paper-with-me

홈 › Papers

Defects Mitigation in Resistive Crossbars for Analog Vector Matrix Multiplication

2019-12-17 · Fan Zhang, Miao Hu

With storage and computation happening at the same place, computing in resistive crossbars minimizes data movement and avoids the memory bottleneck issue. It leads to ultra-high energy efficiency for data-intensive applications. However, defects in crossbars severely affect computing accuracy. Existing solutions, including re-training with defects and redundant designs, but they have limitations in practical implementations. In this work, we introduce row shuffling and output compensation to mitigate defects without re-training or redundant resistive crossbars. We also analyzed the coupling effects of defects and circuit parasitics. Moreover, We study different combinations of methods to achieve the best trade-off between cost and performance. Our proposed methods could rescue up to 10% of defects in ResNet-20 application without performance degradation.

📄 PDF Abstract BibTeX arXiv:1912.07829

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BasisN: Reprogramming-Free RRAM-Based In-Memory-Computing by Basis Combination for Deep Neural Networks

2024-07-04 · Amro Eldebiky, Grace Li Zhang, Xunzhao Yin, Cheng Zhuo 외

Deep neural networks (DNNs) have made breakthroughs in various fields including image recognition and language processing. DNNs execute hundreds of millions of multiply-and-accumulate (MAC) operations. To efficiently acc…

Mitigate Parasitic Resistance in Resistive Crossbar-based Convolutional Neural Networks

2019-12-17 · Fan Zhang, Miao Hu

Traditional computing hardware often encounters on-chip memory bottleneck on large scale Convolution Neural Networks (CNN) applications. With its unique in-memory computing feature, resistive crossbar-based computing att…

MRAM-based Analog Sigmoid Function for In-memory Computing

2022-04-21 · Md Hasibul Amin, Mohammed Elbtity, Mohammadreza Mohammadi, Ramtin Zand

We propose an analog implementation of the transcendental activation function leveraging two spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices and a CMOS inverter. The proposed analog neuron circ…

Evaluating the Scalability of Binary and Ternary CNN Workloads on RRAM-based Compute-in-Memory Accelerators

2025-05-12 · José Cubero-Cascante, Rebecca Pelke, Noah Flohr, Arunkumar Vaidyanathan 외

The increasing computational demand of Convolutional Neural Networks (CNNs) necessitates energy-efficient acceleration strategies. Compute-in-Memory (CIM) architectures based on Resistive Random Access Memory (RRAM) offe…

RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbars

2018-08-31 · Shubham Jain, Abhronil Sengupta, Kaushik Roy, Anand Raghunathan

Resistive crossbars designed with non-volatile memory devices have emerged as promising building blocks for Deep Neural Network (DNN) hardware, due to their ability to compactly and efficiently realize vector-matrix mult…