Performance of an embedded optical vector matrix multiplication processor architecture

被引：2
|
作者：
Yang, C. [1 ,2 ]
Cui, G. X. [2 ]
Huang, Y. Y. [1 ,2 ]
Wu, L. [2 ]
Yang, H. [1 ]
Zhang, Y. H. [2 ]
机构：
[1] Chinese Acad Sci, Inst Semicond, Beijing 100083, Peoples R China
[2] Chinese Acad Sci, Suzhou Inst Nanotech & Nanobion, Suzhou 215125, Peoples R China
来源：
IET OPTOELECTRONICS | 2010年 / 4卷 / 04期
关键词：
D O I：
10.1049/iet-opt.2009.0012
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
An embedded architecture of optical vector matrix multiplier (OVMM) is presented. The embedded architecture is aimed at optimising the data flow of vector matrix multiplier (VMM) to promote its performance. Data dependence is discussed when the OVMM is connected to a cluster system. A simulator is built to analyse the performance according to the architecture. According to the simulation, Amdahl's law is used to analyse the hybrid opto-electronic system. It is found that the electronic part and its interaction with optical part form the bottleneck of system.
引用
收藏
页码：159 / 164
页数：6
相关论文
共 50 条
  • [1] An Embedded Optical Vector Matrix Multiplication Processor
    Fuhui-kai
    INFORMATION TECHNOLOGY APPLICATIONS IN INDUSTRY, PTS 1-4, 2013, 263-266 : 1334 - 1337
  • [2] Controlled optical fibre processor for matrix/vector multiplication
    Pilipovich, VA
    Esman, AK
    Goncharenko, IA
    Posedko, VS
    Solonovich, IF
    SECOND INTERNATIONAL CONFERENCE ON OPTICAL INFORMATION PROCESSING, 1996, 2969 : 125 - 128
  • [3] Optimizing matrix multiplication for a short-vector SIMD architecture - CELL processor
    Kurzak, Jakub
    Alvaro, Wesley
    Dongarra, Jack
    PARALLEL COMPUTING, 2009, 35 (03) : 138 - 150
  • [4] Combinatorial Optimization Using Electro-Optical Vector by Matrix Multiplication Architecture
    Tamir, Dan E.
    Shaked, Natan T.
    Geerts, Wilhelmus J.
    Dolev, Shlomi
    OPTICAL SUPERCOMPUTING, PROCEEDINGS, 2009, 5882 : 130 - +
  • [5] 4-QUADRANT OPTICAL MATRIX VECTOR MULTIPLICATION MACHINE AS A NEURAL-NETWORK PROCESSOR
    ABRAMSON, S
    SAAD, D
    MAROM, E
    KONFORTI, N
    APPLIED OPTICS, 1993, 32 (08): : 1330 - 1337
  • [6] Processor-efficient sparse matrix-vector multiplication
    Heath, LS
    Ribbens, CJ
    Pemmaraju, SV
    COMPUTERS & MATHEMATICS WITH APPLICATIONS, 2004, 48 (3-4) : 589 - 608
  • [7] DENSE MATRIX-VECTOR MULTIPLICATION ON THE CUDA ARCHITECTURE
    Fujimoto, Noriyuki
    PARALLEL PROCESSING LETTERS, 2008, 18 (04) : 511 - 530
  • [8] BINARY-ENCODED VECTOR MATRIX MULTIPLICATION ARCHITECTURE
    ZHOU, CH
    LIU, LR
    WANG, ZJ
    OPTICS LETTERS, 1992, 17 (24) : 1800 - 1802
  • [9] An optical processor for matrix-by-vector multiplication: an application to the distance geometry problem in 1D
    Hengeveld, S. B.
    da Silva, N. Rubiano
    Goncalves, D. S.
    Ribeiro, P. H. Souto
    Mucherino, A.
    JOURNAL OF OPTICS, 2022, 24 (01)
  • [10] Optical vector matrix processor component characterization
    Sunderlin, TA
    Carter, JA
    ADVANCES IN OPTICAL INFORMATION PROCESSING VII, 1996, 2754 : 262 - 270
12345