fannkuch-redux benchmark N=10

Each chart bar shows how many times slower, one ↓ fannkuch-redux program was, compared to the fastest program.

These are not the only programs that could be written. These are not the only compilers and interpreters. These are not the only programming languages.

Column × shows how many times more each program used compared to the benchmark program that used least.

    sort sortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0PyPy 2 2.820.89285,6001009  78% 75% 97% 72%
1.0PyPy 2 2.830.90288,1481009  82% 76% 76% 86%
1.1PyPy 2 2.860.9480,4041009  71% 72% 67% 96%
1.3PyPy 3 #2 3.161.1776,2001008  59% 59% 95% 59%
1.3PyPy 3 #2 3.201.1876,1401008  57% 60% 59% 97%
1.4PyPy 3 3.241.2277,8601271  60% 59% 63% 87%
1.4PyPy 3 #2 3.161.2375,1841008  58% 88% 58% 55%
1.4PyPy 3 #6 1.251.2564,420552  1% 0% 1% 99%
1.4PyPy 3 #6 1.271.2764,820552  6% 3% 99% 1%
1.5PyPy 3 3.281.2977,4401271  56% 89% 55% 54%
1.5PyPy 3 3.291.2977,3001271  55% 91% 55% 57%
1.5PyPy 3 #6 1.311.3164,920552  7% 0% 2% 90%
1.5PyPy 3 #3 3.801.3275,292894  92% 64% 64% 70%
1.5PyPy 3 #3 3.811.3375,056894  66% 63% 66% 94%
1.6PyPy 3 #3 3.851.3877,432894  69% 64% 97% 61%
1.6PyPy 3 #4 4.151.4279,2801069  66% 73% 89% 68%
1.6PyPy 3 #4 4.181.4375,3841069  65% 97% 65% 67%
1.6PyPy 3 #4 4.181.4577,5801069  66% 65% 68% 93%
3.0Cython 10.202.6653,6121027  96% 97% 94% 98%
3.0Cython 10.102.6654,4161027  95% 95% 92% 97%
3.0Nuitka #4 9.952.6760,7721069  97% 97% 94% 97%
3.0Nuitka #3 9.882.6760,268894  94% 96% 92% 95%
3.0Nuitka #4 10.002.6863,3641069  97% 93% 97% 94%
3.0Cython 10.162.6952,7681027  93% 94% 94% 97%
3.1Nuitka #3 9.972.7258,604894  90% 97% 92% 95%
3.1Pyston 10.352.73158,5601009  95% 93% 99% 94%
3.1Nuitka #3 9.932.7659,576894  92% 92% 94% 89%
3.1Nuitka #4 10.122.7859,6001069  92% 95% 92% 93%
3.2Pyston 10.382.83157,8721009  92% 89% 95% 91%
3.3Pyston 10.422.89157,5841009  87% 90% 89% 96%
3.7Python 3 #3 12.613.2955,084894  95% 96% 95% 98%
3.7Python 3 #3 12.563.3253,484894  98% 95% 95% 92%
3.8Python 3 #3 12.733.4153,488894  94% 93% 91% 96%
3.9Python 3 #4 13.023.4152,5761069  99% 94% 96% 95%
3.9Python 3 #4 13.013.4153,5721069  96% 96% 96% 95%
3.9Python 3 #4 13.063.4454,8561069  95% 96% 94% 97%
4.2Nuitka #2 14.113.6857,7921008  99% 97% 98% 97%
4.3Python development version #3 14.293.7649,848894  96% 95% 96% 92%
4.3Nuitka #2 13.913.7860,5081008  94% 94% 96% 93%
4.3Python development version #3 14.273.7851,924894  95% 94% 92% 97%
4.3Python development version #3 14.453.8151,844894  98% 95% 96% 92%
4.3Nuitka #2 14.063.8259,2881008  96% 95% 93% 93%
4.4Python development version #4 14.823.8649,7201069  98% 96% 97% 93%
4.4Python development version #4 14.763.8649,7761069  97% 96% 93% 98%
4.4Python development version #4 15.003.9151,8081069  94% 99% 95% 96%
4.7Python 2 15.914.1342,7081009  95% 97% 96% 98%
4.7Python 2 16.224.1642,2281009  99% 98% 95% 98%
4.9Python 2 16.654.3442,0441009  95% 96% 95% 97%
4.9Nuitka 16.414.3858,4041271  97% 94% 97% 95%
5.0Nuitka 16.424.4357,8641271  96% 95% 96% 92%
5.1Nuitka 16.754.5059,6481271  95% 95% 98% 92%
5.2Nuitka #6 4.574.5810,380552  100% 4% 3% 1%
5.5Nuitka #6 4.834.8310,496552  6% 72% 5% 33%
5.6Python 3 #2 18.654.9154,3761008  97% 94% 96% 95%
5.6Python 3 #2 18.544.9253,2841008  97% 96% 93% 95%
5.6Python 3 #2 18.994.9354,7601008  96% 97% 96% 99%
5.7Nuitka #6 5.015.0110,164552  3% 65% 2% 38%
6.2Python development version #2 21.025.5249,6961008  96% 97% 93% 95%
6.3Python 3 21.475.5655,2241271  96% 97% 96% 98%
6.3Python development version #2 21.555.6149,6761008  98% 96% 97% 94%
6.3Python 3 21.575.6153,4361271  98% 95% 97% 96%
6.3Python development version #2 21.705.6149,7201008  98% 94% 98% 96%
6.3Python 3 21.515.6252,8241271  97% 96% 94% 98%
6.7Python 3 #6 5.965.968,856552  0% 0% 0% 100%
6.8Python 3 #6 6.016.018,924552  14% 1% 87% 1%
6.8Python 3 #6 6.056.059,132552  0% 1% 100% 0%
7.4Python development version 25.536.5751,8801271  98% 97% 98% 96%
7.5Python development version 25.526.6051,8161271  97% 97% 95% 98%
7.8Python development version 26.616.9150,0361271  97% 95% 97% 96%
7.9Python development version #6 6.997.007,676552  0% 0% 100% 0%
7.9Python development version #6 7.027.027,660552  0% 33% 0% 67%
8.1Python development version #6 7.167.167,476552  100% 0% 0% 0%
9.3MicroPython #6 8.258.254,240552  0% 81% 0% 19%
9.3MicroPython #6 8.268.264,248552  0% 11% 0% 89%
9.4MicroPython #6 8.298.294,176552  100% 0% 0% 0%
missing benchmark programs
Jython No program
IronPython No program
Shedskin No program
Numba No program
Grumpy No program

 fannkuch-redux benchmark : Indexed-access to tiny integer-sequence

diff program output N = 7 with this output file to check your program is correct before contributing.

We are trying to show the performance of various programming language implementations - so we ask that contributed programs not only give the correct result, but also use the same algorithm to calculate that result.

For N = 7 programs should generate these permutations (40KB) - which, incidentally, seem to be in the same order as permutations generated by the Tompkins-Paige algorithm, see pages 150-151 Permutation Generation Methods Robert Sedgewick.

The fannkuch benchmark is defined by programs in Performing Lisp Analysis of the FANNKUCH Benchmark, Kenneth R. Anderson and Duane Rettig.

Each program should

The conjecture is that this maximum count is approximated by n*log(n) when n goes to infinity.

FANNKUCH is an abbreviation for the German word Pfannkuchen, or pancakes, in analogy to flipping pancakes.


Thanks to Oleg Mazurov for insisting on a checksum and providing this helpful description of the approach he took -

Revised BSD license

  Home   Conclusions   License   Play