首页> 外文期刊>IEEE Transactions on Parallel and Distributed Systems >Astro: Auto-Generation of Synthetic Traces Using Scaling Pattern Recognition for MPI Workloads
【24h】

Astro: Auto-Generation of Synthetic Traces Using Scaling Pattern Recognition for MPI Workloads

机译:Astro:使用缩放模式识别的MPI工作负载自动生成合成迹线

获取原文
获取原文并翻译 | 示例
           

摘要

Performance modeling of scale-out MPI workloads is critical in assessing trade-offs for high-performance system designs. Traces and workload skeletons are the two main vehicles used to date to accomplish this task. However, the ever-increasing scale and complexity of MPI workloads makes it difficult, sometimes infeasible, to collect the traces and/or skeletonize the workloads, dueto the constraints of computing resources or the unavailability of workload source code. This paper presents Astro, a framework that leverages machine learning techniques to automatically recognize the scaling patterns from training traces, and generate high-quality synthetic traces which mimic original trace behavior and extrapolate it to arbitrary scale. Experimental results show that compared with original traces, the synthetic traces yield less than 15 percent error against a range of metrics for up to 8 K MPI ranks. This framework enables large-scale performance modeling with limited computing resources, and allows modeling proprietary workloads in a portable and secure way.Author: There was a discrepancy in Bibliography in the PDF and the source file. We have followed the source file. ?>
机译:扩展MPI工作负载的性能建模对于评估高性能系统设计的权衡至关重要。跟踪和工作负载框架是迄今为止用于完成此任务的两个主要工具。但是,由于计算资源的限制或工作负载源代码的不可用,MPI工作负载的规模和复杂性不断增加,使得收集痕迹和/或使工作负载框架化有时是不可行的,有时甚至是不可行的。本文介绍了Astro,该框架利用机器学习技术自动识别训练迹线的缩放模式,并生成模仿原始迹线行为并将其推断到任意规模的高质量合成迹线。实验结果表明,与原始迹线相比,对于高达8 K MPI等级的一系列度量标准,合成迹线产生的误差小于15%。该框架允许使用有限的计算资源进行大规模性能建模,并允许以可移植且安全的方式对专有工作负载进行建模。作者:PDF和源文件中的书目存在差异。我们已经关注了源文件。 ?>

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号