Ciro Santilli @cirosantilli 37

loop:
  inc %[i0];
  inc %[i1];
  inc %[i2];
  ...
  inc %[i_n];
  cmp %[max], %[i0];
  jb loop;

loop:
  inc %[i];
  cmp %[max], %[i];
  jb loop;

time ./inc_loop_asm.out 5000000000

11c8:       48 83 45 f0 01          addq   $0x1,-0x10(%rbp)
11cd:       48 8b 45 f0             mov    -0x10(%rbp),%rax
11d1:       48 3b 45 e8             cmp    -0x18(%rbp),%rax
11d5:       72 f1                   jb     11c8 <main+0x7f>

time ./inc_loop.out 2500000000

time ./inc_loop.out 2500000000

          1,052.22 msec task-clock                       #    0.998 CPUs utilized             
                23      context-switches                 #   21.858 /sec                      
                12      cpu-migrations                   #   11.404 /sec                      
                60      page-faults                      #   57.022 /sec                      
    10,015,198,766      instructions                     #    2.08  insn per cycle            
                                                  #    0.00  stalled cycles per insn   
     4,803,504,602      cycles                           #    4.565 GHz                       
        20,705,659      stalled-cycles-frontend          #    0.43% frontend cycles idle      
     2,503,079,267      branches                         #    2.379 G/sec                     
           396,228      branch-misses                    #    0.02% of all branches

    1078:       e8 d3 ff ff ff          call   1050 <strtoll@plt>
}
    107d:       5a                      pop    %rdx
    107e:       c3                      ret