Performance of an embedded optical vector matrix multiplication processor architecture


Autoria(s): Yang C (Yang C.); Cui GX (Cui G. X.); Huang YY (Huang Y. Y.); Wu L (Wu L.); Yang H (Yang H.); Zhang YH (Zhang Y. H.)
Data(s)

2010

Resumo

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.

Submitted by 阎军 (yanj@red.semi.ac.cn) on 2010-09-07T11:57:46Z No. of bitstreams: 1 Performance of an embedded optical vector matrix multiplication processor architecture.pdf: 534672 bytes, checksum: 7dc8b542e4e4aee7da17af2844ed0327 (MD5)

Approved for entry into archive by 阎军(yanj@red.semi.ac.cn) on 2010-09-07T11:58:40Z (GMT) No. of bitstreams: 1 Performance of an embedded optical vector matrix multiplication processor architecture.pdf: 534672 bytes, checksum: 7dc8b542e4e4aee7da17af2844ed0327 (MD5)

Made available in DSpace on 2010-09-07T11:58:40Z (GMT). No. of bitstreams: 1 Performance of an embedded optical vector matrix multiplication processor architecture.pdf: 534672 bytes, checksum: 7dc8b542e4e4aee7da17af2844ed0327 (MD5) Previous issue date: 2010

国内

Identificador

http://ir.semi.ac.cn/handle/172111/13503

http://www.irgrid.ac.cn/handle/1471x/66097

Idioma(s)

英语

Fonte

Yang C (Yang C.), Cui GX (Cui G. X.), Huang YY (Huang Y. Y.), Wu L (Wu L.), Yang H (Yang H.), Zhang YH (Zhang Y. H.).Performance of an embedded optical vector matrix multiplication processor architecture.IET OPTOELECTRONICS,2010,4(4):159-164

Palavras-Chave #光电子学
Tipo

期刊论文