Revisiting bitwidth optimizations

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

Revisiting bitwidth optimizations

Source

International Symposium on Field Programmable Gate Arrays archive
Proceeding of the ACM/SIGDA international symposium on Field programmable gate arrays table of contents

Monterey, California, USA

POSTER SESSION: Processors & CAD tools table of contents

Pages 278-278

Year of Publication: 2009

ISBN:978-1-60558-410-2

Authors

Jason Cong	UCLA Computer Science Department, Los Angeles, CA, USA
Karthik Gururaj	UCLA Computer Science Department, Los Angeles, CA, USA
Bin Liu	UCLA Computer Science Department, Los Angeles, CA, USA
Chunyue Liu	UCLA Computer Science Department, Los Angeles, CA, USA
Yi Zou	UCLA Computer Science Department, Los Angeles, CA, USA
Zhiru Zhang	AutoESL Design Technologies, Los Angeles, CA, USA
Sheng Zhou	AutoESL Design Technologies, Los Angeles, CA, USA

Sponsors

SIGDA: ACM Special Interest Group on Design Automation
ACM: Association for Computing Machinery

Publisher

ACM New York, NY, USA

Bibliometrics

Downloads (6 Weeks): n/a, Downloads (12 Months): n/a, Citation Count: 0

Additional Information:

abstract index terms collaborative colleagues

Tools and Actions:	Review this Article Save this Article to a Binder Display Formats: BibTeX EndNote ACM Ref

DOI Bookmark:	Use this link to bookmark this Article: http://doi.acm.org/10.1145/1508128.1508182 What is a DOI?

ABSTRACT

This paper revisits the classical bitwidth optimization problem for fixed-point designs. Our approach also starts from static analysis (range analysis and precision analysis) techniques. We first point out that AA-based precision analysis, which is widely used in many previous works, are not correctly applied for some corner cases. We propose to use interval coefficients to model the sensitivity (the mathematic form is similar to classical generalized interval arithmetic) to correct those issues. Based on the analysis, we use a convex optimization problem to optimize the area costs. In the formulation, we also allow different bitwidths for the multiple uses of the same signal. We get an additional 2% to 3% area reduction compared with previous AA-based analysis and optimizations. We also conduct some optimality study to see how much the gap between the current methods and the possible optimal point is.

INDEX TERMS

Primary Classification:
B. Hardware
B.7 INTEGRATED CIRCUITS
B.7.2 Design Aids