C++ 有人可以帮我优化这段代码吗?

我正在尝试在大边界上执行循环卷积，有人可以帮助我优化它以运行得更快吗？我正在尝试用大量样本发出信号。缩减采样不是一种选择。

#include <iostream>
#include <time.h> /* clock_t, clock, CLOCKS_PER_SEC */
#include <math.h> /* sqrt */
using namespace std;
void fillarray(double* x, int N)
{
for (int i = 0; i < N; i++)
x[i] = i + 1;
}
void circcon(double* x, double* y, double* u, int N)
{
for (int m = 0; m < N; ++m)
for (int n = 0; n < N; ++n) {
if ((m - n) < 0)
u[m] += x[n] * y[m - n + N];
else
u[m] += x[n] * y[m - n];
}
}
int main(void)
{
int N = 447650;
double* x = new double[N];
double* y = new double[N];
double* u = new double[N];
clock_t t;
t = clock();
fillarray(x, N);
fillarray(y, N);
for (int i = 0; i < N; i++)
u[i] = 0.0;
circcon(x, y, u, N);
t = clock() - t;
printf("It took me %d clicks (%f seconds).n", t, ((float)t) / CLOCKS_PER_SEC);
return 0;
}