SAMBA: Sparsity Aware In-Memory Computing Based Machine Learning Accelerator
Author:
Affiliation:
1. Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
2. Microsoft, San Jose, CA, USA
3. Department of Electrical and Computer Engineering, Iowa State University, Ames, IA, USA
Funder
Center for Brain Inspired Computing
Semiconductor Research Corporation
Defense Advanced Research Projects Agency
National Science Foundation
IARPA MicroE4AI program
DoD Vannevar Bush Fellowship
Army Research Laboratory
U.S. Department of Energy
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
Computational Theory and Mathematics,Hardware and Architecture,Theoretical Computer Science,Software
Link
https://ieeexplore.ieee.org/ielam/12/10213258/10070830-aam.pdf
Reference36 articles.
1. To prune, or not to prune: Exploring the efficacy of pruning for model compression;zhu,2017
2. Learning the sparsity for ReRAM
3. Deep learning inference in facebook data centers: Characterization, performance optimizations and hardware implications;park,2018
4. SNrram: An Efficient Sparse Neural Network Computation Architecture Based on Resistive Random-Access Memory
5. A Massively Parallel Coprocessor for Convolutional Neural Networks
Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Neural architecture search for in-memory computing-based deep learning accelerators;Nature Reviews Electrical Engineering;2024-05-20
2. Enabling efficient machine learning with device-to-algorithm co-design of spintronic hardware: opportunities and challenge;Spintronics XVI;2023-09-28
3. Comparing assembly strategies for third-generation sequencing technologies across different genomes;Genomics;2023-09
4. Energy-Efficient ReRAM-Based ML Training via Mixed Pruning and Reconfigurable ADC;2023 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED);2023-08-07
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3