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) 0.018 s (x 8 = 0.144 s), bandwidth = 14237.2 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     3.509051        584     104.6       0%        1.0
           2     1.765061       1160      52.6      99%        2.0
           3     1.176130       1741      35.1     100%        3.0
           4     0.891754       2297      26.6      97%        3.9
           5     0.719699       2846      21.4      96%        4.9
           6     0.603592       3393      18.0      97%        5.8
           7     0.515945       3969      15.4     102%        6.8
           8     0.446582       4586      13.3     108%        7.9
           9     0.398066       5145      11.9      98%        8.8
          10     0.356911       5738      10.6     103%        9.8
          11     0.325339       6295       9.7      97%       10.8
          12     0.298360       6864       8.9     100%       11.8
          13     0.279717       7322       8.3      81%       12.5
          14     0.262869       7791       7.8      84%       13.3
          15     0.247690       8268       7.4      87%       14.2
          16     0.238053       8603       7.1      62%       14.7
          17     0.223796       9151       6.7     102%       15.7
          18     0.221032       9266       6.6      22%       15.9
          19     0.213539       9591       6.4      64%       16.4
          20     0.205776       9953       6.1      73%       17.1
          21     0.200336      10223       6.0      56%       17.5
          22     0.198964      10293       5.9      15%       17.6
          23     0.193467      10586       5.8      64%       18.1
          24     0.190807      10733       5.7      33%       18.4
          25     0.188268      10878       5.6      33%       18.6
          26     0.185359      11049       5.5      40%       18.9
          27     0.184376      11108       5.5      14%       19.0
          28     0.181203      11302       5.4      48%       19.4
          29     0.180468      11348       5.4      12%       19.4
          30     0.179651      11400       5.4      14%       19.5
          31     0.176721      11589       5.3      51%       19.9
          32     0.176163      11626       5.3      10%       19.9
          33     0.173576      11799       5.2      48%       20.2
          34     0.173546      11801       5.2       1%       20.2
          35     0.172466      11875       5.1      22%       20.3
          36     0.172304      11886       5.1       3%       20.4
          37     0.171312      11955       5.1      21%       20.5
          38     0.172330      11884       5.1     -23%       20.4
          39     0.170885      11985       5.1      33%       20.5
          40     0.172028      11905       5.1     -27%       20.4
Maybe you have about 21 parallel paths? 
exit=0
