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) 0.021 s (x 8 = 0.166 s), bandwidth = 12326.1 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     3.093943        662      92.2       0%        1.0
           2     1.554470       1317      46.3     100%        2.0
           3     1.040782       1968      31.0      99%        3.0
           4     0.779115       2629      23.2     101%        4.0
           5     0.631210       3245      18.8      95%        4.9
           6     0.523727       3910      15.6     102%        5.9
           7     0.455645       4495      13.6      91%        6.8
           8     0.400314       5116      11.9      97%        7.7
           9     0.361432       5666      10.8      87%        8.6
          10     0.327872       6246       9.8      93%        9.4
          11     0.310236       6601       9.2      59%       10.0
          12     0.302153       6778       9.0      31%       10.2
          13     0.296886       6898       8.8      23%       10.4
          14     0.300561       6814       9.0     -17%       10.3
          15     0.298783       6854       8.9       9%       10.4
          16     0.295965       6920       8.8      15%       10.5
          17     0.295957       6920       8.8       0%       10.5
          18     0.295685       6926       8.8       2%       10.5
          19     0.297067       6894       8.9      -9%       10.4
          20     0.298885       6852       8.9     -12%       10.4
          21     0.298224       6867       8.9       5%       10.4
          22     0.301410       6795       9.0     -24%       10.3
          23     0.305871       6696       9.1     -34%       10.1
          24     0.300967       6805       9.0      38%       10.3
          25     0.301411       6795       9.0      -4%       10.3
          26     0.302884       6762       9.0     -13%       10.2
          27     0.300980       6804       9.0      17%       10.3
          28     0.305514       6703       9.1     -42%       10.1
          29     0.303703       6743       9.1      17%       10.2
          30     0.305011       6715       9.1     -13%       10.1
          31     0.304029       6736       9.1      10%       10.2
          32     0.303233       6754       9.0       8%       10.2
          33     0.307488       6660       9.2     -46%       10.1
          34     0.303516       6748       9.0      44%       10.2
          35     0.303163       6755       9.0       4%       10.2
          36     0.304231       6732       9.1     -13%       10.2
          37     0.304109       6734       9.1       1%       10.2
          38     0.305594       6702       9.1     -19%       10.1
          39     0.306664       6678       9.1     -14%       10.1
          40     0.305170       6711       9.1      19%       10.1
Maybe you have about 13 parallel paths? 
exit=0
