An Efficient Fault Tolerant Routing Interconnect System for Neural NOC

kumar, Dr.A. Pradeep and Reddy, Y. Devendar and Reddy, Dr.T. Srinivas and Jamal, K. (2021) An Efficient Fault Tolerant Routing Interconnect System for Neural NOC. In: I3CAC 2021, 7-8 June 2021, Bharath University, Chennai, India.

[img]
Preview
Text (PDF)
eai.7-6-2021.2308772.pdf - Published Version

Download (284kB) | Preview

Abstract

Large scale Neural Network (NN) accelerators typically have multiple processing nodes that can be implemented as a multi-core chip, and can be organized on a network of chips (noise) corresponding to neurons with heavy traffic. Portions of several NoC-based NN chip-to-chip interconnect networks are linked to further enhance overall nerve amplification capacity. Large volumes of multicast on-chip or cross-chip can further complicate the construction of a cross-link network and create a NN barrier of device capacity and resources. In this paper, this refer to inter-chip and inter-chip communication strategies known as neuron connection for NN accelerators. Interconnect for powerful fault-tolerant routing system neural NoC is implemented in this paper. Regarding intra-chip communication, this recommend crossbar arbitrage placement, virtual interrupt and path-based parallelization strategies for virtual channel routing, leading to higher NoC output with lower hardware costs. For multicast-based traffic. Regarding inter-chip communication, this propose a lightweight NoC compatible chip-to-chip interconnection scheme to allow efficient interconnection for NoC-based NN chips. In addition, this will test the proposed methods with four Field Programmable Gate Arrays (FPGAs) on four hardwired Deep Neural Network (DNN) chips. The experimental results show that the proposed interconnection network can effectively handle data traffic with high thr

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: chip-to-chip interconnection deep neural network (dnn) hardware accelerator interconnection architecture network-on-chip (noc)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
QA75 Electronic computers. Computer science
Depositing User: EAI Editor IV
Date Deposited: 11 Jun 2021 08:01
Last Modified: 11 Jun 2021 08:01
URI: https://eprints.eudl.eu/id/eprint/3844

Actions (login required)

View Item View Item