University at Buffalo Applies XtremeData's dbX Data Warehousing Appliance

Data Intensive Computing Initiative (Di2) at the University at Buffalo, SUNY, has selected and adopted XtremeData’s dbX. 

Officials with XtremeData claimed that the company’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.

Company officials said that dbX is the newest and most cost-effective technology for warehousing and analyzing datasets, allowing fast unrestricted ad hoc access to the entire dataset.

"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, in a statement.

Chaudhary said that the XtremeData dbX will allow the 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," he said.

Todd C. Scofield, founder and co-director of the Di2 and managing director of Big Data Fast LLC said that 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 the world and universe.

“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”, said Scofield.

He said that in 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," said Ramanathan.

According to company officials, 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.

Valente said that Di2's research will have impacts beyond wildest dreams on some of the world's worst diseases.

He said that 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," said Valente.