Obálka

A Multiplierless Architecture for Image Convolution in Memory

Uloženo v:
Vydáno v:Journal of Low Power Electronics and Applications vol. 15, no. 4 (2025), p. 63-79
Hlavní autor: Reuben, John
Další autoři: Zeller, Felix, Seiler, Benjamin, Fey Dietmar
Vydáno:
MDPI AG
Témata:
Multiplication
CMOS
Images
Computer memory
Machine vision
Computer architecture
Arithmetic
Multipliers
Artificial neural networks
Convolution
Network latency
On-line přístup:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstrakt:Image convolution is a commonly required task in machine vision and Convolution Neural Networks (CNNs). Due to the large data movement required, image convolution can benefit greatly from in-memory computing. However, image convolution is very computationally intensive, requiring <inline-formula>(n−(k−1))2</inline-formula> Inner Product (IP) computations for convolution of a <inline-formula>n×n</inline-formula> image with a <inline-formula>k×k</inline-formula> kernel. For example, for a convolution of a 224 × 224 image with a 3 × 3 kernel, 49,284 IPs need to be computed, where each IP requires nine multiplications and eight additions. This is a major hurdle for in-memory implementation because in-memory adders and multipliers are extremely slow compared to CMOS multipliers. In this work, we revive an old technique called ‘Distributed Arithmetic’ and judiciously apply it to perform image convolution in memory without area-intensive hard-wired multipliers. Distributed arithmetic performs multiplication using shift-and-add operations, and they are implemented using CMOS circuits in the periphery of ReRAM memory. Compared to Google’s TPU, our in-memory architecture requires 56× less energy while incurring 24× more latency for convolution of a 224 × 224 image with a 3 × 3 filter.
ISSN:2079-9268
DOI:10.3390/jlpea15040063
Zdroj:Advanced Technologies & Aerospace Database