A Fully Parallel 1-Mb CAM LSI for Real-Time Pixel-Parallel Image Processing

Takeshi Ikenaga, Takeshi Ogura

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

For real-time image-processing applications, a highly parallel system that exploits parallelism is desirable. A content addressable memory (CAM), or an associative processor, that can perform various types of parallel processing with words as the basic unit is a promising component for creating such a system because of its suitability for LSI implementation. Conventional CAM LSI's, however, have neither efficient function nor enough capacity for pixel-parallel processing. This paper describes a fully parallel 1-Mb CAM LSI. It has advanced functions for processing various pixel-parallel algorithms, such as mathematical morphology and discrete-time cellular neural networks. Moreover, since it has 16-K words, or processing elements (PE's), which can process 128 × 128 pixels in parallel, a board-sized pixel-parallel image-processing system can be implemented using several chips. A chip capable of operating at 56 MHz and 2.5 V was fabricated using 0.25-μm full-custom CMOS technology with five aluminum layers. A total of 15.5 million transistors have been integrated into a 16.1× 17.0 mm chip. Typical power dissipation is 0.25 W. Processing performance of various update and data transfer operations is 3-640 GOPS. This CAM LSI will make a significant contribution to the development of compact, high-performance image-processing systems.

Original languageEnglish
Pages (from-to)536-543
Number of pages8
JournalIEEE Journal of Solid-State Circuits
Volume35
Issue number4
DOIs
Publication statusPublished - 2000 Apr

Fingerprint

Associative storage
Image processing
Pixels
Processing
Cellular neural networks
Mathematical morphology
Data transfer
Parallel algorithms
Energy dissipation
Transistors
Aluminum

Keywords

  • Associative processor
  • Content addressable memory (CAM)
  • Discrete-time cellular neural networks
  • Mathematical morphology
  • Multiple data (SIMD)
  • Real-time image processing
  • Single instruction

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

A Fully Parallel 1-Mb CAM LSI for Real-Time Pixel-Parallel Image Processing. / Ikenaga, Takeshi; Ogura, Takeshi.

In: IEEE Journal of Solid-State Circuits, Vol. 35, No. 4, 04.2000, p. 536-543.

Research output: Contribution to journalArticle

@article{323aa29dbaf547c38dd4d0fe06c718e6,
title = "A Fully Parallel 1-Mb CAM LSI for Real-Time Pixel-Parallel Image Processing",
abstract = "For real-time image-processing applications, a highly parallel system that exploits parallelism is desirable. A content addressable memory (CAM), or an associative processor, that can perform various types of parallel processing with words as the basic unit is a promising component for creating such a system because of its suitability for LSI implementation. Conventional CAM LSI's, however, have neither efficient function nor enough capacity for pixel-parallel processing. This paper describes a fully parallel 1-Mb CAM LSI. It has advanced functions for processing various pixel-parallel algorithms, such as mathematical morphology and discrete-time cellular neural networks. Moreover, since it has 16-K words, or processing elements (PE's), which can process 128 × 128 pixels in parallel, a board-sized pixel-parallel image-processing system can be implemented using several chips. A chip capable of operating at 56 MHz and 2.5 V was fabricated using 0.25-μm full-custom CMOS technology with five aluminum layers. A total of 15.5 million transistors have been integrated into a 16.1× 17.0 mm chip. Typical power dissipation is 0.25 W. Processing performance of various update and data transfer operations is 3-640 GOPS. This CAM LSI will make a significant contribution to the development of compact, high-performance image-processing systems.",
keywords = "Associative processor, Content addressable memory (CAM), Discrete-time cellular neural networks, Mathematical morphology, Multiple data (SIMD), Real-time image processing, Single instruction",
author = "Takeshi Ikenaga and Takeshi Ogura",
year = "2000",
month = "4",
doi = "10.1109/4.839913",
language = "English",
volume = "35",
pages = "536--543",
journal = "IEEE Journal of Solid-State Circuits",
issn = "0018-9200",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A Fully Parallel 1-Mb CAM LSI for Real-Time Pixel-Parallel Image Processing

AU - Ikenaga, Takeshi

AU - Ogura, Takeshi

PY - 2000/4

Y1 - 2000/4

N2 - For real-time image-processing applications, a highly parallel system that exploits parallelism is desirable. A content addressable memory (CAM), or an associative processor, that can perform various types of parallel processing with words as the basic unit is a promising component for creating such a system because of its suitability for LSI implementation. Conventional CAM LSI's, however, have neither efficient function nor enough capacity for pixel-parallel processing. This paper describes a fully parallel 1-Mb CAM LSI. It has advanced functions for processing various pixel-parallel algorithms, such as mathematical morphology and discrete-time cellular neural networks. Moreover, since it has 16-K words, or processing elements (PE's), which can process 128 × 128 pixels in parallel, a board-sized pixel-parallel image-processing system can be implemented using several chips. A chip capable of operating at 56 MHz and 2.5 V was fabricated using 0.25-μm full-custom CMOS technology with five aluminum layers. A total of 15.5 million transistors have been integrated into a 16.1× 17.0 mm chip. Typical power dissipation is 0.25 W. Processing performance of various update and data transfer operations is 3-640 GOPS. This CAM LSI will make a significant contribution to the development of compact, high-performance image-processing systems.

AB - For real-time image-processing applications, a highly parallel system that exploits parallelism is desirable. A content addressable memory (CAM), or an associative processor, that can perform various types of parallel processing with words as the basic unit is a promising component for creating such a system because of its suitability for LSI implementation. Conventional CAM LSI's, however, have neither efficient function nor enough capacity for pixel-parallel processing. This paper describes a fully parallel 1-Mb CAM LSI. It has advanced functions for processing various pixel-parallel algorithms, such as mathematical morphology and discrete-time cellular neural networks. Moreover, since it has 16-K words, or processing elements (PE's), which can process 128 × 128 pixels in parallel, a board-sized pixel-parallel image-processing system can be implemented using several chips. A chip capable of operating at 56 MHz and 2.5 V was fabricated using 0.25-μm full-custom CMOS technology with five aluminum layers. A total of 15.5 million transistors have been integrated into a 16.1× 17.0 mm chip. Typical power dissipation is 0.25 W. Processing performance of various update and data transfer operations is 3-640 GOPS. This CAM LSI will make a significant contribution to the development of compact, high-performance image-processing systems.

KW - Associative processor

KW - Content addressable memory (CAM)

KW - Discrete-time cellular neural networks

KW - Mathematical morphology

KW - Multiple data (SIMD)

KW - Real-time image processing

KW - Single instruction

UR - http://www.scopus.com/inward/record.url?scp=0242425176&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242425176&partnerID=8YFLogxK

U2 - 10.1109/4.839913

DO - 10.1109/4.839913

M3 - Article

VL - 35

SP - 536

EP - 543

JO - IEEE Journal of Solid-State Circuits

JF - IEEE Journal of Solid-State Circuits

SN - 0018-9200

IS - 4

ER -