Reconfigurable Digital Logic Gate based on Neuromorphic Approach

Singhal, N and Santosh, M and Bose, SC (2019) Reconfigurable Digital Logic Gate based on Neuromorphic Approach. In: 32nd International Conference on VLSI Design and 2019 18th International Conference on Embedded Systems (VLSID-2019), January 5-9, 2019, New Delhi, India.

Preview

PDF Download (520Kb) | Preview

Abstract

This paper presents low power and highly tuneable LIF (modified) neuron model and its usage to implement reconfigurable digital logic gate. Simulations are done using Tower Jazz Semiconductor's 180nm technology and UMC 28 nm technology in Cadence virtuoso environment. Results show the advantage of neuromorphic approach in terms of re-configurability, power and area when compared to traditional logic gate designs. Reconfigurable gate performs AND/OR/NAND/NOR/XOR/XNOR. It works for both spiking input as well as DC input (current signal). Power consumption of reconfigurable gate designed using modified LIF is at least 45% less than the power consumption of CMOS gates.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Neuromorphic, LIF, CMOS, Reconfigurable.
Subjects:	Semiconductor Devices > IC Design
Divisions:	Semiconductor Devices
Depositing User:	Mr. Jitendra Nath Bajpai
Date Deposited:	29 Sep 2021 09:27
Last Modified:	29 Sep 2021 09:27
URI:	http://ceeri.csircentral.net/id/eprint/607

Actions (login required)

View Item