Iterative/ Non-Recursive Merge Sort - algorithm

I was trying iterative merge sort , but am stuck at at conditions when input length is not 2^x.
like int[] A ={4,5,1,254,66,75,12,8,65,4,87,63,53,8,99,54,12,34};
public class MergeSort {
public static void sort(int[] A) {
System.out.println("Log(A.len):"+log(A.length, 2));
for (int i = 0; i < log(A.length, 2); i++) { //log A.len
int r = 2 << i; //2^i
int mid = r >>> 1;
for (int j = 0; j+r < A.length; j = j + r) {
System.out.print("offset:" + j + " mid:" + (j + mid) + " r:" + (j + r));
merge(A, j, (j + mid), (j + r));
}
}
}
public static void merge(int[] A, int offset, int mid, int n) {
mid = mid - offset;
n = n - offset;
int[] L = new int[mid];
int[] R = new int[n - mid];
for (int i = 0; i < mid; i++) {
L[i] = A[i + offset];
R[i] = A[mid + i + offset];
}
System.out.print("\nL:");
print_array(L);
System.out.print("\nR:");
print_array(R);
int l = 0;
int r = 0; //left right pointer
int k = offset;
while (l < mid && r < mid) {
if (L[l] < R[r]) {
// System.out.println("in left");
A[k] = L[l];
l++;
} else {
// System.out.println("in right");
A[k] = R[r];
r++;
}
k++;
}
while (l < mid) {
A[k] = L[l];
l++;
k++;
}
while (r < mid) {
A[k] = R[r];
r++;
k++;
}
System.out.print("\nA:");
print_array(A);
System.out.print("\n\n");
}
public static void main(String[] args) {
int[] A ={4,5,1,254,66,75,12,8,65,4,87,63,53,8,99,54,12,34};
sort(A);
}
public static void print_array(int[] A) {
for (int i = 0; i < A.length; i++) {
System.out.print(A[i] + " ");
}
}
static int log(int x, int base) {
return (int) (Math.log(x) / Math.log(base));
}
}
It works fine when input length is 2^x.
Also is there any better way to implement iterative version , this looks a lot messy.

C++ example of bottom up merge sort. a[] is array to sort, b[] is temp array. It includes a check for number of merge passes and swaps in place if the number of passes would be odd, in order to end up with the sorted data in a[].
void BottomUpMerge(int a[], int b[], size_t ll, size_t rr, size_t ee);
void BottomUpCopy(int a[], int b[], size_t ll, size_t rr);
size_t GetPassCount(size_t n);
void BottomUpMergeSort(int a[], int b[], size_t n)
{
size_t s = 1; // run size
if(GetPassCount(n) & 1){ // if odd number of passes
for(s = 1; s < n; s += 2) // swap in place for 1st pass
if(a[s] < a[s-1])
std::swap(a[s], a[s-1]);
s = 2;
}
while(s < n){ // while not done
size_t ee = 0; // reset end index
while(ee < n){ // merge pairs of runs
size_t ll = ee; // ll = start of left run
size_t rr = ll+s; // rr = start of right run
if(rr >= n){ // if only left run
rr = n;
BottomUpCopy(a, b, ll, rr); // copy left run
break; // end of pass
}
ee = rr+s; // ee = end of right run
if(ee > n)
ee = n;
BottomUpMerge(a, b, ll, rr, ee);
}
std::swap(a, b); // swap a and b
s <<= 1; // double the run size
}
}
void BottomUpMerge(int a[], int b[], size_t ll, size_t rr, size_t ee)
{
size_t o = ll; // b[] index
size_t l = ll; // a[] left index
size_t r = rr; // a[] right index
while(1){ // merge data
if(a[l] <= a[r]){ // if a[l] <= a[r]
b[o++] = a[l++]; // copy a[l]
if(l < rr) // if not end of left run
continue; // continue (back to while)
do // else copy rest of right run
b[o++] = a[r++];
while(r < ee);
break; // and return
} else { // else a[l] > a[r]
b[o++] = a[r++]; // copy a[r]
if(r < ee) // if not end of right run
continue; // continue (back to while)
do // else copy rest of left run
b[o++] = a[l++];
while(l < rr);
break; // and return
}
}
}
void BottomUpCopy(int a[], int b[], size_t ll, size_t rr)
{
do // copy left run
b[ll] = a[ll];
while(++ll < rr);
}
size_t GetPassCount(size_t n) // return # passes
{
size_t i = 0;
for(size_t s = 1; s < n; s <<= 1)
i += 1;
return(i);
}

