代码

#pragma GCC optimize("Ofast")
#pragma GCC target("avx2,popcnt,bmi,bmi2")
void count_4d(int n, const int **x, unsigned *out) {
	for (int i=0; i<n; ++i) { int r[4] = {x[0][i], x[1][i], x[2][i], x[3][i]}; for (int j=0; j<n; ++j) {
out[j] += (r[0]<x[0][j] & r[1]<x[1][j] & r[2]<x[2][j] & r[3]<x[3][j]);
}}
}

评测结果