Special Issue Parallel Processing On Vlsi Arrays

Parallel Processing on VLSI Arrays

Guest Editor: JOSEF A. NOSSEK This is a special issue of the Journal of VLSI Signal Processing comprising eight contributions invited for publica tion on the basis of novel work presented in a special session on "Parallel Processing on VLSI Arrays" at the International Symposium on Circuits and Systems (ISCAS) held in New Orleans in May 1990. Massive parallelism to cope with high-speed requirements stemming from real-time applications and the restrictions in architectural and circuit design, such as regularity and local connectedness, brought about by the VLSI technology are the key questions addressed in these eight papers. They can be grouped into three subsections elaborating on: • Simulation of continuous physical systems, i. e. , numerically solving partial differential equations. • Neural architectures for image processing and pattern recognition. • Systolic architectures for implementing regular and irregular algorithms in VLSI technology. The paper by A. Fettweis and O. Nitsche advocates a signal processing approach for the numerical integration of partial differential equations (PD Es). It is based on the principles of multidimensional wave digital filters (MDWDFs) thereby preserving the passivity of energy dissipating physical systems. It is particularly suited for systems ofPDEs involving time and finite propagation speed. The basic ideas are explained using Maxwell's equa tions as a vehicle for the derivation of a multidimensional equivalent circuit representing the spatially infinitely extended arrangement with only very few circuit elements.

Special Issue--parallel Processing on VLSI Arrays

Parallel Computing Using Optical Interconnections

Advances in optical technologies have made it possible to implement optical interconnections in future massively parallel processing systems. Photons are non-charged particles, and do not naturally interact. Consequently, there are many desirable characteristics of optical interconnects, e.g. high speed (speed of light), increased fanout, high bandwidth, high reliability, longer interconnection lengths, low power requirements, and immunity to EMI with reduced crosstalk. Optics can utilize free-space interconnects as well as guided wave technology, neither of which has the problems of VLSI technology mentioned above. Optical interconnections can be built at various levels, providing chip-to-chip, module-to-module, board-to-board, and node-to-node communications. Massively parallel processing using optical interconnections poses new challenges; new system configurations need to be designed, scheduling and data communication schemes based on new resource metrics need to be investigated, algorithms for a wide variety of applications need to be developed under the novel computation models that optical interconnections permit, and so on. Parallel Computing Using Optical Interconnections is a collection of survey articles written by leading and active scientists in the area of parallel computing using optical interconnections. This is the first book which provides current and comprehensive coverage of the field, reflects the state of the art from high-level architecture design and algorithmic points of view, and points out directions for further research and development.