Binary Search C++, STATUS_ACCESS_VIOLATION - c++

the thing is that we are tring to do for first time a binary search function for a vector class, but I dont really know the reason why this is not working. Does anyone know what could be wrong(Status acces violation when the number is not in the vector array)??
// size_ is de number of used elements i the array
int Vector::bsearch(int value) const
{
int first = 0;
int last = size_ - 1;
int Substraction = size_ /2;
while(last >= first)
{
Substraction = first + (last - first) / 2;
if(array_[Substraction] > value)
last = Substraction;
else if(array_[Substraction] < value)
first = Substraction;
else if(array_[Substraction] == value)
return Substraction;
}
return CS170::Vector::NO_INDEX;
}
//SOLVED
int Vector::bsearch(int value) const
{
unsigned first = 0;
unsigned last = size_ - 1;
unsigned int mid;
if(value < array_[0] || value > array_[size_ - 1])
return CS170::Vector::NO_INDEX;
while(last >= first)
{
mid = first + (last - first) / 2;
if(value < array_[mid])
last = mid - 1;
else if(array_[mid] < value)
first = mid + 1;
else
return mid;
}
return CS170::Vector::NO_INDEX;
}

You're not excluding the element you just tested before the next loop. And your choice of variable names, Subtraction is dreadful. Its a midpoint.
int first = 0;
int last = size_-1;
int mid = 0;
while(last >= first)
{
mid = first + (last - first) / 2;
if(value < array_[mid])
last = mid-1; // don't include element just tested
else if(array_[mid] < value)
first = mid+1; // don't include element just tested
else return mid;
}
return CS170::Vector::NO_INDEX

Your initialization is wrong -
int first = size_ - 1;
int last = first = 0;
should be -
int last = size_ - 1;
int first = 0;
Also, in while you should use the following condition -
while (last>first)

Related

Quickselect Algorithm to return Kth smallest element. Problem with the parameters for recursion

I'm trying to write a quickselect function using a random pivot that returns the Kth smallest element, but I can't figure out the correct parameters for recursion. I believe the first portion of the function works perfectly since I adapted from a quicksort function, just the recursive calls I can't get it right.
int quickselect(int* A, int k, int n) {
int i, left_part, right_part, pivot, temp;
if (n > 1)
{
//Choosing a random pivot and putting it at the end of the array
i = rand() % n;
pivot = A[i];
A[i] = A[n - 1];
A[n - 1] = pivot;
left_part = 0; right_part = n - 1;
// While loop is responsible for the comparison of the elements
while (left_part < right_part)
{
for (; A[left_part] < pivot; left_part++)
;
for (; A[right_part] >= pivot && right_part > left_part; right_part--)
;
if (left_part != right_part)
{
temp = A[left_part];
A[left_part] = A[right_part];
A[right_part] = temp;
}
}
// Making sure pivot is in correct position
A[n - 1] = A[left_part];
A[left_part] = pivot;
if (i == k) {
return A[k];
}
else if (i > k) {
// Element is to the left of pivot
return quickselect(A, k, left_part);
}
else if (i < k) {
// Element is to the right of pivot
return quickselect(A + left_part + 1, k - left_part, n - left_part - 1);
}
}
}

Quick Sort with Insertion Sort

I've been working on this code for hours. The goal is to write an optimized QuickSort (with Insertion sort) on an array of pointers (which point to objects that can be compared). Insertion sort is supposed to be used with array sizes < 4.
So far, I have insertion sort working when I pass in an array < 4.
The quicksort is supposed to use the middle index as a pivot, and move everything < the pivot to the left of pivot, and everything > the pivot to the right of pivot.
I'm not even sure my overall approach to quickSort is correct. This is my first attempt at writing a quick sort. I could really use a nudge in the right direction here. The code that's commented out is something I've already tried.
