High Performance Multiprocessor Architecture Design Methodology for Application-Specific Embedded Systems

Authors:
Syed Saif Abrar
Affiliations:
-
Venue:
HiPC '02 Proceedings of the 9th International Conference on High Performance Computing
Year:
2002

Citing 12
Cited 0

Bus-invert coding for low-power I/O

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Heterogeneous Simulation—Mixing Discrete-Event Models with Dataflow

Journal of VLSI Signal Processing Systems - Special issue on the rapid prototyping of application specific signal processors (RASSP) program
An integrated design environment for performance and dependability analysis

DAC '97 Proceedings of the 34th annual Design Automation Conference
RASSP virtual prototyping of DSP systems

DAC '97 Proceedings of the 34th annual Design Automation Conference
YAPI: application modeling for signal processing systems

Proceedings of the 37th Annual Design Automation Conference
Using a Programming Language for Digital System Design

IEEE Design & Test
AMBA: Enabling Reusable On-Chip Designs

IEEE Micro
Asymptotic Zero-Transition Activity Encoding for Address Busses in Low-Power Microprocessor-Based Systems

GLS '97 Proceedings of the 7th Great Lakes Symposium on VLSI
PHIDEO: a silicon compiler for high speed algorithms

EURO-DAC '91 Proceedings of the conference on European design automation
Wavefront Array Processor: Language, Architecture, and Applications

IEEE Transactions on Computers
Why Systolic Architectures?

Computer
VLSI implementations of image and video multimedia processing systems

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a methodology for the design of application-specific multiprocessor systems. The methodology, named AIM, guides a designer to select the right heterogeneous architecture starting from a set of target applications. The methodology distinguishes between applications and architectures that are modeled as Kahn Process Networks and cycle-accurate bit-true models, respectively. A gradual mapping of applications over architectures is defined to analyze the performance of the resulting system by simulation. As a consequence, functionally complete system is always available with the designer without the overwhelming issues related with the multiprocessor architectures. The described methodology is illustrated through the design of a multiprocessor architecture for an MPEG-1 audio decoder application.