Intel® Developer Zone:
Getting Started With OpenCL™ Applications

Overview

OpenCL™ (Open Computing Language) is an open standard for general-purpose parallel programming for diverse mix of multi-core CPUs, graphics processors, coprocessors, and other parallel processors. OpenCL provides a flexible execution model and uniform programming environment for software developers to write portable code for client systems running on both the CPU and graphics processors like Intel® Iris™ Graphics and Intel® HD Graphics, and for server systems with coprocessors like the Intel® Xeon Phi™ coprocessor.

OpenCL is developed by multiple companies through the Khronos* OpenCL committee.

Intel® SDK for OpenCL™ Applications - Product Matrix

 
Version 2013 R3
Version 2014 Beta

Version XE 2013 R3 

Supported Processors


 

Intel® HD Graphics Family √  
Intel® Iris™ Graphics Family √  
Intel® Atom™ Processor √  
Intel® Core™ Processor √  
Intel® Xeon® Processor   √
Intel® Xeon Phi™ Coprocessor   √

Operating Systems


 

Android* 4.4 (Target1) √  
Ubuntu* 12.04 (Host2) √  
Windows 7* √ √
Windows 8* √ √
Windows 8.1* √  
Windows Server 2008/2012*   √
Red Hat Enterprise Linux* (RHEL)   √
SUSE Linux Enterprise Server* (SLES)   √

1 Target: where your OpenCL application is running
2 Host: where your OpenCL application is developed

Event Archives

OpenCL* Fall Webinar Series

Watch this webinar series that is sure to help you get the most performance out of OpenCL* applications using 4th generation Intel® Core™ processors with Intel® Graphics.

SIGGRAPH 2013

July 21-25 Convention Center, Anaheim, CA, Booth #201

Demos:

Talks:

All Intel’s content from SIGGRAPH 2013 is now available at: software.intel.com/en-us/siggraph2013

GDC 2013

SIGGRAPH 2012

 

Vegas™ Pro by Sony*

Maximizes product performance with hardware-accelerated processing using OpenCL on 4th Generation Intel® Core™ processors and with Intel® Graphics

Video

Learn more


PowerDirector* by Cyberlink

“CyberLink was one of the first ISVs to offer OpenCL support. Implementing it in our award-winning video editor, PowerDirector, has created tremendous value for our customers by enabling big gains in video processing speed and, consequently, a significant reduction in total video editing time.” Louis Chen, Assistant Vice President, CyberLink Corp.

Learn more


Capture One* by Phase One

"Capture One Pro introduces OpenCL based optimizations for Haswell, enabling remarkably faster interaction with and processing of RAW image files, providing a better experience for our quality-conscious users.”

Learn more

  • What is OpenCL™?
  • OpenCL™ (Open Computing Language) is an established open standard for general-purpose parallel programming of heterogeneous systems. OpenCL provides a uniform programming environment for software developers to write portable code for client computer systems, high-performance computing servers, and handheld devices using a diverse mix of multi-core CPUs, Graphics Processers, and other parallel processors and coprocessors. The standard is defined by the OpenCL Working Group, led by Khronos*. More information is available at: khronos.org/opencl
  • What is the Intel® SDK for OpenCL Applications?
  • Available as a free download, the Intel® SDK for OpenCL Applications provides a comprehensive development environment for OpenCL application on Intel platforms including compatible drivers, code samples, development tools, such as the Code Builder, optimization guide, and support for optimization tools.
  • What is the extent of OpenCL support today, and what are the differences between the different versions of the SDK?
  • Intel today supports OpenCL 1.2 on 3rd and 4th generation Intel® Core™ Processors with Intel® HD Graphics and Intel® Iris™ Graphics Family, Intel® Atom™ Processors with Intel HD Graphics, Intel® Xeon® processors, and Intel® Xeon Phi™ coprocessors. The following are the flavors of the SDK for OpenCL eevelopers:
    • Intel® SDK for OpenCL™ Applications 2013: Supports visual computing applications on both CPUs and Intel Graphics on 3rd and 4th generation Intel® Core™ Processors and Intel Atom Processors formerly codenamed Bay Trail.
    • Intel SDK for OpenCL™ Applications XE 2013: Supports highly-parallel compute applications on both Intel Xeon processors and Intel Xeon Phi coprocessors

