基于RRAM横杆阵列的自旋玻璃模拟退火硬件加速

2018 IEEE International Electron Devices Meeting (IEDM) Pub Date : 2018-12-01 DOI:10.1109/IEDM.2018.8614698

J. Shin, Yeonjoo Jeong, Mohammed Affan Zidan, Qiwen Wang, Wei D. Lu

{"title":"基于RRAM横杆阵列的自旋玻璃模拟退火硬件加速","authors":"J. Shin, Yeonjoo Jeong, Mohammed Affan Zidan, Qiwen Wang, Wei D. Lu","doi":"10.1109/IEDM.2018.8614698","DOIUrl":null,"url":null,"abstract":"Simulated annealing (SA) was successfully implemented and accelerated by in-memory computing hardware/software package using RRAM crossbar arrays to solve a spin glass problem. Ta2O5-based RRAM array and stochastic Cu-based CBRAM devices were utilized for calculation of the Hamiltonian and decision of spin-flip events, respectively. A parallel spin-flip strategy was demonstrated to further accelerate the SA algorithm.","PeriodicalId":152963,"journal":{"name":"2018 IEEE International Electron Devices Meeting (IEDM)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"24","resultStr":"{\"title\":\"Hardware Acceleration of Simulated Annealing of Spin Glass by RRAM Crossbar Array\",\"authors\":\"J. Shin, Yeonjoo Jeong, Mohammed Affan Zidan, Qiwen Wang, Wei D. Lu\",\"doi\":\"10.1109/IEDM.2018.8614698\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Simulated annealing (SA) was successfully implemented and accelerated by in-memory computing hardware/software package using RRAM crossbar arrays to solve a spin glass problem. Ta2O5-based RRAM array and stochastic Cu-based CBRAM devices were utilized for calculation of the Hamiltonian and decision of spin-flip events, respectively. A parallel spin-flip strategy was demonstrated to further accelerate the SA algorithm.\",\"PeriodicalId\":152963,\"journal\":{\"name\":\"2018 IEEE International Electron Devices Meeting (IEDM)\",\"volume\":\"32 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"24\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2018 IEEE International Electron Devices Meeting (IEDM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IEDM.2018.8614698\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE International Electron Devices Meeting (IEDM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEDM.2018.8614698","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 24

摘要

利用RRAM交叉棒阵列成功实现了模拟退火(SA)，并通过内存计算硬件/软件包进行了加速，解决了自旋玻璃问题。基于ta2o5的RRAM阵列和基于cu的随机CBRAM器件分别用于计算自旋翻转事件的哈密顿量和决策。提出了一种平行自旋翻转策略，进一步加快了算法的速度。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Hardware Acceleration of Simulated Annealing of Spin Glass by RRAM Crossbar Array

Simulated annealing (SA) was successfully implemented and accelerated by in-memory computing hardware/software package using RRAM crossbar arrays to solve a spin glass problem. Ta2O5-based RRAM array and stochastic Cu-based CBRAM devices were utilized for calculation of the Hamiltonian and decision of spin-flip events, respectively. A parallel spin-flip strategy was demonstrated to further accelerate the SA algorithm.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2018 IEEE International Electron Devices Meeting (IEDM)

自引率

0.00%

发文量