High Reliability NoC switch using Modified Hamming Code with Transient Faults

The scaling of technology decreases the communication issues between components in the System on Chip (SoC). Network on Chip (NoC) has the new architecture to deal with the overheads of communication and it is build with routers and processing elements. The router of NoC is temporarily and/or permanently disabled due to the occurrence of faults. A disabled router gives severe impact on the entire system hence the correction of faults is curial not only for single router but also entire NoC system. A Modified Hamming Code (MHC) is presented for detection and correction transient faults. The encoded data input is categorized in groups and each MHC is applied to each group parallelly there by provides high reliability of this method. The simulation results prove that MHC yields reduced latency and increased speed when compared to conventional Hamming Code (HC).