GridGain Enables Portland State Univ. Researchers to Push Boundaries of Science
In-Memory Computing Advances Pathogen Detection, Diagnosis and Intervention
FOSTER CITY, Calif., Sept. 3, 2013 /PRNewswire/ — GridGain(TM) Systems (Gridgain.com) today announced that it has provided In-Memory computing infrastructure to Portland State University’s program, “Computing with Biomolecules: From Network Motifs to Complex and Adaptive Systems.” The program is one of the most advanced applications of “computational chemistry” to date, and leverages GridGain’s unparalleled high performance computing capabilities to incorporate principles of theoretical chemistry into computer programs.
The project’s long-term goal is to build adaptive learning systems for pathogen detection, medical diagnosis and therapeutic interventions, eventually developing biocompatible biomolecular computers capable of being embedded into an actual living cell or body. As its simulations require computing power beyond the capabilities of traditional infrastructure, the PSU team tapped GridGain’s In-Memory HPC edition to harness up to 512 cores of compute power as a single distributed, high-performance computational engine.
GridGain enables project members to perform large scale simulations of highly complex systems in an extremely scalable, resource-efficient way. “With GridGain we’ve been pushing the boundaries, performing simulations that other teams just couldn’t do,” said Christof Teuscher, PhD, the program’s principal investigator.
“In-Memory technology will completely redefine computing as we know it,” said Nikita Ivanov, Founder & CEO, GridGain. “PSU’s ‘Computing with Biomolecules’ project illustrates the infinite possibilities that are presented when In-Memory is delivered in a comprehensive, unified and easily accessible package.”
Synergizing resources with Columbia University and the University of New Mexico
GridGain facilitates a level of collaboration that is particularly beneficial as PSU’s research team is part of a National Science Foundation (NSF) project working with the University of New Mexico and Columbia University. GridGain has enabled the geographically dispersed teams to pool their resources, building an entirely web-based framework which allows researchers — whether at Portland, Columbia or New Mexico — to log in and run simulations on each other’s clusters.
Optimizing chemical networks with GridGain
The team also uses GridGain to optimize the chemical networks. “These systems are very difficult to design by hand, so we’re using optimization techniques to find solutions to very complex problems. Without GridGain it would take a year to get even the most basic results,” said Teuscher.
Taking the complexity out of distributed computing
Peter Banda, a PSU Computer Science PhD student and Java expert, implemented the GridGain-based framework at the program’s inception three years ago. The process, according to Banda and Christof, was straightforward, and GridGain integrated seamlessly with previously existing technology to provide a transparent, easy-to-use system. This has enabled the team to be more productive by eliminating the complexity of distributed computing and offering a layer of abstraction that allows them to focus on the science. “GridGain has allowed us to do amazing science by removing the need to focus on computing and allowing us to dedicate all our energy to the research,” said Teuscher.
The GridGain-based framework enables the PSU team to get better results much quicker which, as Christof points out, is ultimately crucial for the advancement of science. As such, the team plans to eventually offer this tool to the larger scientific community.
GridGain’s complete In-Memory Computing platform enables organizations to conquer challenges that traditional technology can’t even fathom. While most organizations now ingest infinitely more data than they can possibly make sense of, GridGain’s customers leverage a new level of realtime computing power that allows them to easily innovate ahead of the accelerating pace of business. Built from the ground up, GridGain’s product line delivers all the high performance benefits of In-Memory Computing in a simple, intuitive package. From high performance computing, streaming and database to Hadoop and MongoDB accelerators, GridGain provides a complete end-to-end stack for low-latency, high performance computing for each and every category of payloads and data processing requirements. Fortune 500 companies, top government agencies and innovative mobile and web companies use GridGain to achieve unprecedented performance and business insight. GridGain is headquartered in Foster City, California. Learn more at http://www.gridgain.com.
About the Maseeh College of Engineering and Computer Science at Portland State University
The Fariborz Maseeh College of Engineering and Computer Science at Portland State University (PSU) evolved in parallel with the growth of the high-tech industry in Oregon. This close relationship with community and industry partners has helped to establish PSU as an emerging leader among publicly-funded urban research institutes. Maseeh College serves more than 2,200 students currently enrolled in programs that lead to undergraduate and graduate degrees in disciplines such as Civil and Environmental Engineering, Electrical and Computer Engineering, Engineering and Technology Management; Mechanical and Materials Engineering, and Computer Science. Learn more at www.pdx.edu/cecs.