WVU-Led Dolly Sods GPU Cluster to Push New Frontiers in Computing Analysis in Physics and Astronomy, Drug Discovery, Knowledge Science, and Extra | WVU right now
Dolly Sods will soon be not just the name of a popular wilderness area in eastern West Virginia. It will also be the name of a GPU cluster project that will improve research in physics and astronomy, drug discovery, and data science.
(WVU illustration / Aira Burkhart)
A computer cluster with graphics processors called Dolly Sods will enable researchers across the state to accelerate computational research in areas such as drug development, interstellar phenomena, biometrics, materials design, and business logistics and management.
Blake Mertz, Associate Professor of Chemistry at West Virginia University, leads the project, which was recently funded by a $ 1.1 million National Science Foundation grant.
GPUs are graphics cards that computers, video game consoles, and smartphones use to quickly render pictures. Although GPUs have been used for graphics and video rendering in the past, they have become increasingly popular for use in artificial intelligence applications and to speed up math-intensive calculations.
The Dolly Sods project, Mertz said, will pave the way for cutting-edge research in diagnostic imaging of tumors, screening of small molecule drug design, detection of interstellar phenomena, design and optimization of data algorithms used in space travel, Computer Vision of Medical image and information processing of business-based management decisions.
“GPUs are well suited to performing simplified math calculations over and over, and they can do this much faster and more efficiently than traditional CPU-based solutions,” said Mertz. “By using this technology, we can perform calculations orders of magnitude faster than on a traditional compute cluster, which gives us the ability to solve problems that were previously inaccessible to the WVU computing community.”
Mertz said the project was named Dolly Sods because of the ability to cross borders and the uniqueness of the area.
“The Dolly Sods Wilderness represents many of West Virginia’s defining characteristics: expansive vistas, abundant wildlife, and the opportunity to challenge yourself in the great outdoors, and an environment radically different from any other in the state,” says Mertz. “Dolly Sods forces you to think outside the box of what you normally think of when you think of West Virginia. This GPU cluster aims to do the same thing. to enable WVU researchers to push the limits of what we can do in terms of solving fundamental, environmental, and societal problems for the people of West Virginia and beyond.
“In the case of Dolly Sods, we will have around 20-25 nodes in the cluster,” Mertz continues. “The advantage of a cluster over 25 individual computers is that it makes it much easier for WVU and the nationwide research community to access this shared resource, and allows researchers to group these nodes together to perform much more powerful calculations.”
“The enhanced capabilities of Dolly Sods open up the possibility of investigating scientific problems at a much higher level of detail, as we can access the time periods in which these phenomena occur much more easily than before.”
Dolly Sods will help researchers in many different fields.
For example, Dolly Sods can help run code that can efficiently transmit information from satellites in space to Earth, enable drug development for neurodegenerative diseases, and manipulate huge datasets from places like the Green Bank Telescope.
“For WVU physics and astronomy groups working with signals captured at Green Bank, Dolly Sods represents a paradigm shift: researchers will be able to analyze data in near real time to make assessments and discover new phenomena how to identify pulsars, which could previously only be carried out with national supercomputing resources such as the Pittsburgh Supercomputing Center, ”said Mertz. “This tool will only further strengthen one of WVU’s flagship research programs.
“We anticipate that many researchers in almost all study areas at WVU will use Dolly Sods as this will facilitate the development of new approaches to machine learning and AI, which are crucial for understanding big data problems.”
Mertz said Dolly Sods will also lead to the creation of educational opportunities for first generation college students, female students and those from marginalized communities. It will also help diversify the computationally intensive workforce that will be invaluable to West Virginia.
“In the short term, it will help to train our workforce so that they are more competitive with the many federal authorities in the state,” said Mertz. “Our long-term goal is to provide the West Virginia workforce with world-class training in data science that is consistent with many of the recently launched joint state, academic and industrial initiatives such as West Virginia Forward. As Artificial Intelligence and machine learning approaches become more common in data-driven research, acquiring a tool like Dolly Sods is the next logical step in educating the next generation of data scientists in West Virginia.
“We typically have around a hundred faculty, students and postdocs using our current research computing resources, and with the Dolly Sods acquisition we will easily double that number. That represents a significant number of people at WVU and across the country who will be using computer science as a core component of their research efforts. “
Mertz said the Dolly Sods GPU cluster will support WVU’s long-term goal of making the economically disadvantaged region of Appalachia a prime destination for technology investments.
Together with Mertz, his WVU colleagues are Werner Geldenhuys, School of Pharmacy; Sarah Burke-Spolaor, Physics and Astronomy; Piyush Mehta, Mechanical and Aerospace Engineering; and Gianfranco Doretto, computer science and electrical engineering.
af / 11/18/21
CONTACT: Jessica McGee
Marketing and Communication Director
Eberly College of Arts and Sciences
Call 1-855-WVU-NEWS for the latest West Virginia University news and information from WVUToday.
Follow @WVUT on Twitter today.
Comments are closed.