SOURCE: XtremeData, Inc.

September 07, 2010 09:00 ET

University at Buffalo Applies XtremeData's dbX Data Warehousing Appliance for Navigating "Data Tsunami" Research Efforts

Program's Massive Data Sets Demand Fresh Approach to Accelerating Access to New Knowledge

SCHAUMBURG, IL--(Marketwire - September 7, 2010) -  XtremeData, an innovator providing solutions for large data analytics and complex computing problems, today announced that the Data Intensive Computing Initiative (Di2) at the University at Buffalo, SUNY, has adopted dbX™. XtremeData's dbX offering constitutes the next-generation in database appliances: the only systems created specifically for unconstrained analysis and exploration of very large data sets.

Today's data intensive challenges in science and engineering are forcing researchers to obtain different core technologies, like high performance computing (HPC) clusters, graphics processing unit (GPU) accelerators, field programmable gate array (FPGA) acceleration, and massively parallel processing (MPP) database technology to do their work successfully. Scientific research such as microarray data analysis, gene environmental interaction analysis, and combustion/jet engine simulations regularly create datasets from a few to more than 100 terabytes (TB) for a single experiment. dbX is the newest and most cost-effective technology for warehousing and analyzing these datasets, allowing fast unrestricted ad hoc access to the entire dataset.

What People are Saying About dbX

  • "The Di2 is an academic, government and industry high performance computer research consortium. It leads in developing applications of novel data intensive technologies with traditional and new compute-intensive architectures to shorten complex discovery cycles," said Vipin Chaudhary, co-founder and director of the Di2, associate professor of Computer Science at the University at Buffalo, SUNY, and CEO of Computational Research Laboratories (CRL) Ltd., a wholly-owned subsidiary of Tata Sons Ltd. "The XtremeData dbX will allow our researchers to perform very complex analytics against massive data sets in multiple science and engineering domains. We strongly believe the result of exploiting these assets together will create new knowledge sooner, and deliver solutions faster."

  • "Data tsunamis are being created by the new technologies addressing human health, advanced energy systems, the weather and global warming as well as principles of our world and universe," said Todd C. Scofield, founder and co-director of the Di2 and managing director of Big Data Fast LLC. "For this range of research efforts we require cost-effective, high-performance computing technologies. We chose the XtremeData dbX because it delivers best-in-class time-to-knowledge for our researchers. In our production tests dbX performed extremely well and delivered performance that was one to two orders of magnitude faster than traditional architectures." 

  • "Hybrid FPGA-enabled Data Intensive Supercomputer (DISC) appliances are having a major impact on our discovery processes," said Murali Ramanathan, a leading Multiple Sclerosis and pharmacogenetics researcher, and associate professor of Pharmaceutical Sciences and Neurology at SUNY at Buffalo. "Our algorithms for gene/environment interactional analysis now run incredibly fast, from many hours previously to a few minutes today. The combinatorial explosion problem size we can now effectively solve is quite extraordinary."

The Di2 has combined an unprecedented amount of computing, storage, and acceleration resources. XtremeData's dbX enterprise class data warehousing appliance is integrated with the Di2's compute intensive HPC and GPU infrastructure, allowing complex simulations, including detailed analyses of archived datasets, archival of results into network attached storage (NAS), followed by visualization of them. Application of this new technology is now being used to solve computational problems once considered impossible. 

"The fields of drug discovery, cancer research, and genomics are of personal interest to me," said Geno Valente, vice president of sales and marketing at XtremeData. "Di2's research will have impacts beyond our wildest dreams on some of the world's worst diseases. Being a part of the computational framework supporting cutting edge research is particularly gratifying. By partnering with Di2, we have unlocked powerful FPGAs inside dbX for the worldwide research community via user defined functions within the FPGA. We are already seeing exciting results from this effort and believe this is only the tip of the iceberg."

About University at Buffalo, SUNY
The University at Buffalo is a premier research-intensive public university, a flagship institution in the State University of New York system and its largest and most comprehensive campus. UB's more than 28,000 students pursue their academic interests through more than 300 undergraduate, graduate and professional degree programs. Founded in 1846, the University at Buffalo is a member of the Association of American Universities.

About Data Intensive Discovery Initiative (Di2)
Di2 is dedicated to helping scientists and engineers increase the pace of discovery through the analysis of massive data sets. The current computing platforms used in science and engineering for data analytic tasks of this scale are unable to effectively meet the challenge. This is a huge problem in the science and engineering domains where data is being created at an unprecedented pace. Di2 researchers are developing novel architectures and algorithms for discovery. Di2 also works by bring vendors and researchers together in ways that have not been possible in the past.

About Computational Research Laboratories Limited
Computational Research Laboratories Ltd. (CRL) is a wholly owned subsidiary of Tata Sons Ltd. CRL provides High Performance Computing (HPC) Cloud Research & Development services and solutions to the Automotive, Aerospace, Life Sciences, Media & Entertainment, Weather, Sciences and other sectors. With 'eka,' CRL's supercomputer (the most versatile, largest, and fastest commercially available HPC system in the world), CRL provides an expanded portfolio of cloud services that allows organizations to avail HPC services, without having to undergo the demands for capital expenditure and long turnaround times of cluster set up. CRL has an experienced team of computational experts in multiple domains including Biology, Fluid Dynamics, Materials Science, Seismic Data Processing and Reservoir Simulations with a deep understanding of the scaling of applications in a highly parallel environment.

About XtremeData, Inc.
XtremeData offers innovative solutions to large data analysis and complex computing problems. Its products combine commodity hardware, open-source software and custom hardware-accelerators in a unique and optimal technology mix. XtremeData offers appliances purpose-built for ad hoc analysis of large data sets. XtremeData is headquartered in Schaumburg, IL, USA. For more information, visit www.xtremedata.com.

Contact Information