Windows7 64-bit CUDA7.0 configuration and simple use example in VS2010

Source: Internet
Author: User

1. Check the native configuration to see if the graphics card type supports NVIDIA GPUs, select Computer-Right-click Properties--Device Manager--Display adapter: NVIDIA GeForce GT 610, from Https://developer. Nvidia.com/cuda-gpus can find the corresponding graphics card compute capability;

2. From http://www.nvidia.cn/Download/index.aspx?lang= CN download the appropriate driver 347.88-desktop-win8-win7-winvista-64bit-international-whql.exe and install;

3. Download the appropriate latest version CUDA7.0 installation from Https://developer.nvidia.com/cuda-toolkit according to the native type;

4. Follow the http://docs.nvidia.com/cuda/cuda-getting-started-guide-for-microsoft-windows/index.html#axzz3W8BU10Ol steps Verify that the installation is correct:

(1), open the C:\ProgramData\NVIDIACorporation\CUDA samples\v7.0 directory under the Samples_vs2010.sln project, respectively, in the debug, Release x64 under the compilation of the entire project;

(2), during the compilation process, you will be prompted to find "D3dx9.h", "D3dx10.h", "D3dx11.h" header files, from the http://www.microsoft.com/en-us/download/details.aspx?id= 6812 Download the Dxsdk_jun10.exe, then install to the default directory, and then compile the project;

(3), open the C:\ProgramData\NVIDIACorporation\CUDA samples\v7.0\bin\win64\release directory, open the cmd command line, Drag the DeviceQuery.exe directly into the CMD, enter, display GPU graphics, Cuda version and other related information, the last line shows: Result = PASS;

(4), drag BandwidthTest.exe to cmd, enter, will show Device0:geforce GT 610 and other related information, there will be a line to show: Result = PASS;

5. Create a new console project Testcuda:nvidia---CUDA7.0, Name:testcuda, will automatically generate a kernel.cu file, directly run it;

6. Let the VS2010 cuda file highlight:

(1), to make the. cu,. cuh files in the C + + syntax highlighting: VS2010-->tools-----------File extension--> Write. cu in extension, select MicrosoftVisual C + + in editor, click Add,.cuh Same operation, click OK;

(2), the CUDA keyword highlighting: put C:\ProgramData\NVIDIACorporation\CUDA Samples\v5.0\doc\syntax_highlighting\visual_studio_ The Usertype.dat file in the 8 directory is copied to the C:\ProgramFiles (x86) \microsoft Visual Studio 10.0\Common7\IDE Directory (Note: This machine is a Win7 64-bit system, If the win732 bit system copies the Usertype.dat file to the C:\Program Files\Microsoft Visual Studio 10.0\Common7\IDE directory), CUDA 7.0 does not have the Usertype.dat file, I use the old version 5.0 in the Usertype.dat file;

(3), the Cuda function highlighting, Cuda function input code hint: first, select Vassistx---Visual Assist X Options--Projects---C/c++directories: Platform Select Custom,show Directories for item Select other include files, select New, C:\Program files\nvidia GPU Computing Toolkit\cuda \v7.0\include directory to join, click Apply, OK, then, use Regedit to open the registry, Hkey_current_user\software\whole tomato\visual Assist x\vanet10, Find the Extsource project on the right, the right mouse button to modify, after the original content to add. cu;. cuh; After determining, close the registry and reopen the VS2010 project;

7. Modify the Testcuda project, remove the Kernel.cu file, add the Testcuda.cu file, and/cuda samples/v7.0/1_utilities/bandwidthtest/ The Bandwidthtest.cu file content is copied to the testcuda.cu to implement the Bandwidthtest functionality, and modifications to the engineering configuration include:

(1), CUDA c/c++--> Common--Additional Include directories:.. /.. /.. /src/common/inc;

(2), CUDA c/c++--> Host---Runtime library:multi-threaded Debug (/MTD) or multi-threaded (/MT).

Windows7 64-bit CUDA7.0 configuration and simple use example in VS2010

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.