#include <bits/stdc++.h>
using namespace std;
#define LL long long
#define pb push_back
#define x first
#define y second 
#define endl '\n'
const LL maxn = 4e05+7;
const LL N = 5e05+10;
const LL mod = 1e09+7;
const int inf = 0x3f3f3f3f;
const LL llinf = 5e18;
typedef pair<int,int>pl;

priority_queue<LL , vector<LL>, greater<LL> >mi;//小根堆
priority_queue<LL> ma;//大根堆
LL gcd(LL a, LL b){
	return b > 0 ? gcd(b , a % b) : a;
}

LL lcm(LL a , LL b){
	return a / gcd(a , b) * b;
}
int n , m;
vector<int>a(N , 0);
void init(int n){
	for(int i = 0 ; i <= n ; i ++){
		a[i] = 0;
	}
}
void solve() 
{
	cin >> n >> m;
	int id = 1;
	map<int,int>mp;
	vector<int>stx[n * m + 1] , sty[n * m + 1];
	int x;
	for(int i = 1 ; i <= n ; i ++){
		for(int j = 1 ; j <= m ; j ++){
			cin >> x;
			if(!mp.count(x)){
				mp[x] = id;
				id++;
			}
			stx[mp[x]].pb(i) , sty[mp[x]].pb(j);
		}
	}
	LL ans = 0;
	for(int i = 1 ; i < id ; i ++){
		int len = stx[i].size();
		LL lsum = 0 , rsum = 0;
		for(auto it : stx[i]){
			rsum += it;
		}
		for(int j = 0 ; j < len ; j ++){
			ans += (rsum - stx[i][j] * (len - j));
			ans += (stx[i][j] * j - lsum);
			lsum += stx[i][j];
			rsum -= stx[i][j];
		}
	}
	for(int i = 1 ; i < id ; i ++){
		sort(sty[i].begin() , sty[i].end());
		int len = sty[i].size();
		LL lsum = 0 , rsum = 0;
		for(auto it : sty[i]){
			rsum += it;
		}
		for(int j = 0 ; j < len ; j ++){
			ans += (rsum - sty[i][j] * (len - j));
			ans += (sty[i][j] * j - lsum);
			lsum += sty[i][j];
			rsum -= sty[i][j];
		}
	}
	cout << ans;
}            
int main() 
{
    ios::sync_with_stdio(false);
    cin.tie(0);
    cout.tie(0);
    cout.precision(10);
    int t=1;
	//cin>>t;
    while(t--)
    {
    	solve();
    }
    return 0;
}