If anything is unclear, let me know. Thanks for the help!
void quickSort(Comparable ** array, int fromIndex, int toIndex)
{
while (fromIndex < toIndex)
{
if ((toIndex - fromIndex +1 ) < 4)
{
insertionSort(array, fromIndex, toIndex);
break;
}
else
{
int pivotIndex = partition(array, fromIndex, toIndex);
quickSort(array, fromIndex, pivotIndex - 1);
quickSort(array, pivotIndex + 1, toIndex);
}
}
}
int partition(Comparable ** array, int fromIndex, int toIndex)
{
//Comparable *front = array[fromIndex+1];
int midIndex = (toIndex + fromIndex) / 2;
//int frontIndex = fromIndex;
//Comparable *back = array[toIndex - 1];
//int backIndex = toIndex - 1;
//Comparable *compare = front;
//int compareIndex = frontIndex;
SortFirstMiddleLast(array, fromIndex, midIndex, toIndex);
swap(array, midIndex, toIndex - 1);
int pivotIndex = toIndex - 1;
Comparable * pivot = array[pivotIndex];
int indexLeft = fromIndex + 1;
int indexRight = toIndex - 2;
bool sortFinished = false;
while (*array[indexLeft] < *pivot)
{
indexLeft++;
}
while (*array[indexRight] > *pivot)
{
indexRight--;
}
if ((*array[indexLeft] >= *pivot) && (*array[indexRight] <= *pivot))
{
if (indexLeft < indexRight)
{
swap(array, indexLeft, indexRight);
indexLeft++;
indexRight--;
sortFinished = true;
}
}
if (sortFinished == true)
{
swap(array, pivotIndex, indexLeft);
pivotIndex = indexLeft;
return pivotIndex;
}
// ++frontIndex; // advance to next element
// while (*array[frontIndex] < *array[backIndex])
// {
// // search forward for out of order element
// while ((*array[frontIndex] < *array[backIndex]) && (*array[fromIndex] > *array[frontIndex]))
// ++frontIndex;
// //search backward for out of order element
// while ((*array[frontIndex] < *array[backIndex]) && (*array[compareIndex] <= *array[backIndex]))
// --backIndex;
// swap(array, frontIndex, backIndex);
// }
// //insert mid position comparison element
// if (*array[compareIndex] >= *array[frontIndex])
// {
// swap(array, fromIndex, frontIndex);
// returnValue = frontIndex;
// }
// else
// {
// swap(array,fromIndex, (frontIndex - 1));
// returnValue = (frontIndex - 1);
// }
// return returnValue;
}
void swap(Comparable ** array, int swapIndex1, int swapIndex2)
{
Comparable * temp = array[swapIndex1];
array[swapIndex1] = array[swapIndex2];
array[swapIndex2] = temp;
}
void SortFirstMiddleLast(Comparable ** array, int fromIndex, int midIndex, int toIndex)
{
// first must be less than mid, must be less than last
if (*array[fromIndex] > *array[midIndex])
{
swap(array, fromIndex, midIndex);
}
if (*array[fromIndex] > *array[toIndex - 1])
{
swap(array, fromIndex, toIndex - 1);
}
if (*array[midIndex] > *array[toIndex - 1])
{
swap(array, midIndex, toIndex - 1);
}
}
void insertionSort(Comparable ** array, int fromIndex, int toIndex)
{
for (unsigned i = fromIndex + 1; i < toIndex; i++)
{
for (unsigned j = i; j > 0; j--)
{
if (*array[j] < *array[j - 1])
{
swap(array, j, j-1);
}
else
break;
}
}
}

C++ Binary search algorithm to work like lower_bound

I do have another question following my previous -
I am creating a version of lower_bound with something like binary search. With the BinarySearch function I find a place where to insert the new item and with the for cycle I do move the rest of the array and insert the right item so I can insert it to the right position.
But the following BinarySearch function does not work properly.
Can anyone see why?
