面向 OpenCL™ 应用的英特尔® 软件开发套件

Introduction of Intel® VTune™ GPU In-kernel Profiling feature with OpenCL™ sample code

 

This article is the introduction of Intel® VTune™ Analyzer GPU In-kernel Profiling feature. In the article, one of sample OpenCL™ application from Intel® SDK for OpenCL™ Applications is used. At the beginning it will give the brief introduction of OpenCL and Intel SDK for OpenCL Applications as well. And show you how to profile OpenCL SW with Intel VTune Analyzer GPU profiling features especially focusing on the GPU In-kernel Profiling feature. (Intel® System Studio 2018 has the new Intel VTune Analyzer 2018) 

 (1)  What is the OpenCL

  • 合作伙伴
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 10
  • Microsoft Windows* 8.x
  • C/C++
  • 中级
  • 英特尔® VTune™ 放大器
  • 面向 OpenCL™ 应用的英特尔® 软件开发套件
  • OpenCL*
  • source view
  • Intel® Code For Good
  • 平台分析
  • Debugging OpenCL™ Kernels

    This topic demonstrates how to use the OpenCL™ GPU Kernel Debugger to debug an OpenCL sample application on a Microsoft Windows* OS.

    To debug your OpenCL™ Kernels on GPU using OpenCL Kernel Debugger on a Microsoft Windows* OS, perform the following steps:

    On the target machine, launch the Remote Debugger:

    Host and Target Systems are Stuck

    Symptom:

    The host and target machine seem hung/stuck and never run to completion.

    On the host machine, the host application remains in the "Running" state, seems hung/stuck and never runs to completion or hits a breakpoint in the GPU. In addition, the target machine GFX display state seems frozen/hung.

    Build Artifacts

    Once OpenCL™ program build is completed, the build artifacts appear under the Builds Artifacts note in the Code Builder Session Explorer. The list of artifacts includes:

    订阅 面向 OpenCL™ 应用的英特尔® 软件开发套件