代码

#pragma GCC optimize("unroll-loops")

#include <cstdio>
#include <random>
#include <chrono>

std::mt19937 rng(std::chrono::steady_clock::now().time_since_epoch().count());

typedef unsigned int UI;
typedef unsigned long long ULL;

const UI Mod = 998244353;
const int N = 1400;

UI A[N][N], B[N][N], C[N][N];

int main() {
	for (int i = 0; i < N; ++i) {
		for (int j = 0; j < N; ++j) {
			A[i][j] = rng() % Mod;
			B[i][j] = rng() % Mod;
			C[i][j] = 0;
		}
	}
	for (int i = 0; i < N; ++i)
		for (int k = 0; k < N; ++k)
			for (int j = 0; j < N; ++j) {
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod; ++j;
				C[i][j] = (C[i][j] + (ULL)A[i][k] * B[k][j]) % Mod;
			}
	UI Ans = 0;
	for (int i = 0; i < N; ++i)
		for (int j = 0; j < N; ++j)
			Ans ^= C[i][j];
	printf("%u\n", Ans);
	return 0;
}

评测结果