롤링되지 않은 분기없는 선택 정렬은 어떻습니까?

#include <iostream>
#include <algorithm>
#include <random>

//return the index of the minimum element in array a
int min(const int * const a) {
  int m = a[0];
  int indx = 0;
  #define TEST(i) (m > a[i]) && (m = a[i], indx = i );
  //see http://stackoverflow.com/a/7074042/2140449
  TEST(1);
  TEST(2);
  TEST(3);
  TEST(4);
  TEST(5);
  TEST(6);
  TEST(7);
  TEST(8);
  TEST(9);
  #undef TEST
  return indx;
}

void sort( int * const a ){
  int work[10];
  int indx;
  #define GET(i) indx = min(a); work[i] = a[indx]; a[indx] = 2147483647;
  //get the minimum, copy it to work and set it at max_int in a
  GET(0);
  GET(1);
  GET(2);
  GET(3);
  GET(4);
  GET(5);
  GET(6);
  GET(7);
  GET(8);
  GET(9);
  #undef GET
  #define COPY(i) a[i] = work[i];
  //copy back to a
  COPY(0);
  COPY(1);
  COPY(2);
  COPY(3);
  COPY(4);
  COPY(5);
  COPY(6);
  COPY(7);
  COPY(8);
  COPY(9);
  #undef COPY
}

int main() {
  //generating and printing a random array
  int a[10] = { 1,2,3,4,5,6,7,8,9,10 };
  std::random_device rd;
  std::mt19937 g(rd());
  std::shuffle( a, a+10, g);
  for (int i = 0; i < 10; i++) {
    std::cout << a[i] << ' ';
  }
  std::cout << std::endl;

  //sorting and printing again
  sort(a);
  for (int i = 0; i < 10; i++) {
    std::cout << a[i] << ' ';
  }

  return 0;
}

http://coliru.stacked-crooked.com/a/71e18bc4f7fa18c6

유일하게 관련된 줄은 처음 두 개 #define입니다.

두 개의 목록을 사용하고 첫 번째 목록을 10 번 완전히 다시 검사하여 선택 정렬이 잘못 구현되지만 분기 및 가변 길이 루프를 피하므로 최신 프로세서 및 작은 데이터 세트로 보완 할 수 있습니다.

기준

정렬 네트워크에 대해 벤치마킹했으며 코드가 느려 보입니다. 그러나 언 롤링과 사본을 제거하려고했습니다. 이 코드를 실행 :

#include <iostream>
#include <algorithm>
#include <random>
#include <chrono>

int min(const int * const a, int i) {
  int m = a[i];
  int indx = i++;
  for ( ; i<10; i++)
    //see http://stackoverflow.com/a/7074042/2140449
    (m > a[i]) && (m = a[i], indx = i );
  return indx;
}

void sort( int * const a ){
  for (int i = 0; i<9; i++)
    std::swap(a[i], a[min(a,i)]); //search only forward
}


void sortNet10(int * const data) {  // ten-input sorting network by Waksman, 1969
    int swap;
    if (data[0] > data[5]) { swap = data[0]; data[0] = data[5]; data[5] = swap; }
    if (data[1] > data[6]) { swap = data[1]; data[1] = data[6]; data[6] = swap; }
    if (data[2] > data[7]) { swap = data[2]; data[2] = data[7]; data[7] = swap; }
    if (data[3] > data[8]) { swap = data[3]; data[3] = data[8]; data[8] = swap; }
    if (data[4] > data[9]) { swap = data[4]; data[4] = data[9]; data[9] = swap; }
    if (data[0] > data[3]) { swap = data[0]; data[0] = data[3]; data[3] = swap; }
    if (data[5] > data[8]) { swap = data[5]; data[5] = data[8]; data[8] = swap; }
    if (data[1] > data[4]) { swap = data[1]; data[1] = data[4]; data[4] = swap; }
    if (data[6] > data[9]) { swap = data[6]; data[6] = data[9]; data[9] = swap; }
    if (data[0] > data[2]) { swap = data[0]; data[0] = data[2]; data[2] = swap; }
    if (data[3] > data[6]) { swap = data[3]; data[3] = data[6]; data[6] = swap; }
    if (data[7] > data[9]) { swap = data[7]; data[7] = data[9]; data[9] = swap; }
    if (data[0] > data[1]) { swap = data[0]; data[0] = data[1]; data[1] = swap; }
    if (data[2] > data[4]) { swap = data[2]; data[2] = data[4]; data[4] = swap; }
    if (data[5] > data[7]) { swap = data[5]; data[5] = data[7]; data[7] = swap; }
    if (data[8] > data[9]) { swap = data[8]; data[8] = data[9]; data[9] = swap; }
    if (data[1] > data[2]) { swap = data[1]; data[1] = data[2]; data[2] = swap; }
    if (data[3] > data[5]) { swap = data[3]; data[3] = data[5]; data[5] = swap; }
    if (data[4] > data[6]) { swap = data[4]; data[4] = data[6]; data[6] = swap; }
    if (data[7] > data[8]) { swap = data[7]; data[7] = data[8]; data[8] = swap; }
    if (data[1] > data[3]) { swap = data[1]; data[1] = data[3]; data[3] = swap; }
    if (data[4] > data[7]) { swap = data[4]; data[4] = data[7]; data[7] = swap; }
    if (data[2] > data[5]) { swap = data[2]; data[2] = data[5]; data[5] = swap; }
    if (data[6] > data[8]) { swap = data[6]; data[6] = data[8]; data[8] = swap; }
    if (data[2] > data[3]) { swap = data[2]; data[2] = data[3]; data[3] = swap; }
    if (data[4] > data[5]) { swap = data[4]; data[4] = data[5]; data[5] = swap; }
    if (data[6] > data[7]) { swap = data[6]; data[6] = data[7]; data[7] = swap; }
    if (data[3] > data[4]) { swap = data[3]; data[3] = data[4]; data[4] = swap; }
    if (data[5] > data[6]) { swap = data[5]; data[5] = data[6]; data[6] = swap; }
}