Related

Runtime error for large inputs for sorting ( quicksort)

This is a very simple program where the user inputs (x,y) coordinates and distance 'd' and the program has to find out the number of unrepeated coordinates from (x,y) to (x+d,y).
For eg: if input for one test case is: 4,9,2 then the unrepeated coordinates are (4,9),(5,9) and (6,9)(x=4,y=9,d=2). I have used a sorting algorithm as mentioned in the question (to keep track of multiple occurrences) however the program shows runtime error for test cases beyond 30. Is there any mistake in the code or is it an issue with my compiler?
For a detailed explanation of question: https://www.hackerearth.com/practice/algorithms/sorting/merge-sort/practice-problems/algorithm/missing-soldiers-december-easy-easy/
#include <stdio.h>
#include <stdlib.h>
int partition(int *arr, int p, int r) {
int x;
x = arr[r];
int tmp;
int i = p - 1;
for (int j = p; j <= r - 1; ++j) {
if (arr[j] <= x) {
i = i + 1;
tmp = arr[i];
arr[i] = arr[j];
arr[j] = tmp;
}
}
tmp = arr[i + 1];
arr[i + 1] = arr[r];
arr[r] = tmp;
return (i + 1);
}
void quicksort(int *arr, int p, int r) {
int q;
if (p < r) {
q = partition(arr, p, r);
quicksort(arr, p, q - 1);
quicksort(arr, q + 1, r);
}
}
int count(int A[],int ct) {
int cnt = 0;
for (int i = 0; i < ct; ++i) {
if (A[i] != A[i + 1]) {
cnt++;
}
}
return cnt;
}
int main() {
int t;
scanf("%d", &t);
long int tmp, y, d;
int ct = 0;
int i = 0;
int x[1000];
int j = 0;
for (int l = 0; l < t; ++l) {
scanf("%d%d%d", &tmp, &y, &d);
ct = ct + d + 1; //this counts the total no of coordinates for each (x,y,d)
for (int i = 0; i <= d; ++i) {
x[j] = tmp + i; //storing all possible the x and x+d coordinates
j++;
}
}
int cnt;
int p = ct - 1;
quicksort(x, 0, p); //quicksort sorting
for (int l = 0; l < ct; ++l) {
printf("%d ", x[l]); //prints sorted array not necessary to question
}
cnt = count(x, ct); //counts the number of non-repeated vertices
printf("%d\n", cnt);
}
The problem was the bounds of the array int x[1000] is not enough for the data given below.

