Bit and word-level common subexpression elimination for the synthesis of linear computations

Akihiro Matsuura, Akira Nagoya

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we propose a transformation technique for the multiplications of one variable with multiple constants, which are frequently seen in the various applications of signal processing, image processing, and so forth. The method is based on the exploration of common subexpressions among constants and reduces the number of shifts, additions, and subtractions to implement linear computations with hardware. Our method searches for regularity among elements of a linear transform using matrix decomposition and generates a reduced data-flow graph which preserves the full regularity. We show experimental results obtained using Discrete Cosine Transform (DCT) and Fast Fourier Transform (FFT) and illustrate the effectiveness of the method.

Original languageEnglish
Pages (from-to)455-461
Number of pages7
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE81-A
Issue number3
Publication statusPublished - 1998
Externally publishedYes

Fingerprint

Data flow graphs
Discrete cosine transforms
Fast Fourier transforms
Elimination
Signal processing
Image processing
Regularity
Synthesis
Decomposition
Hardware
Matrix Decomposition
Flow Graphs
Discrete Cosine Transform
Subtraction
Fast Fourier transform
Data Flow
Search Methods
Signal Processing
Image Processing
Multiplication

Keywords

  • Common subexpression elimination
  • High-level synthesis
  • Linear transforms
  • Matrix decomposition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Information Systems

Cite this

@article{b8d1666184c7448887d093974e9942d2,
title = "Bit and word-level common subexpression elimination for the synthesis of linear computations",
abstract = "In this paper, we propose a transformation technique for the multiplications of one variable with multiple constants, which are frequently seen in the various applications of signal processing, image processing, and so forth. The method is based on the exploration of common subexpressions among constants and reduces the number of shifts, additions, and subtractions to implement linear computations with hardware. Our method searches for regularity among elements of a linear transform using matrix decomposition and generates a reduced data-flow graph which preserves the full regularity. We show experimental results obtained using Discrete Cosine Transform (DCT) and Fast Fourier Transform (FFT) and illustrate the effectiveness of the method.",
keywords = "Common subexpression elimination, High-level synthesis, Linear transforms, Matrix decomposition",
author = "Akihiro Matsuura and Akira Nagoya",
year = "1998",
language = "English",
volume = "E81-A",
pages = "455--461",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "3",

}

TY - JOUR

T1 - Bit and word-level common subexpression elimination for the synthesis of linear computations

AU - Matsuura, Akihiro

AU - Nagoya, Akira

PY - 1998

Y1 - 1998

N2 - In this paper, we propose a transformation technique for the multiplications of one variable with multiple constants, which are frequently seen in the various applications of signal processing, image processing, and so forth. The method is based on the exploration of common subexpressions among constants and reduces the number of shifts, additions, and subtractions to implement linear computations with hardware. Our method searches for regularity among elements of a linear transform using matrix decomposition and generates a reduced data-flow graph which preserves the full regularity. We show experimental results obtained using Discrete Cosine Transform (DCT) and Fast Fourier Transform (FFT) and illustrate the effectiveness of the method.

AB - In this paper, we propose a transformation technique for the multiplications of one variable with multiple constants, which are frequently seen in the various applications of signal processing, image processing, and so forth. The method is based on the exploration of common subexpressions among constants and reduces the number of shifts, additions, and subtractions to implement linear computations with hardware. Our method searches for regularity among elements of a linear transform using matrix decomposition and generates a reduced data-flow graph which preserves the full regularity. We show experimental results obtained using Discrete Cosine Transform (DCT) and Fast Fourier Transform (FFT) and illustrate the effectiveness of the method.

KW - Common subexpression elimination

KW - High-level synthesis

KW - Linear transforms

KW - Matrix decomposition

UR - http://www.scopus.com/inward/record.url?scp=0032024199&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032024199&partnerID=8YFLogxK

M3 - Article

VL - E81-A

SP - 455

EP - 461

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 3

ER -