結果

問題 No.1901 bitwise xor convolution (characteristic 2)
ユーザー hitonanode
提出日時 2022-04-12 23:27:57
言語 C++23
(gcc 13.3.0 + boost 1.87.0)
結果
AC  
実行時間 1,469 ms / 4,000 ms
コード長 8,755 bytes
コンパイル時間 2,507 ms
コンパイル使用メモリ 190,508 KB
実行使用メモリ 107,776 KB
最終ジャッジ日時 2024-11-28 01:55:00
合計ジャッジ時間 11,622 ms
ジャッジサーバーID
（参考情報） 		judge5 / judge2
このコードへのチャレンジ
（要ログイン）
ファイルパターン 結果
sample AC * 3
other AC * 7
権限があれば一括ダウンロードができます

ソースコード

diff #
raw source code 

#pragma GCC target("pclmul", "sse2", "sse4.1")
#include <emmintrin.h>
#include <smmintrin.h>
#include <wmmintrin.h>

__int64_t clmul(__int64_t x, __int64_t y) {
    __m128i x_ = _mm_set_epi64x(0, x);
    __m128i y_ = _mm_set_epi64x(0, y);
    __m128i z_ = _mm_clmulepi64_si128(x_, y_, 0);
    return _mm_extract_epi64(z_, 0);
}
#include <algorithm>
#include <array>
#include <bitset>
#include <cassert>
#include <chrono>
#include <cmath>
#include <complex>
#include <deque>
#include <forward_list>
#include <fstream>
#include <functional>
#include <iomanip>
#include <ios>
#include <iostream>
#include <limits>
#include <list>
#include <map>
#include <numeric>
#include <queue>
#include <random>
#include <set>
#include <sstream>
#include <stack>
#include <string>
#include <tuple>
#include <type_traits>
#include <unordered_map>
#include <unordered_set>
#include <utility>
#include <vector>
using namespace std;
using lint = long long;
using pint = pair<int, int>;
using plint = pair<lint, lint>;
struct fast_ios { fast_ios(){ cin.tie(nullptr), ios::sync_with_stdio(false), cout << fixed << setprecision(20); }; } fast_ios_;
#define ALL(x) (x).begin(), (x).end()
#define FOR(i, begin, end) for(int i=(begin),i##_end_=(end);i<i##_end_;i++)
#define IFOR(i, begin, end) for(int i=(end)-1,i##_begin_=(begin);i>=i##_begin_;i--)
#define REP(i, n) FOR(i,0,n)
#define IREP(i, n) IFOR(i,0,n)
template <typename T, typename V>
void ndarray(vector<T>& vec, const V& val, int len) { vec.assign(len, val); }
template <typename T, typename V, typename... Args> void ndarray(vector<T>& vec, const V& val, int len, Args... args) { vec.resize(len), for_each(begin(vec), end(vec), [&](T& v) { ndarray(v, val, args...); }); }
template <typename T> bool chmax(T &m, const T q) { return m < q ? (m = q, true) : false; }
template <typename T> bool chmin(T &m, const T q) { return m > q ? (m = q, true) : false; }
int floor_lg(long long x) { return x <= 0 ? -1 : 63 - __builtin_clzll(x); }
template <typename T1, typename T2> pair<T1, T2> operator+(const pair<T1, T2> &l, const pair<T1, T2> &r) { return make_pair(l.first + r.first, l.second + r.second); }
template <typename T1, typename T2> pair<T1, T2> operator-(const pair<T1, T2> &l, const pair<T1, T2> &r) { return make_pair(l.first - r.first, l.second - r.second); }
template <typename T> vector<T> sort_unique(vector<T> vec) { sort(vec.begin(), vec.end()), vec.erase(unique(vec.begin(), vec.end()), vec.end()); return vec; }
template <typename T> int arglb(const std::vector<T> &v, const T &x) { return std::distance(v.begin(), std::lower_bound(v.begin(), v.end(), x)); }
template <typename T> int argub(const std::vector<T> &v, const T &x) { return std::distance(v.begin(), std::upper_bound(v.begin(), v.end(), x)); }
template <typename T> istream &operator>>(istream &is, vector<T> &vec) { for (auto &v : vec) is >> v; return is; }
template <typename T> ostream &operator<<(ostream &os, const vector<T> &vec) { os << '['; for (auto v : vec) os << v << ','; os << ']'; return os; }
template <typename T> ostream &operator<<(ostream &os, const valarray<T> &vec) { os << '['; for (auto v : vec) os << v << ','; os << ']'; return os; }
template <typename T, size_t sz> ostream &operator<<(ostream &os, const array<T, sz> &arr) { os << '['; for (auto v : arr) os << v << ','; os << ']'; return os; }
#if __cplusplus >= 201703L
template <typename... T> istream &operator>>(istream &is, tuple<T...> &tpl) { std::apply([&is](auto &&... args) { ((is >> args), ...);}, tpl); return is; }
template <typename... T> ostream &operator<<(ostream &os, const tuple<T...> &tpl) { os << '('; std::apply([&os](auto &&... args) { ((os << args << ','), ...);}, tpl); return os << ')'; }
#endif
template <typename T> ostream &operator<<(ostream &os, const deque<T> &vec) { os << "deq["; for (auto v : vec) os << v << ','; os << ']'; return os; }
template <typename T> ostream &operator<<(ostream &os, const set<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <typename T, typename TH> ostream &operator<<(ostream &os, const unordered_set<T, TH> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <typename T> ostream &operator<<(ostream &os, const multiset<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <typename T> ostream &operator<<(ostream &os, const unordered_multiset<T> &vec) { os << '{'; for (auto v : vec) os << v << ','; os << '}'; return os; }
template <typename T1, typename T2> ostream &operator<<(ostream &os, const pair<T1, T2> &pa) { os << '(' << pa.first << ',' << pa.second << ')'; return os; }
template <typename TK, typename TV> ostream &operator<<(ostream &os, const map<TK, TV> &mp) { os << '{'; for (auto v : mp) os << v.first << "=>" << v.second << ','; os << '}'; return os; }
template <typename TK, typename TV, typename TH> ostream &operator<<(ostream &os, const unordered_map<TK, TV, TH> &mp) { os << '{'; for (auto v : mp) os << v.first << "=>" << v.second << ','; os << '}'; return os; }
#ifdef HITONANODE_LOCAL
const string COLOR_RESET = "\033[0m", BRIGHT_GREEN = "\033[1;32m", BRIGHT_RED = "\033[1;31m", BRIGHT_CYAN = "\033[1;36m", NORMAL_CROSSED = "\033[0;9;37m", RED_BACKGROUND = "\033[1;41m", NORMAL_FAINT = "\033[0;2m";
#define dbg(x) cerr << BRIGHT_CYAN << #x << COLOR_RESET << " = " << (x) << NORMAL_FAINT << " (L" << __LINE__ << ") " << __FILE__ << COLOR_RESET << endl
#define dbgif(cond, x) ((cond) ? cerr << BRIGHT_CYAN << #x << COLOR_RESET << " = " << (x) << NORMAL_FAINT << " (L" << __LINE__ << ") " << __FILE__ << COLOR_RESET << endl : cerr)
#else
#define dbg(x) 0
#define dbgif(cond, x) 0
#endif

