What is the fastest/most efficient way to find the highest set bit (msb) in an integer in C?

Question

If I have some integer n, and I want to know the position of the most significant bit (that is, if the least significant bit is on the right, I want to know the position of

Answer 1

Here are some (simple) benchmarks, of algorithms currently given on this page...

The algorithms have not been tested over all inputs of unsigned int; so check that first, before blindly using something ;)

On my machine clz (__builtin_clz) and asm work best. asm seems even faster then clz... but it might be due to the simple benchmark...

//////// go.c ///////////////////////////////
// compile with:  gcc go.c -o go -lm
#include 
#include 
#include 
#include 

/***************** math ********************/

#define POS_OF_HIGHESTBITmath(a) /* 0th position is the Least-Signif-Bit */    \
  ((unsigned) log2(a))         /* thus: do not use if a <= 0 */  

#define NUM_OF_HIGHESTBITmath(a) ((a)               \
                  ? (1U << POS_OF_HIGHESTBITmath(a))    \
                  : 0)



/***************** clz ********************/

unsigned NUM_BITS_U = ((sizeof(unsigned) << 3) - 1);
#define POS_OF_HIGHESTBITclz(a) (NUM_BITS_U - __builtin_clz(a)) /* only works for a != 0 */

#define NUM_OF_HIGHESTBITclz(a) ((a)                    \
                 ? (1U << POS_OF_HIGHESTBITclz(a))  \
                 : 0)


/***************** i2f ********************/

double FF;
#define POS_OF_HIGHESTBITi2f(a) (FF = (double)(ui|1), ((*(1+(unsigned*)&FF))>>20)-1023)


#define NUM_OF_HIGHESTBITi2f(a) ((a)                    \
                 ? (1U << POS_OF_HIGHESTBITi2f(a))  \
                 : 0)




/***************** asm ********************/

unsigned OUT;
#define POS_OF_HIGHESTBITasm(a) (({asm("bsrl %1,%0" : "=r"(OUT) : "r"(a));}), OUT)

#define NUM_OF_HIGHESTBITasm(a) ((a)                    \
                 ? (1U << POS_OF_HIGHESTBITasm(a))  \
                 : 0)




/***************** bitshift1 ********************/

#define NUM_OF_HIGHESTBITbitshift1(a) (({   \
  OUT = a;                  \
  OUT |= (OUT >> 1);                \
  OUT |= (OUT >> 2);                \
  OUT |= (OUT >> 4);                \
  OUT |= (OUT >> 8);                \
  OUT |= (OUT >> 16);               \
      }), (OUT & ~(OUT >> 1)))          \



/***************** bitshift2 ********************/
int POS[32] = {0, 1, 28, 2, 29, 14, 24, 3,
             30, 22, 20, 15, 25, 17, 4, 8, 31, 27, 13, 23, 21, 19,
             16, 7, 26, 12, 18, 6, 11, 5, 10, 9};

#define POS_OF_HIGHESTBITbitshift2(a) (({   \
  OUT = a;                  \
  OUT |= OUT >> 1;              \
  OUT |= OUT >> 2;              \
  OUT |= OUT >> 4;              \
  OUT |= OUT >> 8;              \
  OUT |= OUT >> 16;             \
  OUT = (OUT >> 1) + 1;             \
      }), POS[(OUT * 0x077CB531UL) >> 27])

#define NUM_OF_HIGHESTBITbitshift2(a) ((a)              \
                       ? (1U << POS_OF_HIGHESTBITbitshift2(a)) \
                       : 0)



#define LOOPS 100000000U

int main()
{
  time_t start, end;
  unsigned ui;
  unsigned n;

  /********* Checking the first few unsigned values (you'll need to check all if you want to use an algorithm here) **************/
  printf("math\n");
  for (ui = 0U; ui < 18; ++ui)
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITmath(ui));

  printf("\n\n");

  printf("clz\n");
  for (ui = 0U; ui < 18U; ++ui)
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITclz(ui));

  printf("\n\n");

  printf("i2f\n");
  for (ui = 0U; ui < 18U; ++ui)
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITi2f(ui));

  printf("\n\n");

  printf("asm\n");
  for (ui = 0U; ui < 18U; ++ui) {
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITasm(ui));
  }

  printf("\n\n");

  printf("bitshift1\n");
  for (ui = 0U; ui < 18U; ++ui) {
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITbitshift1(ui));
  }

  printf("\n\n");

  printf("bitshift2\n");
  for (ui = 0U; ui < 18U; ++ui) {
    printf("%i\t%i\n", ui, NUM_OF_HIGHESTBITbitshift2(ui));
  }

  printf("\n\nPlease wait...\n\n");


  /************************* Simple clock() benchmark ******************/
  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITmath(ui);
  end = clock();
  printf("math:\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITclz(ui);
  end = clock();
  printf("clz:\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITi2f(ui);
  end = clock();
  printf("i2f:\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITasm(ui);
  end = clock();
  printf("asm:\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITbitshift1(ui);
  end = clock();
  printf("bitshift1:\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  start = clock();
  for (ui = 0; ui < LOOPS; ++ui)
    n = NUM_OF_HIGHESTBITbitshift2(ui);
  end = clock();
  printf("bitshift2\t%e\n", (double)(end-start)/CLOCKS_PER_SEC);

  printf("\nThe lower, the better. Take note that a negative exponent is good! ;)\n");

  return EXIT_SUCCESS;
}