高Cache命中率的矩阵乘法

#include <ctime>
#include <iostream>

using namespace std;

int main(int argc, char** argv)
{
   int N = 500;
   int A[N][N];
   int B[N][N];
   double C1[N][N];
   double C2[N][N];
   for (int i = 0; i < N; i++) {
       for (int j = 0; j < N; j++) {
           A[i][j] = rand();
           B[i][j] = rand();
       }
   }
   clock_t t1 = clock();
   for (int i = 0; i < N; i++) {
       for (int j = 0; j < N; j++) {
           for (int k = 0; k < N; k++) {
               C1[i][j] += A[i][k] * B[k][j];
           }
       }
   }
   clock_t t2 = clock();
   cout << "Conventional method takes " << t2 - t1 << " milliseconds."  << endl;
   t1 = clock();
   for (int i = 0; i < N; i++) {
       for (int k = 0; k < N; k++) {
           for (int j = 0; j < N; j++) {
               C2[i][j] += A[i][k] * B[k][j];
           }
       }
   }
   t2 = clock();
   cout << "New method takes " << t2 - t1 << " milliseconds." << endl;
}