How access GpuMat in a kernel

edit

Hello,

I'm quite new in cuda programming, and I need to write my own kernel. However, most of the things are clear to me, except one. The folloing sentence is written in the docu: The GpuMat class is convertible to gpu::DevMem2D_ and gpu::PtrStep_ so it can be passed directly to the kernel. I'm asking now myself how to access the buffers within a kernel, specially if I would like to use a struct to store my buffers. Here some PsydoCode:

struct GpuBuffer{
    GpuMat InBuffer1;
    GpuMat InBuffer2;
    GpuMat InBuffer3;
    GpuMat OutBuffer;
};

int main (void)
{
    GpuBuffer d_buffer;
    InitGPUBuffer (d_buffer);
    callKernel(d_buffer);
    return 0;
}

void InitGPUBuffer(GpuBuffer &d_buffer)
{
    Mat QuadFloatArr = Mat.zeros(Size(640, 480), CV_32FC4);
    d_buffer.InBuffer1.upload(QuadFloatArr);
    d_buffer.InBuffer2.upload(QuadFloatArr);
    d_buffer.InBuffer3.upload(QuadFloatArr);
    d_buffer.OutBuffer.upload(QuadFloatArr);
}

void callKernel(GpuBuffer& d_buffer)
{
    Cuda_KernelCall(d_buffer);
}

//cu-file
extern "C" bool Cuda_KernelCall(GpuBuffer& Buffer)
{
    dim3 threads(16,16);    
    dim3 grid((Buffer.InBuffer1.cols/2)/(threads.x), (Buffer.InBuffer1.rows/2)/(threads.y));  

    Kernel<<<treads, grid>>>(Buffer);

    return true;
}

__global__ void Kernel( GpuBuffer Buffer )
{
  int x = (blockIdx.x * blockDim.x) + threadIdx.x;
  int y = (blockIdx.y * blockDim.y) + threadIdx.y;

    // how to access the several buffer that are stored in the struct?
}

Thank you very much in advance.

cheers greg