Machine A: Laptop, Intel(R) Pentium(R) M processor 1.86GHz
Machine B: Desktop, Intel(R) Core(TM)2 Quad CPU    Q6600  @ 2.40GHz

all times in milliseconds

SL(100,2):  10 runs:
  A: 4584,3316,5240,3013,2572,4500,2544,7905,5688,2748
  B: 1808,4548,1308,3349,1852,2744,1712,4744,2348,1416
SL(100,4):  10 runs:
  A: 27530,12753,16661,16369,14885,11044,11897,23970,21993,28026
  B: 27114,6900,16873,11565,6164,13357,8741,6408,21101,9057
SL(100,8):  10 runs:
  A: 27802,57623,39215,85445,33750,119124,40790,24014,37310,46519
  B: 24925,27298,17825,38074,42075,63512,33738,45231,34890,12765
SL(50,256): 1 run:
  A: 120659
  B: 58636

New method:

SL(100,2): 10 runs:
  A: [ 3420, 3612, 6529, 5948, 2704, 4324, 6613, 3556, 3640, 5501 ]
  B: [ 2232, 2092, 4772, 1528, 2284, 3241, 4196, 2196, 1696, 1636 ]
SL(100,4): 10 runs:
  A: [ 15677, 11096, 12121, 15105, 10761, 12661, 18381, 19057, 11733, 15153 ]
  B: [ 7889, 5536, 7536, 8961, 5660, 5469, 5672, 7369, 8780, 6140 ]
SL(100,8): 10 runs:
  A: [ 26837, 23470, 27941, 20406, 38562, 20761, 19494, 27317, 20410, 23669 ]
  B: [ 11213, 9881, 11913, 11032, 11005, 11717, 11424, 11013, 8937, 8892 ]
SL(100,16): 10 runs:
  A: [ 23266, 25425, 22482, 24993, 27406, 26886, 26349, 24250, 25265, 25770 ]
  B: [ 12133, 12433, 13905, 13416, 10073, 12477, 10837, 15412, 17078, 19137 ]
SL(100,256): 10 runs:
  A: [ 51439, 61704, 47263, 51399, 86158, 51463, 47019, 47623, 54291, 45715 ]
  B: [ 22837, 24706, 19085, 20801, 20025, 26490, 26886, 22577, 22074, 27057 ]


Average runtimes:

                2       4       8       16      256
before A     4211   18513   51159        -   120659
before B     2583   12728   34033        -    58636
after A      4585   14175   24887    25209    54407
after B      2587    6901   10703    13690    23254
