 |
Alternative Computing Day 2009  |
| Ben-Gurion University |
Alternative Computing Day 2009
Abstracts and Bios
Wavelength addressing, its physical implementation, and its application in distributed computing networks
Aharon Agranat, Hebrew University
Abstract:
The fact that photons of different wavelengths do not interact can be exploited as a routing paradigm by which each destination is allocated a specific wavelength. Thus, data packets transmitted at a given wavelength will reach their destination without the need for active routing operations along the way. However, simplistic implementation of wavelength addressing in a parallel computing network is ineffective due to its seemingly low scalability, high latency, and cost. It will be shown that these limitations can be obviated by applying the concepts of the laser power grid, and the ORTA multiplexing technique. The underlying for the physical implementation of these concepts by using Electroholography will be outlined. Finally, architecture for a storage area network based on wavelength addressing will be shown.
Bio:
Professor Aharon J. Agranat is the chairman of the department of Applied Physics, the director of the Brojde Center for Innovative Engineering and Computer Science, and the incumbent of the N. Jaller chair of Applied Science at the Hebrew University of Jerusalem. Agranat holds a B.Sc degree in physics and mathematics (1977), an M.Sc degree in Applied Physics (1980), and a PhD degree in physics (1986) all from the Hebrew University of Jerusalem. From 1986 to 1997 he was a senior research fellow and a senior visiting research associate at the California Institute of Technology (Caltech). In Caltech he worked on the development of microelectronic artificial neural networks based on charge transfer devices which he invented, and the investigation of paraelectric photorefractive crystals. In 1991 he joined the faculty of the Hebrew University of Jerusalem and founded the optoelectronic computing laboratory. Agranat is the inventor of Electroholography and the KLTN crystal for which he was awarded the Discover Innovation Award (awarded by the Discover magazine and the Christopher Columbus Society) for the leading invention in the area of communication for the year 2001. He is a Fellow member of the Optical Society of America. He is a member of the Hebrew University Interdisciplinary Center of Neuro-Computing, and an associate editor of the international journal “Fiber and Integrated Optics”. Agranat is the author of many scientific papers, and holds 20 patents in the areas of microelectronics, optoelectronics and materials science.
Quantum Computation - where did we start, where are we going
Dorit Aharonov, Hebrew University
Abstract:
Everybody has heard about Shor's polynomial quantum algorithm for factoring. Not many are familiar with a line of exciting new quantum algorithms of the past few years, which, unlike Shor's algorithm, borrow their intuition from physics and apply it to problems of interest in various areas in science. The renewed connection between quantum computation and physics has also led to other exciting results ranging anywhere on the line between computer science and physics. I will provide a survey of old as well as new ideas in the area, starting from the very beginning: what is a quantum bit?
Bio:
Dorit Aharonov has done her BSc (Physics and Math) and PhD (Physics and computer science) in the Hebrew University of Jerusalem. Her Postdoctoral studies were in Princeton (one year at the IAS) and in Berkeley (one year at the CS department). She has been a faculty member in the CS department in the Hebrew university of Jerusalem since 2001. Her main current interests are quantum computation and quantum complexity, and the study of movement via Kung-Fu and Feldenkreiz.
Unguided Optical Communication Bus for Next Generation Computers
Shlomi Arnon, Ben Gurion University
Abstract:
The importance of high-end computer (HEC) development lies in its ability to solve complex problems in many areas of science and engineering. In order to develop the next generation of HEC, faster buses are required. However, faster buses are potentially unaffordable or unachievable with the further scaling of today’s electrical technology. Some of the parameters that prevent this further scaling include power dissipation, chip pin-out, RF interference, and clock propagation delay in addition to huge energy consumption. In order to overcome scaling limitations related to electrical buses, but without using cumbersome and bulky fiber optical links, the concept of unguided optical communication bus (UOCB) has been introduced. UOCB is a technology for transmitting information through material from one to many points without a waveguide while taking advantage of scattering and diffusion effects. This technology could be used as the optical infrastructure for a next generation computer mother board. But to extract the maximum potential of optical technology, mitigation algorithms for physical phenomena such as scattering and interference are required.
Bio:
Professor Shlomi Arnon is a faculty member in the Department of Electrical and Computer Engineering at Ben-Gurion University (BGU), Israel. There, in 2000, he established the Satellite and Wireless Communication Laboratory which has been under his directorship since then. During 1998-1999 Professor Arnon was a Postdoctoral Associate (Fulbright Fellow) at LIDS, Massachusetts Institute of Technology (MIT), Cambridge, USA. His research has produced more than fifty journal papers in the area of satellite, optical and wireless communication. During part of the summer of 2007, he worked at TU/e and PHILIPS LAB, Eindhoven, Nederland on a novel concept of a dual communication and illumination system. He was visiting professor during the summer of 2008 at TU Delft, Nederland. Prof. Arnon is a frequent invited speaker and program committee member at major IEEE and SPIE conferences in the US and Europe. He was an associate editor for the Optical Society of America - Journal of Optical Networks, on a special issue on optical wireless communication that appeared in 2006, and is now on the editorial board for the IEEE Journal on Selected Areas in Communications for a special issue on optical wireless communication. Professor Arnon continuously takes part in many national and international projects in the areas of satellite communication, remote sensing, cellular and mobile wireless communication. He consults regularly with start-up and well-established companies in the area of optical, wireless and satellite communication. In addition to research, Prof Arnon and his students work on many challenging engineering projects with especial emphasis on the humanitarian dimension. For instance, a long-standing project has dealt with developing a system to detect human survival after earthquakes, or Infant respiration monitoring system to prevent cardiac arrest and Apnea or Detection of falls in the case of epilepsy sufferers and elderly people.
Asymmetric Chip Multi-Core: The future Chip MultiProcessor (CMP)
Uri Weiser, Technion
Abstract:
Computational requirement is characterized by a wide range of diverse applications. This wide range of applications is applicable to all “PC” computing markets (e.g. Mobile, Desktop and Server). In many cases these applications coexist and run simultaneously on a specific system. The applications differ from each other by their practical requirements e.g. performance, BW, latency, power limitation, performance/power requirement, differential services etc. Essentially, these requirements differ from one application to the other (aka asymmetric) and call for reciprocal HW/OS implementation to enable a better response to the applications’ need. On the other hand, device’s power limitation will drive for Asymmetric HW. The diverse requirements and the change in HW calls for a new Asymmetric HW/OS approach. What should be HW/OS asymmetry approach? Should we start from applications’ requirements? Data Content based requirements? What should the HW look like? Asymmetric Processing elements (cores) – same ISA/Different ISA?, how should the applications’ Scheduling work? In this talk we will try to open a small window to the Asymmetric world and present some aspects and solutions. The talk seeks to stimulate discussion, debate and future work.
Bio:
Dr. Weiser is a visiting Professor at the Electrical Engineering department, the Technion IIT. Uri Weiser received the bachelor and master degrees in EE from the Technion and Ph.D in CS from the University of Utah, Salt Lake City. Professor Weiser worked at Intel from 1988-2006. At Intel, Weiser initiated the definition of the Pentium® processor, drove the definition of Intel's MMX™ technology, co-managed the a new Intel Microprocessor Design Center at Austin, Texas and formed an Advanced Media applications research activity. Weiser was appointed an Intel Fellow in 1996, in 2002 he became an IEEE Fellow and in 2005 an ACM Fellow. Prior to his career at Intel, Weiser worked for the Israeli Department of Defense (RAFAEL 1970-1984), as a research and system engineer and National Semiconductor Design Center in Israel (1984-1988), where he led the design of the NS32532 microprocessor. Uri’s major technical impact involve the first Pentium processor, the MMX, the Trace Cache, Nahalal (cache architecture), MC vs. MT machines, Asymmetry Cluster CMP and more. Uri is technically involve with several startups (e.g. Commex, Novatrans, Lucid and others). Professor Weiser was an Associate Editor of IEEEMicro Magazine (1992-2004) and is in the editorial board of Computer Architecture Letters.
