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 2.811.1682,7281009  98% 91% 69% 78%
1.1PyPy 3 3.161.2680,2041271  58% 91% 55% 57%
1.1PyPy 3 #6 1.261.2867,860552  98% 7% 1% 2%
1.1PyPy 2 2.891.2882,7761009  88% 85% 85% 77%
1.1PyPy 3 3.251.3280,1681271  56% 91% 56% 55%
1.1PyPy 3 #6 1.251.3368,012552  1% 98% 2% 2%
1.1PyPy 3 3.261.3380,5961271  55% 58% 55% 88%
1.2PyPy 3 #6 1.281.3568,144552  1% 98% 4% 4%
1.2PyPy 3 #2 3.261.3580,0681008  52% 56% 66% 82%
1.2PyPy 2 2.951.3682,6841009  77% 80% 98% 85%
1.2PyPy 3 #2 3.281.3679,1361008  52% 56% 95% 50%
1.2PyPy 3 #4 4.161.4480,6481069  96% 71% 67% 66%
1.3PyPy 3 #2 3.331.5180,3441008  80% 52% 61% 48%
1.3PyPy 3 #4 4.231.5581,0761069  63% 68% 62% 90%
1.4PyPy 3 #4 4.291.6380,8281069  64% 90% 58% 63%
1.6PyPy 3 #3 4.331.8279,936894  82% 83% 95% 78%
1.7PyPy 3 #3 4.512.0179,504894  78% 78% 87% 95%
2.0PyPy 3 #3 4.492.2979,508894  97% 79% 82% 77%
2.3Pyston 10.352.73158,5601009  95% 93% 99% 94%
2.4Pyston 10.382.83157,8721009  92% 89% 95% 91%
2.5Nuitka #4 10.962.8658,2841069  98% 93% 98% 96%
2.5Nuitka #4 10.922.8756,9041069  96% 97% 98% 93%
2.5Nuitka #3 10.732.8755,688894  96% 93% 96% 91%
2.5Graal #6 3.332.88422,792552  8% 1% 15% 95%
2.5Pyston 10.422.89157,5841009  87% 90% 89% 96%
2.5Graal #6 3.342.89421,480552  14% 95% 8% 1%
2.5Nuitka #3 10.862.9156,888894  95% 90% 97% 93%
2.5Graal #6 3.372.92423,180552  61% 15% 30% 16%
2.5Nuitka #3 10.872.9457,452894  90% 97% 93% 93%
2.6Nuitka #4 11.072.9857,4161069  93% 95% 92% 95%
3.0Python 3 #3 12.963.4653,456894  98% 97% 98% 90%
3.0Python development version #3 13.233.5047,140894  98% 98% 92% 99%
3.0Python 3 #3 13.123.5053,336894  99% 97% 97% 91%
3.0Python development version #3 13.263.5146,752894  99% 95% 96% 97%
3.0Python development version #3 13.363.5346,800894  98% 98% 93% 99%
3.1Python 3 #3 13.143.5753,624894  93% 98% 92% 94%
3.1Python development version #4 13.623.5947,3441069  98% 99% 92% 99%
3.1Python development version #4 13.813.6046,6641069  98% 99% 96% 99%
3.1Python development version #4 13.893.6447,1441069  97% 100% 96% 99%
3.2Python 3 #4 13.813.6653,6561069  98% 98% 99% 91%
3.2Nuitka #2 14.013.6758,3881008  98% 94% 97% 96%
3.2Nuitka #2 13.843.6858,2761008  95% 95% 92% 97%
3.2Nuitka #2 14.323.7155,7281008  97% 100% 95% 97%
3.2Python 3 #4 13.913.7153,3721069  99% 96% 96% 91%
3.2Python 3 #4 14.053.7753,3481069  97% 96% 97% 91%
3.7Nuitka 16.564.2758,1361271  97% 98% 97% 99%
3.8Python 2 16.554.3741,9321009  97% 98% 96% 96%
3.8Python 2 16.304.3743,2921009  96% 95% 94% 95%
3.8Nuitka 16.584.3857,1281271  97% 93% 97% 95%
3.8Nuitka 16.794.4155,0401271  99% 96% 96% 94%
4.0Python 2 17.084.6543,6201009  97% 96% 98% 97%
4.2Python development version #2 18.364.8547,0001008  96% 99% 98% 95%
4.2Python development version #2 18.714.8646,5001008  99% 99% 99% 99%
4.2Nuitka #6 4.874.889,884552  100% 0% 1% 1%
4.2Nuitka #6 4.934.939,632552  1% 1% 100% 1%
4.3Python development version #2 18.554.9547,0241008  96% 98% 97% 94%
4.6Python 3 #2 20.205.3753,3201008  95% 98% 96% 99%
4.7Python 3 #2 20.085.4153,6321008  98% 99% 97% 94%
4.7Python 3 #2 20.145.4553,5321008  95% 95% 94% 97%
4.9Python development version 21.665.6647,5281271  99% 98% 96% 99%
4.9Python development version 21.515.7046,8321271  97% 99% 97% 93%
4.9Python development version 21.485.7046,9361271  96% 99% 97% 94%
5.3Python development version #6 6.106.117,832552  6% 1% 1% 100%
5.3Python development version #6 6.166.167,788552  5% 1% 100% 1%
5.4Python development version #6 6.196.257,960552  26% 1% 78% 1%
5.4Python 3 24.086.3253,7641271  97% 97% 99% 97%
5.4Python 3 24.136.3253,8881271  99% 98% 97% 97%
5.5Python 3 24.216.3853,5321271  97% 97% 96% 98%
5.9Python 3 #6 6.766.808,448552  5% 10% 100% 5%
6.1Python 3 #6 7.007.098,384552  9% 38% 10% 74%
6.7Python 3 #6 7.517.738,648552  35% 51% 25% 49%
7.2MicroPython #6 8.348.354,164552  1% 7% 100% 2%
7.4MicroPython #6 8.358.574,184552  31% 61% 1% 14%
7.4MicroPython #6 8.368.644,236552  1% 77% 2% 27%
13Nuitka #6 14.5314.549,888552  1% 100% 1% 1%
missing benchmark programs
Jython No program
IronPython No program
Cython 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