Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels

碩士 === 國立臺灣大學 === 電子工程學研究所 === 97 === A Bidirectional channel Network-on-Chip (BiNoC) architecture is proposed to enhance the performance of on-chip communication while supporting prioritized traffics in the network. The BiNoC allows each communication channel to be dynamically self-configured to t...

Full description

Bibliographic Details
Main Authors: Shih-Hsin Lo, 羅士欣
Other Authors: Sao-Jie Chen
Format: Others
Language:en_US
Published: 2009
Online Access:http://ndltd.ncl.edu.tw/handle/41884582431000916895
id ndltd-TW-097NTU05428104
record_format oai_dc
spelling ndltd-TW-097NTU054281042016-05-04T04:31:49Z http://ndltd.ncl.edu.tw/handle/41884582431000916895 Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels 一個可動態調整通道的晶片網路架構設計 Shih-Hsin Lo 羅士欣 碩士 國立臺灣大學 電子工程學研究所 97 A Bidirectional channel Network-on-Chip (BiNoC) architecture is proposed to enhance the performance of on-chip communication while supporting prioritized traffics in the network. The BiNoC allows each communication channel to be dynamically self-configured to transmit flits in either direction in order to better utilize on-chip hardware resources. This added flexibility promises better bandwidth utilization, lower packet delivery latency, and higher packet consumption rate at each on-chip router. In this Thesis, a novel on-chip router architecture supporting the self-configuring bidirectional channel mechanism is presented. It is shown that the associated hardware overhead is negligible. Cycle-accurate simulation runs on this BiNoC network under synthetic and real-world traffic patterns demonstrate consistent and significant performance advantage over a conventional mesh grid NoC architecture equipped with hard-wired unidirectional channels. Sao-Jie Chen 陳少傑 2009 學位論文 ; thesis 90 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 碩士 === 國立臺灣大學 === 電子工程學研究所 === 97 === A Bidirectional channel Network-on-Chip (BiNoC) architecture is proposed to enhance the performance of on-chip communication while supporting prioritized traffics in the network. The BiNoC allows each communication channel to be dynamically self-configured to transmit flits in either direction in order to better utilize on-chip hardware resources. This added flexibility promises better bandwidth utilization, lower packet delivery latency, and higher packet consumption rate at each on-chip router. In this Thesis, a novel on-chip router architecture supporting the self-configuring bidirectional channel mechanism is presented. It is shown that the associated hardware overhead is negligible. Cycle-accurate simulation runs on this BiNoC network under synthetic and real-world traffic patterns demonstrate consistent and significant performance advantage over a conventional mesh grid NoC architecture equipped with hard-wired unidirectional channels.
author2 Sao-Jie Chen
author_facet Sao-Jie Chen
Shih-Hsin Lo
羅士欣
author Shih-Hsin Lo
羅士欣
spellingShingle Shih-Hsin Lo
羅士欣
Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
author_sort Shih-Hsin Lo
title Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
title_short Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
title_full Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
title_fullStr Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
title_full_unstemmed Design of a Network-on-Chip Architecture with Dynamically Reconfigurable Channels
title_sort design of a network-on-chip architecture with dynamically reconfigurable channels
publishDate 2009
url http://ndltd.ncl.edu.tw/handle/41884582431000916895
work_keys_str_mv AT shihhsinlo designofanetworkonchiparchitecturewithdynamicallyreconfigurablechannels
AT luóshìxīn designofanetworkonchiparchitecturewithdynamicallyreconfigurablechannels
AT shihhsinlo yīgèkědòngtàidiàozhěngtōngdàodejīngpiànwǎnglùjiàgòushèjì
AT luóshìxīn yīgèkědòngtàidiàozhěngtōngdàodejīngpiànwǎnglùjiàgòushèjì
_version_ 1718259981232373760