The UCLA Henry Samueli School of Engineering and Applied Science has been awarded a $10 million grant by the National Science Foundation's Expeditions in Computing program to develop high-performance, energy efficient, customizable computing that could revolutionize the way computers are used in health care and other important applications.
In particular, UCLA Engineering researchers will demonstrate how the new technology, known as domain-specific computing, could transform the role of medical imaging and hemodynamic simulation, providing more cost-effective and convenient solutions for preventive, diagnostic and therapeutic procedures and dramatically improving health care quality, efficiency and patient outcomes.
"This significant award is another testament to the world-class faculty here at UCLA who continue to push the envelope to solve society's most pressing issues," said UCLA Chancellor Gene Block. "We are grateful to the NSF, which has repeatedly provided crucial funding to our faculty, helping to place the university among the nation's top five in research funding."
In an effort to meet ever-increasing computing needs in various fields, the computing industry has entered an "era of parallelization," in which tens of thousands of computer servers are connected in warehouse-scale data centers, said Jason Cong, the Chancellor's Professor of Computer Science and director of the new UCLA Center for Domain-Specific Computing (CDSC), which will oversee the research. But these parallel, general-purpose computing systems still face serious challenges in terms of performance, energy, space and cost.
Domain-specific computing holds significant advantages, Cong said. While general-purpose computing relies on computer architecture and languages aimed at any type of application, domain-specific computing utilizes a customizable architecture and custom-oriented, high-level computer languages tailored to a particular application area or domain — in this case, medical imaging and hemodynamic modeling. This customization ultimately results in much less energy consumption, faster results, lower costs and increased productivity.
The goal of the new UCLA center, Cong said, is to look beyond parallelization and focus on domain-specific customization to bring significant power-performance efficiency improvement to important application domains.
"The broader impact of our work at the CDSC will be measured by the new digital revolution enabled by customized computing," Cong said. "We will demonstrate the feasibility and advantages of the proposed research in the domain of health care, given its significant impact on the national economy and quality-of-life issues.
"In regards to medical imaging and hemodynamic modeling, we'll be able to see inside the brain and facilitate real-time surgery, for example," he said. "Also, doctors will be able to do preventative procedures much faster with automatic analysis and diagnosis of MRIs and CT scan images. Much of the work that relies on people today may take hours or days to complete with existing computing technology, but with the domain-specific customizable technique, the work can be done in minutes. The whole team is very excited about the NSF support we're getting to develop this new approach."
UCLA is one of three lead institutions receiving the latest round of awards under the NSF Expeditions in Computing program. The program, established last year by the agency's Directorate for Computer and Information Science and Engineering (CISE), provides the CISE research and education community with the opportunity to pursue ambitious, fundamental research agendas that promise to define the future of computing and information and render great benefit to society. Funded at levels of up to $2 million per year for five years, the Expeditions programs represent some of the largest single investments currently made by the directorate.
"We're looking forward to domain-specific computing as an approach to tackling the parallelism and energy challenges in future multicore systems," said Vivek Sarkar, associate director of the CDSC and a professor of computer science at Rice University. "The fact that our work will begin in the critically important health care domain is a huge motivation for the entire team."
Research being conducted by the CDSC is a collaborative effort among faculty from UCLA's engineering school, medical school and applied mathematics program, as well as faculty from Rice University, Ohio State University and UC Santa Barbara.
"The CDSC will thrive under Jason's leadership," said Vijay K. Dhir, dean of UCLA Engineering. "Jason exemplifies the type of faculty we have here at the school, showing unwavering dedication to both research and education."
Cong said he and his colleagues recognize that to achieve broad and lasting success there will also be a need to train a new generation of students who are prepared for customized computing and can effectively apply such techniques to many areas of society, furthering the digital revolution.
To accomplish this, the CDSC will integrate research with education, exposing graduate, undergraduate and high school students to the new concepts and research from this project through several new courses jointly developed and shared by researchers from all four universities.
Summer research fellowship programs will be created to support high school and undergraduate students, and special efforts will be made to attract underrepresented students at all levels through partnerships with campus organizations focused on diversity such, as UCLA Engineering's Center for Excellence in Engineering Diversity.
The UCLA Henry Samueli School of Engineering and Applied Science, established in 1945, offers 28 academic and professional degree programs, including an interdepartmental graduate degree program in biomedical engineering. Ranked among the top 10 engineering schools at public universities nationwide, the school is home to five multimillion-dollar interdisciplinary research centers in wireless sensor systems, nanotechnology, nanomanufacturing and nanoelectronics, all funded by federal and private agencies.