这是 CUDA 架构上的矩阵乘法程序。当数组大小为 30 x 30 时,此代码工作正常,但当大小更大时,输出为一系列 0。我正在为 Linux 机器上托管的 CUDA 使用标准 ec2 实例。任何人都可以找出原因吗?
#include <stdio.h>
#define SIZE 30
__global__ void matrix_multiply(float *input1,float *input2,float *output,int dimension){
int input1_index = threadIdx.x / dimension * dimension;
int input2_index = threadIdx.x % dimension;
int i=0;
for( i =0; i <dimension; i++){
output[threadIdx.x] += input1[input1_index + i] * input2[input2_index + i * dimension];
}
}
int main(){
int i,j,natural_number=1;
float input1[SIZE][SIZE],input2[SIZE][SIZE],result[SIZE][SIZE]={0};
float *c_input1,*c_input2,*c_result;
for(i=0;i<SIZE;i++){
for(j=0;j<SIZE;j++){
input1[i][j]=input2[i][j]=natural_number++;
}
}
cudaMalloc((void**)&c_input1,sizeof(input1));
cudaMalloc((void**)&c_input2,sizeof(input2));
cudaMalloc((void**)&c_result,sizeof(result));
cudaMemcpy(c_input1,input1,sizeof(input1),cudaMemcpyHostToDevice);
cudaMemcpy(c_input2,input2,sizeof(input2),cudaMemcpyHostToDevice);
cudaMemcpy(c_result,result,sizeof(result),cudaMemcpyHostToDevice);
matrix_multiply<<<1,SIZE * SIZE>>>(c_input1,c_input2,c_result,SIZE);
if(cudaGetLastError()!=cudaSuccess){
printf("%s\n",cudaGetErrorString(cudaGetLastError()));
}
cudaMemcpy(result,c_result,sizeof(result),cudaMemcpyDeviceToHost);
for(i=0;i<SIZE;i++){
for(j=0;j<SIZE;j++){
printf("%.2f ",result[i][j]);
}
printf("\n");
}
cudaFree(c_input1);
cudaFree(c_input2);
cudaFree(c_result);
return 0;
}