CUDA是NVIDIA的GPU开发工具,眼下在大规模并行计算领域有着广泛应用。

windows平台上面的CUDA开发之前。最好去NVIDIA官网查看说明,然后下载对应的driver。 ToolKits等等。

假设你下载最新版本号的CUDA7.0。里面事实上已经包括了driver及Tool kits。

特别要注意:目标最高版本号为CUDA7.0。仅支持64位系统(32位没法安装CUDA 7.0 Tool Kits)。另外,VS编译平台最低要求是VS2010。

So,那些依旧用VC6或者VS2008的就别犹豫了。赶快换平台吧。

以下贴出NVIDIA官网的start guide:(坑爹的NVIDIA。在develop的地方以及下载tool kits的地方,都没有提到这个start guide,造成笔者重复安装配置了多次。奔溃。。。

。)

1. Introduction

CUDA® is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU).

CUDA was developed with several design goals in mind:

  • Provide a small set of extensions to standard programming languages, like C, that enable a straightforward implementation of parallel algorithms. With CUDA C/C++, programmers can focus on the task of parallelization of the algorithms rather
    than spending time on their implementation.
  • Support heterogeneous computation where applications use both the CPU and GPU. Serial portions of applications are run on the CPU, and parallel portions are offloaded to the GPU. As such, CUDA can be incrementally applied to existing applications.
    The CPU and GPU are treated as separate devices that have their own memory spaces. This configuration also allows simultaneous computation on the CPU and GPU without contention for memory resources.

CUDA-capable GPUs have hundreds of cores that can collectively run thousands of computing threads. These cores have shared resources including a register file and a shared memory. The on-chip shared memory allows parallel tasks running on these cores to share
data without sending it over the system memory bus.

This guide will show you how to install and check the correct operation of the CUDA development tools.

1.1. System
Requirements

To use CUDA on your system, you will need the following installed:

The next two tables list the currently supported Windows operating systems and compilers.

Table 1. Windows Operating System Support in CUDA 7.0
Operating System Native x86_64 Cross (x86_32 on x86_64)
Windows 8.1 YES YES
Windows 7 YES YES
Windows Server 2012 R2 YES YES
Windows Server 2008 R2 YES YES
Table 2. Windows Compiler Support in CUDA 7.0
Compiler IDE Native x86_64 Cross (x86_32 on x86_64)
Visual C++ 12.0 Visual Studio 2013 YES YES
Visual Studio Community 2013 YES NO
Visual C++ 11.0 Visual Studio 2012 YES YES
Visual C++ 10.0 Visual Studio 2010 YES YES

x86_32 support is limited. See the x86 32-bit
Support
 section for details.

x86
32-bit Support

Native development using the CUDA Toolkit on x86_32 is unsupported. Deployment and execution of CUDA applications on x86_32 is still supported, but is limited to use with GeForce GPUs. To create 32-bit CUDA applications,
use the cross-development capabilities of the CUDA Toolkit on x86_64.

Support for developing and running x86 32-bit applications on x86_64 Windows is limited to use with:

  • GeForce GPUs
  • CUDA Driver
  • CUDA Runtime (cudart)
  • CUDA Math Library (math.h)
  • CUDA C++ Compiler (nvcc)
  • CUDA Development Tools

1.2. About
This Document

This document is intended for readers familiar with Microsoft Windows operating systems and the Microsoft Visual Studio environment. You do not need previous experience with CUDA or experience with parallel computation.

2. Installing CUDA Development Tools

The setup of CUDA development tools on a system running the appropriate version of Windows consists of a few simple steps:

  • Verify the system has a CUDA-capable GPU.
  • Download the NVIDIA CUDA Toolkit.
  • Install the NVIDIA CUDA Toolkit.
  • Test that the installed software runs correctly and communicates with the hardware.

2.1. Verify
You Have a CUDA-Capable GPU

To verify that your GPU is CUDA-capable, open the Control Panel (Start > Control
Panel) and double click on System. In the System Properties window that opens, click the Hardware tab,
then Device Manager. Expand the Display adapters entry. There you will find the vendor name and model of your graphics card. If it is an NVIDIA
card that is listed in http://developer.nvidia.com/cuda-gpus, your GPU is CUDA-capable.

The Release Notes for the CUDA Toolkit also contain a list of supported products.

