Setting up my environment

Hello! I’m new to CUDA programming, and am in the process of setting up my computer to edit, compile and run CUDA C codes. MY OS is Windows 7, and I’m using VS 2008 as my IDE. A few days ago I downloaded and installed the latest driver for my GPU (GeForce 9400M G) as well as the CUDA toolkit and the SDK, all from NVIDIA website. Everything seemed to be working: I can run the bandwidthTest and Particles application from my SDK folders.

However, when I open the source code for bandwidthTest, I cannot run it in debug mode, and I get the following error:

Error 1 fatal error LNK1181: cannot open input file ‘cutil32D.lib’

Also, when I create a blank project, I don’t seem to be able to build and run the project. I think there is some issue with my configuration settings, but I’m not sure. By the way, I do change the configuration settings in VS from C++ to C, and change the file extension from .cpp to .cu. I can build the project with a .c extension (no device code or reference), but changing it to .cu causes the problem.

Any help or suggestions would be appreciated!

Thank you,
Ali

Right click on the project in the solution explorer window, choose properties and see what Nvidia had written, and then copy and paste to your own project.
Do the same with your *.cu files. And try to rebuilt your project again.
Good luck. :yes:

Right click on the project in the solution explorer window, choose properties and see what Nvidia had written, and then copy and paste to your own project.
Do the same with your *.cu files. And try to rebuilt your project again.
Good luck. :yes:

I’m not sure if I follow. Are you suggesting that I open one of the projects from the SDK folders and copy the properties to my own project? The problem is, I can’t build the SDK projects either!

I think I need to define the following environment variables, but not sure how to: CUDA_BIN_PATH, CUDA_INC_PATH, CUDA_LIB_PATH. I’m referring to the instructions provided by a pdf file called GettingStartedWindows from NVIDIA website.

Thank you for your help!

I’m not sure if I follow. Are you suggesting that I open one of the projects from the SDK folders and copy the properties to my own project? The problem is, I can’t build the SDK projects either!

I think I need to define the following environment variables, but not sure how to: CUDA_BIN_PATH, CUDA_INC_PATH, CUDA_LIB_PATH. I’m referring to the instructions provided by a pdf file called GettingStartedWindows from NVIDIA website.

Thank you for your help!