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) for (int j=0; j<n; ++j) {
out[j] += (x[0][i]<x[0][j] & x[1][i]<x[1][j] & x[2][i]<x[2][j]);
}
}

评测结果