    (New!) Intel SDK for OpenCL Applications 2014 Beta: Extends the 2013 version with support for Android* OS as target platform for application development, support for Ubuntu* OS as host system for application development, and new tools like API Debugger. Products comparison available here

  • How do I download the Intel SDK for OpenCL Applications?
  • The various packages and versions of the Intel® SDK for OpenCL Applications are available as free downloads for developers at intel.com/software/opencl.
  • What is OpenCL 1.2 and what benefits does it provide to developers?
  • OpenCL 1.2 ratified by the Khronos group in December 2012. OpenCL 1.2 promises more flexibility in software design for OpenCL developers with improved compilation, linking, and library support, and improved graphics and media surface sharing. The Intel SDK for OpenCL Applications provides way to develop and use the new features available with the OpenCL technology version 1.2.
  • Are Intel's implementations of the OpenCL Standard fully certified with the OpenCL 1.2 specification?
  • The production versions of the OpenCL runtimes for 3rd and 4th Generation Intel Core Processors with Intel® Graphics, Intel Atom Processors formerly codenamed Bay Trail, for the Intel Xeon Processors, and Intel Xeon Phi coprocessors are fully certified with the OpenCL 1.2 specification.
  • How long has Intel been involved in OpenCL technology?
  • Intel was a founding member of the OpenCL Working Group, led by Khronos. Intel has been one of the leading voices in ensuring the OpenCL feature set supports OpenCL programmers on current and future Intel® Architecture.
  • How do I get support for Intel SDK for OpenCL Applications?
  • You are welcome to join the Intel SDK for OpenCL™ Applications Support Forum to post your questions and issues. The support team monitors the discussion to address questions. This forum covers OpenCL issues on CPU, Intel HD Graphics, and Intel Xeon Phi coprocessor.
  • Where do I find more information about Intel® SDK for OpenCL Applications?
  • The Getting Started With OpenCL Applications on Intel Developers Zone is a one-stop shop for downloads, support, and information on the Intel SDK for OpenCL Applications. Here you'll find free downloads of the SDK, software, code samples, product documentation, information on interoperable products, videos, technical articles, case studies, and the support forum.
  • How can I share my OpenCL Code with Intel?
  • This product support is done through the Intel® SDK for OpenCL Applications Support Forum. The forum provides you the option to attach your code files to a forum post. If you need to share private information with the SDK support team, request support engineers to answer your thread in a private channel.
    For sharing more information with Intel, we encourage you to become an Intel® Software Partner. Join us today at software.intel.com/en-us/partner-home.
  • Which debugging and optimization tools does Intel provide for OpenCL developers?
  • Intel SDK for OpenCL Applications provides a comprehensive environment for building, debugging, and tuning your OpenCL applications. In addition, OpenCL profiling is available with Intel's profiling tools like the Intel® VTune™ Amplifier XE and the Intel® Graphics Performance Analyzers (Intel® GPA).

    The SDK includes the following tools for OpenCL development:

    • Kernel Builder for OpenCL™ API - enables kernels design and optimization
    • Integration with IDEs
    • OpenCL Kernel Debugger

    Each SDK version includes a user guide with more details on available tools and provides guidelines on using them.

