perf stat bin/prototype
598.867

 Performance counter stats for 'bin/prototype':

      12965,118733 task-clock                #    7,779 CPUs utilized          
            10.973 context-switches          #    0,846 K/sec                  
             1.045 CPU-migrations            #    0,081 K/sec                  
           284.210 page-faults               #    0,022 M/sec                  
    17.266.521.878 cycles                    #    1,332 GHz                     [82,84%]
    15.286.104.871 stalled-cycles-frontend   #   88,53% frontend cycles idle    [82,84%]
    10.719.958.132 stalled-cycles-backend    #   62,09% backend  cycles idle    [67,65%]
     3.744.397.009 instructions              #    0,22  insns per cycle        
                                             #    4,08  stalled cycles per insn [84,40%]
       745.386.453 branches                  #   57,492 M/sec                   [83,50%]
        26.058.804 branch-misses             #    3,50% of all branches         [83,33%]

       1,666595682 seconds time elapsed


perf stat numactl --cpunodebind=0 bin/prototype
272.614

 Performance counter stats for 'numactl --cpunodebind=0 bin/prototype':

       3887,450198 task-clock                #    3,345 CPUs utilized          
             2.360 context-switches          #    0,607 K/sec                  
               208 CPU-migrations            #    0,054 K/sec                  
           282.794 page-faults               #    0,073 M/sec                  
     8.472.475.622 cycles                    #    2,179 GHz                     [83,66%]
     7.405.805.964 stalled-cycles-frontend   #   87,41% frontend cycles idle    [83,80%]
     6.380.684.207 stalled-cycles-backend    #   75,31% backend  cycles idle    [66,90%]
     2.170.702.546 instructions              #    0,26  insns per cycle        
                                             #    3,41  stalled cycles per insn [85,07%]
       430.561.957 branches                  #  110,757 M/sec                   [82,72%]
        16.758.653 branch-misses             #    3,89% of all branches         [83,06%]

       1,162185180 seconds time elapsed

perf stat numactl --cpunodebind=0-1 bin/prototype
356.726

 Performance counter stats for 'numactl --cpunodebind=0-1 bin/prototype':

       6127,077466 task-clock                #    4,648 CPUs utilized          
             4.926 context-switches          #    0,804 K/sec                  
               469 CPU-migrations            #    0,077 K/sec                  
           283.291 page-faults               #    0,046 M/sec                  
    10.217.787.787 cycles                    #    1,668 GHz                     [82,26%]
     8.944.310.671 stalled-cycles-frontend   #   87,54% frontend cycles idle    [82,54%]
     7.077.541.651 stalled-cycles-backend    #   69,27% backend  cycles idle    [68,59%]
     2.394.846.569 instructions              #    0,23  insns per cycle        
                                             #    3,73  stalled cycles per insn [84,96%]
       471.191.796 branches                  #   76,903 M/sec                   [83,73%]
        19.007.439 branch-misses             #    4,03% of all branches         [83,03%]

       1,318087487 seconds time elapsed

perf stat numactl --cpunodebind=0-2 bin/protoype
472.794

 Performance counter stats for 'numactl --cpunodebind=0-2 bin/prototype':

       9671,244269 task-clock                #    6,490 CPUs utilized          
             7.698 context-switches          #    0,796 K/sec                  
               716 CPU-migrations            #    0,074 K/sec                  
           283.933 page-faults               #    0,029 M/sec                  
    14.050.655.421 cycles                    #    1,453 GHz                     [83,16%]
    12.498.787.039 stalled-cycles-frontend   #   88,96% frontend cycles idle    [83,08%]
     9.386.588.858 stalled-cycles-backend    #   66,81% backend  cycles idle    [66,25%]
     2.834.408.038 instructions              #    0,20  insns per cycle        
                                             #    4,41  stalled cycles per insn [83,44%]
       570.440.458 branches                  #   58,983 M/sec                   [83,72%]
        22.158.938 branch-misses             #    3,88% of all branches         [83,92%]

       1,490160954 seconds time elapsed