代码

#pragma GCC optimize("Ofast")

#define idx(i, j) ((i) * n + (j))

#define A0(i) (c[i]+=a*b[i])
#define A1(i) A0(i), A0(i+1)
#define A2(i) A1(i), A1(i+(1<<1))
#define A3(i) A2(i), A2(i+(1<<2))
#define A4(i) A3(i), A3(i+(1<<3))

void matrix_multiply(int n, const double *A, const double *B, double *C) {
	for(int i=0; i<n*n; ++i) C[i]=0;
	for (int i = 0; i < n; i++) {
		for (int k = 0; k < n; k++) {
			double *c=C+i*n;
			const double a=A[idx(i, k)], *b=B+k*n;
			for (int j = 0; j < n; j+=16) {
				A4(j);
			}
		}
	}
}

评测结果