|Title:||Exploiting The Unique Features of Emerging Nonvolatile Memories in Next-Generation Memory System Design|
|Date:||March 15, 2016 (Tuesday)|
|Time:||11:00 a.m. - 12:00 noon|
|Venue:||Room 121, 1/F, Ho Sin-hang Engineering Building,
The Chinese University of Hong Kong,
|Speaker:||Ms. Ping Chi
Department of Electrical & Computer Engineering
University of California at Santa Barbara
As technology scales, the conventional memory technologies, such as SRAM and DRAM, face some severe design challenges, like the increasing leakage power and the decreasing reliability. In recent years, some emerging nonvolatile memories, such as resistive random access memory (ReRAM) and spin-transfer torque magnetic RAM (STT-RAM), have been developed, and widely studied as the replacements for SRAM and DRAM in next-generation memory system design thanks to some of their nice features such as zero leakage power. They have other nice characteristics that have not been well exploited yet such as non-volatility.
This talk will mainly introduce two recent projects that utilize the unique features of ReRAM and multi-level cell (MLC) STT-RAM. The first project leverages the computation capability of ReRAM crossbar structure, and designs a novel processing-in-memory architecture to accelerate neural network applications in ReRAM based main memory. The second project takes advantage of the non-volatility and the read and write characteristics of MLC STT-RAM, and designs a fast and energy-efficient local checkpointing scheme in MLC STT-RAM based main memory. The speaker will briefly introduce her other related projects and share her plan for the future work at the end.
Ping Chi received the B.S. and M.S. degrees from Tsinghua University, Beijing, China in 2008 and 2011, respectively. She is currently pursuing the Ph.D. degree with the Electrical and Computer Engineering Department, University of California at Santa Barbara, Santa Barbara, CA, USA.
Her current research interests include system and computer architecture, with a particular emphasis on memory systems, high-performance computing, and low-power systems.
Ms. Chi was a recipient of the IEEE/ACM William J. McCalla ICCAD Best Paper Award - Front End in 2014, and was the second place winner of ACM Student Research Competition at ICCAD 2014.
Enquiries: Miss Ricola Lo at tel 3943 8440
For more information, please refer to http://www.cse.cuhk.edu.hk/seminar.