跳到主要导航 跳到搜索 跳到主要内容

A skyrmion racetrack memory based computing in-memory architecture for binary neural convolutional network

  • Beihang University
  • Tsinghua University

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

A Skyrmion Racetrack Memory (SRM) based Computing In-Memory Architecture (SRM-CIM) was proposed in this paper. Both data and computing operation can be achieved in SRM-CIM. SRM-CIM is used to support convolutional computing in Binary Convolutional Neural Network (BCNN). Experimental results show that SRM-CIM achieves 98.7% and 82% energy reduction when compared with RRAM and SOT-MRAM based counterparts.

源语言英语
主期刊名GLSVLSI 2019 - Proceedings of the 2019 Great Lakes Symposium on VLSI
出版商Association for Computing Machinery
271-274
页数4
ISBN(电子版)9781450362528
DOI
出版状态已出版 - 13 5月 2019
活动29th Great Lakes Symposium on VLSI, GLSVLSI 2019 - Tysons Corner, 美国
期限: 9 5月 201911 5月 2019

丛书

姓名Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

会议

会议29th Great Lakes Symposium on VLSI, GLSVLSI 2019
国家/地区美国
Tysons Corner
时期9/05/1911/05/19

学术指纹

探究 'A skyrmion racetrack memory based computing in-memory architecture for binary neural convolutional network' 的科研主题。它们共同构成独一无二的学术指纹。

引用此