Debugging CUDA - CudaUnknownError

我正在尝试使用CUDA创建mandlebrot集的位图图像。我看了一些教程，已经在这里获得了一些关于将非托管CUDAdll与托管C#gui集成的过程的帮助。我现在遇到的问题是我的CUDA dll没有正确形成位图，当我在内核启动后在cudaDeviceSynchronize（）上使用错误检查宏时，我会得到cudaUnknowError。

以下是相关代码：

#define gpuErrchk(ans) { gpuAssert((ans), __FILE__, __LINE__); }
inline void gpuAssert(cudaError_t code, char *file, int line, bool abort=true)
{
   if (code != cudaSuccess) 
   {
      fprintf(stderr,"GPUassert: %s %s %dn", cudaGetErrorString(code), file, line);
      if (abort) exit(code);
   }
}

struct complex
{
    float r, i;
    __device__ complex(float _r, float _i) : r(_r), i(_i) {}
    __device__ float magnitudeSquared(){ return (r*r + i*i) ; }
    __device__ complex& operator*=(const complex& rhs)
    {
        r = (r * rhs.r - i * rhs.i);
        i = (r * rhs.i + i * rhs.r);
        return *this;
    }
    __device__ complex& operator+=(const complex& rhs)
    {
        r = (r + rhs.r);
        i = (i + rhs.i);
        return *this;
    }
};
__device__ int mandlebrotDiverge(complex *z)
{
    complex c(*z);
    int i = 0;
    for(i = 0; i < MAX_ITERATIONS; i++)
    {
        *z *= *z;
        *z += c;
        if(z->magnitudeSquared() >= 2)
        {
            return 1;
        }
    }
    return 0;
}
__global__ void kernel(int *ptr, int width, int height)
{
    int x = threadIdx.x + blockIdx.x * blockDim.x;
    int y = threadIdx.y + blockIdx.y * blockDim.y;
    int offset = x + y * blockDim.x * gridDim.x;
    float scale = 1.5f;
    complex z(scale*(float)(width/2 - x)/(width/2), scale*(float)(height/2 - y)/(height/2));
    if(offset < (1920*1080))
    {
        int mValue = mandlebrotDiverge(&z);
        ptr[offset*3 + (uint8_t)0] = (uint8_t)(mValue*255);
        ptr[offset*3 + (uint8_t)1] = (uint8_t)(mValue*255);
        ptr[offset*3 + (uint8_t)2] = (uint8_t)(mValue*255);
    }
}


extern "C" __declspec(dllexport) void __cdecl generateBitmap(void *bitmap)
{
    int width = 1920;
    int height = 1080;
    int *dev_bmp;
    dim3 blocks(width/16, height/16);
    dim3 threads(16, 16);
    gpuErrchk(cudaMalloc((void**)&dev_bmp, (3*width*height)));
    kernel<<<blocks, threads>>>(dev_bmp, width, height);
    gpuErrchk(cudaPeekAtLastError());
    gpuErrchk(cudaDeviceSynchronize());
    gpuErrchk(cudaMemcpy(bitmap, dev_bmp, (width*height*3), cudaMemcpyDeviceToHost));
    cudaFree(dev_bmp);
}

当我逐步完成代码时，一切似乎都正常工作，直到我到达gpuErrchk（cudaDeviceSynchronize（））；-当我进入时，错误代码只是简单地说"cudaUnknowError"。我不知道我在这一点上做错了什么。如有任何关于如何改进此解决方案的帮助或建议，我们将不胜感激。

编辑：

好吧，看看CUDA_memcheck，我得到了这个错误（数百次）：

========= CUDA-MEMCHECK
========= Invalid __global__ write of size 4
=========     at 0x00000a10 in C:/.../kernel.cu:77:kernel(int*, int, int)
=========     by thread (15,11,0) in block (1,17,0)
=========     Address 0x05a37f74 is out of bounds
=========     Saved host backtrace up to driver entry point at kernel launch time

所以我从*int改为*unsigned char，因为我试图分配单个字节的数组，而不是int。很多错误都被清除了，但现在我得到了这个：

========= CUDA-MEMCHECK
========= Program hit error 6 on CUDA API call to cudaDeviceSynchronize 
=========     Saved host backtrace up to driver entry point at error
=========     Host Frame:C:Windowssystem32nvcuda.dll (cuD3D11CtxCreate + 0x102459) [0x11e4b9]
=========     Host Frame:C:...cudart32_55.dll (cudaDeviceSynchronize + 0xdd) [0x1149d]
=========     Host Frame:C:...FractalMaxUnmanaged.dll (generateBitmap + 0xf0) [0x97c0]
=========
========= ERROR SUMMARY: 1 error

好吧，我正在取得进展，但现在当我遍历c#应用程序时，字节缓冲区中每个字节的值都是255，这没有意义。这是c#代码：

public unsafe class NativeMethods
{
    [DllImport(@"C:UsersBillDocumentsVisual Studio 2012ProjectsFractalMaxUnmanagedDebugFractalMaxUnmanaged.dll", CallingConvention=CallingConvention.Cdecl)]
    public static extern void generateBitmap(void *bitmap);
    public static Bitmap create()
    {
        byte[] buf = new byte[1920 * 1080 * 3];
        fixed (void* pBuffer = buf)
        {
            generateBitmap(pBuffer);
        }
        IntPtr unmanagedPtr = Marshal.AllocHGlobal(buf.Length);
        Marshal.Copy(buf, 0, unmanagedPtr, buf.Length);
        Bitmap img = new Bitmap(1920, 1080, 1920*3, PixelFormat.Format24bppRgb, unmanagedPtr);
        Marshal.FreeHGlobal(unmanagedPtr);
        return img;
    }
}