Implementation of biological sprouting algorithm for NoC fault tolerance

Sethi, M.A.J. and Hussin, F.A. and Hamid, N.H. (2013) Implementation of biological sprouting algorithm for NoC fault tolerance. In: UNSPECIFIED.

Full text not available from this repository.
Official URL: https://www.scopus.com/inward/record.uri?eid=2-s2....

Abstract

Scientists are always attracted by the bio-inspired techniques to solve the difficult engineering world problems. These techniques are being used as the novel way to solve the faulty situation in Network on Chip (NoC). Faults in NoC arises due to big sizes of interconnects as the size of the devices were continuously reduced to cope with the communication requirement of processing elements (PE's). Due to these faults a lot of conventional fault tolerant techniques have been proposed. But all of these techniques have drawbacks of latency, less bandwidth utilization and lesser throughput. In this paper, a novel bio-inspired technique "sprouting" is proposed. Bio-inspired sprouting algorithm is based on biological brain technique which makes the algorithm robust and the NoC fault tolerant. The result shows that the bio-inspired algorithm efficiently utilizes the bandwidth and throughput, packet network latency is degrading gracefully during the network recovery from fault. The average packet network latency increases 20.51, NoC bandwidth reduces 0.471 and throughput is drop to 37.22 during the recovery from faults. © 2013 IEEE.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Additional Information: cited By 7; Conference of 2013 IEEE International Conference on Circuits and Systems: ""Advanced Circuits and Systems for Sustainability"", ICCAS 2013 ; Conference Date: 18 September 2013 Through 19 September 2013; Conference Code:102360
Uncontrolled Keywords: Bandwidth; Neurons; Packet networks; Sustainable development; Throughput, Fault-tolerant; Network on chip; Processing elements; Sprouting; Synapse; Synaptogensis, Algorithms
Depositing User: Mr Ahmad Suhairi UTP
Date Deposited: 09 Nov 2023 15:52
Last Modified: 09 Nov 2023 15:52
URI: https://khub.utp.edu.my/scholars/id/eprint/3900

Actions (login required)

View Item
View Item