fannkuch-redux benchmark N=12

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.

     sortsortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0OCaml #3 0.0116.2522,3081017  100% 100% 100% 100%
1.0OCaml #4 0.0116.4912,1601004  100% 100% 100% 100%
3,230C++ g++ #7 22.6122.627321150  100% 1% 0% 0%
3,235C gcc #4 22.6422.657521183  100% 0% 1% 1%
5,093C gcc #5 35.659.101,516910  99% 96% 97% 100%
6,405Ada 2005 GNAT #3 44.8311.274,1002100  100% 100% 99% 100%
6,657C# Mono #2 46.6046.6139,548564  0% 1% 100% 1%
7,416C++ g++ #4 51.9113.281,7841439  94% 99% 100% 98%
7,549C++ g++ #5 52.8413.511,8041440  100% 99% 93% 100%
7,763C gcc #3 54.3454.36800567  0% 0% 1% 100%
7,785C gcc #2 54.4913.948801557  95% 99% 99% 99%
7,963Fortran Intel #3 55.7413.9810,5361148  100% 100% 100% 100%
8,224Rust #2 57.5714.708,1281191  98% 100% 99% 94%
8,227Fortran Intel 57.5957.61516590  1% 0% 1% 100%
8,478Lisp SBCL #5 59.3559.3732,868674  1% 1% 0% 100%
8,507C++ g++ 59.5515.213,6961059  100% 94% 98% 100%
8,518Scala #2 59.6215.2336,8201017  99% 98% 98% 97%
9,087F# Mono #4 63.6163.6238,748612  100% 1% 1% 0%
9,277Lisp SBCL #4 64.9416.7332,1481518  99% 100% 98% 92%
9,328Go 65.2916.461,024900  100% 99% 99% 99%
9,747Haskell GHC #5 68.2317.368,080834  100% 99% 99% 96%
9,757C++ g++ #3 68.3068.32720593  0% 0% 100% 1%
9,806Java  68.6417.4133,0321282  98% 98% 99% 99%
10,050C# Mono 70.3570.3739,380520  100% 1% 0% 0%
10,108Java  #2 70.7670.7243,452514  1% 1% 0% 99%
10,584Lisp SBCL #3 74.0974.1123,696821  1% 100% 0% 0%
10,954Haskell GHC #4 76.6870.906,288658  86% 17% 3% 3%
10,962Clojure #3 76.7420.0574,4761491  96% 99% 94% 94%
11,933F# Mono #3 83.5322.5451,160945  88% 96% 91% 96%
12,027Dart #2 84.1983.6038,680495  1% 22% 78% 1%
12,277OCaml #2 85.9485.962,740473  1% 0% 0% 100%
12,469Pascal Free Pascal 87.2821.877521018  100% 100% 100% 100%
12,614C gcc 88.3088.32816508  0% 0% 100% 1%
13,178Scala 92.2492.2147,188459  1% 100% 1% 1%
13,731C# Mono #3 96.1224.5242,9281096  98% 98% 98% 99%
13,864F# Mono #2 97.0597.0743,192548  0% 0% 100% 1%
13,959OCaml 97.7297.74708524  1% 0% 100% 0%
22,717F# Mono 159.02159.2349,744551  1% 1% 85% 16%
26,844Clojure #2 187.9160.8191,2761252  79% 78% 76% 75%
27,253Lisp SBCL #2 190.77191.0481,520513  1% 1% 0% 100%
39,805Racket #2 278.63278.6220,164903  1% 22% 39% 41%
43,551Racket 5 min5 min20,504649  1% 0% 0% 100%
43,577Racket #3 5 min85.9626,5761096  86% 84% 86% 99%
67,248Erlang HiPE 7 min119.2920,3401038  100% 99% 98% 99%
75,660Haskell GHC #2 8 min165.247,740808  81% 81% 80% 81%
91,205Ruby JRuby 10 min10 min675,384384  11% 30% 47% 15%
110,310Haskell GHC 12 min9 min8,636553  39% 43% 26% 35%
111,319Erlang 12 min199.7121,2921038  99% 97% 94% 100%
179,367Hack 20 min20 min117,804532  13% 1% 0% 87%
185,205Ruby JRuby #2 21 min5 min684,4681426  90% 92% 99% 82%
283,128Python 3 #4 33 min8 min39,992944  99% 97% 100% 97%
328,235Perl #2 38 min9 min10,976565  100% 99% 100% 99%
339,230Python 3 #6 39 min39 min5,432385  95% 0% 0% 6%
358,677Ruby 41 min41 min7,260384  91% 9% 0% 2%
365,378Perl 42 min42 min1,872457  5% 18% 0% 78%
374,135PHP #2 43 min43 min3,304441  1% 38% 0% 62%
379,998PHP #3 44 min11 min15,1881150  100% 100% 100% 100%
392,739Hack #2 45 min45 min115,480440  20% 4% 1% 77%
444,298Ruby #2 51 min13 min28,5321426  97% 97% 98% 98%
458,590PHP 53 min53 min3,344482  1% 0% 0% 100%
Haskell GHC #3 Timed Out1h 00 min1153
Hack #3 Failed1150
"wrong" (different) algorithm / less comparable programs
5,395C++ g++ #6 37.7637.77752894
5,498C# Mono #4 38.4838.5039,552710
5,929Java  #3 41.5010.5633,4081633
6,085C# Mono #5 42.6011.0042,1641400
7,636Lisp SBCL 53.4513.5443,6281607
277,237Python 3 #3 1940.66490.6039,868773

 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