Intel® SDK for OpenCL™ Applications 2013

  • What is New in Intel® SDK for OpenCL™ Applications 2013 R3?
  • New features with this SDK are comparing to the lower version:
    • Unified SDK package with support for Windows* 7, Windows* 8, and Windows* 8.1 OS
    • Support the unified Intel® Graphics Driver version 15.33.8 and higher on all supported Windows* OS versions and on all supported Intel® Core™ Processors and Intel® Atom™ Processors.
    • Video Motion Estimation Sample
    • Updated header files:
      • cl.hpp
      • cl_ext.h
  • What is New in Intel® SDK for OpenCL™ Applications 2013 R2?
  • New features with this SDK are comparing to the lower version:
    • Support for Windows* 8.1 Operating System, 32-bit and 64-bit versions.
    • OpenCL™ 1.2 compliant on Intel® Atom™ Processors formerly codenamed Bay Trail
      • Intel Atom Processor Z3000 Series with Intel HD Graphics
      • Intel® Celeron® Processor J1000/N2000 Series with Intel HD Graphics
      • Intel® Pentium® Processor J2000/N3000 Series with Intel HD Graphics
    • Tracing of OpenCL kernels execution on Intel® Processor Graphics with Intel® VTune™ Amplifier XE 2013 Update 12 and above.
    • New OpenCL vendor extensions with support to hardware accelerated motion estimation built-in kernels
      • cl_accelerator_intel
      • cl_intel_motion_estimation
  • What Are Intel® HD Graphics and Intel® Iris™ Graphics Families?
  • 3rd and 4th generation Intel Core Processors are integrated with powerful graphic engines named Intel® HD Graphics, Intel® Iris™ Graphics, and Intel Iris Pro Graphics. The Intel Graphics Driver for Windows* expose OpenCL 1.2 devices for both the Intel Core processor (CPU) and the Intel HD Graphics (GPU). The latest release of Intel Graphics Driver adds OpenCL 1.2 support for Intel® Atom™ Processors formerly codenamed Bay Trail. For more information refer to intel.com/content/www/us/en/architecture-and-technology/hd-graphics/hd-graphics-developer.html
  • How Do I Download Intel® SDK for OpenCL™ Applications 2013 and which Package Should I Use?
  • OpenCL support packages are available in 3 configurations:
    • SDK package with development tools and documentation. Use this package when you want to develop an OpenCL application.
    • Intel Graphics Driver for Windows* 7 and 8.1 with OpenCL™ 1.2 runtime for both CPU and Intel Graphics. Install the latest version of the driver to get full OpenCL support on the supported systems.
    • CPU runtime only package with OpenCL complier and runtime for CPU device. Use this package if you want to test OpenCL™ 1.2 on systems without the SDK installed and without an Intel graphics driver that supports OpenCL.

    To download the SDK package go to the SDK page, select “Download” and choose the package you need in the pop-up menu. See more information in the installation notes.

  • What Optional OpenCL™ Features Are Implemented?
  • Intel SDK for OpenCL™ Applications 2013 supports many optional OpenCL 1.2 features and extensions such as interoperability with DirectX*, OpenGL*, Media Surface Sharing, and many more. For a full list of supported features and their descriptions, please see the Intel SDK for OpenCL™ Applications 2013 Users' Guide or the SDK release notes.
  • Can OpenCL 1.1 Applications Run with the New SDK?
  • Yes. OpenCL 1.2 devices are compatible with OpenCL 1.1 applications. Moreover, if you developed OpenCL applications with Intel SDK for OpenCL Applications 2012 that target Intel HD Graphics, these applications should also run as is with this new SDK. Please check issues and limitations in the release notes for more information.
  • Can I Develop Applications for Windows* 8.1?
  • Yes. This SDK provides compatibility of desktop applications across Windows* 7, 8, and 8.1 on a wide range of Intel processors. Windows 8 desktop applications retain the flexibility of a traditional Windows desktop along with touch capabilities. Verify that you have updated your graphics driver to the latest version here.
  • Can I Distribute Applications Developed with Intel SDK for OpenCL Applications 2013?
  • Yes. OpenCL 1.2 compliant applications will run seamlessly on all systems that have the latest driver version. If application targets a system without support for OpenCL in the Intel® Graphics Driver, you can direct users to download the CPU only runtime and run your OpenCL workloads on the CPU.
  • How Do I Uninstall Intel SDK for OpenCL™ Applications?
  • To remove SDK components use the Control Panel or select Start > All Programs > Intel® SDK for OpenCL™ Applications 2013 R3 > Uninstall.

    See more information in the installation notes.

