Slides available here!

Speaker:

Yuan Xie, University of California at Santa Barbara, USA

Title:

PIM Architecture for Neuromorphic Computing with ReRAM-based NVM

Abstract:

Neuromorphic computing has the great potential to mimic how the human brain works and lead to new computing paradigms. However, with an architecture of separate computation and data storage components, most neuromorphic computing systems suffer from the "memory wall" issue that conventional computing systems have. Processing-in-memory (PIM) is a promising solution to address it, by reducing the data movement overhead between the processing units and the memory. In this work, we propose a novel PIM architecture, called PRIME, utilizing metal-oxide resistive random access memory (ReRAM) as main memory and also for computation. ReRAM has been considered as a potential candidate to build low-cost memory systems; moreover, with its crossbar array structure, ReRAM can perform matrix-vector multiplication efficiently, and has been widely studied to accelerate neural network (NN) applications. Our PRIME design is based on a ReRAM based main memory system, in which a portion of ReRAM crossbar arrays can be configured as accelerators for NN applications or normal memory for a larger memory space. We provide a concrete microarchitecture and circuit design to enable the morphable functions with an insignificant area overhead. We also design a software/hardware interface for developers to implement various NNs on PRIME. In addition, we will also brief mention recent work on ISA design and software toolchains for Neuromorphic computing.

Bio:

Yuan Xie received the B.S. degree in electronic engineering from Tsinghua University, Beijing, in 1997, and the M.S. and Ph.D. degrees in electrical engineering from Princeton University in 1999 and 2002, respectively. He is currently a Professor in the Electrical and Computer Engineering department at the University of California at Santa Barbara. Before joining UCSB in Fall 2014, he was with Pennsylvania State University, AMD Research, and IBM Microelectronic Division's Worldwide Design.

Prof. Xie is a recipient of the National Science Foundation Early Faculty (CAREER) award, the SRC Inventor Recognition Award, IBM Faculty Award, and several Best Paper Award and Best Paper Award Nominations at IEEE/ACM conferences. He has published more than 200 research papers in journals and refereed conference proceedings, in the area of EDA, computer architecture, VLSI circuit designs, and embedded systems. His current research projects include: three-dimensional integrated circuits (3D ICs) design, EDA, and architecture; emerging memory technologies; low power and thermal-aware design; reliable circuits and architectures; and embedded system synthesis. He is currently Editor-in-Chief for ACM Journal of Emerging Technologies in Computing Systems (JETC), Senior Associate Editor for ACM Transactions on Design Automation for Electronics Systems (TODAE), IEEE Transactions on Computers (TC), and IET Computers and Digital Techniques (IET CDT). He is Fellow of IEEE.



* If you wish to modify any information or update your photo, please contact the Publicity Chair at the following address.