Passing structs to CUDA kernels

Question

I\'m new to CUDA C, and am trying to pass a typedef\'d struct into a kernel. My method worked fine when I tried it with a struct containing only ints, but when I switch to float

Answer 1

Since there doesn't appear to be any decent documentation on how to do this, I thought I'd post the final, revised code here. It turns out that the __align__ part was unnecessary as well, the actual problem was the use of %d in the printf when trying to print floats.

#include 
#include 

typedef struct
{
    float a, b;
} point;

__global__ void testKernel(point *p)
{
    int i = blockIdx.x * blockDim.x + threadIdx.x;
    p[i].a = 1.1;
    p[i].b = 2.2;
}

int main(void)
{
        // set number of points 
    int numPoints    = 16,
        gpuBlockSize = 4,
        pointSize    = sizeof(point),
        numBytes     = numPoints * pointSize,
        gpuGridSize  = numPoints / gpuBlockSize;

        // allocate memory
    point *cpuPointArray,
          *gpuPointArray;
    cpuPointArray = (point*)malloc(numBytes);
    cudaMalloc((void**)&gpuPointArray, numBytes);

        // launch kernel
    testKernel<<>>(gpuPointArray);

        // retrieve the results
    cudaMemcpy(cpuPointArray, gpuPointArray, numBytes, cudaMemcpyDeviceToHost);
    printf("testKernel results:\n");
    for(int i = 0; i < numPoints; ++i)
    {
        printf("point.a: %f, point.b: %f\n",cpuPointArray[i].a,cpuPointArray[i].b);
    }

        // deallocate memory
    free(cpuPointArray);
    cudaFree(gpuPointArray);

    return 0;
}