bool CReg::AddCar ( const char *name){
CArr * tmp = new CArr(name); // an item I am going to insert
int pos = BinarySearch(name,0,len); //len = number of items in array
checkLen(); // whether I do have enough space to move the array right
if (length!=0)
for (int i = m_len; i>=pos; i-- )
Arr[i+1] = spzArr[i];
Arr[pos] = tmp;
length++;
checkLen();
return true;
}
int BinarySearch(const char * name, int firstindex, int lastindex) {
if (lenght == 0) return 0; //number of items in array
if (firstindex == lastindex) return lastindex;
int tmp = lastindex - firstindex;
int pos = firstindex + tmp / 2; //position the new item should go to
if (tmp % 2)++pos;
if (lastindex == pos || firstindex == pos) return pos;
if (strcmp(name, Arr[pos]) < 0) return BinarySearch(name, firstindex, pos - 1);
if (strcmp(name, Arr[pos]) > 0) return BinarySearch(name, pos + 1, lastindex);
return pos;
}
A fixed version of BinarySearch
int BinarySearch(const char* name, int firstindex, int lastindex)
{
if (firstindex == lastindex) return lastindex;
int dist = lastindex - firstindex;
int mid = firstindex + dist / 2; //position the new item should go to
if (strcmp(name, Arr[mid]) < 0) return BinarySearch(name, firstindex, mid);
if (strcmp(name, Arr[mid]) > 0) return BinarySearch(name, mid + 1, lastindex);
return mid;
}
But you may directly use std::lower_bound:
// Assuming std::vector<std::string> Arr;
void CReg::AddCar(const std::string& name)
{
auto it = std::lower_bound(Arr.begin(), Arr.end(), name);
Arr.insert(it, name);
}

C++ Binary Search Algorithm not working

So I have a vector of ints named bList that has information already in it. I have it sorted before running the binary search.
//I have already inserted random ints into the vector
//Sort it
bubbleSort();
//Empty Line for formatting
cout << "\n";
//Print out sorted array.
print();
cout << "It will now search for a value using binary search\n";
int val = binSearch(54354);
cout<<val;
My bubble sort algorithm does work.
I have it returning an int which is the location of the searched value in the list.
//Its one argument is the value you are searching for.
int binSearch(int isbn) {
int lower = 0;
int upper = 19;//Vector size is 20.
int middle = (lower + upper) / 2;
while (lower < upper) {
middle = (lower + upper) / 2;
int midVal = bList[middle];
if (midVal == isbn) {
return middle;
break;
} else if (isbn > midVal) {
lower = midVal + 1;
} else if (isbn < midVal) {
upper - midVal - 1;
}
}
}
But for some reason, when I run it, it just keeps running and doesn't return anything.
Here the bug is:
// ...
} else if (isbn > midVal) {
lower = midVal + 1;
} else if (isbn < midVal) {
upper - midVal - 1;
}
You may want
lower = middle + 1;
and
upper = middle - 1;
instead.
You also need to explicitly return something when the required number cannot be found.
You still have a slight logic problem with your while condition:
int binary_search(int i, const std::vector<int>& vec) // you really should pass in the vector, if not convert it to use iterators
{
int result = -1; // default return value if not found
int lower = 0;
int upper = vec.size() - 1;
while (lower <= upper) // this will let the search run when lower == upper (meaning the result is one of the ends)
{
int middle = (lower + upper) / 2;
int val = vec[middle];
if (val == i)
{
result = middle;
break;
}
else if (i > val)
{
lower = middle + 1; // you were setting it to the value instead of the index
}
else if (i < val)
{
upper = middle - 1; // same here
}
}
return result; // moved your return down here to always return something (avoids a compiler error)
}
Alternatively, you could switch it to use iterators instead:
template<class RandomIterator>
RandomIterator binary_search(int i, RandomIterator start, RandomIterator end)
{
RandomIterator result = end;
while (start <= end) // this will let the search run when start == end (meaning the result is one of the ends)
{
RandomIterator middle = start + ((end - start) / 2);
if (*middle == i)
{
result = middle;
break;
}
else if (i > *middle)
{
start = middle + 1;
}
else if (i < *middle)
{
end = middle - 1;
}
}
return result;
}

What is the fastest search method for a sorted array?

Answering to another question, I wrote the program below to compare different search methods in a sorted array. Basically I compared two implementations of Interpolation search and one of binary search. I compared performance by counting cycles spent (with the same set of data) by the different variants.
However I'm sure there is ways to optimize these functions to make them even faster. Does anyone have any ideas on how can I make this search function faster? A solution in C or C++ is acceptable, but I need it to process an array with 100000 elements.
