleware allows customers to speed-up simulation and data processing algorithms, benefiting from high performance computing technologies available in the market such as multiple-core CPUs, GPUs or other acceleration hardware. Acceleware solutions are deployed by companies worldwide such Philips, Boston Scientific, Samsung, Eli Lilly, General Mills, Nokia, LG, RIM, Kyocera, Medtronic, Hitachi, Fujifilm, FDA, Mitsubishi, Sony Ericsson, AGC, NTT DoCoMo, and Renault to speed up product design, analyze data and make better business decisions in areas such as electronic manufacturing, oil & gas, medical and security imaging, industrial and consumer products, and academic research. Acceleware is a public company on Canada's TSX Venture Exchange under the trading symbol AXE.
Source: Acceleware Corp.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?