{"title":"Mitigating NBTI Degradation on FinFET GPUs through Exploiting Device Heterogeneity","authors":"Ying Zhang, Sui Chen, Lu Peng, Shaoming Chen","doi":"10.1109/ISVLSI.2014.21","DOIUrl":null,"url":null,"abstract":"Recent experimental studies reveal that FinFET devices commercialized in recent years tend to suffer from moresevere NBTI degradation compared to planar transistors, necessitating effective techniques on processors built with FinFET for endurable operations. We propose to address this problem by exploiting the device heterogeneity and leveraging the slower NBTI aging rate manifested on the planar devices. We focus on modern graphics processing units in this study due to their wide usage in the current community. We validate the effectiveness of the technique byapplying it to the warp scheduler and demonstrate NBTIdegradation is considerably alleviated with slight performance overhead.","PeriodicalId":405755,"journal":{"name":"2014 IEEE Computer Society Annual Symposium on VLSI","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE Computer Society Annual Symposium on VLSI","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISVLSI.2014.21","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 13
Abstract
Recent experimental studies reveal that FinFET devices commercialized in recent years tend to suffer from moresevere NBTI degradation compared to planar transistors, necessitating effective techniques on processors built with FinFET for endurable operations. We propose to address this problem by exploiting the device heterogeneity and leveraging the slower NBTI aging rate manifested on the planar devices. We focus on modern graphics processing units in this study due to their wide usage in the current community. We validate the effectiveness of the technique byapplying it to the warp scheduler and demonstrate NBTIdegradation is considerably alleviated with slight performance overhead.