Guest Editors’ Introduction:
Application-Specific Systemon-a-Chip Multiprocessors Wayne Wolf
Ahmed A. Jerraya
Princeton University
TIMA Laboratory THIS SPECIAL TRACK introduces new results in the emerging area of application-specific SOC multiprocessors. These new systems are emerging because of a technology push and a demand pull. On the technology side, manufacturers can produce chips with hundreds of millions of transistors, several powerful processors, and megabytes of onchip memory. On the demand side, new markets such as telecommunications and multimedia demand huge processing power. Harnessing the computational resources provided by VLSI technology, designers can create single-chip multiprocessors for new applications that are not feasible with multichip systems. The six articles in this special track cover a broad spectrum of approaches to the multiprocessor SOC challenge. In “Colif: A Design Representation for Application-Specific Multiprocessor SOCs,” Wander O. Cesário et al. consider the challenges posed in describing large digital systems and present a new design representation for SOCs. “Viper: A Multiprocessor SOC for Advanced Set-Top Box and Digital TV Systems,” by Santanu Dutta, Rune Jensen, and Alf Rieckmann, describes a chip design targeted toward digital television. In “Automating the Design of SOCs Using Cores,” Reinaldo A. Bergamaschi et al. present an approach for effectively using and reusing components in multiprocessor SOCs. In “Energy-Aware Runtime Scheduling for Embedded Multiprocessor SOCs,” Peng Yang et al. describe new ways to design energy-efficient multiprocessor SOCs. This special track continues in the JanuaryFebruary 2002 issue with two more articles: “A Complete Strategy for Testing an On-Chip Multiprocessor Architecture,” by Chouki Aktouf,
describes new approaches to the challenge of testing multiprocessor SOCs. And “A LargeArea Integrated Multiprocessor System for Video Applications,” by Markus Rudack et al., describes a multiprocessor architecture for video applications. SOCs are perhaps the major challenge in VLSI systems today, and SOC technology will open up many new applications and markets. ■
September–October 2001
0740-7475/01/$10.00 © 2001 IEEE
Wayne Wolf is an electrical engineering professor at Princeton University and chief scientist at MediaWorks Technology. His research interests include SOCs, multimedia computing, embedded computing, and VLSI CAD. Wolf has a BS, MS, and PhD in electrical engineering from Stanford University.
Ahmed A. Jerraya leads the System-Level Synthesis Group at TIMA Laboratory in Grenoble, France, and is research director of the National Center for Scientific Research. His research interests include SOCs and system-level specification languages. Jerraya has a Dr Ing in computer sciences from the University of Grenoble, France, and a Dipl Ing in computer science from the University of Tunis, Tunisia. Direct questions or comments about this special issue to Wayne Wolf, Dept. of Electrical Engineering, Princeton University, Princeton, NJ 08544-5263;
[email protected].
7