  • How Can I Uninstall Intel® SDK for OpenCL™ Applications Manually?
  • To uninstall the SDK manually follow the steps below:
    For 64-bit operating systems:
    • delete the folder C:\Program Files (x86)\Intel\OpenCL SDK\
    • delete environment variable INTELOCLSDKROOT
    • edit PATH environment variable to remove the path(s) to C:\Program Files (x86)\Intel\OpenCL SDK\\bin\x64|x86
    • delete registry key HKEY_LOCAL_MACHINE\SOFTWARE\Wow6432Node\Intel\OpenCL [IntelOpenCL32.dll]
    • delete registry key HKEY_LOCAL_MACHINE\SOFTWARE\Intel\OpenCL [IntelOpenCL64.dll]
    • delete the folder C:\Program Files\Intel\OpenCL SDK\
    • delete environment variable INTELOCLSDKROOT
    • edit PATH environment variable to remove the path to C:\Program Files (x86)\Intel\OpenCL SDK\\bin\x86
    • delete registry key HKEY_LOCAL_MACHINE\SOFTWARE\Intel\OpenCL [IntelOpenCL32.dll]

    See more information in the installation notes.

  • Does Intel Graphics Generate Code that Fully Utilizes the Execution Units?
  • Generally, the Intel Graphics driver is designed to generate and run OpenCL™ code that fully utilizes the execution units (EUs). Nevertheless, it is recommended to read Intel SDK for OpenCL Applications - Optimization Guide to learn how to get the best performance out of the Intel HD Graphics.
  • Does Intel SDK for OpenCL Applications Generate Code that Fully Utilizes the Intel® Advanced Vector Extensions (Intel® AVX and Intel® AVX2)?
  • Yes, Intel SDK for OpenCL™ Applications 2013 introduces performance improvements that include full code generation on the Intel Advanced Vector Extensions (Intel AVX and Intel AVX2). The Implicit CPU Vectorization Module generates the Intel AVX and Intel AVX2 code depending on what the target platform supports.
  • Is It Possible to Tell OpenCL Not to Use All Graphics Execution Units or CPU Cores?
  • By default the Intel HD Graphics utilizes all execution units and this is not configurable.
    However, for the CPU device the Intel SDK for OpenCL Applications provides support of the Device Fission optional feature (also known as sub device), which can be used to control a number of CPU cores used for OpenCL. For more information on device fission please see the related article.
  • Which Debugging and Optimization Tools Are Included in the Intel SDK for OpenCL Applications 2013?
  • The Intel SDK for OpenCL™ Applications 2013 provides a comprehensive environment for building, debugging, and tuning of your OpenCL™ applications. In addition, the SDK takes advantage of the following Intel profiling tools:
    1. Intel VTune™ Amplifier XE
    2. Intel Graphics Performance Analyzers (Intel GPA).

    The table below shows the availability of tools:

    Tool CPU Intel HD Graphics (GPU)

    Kernel Builder (Standalone)

    Yes

    Yes

    Integration with Microsoft Visual Studio* 2008-2012

    Yes

    Yes

    Step by Step Kernel Debugger

    Yes

    No

    Intel VTune™ Amplifier XE

    Yes

    Yes

    Intel GPA

    Yes

    Yes

    Read more at the tools section of the user guide.
    Tools support for Linux OS for CPU and Intel Xeon Phi coprocessor is available with the Intel SDK for OpenCL Applications XE – intel.com/software/opencl-xe.

  • What Is the Status of OpenCL™ on Intel Processors on Apple* Mac OS* X?
  • As of today, Apple supports OpenCL as part of Mac OS* X. Ask Apple for direct comment on specific features and compatibility.
  • When Would You Suggest Using Intel Media SDK and OpenCL Together with the SDK?
  • The Intel Media SDK and the Intel SDK for OpenCL Applications are complementary tools. The Intel Media SDK provides the best performance for media encode, decode and processing using Intel Processor Graphics. OpenCL could be used in conjunction with the Intel Media SDK for custom video pre-processing filters running on either Intel CPUs or Intel Processor Graphics. The SDK includes a sample to illustrate exactly this.
  • How Can I Debug my OpenCL™ Kernels?
  • The Kernel Debugger that is part of the SDK is a Microsoft Visual Studio* plug-in, which enables stepping into OpenCL kernels using the familiar interface of the Microsoft Visual Studio* software debugger for Intel CPUs. To get more debugging capabilities, use the printf function inside OpenCL™ kernels on both the CPU and Intel HD Graphics. For more debugging capabilities, try the new SDK 2014 Beta version.
  • What is Intel® SDK for OpenCL™ Applications XE 2013?
  • Intel® SDK for OpenCL™ Applications XE 2013 is a comprehensive software development environment for OpenCL applications in the domain of highly parallel applications. It adds OpenCL 1.2 support on both Intel® Xeon® processors and Intel® Xeon Phi™ coprocessors.
  • What's new with Intel® SDK for OpenCL™ Applications XE 2013 R3?
  • New features included in this release are:

    • Gold support for OpenCL 1.2 using the Intel® Xeon Phi™ coprocessor on Windows* OS.
    • Fixed kernel compilation crashes under debug and profiling modes.
    • Performance improvements.
    • New performance related environment variables on the Intel Xeon Phi coprocessors.

