#include // created [2019/12/04] 23:59:42 #pragma GCC diagnostic ignored "-Wsign-compare" #pragma GCC diagnostic ignored "-Wsign-conversion" using i32 = int32_t; using i64 = int64_t; using u32 = uint32_t; using u64 = uint64_t; using uint = unsigned int; using usize = std::size_t; using ll = long long; using ull = unsigned long long; using ld = long double; template constexpr T popcount(const T u) { return u ? static_cast(__builtin_popcountll(static_cast(u))) : static_cast(0); } template constexpr T log2p1(const T u) { return u ? static_cast(64 - __builtin_clzll(static_cast(u))) : static_cast(0); } template constexpr T msbp1(const T u) { return log2p1(u); } template constexpr T lsbp1(const T u) { return __builtin_ffsll(u); } template constexpr T clog(const T u) { return u ? log2p1(u - 1) : static_cast(u); } template constexpr bool ispow2(const T u) { return u and (static_cast(u) & static_cast(u - 1)) == 0; } template constexpr T ceil2(const T u) { return static_cast(1) << clog(u); } template constexpr T floor2(const T u) { return u == 0 ? static_cast(0) : static_cast(1) << (log2p1(u) - 1); } template constexpr bool btest(const T mask, const usize ind) { return static_cast((static_cast(mask) >> ind) & static_cast(1)); } template void bset(T& mask, const usize ind) { mask |= (static_cast(1) << ind); } template void breset(T& mask, const usize ind) { mask &= ~(static_cast(1) << ind); } template void bflip(T& mask, const usize ind) { mask ^= (static_cast(1) << ind); } template void bset(T& mask, const usize ind, const bool b) { (b ? bset(mask, ind) : breset(mask, ind)); } template constexpr T bcut(const T mask, const usize ind) { return ind == 0 ? static_cast(0) : static_cast((static_cast(mask) << (64 - ind)) >> (64 - ind)); } template bool chmin(T& a, const T& b) { return (a > b ? a = b, true : false); } template bool chmax(T& a, const T& b) { return (a < b ? a = b, true : false); } constexpr unsigned int mod = 1000000007; template constexpr T inf_v = std::numeric_limits::max() / 4; template constexpr Real pi_v = Real{3.141592653589793238462643383279502884}; template T read() { T v; return std::cin >> v, v; } template auto read(const usize size, Args... args) { std::vector(args...))> ans(size); for (usize i = 0; i < size; i++) { ans[i] = read(args...); } return ans; } template auto reads() { return std::tuple...>{read()...}; } # define SHOW(...) static_cast(0) constexpr ull TEN(const usize n) { return n == 0 ? 1ULL : TEN(n - 1) * 10ULL; } template std::vector make_v(const usize size, const T v) { return std::vector(size, v); } template auto make_v(const usize size, Args... args) { return std::vector(size, make_v(args...)); } int main() { const int N = read(); const int K = read(); if ((N / K) % 2 == 1 and N % 2 == 0) { return std::cout << "No" << std::endl, 0; } const int M = N / K; if (M == 1) { return std::cout << "No" << std::endl, 0; } std::cout << "Yes" << std::endl; std::vector> ans(K); auto three = [&]() { const int L = (K-1)/2; std::vector vs(3*K); for(int i=0;i r(K); for (int j = 0; j < K; j++) { r[j] = i * K + j; } if (i % 2 == 1) { std::reverse(r.begin(), r.end()); } for (int j = 0; j < K; j++) { ans[j].push_back(r[j]); } } } else { assert(K % 2 == 1); // 3段あればOK three(); // 他の段は昇順/降順 交互 for (int i = 3; i < M; i++) { std::vector r(K); for (int j = 0; j < K; j++) { r[j] = i * K + j; } if (i % 2 == 1) { std::reverse(r.begin(), r.end()); } for (int j = 0; j < K; j++) { ans[j].push_back(r[j]); } } } for (int i = 0; i < K; i++) { for (int j = 0; j < M; j++) { std::cout << ans[i][j] + 1 << " "; } std::cout << std::endl; } return 0; }