// while (clock()<=69*CLOCKS_PER_SEC)
// #pragma comment(linker, "/stack:200000000")
// #pragma GCC optimize("O3")
// #pragma GCC target ("avx2")
// #pragma GCC optimize("Ofast")
// #pragma GCC target("sse,sse2,sse3,ssse3,sse4,popcnt,abm,mmx,avx,tune=native")
// #pragma GCC optimize("unroll-loops")
#include <bits/stdc++.h>
#include <ext/pb_ds/assoc_container.hpp>
#include <ext/pb_ds/tree_policy.hpp>
using namespace __gnu_pbds;
using namespace std;
template <typename T>
using ordered_set =
tree<T, null_type, less<T>, rb_tree_tag, tree_order_statistics_node_update>;
#define sim template <class c
#define ris return *this
#define dor > debug &operator<<
#define eni(x) \
sim > typename enable_if<sizeof dud<c>(0) x 1, debug &>::type operator<<(c i) \
{
sim > struct rge {
c b, e;
};
sim > rge<c> range(c i, c j) { return rge<c>{i, j}; }
sim > auto dud(c *x) -> decltype(cerr << *x, 0);
sim > char dud(...);
struct debug {
#ifdef XOX
~debug()
{
cerr << endl;
}
eni(!=) cerr << boolalpha << i;
ris;
} eni(==) ris << range(begin(i), end(i));
}
sim, class b dor(pair<b, c> d)
{
ris << "" << d.first << " --> " << d.second << "";
}
sim dor(rge<c> d)
{
*this << "[";
for(auto it = d.b; it != d.e; ++it)
*this << ", " + 2 * (it == d.b) << *it;
ris << "]";
}
#else
sim dor(const c &)
{
ris;
}
#endif
}
;
#define imie(...) " [" << #__VA_ARGS__ ": " << (__VA_ARGS__) << "] "
#ifdef XOX
#warning Times may differ!!!
#endif
#define endl '\n'
#define pb emplace_back
#define vt vector
#define rep(i, a, b) for(int i = a; i < (b); ++i)
#define all(x) begin(x), end(x)
#define sz(x) (int)(x).size()
typedef long long ll;
typedef pair<int, int> pii;
typedef vector<int> vi;
const int nax = 1e6, mod = 1e9 + 7;
struct L {
ll a, b, from;
ll operator()(ll x)
{
return a * x + b;
}
pair<ll, ll> inter(L &he) const
{
ll up = he.b - b;
ll down = a - he.a;
return {up, down};
}
};
struct CHT {
vector<L> hull;
int start = 0;
pair<ll, ll> query(ll x)
{
while(start <= (int)hull.size() - 2) {
L A = hull[start], B = hull[start + 1];
if(A(x) <= B(x))
start++;
else
break;
}
return {hull[start](x), hull[start].from};
}
void add(L x)
{
while(start <= (int)hull.size() - 2) {
L A = hull.end()[-2], B = hull.end()[-1];
auto one = A.inter(B), two = B.inter(x);
if(two.second == 0) {
if(B.b <= x.b)
hull.pop_back();
else
break;
continue;
}
if(one.first * two.second <= two.first * one.second)
hull.pop_back();
else
break;
}
hull.push_back(x);
}
};
ll sq(ll x)
{
return x * x;
}
int main()
{
cin.tie(nullptr)->sync_with_stdio(0);
int n, k;
cin >> n >> k;
vector<int> p(n + 1);
for(int i = 1; i <= n; i++) {
cin >> p[i];
p[i] += p[i - 1];
}
// p[i]*(p[j]-p[i])+dp[j]
// p[i]p[j]-p[i]^2+dp[j]
vector<CHT> hull(k + 1);
hull[0].add({p[n], 0, n});
vt<vt<int>> kto(n + 1, vt<int>(k + 1));
for(int i = n - 1; i >= 1; i--) {
for(int use = k; use >= 1; use--) {
if(hull[use - 1].hull.empty()) continue;
pair<ll, ll> dp = hull[use - 1].query(p[i]);
L in = {p[i], -sq(p[i]) + dp.first, i};
kto[i][use] = dp.second;
hull[use].add(in);
}
}
pair<ll, ll> dp = hull[k].query(0);
cout << dp.first << endl;
vector<int> print;
while(k) {
cout << dp.second << " ";
dp.second = kto[dp.second][k--];
}
cout << endl;
}
