A Multi-Level Transformation Approach to HW/SW Codesign: A Case Study

Authors:
Tommy King-Yin Cheung;Graham Hellestrand;Prasert Kanthamanon
Affiliations:
VLSI and Systems Technology Laboratory, School of Computer Science and Engineering, University of New South Wales, Kensington 2052, Australia;VLSI and Systems Technology Laboratory, School of Computer Science and Engineering, University of New South Wales, Kensington 2052, Australia;VLSI and Systems Technology Laboratory, School of Computer Science and Engineering, University of New South Wales, Kensington 2052, Australia
Venue:
CODES '96 Proceedings of the 4th International Workshop on Hardware/Software Co-Design
Year:
1996

Citing 5
Cited 3

Can programming be liberated from the von Neumann style?: a functional style and its algebra of programs

Communications of the ACM
Specification and Design of Embedded Hardware-Software Systems

IEEE Design & Test
Automating the Design of Algorithm

Proceedings of the IFIP TC2/WG 2.1 State-of-the-Art Report on Formal Program Development
Deriving the Fast Fourier Algorithm by Calculation

Proceedings of the 1989 Glasgow Workshop on Functional Programming
muFP, a language for VLSI design

LFP '84 Proceedings of the 1984 ACM Symposium on LISP and functional programming

An algebraic hardware/software partitioning algorithm

Journal of Computer Science and Technology
A Safe, Accurate Intravenous Infusion Control System

IEEE Micro
ParTS: A Partitioning Transformation System

FM '99 Proceedings of the Wold Congress on Formal Methods in the Development of Computing Systems-Volume II

Quantified Score

Hi-index	0.01

Visualization

Abstract

This reported work applies a transformational synthesis approach to hardware/software codesign. In this approach, the process of algorithm design is coupled early on with hardware design to allow for a complete design space exploration. Both the specification and the transformation mechanisms are encoded in a functional notation, called form, which facilitates algorithmic derivation, structural transformation and verification. In the algorithmic derivation phase, possible computational schedules for a given application function are generated from a partial specification of the target architecture. At the hardware level, structural transformations are applied to explore possible datapath designs, where different designs yield different performance and cost. Other design metrics such as interface buffer size, software code size and data size etc. are also included to determine analytically a hardware/ software partition.