Select a calendar:
Filter March Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for March 25, 2010
-
Architectural Inference and the Pursuit of Efficiency
Thu, Mar 25, 2010 @ 09:45 AM - 11:00 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Benjamin Lee,
Stanford UniversityAbstract:
Energy efficiency is a defining challenge in modern computing. Limits in technology scaling pose challenges in power density while limits in software parallelism raise questions about future multi-core integration. Without process and parallelism to drive efficiency, we must rely on specialization and design coordination across the hardware/software interface. However, specialization is prohibitively expensive, incurring high non-recurring engineering costs that arise from an intractable number of degrees of freedom. I present the case for architectural inference to provide tractability for complex design questions in computer architecture. Inference enables comprehensive solutions to long-standing and previously intractable design priorities in heterogeneous specialization, application/architecture co-design, and architecture/circuit co-design. I also describe strategies for leveraging efficient components in cloud computing systems. In particular, I discuss experiences from deploying the Microsoft Bing search engine on mobile processors for energy efficiency. I also note the price of efficiency, which is exacted from application robustness and flexibility, and the implications for future system design. Biography:
Benjamin Lee is an NSF Computing Innovation Fellow in Electrical Engineering and a member of the VLSI Research Group at Stanford University. His research focuses on scalable technologies, power-efficient architectures, and high-performance applications. He is also interested in economics and policy for sustainable IT infrastructure. Dr. Lee has co-authored more than twenty papers in these areas, earning six nominations/awards such as the Harvard nomination for the ACM doctoral dissertation award, an IEEE Micro Top Pick, and a Communications of the ACM highlight. He has held visiting positions at Microsoft Research, Intel Labs, and Lawrence Livermore National Lab. Dr. Lee received his B.S. from the University of California at Berkeley and his S.M., Ph.D. from Harvard University.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - -248
Audiences: Everyone Is Invited
Contact: Estela Lopez
-
Photonics Seminar (Student Talk)
Thu, Mar 25, 2010 @ 01:00 PM - 02:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Large tuning of birefringence in two strip silicon waveguidesvia optomechanical motion Jing Ma An optomechanical method is presented to tune phase birefringence in parallel silicon strip waveguides. We first calculate the deformation of suspended, parallel strip waveguides due to optical forces. We optimize the frequency and polarization of the pump light to obtain a 9nm deformation for an optical power of 20mW. Widely tunable phase birefringence can be achieved by varying the pump power, with maximum values of 0.026. The giant phase birefringence allows linear to circular polarization conversion within 30µm for a pump power of 67mW. In-Plane Thermally Tuned Silicon-on-Insulator Wavelength Selective ReflectorLawrence StewartThe transparency of silicon at communications wavelengths makes it an ideal choice for low loss optical devices; however, silicon suffers from few and comparatively weak tuning methods. Free carrier injection or depletion are widely used and are suitable for high speed modulators, but these devices are ultimately limited by free carrier induced absorption effects. While a much slower process, thermal tuning allows for large refractive index changes with minimal changes in optical absorption. A thermally tunable silicon-on-insulator wavelength selective reflector is proposed for an application as a mirror in an integrated tunable laser. Simulations and recent experimental results of thermally tuned microring devices will be presented.
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Jing Ma
-
Low Power Compact Servers
Thu, Mar 25, 2010 @ 04:00 PM - 06:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Distinguished Lecturer SeriesDr. Trevor Mudge,
University of MichiganABSTRACT
Trevor Mudge received a Ph.D. in Computer Science from the University of Illinois.
Since then he has been at the University of Michigan. He was named the Bredt Professor of Engineering after a ten year term as Director of the Advanced Computer Architecture Laboratory -- a group of a dozen faculty and 80 graduate students. He is author of numerous papers on computer architecture, programming languages, VLSI design, and computer vision. He has also chaired 42 theses in these areas. He is a Fellow of the IEEE, a member of the ACM, the IET, and the British Computer Society.BIOGRAPHY
With power and cooling becoming an increasingly costly part of the operating cost of a server, the old trend of striving for higher performance with little regard for power is over. Emerging semiconductor process technologies, multicore architectures, and new interconnect technology provide an avenue for future servers to become low power, compact, and possibly mobile. In our talk we examine three techniques for achieving low power: 1) Near threshold operation; 2) 3D die stacking; and 3) replacing DRAM with Flash memory.Lecture 4:00PM
Reception to follow at 5:00PM in SAL LobbyLocation: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Estela Lopez