Please spot the error in this merge sort code

I have provided the code for sorting an array using the merge sort algorithm, I'm unable to find the error, this code is not giving the correctly sorted array as it's output. The function mergesort is called recursively to divide the array till its size is reduced to 1. Then multiple arrays are merged using the merge function.
#include <bits/stdc++.h>
using namespace std;
void merge(int a[], int m, int l, int h) {
int n1 = m - l + 1, n2 = h - m;
int t1[n1], t2[n2];
for (int i = 0; i < n1; i++) {
t1[i] = a[i + l];
}
for (int i = 0; i < n2; i++) {
t2[i] = a[i + m + 1];
}
int k = 0, p = 0, r = 0;
while (k < n1 && p < n2) {
if (t1[k] <= t2[p]) {
a[r] = t1[k];
k++;
r++;
} else {
a[r] = t2[p];
p++;
r++;
}
}
while (k < n1) {
a[r] = t1[k];
k++;
r++;
}
while (p < n2) {
a[r] = t2[p];
p++;
r++;
}
}
void mergesort(int a[], int l, int h) {
if (l < h) {
int m = l + (h - l) / 2;
mergesort(a, l, m);
mergesort(a, m + 1, h);
merge(a, m, l, h);
}
}
int main() {
int a[5] = { 1, 2, 3, 4, 5 };
mergesort(a, 0, 4);
for (int i = 0; i < 5; i++) {
cout << a[i] << " ";
}
return 0;
}
The bug in the merge function is r should be initialized to l, not 0. You are not merging the slices into the original position.
Also note that the last loop while (p < n2) in this function is redundant: the remaining elements in the right slice are already in the proper place in the original array.
Here is a modified version:
void merge(int a[], int m, int l, int h) {
int n1 = m - l + 1, n2 = h - m;
int t1[n1], t2[n2];
for (int i = 0; i < n1; i++) {
t1[i] = a[i + l];
}
for (int i = 0; i < n2; i++) {
t2[i] = a[i + m + 1];
}
int k = 0, p = 0, r = l;
while (k < n1 && p < n2) {
if (t1[k] <= t2[p]) {
a[r] = t1[k];
k++;
r++;
} else {
a[r] = t2[p];
p++;
r++;
}
}
while (k < n1) {
a[r] = t1[k];
k++;
r++;
}
}
To further simplify the code, here are some more remarks:
it is less confusing to make use the convention that h be the first index beyond the end of the slice. This way the initial call uses the array length and mergesort can compute the slice length as h - l.
variable name l looks confusingly close to number 1.
the arguments to merge are usually in the order l, m, h, and m is the index of the start of the right slice.
the right slice does not need saving.
using variable length arrays with automatic storage t1[n2] may cause a stack overflow for large arrays.
Here is a modified version:
#include <bits/stdc++.h>
using namespace std;
void merge(int a[], int lo, int m, int hi) {
int i, j, k;
int n1 = m - lo;
int t1[n1];
for (i = 0; i < n1; i++) {
t1[i] = a[lo + i];
}
i = 0;
j = m;
k = lo;
while (i < n1 && j < hi) {
if (t1[i] <= a[j]) {
a[k++] = t1[i++];
} else {
a[k++] = a[j++];
}
}
while (i < n1) {
a[k++] = t1[i++];
}
}
void mergesort(int a[], int lo, int hi) {
if (hi - lo >= 2) {
int m = lo + (hi - lo) / 2;
mergesort(a, lo, m);
mergesort(a, m, hi);
merge(a, lo, m, hi);
}
}
int main() {
int a[5] = { 1, 5, 2, 4, 3 };
mergesort(a, 0, 5);
for (int i = 0; i < 5; i++) {
cout << a[i] << " ";
}
cout << "\n";
return 0;
}

Merge sort: time limit exceed

Why I am getting time limit exceeded error in sorting array using merge sort algorithm? What is wrong with my code? I have taken an input of 9 elements.
Input: 4 2 1 8 5 9 6 7 0
Output: Time limit exceeded
#include <bits/stdc++.h>
using namespace std;
int a[100];
void merge(int a[], int l, int r, int m) {
int t[r - l + 1];
int i = l, j = m + 1, k = 0;
while (i <= m && j <= r) {
if (a[i] < a[j])
t[k++] = a[i++];
else
t[k++] = a[j++];
}
while (i <= m)
t[k++] = a[i++];
while (j <= r)
t[k++] = a[j++];
for (int i = l; i <= r; i++)
a[i] = t[i - l];
}
void msort(int a[], int l, int r) {
if (l > r)
return;
int m = (r + l) / 2;
msort(a, l, m);
msort(a, m + 1, r);
merge(a, l, r, m);
}
int main() {
int n;
cin >> n;
for (int i = 0; i < n; i++)
cin >> a[i];
msort(a, 0, n - 1);
for (int i = 0; i < n; i++)
cout << a[i] << " ";
cout << endl;
return 0;
}
There are some problems in your code:
The test for termination in msort() is incorrect: you should stop when the slice has a single element or less. You currently loop forever on slices of 1 element.
if (l >= r) return;
You should test in main() if the number n of elements read from the user is no greater than 100, the size of the global array a into which you read the elements to be sorted. You should instead use a local array with the proper size or allocate the array from the heap. The temporary array t in merge() might also be too large for automatic allocation. It is more efficient to allocate temporary space once and pass it recursively.
Note also that it is idiomatic in C and C++ to specify array slices with the index of the first element and the index of the element after the last one. This simplifies the code and allows for empty arrays and avoid special cases for unsigned index types.
Here is a modified version with this approach:
#include <bits/stdc++.h>
using namespace std;
void merge(int a[], int l, int r, int m, int t[]) {
int i = l, j = m, k = 0;
while (i < m && j < r) {
if (a[i] < a[j])
t[k++] = a[i++];
else
t[k++] = a[j++];
}
while (i < m)
t[k++] = a[i++];
while (j < r)
t[k++] = a[j++];
for (int i = l; i < r; i++)
a[i] = t[i - l];
}
void msort(int a[], int l, int r, int t[]) {
if (r - l > 1) {
int m = l + (r - l) / 2;
msort(a, l, m, t);
msort(a, m, r, t);
merge(a, l, r, m, t);
}
}
void msort(int a[], int n) {
if (n > 1) {
int *t = new int[n];
msort(a, 0, n, t);
delete[] t;
}
}
int main() {
int n;
cin >> n;
if (n <= 0)
return 1;
int *a = new int[n];
for (int i = 0; i < n; i++)
cin >> a[i];
msort(a, n);
for (int i = 0; i < n; i++)
cout << a[i] << " ";
cout << endl;
delete[] a;
return 0;
}