#include <stdlib.h>
#include <stdio.h>
#include <time.h>
#include <stdint.h>
#include <assert.h>
static __inline__ unsigned long long rdtsc(void)
{
unsigned long long int x;
__asm__ volatile (".byte 0x0f, 0x31" : "=A" (x));
return x;
}
int interpolationSearch(int sortedArray[], int toFind, int len) {
// Returns index of toFind in sortedArray, or -1 if not found
int64_t low = 0;
int64_t high = len - 1;
int64_t mid;
int l = sortedArray[low];
int h = sortedArray[high];
while (l <= toFind && h >= toFind) {
mid = low + (int64_t)((int64_t)(high - low)*(int64_t)(toFind - l))/((int64_t)(h-l));
int m = sortedArray[mid];
if (m < toFind) {
l = sortedArray[low = mid + 1];
} else if (m > toFind) {
h = sortedArray[high = mid - 1];
} else {
return mid;
}
}
if (sortedArray[low] == toFind)
return low;
else
return -1; // Not found
}
int interpolationSearch2(int sortedArray[], int toFind, int len) {
// Returns index of toFind in sortedArray, or -1 if not found
int low = 0;
int high = len - 1;
int mid;
int l = sortedArray[low];
int h = sortedArray[high];
while (l <= toFind && h >= toFind) {
mid = low + ((float)(high - low)*(float)(toFind - l))/(1+(float)(h-l));
int m = sortedArray[mid];
if (m < toFind) {
l = sortedArray[low = mid + 1];
} else if (m > toFind) {
h = sortedArray[high = mid - 1];
} else {
return mid;
}
}
if (sortedArray[low] == toFind)
return low;
else
return -1; // Not found
}
int binarySearch(int sortedArray[], int toFind, int len)
{
// Returns index of toFind in sortedArray, or -1 if not found
int low = 0;
int high = len - 1;
int mid;
int l = sortedArray[low];
int h = sortedArray[high];
while (l <= toFind && h >= toFind) {
mid = (low + high)/2;
int m = sortedArray[mid];
if (m < toFind) {
l = sortedArray[low = mid + 1];
} else if (m > toFind) {
h = sortedArray[high = mid - 1];
} else {
return mid;
}
}
if (sortedArray[low] == toFind)
return low;
else
return -1; // Not found
}
int order(const void *p1, const void *p2) { return *(int*)p1-*(int*)p2; }
int main(void) {
int i = 0, j = 0, size = 100000, trials = 10000;
int searched[trials];
srand(-time(0));
for (j=0; j<trials; j++) { searched[j] = rand()%size; }
while (size > 10){
int arr[size];
for (i=0; i<size; i++) { arr[i] = rand()%size; }
qsort(arr,size,sizeof(int),order);
unsigned long long totalcycles_bs = 0;
unsigned long long totalcycles_is_64 = 0;
unsigned long long totalcycles_is_float = 0;
unsigned long long totalcycles_new = 0;
int res_bs, res_is_64, res_is_float, res_new;
for (j=0; j<trials; j++) {
unsigned long long tmp, cycles = rdtsc();
res_bs = binarySearch(arr,searched[j],size);
tmp = rdtsc(); totalcycles_bs += tmp - cycles; cycles = tmp;
res_is_64 = interpolationSearch(arr,searched[j],size);
assert(res_is_64 == res_bs || arr[res_is_64] == searched[j]);
tmp = rdtsc(); totalcycles_is_64 += tmp - cycles; cycles = tmp;
res_is_float = interpolationSearch2(arr,searched[j],size);
assert(res_is_float == res_bs || arr[res_is_float] == searched[j]);
tmp = rdtsc(); totalcycles_is_float += tmp - cycles; cycles = tmp;
}
printf("----------------- size = %10d\n", size);
printf("binary search = %10llu\n", totalcycles_bs);
printf("interpolation uint64_t = %10llu\n", totalcycles_is_64);
printf("interpolation float = %10llu\n", totalcycles_is_float);
printf("new = %10llu\n", totalcycles_new);
printf("\n");
size >>= 1;
}
}
If you have some control over the in-memory layout of the data, you might want to look at Judy arrays.
Or to put a simpler idea out there: a binary search always cuts the search space in half. An optimal cut point can be found with interpolation (the cut point should NOT be the place where the key is expected to be, but the point which minimizes the statistical expectation of the search space for the next step). This minimizes the number of steps but... not all steps have equal cost. Hierarchical memories allow executing a number of tests in the same time as a single test, if locality can be maintained. Since a binary search's first M steps only touch a maximum of 2**M unique elements, storing these together can yield a much better reduction of search space per-cacheline fetch (not per comparison), which is higher performance in the real world.
n-ary trees work on that basis, and then Judy arrays add a few less important optimizations.
