An example of bufferless mergesort in C.
#define SWAP(type, a, b) \
do { type t=(a);(a)=(b);(b)=t; } while (0)
static void reverse_(int* a, int* b)
{
for ( --b; a < b; a++, b-- )
SWAP(int, *a, *b);
}
static int* rotate_(int* a, int* b, int* c)
/* swap the sequence [a,b) with [b,c). */
{
if (a != b && b != c)
{
reverse_(a, b);
reverse_(b, c);
reverse_(a, c);
}
return a + (c - b);
}
static int* lower_bound_(int* a, int* b, const int key)
/* find first element not less than @p key in sorted sequence or end of
* sequence (@p b) if not found. */
{
int i;
for ( i = b-a; i != 0; i /= 2 )
{
int* mid = a + i/2;
if (*mid < key)
a = mid + 1, i--;
}
return a;
}
static int* upper_bound_(int* a, int* b, const int key)
/* find first element greater than @p key in sorted sequence or end of
* sequence (@p b) if not found. */
{
int i;
for ( i = b-a; i != 0; i /= 2 )
{
int* mid = a + i/2;
if (*mid <= key)
a = mid + 1, i--;
}
return a;
}
static void ip_merge_(int* a, int* b, int* c)
/* inplace merge. */
{
int n1 = b - a;
int n2 = c - b;
if (n1 == 0 || n2 == 0)
return;
if (n1 == 1 && n2 == 1)
{
if (*b < *a)
SWAP(int, *a, *b);
}
else
{
int* p, * q;
if (n1 <= n2)
p = upper_bound_(a, b, *(q = b+n2/2));
else
q = lower_bound_(b, c, *(p = a+n1/2));
b = rotate_(p, b, q);
ip_merge_(a, p, b);
ip_merge_(b, q, c);
}
}
void mergesort(int* v, int n)
{
if (n > 1)
{
int h = n/2;
mergesort(v, h); mergesort(v+h, n-h);
ip_merge_(v, v+h, v+n);
}
}
An example of adaptive mergesort (optimized).
Adds support code and modifications to accelerate the merge when an auxiliary buffer of any size is available (still works without additional memory). Uses forward and backward merging, ring rotation, small sequence merging and sorting, and iterative mergesort.
#include <stdlib.h>
#include <string.h>
static int* copy_(const int* a, const int* b, int* out)
{
int count = b - a;
if (a != out)
memcpy(out, a, count*sizeof(int));
return out + count;
}
static int* copy_backward_(const int* a, const int* b, int* out)
{
int count = b - a;
if (b != out)
memmove(out - count, a, count*sizeof(int));
return out - count;
}
static int* merge_(const int* a1, const int* b1, const int* a2,
const int* b2, int* out)
{
while ( a1 != b1 && a2 != b2 )
*out++ = (*a1 <= *a2) ? *a1++ : *a2++;
return copy_(a2, b2, copy_(a1, b1, out));
}
static int* merge_backward_(const int* a1, const int* b1,
const int* a2, const int* b2, int* out)
{
while ( a1 != b1 && a2 != b2 )
*--out = (*(b1-1) > *(b2-1)) ? *--b1 : *--b2;
return copy_backward_(a1, b1, copy_backward_(a2, b2, out));
}
static unsigned int gcd_(unsigned int m, unsigned int n)
{
while ( n != 0 )
{
unsigned int t = m % n;
m = n;
n = t;
}
return m;
}
static void rotate_inner_(const int length, const int stride,
int* first, int* last)
{
int* p, * next = first, x = *first;
while ( 1 )
{
p = next;
if ((next += stride) >= last)
next -= length;
if (next == first)
break;
*p = *next;
}
*p = x;
}
static int* rotate_(int* a, int* b, int* c)
/* swap the sequence [a,b) with [b,c). */
{
if (a != b && b != c)
{
int n1 = c - a;
int n2 = b - a;
int* i = a;
int* j = a + gcd_(n1, n2);
for ( ; i != j; i++ )
rotate_inner_(n1, n2, i, c);
}
return a + (c - b);
}
static void ip_merge_small_(int* a, int* b, int* c)
/* inplace merge.
* @note faster for small sequences. */
{
while ( a != b && b != c )
if (*a <= *b)
a++;
else
{
int* p = b+1;
while ( p != c && *p < *a )
p++;
rotate_(a, b, p);
b = p;
}
}
static void ip_merge_(int* a, int* b, int* c, int* t, const int ts)
/* inplace merge.
* @note works with or without additional memory. */
{
int n1 = b - a;
int n2 = c - b;
if (n1 <= n2 && n1 <= ts)
{
merge_(t, copy_(a, b, t), b, c, a);
}
else if (n2 <= ts)
{
merge_backward_(a, b, t, copy_(b, c, t), c);
}
/* merge without buffer. */
else if (n1 + n2 < 48)
{
ip_merge_small_(a, b, c);
}
else
{
int* p, * q;
if (n1 <= n2)
p = upper_bound_(a, b, *(q = b+n2/2));
else
q = lower_bound_(b, c, *(p = a+n1/2));
b = rotate_(p, b, q);
ip_merge_(a, p, b, t, ts);
ip_merge_(b, q, c, t, ts);
}
}
static void ip_merge_chunk_(const int cs, int* a, int* b, int* t,
const int ts)
{
int* p = a + cs*2;
for ( ; p <= b; a = p, p += cs*2 )
ip_merge_(a, a+cs, p, t, ts);
if (a+cs < b)
ip_merge_(a, a+cs, b, t, ts);
}
static void smallsort_(int* a, int* b)
/* insertion sort.
* @note any stable sort with low setup cost will do. */
{
int* p, * q;
for ( p = a+1; p < b; p++ )
{
int x = *p;
for ( q = p; a < q && x < *(q-1); q-- )
*q = *(q-1);
*q = x;
}
}
static void smallsort_chunk_(const int cs, int* a, int* b)
{
int* p = a + cs;
for ( ; p <= b; a = p, p += cs )
smallsort_(a, p);
smallsort_(a, b);
}
static void mergesort_lower_(int* v, int n, int* t, const int ts)
{
int cs = 16;
smallsort_chunk_(cs, v, v+n);
for ( ; cs < n; cs *= 2 )
ip_merge_chunk_(cs, v, v+n, t, ts);
}
static void* get_buffer_(int size, int* final)
{
void* p = NULL;
while ( size != 0 && (p = malloc(size)) == NULL )
size /= 2;
*final = size;
return p;
}
void mergesort(int* v, int n)
{
/* @note buffer size may be in the range [0,(n+1)/2]. */
int request = (n+1)/2 * sizeof(int);
int actual;
int* t = (int*) get_buffer_(request, &actual);
/* @note allocation failure okay. */
int tsize = actual / sizeof(int);
mergesort_lower_(v, n, t, tsize);
free(t);
}