#include <cassert>
#include <vector>

// CUT begin
// Fast Walsh-Hadamard transform and its abstraction
// Tutorials: <https://codeforces.com/blog/entry/71899>
//            <https://csacademy.com/blog/fast-fourier-transform-and-variations-of-it>
template <typename T, typename F> void abstract_fwht(std::vector<T> &seq, F f) {
    const int n = seq.size();
    assert(__builtin_popcount(n) == 1);
    for (int w = 1; w < n; w *= 2) {
        for (int i = 0; i < n; i += w * 2) {
            for (int j = 0; j < w; j++) { f(seq[i + j], seq[i + j + w]); }
        }
    }
}

template <typename T, typename F1, typename F2>
std::vector<T> bitwise_conv(std::vector<T> x, std::vector<T> y, F1 f, F2 finv) {
    const int n = x.size();
    assert(__builtin_popcount(n) == 1);
    assert(x.size() == y.size());
    if (x == y) {
        abstract_fwht(x, f), y = x;
    } else {
        abstract_fwht(x, f), abstract_fwht(y, f);
    }
    for (size_t i = 0; i < x.size(); i++) { x[i] *= y[i]; }
    abstract_fwht(x, finv);
    return x;
}

// bitwise xor convolution (FWHT-based)
// ret[i] = \sum_j x[j] * y[i ^ j]
// if T is integer, ||x||_1 * ||y||_1 * 2 < numeric_limits<T>::max()
template <typename T> std::vector<T> xorconv(std::vector<T> x, std::vector<T> y) {
    auto f = [](T &lo, T &hi) {
        T c = lo + hi;
        hi = lo - hi, lo = c;
    };
    auto finv = [](T &lo, T &hi) {
        T c = lo + hi;
        hi = (lo - hi) / 2,
        lo = c / 2; // Reconsider HEAVY complexity of division by 2 when T is ModInt
    };
    return bitwise_conv(x, y, f, finv);
}

// bitwise AND conolution
// ret[i] = \sum_{(j & k) == i} x[j] * y[k]
template <typename T> std::vector<T> andconv(std::vector<T> x, std::vector<T> y) {
    return bitwise_conv(
        x, y, [](T &lo, T &hi) { lo += hi; }, [](T &lo, T &hi) { lo -= hi; });
}

// bitwise OR convolution
// ret[i] = \sum_{(j | k) == i} x[j] * y[k]
template <typename T> std::vector<T> orconv(std::vector<T> x, std::vector<T> y) {
    return bitwise_conv(
        x, y, [](T &lo, T &hi) { hi += lo; }, [](T &lo, T &hi) { hi -= lo; });
}

constexpr int D = 32;

using Int = __int64_t;
__int64_t rd() {
    __int64_t ret = 0;
    REP(d, D) {
        __int64_t b;
        cin >> b;
        ret += b << d;
    }
    return ret;
}


#include <valarray>

valarray<lint> rdva() {
    valarray<lint> ret(D);
    for (auto &x : ret) cin >> x;
    return ret;
}

int main() {
    int N;
    cin >> N;
    vector<valarray<lint>> A(1 << N), B(1 << N);
    for (auto &x : A) x = rdva();
    for (auto &x : B) x = rdva();

    auto f_xor = [](valarray<lint> &lo, valarray<lint> &hi) {
        valarray<lint> c(lo.size());
        c += lo;
        c += hi;
        hi = lo - hi, lo = c;
    };
    abstract_fwht(A, f_xor);
    abstract_fwht(B, f_xor);
    REP(i, A.size()) {
        valarray<lint> v(63);
        REP(d, D) REP(e, D) v[d + e] += A[i][d] * B[i][e];
        A[i] = v;
    }
    abstract_fwht(A, f_xor);
    for (auto vec : A) {
        for (auto x : vec) { cout << abs((x >> N) % 2) << ' '; }
        cout << '\n';
    }
}
0