CUDA: cudaMemcpy only works in emulation mode

I am just starting to learn how to use CUDA. I am trying to run some simple example code:

float *ah, *bh, *ad, *bd;
ah = (float *)malloc(sizeof(float)*4);
bh = (float *)malloc(sizeof(float)*4);
cudaMalloc((void **) &ad, sizeof(float)*4);
cudaMalloc((void **)开发者_如何学C &bd, sizeof(float)*4);
... initialize ah ...

/* copy array on device */
cudaMemcpy(ad,ah,sizeof(float)*N,cudaMemcpyHostToDevice);
cudaMemcpy(bd,ad,sizeof(float)*N,cudaMemcpyDeviceToDevice);
cudaMemcpy(bh,bd,sizeof(float)*N,cudaMemcpyDeviceToHost);

When I run in emulation mode (nvcc -deviceemu) it runs fine (and actually copies the array). But when I run it in regular mode, it runs w/o error, but never copies the data. It's as if the cudaMemcpy lines are just ignored.

What am I doing wrong?

Thank you very much, Jason

You should check for errors, ideally on each malloc and memcpy but just doing it once at the end will be sufficient (cudaGetErrorString(cudaGetLastError()).

Just to check the obvious:

• You do have a CUDA capable GPU, right? Run the deviceQuery SDK sample to check the device is working correctly and all the drivers are installed and working.
• N (in the memcpy) is equal to 4 (in the malloc), right?

See if you have a CUDA enabled device. Probably you can try running the code below and see what info you get:

#include <cstdio>

int main( void ) {
    cudaDeviceProp  prop;

    int count;
    cudaGetDeviceCount( &count );
    for (int i=0; i< count; i++) {
        cudaGetDeviceProperties( &prop, i );
        printf( "   --- General Information for device %d ---\n", i );
        printf( "Name:  %s\n", prop.name );
        printf( "Compute capability:  %d.%d\n", prop.major, prop.minor );
        printf( "Clock rate:  %d\n", prop.clockRate );
        printf( "Device copy overlap:  " );
        if (prop.deviceOverlap)
            printf( "Enabled\n" );
        else
            printf( "Disabled\n");
        printf( "Kernel execution timeout :  " );
        if (prop.kernelExecTimeoutEnabled)
            printf( "Enabled\n" );
        else
            printf( "Disabled\n" );

        printf( "   --- Memory Information for device %d ---\n", i );
        printf( "Total global mem:  %ld\n", prop.totalGlobalMem );
        printf( "Total constant Mem:  %ld\n", prop.totalConstMem );
        printf( "Max mem pitch:  %ld\n", prop.memPitch );
        printf( "Texture Alignment:  %ld\n", prop.textureAlignment );

        printf( "   --- MP Information for device %d ---\n", i );
        printf( "Multiprocessor count:  %d\n",
                    prop.multiProcessorCount );
        printf( "Shared mem per mp:  %ld\n", prop.sharedMemPerBlock );
        printf( "Registers per mp:  %d\n", prop.regsPerBlock );
        printf( "Threads in warp:  %d\n", prop.warpSize );
        printf( "Max threads per block:  %d\n",
                    prop.maxThreadsPerBlock );
        printf( "Max thread dimensions:  (%d, %d, %d)\n",
                    prop.maxThreadsDim[0], prop.maxThreadsDim[1],
                    prop.maxThreadsDim[2] );
        printf( "Max grid dimensions:  (%d, %d, %d)\n",
                    prop.maxGridSize[0], prop.maxGridSize[1],
                    prop.maxGridSize[2] );
        printf( "\n" );
    }
}