2.2. Download
the NVIDIA CUDA Toolkit

The NVIDIA CUDA Toolkit is available at http://developer.nvidia.com/cuda-downloads. Choose the platform
you are using and one of the following installer formats:

  1. Network Installer: A minimal installer which later downloads packages required for installation. Only the packages selected during the selection phase of the installer are downloaded. This installer is useful for users who want to minimize download
    time.
  2. Full Installer: An installer which contains all the components of the CUDA Toolkit and does not require any further download. This installer is useful for systems which lack network access and for enterprise deployment.

The CUDA Toolkit installs the CUDA driver and tools needed to create, build and run a CUDA application as well as libraries, header files, CUDA samples source code, and other resources.

Download Verification

The download can be verified by comparing the MD5 checksum posted at http://developer.nvidia.com/cuda-downloads/checksums with
that of the downloaded file. If either of the checksums differ, the downloaded file is corrupt and needs to be downloaded again.

To calculate the MD5 checksum of the downloaded file, follow the instructions at http://support.microsoft.com/kb/889768.

2.3. Install
the CUDA Software

Before installing the toolkit, you should read the Release Notes, as they provide details on installation and software functionality.

Note: The driver and toolkit must be installed for CUDA to function. If you have not installed a stand-alone driver, install the driver
from the NVIDIA CUDA Toolkit.
Note: The installation may fail if Windows Update starts after the installation has begun. Wait until Windows Update is complete and then
try the installation again.

Graphical Installation

Install the CUDA Software by executing the CUDA installer and following the on-screen prompts.

Silent Installation

Alternatively, the installer can be executed in silent mode by executing the package with the -s flag.
Additional flags can be passed which will install specific subpackages instead of all packages. Allowed subpackage names are: CUDAToolkit_7.0, CUDASamples_7.0,
CUDAVisualStudioIntegration_7.0, and Display.Driver. For example, to install only the driver and the toolkit components:

<PackageName>.exe -s CUDAToolkit_7.0 Display.Driver

Subpackage Details

  • Display Driver

    Required to run CUDA applications.

  • CUDA Toolkit

    The CUDA Toolkit installation defaults to C:\Program
    Files\NVIDIA GPU Computing Toolkit\CUDA\v7.0. 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 documentation, including:

    • CUDA C Programming Guide
    • CUDA C Best Practices Guide
    • documentation for the CUDA libraries
    • other CUDA Toolkit-related documentation
  • CUDA Visual Studio Integration

    The CUDA Visual Studio Integration registers the CUDA plugins with the supported and installed versions of Visual Studio on the system and installs Nsight Visual Studio Edition. This integration allows
    for CUDA development within Visual Studio.

  • CUDA Samples

    The CUDA Samples contain source code for many example problems and templates with Microsoft Visual Studio 2010, 2012, and 2013 projects.

    The CUDA Samples installation defaults to C:\ProgramData\NVIDIA
    Corporation\CUDA Samples\v7.0.

    Note:C:\ProgramData\ is
    a hidden folder. It can be made visible within Windows Explorer by enabling it through the menu options within Windows Explorer (Tools | Options).

Extracting and Inspecting the Files Manually

Sometimes it may be desirable to extract or inspect the installable files directly, such as in enterprise deployment, or to browse the files before installation. The full installation package can be extracted using a decompression
tool which supports the LZMA compression method, such as 7-zip or WinZip.

Once extracted, the CUDA Toolkit files will be in the CUDAToolkit folder,
and similarily for the CUDA Samples and CUDA Visual Studio Integration. Within each directory is a .dll and .nvi file that can be ignored as they are not part of the installable files.

Note: Accessing the files in this manner does not set up any environment settings, such as variables or Visual Studio integration. This
is intended for enterprise-level deployment.

2.3.1. Uninstalling
the CUDA Software

All subpackages can be uninstalled through the Windows Control Panel by using the Programs and Features widget.

2.4. Use
a Suitable Driver Model

On Windows 7 and later, the operating system provides two driver models under which the NVIDIA Driver may operate:

  • The WDDM driver model is used for display devices.
  • The Tesla Compute Cluster (TCC) mode of the NVIDIA Driver is available for non-display
    devices such as NVIDIA Tesla GPUs; it uses the Windows WDM driver model.

