Abstract:
In this talk, I will introduce a first-of-its kind quantum-inspired coupled oscillator based compute engine implemented in a standard 65nm technology targeted for NP-hard or NP-complete problems such as max-cut, graph coloring, traveling salesman, and pattern recognition. The NP-hard problem is first mapped to the coupling weights while the solution is represented by the phases of the individual oscillators, which are read out using on-chip phase sampling circuits. Our hardware exploits the natural tendency of a network of coupled oscillator to settle to the ground state, which offers significant performance and power advantages compared to traditional digital approaches.
Speaker Bio:
Chris H. Kim received his B.S. and M.S. degrees from Seoul National University and a Ph.D. degree from Purdue University. He is currently a professor at the University of Minnesota. Prof. Kim is the recipient of the University of Minnesota Taylor Award for Distinguished Research, SRC Technical Excellence Award, Council of Graduate Students Outstanding Faculty Award, NSF CAREER Award, Mcknight Foundation Land-Grant Professorship, 3M Non-Tenured Faculty Award, DAC/ISSCC Student Design Contest Award, IBM Faculty Partnership Award, IEEE Circuits and Systems Society Outstanding Young Author Award, the ICCAD Ten Year Retrospective Most Influential Paper Award, ISLPED Low Power Design Contest Award (4 times), and ISLPED Best Paper Award (2 times). His group has expertise in digital, mixed-signal, and memory IC design, with special emphasis on circuit reliability, hardware security, memory circuits, radiation effects, time-based circuits, beyond-CMOS technologies, and machine learning hardware design. He is an IEEE fellow.
Subscribe or Invite your friends to sign up for our mailing list and get to hear about exciting electron-device relevant talks. We promise no spam and try to minimize email. http://site.ieee.org/scv-eds/subscribe/
No comments:
Post a Comment