Bottom line: even "Random Access Memory" (RAM) is faster when accessed sequentially than randomly. A search algorithm should use that fact to its advantage.
Benchmarked on Win32 Core2 Quad Q6600, gcc v4.3 msys. Compiling with g++ -O3, nothing fancy.
Observation - the asserts, timing and loop overhead is about 40%, so any gains listed below should be divided by 0.6 to get the actual improvement in the algorithms under test.
Simple answers:
On my machine replacing the int64_t with int for "low", "high" and "mid" in interpolationSearch gives a 20% to 40% speed up. This is the fastest easy method I could find. It is taking about 150 cycles per look-up on my machine (for the array size of 100000). That's roughly the same number of cycles as a cache miss. So in real applications, looking after your cache is probably going to be the biggest factor.
Replacing binarySearch's "/2" with a ">>1" gives a 4% speed up.
Using STL's binary_search algorithm, on a vector containing the same data as "arr", is about the same speed as the hand coded binarySearch. Although on the smaller "size"s STL is much slower - around 40%.
I have an excessively complicated solution, which requires a specialized sorting function. The sort is slightly slower than a good quicksort, but all of my tests show that the search function is much faster than a binary or interpolation search. I called it a regression sort before I found out that the name was already taken, but didn't bother to think of a new name (ideas?).
There are three files to demonstrate.
The regression sort/search code:
#include <sstream>
#include <math.h>
#include <ctime>
#include "limits.h"
void insertionSort(int array[], int length) {
int key, j;
for(int i = 1; i < length; i++) {
key = array[i];
j = i - 1;
while (j >= 0 && array[j] > key) {
array[j + 1] = array[j];
--j;
}
array[j + 1] = key;
}
}
class RegressionTable {
public:
RegressionTable(int arr[], int s, int lower, int upper, double mult, int divs);
RegressionTable(int arr[], int s);
void sort(void);
int find(int key);
void printTable(void);
void showSize(void);
private:
void createTable(void);
inline unsigned int resolve(int n);
int * array;
int * table;
int * tableSize;
int size;
int lowerBound;
int upperBound;
int divisions;
int divisionSize;
int newSize;
double multiplier;
};
RegressionTable::RegressionTable(int arr[], int s) {
array = arr;
size = s;
multiplier = 1.35;
divisions = sqrt(size);
upperBound = INT_MIN;
lowerBound = INT_MAX;
for (int i = 0; i < size; ++i) {
if (array[i] > upperBound)
upperBound = array[i];
if (array[i] < lowerBound)
lowerBound = array[i];
}
createTable();
}
RegressionTable::RegressionTable(int arr[], int s, int lower, int upper, double mult, int divs) {
array = arr;
size = s;
lowerBound = lower;
upperBound = upper;
multiplier = mult;
divisions = divs;
createTable();
}
void RegressionTable::showSize(void) {
int bytes = sizeof(*this);
bytes = bytes + sizeof(int) * 2 * (divisions + 1);
}
void RegressionTable::createTable(void) {
divisionSize = size / divisions;
newSize = multiplier * double(size);
table = new int[divisions + 1];
tableSize = new int[divisions + 1];
for (int i = 0; i < divisions; ++i) {
table[i] = 0;
tableSize[i] = 0;
}
for (int i = 0; i < size; ++i) {
++table[((array[i] - lowerBound) / divisionSize) + 1];
}
for (int i = 1; i <= divisions; ++i) {
table[i] += table[i - 1];
}
table[0] = 0;
for (int i = 0; i < divisions; ++i) {
tableSize[i] = table[i + 1] - table[i];
}
}
int RegressionTable::find(int key) {
double temp = multiplier;
multiplier = 1;
int minIndex = table[(key - lowerBound) / divisionSize];
int maxIndex = minIndex + tableSize[key / divisionSize];
int guess = resolve(key);
double t;
while (array[guess] != key) {
// uncomment this line if you want to see where it is searching.
