#include <bits/stdc++.h>
using namespace std;

#define V vector
#define pb push_back
#define fi first
#define se second
#define all0(x) (x).begin(), (x).end()
#define all1(x) (x).begin() + 1, (x).end()

typedef long long LL;
typedef pair<int, int> pi;

const LL mod = 998244353;
LL MOD(LL x) {
    if (x >= mod) return x - mod;
    if (x < 0) return x + mod;
    return x;
}

const int N = 5e5 + 1000;

struct BIT {
    LL fen[N];
    void add(int x, LL d) {
        x++;
        while (x < N) {
            fen[x] += d;
            x += x & -x;
        }
    }
    LL query(int x) {
        x++;
        LL ans = 0;
        while (x) ans += fen[x], x -= x & -x;
        return ans;
    }
    LL query(int l, int r) { return query(r) - query(l - 1); }
} fen;

LL cal_inv(V<int> a) {
    int n = a.size();
    for (int i = 0; i < n + 10; i++) fen.fen[i] = 0;
    LL ans = 0;
    for (int i = 0; i < n; i++) {
        // for (int j = 0; j < n; j++) {
        //     cout << fen.query(j, j) << " ";
        // }
        // cout << "\n";
        // for (int j = 1; j <= n; j++) {
        //     cout << fen.fen[j] << " ";
        // }
        // cout << "\n";
        ans += fen.query(a[i], n - 1);
        fen.add(a[i], 1);
    }
    return ans;
}

LL qpow(LL x, LL k) {
    LL ans = 1;
    while (k) {
        if (k & 1) ans = ans * x % mod;
        k >>= 1;
        x = x * x % mod;
    }
    return ans;
}

LL inv2 = qpow(2, mod - 2);

LL sum(LL l, LL r) { return (l + r) * (r - l + 1) % mod * inv2 % mod; }

void solve() {
    int L, B;
    cin >> L >> B;
    V<LL> pbb(L * 2);
    pbb[0] = 1;
    for (int i = 1; i < L * 2; i++) {
        pbb[i] = pbb[i - 1] * B % mod;
    }
    V<int> p(L);
    for (int i = 0; i < L; i++) cin >> p[i];
    V<V<int>> v(L, V<int>(B));
    for (int i = 0; i < L; i++) {
        for (int j = 0; j < B; j++) {
            cin >> v[i][j];
        }
    }
    V<LL> t(L);
    for (int i = 0; i < L; i++) t[i] = cal_inv(v[i]) % mod;
    V<int> g(L);
    for (int i = 1; i <= L + 10; i++) {
        fen.fen[i] = 0;
    }
    for (int i = L - 1; i >= 0; i--) {
        g[i] = fen.query(0, p[i]);
        fen.add(p[i], 1);
    }
    V<LL> f(L);
    for (int i = 0; i < L; i++) {
        f[i] = MOD(pbb[2 * p[i] - g[i]] * t[i] % mod +
                   sum(0, pbb[g[i]] - 1) * sum(0, B - 1) % mod *
                       pbb[2 * p[i] - 2 * g[i]]);
    }
    // cout << "g : " << "\n";
    // for (int i = 0; i < L; i++) {
    //     cout << g[i] << " ";
    // }
    // cout << "\n";
    // cout << "t : " << "\n";
    // for (int i = 0; i < L; i++) {
    //     cout << t[i] << " ";
    // }
    // cout << "\n";
    // cout << "f : " << "\n";
    // for (int i = 0; i < L; i++) {
    //     cout << f[i] << " ";
    // }
    // cout << "\n";
    LL ans = 0;
    for (int i = 0; i < L; i++) {
        ans = MOD(ans + pbb[L - 1 - p[i]] * f[i] % mod);
    }
    cout << ans << "\n";
}
int main() {
    ios::sync_with_stdio(0), cin.tie(0);
    solve();
}