首页> 外文期刊>Advances in software engineering >LTTng CLUST: A System-Wide Unified CPU and GPU Tracing Tool for OpenCL Applications
【24h】

LTTng CLUST: A System-Wide Unified CPU and GPU Tracing Tool for OpenCL Applications

机译:LTTng CLUST:适用于OpenCL应用程序的系统范围的统一CPU和GPU跟踪工具

获取原文
           

摘要

As computation schemes evolve and many new tools become available to programmers to enhance the performance of their applications, many programmers startedto look towards highly parallel platforms such asGraphical Processing Unit(GPU). Offloading computations that can take advantage of the architecture of the GPUis a technique that has proven fruitful in recent years. This technology enhances the speed and responsiveness of applications. Also, as a side effect, it reduces thepower requirements for those applications and therefore extends portable devices battery life and helps computing clusters to run more power efficiently. Many performance analysis tools such asLTTng,straceandSystemTapalready allowCentral Processing Unit(CPU) tracing and help programmers to use CPU resources more efficiently. On the GPU side, different tools such asNvidia’sNsight,AMD’sCodeXL, and third partyTAUandVampirTraceallow tracingApplication Programming Interface(API) calls and OpenCL kernel execution. These tools are useful but are completelyseparate, and none of them allow a unified CPU-GPUtracing experience. We propose an extension to the existing scalableand highly efficientLTTngtracing platform to allowunified tracing of GPU along with CPU’s full tracingcapabilities.
机译:随着计算方案的发展以及许多新工具可供程序员用来增强其应用程序的性能,许多程序员开始将目光投向高度并行的平台,例如图形处理单元(GPU)。可以利用GPU架构的卸载计算是一项近年被证明富有成果的技术。该技术提高了应用程序的速度和响应速度。另外,它的副作用是,它降低了这些应用程序的电源需求,从而延长了便携式设备的电池寿命,并帮助计算群集高效地运行更多电源。诸如LTTng,strace和SystemTapal之类的许多性能分析工具都允许跟踪中央处理器(CPU),并帮助程序员更有效地使用CPU资源。在GPU方面,Nvidia的Nsight,AMD的CodeXL和第三方TAU和VampirTraceallow等不同的工具可跟踪应用程序编程接口(API)调用和OpenCL内核执行。这些工具很有用,但完全分开,并且都无法提供统一的CPU-GPU跟踪体验。我们建议对现有的可扩展且高效的LTTng跟踪平台进行扩展,以支持GPU的统一跟踪以及CPU的全部跟踪功能。

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