Evolution or Revolution? Conventional and Neuromorphic Systems Leveraging Emerging Memory Technologies

Jan 18

Monday, January 18, 2016

12:00 pm - 1:00 pm
Fitzpatrick Center Schiciano Auditorium Side A


Hai (Helen) Li, Associate Professor, University of Pittsburgh

As big data processing becomes pervasive and ubiquitous in our lives, the desire for embedded-everywhere and human-centric information systems calls for an "intelligent" computing paradigm that is capable of handling large volume of data through massively parallel operations under limited hardware and power resources. This demand, however, is unlikely to be satisfied through the traditional computer systems whose performance is greatly hindered by the increasing performance gap between CPU and memory as well as the fast-growing power consumption. Inspired by the working mechanism of human brains, a neuromorphic system naturally possesses a massively parallel architecture with closely coupled memory, offering a great opportunity to break the "memory wall" in von Neumann architecture. In this talk, I will give an overview of our research on emerging nonvolatile memory (eNVM) technologies that feature many attractive characteristics such as non-volatility, high cell density, nanosecond access time and low operation voltage. The talk starts with the expectations of modern computing systems on memory hierarchy, followed by two examples in eNVM design and applications in conventional and neuromorphic computing systems, respectively. Our prospects on the research of eNVM technologies will be also given at the end of this talk, offering the audiences an alternative thinking about the future evolution and revolution of modern computing systems. Lunch served at 11:45.


Naseree, Alexandra