Driver API and Runtime API interoperability

[srhines]

Unfortunately, this is not true, at least on Mac OS X 10.6 using the CUDA 3.0 Beta drivers and toolkit.

[codebox]include <cuda.h>

include <cutil.h>

global void incr(int* vector, int length) {

int globalIndex = blockIdx.x * blockDim.x + threadIdx.x;

if (globalIndex < length) {

vector[globalIndex] = vector[globalIndex] + 1;

}

}

int main(void)

{

int length = 1000;

CUdeviceptr driverPtr;

cuMemAlloc(&driverPtr, sizeof(int) * length);

int* hostPtr = (int*)malloc(sizeof(int) * length);

for(int i = 0; i < length; i++) {

hostPtr[i] = i;

}

cuMemcpyHtoD(driverPtr, hostPtr, sizeof(int) * length);

/*** ILL FATED CAST ***/

int* runtimePtr = (int*)driverPtr;

/**************************/

int blocks = (length - 1)/256 + 1;

incr<<<blocks, 256>>>(runtimePtr, length);

CUDA_SAFE_THREAD_SYNC();

return 0;

}[/codebox]

Yields an error:

Cuda error in file ‘driver.cu’ in line 29 : unspecified launch failure.

Does it work on another platform with CUDA 3.0 Beta?

You are not checking error codes or you would see that you have not properly initialized the driver (cuInit, cuCtxCreate, …). If you start with a cudaFree(0) or similar runtime call that creates a context, your app will work properly. If you just start out with cuMemAlloc (and no error checking), you are going to get CUDA_ERROR_NOT_INITIALIZED for all subsequent calls.