DocumentCode
2365220
Title
Forecasting-Based Dynamic Virtual Channels Allocation for Power Optimization of Network-on-Chips
Author
Rahmani, Amir-Mohammad ; Daneshtalab, Masoud ; Afzali-Kusha, Ali ; Safari, XSaeed ; Pedram, Masoud
Author_Institution
Nanoelectron. Center of Excellence, Univ. of Tehran, Tehran
fYear
2009
fDate
5-9 Jan. 2009
Firstpage
151
Lastpage
156
Abstract
In this paper, we present a dynamic power management technique for optimizing the use of virtual channels in network on chips. The technique which is called dynamic virtual channels allocation (DVCA) makes use of the traffic conditions and past buffer utilization to dynamically forecast the number of virtual channels that should be active. In this technique, for low(high) traffic loads, a small (large) number of VCs are allocated to the corresponding input channel. This provides us with the ability to reduce the power consumption of the router while maintaining the data communication rate. To assess the efficacy of the proposed method, the network on chip has been simulated using several traffic profiles. The simulation results show that up to 35% reduction in the buffer power consumption and up to 20% savings in the overall router power consumption may be achieved. Finally, the area and power overheads of the technique are negligible.
Keywords
channel allocation; data communication; network-on-chip; power consumption; telecommunication network routing; telecommunication traffic; buffer utilization; data communication rate; dynamic power management technique; dynamic virtual channels allocation; network-on-chips; router power consumption; traffic conditions; Channel allocation; Communication switching; Data communication; Delay; Design optimization; Energy consumption; Network-on-a-chip; Switches; Telecommunication traffic; Throughput;
fLanguage
English
Publisher
ieee
Conference_Titel
VLSI Design, 2009 22nd International Conference on
Conference_Location
New Delhi
ISSN
1063-9667
Print_ISBN
978-0-7695-3506-7
Type
conf
DOI
10.1109/VLSI.Design.2009.87
Filename
4749667
Link To Document