SP-CNN: A SCALABLE AND PROGRAMMABLE CNN-BASED ACCELERATOR

被引：14

作者：

Manatunga, Dilan ^{[1
]}

Kim, Hyesoon ^{[1
]}

Mukhopadhyay, Saibal ^{[2
]}

机构：

[1] Georgia Inst Technol, Sch Comp Sci, Atlanta, GA 30332 USA

[2] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA

来源：

IEEE MICRO | 2015年 / 35卷 / 05期

基金：

美国国家科学基金会;

关键词：

CELLULAR NEURAL-NETWORKS;

D O I：

10.1109/MM.2015.121

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this article, the authors use a Cellular Neural Network (CNN)-A neural computing paradigm that is well suited for image processing applications-As a specialized accelerator for mobile computing. They propose SP-CNN, An architecture and a multiplexing algorithm that provides scalability to CNN architectures. They demonstrate the proposed multiplexing algorithms over six image processing benchmarks and present a performance analysis of SP-CNN.

引用

页码：42 / 50

页数：9

共 6 条

[1]

[Anonymous], 2010, SOFTWARE LIB CELLULA

[2] CELLULAR NEURAL NETWORKS - APPLICATIONS [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1273-1290

[3] CELLULAR NEURAL NETWORKS - THEORY [J].

CHUA, LO ;

YANG, L .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS, 1988, 35 (10) :1257-1272

[4] 24-GOPS 4.5-mm2 Digital Cellular Neural Network for Rapid Visual Attention in an Object-Recognition SoC [J].

Lee, Seungjin ;

Kim, Minsu ;

Kim, Kwanho ;

Kim, Joo-Young ;

Yoo, Hoi-Jun .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2011, 22 (01) :64-73

[5]

Mujtaba H., 2012, INTEL AIMS MOBILE SP

[6] DRAMSim2: A Cycle Accurate Memory System Simulator [J].

Rosenfeld, Paul ;

Cooper-Balis, Elliott ;

Jacob, Bruce .

IEEE COMPUTER ARCHITECTURE LETTERS, 2011, 10 (01) :16-19

← 1 →