    For more details go to Intel® SDK for OpenCL™ Applications XE release notes.

  • What's new with Intel® SDK for OpenCL™ Applications XE 2013 R2?
  • In addition to the OpenCL 1.2 support for Linux* OS, the R2 release adds Beta software support for OpenCL 1.2 using Intel Xeon Phi coprocessors on Windows* operating systems.

    Other new features included in this release are:

    • Support for Intel Xeon Processor E5-2600 Product Families
    • Preview feature: Support for OpenCL SPIR 1.2 provisional specification
    • Intel® VTune™ Amplifier XE 2013 source-view support for OpenCL Kernels on Intel Xeon Phi coprocessors.
  • I have used previous versions, How can I upgrade for the latest production version?
  • If you developed code with the previous version, your code is expected to work as is on the new version. Simply download the new Intel SDK for OpenCL Applications XE 2013 at intel.com/software/opencl-xe and then follow the installation notes available at Installation Notes.
  • What hardware platforms and operating systems are supported?
  • Intel SDK for OpenCL Applications XE supports Windows* 7, 8, Server 2008, Server 2012, RedHat Linux* and SUSE Linux* operating systems. For more details see the System Requirements section of the Release Notes.
  • Where can I download the Intel SDK for OpenCL XE 2013?
  • You can download the Intel SDK for OpenCL Applications XE 2013 from intel.com/software/opencl-xe.
  • Will I need to have an Intel Xeon Phi Coprocessor to use this software?
  • The Intel SDK for OpenCL Applications XE 2013 includes 2 packages: the SDK, and the CPU and coprocessor shared runtime. To run the coprocessor OpenCL device you need the Intel Xeon Phi coprocessor to be physically on your system, otherwise the installed runtime will provide OpenCL support only for the CPU. Thus the answer to this question is "Yes", however developers who do not have access to an Intel Xeon Phi coprocessor device will be able to start development on a CPU device and be ready for future availability of the coprocessor.
  • Where can I learn more about Intel Xeon Phi Coprocessor?
  • Information resources for Intel Xeon Phi coprocessor are available at software.intel.com/mic-developer.
  • Is this implementation fully certified with the OpenCL 1.2 specification?
  • Yes, the SDK XE 2013 R3 version implementation is fully certified with the OpenCL 1.2 specification.
  • Does OpenCL fully utilize the Intel® Many Integrated Core Architecture (Intel MIC Architecture)?
  • Intel SDK for OpenCL Applications XE 2013 implements implicit vectorization and threading systems that fully utilize the multicore, many-core, and vector technologies available with Intel Xeon processor and Intel Xeon Phi coprocessor.
  • Can I distribute applications developed with Intel SDK for OpenCL Applications XE 2013?
  • Yes, this production software provides you the option to deploy applications with this software. Please read more in the product End-User License Agreement.
  • Which debugging and optimization tools does Intel provide for OpenCL Developers for Linux* operating systems?
  • Intel SDK for OpenCL Applications XE 2013 provides a comprehensive environment for the building, debugging, and tuning your OpenCL* applications. In addition, the SDK takes advantage of the Intel VTune™ Amplifier XE tool.

    The table below shows the availability of OpenCL tools for Linux* operating systems running on Intel Xeon processors and the Intel Xeon Phi coprocessors.