//cout << "Regression Guessing " << guess << ", not there." << endl;
if (array[guess] < key) {
minIndex = guess + 1;
}
if (array[guess] > key) {
maxIndex = guess - 1;
}
if (array[minIndex] > key || array[maxIndex] < key) {
return -1;
}
t = ((double)key - array[minIndex]) / ((double)array[maxIndex] - array[minIndex]);
guess = minIndex + t * (maxIndex - minIndex);
}
multiplier = temp;
return guess;
}
inline unsigned int RegressionTable::resolve(int n) {
float temp;
int subDomain = (n - lowerBound) / divisionSize;
temp = n % divisionSize;
temp /= divisionSize;
temp *= tableSize[subDomain];
temp += table[subDomain];
temp *= multiplier;
return (unsigned int)temp;
}
void RegressionTable::sort(void) {
int * out = new int[int(size * multiplier)];
bool * used = new bool[int(size * multiplier)];
int higher, lower;
bool placed;
for (int i = 0; i < size; ++i) {
/* Figure out where to put the darn thing */
higher = resolve(array[i]);
lower = higher - 1;
if (higher > newSize) {
higher = size;
lower = size - 1;
} else if (lower < 0) {
higher = 0;
lower = 0;
}
placed = false;
while (!placed) {
if (higher < size && !used[higher]) {
out[higher] = array[i];
used[higher] = true;
placed = true;
} else if (lower >= 0 && !used[lower]) {
out[lower] = array[i];
used[lower] = true;
placed = true;
}
--lower;
++higher;
}
}
int index = 0;
for (int i = 0; i < size * multiplier; ++i) {
if (used[i]) {
array[index] = out[i];
++index;
}
}
insertionSort(array, size);
}
And then there is the regular search functions:
#include <iostream>
using namespace std;
int binarySearch(int array[], int start, int end, int key) {
// Determine the search point.
int searchPos = (start + end) / 2;
// If we crossed over our bounds or met in the middle, then it is not here.
if (start >= end)
return -1;
// Search the bottom half of the array if the query is smaller.
if (array[searchPos] > key)
return binarySearch (array, start, searchPos - 1, key);
// Search the top half of the array if the query is larger.
if (array[searchPos] < key)
return binarySearch (array, searchPos + 1, end, key);
// If we found it then we are done.
if (array[searchPos] == key)
return searchPos;
}
int binarySearch(int array[], int size, int key) {
return binarySearch(array, 0, size - 1, key);
}
int interpolationSearch(int array[], int size, int key) {
int guess = 0;
double t;
int minIndex = 0;
int maxIndex = size - 1;
while (array[guess] != key) {
t = ((double)key - array[minIndex]) / ((double)array[maxIndex] - array[minIndex]);
guess = minIndex + t * (maxIndex - minIndex);
if (array[guess] < key) {
minIndex = guess + 1;
}
if (array[guess] > key) {
maxIndex = guess - 1;
}
if (array[minIndex] > key || array[maxIndex] < key) {
return -1;
}
}
return guess;
}
And then I wrote a simple main to test out the different sorts.
#include <iostream>
#include <iomanip>
#include <cstdlib>
#include <ctime>
#include "regression.h"
#include "search.h"
using namespace std;
void randomizeArray(int array[], int size) {
for (int i = 0; i < size; ++i) {
array[i] = rand() % size;
}
}
int main(int argc, char * argv[]) {
int size = 100000;
string arg;
if (argc > 1) {
arg = argv[1];
size = atoi(arg.c_str());
}
srand(time(NULL));
int * array;
cout << "Creating Array Of Size " << size << "...\n";
array = new int[size];
randomizeArray(array, size);
cout << "Sorting Array...\n";
RegressionTable t(array, size, 0, size*2.5, 1.5, size);
//RegressionTable t(array, size);
t.sort();
int trials = 10000000;
int start;
cout << "Binary Search...\n";
start = clock();
for (int i = 0; i < trials; ++i) {
binarySearch(array, size, i % size);
}
cout << clock() - start << endl;
cout << "Interpolation Search...\n";
start = clock();
for (int i = 0; i < trials; ++i) {
interpolationSearch(array, size, i % size);
}
cout << clock() - start << endl;
cout << "Regression Search...\n";
start = clock();
for (int i = 0; i < trials; ++i) {
t.find(i % size);
}
cout << clock() - start << endl;
return 0;
}
Give it a try and tell me if it's faster for you. It's super complicated, so it's really easy to break it if you don't know what you are doing. Be careful about modifying it.
