我是CUDA C的新手,正在尝试将一个typedef的结构体传递到内核中。当我使用只包含int的结构体时,我的方法很好用,但是当我切换到floats时,结果返回无意义的数字。我认为这与对齐有关,并且我尝试在类型声明中包含__align__
,但没有成功。有人可以给我一个示例说明如何做到这一点,或者提供替代方法吗?我正在尝试设置它,以便我可以轻松添加或删除字段,而不更改结构和内核之外的任何内容。 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;
}