A SIMD neural network processor for image processing

Dongsun Kim, Hyunsik Kim, Hongsik Kim, Gunhee Han, Duckjin Chung

Research output: Contribution to journalConference article

7 Citations (Scopus)

Abstract

Artificial Neural Networks (ANNs) and image processing requires massively parallel computation of simple operator accompanied by heavy memory access. Thus, this type of operators naturally maps onto Single Instruction Multiple Data (SIMD) stream parallel processing with distributed memory. This paper proposes a high performance neural network processor whose function can be changed by programming. The proposed processor is based on the SIMD architecture that is optimized for neural network and image processing. The proposed processor supports 24 instructions, and consists of 16 Processing Units (PUs) per chip. Each PU includes 24-bit 2K-word Local Memory (LM) and a Processing Element (PE). The proposed architecture allows multichip expansion that minimizes chip-to-chip communication bottleneck. The proposed processor is verified with FPGA implementation and the functionality is verified with character recognition application.

Original languageEnglish
Pages (from-to)665-672
Number of pages8
JournalLecture Notes in Computer Science
Volume3497
Issue numberII
DOIs
Publication statusPublished - 2005
EventSecond International Symposium on Neural Networks: Advances in Neural Networks - ISNN 2005 - Chongqing, China
Duration: 2005 May 302005 Jun 1

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'A SIMD neural network processor for image processing'. Together they form a unique fingerprint.

Cite this