I compiled the main with g++ on ubuntu.
Unless your data is known to have special properties, pure interpolation search has the risk of taking linear time. If you expect interpolation to help with most data but don't want it to hurt in the case of pathological data, I would use a (possibly weighted) average of the interpolated guess and the midpoint, ensuring a logarithmic bound on the run time.
One way of approaching this is to use a space versus time trade-off. There are any number of ways that could be done. The extreme way would be to simply make an array with the max size being the max value of the sorted array. Initialize each position with the index into sortedArray. Then the search would simply be O(1).
The following version, however, might be a little more realistic and possibly be useful in the real world. It uses a "helper" structure that is initialized on the first call. It maps the search space down to a smaller space by dividing by a number that I pulled out of the air without much testing. It stores the index of the lower bound for a group of values in sortedArray into the helper map. The actual search divides the toFind number by the chosen divisor and extracts the narrowed bounds of sortedArray for a normal binary search.
For example, if the sorted values range from 1 to 1000 and the divisor is 100, then the lookup array might contain 10 "sections". To search for value 250, it would divide it by 100 to yield integer index position 250/100=2. map[2] would contain the sortedArray index for values 200 and larger. map[3] would have the index position of values 300 and larger thus providing a smaller bounding position for a normal binary search. The rest of the function is then an exact copy of your binary search function.
The initialization of the helper map might be more efficient by using a binary search to fill in the positions rather than a simple scan, but it is a one time cost so I didn't bother testing that. This mechanism works well for the given test numbers which are evenly distributed. As written, it would not be as good if the distribution was not even. I think this method could be used with floating point search values too. However, extrapolating it to generic search keys might be harder. For example, I am unsure what the method would be for character data keys. It would need some kind of O(1) lookup/hash that mapped to a specific array position to find the index bounds. It's unclear to me at the moment what that function would be or if it exists.
I kludged the setup of the helper map in the following implementation pretty quickly. It is not pretty and I'm not 100% sure it is correct in all cases but it does show the idea. I ran it with a debug test to compare the results against your existing binarySearch function to be somewhat sure it works correctly.
The following are example numbers:
100000 * 10000 : cycles binary search = 10197811
100000 * 10000 : cycles interpolation uint64_t = 9007939
100000 * 10000 : cycles interpolation float = 8386879
100000 * 10000 : cycles binary w/helper = 6462534
Here is the quick-and-dirty implementation:
#define REDUCTION 100 // pulled out of the air
typedef struct {
int init; // have we initialized it?
int numSections;
int *map;
int divisor;
} binhelp;
int binarySearchHelp( binhelp *phelp, int sortedArray[], int toFind, int len)
{
// Returns index of toFind in sortedArray, or -1 if not found
int low;
int high;
int mid;
if ( !phelp->init && len > REDUCTION ) {
int i;
int numSections = len / REDUCTION;
int divisor = (( sortedArray[len-1] - 1 ) / numSections ) + 1;
int threshold;
int arrayPos;
phelp->init = 1;
phelp->divisor = divisor;
phelp->numSections = numSections;
phelp->map = (int*)malloc((numSections+2) * sizeof(int));
phelp->map[0] = 0;
phelp->map[numSections+1] = len-1;
arrayPos = 0;
// Scan through the array and set up the mapping positions. Simple linear
// scan but it is a one-time cost.
