【24h】

Debugging Massively Parallel Programs with ATEMPT

机译:使用ATTEMPT调试大规模并行程序

获取原文

摘要

When thinking of programs running of massively parallel architectures, currently available debugging tools and their way of visualization are often useless. With large numbers of processors, the displays get to crowded and one of the main tasks in debugging, the inspection of events is impossible. This paper describes ATEMPT (A Tool for Event ManiPulaTion) which is the inspection tool of the MAD debugging environment. It visualizes monitored executions and provides facilities to investigate program runs. Furthermore it contains functionality to reduce the complexity of parallel program visualization. The main concept is to abstract the monitored data to points of major interest, which are places where bugs occurred. With these abstraction mechanisms it is possible to debug programs for massively parallel architectures.
机译:当考虑运行大规模并行体系结构的程序时,当前可用的调试工具及其可视化方式通常是无用的。由于处理器数量众多,显示变得拥挤,并且是调试的主要任务之一,因此无法进行事件检查。本文介绍了ATEMPT(一种用于事件处理的工具),它是MAD调试环境的检查工具。它可视化受监视的执行,并提供调查程序运行的工具。此外,它还包含减少并行程序可视化的复杂性的功能。主要概念是将监视的数据抽象到主要关注点,这些重要点是发生错误的地方。利用这些抽象机制,可以调试大规模并行体系结构的程序。

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