fannkuch-redux benchmark N=12

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

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.

    sortsort sort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0C++ g++ #3 57.9157.93284593  1% 0% 0% 100%
1.0C++ g++ #7 27.2727.282841150  0% 100% 0% 1%
1.1C gcc #3 47.9847.99316567  0% 100% 1% 1%
1.1C gcc 57.8857.90316508  0% 100% 1% 1%
1.1C gcc #4 27.2627.273161183  0% 0% 1% 100%
1.2C gcc #5 38.269.75340910  100% 99% 99% 95%
1.2C gcc #2 54.7714.243441557  91% 98% 100% 96%
1.8Fortran Intel 66.4266.43520590  0% 1% 1% 100%
2.1OCaml #2 83.3483.36604473  0% 1% 1% 100%
2.1OCaml 154.52154.55604524  1% 1% 1% 100%
2.5Pascal Free Pascal 67.5416.936961018  100% 100% 100% 100%
2.7Go 103.1825.97760900  99% 99% 100% 100%
3.6C++ g++ #4 52.4813.371,0361439  100% 100% 99% 95%
3.6C++ g++ #5 50.0312.881,0361440  99% 99% 100% 99%
5.8Ada 2005 GNAT #3 39.299.871,6562100  100% 100% 100% 100%
6.2Perl 46 min46 min1,768457  21% 0% 79% 1%
9.0PHP #2 40 min40 min2,556441  99% 1% 1% 2%
9.1PHP 53 min53 min2,588482  0% 1% 1% 100%
12Haskell GHC #3 54.3613.893,4241153  98% 98% 100% 95%
13Haskell GHC #5 80.2520.473,712834  98% 99% 95% 100%
15Python 3 #6 45 min45 min4,180385  0% 100% 1% 1%
18Haskell GHC #2 7 min143.655,020808  75% 76% 75% 75%
18Ruby 47 min47 min5,172384  97% 1% 4% 0%
33OCaml #4 0.0133.609,4281004  100% 100% 100% 100%
34Haskell GHC 10 min8 min9,592553  25% 44% 18% 42%
36Haskell GHC #4 89.3686.6210,088658  2% 1% 1% 100%
37PHP #3 41 min10 min10,5161150  100% 99% 99% 100%
39Rust 45.7511.6910,9601188  95% 98% 100% 99%
44Perl #2 39 min9 min12,380565  100% 100% 99% 99%
44Fortran Intel #3 75.1818.8512,4641148  100% 100% 100% 100%
46Erlang HiPE 6 min102.5312,9441038  100% 98% 98% 100%
59Racket 5 min5 min16,876649  0% 26% 1% 75%
60Lisp SBCL #3 68.5768.5917,068821  1% 0% 1% 100%
65Racket #3 5 min83.6318,3761096  97% 99% 98% 100%
65Ruby #2 1h 13 min18 min18,5281426  98% 96% 100% 97%
66C# Mono #2 64.4964.5118,616564  1% 0% 100% 0%
66C# Mono 88.8288.8418,624520  0% 100% 1% 0%
67OCaml #3 0.0127.0818,9601017  100% 100% 100% 100%
67F# Mono #4 72.0872.1119,124612  0% 1% 100% 1%
70C# Mono #3 114.9829.2819,7881096  99% 99% 98% 98%
70Java  64.3816.3319,9081282  98% 100% 98% 99%
71Java  #2 75.3675.3220,052514  1% 1% 100% 0%
73Dart #2 76.6076.0120,856495  0% 2% 2% 100%
74F# Mono #2 102.17102.2020,968548  0% 100% 0% 1%
77Lisp SBCL #5 62.3462.3621,860674  0% 0% 100% 0%
79Scala 100.0099.9422,296459  1% 99% 0% 1%
79Racket #2 5 min5 min22,432903  0% 1% 100% 0%
81Scala #2 60.3615.4223,1041017  98% 97% 98% 98%
82F# Mono #3 125.0432.7623,212945  93% 98% 95% 97%
83F# Mono 168.29168.2423,536551  1% 51% 50% 1%
90Lisp SBCL #4 61.3815.7925,4961518  95% 98% 98% 99%
99Python 3 #4 43 min10 min28,068944  100% 99% 98% 98%
145Lisp SBCL #2 159.13159.2141,084513  1% 0% 100% 1%
188Clojure #3 144.5937.0253,3361491  97% 98% 99% 97%
200Clojure #2 258.8076.9156,9041088  85% 85% 83% 83%
2,320Ruby JRuby 50 min50 min658,916384  32% 20% 19% 32%
2,763Ruby JRuby #2 46 min13 min784,8201426  95% 89% 88% 90%
C++ g++ Failed1059
Rust #2 Make Error1102
"wrong" (different) algorithm / less comparable programs
1.0C++ g++ #6 36.5036.52284894
66C# Mono #4 86.1686.1718,884710
74C# Mono #5 113.5828.8921,0721400
80Java  #3 46.2911.7622,5801633
99Python 3 #3 2286.85578.4928,040773
114Lisp SBCL 53.3413.4932,3641607

 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