Keynote Speakers
Rajesh Gupta (UCSD)
Sense & Adapt: Our evolving models of computing machines up and down the abstract stack
A modern computing system is an elaborate stack of hardware and software with stable intermediate points that enable a platform builder to construct all sorts of machines with 'commodity' hardware and software pieces. Unfortunately, this extraordinary flexibility comes at a huge cost: two to three orders of magnitude in efficiency and cost. This is far beyond the range of most engineered systems. This observation has been at the root of our quest for new architectures — from modifications to von Neumann to data-flow variants — and new ways of building/synthesizing hardware pieces for new machines — co-processors to synthesized accelerators. This talk pulls the most interesting and promising vectors of research in this line of thinking to outline a vision of emerging machines: that are engineered less but enabled more to sense and adapt the computation to the environment in which they are placed.
Rajesh K. Gupta is a QUALCOMM professor in Computer Science and Engineering at UC San Diego. His research focus is on energy efficiency from algorithms, devices to systems that scale from IC chips, data centers to commercial buildings. His past contributions include SystemC modeling and SPARK parallelizing high-level synthesis, both of which have been incorporated into industrial practice. Earlier Gupta lead or co-lead DARPA-sponsored efforts under the Data Intensive Systems (DIS) and Power Aware Computing and Communications (PACC) programs on role of adaptation in energy efficient system architectures. His ongoing projects are focused on mitigating microelectronic variability and creating non-volatile storage/memory systems. In recent years, Gupta and his students have received a best paper award at IEEE/ACM DCOSS’08 and a best demonstration award at IEEE/ACM IPSN/SPOTS’05. Gupta received a BTech in EE from IIT Kanpur, MS in EECS from UC Berkeley and a PhD in Electrical Engineering from Stanford University. Gupta is a Fellow of the IEEE. Gupta serves as chair of Computer Science and as associate director of the Qualcomm Institute at UCSD.
Björn Brandenburg (Max Planck Institute for Software Systems)
Quo vadis, RTOS? A look at the design of present and future real-time operating systems for the multicore age
With the advent of the multicore age, real-time operating system (RTOS) developers are faced with the challenge of having to fundamentally rethink the design of their systems. How to "best" schedule the (increasingly many) available cores? How to enable efficient inter-core synchronization? What about tradeoffs in predictability, flexibility, and performance? More often than not, the "best practices" and design choices made in uniprocessor systems (and codified in RTOS standards) are ill-suited for multicore platforms. In response, the real-time literature has accumulated a bewildering array of new potential solutions — including numerous proposals for global, clustered, partitioned, and semi-partitioned scheduling approaches and various suspension- and spin-based locking protocols, to name just a few categories. However, the right choice in practice is often far from obvious, owing both to the intricate interplay of analytical and engineering concerns in a typical RTOS, and to a not insignificant gap between theory and practice in the real-time literature. Fortunately, research in the past decade has illuminated many of these issues and a clearer picture has emerged. In this talk, based on our experience building LITMUS^RT, I will first illustrate some of the major differences between theory and practice and their implications, and then survey and summarize some of the key results and observations that inform the current state of the art in multiprocessor RTOS design. Finally, I will highlight some of the most pressing open problems and shortcomings in current systems, and speculate on likely trends in the next decade of RTOS research.
Björn Brandenburg is a tenure-track research group leader (a position equivalent to a US assistant professorship) at the Max Planck Institute for Software Systems (MPI-SWS) in Kaiserslautern, Germany. He joined MPI-SWS in 2011 after obtaining his PhD from the University of North Carolina at Chapel Hill, where he worked under the direction of Jim Anderson on multiprocessor real-time systems. His research is focused on operating systems for predictable multiprocessor real-time systems and spans from the analytical foundations on the one hand, to practical systems and implementation issues on the other hand, with a special focus on real-time locking and scheduling. His dissertation work was recognized with three competitive dissertation awards (UNC Dean’s Distinguished Dissertation Award 2012, CGS/ProQuest Distinguished Dissertation Award 2012, EDAA Outstanding Dissertations Award 2012). Since 2007, he has (co-)authored more than 40 peer-reviewed papers, three of which were recognized with best-paper awards (RTSS, EMSOFT, SIES). He is the lead developer and maintainer of LITMUSRT (http://www.litmus-rt.org), a real-time extension of the Linux kernel that has been continuously maintained since 2006 and used in numerous published studies (8 PhD and Master's theses and more than 40 papers by groups in North & South America, Asia, and Europe).
Mary Baker (HP Labs)
Stepping Stones to an Easier World
New technology brings us many wonders and also many frustrations and obstacles. In this talk I describe two mobile and wearable research projects that attempt to remove some of these obstacles in our daily lives. The first project, Mobius, tackles frustrations around authentication. Every day we must prove our right to access online sites and services, devices such as smart phones and PCs, and physical objects and infrastructure such as cars and doors. We performed a wearable digital diary study to gather information about people's authentication behavior, their likes and dislikes, and what does or doesn't work for them. Results indicate the feasibility of reducing the user authentication burden with a "universal authenticator'' — a wearable device that assumes the responsibility of authenticating its owner to restricted resources, both physical and virtual. Mobius is our prototype design of a universal authenticator in the form of a perpetually powered ring. The second project, the Sound of Silence, makes it easier to share content among and otherwise communicate with participants in an event like a formal meeting, a chance encounter, or a broadcast TV or radio program. We compare simple privacy-preserving "silence signatures" gathered on mobile devices to capture the dynamically changing group membership of such events. For both of these projects I'll describe what worked, what failed, and what we should worry about in the future.
Mary Baker is a senior research scientist at HP Labs in Palo Alto. Her research interests include distributed systems, wearables, digital preservation, and mobile systems and applications. Baker received her Ph.D. in Computer Science from the University of California at Berkeley. Before working at HP, she ran the MosquitoNet mobile research group at Stanford University. She is a founding member of the IEEE Pervasive Computing editorial board and the SNIA technical working group focused on digital preservation.
Paul Zimmerman (Intel)
Driving Innovation in Education
During the keynote Paul will address general areas of interest in education. Paul will talk about Innovation over time, some of the challenges innovators face, and how we might translate innovation into Higher Education. Finally there will be a proposal of a Government, Industry, and University partnership to drive the innovation.
''Paul Zimmerman received his BS, MS and Ph.D. in Chemistry from the University of Pittsburgh. Paul also completed an MBA in 2001 at Arizona State University. Paul has worked for Intel Corporation since 1994, starting in the Portland Technology Development. During his time at Intel Paul has worked to develop materials tools and processes for FEOL, BEOL, metrology and lithography. Paul has co-authored over 80 publications and has been awarded 14 patents for development of various materials and processes.
Currently, Paul manages Intel’s University Program Office. UPO works with Intel’s business units to drive the latest technology into higher education ensuring the preparation the most capable and well-prepared workforce to drive a global economy.''