struct - 将结构传递到CUDA内核

Question

我是CUDA C的新手，正在尝试将类型定义的结构传递到内核中。当我使用仅包含int的结构尝试此方法时，我的方法运行良好，但是当我切换到float时，返回无意义的数字作为结果。我认为这与对齐有关，我尝试在我的类型声明中包含__align__，但无济于事。有人可以给我一个例子，还是提供替代方法？我正在尝试对其进行设置，以便可以轻松添加或删除字段，而无需更改结构和内核以外的任何内容。我的代码：

typedef struct __align__(8)
{
    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 = new point[numPoints],
          *gpuPointArray = new point[numPoints];
    cpuPointArray = (point*)malloc(numBytes);
    cudaMalloc((void**)&gpuPointArray, numBytes);

        // launch kernel
    testKernel<<<gpuGridSize,gpuBlockSize>>>(gpuPointArray);

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

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

    return 0;
}

Answer 1

由于似乎没有任何有关此操作的不错的文档，因此我认为我将在此处发布最终的，经过修订的代码。事实证明，__align__部分也是不必要的，实际问题是在尝试打印浮点数时在printf中使用了％d。

#include <stdlib.h>
#include <stdio.h>

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<<<gpuGridSize,gpuBlockSize>>>(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;
}