Optical Solutions for Bounded NP-Complete Problems
Shlomi Dolev, BGU
Abstract:
Architectures for optical processors designed to solve bounded instances of NP-Complete problems are suggested. One approach mimics the traveling salesman by traveling beams that simultaneously examine the different possible paths. The design allows solving primitives such as the Hamiltonian path, Clique, Independent Set, Vertex Cover, Partition, 3-SAT, 3D-matching and the Permanent. The second approach uses optical vector matrix multiplication, representing all possible Hamiltonian paths by a matrix in a doubling prepossessing stage and multiplying the matrix by the instance of graph to be considered. The third approach uses a preprocessing stage in which O(n^2) masks are constructed, each representing a different edge in the graph. The choice and combination of the appropriate (small) subset of these masks yields the solution. The solution is rejected in cases where the combination of these masks totally blocks the light and accepted otherwise. The talk summarize joint works with: Hen Fitoussi, Ephraim Korach, Stephane Messika, Yuval Nir, Joseph Rosen, Natan Shaked, Galit Uzan and Amir Anter
Bio: Shlomi Dolev received his B.Sc. in Engineering and B.A. in Computer Science in 1984 and 1985, and his M.Sc. and D.Sc. in computer Science in 1990 and 1992 from the Technion Israel Institute of Technology. From 1992 to 1995 he was at Texas A&M University as a visiting research specialist. In 1995 he joined the Department of Mathematics and Computer Science at Ben-Gurion University where he is now an full professor. He was a visiting researcher/professor at MIT, DIMACS, and LRI, for several periods during summers. Shlomi is the author of the book ``self-stabilization'' published by the MIT Press. He published more than hundred journal and conference scientific articles, and served in the program committee of more than fifty conferences including: the ACM Symposium on Principles of Distributed Computing, and the International Symposium on DIStributed Computing. He is an associate editor of the IEEE Transactions on Computers, the AIAA Journal of Aerospace Computing, Information and Communication and a guest editor of the Distributed Computing Journal and Theoretical Computer Science. His research grants include IBM faculty awards, Intel academic grants, and the NSF. Shlomi established the computer science department at Ben-Gurion university, and served as the first chair of the department, where he now holds the Rita Altura trust chair in computer science. His current research interests include distributed computing, distributed systems, security and cryptography and communication networks; in particular the self-stabilization property of such systems. Recently, he is involved in optical computing research.
Molecular Syllogisms
Ehud Shapiro, Weizmann Institute
Abstract:
Autonomous programmable computing devices made of biological molecules hold the promise of interacting with the biological environment in future biological and medical applications. Previously, molecular implementations of finite automata and logic gates were developed. Here we show an autonomous programmable molecular system capable of performing simple logical deductions. Using molecular representations of facts such as Man(Socrates) (Socrates is a Man) and rules such as Mortal(X)<--Man(X) (Every Man is Mortal), the system can answer molecular queries such as Mortal(Socrates)? (Is Socrates Mortal?) and Mortal(X)? (Who is Mortal?). This molecular computing system compares favorably with previous systems in terms of expressive power, performance and precision. A compiler translates facts, rules and queries into their molecular representations and subsequently operates a robotic system that realizes the logical deductions and delivers the result to the user. This hybrid electronic-molecular system represents the first high-level computer programming language with a molecular-scale implementation.
Bio:
TBA
Learning from Bacteria about Information Processing
Eshel Ben-Jacob, Tel Aviv University
Abstract:
Bacteria, the first and most fundamental of all organisms, lead rich social life in complex hierarchical communities. Collectively, they gather information from the environment, learn from past experience, and take decisions. Bacteria do not store genetically all the information required for efficient responding to all possible environmental conditions. To solve the new encountered problems (challenges) posed by the environment, they first asses the problem via collective sensing, recall stored information of past experience and then execute distributed information processing of the 109-12 bacteria in the colony thus turning the colony into super-brain. Super-brain, because the billions of bacteria in the colony use sophisticated communication strategies to link the intracellular computation networks of each bacterium (including signaling path ways of billions of molecules) into a network of networks. I will then show illuminating movies of swarming intelligence of live bacteria in which they solve optimization problems that are beyond what we, human being, can solve with our most powerful computers. This will lead me to a discussion about the special nature of bacteria computational principles in comparison to our Turing Algorithm computational principles. If time will permit, I will show that we can learn from the bacteria about our brain. In particular that the crucial role of the neglected other side of the brain - distributed information processing of the astrocytes.
Bio:
TBA