Bit-reversal algorithm by Rutkowska

I found a very interesting paper about bit-reversal algorithm suitable for in-place FFT: "A simple algorithm for the bit-reversal permutation" by
Urszula Rutkowska from 1990 (doi.org/10.1016/0165-1684(91)90008-7).
However, her algorithm G1 does not appear to work as the very first iteration results in out-of-bounds error for that N1 = L << 1 and swap(a + 1, a + N1);. I assume L means the length of input vector.
Please, does anyone know if there was any errata for the paper or how to fix the algorithm?
The paper's pseudocode:
G1(L)
{int i,j,L1
N1,N2,a,b;
unsigned k;
j=0; L1=L-1;
N1=L<<1;N2=N1+1;
for(i=0;i<L1;i++)
{if(i<j)
{ a=i<<1;
b=j<<1;
swap(a,b);
swap(a+N2,b+N2);
swap(a+1,b+N1);
swap(b+1,a+N1);
}
else
if(i==j)
{ a=i<<1;
swap(a+1,a+N1);
}
k=L>>1;
while(k<=j){ j=j-k;
k=k>>1;
}
j+=k;
}
i<<=1;
swap(i+1,i+N1);
}
Screenshot of the paper:
It was pretty garbled, frankly. I had to read the paper for the idea (run Gold's algorithm (G) for L/4 and then derive the swaps for L) and then sort of massage the code into the right form. Here's my final result.
#include <assert.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
static bool is_power_of_two(int L) { return L > 0 && (L & (L - 1)) == 0; }
static void swap(int i, int j) { printf("swap %d,%d\n", i, j); }
static void G(int L) {
assert(is_power_of_two(L));
int j = 0;
for (int i = 0; i < L - 1; i++) {
if (i < j) {
swap(i, j);
}
int k = L >> 1;
while (j >= k) {
j -= k;
k >>= 1;
}
j += k;
}
}
static void G1(int L) {
assert(is_power_of_two(L));
if (L < 4) {
return;
}
int j = 0;
int N1 = L >> 1;
int N2 = N1 + 1;
int L2 = L >> 2;
for (int i = 0; i < L2 - 1; i++) {
if (i < j) {
int a = i << 1;
int b = j << 1;
swap(a, b);
swap(a + N2, b + N2);
swap(a + 1, b + N1);
swap(b + 1, a + N1);
} else if (i == j) {
int a = i << 1;
swap(a + 1, a + N1);
}
int k = L2 >> 1;
while (j >= k) {
j -= k;
k >>= 1;
}
j += k;
}
int a = (L2 - 1) << 1;
swap(a + 1, a + N1);
}
int main(int argc, char *argv[]) {
assert(1 < argc);
int L = atoi(argv[1]);
G(L);
putchar('\n');
G1(L);
}

