DocumentCode :
2613457
Title :
High performance Networks on Chip architecture with a new routing strategy for neural network
Author :
Dong, Yiping ; Lin, Zhen ; Watanabe, Takahiro
Author_Institution :
Waseda Univ., Kitakyushu, Japan
fYear :
2010
fDate :
22-24 Sept. 2010
Firstpage :
347
Lastpage :
350
Abstract :
Hardware implementation by Networks on Chip (NoC) for Artificial Neural Network (ANN) was proposed to improve. In this work, a new architecture of NoC which has a hardware implementation of routing algorithm is proposed for ANN design. This routing strategy could reduce the packet size of header. The NOXIM NoC simulator is used to simulate the proposed system in term of latency, throughput and power consumption. The experimental results indicate that the proposed new NoC architecture is effective in increasing throughput and reducing latency and power consumption, compare with the traditional one. The ANN with the new NoC architecture could achieve higher performance and lower communication load.
Keywords :
network routing; network-on-chip; neural net architecture; neural nets; NOXIM NoC simulator; NoC architecture; chip architecture; hardware implementation; network on chip; neural network; new routing strategy; power consumption; routing algorithm; Artificial neural networks; Hardware; Neurons; Power demand; Routing; Switches; Throughput;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Microelectronics and Electronics (PrimeAsia), 2010 Asia Pacific Conference on Postgraduate Research in
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-6735-8
Electronic_ISBN :
978-1-4244-6736-5
Type :
conf
DOI :
10.1109/PRIMEASIA.2010.5604890
Filename :
5604890
Link To Document :
بازگشت