当前位置: X-MOL 学术arXiv.cs.PF › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Hierarchical Roofline Analysis: How to Collect Data using Performance Tools on Intel CPUs and NVIDIA GPUs
arXiv - CS - Performance Pub Date : 2020-09-05 , DOI: arxiv-2009.02449
Charlene Yang

This paper surveys a range of methods to collect necessary performance data on Intel CPUs and NVIDIA GPUs for hierarchical Roofline analysis. As of mid-2020, two vendor performance tools, Intel Advisor and NVIDIA Nsight Compute, have integrated Roofline analysis into their supported feature set. This paper fills the gap for when these tools are not available, or when users would like a more customized workflow for certain analysis. Specifically, we will discuss how to use Intel Advisor, RRZE LIKWID, Intel SDE and Intel Amplifier on Intel architectures, and nvprof, Nsight Compute metrics, and Nsight Compute section files on NVIDIA architectures. These tools will be used to collect information for as many memory/cache levels in the memory hierarchy as possible in order to provide insights into application's data reuse and cache locality characteristics.

中文翻译:

分层屋顶线分析:如何在 Intel CPU 和 NVIDIA GPU 上使用性能工具收集数据

本文调查了一系列在 Intel CPU 和 NVIDIA GPU 上收集必要性能数据以进行分层 Roofline 分析的方法。截至 2020 年年中,两个供应商性能工具 Intel Advisor 和 NVIDIA Nsight Compute 已将 Roofline 分析集成到其支持的功能集中。本文填补了这些工具不可用时的空白,或者当用户希望针对某些分析使用更自定义的工作流程时。具体来说,我们将讨论如何在 Intel 架构上使用 Intel Advisor、RRZE LIKWID、Intel SDE 和 Intel Amplifier,以及如何在 NVIDIA 架构上使用 nvprof、Nsight Compute 指标和 Nsight Compute 部分文件。这些工具将用于收集内存层次结构中尽可能多的内存/缓存级别的信息,以便深入了解应用程序
更新日期:2020-10-06
down
wechat
bug