    Tool Intel® Xeon™ Processor

     

    Intel® Xeon Phi™ Coprocessor

     

    Kernel Builder (Standalone and integration with Eclipse* IDE and Microsoft Visual Studio* 2008-2012 IDE)

    Yes

    Yes

    Offline Compiler Command-Line Interface (standalone)

    Yes

    Yes

    Step by Step Kernel Debugger

    Yes

    No

    Intel® VTune™ Amplifier XE

    Yes

    Yes

    More details available in the product's user guide

  • What is Intel® SDK for OpenCL™ Applications 2014 Beta?
  • The Intel SDK for OpenCL Applications 2014 Beta provides a comprehensive development platform for OpenCL applications on Windows* and Android* operating systems running on Intel® Architecture Processors with Intel® HD Graphics and Intel® Iris™ Graphics families.
  • What is New in Intel SDK for OpenCL Applications 2014 Beta?
  • Intel SDK for OpenCL Applications 2014 Beta extends the already supported Windows* operating systems with the Android* OS support. Comparing to the Intel® SDK for OpenCL Applications 2013 version, this new 2014 Beta software brings the following new features and capabilities:

    What's New:

    • Support for Android* OS 4.4 (KitKat) as target platform running on Intel® Atom™ processors with Intel HD Graphics, formerly codenamed Bay Trail.
    • Introduction of the Code Builder - a single toolset, bundled with the SDK, that includes all SDK 2013 features and the following new capabilities:
      • Remote OpenCL Kernel development on supported Android devices and emulator
      • Integration with Eclipse* IDE
      • Integration with Microsoft Visual Studio* 2013 IDE
      • OpenCL API level debugging with command tracing, queue, and memory views
      • OpenCL kernel performance analysis (deep kernel analysis)
      • Automatic generation of OpenCL host code with predefined kernels
      • Saving and Restoring sessions in the Kernel Builder
    • Support for Ubuntu* OS 12.04 as the host system for application development
    • Microsoft Visual Studio* 2013 support in the OpenCL samples that are available online.
  • What Version of OpenCL Standard is Supported on Android* OS?
  • The support for OpenCL 1.2 for Android operating systems is based on a published Khronos* Specification.
  • Does this SDK Supports Android* RenderScript?
  • The RenderScript technology is supported on Android* OS 4.4 (KitKat) on the Intel® Atom™ processors with Intel HD Graphics, formerly codenamed Bay Trail. To learn more on how to accelerate applications with SoC Compute and RenderScript*, try Intel® INDE.
  • What Are the System Requirements?
  • For information on supported operating systems, hardware, and additionally required software, see the System Requirements section of the Release Notes.
  • Does Intel SDK for OpenCL Applications 2014 Beta Install on Non-Intel Systems?
  • To run and use the Intel SDK for OpenCL Applications 2014 Beta you must have a PC based on an IA-32 or Intel 64 architecture processor.
  • What Intel® Graphics Devices and Drivers Are Supported?
  • The following Intel Graphics devices support the OpenCL technology:

    • Intel® Iris™ Pro Graphics 5200
    • Intel® Iris™ Graphics 5100
    • Intel® HD Graphics 4200/4400/4600/5000
    • Intel® HD Graphics 4000/2500
    • Intel® HD Graphics of the Intel Atom processors formally codenamed "Bay Trail"

    For OpenCL technology support on the aforementioned graphics devices, you need the Intel® Graphics Driver version 15.33.3 or higher.

  • Can I Distribute Applications Developed with the Intel SDK for OpenCL Applications 2014 Beta?
  • Yes. Windows* and Android* applications that are compliant with the OpenCL 1.2 specification are able to run seamlessly on all systems that have the latest driver version. The SDK 2014 Beta is working with certified OpenCL drivers, also available at: http://software.intel.com/en-us/articles/opencl-drivers.
  • Why Can’t I Distribute Ubuntu Applications Developed with the 2104 Beta version?
  • The purpose of the Ubuntu* OS support is remote development of OpenCL application on Android device or emulator. The OpenCL device that is available upon SDK installation on a machine with Ubuntu OS should only provide development environment on the host system, enabling building OpenCL kernel code on the host machine before testing and optimizing it on a target Android system.
  • What is the New Code Builder Tool?
  • Intel SDK for OpenCL Applications 2014 Beta includes a new tool called Code Builder with the following capabilities:

    • JumpStart Kit – an integrated wizard that generates OpenCL code and also assist in building the first OpenCL project.
    • Code Editing – a set of tools that provide full integration with Eclipse* and Microsoft Visual Studio* IDEs, including syntax highlighting and code completion.
    • Compile and Build – tools that provide offline compilation and binary generation of OpenCL kernels, remote building on Android devices as target platform, and full IDE integration, with support for compile errors reporting.
    • OpenCL API debug – a tool for debugging OpenCL API calls, objects, and queues. Also provides OpenCL kernel debugging capabilities.
    • OpenCL Kernel Debugging – a feature for step by step debugging on the host CPU.
    • Kernel Analysis – a feature for dynamic performance analysis of OpenCL kernels on the target Intel® Graphics and CPU device.

