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) 0.009 s (x 8 = 0.074 s), bandwidth = 27544.7 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     3.450786        593     102.8       0%        1.0
           2     1.726411       1186      51.5     100%        2.0
           3     1.222395       1675      36.4      88%        2.8
           4     0.912756       2244      27.2     101%        3.8
           5     0.721474       2839      21.5     105%        4.8
           6     0.603737       3392      18.0      98%        5.7
           7     0.513811       3986      15.3     104%        6.7
           8     0.462179       4431      13.8      80%        7.5
           9     0.416027       4923      12.4      90%        8.3
          10     0.366474       5588      10.9     119%        9.4
          11     0.333495       6141       9.9      99%       10.3
          12     0.307336       6664       9.2      94%       11.2
          13     0.285666       7169       8.5      92%       12.1
          14     0.267763       7649       8.0      88%       12.9
          15     0.254174       8057       7.6      76%       13.6
          16     0.238417       8590       7.1      99%       14.5
          17     0.225067       9100       6.7      95%       15.3
          18     0.214641       9542       6.4      83%       16.1
          19     0.204981       9991       6.1      86%       16.8
          20     0.195501      10476       5.8      92%       17.7
          21     0.187393      10929       5.6      87%       18.4
          22     0.180883      11322       5.4      76%       19.1
          23     0.172301      11886       5.1     109%       20.0
          24     0.167178      12250       5.0      71%       20.6
          25     0.163118      12555       4.9      61%       21.2
          26     0.161085      12714       4.8      32%       21.4
          27     0.159396      12848       4.8      28%       21.6
          28     0.158523      12919       4.7      15%       21.8
          29     0.155469      13173       4.6      56%       22.2
          30     0.154778      13232       4.6      13%       22.3
          31     0.154060      13294       4.6      14%       22.4
          32     0.154380      13266       4.6      -7%       22.4
          33     0.156021      13126       4.6     -35%       22.1
          34     0.154849      13226       4.6      26%       22.3
          35     0.155100      13204       4.6      -6%       22.2
          36     0.156893      13053       4.7     -42%       22.0
          37     0.156117      13118       4.7      18%       22.1
          38     0.155995      13129       4.6       3%       22.1
          39     0.156358      13098       4.7      -9%       22.1
          40     0.161008      12720       4.8    -119%       21.4
Maybe you have about 27 parallel paths? 
exit=0
