Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Farias, Matheus, Kung, H. T.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909680292331520
author Farias, Matheus
Kung, H. T.
author_facet Farias, Matheus
Kung, H. T.
contents We introduce a novel approach to reduce the number of times required for reprogramming memristors on bit-sliced compute-in-memory crossbars for deep neural networks (DNNs). Our idea addresses the limited non-volatile memory endurance, which restrict the number of times they can be reprogrammed. To reduce reprogramming demands, we employ two techniques: (1) we organize weights into sorted sections to schedule reprogramming of similar crossbars, maximizing memristor state reuse, and (2) we reprogram only a fraction of randomly selected memristors in low-order columns, leveraging their bit-level distribution and recognizing their relatively small impact on model accuracy. We evaluate our approach for state-of-the-art models on the ImageNet-1K dataset. We demonstrate a substantial reduction in crossbar reprogramming by 3.7x for ResNet-50 and 21x for ViT-Base, while maintaining model accuracy within a 1% margin.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21730
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking
Farias, Matheus
Kung, H. T.
Hardware Architecture
Artificial Intelligence
Emerging Technologies
Machine Learning
We introduce a novel approach to reduce the number of times required for reprogramming memristors on bit-sliced compute-in-memory crossbars for deep neural networks (DNNs). Our idea addresses the limited non-volatile memory endurance, which restrict the number of times they can be reprogrammed. To reduce reprogramming demands, we employ two techniques: (1) we organize weights into sorted sections to schedule reprogramming of similar crossbars, maximizing memristor state reuse, and (2) we reprogram only a fraction of randomly selected memristors in low-order columns, leveraging their bit-level distribution and recognizing their relatively small impact on model accuracy. We evaluate our approach for state-of-the-art models on the ImageNet-1K dataset. We demonstrate a substantial reduction in crossbar reprogramming by 3.7x for ResNet-50 and 21x for ViT-Base, while maintaining model accuracy within a 1% margin.
title Efficient Reprogramming of Memristive Crossbars for DNNs: Weight Sorting and Bit Stucking
topic Hardware Architecture
Artificial Intelligence
Emerging Technologies
Machine Learning
url https://arxiv.org/abs/2410.21730