Mergesort implementation is slow

I'am doing a report about different sorting algorithms in C++. What baffles me is that my mergesort seems to be slower than heapsort in both of the languages. What I've seen is that heapsort is supposed to be slower.
My mergesort sorts an unsorted array with size 100000 at a speed of 19.8 ms meanwhile heapsort sorts it at 9.7 ms. The code for my mergesort function in C++ is as follows:
void merge(int *array, int low, int mid, int high) {
int i, j, k;
int lowLength = mid - low + 1;
int highLength = high - mid;
int *lowArray = new int[lowLength];
int *highArray = new int[highLength];
for (i = 0; i < lowLength; i++)
lowArray[i] = array[low + i];
for (j = 0; j < highLength; j++)
highArray[j] = array[mid + 1 + j];
i = 0;
j = 0;
k = low;
while (i < lowLength && j < highLength) {
if (lowArray[i] <= highArray[j]) {
array[k] = lowArray[i];
i++;
} else {
array[k] = highArray[j];
j++;
}
k++;
}
while (i < lowLength) {
array[k] = lowArray[i];
i++;
k++;
}
while (j < highLength) {
array[k] = highArray[j];
j++;
k++;
}
}
void mergeSort(int *array, int low, int high) {
if (low < high) {
int mid = low + (high - low) / 2;
mergeSort(array, low, mid);
mergeSort(array, mid + 1, high);
merge(array, low, mid, high);
}
}
The example merge sort is doing allocation and copying of data in merge(), and both can be eliminated with a more efficient merge sort. A single allocation for the temp array can be done in a helper / entry function, and the copy is avoided by changing the direction of merge depending on level of recursion either by using two mutually recursive functions (as in example below) or with a boolean parameter.
Here is an example of a C++ top down merge sort that is reasonably optimized. A bottom up merge sort would be slightly faster, and on a system with 16 registers, a 4 way bottom merge sort a bit faster still, about as fast or faster than quick sort.
// prototypes
void TopDownSplitMergeAtoA(int a[], int b[], size_t ll, size_t ee);
void TopDownSplitMergeAtoB(int a[], int b[], size_t ll, size_t ee);
void TopDownMerge(int a[], int b[], size_t ll, size_t rr, size_t ee);
void MergeSort(int a[], size_t n) // entry function
{
if(n < 2) // if size < 2 return
return;
int *b = new int[n];
TopDownSplitMergeAtoA(a, b, 0, n);
delete[] b;
}
void TopDownSplitMergeAtoA(int a[], int b[], size_t ll, size_t ee)
{
if((ee - ll) == 1) // if size == 1 return
return;
size_t rr = (ll + ee)>>1; // midpoint, start of right half
TopDownSplitMergeAtoB(a, b, ll, rr);
TopDownSplitMergeAtoB(a, b, rr, ee);
TopDownMerge(b, a, ll, rr, ee); // merge b to a
}
void TopDownSplitMergeAtoB(int a[], int b[], size_t ll, size_t ee)
{
if((ee - ll) == 1){ // if size == 1 copy a to b
b[ll] = a[ll];
return;
}
size_t rr = (ll + ee)>>1; // midpoint, start of right half
TopDownSplitMergeAtoA(a, b, ll, rr);
TopDownSplitMergeAtoA(a, b, rr, ee);
TopDownMerge(a, b, ll, rr, ee); // merge a to b
}
void TopDownMerge(int a[], int b[], size_t ll, size_t rr, size_t ee)
{
size_t o = ll; // b[] index
size_t l = ll; // a[] left index
size_t r = rr; // a[] right index
while(1){ // merge data
if(a[l] <= a[r]){ // if a[l] <= a[r]
b[o++] = a[l++]; // copy a[l]
if(l < rr) // if not end of left run
continue; // continue (back to while)
while(r < ee) // else copy rest of right run
b[o++] = a[r++];
break; // and return
} else { // else a[l] > a[r]
b[o++] = a[r++]; // copy a[r]
if(r < ee) // if not end of right run
continue; // continue (back to while)
while(l < rr) // else copy rest of left run
b[o++] = a[l++];
break; // and return
}
}
}

Resources