Question

好的，到目前为止，我可以在主机上创建一个数组（float类型），并将其复制到gpu，然后将其作为另一个数组返回到主机（通过比较来测试副本是否成功）到原来的）。

然后我从GPU上的阵列创建一个CUDA数组。然后我将该数组绑定到CUDA纹理。

我现在想要读回纹理并与原始数组进行比较（再次测试它是否正确复制）。我看到了一些使用下面显示的readTexel()函数的示例代码。它似乎对我没有用...（基本上一切都有效，除了从bindToTexture(float* deviceArray)行开始的readTexels(SIZE, testArrayDevice)函数中的部分。）

有任何不同方法的建议吗？或者我的代码中遗漏了一些明显的问题？

感谢帮助人员！

#include <stdio.h>
#include <assert.h>
#include <cuda.h>

#define SIZE 20;

//Create a channel description to use.
cudaChannelFormatDesc channelDesc = cudaCreateChannelDesc(32, 0, 0, 0, cudaChannelFormatKindFloat);

//Create a texture to use.
texture<float, 2, cudaReadModeElementType> cudaTexture;
//cudaTexture.filterMode = cudaFilterModeLinear;
//cudaTexture.normalized = false;

__global__ void readTexels(int amount, float *Array)
{
  int index = blockIdx.x * blockDim.x + threadIdx.x;

  if (index < amount)
  {
    float x = tex1D(cudaTexture, float(index));
    Array[index] = x;
  }
}

float* copyToGPU(float* hostArray, int size)
{
  //Create pointers, one for the array to be on the device, and one for bringing it back to the host for testing.
  float* deviceArray;
  float* testArray;

  //Allocate some memory for the two arrays so they don't get overwritten.
  testArray = (float *)malloc(sizeof(float)*size);

  //Allocate some memory for the array to be put onto the GPU device.
  cudaMalloc((void **)&deviceArray, sizeof(float)*size);

  //Actually copy the array from hostArray to deviceArray.
  cudaMemcpy(deviceArray, hostArray, sizeof(float)*size, cudaMemcpyHostToDevice);

  //Copy the deviceArray back to testArray in host memory for testing.
  cudaMemcpy(testArray, deviceArray, sizeof(float)*size, cudaMemcpyDeviceToHost);

  //Make sure contents of testArray match the original contents in hostArray.
  for (int i = 0; i < size; i++)
  {
    if (hostArray[i] != testArray[i])
    {
      printf("Location [%d] does not match in hostArray and testArray.\n", i);
    }
  }

  //Don't forget free these arrays after you're done!
  free(testArray);

  return deviceArray; //TODO: FREE THE DEVICE ARRAY VIA cudaFree(deviceArray);
}

cudaArray* bindToTexture(float* deviceArray)
{
  //Create a CUDA array to translate deviceArray into.
  cudaArray* cuArray;

  //Allocate memory for the CUDA array.
  cudaMallocArray(&cuArray, &cudaTexture.channelDesc, SIZE, 1);

  //Copy the deviceArray into the CUDA array.
  cudaMemcpyToArray(cuArray, 0, 0, deviceArray, sizeof(float)*SIZE, cudaMemcpyHostToDevice);

  //Release the deviceArray
  cudaFree(deviceArray);

  //Bind the CUDA array to the texture.
  cudaBindTextureToArray(cudaTexture, cuArray);

  //Make a test array on the device and on the host to verify that the texture has been saved correctly.
  float* testArrayDevice;
  float* testArrayHost;

  //Allocate memory for the two test arrays.
  cudaMalloc((void **)&testArray, sizeof(float)*SIZE);
  testArrayHost = (float *)malloc(sizeof(float)*SIZE);

  //Read the texels of the texture to the test array in the device.
  readTexels(SIZE, testArrayDevice);

  //Copy the device test array to the host test array.
  cudaMemcpy(testArrayHost, testArrayDevice, sizeof(float)*SIZE, cudaMemcpyDeviceToHost);

  //Print contents of the array out.
  for (int i = 0; i < SIZE; i++)
  {
    printf("%f\n", testArrayHost[i]);
  }

  //Free the memory for the test arrays.
  free(testArrayHost);
  cudaFree(testArrayDevice);

  return cuArray; //TODO: UNBIND THE CUDA TEXTURE VIA cudaUnbindTexture(cudaTexture);
  //TODO: FREE THE CUDA ARRAY VIA cudaFree(cuArray);
}


int main(void)
{
  float* hostArray;

  hostArray = (float *)malloc(sizeof(float)*SIZE);

  for (int i = 0; i < SIZE; i++)
  {
    hostArray[i] = 10.f + i;
  }

  float* deviceAddy = copyToGPU(hostArray, SIZE);

  free(hostArray);

  return 0;
}

Answer 1

简言之：

-------------在你的main.cu ----------------------------- -------------------------------------------------- --------

-1。将纹理定义为全局变量


       texture refTexture; // global variable !
       // meaning: address the texture with (x,y) (2D) and get an unsinged int

在主要功能中：

-2。使用与纹理结合的数组

    cudaArray* myArray; // declar.
    // ask for memory
    cudaMallocArray (   &myArray,

                        &refTex.channelDesc, /* with this you don't need to fill a channel descriptor */
                        width,

                        height);

-3。将数据从CPU复制到GPU（到阵列）

 cudaMemcpyToArray ( arrayCudaEntrada, // destination: the array

                        0, 0, // offsets 
                        sourceData, // pointer uint*
                        widthheightsizeof(uint), // total amount of bytes to be copied 
                        cudaMemcpyHostToDevice);

-4。绑定纹理和数组

    cudaBindTextureToArray( refTex,arrayCudaEntrada)

-5。更改纹理中的一些参数



   refTextura_In.normalized = false; // don't automatically convert fetched data to [0,1[
      refTextura_In.addressMode[0] = cudaAddressModeClamp;  // if my indexing is out of bounds: automatically use a valid indexing (0 if negative index, last if too great index)
      refTextura_In.addressMode[1] = cudaAddressModeClamp;

----------在内核中---------------------------------- ----------------------

    // find out indexes (f,c) to process by this thread
     uint f = (blockIdx.x * blockDim.x) + threadIdx.x;
     uint c = (blockIdx.y * blockDim.y) + threadIdx.y;

  // this is curious and necessary: indexes for reading from a texture
  // are floats !. Even if you are certain to access (4,5) you have
  // match the "center" this is (4.5, 5.5)
  uint read = tex2D( refTex, c+0.5f, f+0.5f); // texRef is a global variable


  // this is curious and necessary: indexes for reading from a texture
  // are floats !. Even if you are certain to access (4,5) you have
  // match the "center" this is (4.5, 5.5)
  uint read = tex2D( refTex, c+0.5f, f+0.5f); // texRef is a global variable

现在您处理读取结果并将结果写入设备全局的其他区域记忆，而不是纹理本身！

Answer 2

readTexels()是一个内核（__global__）函数，即它在GPU上运行。因此，您需要使用正确的语法来启动内核。

通过NVIDIA CUDA site查看CUDA编程指南和一些SDK示例，了解如何启动内核。

提示：它最终会像readTexels<<<grid,block>>>(...)

那样

如何读回CUDA纹理进行测试？

2 个答案: