#include <stdio.h>
#include "cln/cln.h"
using namespace cln;

typedef struct { unsigned long t[2]; } timing;
#define timing_now(x) asm volatile(".byte 15;.byte 49" : "=a"((x)->t[0]),"=d"((x)->t[1]))
#define timing_diff(x,y) (((x)->t[0] - (double) (y)->t[0]) + 4294967296.0 * ((x)->t[1] - (double) (y)->t[1]))

#define SIZES 88
#define TIMINGS 6

int b[SIZES] = {
  1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 14, 16, 20, 24, 28, 32, 40, 48, 56
, 64, 80, 96, 112, 128, 160, 192, 224, 256, 320, 384, 448, 512, 640, 768, 896
, 1024, 1280, 1536, 1792, 2048, 2560, 3072, 3584, 4096, 5120, 6144, 7168
, 8192, 10240, 12288, 14336, 16384, 20480, 24576, 28672
, 32768, 40960, 49152, 57344, 65536, 81920, 98304, 114688
, 131072, 163840, 196608, 229376, 262144, 327680, 393216, 458752
, 524288, 655360, 786432, 917504, 1048576, 1310720, 1572864, 1835008
, 2097152, 2621440, 3145728, 3670016, 4194304, 5242880, 6291456, 7340032
, 8388608
} ;

timing t[SIZES][TIMINGS + 2];

int main(void)
{
  cl_I x;
  cl_I y;
  cl_I z;
  int i;
  int j;

  for (i = 0;i < SIZES;++i) {
    x = 1;
    x = x << b[i];
    x = x - 1;
    y = x;

    timing_now(&t[i][0]);
    for (j = 0;j < TIMINGS;++j) {
      z = x * y;
      timing_now(&t[i][j + 1]);
    }
  }

  for (i = 0;i < SIZES;++i) {
    printf("%8d: ",b[i]);
    for (j = 0;j < TIMINGS;++j)
      printf("%10.0f ",timing_diff(&t[i][j + 1],&t[i][j]));
    printf("\n");
  }

  return 0;
}