Initializing array made of 33554432 64-bit words (256.00 MiB).
Source pages allocated with transparent hugepages: 100.0% (65536 pages, 100.0% flagged)
Legend:
  BandW: Implied bandwidth (assuming 64-byte cache line) in MB/s
  % Eff: Effectiness of this lane count compared to the prior, as a % of ideal
  Speedup: Speedup factor for this many lanes versus one lane
Applying Sattolo's algorithm... chain total: 33554432
Time to sum up the array (linear scan) 0.012 s (x 8 = 0.095 s), bandwidth = 21643.6 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     3.847337        532     114.7       0%        1.0
           2     1.835069       1116      54.7     105%        2.1
           3     1.187281       1725      35.4     106%        3.2
           4     0.835787       2450      24.9     118%        4.6
           5     0.653469       3134      19.5     109%        5.9
           6     0.548348       3735      16.3      97%        7.0
           7     0.456895       4482      13.6     117%        8.4
           8     0.401944       5095      12.0      96%        9.6
           9     0.358789       5708      10.7      97%       10.7
          10     0.320304       6394       9.5     107%       12.0
          11     0.291095       7036       8.7     100%       13.2
          12     0.272887       7505       8.1      75%       14.1
          13     0.256523       7984       7.6      78%       15.0
          14     0.245585       8339       7.3      60%       15.7
          15     0.231538       8845       6.9      86%       16.6
          16     0.222683       9197       6.6      61%       17.3
          17     0.207260       9881       6.2     118%       18.6
          18     0.200970      10191       6.0      55%       19.1
          19     0.193467      10586       5.8      71%       19.9
          20     0.184488      11101       5.5      93%       20.9
          21     0.180456      11349       5.4      46%       21.3
          22     0.173843      11781       5.2      81%       22.1
          23     0.168148      12180       5.0      75%       22.9
          24     0.166855      12274       5.0      18%       23.1
          25     0.164665      12437       4.9      33%       23.4
          26     0.159518      12839       4.8      81%       24.1
          27     0.156237      13108       4.7      56%       24.6
          28     0.156975      13047       4.7     -13%       24.5
          29     0.155981      13130       4.6      18%       24.7
          30     0.150187      13636       4.5     111%       25.6
          31     0.151892      13483       4.5     -35%       25.3
          32     0.147418      13893       4.4      94%       26.1
          33     0.146484      13981       4.4      21%       26.3
          34     0.144720      14151       4.3      41%       26.6
          35     0.142179      14404       4.2      61%       27.1
          36     0.134941      15177       4.0     183%       28.5
          37     0.133351      15358       4.0      44%       28.9
          38     0.135770      15084       4.0     -69%       28.3
          39     0.135047      15165       4.0      21%       28.5
          40     0.134382      15240       4.0      20%       28.6
Maybe you have about 23 parallel paths? 
exit=0