The TCC driver mode provides a number of advantages for CUDA applications on GPUs that support this mode. For example:

  • TCC eliminates the timeouts that can occur when running under WDDM due to the Windows Timeout
    Detection and Recovery
     mechanism for display devices.
  • TCC allows the use of CUDA with Windows Remote Desktop, which is not possible for WDDM devices.
  • TCC allows the use of CUDA from within processes running as Windows services, which is not possible for WDDM devices.
  • TCC reduces the latency of CUDA kernel launches.

TCC is enabled by default on most recent NVIDIA Tesla GPUs. To check which driver mode is in use and/or to switch driver modes, use the nvidia-smi tool
that is included with the NVIDIA Driver installation (see nvidia-smi
-h for details).

Note: Keep in mind that when TCC mode is enabled for a particular GPU, that GPU cannot be
used as a display device.
Note: NVIDIA GeForce GPUs do not support TCC mode.

2.5. Verify
the Installation

Before continuing, it is important to verify that the CUDA toolkit can find and communicate correctly with the CUDA-capable hardware. To do this, you need to compile and run some of the included sample programs.

2.5.1. Running
the Compiled 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 to:

Start > All Programs > Accessories > Command Prompt

CUDA Samples include 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 deviceQuery program located at

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v7.0\bin\win64\Release

This assumes that you used the default installation directory structure. If CUDA is installed and configured correctly, the output should look similar to Figure
1
.

Figure 1. Valid Results from deviceQuery CUDA Sample

The exact appearance and the output lines might be different on your system. The important outcomes are that a device was found, that the device(s) match what is installed in your system, and that the test passed.

If a CUDA-capable device and the CUDA Driver are installed but deviceQuery reports
that no CUDA-capable devices are present, ensure the deivce and driver are properly installed.

Running the bandwidthTest program,
located in the same directory as deviceQuery above,
ensures that the system and the CUDA-capable device are able to communicate correctly. The output should resemble Figure
2
.

Figure 2. Valid Results from bandwidthTest CUDA Sample

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-capable 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 Particles executable at

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v7.0\bin\win64\Release

3. Compiling CUDA Programs

The project files in the CUDA Samples have been designed to provide simple, one-click builds of the programs that include all source code. To build the Windows projects (for release or debug mode), use the provided *.sln solution
files for Microsoft Visual Studio 2010, 2012, or 2013. You can use either the solution files located in each of the examples directories in

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v7.0\<category>\<sample_name>

or the global solution files Samples*.sln located
in

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v7.0

CUDA Samples are organized according to <category>.
Each sample is organized into one of the following folders: (0_Simple, 1_Utilities, 2_Graphics, 3_Imaging, 4_Finance, 5_Simulations, 6_Advanced, 7_CUDALibraries).

3.1. Compiling
Sample Projects

The bandwidthTest project
is a good sample project to build and run. It is located in the NVIDIA
Corporation\CUDA Samples\v7.0\1_Utilities\bandwidthTest directory.

If you elected to use the default installation location, the output is placed in CUDA
Samples\v7.0\bin\win64\Release. Build the program using the appropriate solution file and run the executable. If all works correctly, the output should be similar to Figure
2
.

3.2. Sample
Projects

The sample projects come in two configurations: debug and release (where release contains no debugging information) and different Visual Studio projects.

A few of the example projects require some additional setup. The simpleD3D9 example
requires the system to have a Direct3D SDK (June 2010 or later) installed and the Visual C++ directory paths (located in Tools > Options...)
properly configured. Consult the Direct3D documentation for additional details.

These sample projects also make use of the $CUDA_PATH environment
variable to locate where the CUDA Toolkit and the associated .props files
are.

The environment variable is set automatically using the Build Customization CUDA 7.0.props file,
and is installed automatically as part of the CUDA Toolkit installation process.

For Visual Studio 2010, the CUDA 7.0.props file
is installed into:

C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\BuildCustomizations
For Visual Studio 2012, the CUDA 7.0.props file
is installed into:

C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V110\BuildCustomizations
For Visual Studio 2013, the CUDA 7.0.props file
is installed into:

C:\Program Files (x86)\MSBuild\Microsoft.Cpp\v4.0\V120\BuildCustomizations

You can reference this CUDA 7.0.props file
when building your own CUDA applications.

