当我尝试从设备执行的函数中访问全局数组时,我发现了一些困难:
float globTemp[3][3] = "some value in here";
__device__ float* globTemp_d;
__global__ void compute(int *a, int w)
{
int x = threadIdx.x + blockDim.x * blockIdx.x;
int y = threadIdx.y + blockDim.y * blockIdx.y;
int i = y*w+x;
if(x<3 && y<3)
a[i] = 1+globTemp_d[i];
}
int hostFunc(){
float *a_d;
cudaMalloc((void**)&a_d, 3*3*sizeof(int));
cudaMalloc((void**)&globTemp_d, 3*3*sizeof(int));
cudaMemcpy(globTemp_d,globTemp, 3*3*sizeof(float), cudaMemcpyHostToDevice);
compute<<<1,1>>>(a_d,3);
cudaMemcpy(a,a_d, 3*3*sizeof(float), cudaMemcpyDeviceToHost);
}
但是,当我尝试访问 globTemp_d[i] 时出现 seg 错误。我在这里做错了吗?