Position of least significant bit that is set

Question

I am looking for an efficient way to determine the position of the least significant bit that is set in an integer, e.g. for 0x0FF0 it would be 4.

A trivial impleme

Answer 1

Weee, loads of solutions and not a benchmark in sight. You people should be ashamed of yourselves ;-)

My machine is an Intel i530 (2.9 GHz), running Windows 7 64-bit. I compiled with a 32-bit version of MinGW.

$ gcc --version
gcc.exe (GCC) 4.7.2

$ gcc bench.c -o bench.exe -std=c99 -Wall -O2
$ bench
Naive loop.         Time = 2.91  (Original questioner)
De Bruijn multiply. Time = 1.16  (Tykhyy)
Lookup table.       Time = 0.36  (Andrew Grant)
FFS instruction.    Time = 0.90  (ephemient)
Branch free mask.   Time = 3.48  (Dan / Jim Balter)
Double hack.        Time = 3.41  (DocMax)

$ gcc bench.c -o bench.exe -std=c99 -Wall -O2 -march=native
$ bench
Naive loop.         Time = 2.92
De Bruijn multiply. Time = 0.47
Lookup table.       Time = 0.35
FFS instruction.    Time = 0.68
Branch free mask.   Time = 3.49
Double hack.        Time = 0.92

My code:

#include 
#include 
#include 


#define ARRAY_SIZE 65536
#define NUM_ITERS 5000  // Number of times to process array


int find_first_bits_naive_loop(unsigned nums[ARRAY_SIZE])
{
    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            unsigned value = nums[i];
            if (value == 0)
                continue;
            unsigned pos = 0;
            while (!(value & 1))
            {
                value >>= 1;
                ++pos;
            }
            total += pos + 1;
        }
    }

    return total;
}


int find_first_bits_de_bruijn(unsigned nums[ARRAY_SIZE])
{
    static const int MultiplyDeBruijnBitPosition[32] = 
    {
       1, 2, 29, 3, 30, 15, 25, 4, 31, 23, 21, 16, 26, 18, 5, 9, 
       32, 28, 14, 24, 22, 20, 17, 8, 27, 13, 19, 7, 12, 6, 11, 10
    };

    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            unsigned int c = nums[i];
            total += MultiplyDeBruijnBitPosition[((unsigned)((c & -c) * 0x077CB531U)) >> 27];
        }
    }

    return total;
}


unsigned char lowestBitTable[256];
int get_lowest_set_bit(unsigned num) {
    unsigned mask = 1;
    for (int cnt = 1; cnt <= 32; cnt++, mask <<= 1) {
        if (num & mask) {
            return cnt;
        }
    }

    return 0;
}
int find_first_bits_lookup_table(unsigned nums[ARRAY_SIZE])
{
    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            unsigned int value = nums[i];
            // note that order to check indices will depend whether you are on a big 
            // or little endian machine. This is for little-endian
            unsigned char *bytes = (unsigned char *)&value;
            if (bytes[0])
                total += lowestBitTable[bytes[0]];
            else if (bytes[1])
              total += lowestBitTable[bytes[1]] + 8;
            else if (bytes[2])
              total += lowestBitTable[bytes[2]] + 16;
            else
              total += lowestBitTable[bytes[3]] + 24;
        }
    }

    return total;
}


int find_first_bits_ffs_instruction(unsigned nums[ARRAY_SIZE])
{
    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            total +=  __builtin_ffs(nums[i]);
        }
    }

    return total;
}


int find_first_bits_branch_free_mask(unsigned nums[ARRAY_SIZE])
{
    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            unsigned value = nums[i];
            int i16 = !(value & 0xffff) << 4;
            value >>= i16;

            int i8 = !(value & 0xff) << 3;
            value >>= i8;

            int i4 = !(value & 0xf) << 2;
            value >>= i4;

            int i2 = !(value & 0x3) << 1;
            value >>= i2;

            int i1 = !(value & 0x1);

            int i0 = (value >> i1) & 1? 0 : -32;

            total += i16 + i8 + i4 + i2 + i1 + i0 + 1;
        }
    }

    return total;
}


int find_first_bits_double_hack(unsigned nums[ARRAY_SIZE])
{
    int total = 0; // Prevent compiler from optimizing out the code
    for (int j = 0; j < NUM_ITERS; j++) {
        for (int i = 0; i < ARRAY_SIZE; i++) {
            unsigned value = nums[i];
            double d = value ^ (value - !!value); 
            total += (((int*)&d)[1]>>20)-1022; 
        }
    }

    return total;
}


int main() {
    unsigned nums[ARRAY_SIZE];
    for (int i = 0; i < ARRAY_SIZE; i++) {
        nums[i] = rand() + (rand() << 15);
    }

    for (int i = 0; i < 256; i++) {
        lowestBitTable[i] = get_lowest_set_bit(i);
    }


    clock_t start_time, end_time;
    int result;

    start_time = clock();
    result = find_first_bits_naive_loop(nums);
    end_time = clock();
    printf("Naive loop.         Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);

    start_time = clock();
    result = find_first_bits_de_bruijn(nums);
    end_time = clock();
    printf("De Bruijn multiply. Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);

    start_time = clock();
    result = find_first_bits_lookup_table(nums);
    end_time = clock();
    printf("Lookup table.       Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);

    start_time = clock();
    result = find_first_bits_ffs_instruction(nums);
    end_time = clock();
    printf("FFS instruction.    Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);

    start_time = clock();
    result = find_first_bits_branch_free_mask(nums);
    end_time = clock();
    printf("Branch free mask.   Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);

    start_time = clock();
    result = find_first_bits_double_hack(nums);
    end_time = clock();
    printf("Double hack.        Time = %.2f, result = %d\n", 
        (end_time - start_time) / (double)(CLOCKS_PER_SEC), result);
}