{"title":"LEnS: Lifetime Enhancement Coding Scheme for Non-volatile Memory Processors","authors":"Swatilekha Majumdar","doi":"10.1109/MWSCAS47672.2021.9531891","DOIUrl":null,"url":null,"abstract":"Limited write endurance and high write energy consumption per bit restrict the use of emerging non-volatile memory devices. Many studies concentrate on reducing the number of bit-flips per write operation to reduce bottleneck issues. In this paper, we propose a lifetime enhancement scheme for eNVM device-based memories that distributes the number of bit-flips across the bitstream and can improve the endurance and energy performance of the NVM processors. The proposed scheme significantly reduces the number of bit-flips by ≥40% in write-intensive applications and improves the processor’s performance by ~ 55% as compared to content-aware bit-shuffling scheme.","PeriodicalId":6792,"journal":{"name":"2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)","volume":"5 1","pages":"365-368"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Midwest Symposium on Circuits and Systems (MWSCAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MWSCAS47672.2021.9531891","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
Limited write endurance and high write energy consumption per bit restrict the use of emerging non-volatile memory devices. Many studies concentrate on reducing the number of bit-flips per write operation to reduce bottleneck issues. In this paper, we propose a lifetime enhancement scheme for eNVM device-based memories that distributes the number of bit-flips across the bitstream and can improve the endurance and energy performance of the NVM processors. The proposed scheme significantly reduces the number of bit-flips by ≥40% in write-intensive applications and improves the processor’s performance by ~ 55% as compared to content-aware bit-shuffling scheme.