std::chrono::duration<double> benchmark( void(*func)(int * const), const int seed ) {
  std::mt19937 g(seed);
  int a[10] = {10,11,12,13,14,15,16,17,18,19};
  std::chrono::high_resolution_clock::time_point t1, t2;
  t1 = std::chrono::high_resolution_clock::now();
  for (long i = 0; i < 1e7; i++) {
    std::shuffle( a, a+10, g);
    func(a);
  }
  t2 = std::chrono::high_resolution_clock::now();
  return std::chrono::duration_cast<std::chrono::duration<double>>(t2 - t1);
}

int main() {
  std::random_device rd;
  for (int i = 0; i < 10; i++) {
    const int seed = rd();
    std::cout << "seed = " << seed << std::endl;
    std::cout << "sortNet10: " << benchmark(sortNet10, seed).count() << std::endl;
    std::cout << "sort:      " << benchmark(sort,      seed).count() << std::endl;
  }
  return 0;
}

정렬 네트워크와 비교 하여 브랜치리스 선택 정렬에서 지속적으로 더 나은 결과를 얻고 있습니다.

$ gcc -v
gcc version 5.2.0 (GCC)
$ g++ -std=c++11 -Ofast sort.cpp && ./a.out
seed = -1727396418
sortNet10: 2.24137
sort:      2.21828
seed = 2003959850
sortNet10: 2.23914
sort:      2.21641
seed = 1994540383
sortNet10: 2.23782
sort:      2.21778
seed = 1258259982
sortNet10: 2.25199
sort:      2.21801
seed = 1821086932
sortNet10: 2.25535
sort:      2.2173
seed = 412262735
sortNet10: 2.24489
sort:      2.21776
seed = 1059795817
sortNet10: 2.29226
sort:      2.21777
seed = -188551272
sortNet10: 2.23803
sort:      2.22996
seed = 1043757247
sortNet10: 2.2503
sort:      2.23604
seed = -268332483
sortNet10: 2.24455
sort:      2.24304

답변

/**
 * A Functor class to create a sort for fixed sized arrays/containers with a
 * compile time generated Bose-Nelson sorting network.
 * \tparam NumElements  The number of elements in the array or container to sort.
 * \tparam T            The element type.
 * \tparam Compare      A comparator functor class that returns true if lhs < rhs.
 */
template <unsigned NumElements, class Compare = void> class StaticSort
{
    template <class A, class C> struct Swap
    {
        template <class T> inline void s(T &v0, T &v1)
        {
            T t = Compare()(v0, v1) ? v0 : v1; // Min
            v1 = Compare()(v0, v1) ? v1 : v0; // Max
            v0 = t;
        }

        inline Swap(A &a, const int &i0, const int &i1) { s(a[i0], a[i1]); }
    };

    template <class A> struct Swap <A, void>
    {
        template <class T> inline void s(T &v0, T &v1)
        {
            // Explicitly code out the Min and Max to nudge the compiler
            // to generate branchless code.
            T t = v0 < v1 ? v0 : v1; // Min
            v1 = v0 < v1 ? v1 : v0; // Max
            v0 = t;
        }

        inline Swap(A &a, const int &i0, const int &i1) { s(a[i0], a[i1]); }
    };

    template <class A, class C, int I, int J, int X, int Y> struct PB
    {
        inline PB(A &a)
        {
            enum { L = X >> 1, M = (X & 1 ? Y : Y + 1) >> 1, IAddL = I + L, XSubL = X - L };
            PB<A, C, I, J, L, M> p0(a);
            PB<A, C, IAddL, J + M, XSubL, Y - M> p1(a);
            PB<A, C, IAddL, J, XSubL, M> p2(a);
        }
    };

    template <class A, class C, int I, int J> struct PB <A, C, I, J, 1, 1>
    {
        inline PB(A &a) { Swap<A, C> s(a, I - 1, J - 1); }
    };

    template <class A, class C, int I, int J> struct PB <A, C, I, J, 1, 2>
    {
        inline PB(A &a) { Swap<A, C> s0(a, I - 1, J); Swap<A, C> s1(a, I - 1, J - 1); }
    };

    template <class A, class C, int I, int J> struct PB <A, C, I, J, 2, 1>
    {
        inline PB(A &a) { Swap<A, C> s0(a, I - 1, J - 1); Swap<A, C> s1(a, I, J - 1); }
    };

    template <class A, class C, int I, int M, bool Stop = false> struct PS
    {
        inline PS(A &a)
        {
            enum { L = M >> 1, IAddL = I + L, MSubL = M - L};
            PS<A, C, I, L, (L <= 1)> ps0(a);
            PS<A, C, IAddL, MSubL, (MSubL <= 1)> ps1(a);
            PB<A, C, I, IAddL, L, MSubL> pb(a);
        }
    };

    template <class A, class C, int I, int M> struct PS <A, C, I, M, true>
    {
        inline PS(A &a) {}
    };

public:
    /**
     * Sorts the array/container arr.
     * \param  arr  The array/container to be sorted.
     */
    template <class Container> inline void operator() (Container &arr) const
    {
        PS<Container, Compare, 1, NumElements, (NumElements <= 1)> ps(arr);
    };

    /**
     * Sorts the array arr.
     * \param  arr  The array to be sorted.
     */
    template <class T> inline void operator() (T *arr) const
    {
        PS<T*, Compare, 1, NumElements, (NumElements <= 1)> ps(arr);
    };
};

#include <iostream>
#include <vector>

int main(int argc, const char * argv[])
{
    enum { NumValues = 10 };

    // Arrays
    {
        int rands[NumValues];
        for (int i = 0; i < NumValues; ++i) rands[i] = rand() % 100;
        std::cout << "Before Sort: \t";
        for (int i = 0; i < NumValues; ++i) std::cout << rands[i] << " ";
        std::cout << "\n";
        StaticSort<NumValues> staticSort;
        staticSort(rands);
        std::cout << "After Sort: \t";
        for (int i = 0; i < NumValues; ++i) std::cout << rands[i] << " ";
        std::cout << "\n";
    }

    std::cout << "\n";

    // STL Vector
    {
        std::vector<int> rands(NumValues);
        for (int i = 0; i < NumValues; ++i) rands[i] = rand() % 100;
        std::cout << "Before Sort: \t";
        for (int i = 0; i < NumValues; ++i) std::cout << rands[i] << " ";
        std::cout << "\n";
        StaticSort<NumValues> staticSort;
        staticSort(rands);
        std::cout << "After Sort: \t";
        for (int i = 0; i < NumValues; ++i) std::cout << rands[i] << " ";
        std::cout << "\n";
    }

    return 0;
}

Direct call to qsort library function       : 326.81
Naive implementation (insertion sort)       : 132.98
Insertion Sort (Daniel Stutzbach)           : 104.04
Insertion Sort Unrolled                     : 99.64
Insertion Sort Unrolled (Glenn Teitelbaum)  : 81.55
Rank Order                                  : 44.01
Rank Order with registers                   : 42.40
Sorting Networks (Daniel Stutzbach)         : 88.06
Sorting Networks (Paul R)                   : 31.64
Sorting Networks 12 with Fast Swap          : 29.68
Sorting Networks 12 reordered Swap          : 28.61
Reordered Sorting Network w/ fast swap      : 24.63
Templated Sorting Network (this class)      : 25.37

{
    final int a=in[0]<in[1]?in[0]:in[1];
    final int b=in[0]<in[1]?in[1]:in[0];
    in[0]=a;
    in[1]=b;
}
for(int x=2;x<10;x+=2)
{
    final int a=in[x]<in[x+1]?in[x]:in[x+1];
    final int b=in[x]<in[x+1]?in[x+1]:in[x];
    int y= x-1;

    while(y>=0&&in[y]>b)
    {
        in[y+2]= in[y];
        --y;
    }
    in[y+2]=b;
    while(y>=0&&in[y]>a)
    {
        in[y+1]= in[y];
        --y;
    }
    in[y+1]=a;
}