fannkuch-redux benchmark N=12

Each chart bar shows how many times more Code, one ↓ fannkuch-redux program used, compared to the program that used least Code.

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.

    sortsortsort 
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0Ruby 40 min40 min7,508384  0% 0% 0% 100%
1.0Ruby JRuby 12 min12 min632,076384  33% 21% 24% 24%
1.0Python 3 #6 38 min38 min5,428385  1% 0% 0% 100%
1.1PHP #2 48 min48 min3,256441  100% 0% 0% 0%
1.2Perl 43 min43 min1,864457  0% 0% 0% 100%
1.2Scala 88.7688.7023,636459  1% 1% 99% 0%
1.2OCaml #2 90.3990.42764473  93% 0% 0% 7%
1.3PHP 57 min57 min3,312482  3% 97% 0% 0%
1.3Dart #2 83.5182.7324,464495  1% 1% 0% 100%
1.3C gcc 63.1763.19392508  1% 1% 100% 0%
1.3Lisp SBCL #2 188.07188.3878,600513  49% 1% 1% 51%
1.3Java  #2 69.6169.5719,664514  0% 99% 1% 1%
1.4C# Mono 69.8969.9121,348520  0% 0% 100% 1%
1.4OCaml 106.38106.41764524  96% 0% 0% 4%
1.4Hack 16 min16 min55,344532  1% 0% 0% 100%
1.4F# Mono #2 84.3584.3821,244548  0% 1% 100% 0%
1.4F# Mono 144.24144.1324,672551  68% 18% 10% 5%
1.4Haskell GHC 12 min8 min3,948553  55% 28% 32% 25%
1.5C# Mono #2 48.9748.9819,568564  0% 1% 1% 100%
1.5Perl #2 35 min8 min8,720565  100% 99% 99% 99%
1.5C gcc #3 52.4452.47392567  1% 99% 1% 2%
1.5Fortran Intel 58.8258.84520590  0% 0% 0% 100%
1.5C++ g++ #3 59.1559.17360593  1% 100% 0% 0%
1.6F# Mono #4 63.7263.7420,372612  0% 0% 100% 0%
1.7Rust 71.7817.9939,844644  100% 100% 100% 100%
1.7Racket 297.55297.5218,840649  1% 41% 0% 59%
1.7Haskell GHC #4 71.1466.002,460658  3% 3% 3% 100%
1.8Lisp SBCL #5 59.4659.4834,456674  1% 0% 1% 100%
2.1Python 3 #2 59 min15 min40,096797  98% 97% 100% 97%
2.1Haskell GHC #2 8 min162.275,344808  83% 83% 83% 82%
2.1Lisp SBCL #3 74.1474.1723,504821  100% 0% 0% 1%
2.2Haskell GHC #5 63.3916.154,036834  99% 100% 100% 94%
2.3Go 67.1616.861,032900  100% 100% 100% 100%
2.4Racket #2 272.16272.1420,220903  0% 1% 100% 0%
2.5F# Mono #3 84.1522.3832,076945  92% 96% 93% 96%
2.6OCaml #4 0.0016.3011,2801004  100% 100% 100% 100%
2.6OCaml #3 0.0117.3621,3721017  100% 100% 100% 100%
2.6Scala #2 69.8917.7725,6401017  97% 98% 100% 98%
2.7Pascal Free Pascal 87.2821.877521018  100% 100% 100% 100%
2.7Erlang HiPE 8 min125.7312,8721038  99% 100% 97% 97%
2.7Erlang 13 min203.7611,7961038  100% 98% 100% 100%
2.8Clojure #2 166.4852.0762,9601088  80% 80% 79% 79%
2.9Racket #3 286.8072.7320,6761096  100% 95% 100% 100%
2.9C# Mono #3 87.6822.2922,9601096  97% 99% 98% 99%
2.9Python 3 1h 05 min16 min40,1001108  99% 100% 99% 100%
3.0Fortran Intel #3 51.2012.848,5641148  100% 100% 100% 100%
3.0PHP #3 56 min14 min14,9681150  99% 98% 99% 95%
3.0C++ g++ #7 22.6922.703601150  1% 0% 1% 100%
3.1C gcc #4 22.6622.673921183  0% 1% 100% 0%
3.3Java  70.0617.7319,7201282  99% 99% 98% 99%
3.7Ruby #2 52 min13 min31,5121426  98% 97% 97% 98%
3.7Ruby JRuby #2 30 min8 min650,4721426  98% 91% 94% 90%
3.7C++ g++ #4 53.5613.731,2641439  99% 100% 98% 94%
3.8C++ g++ #5 53.3313.631,2641440  100% 98% 99% 94%
3.9Clojure #3 82.0121.3359,1761491  99% 95% 96% 96%
4.0Lisp SBCL #4 65.1216.7534,0041518  98% 99% 100% 92%
4.1C gcc #2 55.4814.254281557  98% 96% 96% 100%
5.5Ada 2005 GNAT #3 38.259.611,9762100  100% 99% 100% 100%
C++ g++ Failed1059
Haskell GHC #3 Timed Out5 min1153
Hack #2 Timed Out1h 20 min440
Hack #3 Failed1150
"wrong" (different) algorithm / less comparable programs
1.8C# Mono #4 40.2440.2619,568710
2.3C++ g++ #6 37.8637.87364894
3.6C# Mono #5 46.8912.0024,8681400
4.2Lisp SBCL 52.3813.2843,6841607
4.3Java  #3 40.9810.4121,0321633

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

You can write your own program for this task and contribute to the benchmarks game by following these general instructions.

More specifically:

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