目前在 Windows 中编码 CUDA 的更好方法无疑是 Nsight Visual Studio Edition 环境。随着 CUDA 5 的发布，还推出了 Nvidia Nsight Eclipse 版本，具有相同的编程功能，但使用 Eclipse 的 IDE。 Nsight Eclipse 版本可在 Linux 和 MacOS 上使用（但不可在 Windows 上使用）。您可以使用 CUDA 5 候选版本 进行尝试：http:// developer.nvidia.com/cuda/cuda-toolkit
Definitely the better way to code CUDA in Windows right now is Nsight Visual Studio Edition environment. With the release of CUDA 5, comes also the Nvidia Nsight Eclipse Edition, with the same programming capabilities but with the IDE of Eclipse. Nsight Eclipse Edition is available on Linux and MacOS (but not Windows). You can try it already with the CUDA 5 release candidate : http://developer.nvidia.com/cuda/cuda-toolkit
I've used CUDA 2.1, and VS2008, and haven't had any problems. Just make sure after you install the toolkit and the SDK, that you do the following:
Open "My Computer" (or explorer, or whatever) and navigate to C:\ProgramData\NVIDIA Corporation\NVIDIA CUDA SDK\common
Double-click on cutil_vc90.sln (assuming you're using CUDA 2.1 and VS2008); when the solution loads up, you will see a drop-down menu for the build configuration. If you are on a 64-bit platform, you need to change this from Win32 to x64.
Build the solution.
Look up top again -- you should see the build configuration menu that says "Debug". Change it to "Release" and build the solution again.
Close Visual Studio.
Back in the explorer window, find the file "paramgl_vc90.sln". Double-click it to open that solution.
Repeat the same configuration setup and build process as described above, then close Visual Studio.
At this point, you should be able to compile the SDK projects; if you are using VS2008, make sure you open the solutions ending in _vc90.sln. Again, if you're on x64, you need to also make sure to set the build platform to "x64" in that drop-down menu.
If you get this far, and you're ready to write your own projects, check out the "template" project that comes with the SDK. You should be able to make a copy of that and use it for your own stuff, with the compiler settings (for CUDA, that is) already set up.
在 Windows 中，您可以使用 NVIDIA Parallel Nsight Visual Studio 解决方案。我认为在 Windows 上进行 GPU 开发没有更好的选择。以及Linux + GPU 开发== SUX。 有人尝试制作一些用于 GPU 开发的 Linux 发行版友好，但考虑到这些只是实现这一目标的第一步 - 我对这个产品的期望并不高。 （他们也有损坏的链接）
In windows you can use NVIDIA Parallel Nsight Visual Studio solution. I think there is no better alternative for GPU development on windows. And Linux + GPU development == SUX. There are some attempts to make some Linux distro which would be GPU-development friendly, but given that these are first steps to this goal - I don't expect too much from this product. (Also they have broken links)
Under my Win7 I use MSVS 10 with NVidia debugger and Parallel Nsight integrated. I have cross-platform build with cmake. It's so easy with cmake. Under Linux (I use Fedora 16) I work in QT creator because it integrates well with cmake and debugger (and looks better than other IMXO). Inder Linux you can attach NVidia debugger, too.
发布评论
评论（4）
目前在 Windows 中编码 CUDA 的更好方法无疑是 Nsight Visual Studio Edition 环境。随着 CUDA 5 的发布，还推出了 Nvidia Nsight Eclipse 版本，具有相同的编程功能，但使用 Eclipse 的 IDE。 Nsight Eclipse 版本可在 Linux 和 MacOS 上使用（但不可在 Windows 上使用）。您可以使用 CUDA 5 候选版本 进行尝试：http:// developer.nvidia.com/cuda/cuda-toolkit
Definitely the better way to code CUDA in Windows right now is Nsight Visual Studio Edition environment. With the release of CUDA 5, comes also the Nvidia Nsight Eclipse Edition, with the same programming capabilities but with the IDE of Eclipse. Nsight Eclipse Edition is available on Linux and MacOS (but not Windows). You can try it already with the CUDA 5 release candidate : http://developer.nvidia.com/cuda/cuda-toolkit
我用过CUDA 2.1和VS2008，没有遇到任何问题。只需确保安装工具包和 SDK 后执行以下操作：
至此，您应该可以编译SDK项目了；如果您使用的是 VS2008，请确保打开以 _vc90.sln 结尾的解决方案。同样，如果您使用的是 x64，则还需要确保在该下拉菜单中将构建平台设置为“x64”。
如果您已经完成了这一步，并且您已准备好编写自己的项目，请查看 SDK 附带的“模板”项目。您应该能够复制它并将其用于您自己的东西，并且已经设置了编译器设置（即针对 CUDA）。
nvidia 上也有一个线程 http://forums.nvidia.com/index .php?showtopic=91057
I've used CUDA 2.1, and VS2008, and haven't had any problems. Just make sure after you install the toolkit and the SDK, that you do the following:
At this point, you should be able to compile the SDK projects; if you are using VS2008, make sure you open the solutions ending in _vc90.sln. Again, if you're on x64, you need to also make sure to set the build platform to "x64" in that drop-down menu.
If you get this far, and you're ready to write your own projects, check out the "template" project that comes with the SDK. You should be able to make a copy of that and use it for your own stuff, with the compiler settings (for CUDA, that is) already set up.
there is a thread on nvidia for this as well http://forums.nvidia.com/index.php?showtopic=91057
在 Windows 中，您可以使用 NVIDIA Parallel Nsight Visual Studio 解决方案。我认为在 Windows 上进行 GPU 开发没有更好的选择。以及
Linux + GPU 开发== SUX。有人尝试制作一些用于 GPU 开发的 Linux 发行版友好，但考虑到这些只是实现这一目标的第一步 - 我对这个产品的期望并不高。 （他们也有损坏的链接）
In windows you can use NVIDIA Parallel Nsight Visual Studio solution. I think there is no better alternative for GPU development on windows. And
Linux + GPU development == SUX.There are some attempts to make some Linux distro which would be GPU-development friendly, but given that these are first steps to this goal - I don't expect too much from this product. (Also they have broken links)
在我的 Win7 下，我使用带有 NVidia 调试器和集成的 Parallel Nsight 的 MSVS 10。我使用 cmake 进行跨平台构建。用cmake就这么简单。在 Linux 下（我使用 Fedora 16），我在 QT Creator 中工作，因为它与 cmake 和调试器集成良好（并且看起来比其他 IMXO 更好）。在 Linux 下，您也可以附加 NVidia 调试器。
Under my Win7 I use MSVS 10 with NVidia debugger and Parallel Nsight integrated. I have cross-platform build with cmake. It's so easy with cmake. Under Linux (I use Fedora 16) I work in QT creator because it integrates well with cmake and debugger (and looks better than other IMXO). Inder Linux you can attach NVidia debugger, too.