An Energy Consumption Model for SRAM-Based In-Memory-Computing Architectures-Reference-Cited by-同舟云学术

An Energy Consumption Model for SRAM-Based In-Memory-Computing Architectures

Published:2024-03-19 Issue:6 Volume:13 Page:1121
ISSN:2079-9292
Container-title:Electronics
language:en
Short-container-title:Electronics

Author:

Akgül Berke¹^ORCID,Karalar Tufan Coşkun²^ORCID

Affiliation:

1. Electronics and Communication Engineering, Yıldız Technical University, 34230 Istanbul, Türkiye

2. Electronics and Communication Engineering, Istanbul Technical University, 34485 Istanbul, Türkiye

Abstract

In this paper, a mathematical model for obtaining energy consumption of IMC architectures is constructed. This model provides energy estimation based on the distribution of a specific dataset. In addition, the estimation reduces the required simulation time to create an energy consumption model of SRAM-based IMC architectures. To validate our model with realistic data, the energy consumption of IMC is compared by using NeuroSim V3.0 for the CIFAR-10 and MNIST-like datasets. Furthermore, an application is created with our model to select highest performing quantization mapping based upon the parameters of energy consumption and accuracy.

Publisher

MDPI AG

Link

https://www.mdpi.com/2079-9292/13/6/1121/pdf

Reference33 articles.

1. Park, J.S., and Na, H.J. (2020). Front-End of Vehicle-Embedded Speech Recognition for Voice-Driven Multi-UAVs Control. Appl. Sci., 10.

2. Yin, S., Ouyang, P., Zheng, S., Song, D., Li, X., Liu, L., and Wei, S. (2018, January 18–22). A 141 UW, 2.46 PJ/Neuron Binarized Convolutional Neural Network Based Self-Learning Speech Recognition Processor in 28NM CMOS. Proceedings of the 2018 IEEE Symposium on VLSI Circuits, Honolulu, HI, USA.

3. A 510-nW Wake-Up Keyword-Spotting Chip Using Serial-FFT-Based MFCC and Binarized Depthwise Separable CNN in 28-nm CMOS;Shan;IEEE J. Solid-State Circuits,2021

4. Shah, M., Wang, J., Blaauw, D., Sylvester, D., Kim, H.S., and Chakrabarti, C. (2015, January 14–16). A fixed-point neural network for keyword detection on resource constrained hardware. Proceedings of the 2015 IEEE Workshop on Signal Processing Systems (SiPS), Hangzhou, China.

5. A 64-Tile 2.4-Mb In-Memory-Computing CNN Accelerator Employing Charge-Domain Compute;Valavi;IEEE J. Solid-State Circuits,2019