NVIDIA Cuda C Getting Started Guide for Microsoft Windows

Download the Cuda Software

The Cuda software is available athttp: // www.nvidia.com/object/cuda_get.html.

Choose the platform you are using and download the following:

The Cuda driver
The Cuda driver is integrated into the NVIDIA forceware graphics driver, which can be downloaded fromhttp: // www.nvidia.com/drivers.
To use the Cuda toolkit, you must have at least the version of the NVIDIA graphics driver specified in the Cuda toolkit release notes. A developer version of the NVIDIA graphics driver is available from the Cuda software download page that corresponds to
Version of the Cuda toolkit also available for download there, but any newer NVIDIA driver will work as well.

The Cuda Toolkit

The Cuda toolkit contains the tools needed to compile and build a Cuda application in conjunction with Microsoft Visual Studio. It supports des tools, libraries, header files, and other resources.

 The GPU computing SDK

The GPU computing SDK (software development kit) has des sample projects that have all the necessary project configuration and build files to perform one-clickbuilds using Microsoft Visual Studio. these software packages are available for both 32-bit
Windows and 64-bit windows.

 

Install the Cuda Software

 

Use the following procedure to install the Cuda software:

1. Install the Cuda toolkit.
Install the Cuda Toolkit by executing the Toolkit installer package and following the on-screen prompts. the Cuda toolkit installation defaults to C: \ Program Files \ nvidia gpu computing toolkit \ Cuda \ v #. #, where #. # Is version number 3.2 or higher. this directory
Contains the following:

Bin \-the compiler executables and runtime Libraries

Include \-the header files needed to compile Cuda programs
Lib \-the library files needed to link Cuda programs
Doc \-The Cuda C Programming Guide, Cuda C best practices guide, documentation for the Cuda libraries, and other Cuda toolkit-related documentation

Note: Cuda toolkit versions 3.1 and earlier installed into C: \ Cuda by default, requiring prior Cuda toolkit versions to be uninstalled before the installation of new versions. beginning with Cuda Toolkit 3.2, multiple Cuda Toolkit
Versions can be installed simultaneously.

2. Install the GPU computing SDK.
Install the GPU computing SDK by executing the installer package and following the on-screen prompts. the GPU computing SDK is installed in C: \ Documents ents and Settings \ All Users \ Application Data \ NVIDIA Corporation \ nvidia gpu computing SDK (or under % programdata % \ NVIDIA
Corporation \... on Windows Vista or later) and contains source code for example problems and templates for Microsoft Visual Studio.

 

Verify the installation

Before continuing, it is important to verify that the Cuda programs can find and

Communicate correctly with the cuda-enabled hardware. To do this, you need
Compile and run some of the supported ded sample programs.
Compiling the examples
The version of the Cuda Toolkit can be checked by running nvcc-V in a command
Prompt window. You can display a command prompt window by going:
Start-> All Programs-> accessories-> Command Prompt
The GPU computing SDK has des sample programs in both source and compiled form.

 
To verify a correct configuration of the hardware and software, it is highly recommended that you run the bandwidthtest program located in C: \ Documents and Settings \ All Users \ Application Data \ NVIDIA Corporation \ nvidia gpu computing SDK \ c \ bin \ Win32 \ release,
Presuming that you used the default installation directory structure. (on 64-bit versions of Windows, the directory name ends with \ win64 \ release .) if Cuda is installed and configured correctly, the output shoshould look similar to figure 1.

The device name (second line) and the bandwidth numbers vary from system to system. the important items are the second line, which confirms a Cuda device was found, and the second-to-last line, which confirms that all necessary
Tests passed.

If the tests do not pass, make sure you do have a cuda-enabled nvidia gpu on your system and make sure it is properly installed. to see a graphical representation of what Cuda can do, run the sample participant

Executable in:
For Windows XP:
C: \ Documents ents and Settings \ All Users \ Application Data \ nvidia gpu computing SDK \ c \ bin \ Win32 \ release (or... \ Win64 \ release on 64-bit Windows)

For Windows Vista and Windows 7:
C: \ programdata \ NVIDIA Corporation \ nvidia gpu computing SDK \ c \ bin \ Win32 \ release (or... \ Win64 \ release on 64-bit Windows)

 

------- From NVIDIA