Title :
Transition level energy consumption of NoC (network-on-chip) using data encoding techniques
Author :
Ashokkumar, N. ; Kavitha, A.
Author_Institution :
Dept. of ECE, RVS Coll. of Eng. & Technol., Dindigul, India
Abstract :
Network on chip (NoC), a communication subsystem provides efficient communication between IP cores like data transmission between IP cores through link interface. This technology implies the parameters consideration and one main consideration is power. The power dissipated by the links through a network on chip starts to compete with the power dissipated by the other elements. Proposed Power reduction techniques at all levels of design hierarchy begins with algorithms, architectures and end with circuits. The average power consumption of a processor based system can be achieved by minimizing the number of transitions (i.e., switching activity) on the buses connected to the Primary Outputs(POs) of the processor. The idea presented is based on encoding the packets before they are injected into the network in such a way as to minimize both switching activity and coupling activity in the NoC´slink. Proposed data encoding scheme is to reduce power dissipation and energy consumption by minimizing the coupling transition activities on the links of the interconnection network.
Keywords :
encoding; network-on-chip; power consumption; IP cores; NoC; communication subsystem; coupling activity; data encoding techniques; data transmission; interconnection network; link interface; network-on-chip; power dissipation; power reduction techniques; processor average power consumption; switching activity; transition level energy consumption; Computer architecture; Couplings; Encoding; Energy consumption; Power demand; Power dissipation; Switches; Coupling transition; Link; Network-on-Chip (NoC); Power Dissipation; Routing; Switching;
Conference_Titel :
Computing for Sustainable Global Development (INDIACom), 2015 2nd International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-9-3805-4415-1