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) 0.006 s (x 8 = 0.045 s), bandwidth = 45110.1 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     4.534684        452     135.1       0%        1.0
           2     2.232654        917      66.5     102%        2.0
           3     1.474070       1389      43.9     102%        3.1
           4     1.104949       1853      32.9     100%        4.1
           5     0.881732       2323      26.3     101%        5.1
           6     0.728902       2810      21.7     104%        6.2
           7     0.625460       3274      18.6      99%        7.3
           8     0.547770       3739      16.3      99%        8.3
           9     0.487073       4205      14.5     100%        9.3
          10     0.444066       4612      13.2      88%       10.2
          11     0.399504       5126      11.9     110%       11.4
          12     0.369881       5537      11.0      89%       12.3
          13     0.338841       6044      10.1     109%       13.4
          14     0.315058       6500       9.4      98%       14.4
          15     0.292715       6997       8.7     106%       15.5
          16     0.275265       7440       8.2      95%       16.5
          17     0.257701       7947       7.7     108%       17.6
          18     0.242718       8438       7.2     105%       18.7
          19     0.231536       8845       6.9      88%       19.6
          20     0.216397       9464       6.4     131%       21.0
          21     0.204814       9999       6.1     112%       22.1
          22     0.195535      10474       5.8     100%       23.2
          23     0.186761      10966       5.6     103%       24.3
          24     0.180244      11362       5.4      84%       25.2
          25     0.172941      11842       5.2     101%       26.2
          26     0.164326      12463       4.9     130%       27.6
          27     0.158772      12899       4.7      91%       28.6
          28     0.152748      13408       4.6     106%       29.7
          29     0.153780      13318       4.6     -20%       29.5
          30     0.148711      13772       4.4      99%       30.5
          31     0.144163      14206       4.3      95%       31.5
          32     0.141138      14511       4.2      67%       32.1
          33     0.136725      14979       4.1     103%       33.2
          34     0.133096      15387       4.0      90%       34.1
          35     0.130584      15683       3.9      66%       34.7
          36     0.127034      16122       3.8      98%       35.7
          37     0.124194      16490       3.7      83%       36.5
          38     0.121186      16900       3.6      92%       37.4
          39     0.118173      17330       3.5      97%       38.4
          40     0.116076      17644       3.5      71%       39.1
Maybe you have about 28 parallel paths? 
exit=0