3.3. Build
Customizations for New Projects

When creating a new CUDA application, the Visual Studio project file must be configured to include CUDA build customizations. To accomplish this, click File-> New | Project... NVIDIA-> CUDA->, then select a template for your
CUDA Toolkit version. For example, selecting the "CUDA 7.0 Runtime" template will configure your project for use with the CUDA 7.0 Toolkit. The new project
is technically a C++ project (.vcxproj) that is preconfigured to use NVIDIA's Build Customizations. All standard capabilities of Visual Studio C++ projects will be available.

To specify a custom CUDA Toolkit location, under CUDA C/C++, select Common, and set the CUDA
Toolkit Custom Dir field as desired. Note that the selected toolkit must match the version of the Build Customizations.

3.4. Build
Customizations for Existing Projects

When adding CUDA acceleration to existing applications, the relevant Visual Studio project files must be updated to include CUDA build customizations. This can be done using one of the following two methods:

  1. Open the Visual Studio project, right click on the project name, and select Build Customizations..., then select the CUDA Toolkit version you would like to target.
  2. Alternatively, you can configure your project always to build with the most recently installed version of the CUDA Toolkit. First add a CUDA build customization to your project as above. Then, right click on the project name and select Properties.
    Under CUDA C/C++, select Common, and set the CUDA Toolkit Custom Dir field to $(CUDA_PATH) .
    Note that the $(CUDA_PATH) environment variable is
    set by the installer.

While Option 2 will allow your project to automatically use any new CUDA Toolkit version you may install in the future, selecting the toolkit version explicitly as in Option 1 is often better in practice, because if there
are new CUDA configuration options added to the build customization rules accompanying the newer toolkit, you would not see those new options using Option 2.

If you use the $(CUDA_PATH) environment
variable to target a version of the CUDA Toolkit for building, and you perform an installation or uninstallation of any version of the CUDA Toolkit, you should validate that the $(CUDA_PATH) environment
variable points to the correct installation directory of the CUDA Toolkit for your purposes. You can access the value of the $(CUDA_PATH) environment
variable via the following steps:

  1. Open a run window from the Start Menu
  2. Run:
    control sysdm.cpl
  3. Select the "Advanced" tab at the top of the window
  4. Click "Environment Variables" at the bottom of the window
Note for advanced users: If you wish to try building your project against a newer CUDA Toolkit without making changes to any of your project files, go to the Visual Studio
command prompt, change the current directory to the location of your project, and execute a command such as the following:

msbuild <projectname.extension> /t:Rebuild /p:CudaToolkitDir="drive:/path/to/new/toolkit/"

4. Additional Considerations

Now that you have CUDA-capable hardware and the NVIDIA CUDA Toolkit installed, you can examine and enjoy the numerous included programs. To begin using CUDA to accelerate the performance of your own applications, consult
the CUDA C Programming Guide, located in the CUDA Toolkit documentation directory.

A number of helpful development tools are included in the CUDA Toolkit or are available for download from the NVIDIA Developer Zone to assist you as you develop your CUDA programs, such as NVIDIA® Nsight™ Visual
Studio Edition, NVIDIA Visual Profiler, and cuda-memcheck.

For technical support on programming questions, consult and participate in the developer forums at http://developer.nvidia.com/cuda/.

以上英文内容转自:

http://docs.nvidia.com/cuda/cuda-getting-started-guide-for-microsoft-windows/index.html#axzz3W8BU10Ol

Windows平台CUDA开发之前的准备工作的更多相关文章

  1. [Flutter] Windows平台Flutter开发环境搭建(Andorid Studio)

    前两天网友在群里说起了Flutter,就了解了一下,在手机上跑了它的demo,直接就被打动了. 虽然网上有很多教程,但真正开始的时候,还是会碰到很多坑.下面详细的讲解Flutter + Android ...

  2. TQ2440 学习笔记—— 1、Windows平台下开发工具安装与环境建立

    板子:广州天嵌公司的TQ2440,处理器为三星的S3C2440 1.开发工具的安装与环境建立 系统:win7  64位 SecureCRT软件:该软件能够取代Windows中的超级终端,是个非常好的串 ...

  3. Windows平台开发Mapreduce程序远程调用运行在Hadoop集群—Yarn调度引擎异常

    共享原因:虽然用一篇博文写问题感觉有点奢侈,但是搜索百度,相关文章太少了,苦苦探寻日志才找到解决方案. 遇到问题:在windows平台上开发的mapreduce程序,运行迟迟没有结果. Mapredu ...

