Really simple example not working

Accelerated Computing CUDA CUDA Programming and Performance
1

** figured it out, see below **

Does anyone know why the following function works in CPU emulation mode, but not on my GPU? I’m running an GeForce 8800 GT. When I run the code in emulation mode, it correctly sets each pixel in the image to blue. The GPU blacks out the entire image. There is an error string returned: “invalid device function” – and if I comment out the entire body of GPUIdentity (below), it still throws this error! I’m a total CUDA noob but an experienced C++ developer, and I feel like I’m probably missing something really simple. Thanks in advance!

[codebox]#if __DEVICE_EMULATION__ 
bool InitCUDA(){return true;}

#else

bool InitCUDA()

{

	int count = 0;

	int i = 0;

	cudaGetDeviceCount(&count);

	if(count == 0) {

		fprintf(stderr, "There is no device.\n");

		return false;

	}

	for(i = 0; i < count; i++) {

		cudaDeviceProp prop;

		if(cudaGetDeviceProperties(&prop, i) == cudaSuccess) {

			if(prop.major >= 1) {

				break;

			}

		}

	}

	if(i == count) {

		fprintf(stderr, "There is no device supporting CUDA.\n");

		return false;

	}

	cudaSetDevice(i);

	printf("CUDA initialized.\n");

	return true;

}

#endif

[/codebox]

2

Fixed it - using the VS CUDA add-in, I needed to set Project properties → Configuration properties → CUDA → Output → Intern Mode = Real.