    The Code Builder is integrated with Microsoft Visual Studio* and Eclipse* IDEs, and is also available in a standalone version - the Kernel Builder for OpenCL API.

  • Do I Need to Install the CPU Package Separately?
  • Intel Graphics Driver for the 3rd and 4th Generation Intel® Core™ Processors installs OpenCL runtime for both GPU and CPU devices. To acquire the OpenCL runtime for the 2nd Generation Intel Core Processor family refer to the OpenCL Drivers page at http://software.intel.com/en-us/articles/opencl-drivers.
  • Is OpenCL Kernel Debugging Supported on GPU?
  • Intel SDK for OpenCL Applications 2014 Beta supports debugging OpenCL kernels on the CPU only.
  • I Can't Set Breakpoints or Debug my OpenCL Kernel. What Should I Do?
  • Debugging of OpenCL kernels is supported only on the CPU device. Follow the steps below for debugging OpenCL kernels on the CPU device from Microsoft Visual Studio* IDE.

    • Enable the debugger in the Visual Studio IDE by going to Tools > Code Builder Options and checking the Enable OpenCL Kernel Debugging check box.
    • From the host code, build the kernel by passing "-g -s <path_to_kernel>" to clBuildProgram().
    • Make sure there are no #include files in the kernel that is being debugged

You can reply to any of the forum topics below by clicking on the title. Please do not include private information such as your email address or product serial number in your posts. If you need to share private information with an Intel employee, they can start a private thread for you.

