Today's computers are equipped with multiple processing cores that allow them to execute multiple tasks simultaneously. Although most computers have multiple processing cores, even the most experienced programmers don't have good tools to use to write correct and efficient parallel programs.
Kunal Agrawal, Angelina Lee
I-Ting Angelina Lee, assistant professor, and Kunal Agrawal, associate professor, both in computer science in the School of Engineering & Applied Science at Washington University in St. Louis, will work to make it easier for programmers to create these high-performance parallel programs with a three-year, $449,947 grant from the National Science Foundation.
The team is targeting parallel programs, or those designed to use multiple cores simultaneously. Parallel programs can potentially process larger amounts of data in the same time, or perform the same computation in a shorter amount of time compared to serial programs.
They will focus on improving the locality of parallel programs, which can greatly impact the performance of programs. A program with good locality uses the computer's cache efficiently. The cache is a small piece of memory that stores data that can be quickly accessed. Because a cache has limited capacity, and a programmer cannot control what data is kept in a cache, maintaining good locality can be challenging, Lee says.
Combining strategies from algorithm design and scheduling theory, Lee and Agrawal will work to create a platform that allows programmers to write a parallel program in a high-level language without considering the locality of the program. The platform would transform the program and execute it in a way that improves locality and uses cache effectively. Ultimately, the resulting platform would make the job of programmers much easier.
"Once we establish the platform, we will make it freely available on the Internet, which can support highly efficient software," Lee says.
The School of Engineering & Applied Science at Washington University in St. Louis focuses intellectual efforts through a new convergence paradigm and builds on strengths, particularly as applied to medicine and health, energy and environment, entrepreneurship and security. With 88 tenured/tenure-track and 40 additional full-time faculty, 1,300 undergraduate students, more than 900 graduate students and more than 23,000 alumni, we are working to leverage our partnerships with academic and industry partners — across disciplines and across the world — to contribute to solving the greatest global challenges of the 21st century.