for ( i = 1; i <= numSections; i++ ) {
threshold = i * divisor;
while ( arrayPos < len && sortedArray[arrayPos] < threshold )
arrayPos++;
if ( arrayPos < len )
phelp->map[i] = arrayPos;
else
// kludge to take care of aliasing
phelp->map[i] = len - 1;
}
}
if ( phelp->init ) {
int section = toFind / phelp->divisor;
if ( section > phelp->numSections )
// it is bigger than all values
return -1;
low = phelp->map[section];
if ( section == phelp->numSections )
high = len - 1;
else
high = phelp->map[section+1];
} else {
// use normal start points
low = 0;
high = len - 1;
}
// the following is a direct copy of the Kriss' binarySearch
int l = sortedArray[low];
int h = sortedArray[high];
while (l <= toFind && h >= toFind) {
mid = (low + high)/2;
int m = sortedArray[mid];
if (m < toFind) {
l = sortedArray[low = mid + 1];
} else if (m > toFind) {
h = sortedArray[high = mid - 1];
} else {
return mid;
}
}
if (sortedArray[low] == toFind)
return low;
else
return -1; // Not found
}
The helper structure needs to be initialized (and memory freed):
help.init = 0;
unsigned long long totalcycles4 = 0;
... make the calls same as for the other ones but pass the structure ...
binarySearchHelp(&help, arr,searched[j],length);
if ( help.init )
free( help.map );
help.init = 0;
Look first at the data and whether a big gain can be got by data specific method over a general method.
For large static sorted datasets, you can create an additional index to provide partial pigeon holing, based on the amount of memory you're willing to use. e.g. say we create a 256x256 two dimensional array of ranges, which we populate with the start and end positions in the search array of elements with corresponding high order bytes. When we come to search, we then use the high order bytes on the key to find the range / subset of the array we need to search. If we did have ~ 20 comparisons on our binary search of 100,000 elements O(log2(n)) we're now down to ~4 comarisons for 16 elements, or O(log2 (n/15)). The memory cost here is about 512k
Another method, again suited to data that doesn't change much, is to divide the data into arrays of commonly sought items and rarely sought items. For example, if you leave your existing search in place running a wide number of real world cases over a protracted testing period, and log the details of the item being sought, you may well find that the distribution is very uneven, i.e. some values are sought far more regularly than others. If this is the case, break your array into a much smaller array of commonly sought values and a larger remaining array, and search the smaller array first. If the data is right (big if!), you can often achieve broadly similar improvements to the first solution without the memory cost.
There are many other data specific optimizations which score far better than trying to improve on tried, tested and far more widely used general solutions.
Posting my current version before the question is closed (hopefully I will thus be able to ehance it later). For now it is worse than every other versions (if someone understand why my changes to the end of loop has this effect, comments are welcome).
int newSearch(int sortedArray[], int toFind, int len)
{
// Returns index of toFind in sortedArray, or -1 if not found
int low = 0;
int high = len - 1;
int mid;
int l = sortedArray[low];
int h = sortedArray[high];
while (l < toFind && h > toFind) {
mid = low + ((float)(high - low)*(float)(toFind - l))/(1+(float)(h-l));
int m = sortedArray[mid];
if (m < toFind) {
l = sortedArray[low = mid + 1];
} else if (m > toFind) {
h = sortedArray[high = mid - 1];
} else {
return mid;
}
}
if (l == toFind)
return low;
else if (h == toFind)
return high;
else
return -1; // Not found
}
The implementation of the binary search that was used for comparisons can be improved. The key idea is to "normalize" the range initially so that the target is always > a minimum and < than a maximum after the first step. This increases the termination delta size. It also has the effect of special casing targets that are less than the first element of the sorted array or greater than the last element of the sorted array. Expect approximately a 15% improvement in search time. Here is what the code might look like in C++.
int binarySearch(int * &array, int target, int min, int max)
{ // binarySearch
// normalize min and max so that we know the target is > min and < max
if (target <= array[min]) // if min not normalized
{ // target <= array[min]
if (target == array[min]) return min;
return -1;
} // end target <= array[min]
// min is now normalized
if (target >= array[max]) // if max not normalized
{ // target >= array[max]
if (target == array[max]) return max;
return -1;
} // end target >= array[max]
// max is now normalized
while (min + 1 < max)
{ // delta >=2
int tempi = min + ((max - min) >> 1); // point to index approximately in the middle between min and max
int atempi = array[tempi]; // just in case the compiler does not optimize this
if (atempi > target)max = tempi; // if the target is smaller, we can decrease max and it is still normalized
else if (atempi < target)min = tempi; // the target is bigger, so we can increase min and it is still normalized
else return tempi; // if we found the target, return with the index
// Note that it is important that this test for equality is last because it rarely occurs.
} // end delta >=2
return -1; // nothing in between normalized min and max
} // end binarySearch