New topic    Search within this forum     Subscribe to this forum


Inconsistent cl_device_id order
By Sean S.1
I tried to create a program from source, build it and save its binary, and then create a program from binary.  However, when I went to build it the second time I got the follow error: -42 (CL_INVALID_BINARY).  I tracked down the issue being that the order of the cl_device_id's I passed to clCreateContext, if not the same order I get when I query clProgramGetInfo with CL_PROGRAM_DEVICES.  This was quite an unexpected surprise.  Why wouldn't this order be maintained?  Changing that order causes me more headache as I need to query clGetDeviceInfo all over again.  I realize after reading through the spec that it does not require a consistent order, but what is to be gained from not maintaining an order even within the same program execution?   Btw, I'm using the latest non-beta Intel graphics driver and OpenCL SDK for Windows 8.1 64-bit with Visual Studio 2012 Professional.
I uninstalled sdk 2012, but can't install sdk 2013
By wang h.2
I am having problems installing the 2013 version of the OpenCL SDK, on Windows 7 with VS 2010. I have a Xeon E5-26900 CPU(32-bit). I have installed 2012 version of the OpenCL SDK and it worked very well. I just want to update my version. So that I firstly uninstalled 2012 version by running Start > All Programs > Intel SDK for OpenCL Applications 2013 > Uninstall . Then I click "intel_sdk_for_ocl_applications_2013_r3_runtime_x86_setup.msi" to install version 2013. But it reported a crash, and it says "A newer version of Intel SDK for OpenCL* - CPU only Runtime Package is already installed." "your system has not been modified. to install this program at a later time , run setup wizard again . " However, neither version shows up in the Control Panel uninstall programs list. When I try running the 2012 installer again, it says "The installer identyfied that the installed version of CPU only Runtime Package was broken". Is there a manual procedure for uninstalling the SDK? .
Opencl: incorrect results on phi
By Dave O.8
This kernel runs on host cpu but produces wrong outputs when run Phi. What's the issue witht the Phi here?   //KERNEL_SIMPLE __kernel void Convolve(const __global  float * pInput,                         __constant float * pFilter,                         __global  float * pOutput,                         const int nInWidth,                         const int nFilterWidth) {     const int nWidth = get_global_size(0);     const int xOut = get_global_id(0);     const int yOut = get_global_id(1);     const int xInTopLeft = xOut;     const int yInTopLeft = yOut;     float sum = 0;     for (int r = 0; r < nFilterWidth; r++)     {         const int idxFtmp = r * nFilterWidth;         const int yIn = yInTopLeft + r;         const int idxIntmp = yIn * nInWidth + xInTopLeft;         for (int c = 0; c < nFilterWidth; c++)         {             const int idxF  = idxFtmp  + c;             const int idxIn = idxIntmp + c;             sum += pFilter[idxF]*pInput[idxIn];     ...
clBuildProgram crashes when targetting HD 4400 Intel GPU
By Aaron B.2
Hello, I am working on an open source jpeg 2000 decoder: https://github.com/OpenCodec/ThousandthChicken I am on windows, using visual studio 2012 and the 2014 beta OpenCL sdk. My laptop has an intel CPU and an HD4400 intel GPU.  When I target the CPU, everything works fine. But, when I target the GPU, clBuildProgram crashes with an access violation.   Thanks, Aaron
Kernel Builder Crashes when trying to "Analyze" kernel. Build is fine
By Dave O.2
Hi   I have this error when I try to analyze a kernel. The build is fine for both 32-bit and 64-bit Kernel Builder. What's the problem?  Problem signature:   Problem Event Name:    APPCRASH   Application Name:    KernelBuilder64.exe   Application Version:    3.0.1.15611   Application Timestamp:    5294801b   Fault Module Name:    StackHash_1e37   Fault Module Version:    0.0.0.0   Fault Module Timestamp:    00000000   Exception Code:    c0000005   Exception Offset:    00000000034202c6   OS Version:    6.1.7601.2.1.0.256.48   Locale ID:    1033   Additional Information 1:    1e37   Additional Information 2:    1e373e69fff075aed81f57003e66ce10   Additional Information 3:    9f0e   Additional Information 4:    9f0e095f32a88249d7a2b7eca4e322ea Read our privacy statement online:   http://go.microsoft.com/fwlink/?linkid=104288&clcid=0x0409 If the online privacy statement is not available, please read our privacy statement offline:   C:\Windows\system32\en-US\erofflps....
Can't install Intel OpenCL SDK 2013
By Jian L.3
Hi everyone, My system is windows 7 home premium, my GPU is Intel HD Graphics 4000, and I have updated the latest the driver. The VS version is Visual Sdudio 2012 Express.  However, when I follow the instruction of install OpenCL SDK, it has problem as follows: "Intel@ SDK OpenCL* Applicatiuons 2013 setup Wizard ended prematurely because of an error. Your system has not been modified. To install program at a later time, run Step Wizard again." If I try SDK 2014 beta: "There is a problem with this Windows Installer package. A program required for this install to complete could not be run." This is my first time to try OpenCL.  Could anyone tell me how to fix this problem?? Thank you!
Program cannot build when setting device to "1"
By Aaron B.2
Hello, I have a laptop with both intel haswell chip and intel HD 4400 GPU I have VS 2012 and the 2014 beta opencl sdk installed. I have taken the median filter sample and modified it to run my own kernel. Using the default device "0" (CPU), everything works fine.  But, if I set device to "1", then I get an error when trying to build the opencl kernel. i.e. when calling clBuildProgram Thanks, Aaron                 .
Can't use intel GPU with OpenCL while AMD HD8790M is installed
By Klamer S.10
In my DELL E6540 laptop I have a Intel HD4600 and an AMD HD8790M GPU. Before installing the AMD graphics driver I could use OpenCL with the Intel GPU (but obviously not the AMD GPU) as well as the Intel CPU device. After installing the AMD graphics driver I can use OpenCL on the Intel CPU device; the AMD GPU device, and the AMD CPU device.   How can I have access to both the Intel GPU and the AMD GPU OpenCL devices?   OS is WIndows 7.1 64 bit. Intel graphics driver is 10.18.10.3496 AMD graphics driver is 13.350.1005.0 (using Catalyst 14.2 Beta1.3

Pages

Subscribe to Forums