Texas ECE Professors Andreas Gerstlauer and Lizy K. John together with collaborators at the University of California, Riverside have been awarded a $1M grant by the National Science Foundation (NSF) to study application of machine learning techniques for performance and power prediction in early design stages of future computer systems.
The project is described below:
With semiconductor scaling reaching physical limits, performance and power consumption are ever more critical aspects in the design of emerging computer systems. Next-generation systems ranging from small embedded devices to city-scale data centers are expected to contain a heterogeneous mix of multiple CPUs, GPUs, FPGAs, accelerators and memory stacks all in the same package or die. This poses fundamental new challenges for designing, programming and managing of such systems. Fast and accurate power and performance models of architectures and the applications running on them are essential for evaluating design options before systems are built. With increase in complexity of systems and applications, traditional simulation-based or analytical modeling approaches are rapidly becoming too slow or inaccurate to be feasible.
This project aims to investigate use of advanced machine learning-based, predictive methodologies to rapidly estimate the performance and power consumption of future generation products at early design stages using observations obtained on commercially available silicon today, specifically to aid in heterogeneous system design, programming and runtime management. Such techniques will allow efficient design cycles ensuring that the next-generation computing infrastructure meets the consumer and society's needs. In addition, the project will be complemented by educational, outreach and active industry collaboration and technology transfer activities.
Dr. Andreas Gerstlauer is an Associate Professor in the Department of Electrical & Computer Engineering at The University of Texas at Austin. Dr. Gerstlauer is co-author on 3 books and more than 60 conference and journal publications. His work was reprinted as one of the most influential contributions of 10 years at the DATE conference. He has presented in numerous conference and industrial tutorials, and he serves as an Associated Editor for the ACM Transactions on Embedded Computer Systems (TECS) as well as program committee member of major international conferences, such as DAC, DATE, CODES+ISSS and ICCD.
Dr. Lizy Kurian John holds the Cullen Trust for Higher Education Endowed Professorship in Engineering #3 in the Department of Electrical & Computer Engineering at The University of Texas at Austin. Professor John holds 8 U. S. patents and has published 16 book chapters, 170 refereed journal and conference publications, and approximately 50 workshop papers. She has coauthored books on Digital Systems Design using VHDL (Cengage Publishers), Digital Systems Design using Verilog (Cengage Publishers) and has edited a book on Computer Performance Evaluation and Benchmarking (CRC Press). She has also edited three books on workload characterization.