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) 0.023 s (x 8 = 0.188 s), bandwidth = 10922.0 MB/s 
Size: 33554432 (262144.00 KiB, 256.00 MiB)
---------------------------------------------------------------------
- # of lanes --- time (s) ---- BandW -- ns/hit -- % Eff -- Speedup --
---------------------------------------------------------------------
           1     3.184210        643      94.9       0%        1.0
           2     1.618242       1266      48.2      98%        2.0
           3     1.125176       1820      33.5      91%        2.8
           4     0.855845       2393      25.5      96%        3.7
           5     0.696433       2941      20.8      93%        4.6
           6     0.637959       3210      19.0      50%        5.0
           7     0.649474       3153      19.4     -13%        4.9
           8     0.634892       3226      18.9      18%        5.0
           9     0.643230       3184      19.2     -12%        5.0
          10     0.643963       3180      19.2      -1%        4.9
          11     0.630192       3250      18.8      24%        5.1
          12     0.631658       3242      18.8      -3%        5.0
          13     0.635279       3224      18.9      -7%        5.0
          14     0.638498       3208      19.0      -7%        5.0
          15     0.634198       3229      18.9      10%        5.0
          16     0.643484       3183      19.2     -23%        4.9
          17     0.633925       3231      18.9      25%        5.0
          18     0.632466       3238      18.8       4%        5.0
          19     0.632879       3236      18.9      -1%        5.0
          20     0.627748       3262      18.7      16%        5.1
          21     0.630012       3251      18.8      -8%        5.1
          22     0.631560       3243      18.8      -5%        5.0
          23     0.635295       3224      18.9     -14%        5.0
          24     0.627038       3266      18.7      31%        5.1
          25     0.627863       3262      18.7      -3%        5.1
          26     0.626118       3271      18.7       7%        5.1
          27     0.631676       3242      18.8     -24%        5.0
          28     0.632479       3238      18.8      -4%        5.0
          29     0.629175       3255      18.8      15%        5.1
          30     0.627921       3262      18.7       6%        5.1
          31     0.625978       3272      18.7      10%        5.1
          32     0.625337       3275      18.6       3%        5.1
          33     0.636266       3219      19.0     -58%        5.0
          34     0.626298       3270      18.7      53%        5.1
          35     0.616817       3320      18.4      53%        5.2
          36     0.619228       3307      18.5     -14%        5.1
          37     0.618333       3312      18.4       5%        5.1
          38     0.617779       3315      18.4       3%        5.2
          39     0.615863       3325      18.4      12%        5.2
          40     0.624305       3280      18.6     -55%        5.1
Maybe you have about 6 parallel paths? 
exit=0
