如果要从主机将阵列复制到设备,请执行 cudamalloc 和 cudaMemcpy 。但是要减轻麻烦,只需使用cudaMallocManaged而不需要前两件事,并且生活从未像现在这样简单。 代码看起来像这样(或多或少)
__global__ void convert(float kelvin[], float celsius[]) //can pass
arrays in kernel
{
int i = blockIdx.x * blockDim.x + threadIdx.x;
if (i<N)
kelvin[i]=celsius[i]+273.15;
}
int main()
{
float *celsius =(float *)malloc(N*sizeof(float));
float *kelvin =(float *)malloc(N*sizeof(float));
cudaMallocManaged(&celsius, N*sizeof(float));
cudaMallocManaged(&kelvin, N*sizeof(float));
// init celsius here
dim3 blocksPerGrid(1,1,1); //use only one block
dim3 threadsPerBlock(N,1,1); //use N threads in the block
convert<<<blocksPerGrid, threadsPerBlock>>>(kelvin,celsius);
cudaDeviceSynchronize();
//Doing stuff with the output here
return 0;
}
前面的例子对我来说似乎很清楚。 但是,该怎么做 用于2D和3D阵列的cudaMallocManaged ?我一直在尝试
__global__ void MatAdd(float A[N][N], float B[N][N], float C[N][N])
{
int i = blockIdx.x * blockDim.x + threadIdx.x;
int j = blockIdx.y * blockDim.y + threadIdx.y;
if (i < N && j < N)
C[i][j] = A[i][j] + B[i][j];
}
int main()
{ // I thonk, 2D arrays can be passed as pointer to pointers
float **A = (float **)malloc(N*N*sizeof(float));
float **B = (float **)malloc(N*N*sizeof(float));
float **C = (float **)malloc(N*N*sizeof(float));
cudaMallocManaged(&A, N*N*sizeof(float));
cudaMallocManaged(&B, N*N*sizeof(float));
cudaMallocManaged(&C, N*N*sizeof(float));
A[N][N]={{1,0,0},{0,1,0},{0,0,1}};
B[N][N]={{1,0,0},{0,1,0},{0,0,1}};
dim3 threadsPerBlock(16, 16);
dim3 numBlocks(N / threadsPerBlock.x, N / threadsPerBlock.y);
MatAdd<<<numBlocks, threadsPerBlock>>>(A, B, C);
//outputs and all
}
但是,它显示了以下错误
matrix_add.cu(22): error: too many initializer values
matrix_add.cu(25): error: argument of type "float **" is incompatible with parameter of type "float (*)[3]"
我们非常感谢您的帮助。
答案 0 :(得分:0)
您的尝试有很多错误,以至于编写一个工作版本比列出问题代码中的所有单个问题要快得多。因此,这是您尝试执行的操作的可行版本:
#include <algorithm>
#include <iostream>
const int N = 3;
__global__ void MatAdd(float A[][N], float B[][N], float C[][N])
{
int i = blockIdx.x * blockDim.x + threadIdx.x;
int j = blockIdx.y * blockDim.y + threadIdx.y;
if (i < N && j < N)
C[i][j] = A[i][j] + B[i][j];
}
int main()
{
float* A; cudaMallocManaged(&A, N*N*sizeof(float));
float* B; cudaMallocManaged(&B, N*N*sizeof(float));
float* C; cudaMallocManaged(&C, N*N*sizeof(float));
const float A_vals[N][N]={{1,0,0},{0,1,0},{0,0,1}};
const float B_vals[N][N]={{1,0,0},{0,1,0},{0,0,1}};
float (*C_vals)[N] = reinterpret_cast<float (*)[N]>(C);
std::copy(&A_vals[0][0], &A_vals[0][0] + N*N, A);
std::copy(&B_vals[0][0], &B_vals[0][0] + N*N, B);
dim3 threadsPerBlock(16, 16);
dim3 numBlocks(1, 1);
MatAdd<<<numBlocks, threadsPerBlock>>>( reinterpret_cast<float (*)[N]>(A),
reinterpret_cast<float (*)[N]>(B),
C_vals );
cudaDeviceSynchronize();
for(int i=0; i<N; i++) {
for(int j=0; j<N; j++) {
std::cout << C_vals[i][j] << " ";
}
std::cout << std::endl;
}
return 0;
}
一些要点:
[][]
访问语法(这适用于malloc
,new
或以下任何一种CUDA主机内存分配API。有关更多详细信息,请参见here。我只能建议您仔细研究它,直到了解其工作原理。