An Energy Efficient Time-Multiplexing Computing-in-Memory Architecture for Edge Intelligence
Open Access
- 15 September 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal on Exploratory Solid-State Computational Devices and Circuits
- Vol. 8 (2) , 111-118
Abstract
The growing data volume and complexity of Deep Neural Networks (DNN) require new architectures to surpass the limitation of the von-Neumann bottleneck, with Computing-in-memory (CIM) as a promising direction for implementing energy-efficient neural networks. However, CIM’s peripheral sensing circuits are usually power and area hungry components. We propose a time-multiplexing Computing-in-Memory architecture (TM-CIM) based on memristive analog computing to share the peripheral circuits and process one column at a time. The memristor array is arranged in a column-wise manner that avoids wasting power/energy on unselected columns. In addition, DAC (digital-to-analog converter) power and energy efficiency, which turns out to be an even greater overhead than ADC (analog-to-digital converter), can be fine-tuned in TM-CIM for significant improvement. For a 256*256 crossbar array with a typical setting, TM-CIM saves 18.4× in energy with 0.136 pJ/MAC efficiency, and 19.9× area for 1T1R case and 15.9× for 2T2R case. Performance estimation on VGG-16 indicates that TM-CIM can save over 16× area. A trade-off between the chip area, peak power, and latency is also presented, with a proposed scheme to further reduce the latency on VGG-16, without significantly increasing chip area and peak power.Keywords
Funding Information
- Singapore government’s Research, Innovation and Enterprise 2020 plan (A1687b0033)
This publication has 13 references indexed in Scilit:
- A Robust 8-Bit Non-Volatile Computing-in-Memory Core for Low-Power Parallel MAC OperationsIEEE Transactions on Circuits and Systems I: Regular Papers, 2020
- 33.1 A 74 TMACS/W CMOS-RRAM Neurosynaptic Core with Dynamically Reconfigurable Dataflow and In-situ Transposable Weights for Probabilistic Graphical Models2020
- Fully hardware-implemented memristor convolutional neural networkNature, 2020
- A Deep Neural Network Accelerator Based on Tiled RRAM Architecture2019
- Monolithically Integrated RRAM- and CMOS-Based In-Memory Computing Optimizations for Efficient Deep LearningIEEE Micro, 2019
- In situ training of feed-forward and recurrent convolutional memristor networksNature Machine Intelligence, 2019
- A 16Mb dual-mode ReRAM macro with sub-14ns computing-in-memory and memory functions enabled by self-write termination scheme2017
- Neuromorphic computing using non-volatile memoryAdvances in Physics: X, 2016
- ISAACACM SIGARCH Computer Architecture News, 2016
- A Low Active Leakage and High Reliability Phase Change Memory (PCM) Based Non-Volatile FPGA Storage ElementIEEE Transactions on Circuits and Systems I: Regular Papers, 2014