Understanding time-varying vulnerability accross GPU Program Lifetime

2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT) Pub Date : 2022-10-19 DOI:10.1109/DFT56152.2022.9962365

Hao Qiu, Semiu A. Olowogemo, B. Lin, W. H. Robinson, D. Limbrick

{"title":"Understanding time-varying vulnerability accross GPU Program Lifetime","authors":"Hao Qiu, Semiu A. Olowogemo, B. Lin, W. H. Robinson, D. Limbrick","doi":"10.1109/DFT56152.2022.9962365","DOIUrl":null,"url":null,"abstract":"Time-varying behaviors of GPU program vulnerability could be exploited to reduce overheads for fault-tolerant designs. However, the inherent parallelism and performance overheads for massive fault injection (FI) hindered such assessments using FI. NVBitFI, a GPU FI tool featuring high-performance and good compatibility, allows time-varying vulnerability evaluations using FI within a reasonable time. We extended NVBitFI to control FI tests on the temporal dimension. A scalable workflow characterizing the time-varying vulnerability of GPU programs at two granularities is presented. A convenient approach to profile vulnerability with actual GPU time is also proposed. Results obtained from 60K fault injections demonstrated the feasibility of the proposed methodologies. A case study exploring the improved instruction-level grouping is presented. More than 340K faults are injected into the vectorAdd kernel to show the possibility to generalize the time-varying behavior of smaller inputs to realistic workloads with large inputs.","PeriodicalId":411011,"journal":{"name":"2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DFT56152.2022.9962365","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

Time-varying behaviors of GPU program vulnerability could be exploited to reduce overheads for fault-tolerant designs. However, the inherent parallelism and performance overheads for massive fault injection (FI) hindered such assessments using FI. NVBitFI, a GPU FI tool featuring high-performance and good compatibility, allows time-varying vulnerability evaluations using FI within a reasonable time. We extended NVBitFI to control FI tests on the temporal dimension. A scalable workflow characterizing the time-varying vulnerability of GPU programs at two granularities is presented. A convenient approach to profile vulnerability with actual GPU time is also proposed. Results obtained from 60K fault injections demonstrated the feasibility of the proposed methodologies. A case study exploring the improved instruction-level grouping is presented. More than 340K faults are injected into the vectorAdd kernel to show the possibility to generalize the time-varying behavior of smaller inputs to realistic workloads with large inputs.

查看原文本刊更多论文

理解跨GPU程序生命周期的时变漏洞

利用GPU程序漏洞的时变行为可以减少容错设计的开销。然而，大规模故障注入(FI)固有的并行性和性能开销阻碍了使用FI进行此类评估。NVBitFI是一款高性能、兼容性好的GPU FI工具，允许在合理时间内使用FI进行时变漏洞评估。我们扩展了NVBitFI来控制时间维度上的FI测试。提出了一种描述GPU程序在两个粒度上时变漏洞的可扩展工作流。提出了一种利用实际GPU时间来分析漏洞的简便方法。从60K断层注入中获得的结果证明了所提出方法的可行性。本文提出了一种改进的教学级分组方法。在vectorAdd内核中注入了340K以上的故障，以显示将较小输入的时变行为推广到具有大输入的实际工作负载的可能性。

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

2022 IEEE International Symposium on Defect and Fault Tolerance in VLSI and Nanotechnology Systems (DFT)

自引率

0.00%

发文量