Intel® SDK for OpenCL™ Applications

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

  • Partners
  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 10
  • Microsoft Windows* 8.x
  • C/C++
  • Intermediate
  • Intel® VTune™ Amplifier
  • Intel® SDK for OpenCL™ Applications
  • OpenCL*
  • source view
  • Intel® Code For Good
  • Platform Analysis
  • Debugging OpenCL™ Kernels on GPU

    Intel® SDK for OpenCL™ Applications delivers a seamless debugging experience that enables you to debug both CPU and GPU portions of your application simultaneously.

    This chapter provides OpenCL GPU Debugger installation walkthrough and demonstrates how to use the debugger to debug an OpenCL sample application.

    Editing the Variables

    To edit the variables in the system using the Kernel Development Framework, do the following:

    1. Open the Code Builder Variable Management view.
    2. Right-click a variable name.
    3. Click Edit Variable.
    4. Change the desired properties and click OK.

    Message Protocol error

    Symptom: Protocol error message

    Solution: Change firewall settings, or debugging port

    If you receive a "Protocol error" message, you need to change your firewall settings, or change the debugging port in the OpenCL™ Debugger plug-in for Microsoft Visual Studio* IDE.

    Kernel Development Framework

    Kernel Development Framework enables you to build and analyze OpenCL™ kernels.

    The framework supports Intel® Architecture processors and  Intel® Processor Graphics. The tool provides full offline OpenCL language compilation, which includes:

    Subscribe to Intel® SDK for OpenCL™ Applications