  4. Linux下编译静态MinGW环境,编译windows平台Qt程序(使用MXE)

    参考链接: MXE.>大多数程序都是在windows平台下开发的程序.windows 在现实中也是绕不过的一个系统平台,做为受过几年VC,MFC”虐待”的程序员,在做为一个程序员之前是一位Lin ...

  5. QT + OpenCV + MinGW 在windows下配置开发环境

           由于研究项目需要,最近开始接触C++界面设计,关于“QT + OpenCV + MinGW在windows下配置开发环境”着实让人头疼,单次配置时间相当长,也十分不容易,本人第一次配置成 ...

  6. Windows平台Python Pyramid实战从入门到进阶:第一个服务

    Pyramid是比较流行的Python Web 框架,比较灵活,功能也很强大.最近项目上用到,便打算学习一下.网上教程比较少,而且很多都是针对linux平台的,我是windows土著所以对那些linu ...

  7. windows平台CodeBlocks MinGW C++11开发环境搭建

    前言: 本文是以单独下载codeblock编辑器跟MinGW编译器这种方式进行安装,下载带MinGW编译器的codeblocks版本安装配置方式跟这个类似. 一: 下载并安装MinGW 这个参考我写的 ...

  8. Linux下开发Windows平台运行的程序 - MinGW

    开源不乏神人,于是有了MinGW(Minimalist GNU for Windows),又称mingw32,是将GCC编译器和GNU Binutils一直到Win32平台下,包含一系列头文件.库和可 ...

  9. cocos2d-x 2.1.4学习笔记01:windows平台搭建cocos2d-x开发环境

    cocos2d-x的大致开发流程是,首先使用win32版进行代码编写并完成游戏,然后将代码迁移到对应的开发环境上进行交叉编译完成游戏打包,如iphone上是mac+xcode,android是ecli ...

随机推荐

  1. 继承AbstractRoutingDataSource再通过AOP实现动态数据源切换(转)

    关于AbstractRoutingDataSource我在研究开源中国的开源项目时候才发现,好奇的看了一下代码发现自己看不明白,大概就看懂了Spring AOP切面这里,根据注释作者的意思是通过这个可 ...

  2. js34

    <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/stri ...

  3. 【例题 8-1 UVA 120 】Stacks of Flapjacks

    [链接] 我是链接,点我呀:) [题意] 在这里输入题意 [题解] 从大到小安排. 显然想让第i大的数字归位 只要让他翻到最上面,然后再翻回来就ok了 即operate(pos[i]) -> o ...

  4. 【AIM Tech Round 4 (Div. 2) B】Rectangles

    [链接]http://codeforces.com/contest/844/problem/B [题意] 也是道计数水题,没什么记录意义 [题解] 枚举每个点的位置在,然后往右往下 枚举和它一样颜色的 ...

  5. [Angular] Use :host-context and the ::ng-deep selector to apply context-based styling

    If you want to style host component. You can use ':host-context'. // host @Component({ selector: 'my ...

  6. 不是IT圈人的IT创业优劣势!

    不是IT圈人的IT创业优势: 1)更尊重市场导向而非技术   2)更关注产品细节而非技术  3)更关注企业平衡而非技术 不是IT圈人的IT创业劣势: 1)因营销而放弃技术规划   2)因需求而丧失技术 ...

  7. 第一个使用Spring Tool Suite(STS)和Maven建立的Spring mvc 项目

    一.目标 在这篇文章中.我将要向您展示怎样使用Spring Frameworks 和 Maven build创建您的第一个J2ee 应用程序. 二.信息 Maven是一个java项目的构建工具(或者自 ...

  8. android对话框(Dialog)的使用方法

    Activities提供了一种方便管理的创建.保存.回复的对话框机制.比如 onCreateDialog(int), onPrepareDialog(int, Dialog), showDialog( ...

  9. 网页设计实战3 ufo类型的科技网页如何实现

    网页设计实战3 ufo类型的科技网页如何实现 一.总结 一句话总结:基础的图片素材就是如何几张图片,这个效果只是通过jquery或者js让那个png图片旋转起来了,如此而已.其实核心就是一个trans ...

  10. [selenium]选取下拉框内容的方法

    说明:本文章主要是对select元素操作的讲解,非select元素的下拉框需要另外分析 1.select元素示例: 2.select下拉框选取的3种方法 WebElement selector = d ...