Panels & Demos & Distinguished Papers & ...
Industrial Session and Demo
Element CXI: Exploring Elemental Computing in Academia
Virginia Tech., USA
The ElementCXI Elemental Computing Array (ECA) is composed of heterogeneous Elements that dynamically form specific computing structures on demand, simultaneously and in parallel, on each clock cycle. In addition, each Element has multiple contexts, so the combinations of elements and contexts create massive flexibility yet retains the efficiency missing in a multicore processor. By constantly configuring to match system and application demands, the ECA is inherently low power and high performance while spanning broad application spaces. At run time, code is dynamically placed into the ECA elements to work around defects on a device whether they were fabrication defects or came about later due to device wear out. Resiliency extends the useful lifetime of products and allows for graceful system degradation instead of catastrophic failure. The ECA combines four computational styles: sequential, data-flow, message-passing, and DMA in a rapidly-reconfigurable distributed system on a chip.
For academicians, this architecture provides a means of exploring many interesting research issues that cannot otherwise be investigated with other technologies, such as FPGAs and DSPs. Some of these issues include (a) true run-time reconfiguration and hardware virtualization, (b) resiliency and fault recovery, and (c) hardware operating systems. All of these factors will play an important role in the future of high-performance embedded computation, and will encourage us to rethink how contemporary media devices, radios, and networks are made. This presentation focuses on open research opportunities that have the potential of advancing core reconfigurable computing concepts. A set of academic tools will be presented and demonstrated that are readily extended for a variety of sandbox experiments.
Peter Athanas is a Professor in the Department of Electrical and Computer Engineering at Virginia Tech. His research interests include high-performance embedded computing, configurable computing, VLSI, and signal processing. Athanas received his BS degree in electrical engineering from The University of Toledo, his MS degree in electrical engineering from Rensselaer Polytechnic Institute, his Sc.M. degree in applied mathematics at Brown University, and a PhD. degree in electrical engineering from Brown University, where his work focused on configurable computing architectures and compilers. He currently serves as director of the Virginia Tech Configurable Computing Laboratory, and site director of the NSF Center for Reconfigurable High Performance Computing.