Hello readers (maybe it’s only me… whatever)…
I have been attending a course named “Programming Massively Parallel Processors”, these days. I have learned many things about this Framework but still I need to actually “run” my first program.
In this post I will write the steps I am following to run my first CUDA program.
Steps:
- Download and install the CUDA Version 3.2.16 64 bits.
- Download and install the CUDA GPU Computing SDK Samples Version 3.2.16 64 bits.
- Download and install the CUDA Developer Driver for Windows 7, version 3.2.
After this, I launched my Visual Studio 2005, and opened the Visual Studio Sample Code located at :
C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 3.2\C\src\deviceQuery\deviceQuery.sln
I tried to run it with Debug and Win32 options, and Bang!! I got the following error when linking:
1>LINK : fatal error LNK1181: cannot open input file 'cutil32D.lib'
Fortunately, a good Samaritan wrote the following to solve the problem: “… Go to the SDK install directory, then into the “C” directory. You’ll see a “common” directory, in there open the cutil.sln solution (or cutil_vc90.sln for VS2008) and build it in release and debug modes for your platform….
The cutil library is used to avoid replicating the same code through all the samples, if you’re starting your own project I’d avoid reusing the cutil library and write your own checker. For example, you should probably fail gracefully if you detect a CUDA error rather than just calling exit() as done in cutil…..” Tom (StackOverflow.com contributor…
Of course I should read the Manual, but I like to get things running asap… and later… more calmed.. read the Manual…. :-p …..
Anyway, I followed the steps mentioned there…..Compiled the CUTIL library and compile again and Bang Bang !!! The following error appeared:
fatal error LNK1181: cannot open input file 'shrUtils32D.lib'
But since right know I am more knowledgeable in the subject (Did I write OK kNOWLEDGEABLE?) I know that I should compile the shrUtils32D.lib, which I found here: SDK\OpenCL\common\oclUtils.sln
I built this solution and recompile my initial deviceQuery.sln (C:\ProgramData\NVIDIA Corporation\NVIDIA GPU Computing SDK 3.2\C\src\deviceQuery\deviceQuery.sln
And…….. guess what ……..It raaaaaaaaaaaan!!!!! See the output:
deviceQuery.cpp output
Now I am ready to rock and roll !!!!!