The Past, Present and Future of Parallel Computing

Abstract – In this talk, I will trace my involvement with parallel computing over the last thirty years. I will relate my experiences as a graduate student at Michigan, my challenges as a junior faculty member at Stanford and my efforts to commercialize multicore processors at a startup company. I will talk about the freedom we have in academia to pursue new research directions and how I have used this freedom to broaden my research agenda to have more impact. I will talk about the effect that parallel computing has had on AI and the effect that AI will have on parallel computing. I will end with predictions about what we can expect to see from the intersection of these two fields in the future.

Biography – Kunle Olukotun is the Cadence Design Systems Professor of Electrical Engineering and Computer Science at Stanford University and he has been on the faculty since 1991. He is well known as a pioneer in multicore processor design and for leading the Stanford Hydra chip multiprocessor (CMP) project which developed one of the first chip multiprocessors with support for thread-level speculation (TLS). Olukotun founded Afara Websystems to develop high-throughput, low-power multicore processors for server systems. The Afara multicore processor, called Niagara, was acquired by Sun Microsystems and Niagara-derived processors now power all Oracle SPARC-based servers.

Olukotun currently directs the Stanford Pervasive Parallelism Lab (PPL), which seeks to proliferate the use of heterogeneous parallelism in all application areas using Domain Specific Languages (DSLs). Olukotun is an ACM Fellow and IEEE Fellow. Olukotun received his PhD in computer engineering from the University of Michigan.