Energy Efficient 0.5V 4.8pJ/SOP 0.93μW Leakage/Core Neuromorphic Processor Design

Page view(s)
88
Checked on Oct 04, 2024
Energy Efficient 0.5V 4.8pJ/SOP 0.93μW Leakage/Core Neuromorphic Processor Design
Title:
Energy Efficient 0.5V 4.8pJ/SOP 0.93μW Leakage/Core Neuromorphic Processor Design
Journal Title:
IEEE Transactions on Circuits and Systems II: Express Briefs
Publication Date:
13 July 2021
Citation:
Nambiar, V. P., Pu, J., Lee, Y. K., Mani, A., Koh, E. K., Wong, M. M., Li, F., Goh, W. L., & Do, A. T. (2021). Energy Efficient 0.5V 4.8pJ/SOP 0.93μW Leakage/Core Neuromorphic Processor Design. IEEE Transactions on Circuits and Systems II: Express Briefs, 68(9), 3148–3152. https://doi.org/10.1109/tcsii.2021.3096883
Abstract:
This brief presents a neuromorphic processor with asynchronous routers and configurable LIF neuron models. The neurocore microarchitecture revolves around a high- V th SRAM to reduce leakage, alongside reconfigurable neuron compute logic circuits and async routers to maximize energy efficiency. The neuron compute module achieves low power via an area efficient ALU implementation by using only adder and bitshifter circuits. We describe this LIF neuron model ALU design, and also include key neurocore verification scenarios (i.e., router deadlocks and functional coverage), CPU-neurocore control flow, and asynchronous router performance analysis. Our 16-core fabricated chip in 40 nm CMOS process works down to 0.5V. The measured leakage and average energy efficiency are 0.93 μW/core and 4.8 pJ/SOP respectively (at 0.5V), which is 20% better than state of the art.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the A*STAR - AME Programmatic - Neuromorphic Computing
Grant Reference no. : A1687b0033
Description:
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1549-7747
1558-3791
Files uploaded: