MVSTT: A Multi-Value Computation-in-Memory based on Spin-Transfer Torque Memories

A. Jafari, M. Mayahinia, Soyed Tuhin Ahmed, Christopher Münch, M. Tahoori
{"title":"MVSTT: A Multi-Value Computation-in-Memory based on Spin-Transfer Torque Memories","authors":"A. Jafari, M. Mayahinia, Soyed Tuhin Ahmed, Christopher Münch, M. Tahoori","doi":"10.1109/DSD57027.2022.00052","DOIUrl":null,"url":null,"abstract":"Analog Computation-in-Memory (CiM) with emerging non-volatile memories leads to significant performance and energy efficiency. Spin-Transfer Torque Magnetic Memory (STT-MRAM) is one of the promising technologies for CiM architectures. Although STT-MRAM has various benefits, it does not have the potential to be used directly in analog multi-value CiM operations due to its limited levels of cell resistance states. In this paper, we propose a novel flexible multi-value design for STT-MRAM (MVSTT) with the potential to be used for multi-value CiM. In the multi-value CiM, we are able to have various 2s resistive state combinations from $s$ selected MTJs, which is not possible in the normal STT-MRAM CiM. The size of the MVSTT can be adjusted at run-time depending on the application's requirements. The benefits of the proposed scheme are quantified in representative applications such as multi-value matrix multiplications, which is the basic computation of Neural Networks applications. For the multi-value matrix multiplication, the energy, and delay gain is up to 9.7 × and 13.3 ×, respectively, to non-CiM matrix-vector-multiplication. Also, for the neural network, the proposed design allows up to a 32 × reduction in the STT-MRAM cells per crossbar to achieve a similar inference accuracy as the binarized neural network.","PeriodicalId":211723,"journal":{"name":"2022 25th Euromicro Conference on Digital System Design (DSD)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 25th Euromicro Conference on Digital System Design (DSD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DSD57027.2022.00052","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Analog Computation-in-Memory (CiM) with emerging non-volatile memories leads to significant performance and energy efficiency. Spin-Transfer Torque Magnetic Memory (STT-MRAM) is one of the promising technologies for CiM architectures. Although STT-MRAM has various benefits, it does not have the potential to be used directly in analog multi-value CiM operations due to its limited levels of cell resistance states. In this paper, we propose a novel flexible multi-value design for STT-MRAM (MVSTT) with the potential to be used for multi-value CiM. In the multi-value CiM, we are able to have various 2s resistive state combinations from $s$ selected MTJs, which is not possible in the normal STT-MRAM CiM. The size of the MVSTT can be adjusted at run-time depending on the application's requirements. The benefits of the proposed scheme are quantified in representative applications such as multi-value matrix multiplications, which is the basic computation of Neural Networks applications. For the multi-value matrix multiplication, the energy, and delay gain is up to 9.7 × and 13.3 ×, respectively, to non-CiM matrix-vector-multiplication. Also, for the neural network, the proposed design allows up to a 32 × reduction in the STT-MRAM cells per crossbar to achieve a similar inference accuracy as the binarized neural network.
MVSTT:一种基于自旋传递转矩存储器的多值内存计算
模拟内存计算(CiM)与新兴的非易失性存储器带来显著的性能和能源效率。自旋传递转矩磁记忆技术(STT-MRAM)是CiM结构中很有前途的技术之一。尽管STT-MRAM具有各种优势,但由于其有限的单元电阻状态水平,它不具有直接用于模拟多值CiM操作的潜力。在本文中,我们提出了一种新的灵活的多值STT-MRAM (MVSTT)设计,具有用于多值CiM的潜力。在多值CiM中,我们能够从$s$选择的mtj中获得各种2s电阻状态组合,这在正常的STT-MRAM CiM中是不可能的。MVSTT的大小可以在运行时根据应用程序的需求进行调整。在代表性的应用中,如神经网络应用的基础计算——多值矩阵乘法,量化了该方案的优点。对于多值矩阵乘法,与非cim矩阵矢量乘法相比,能量增益和延迟增益分别高达9.7倍和13.3倍。此外,对于神经网络,所提出的设计允许每个交叉条的STT-MRAM单元减少32倍,以实现与二值化神经网络相似的推理精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信