Tony Nowatzki, an assistant professor of computer science at the UCLA Samueli School of Engineering, has received a three-year joint Intel/NSF grant to study the foundations of microarchitecture research (FOMR program), in particular how to sustain exponential single-thread performance growth.
With ever-slowing scaling trends in microprocessor technologies, the traditional techniques of improving processor performance through scaling core microarchitecture are no longer viable. Achieving higher performance requires new execution models, requiring hardware/software interaction that was previously difficult to exploit in hardware alone.
Nowatzki is developing a multicore chip microarchitecture that would dynamically transform programs to use accelerators tuned to the specific properties of those programs, leveraging dynamic translation and code-injection techniques to avoid modifications to user-level software, compilers and operating systems. This goal of this research is to help steer microprocessor design in novel ways that can help sustain exponential performance improvements, and provide insights into foundational microarchitecture questions.
Nowatzki joined UCLA in January 2017. His research interests include microarchitecture, hardware/software interfaces, and compilers. He teaches an undergraduate course on computer organization and operating systems, and graduate courses on hardware/software designs for machine learning, and the specializations of computer architectures. Honors for his research include twice being named as one of IEEE Micro’s Top Picks in Computer Architecture (2016 and 2017) and receiving a distinguished paper award at the PLDI (Programming Language Design and Implementation) conference.
Nowatzki received his doctorate and master’s degree from the University of Wisconsin, Madison, and his bachelor’s degree from the University of Minnesota, Twin Cities.
Visit here for more details about the award.