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 #4 0.0065.0211,4161004  0% 0% 0% 100%
1.0OCaml #3 0.0069.3021,4001017  0% 0% 0% 100%
5,665C++ g++ #7 22.6622.673601150  1% 1% 0% 100%
5,677C gcc #4 22.7122.723961183  1% 0% 0% 100%
8,643C gcc #5 34.5734.58424910  0% 0% 0% 100%
9,567Ada 2005 GNAT #3 38.2738.301,9602100  1% 0% 1% 100%
12,241C# Mono #2 48.9748.9819,564564  1% 1% 0% 100%
12,243Fortran Intel #3 48.9748.997,5961148  0% 0% 0% 100%
12,625Rust 50.5050.526,9601162  0% 1% 1% 100%
13,108C gcc #3 52.4352.45396567  1% 0% 0% 100%
13,322C++ g++ #5 53.2953.311,2721440  1% 1% 0% 100%
13,388C++ g++ #4 53.5553.571,2721439  1% 1% 1% 100%
13,863C gcc #2 55.4555.474241557  0% 1% 1% 100%
13,946Scala #2 55.7855.8030,9241017  1% 1% 1% 100%
14,405Fortran Intel 57.6257.64244590  0% 0% 0% 100%
14,544Lisp SBCL #5 58.1858.1932,160674  1% 0% 0% 100%
14,764C++ g++ #3 59.0659.08364593  1% 0% 0% 100%
15,779C gcc 63.1263.14392508  1% 0% 1% 100%
15,930F# Mono #4 63.7263.7420,380612  1% 0% 0% 100%
16,318Go 65.2765.291,024900  0% 0% 1% 100%
16,479Lisp SBCL #4 65.9265.9331,6481518  1% 0% 0% 100%
17,467Java  69.8769.8841,3361282  0% 0% 0% 100%
17,471C# Mono 69.8869.9119,304520  1% 0% 1% 100%
17,546Haskell GHC #5 70.1870.212,340834  1% 1% 1% 100%
17,566Clojure #3 70.2670.2978,5961491  1% 1% 0% 100%
17,720Haskell GHC #4 70.8870.902,096658  1% 1% 0% 100%
18,286Java  #2 73.1473.1623,852514  1% 0% 0% 100%
18,447Lisp SBCL #3 73.7973.8023,212821  1% 0% 0% 100%
18,790JavaScript V8 #3 75.1675.188,280539  1% 0% 0% 100%
19,456JavaScript V8 #2 77.8277.848,252472  1% 0% 0% 100%
20,231Dart #2 80.9280.9523,828495  1% 0% 0% 100%
21,028F# Mono #3 84.1184.1431,048945  0% 1% 1% 100%
21,086F# Mono #2 84.3484.3721,228548  1% 0% 0% 100%
21,819Pascal Free Pascal 87.2887.317521018  1% 0% 0% 100%
21,936C# Mono #3 87.7487.7720,9961096  0% 0% 1% 100%
22,596OCaml #2 90.3890.41760473  0% 0% 0% 100%
22,794JavaScript V8 91.1791.208,240463  1% 0% 1% 100%
22,890Scala 91.5691.5925,728459  1% 0% 0% 100%
26,593OCaml 106.37106.41764524  0% 0% 0% 100%
36,033F# Mono 144.13144.2925,140551  0% 1% 1% 100%
39,095Clojure #2 156.38156.4969,2401088  1% 1% 0% 100%
48,127Lisp SBCL #2 192.51192.7678,428513  0% 1% 1% 100%
62,111Haskell GHC #2 248.45248.543,536808  1% 1% 0% 100%
68,001Racket #2 272.01272.0820,224903  0% 0% 1% 100%
74,017Racket #3 296.07296.1420,8041096  0% 1% 1% 100%
74,349Racket 297.40297.4818,820649  0% 0% 1% 100%
114,105Erlang HiPE 7 min7 min13,3281038  1% 0% 0% 100%
119,170Haskell GHC 7 min7 min3,492553  0% 0% 1% 100%
170,118Ruby JRuby 11 min11 min679,112384  1% 0% 0% 100%
172,557Smalltalk VisualWorks 11 min11 min42,580838  0% 0% 0% 100%
252,076Hack 16 min16 min74,064532  0% 0% 0% 100%
270,783Ruby JRuby #2 18 min18 min682,2241426  0% 1% 1% 100%
446,611Lua 29 min29 min1,008462  1% 1% 1% 100%
535,409Hack #2 35 min35 min74,064440  1% 0% 0% 100%
571,856Perl 38 min38 min1,836457  0% 0% 0% 100%
583,250Python 3 #6 38 min38 min5,416385  1% 0% 0% 100%
647,793Ruby 43 min43 min7,416384  0% 1% 0% 100%
739,698PHP #2 49 min49 min3,264441  0% 0% 0% 100%
754,670PHP #3 50 min50 min15,5601150  0% 0% 0% 100%
794,245Ruby #2 52 min52 min30,5081426  1% 0% 1% 100%
839,370PHP 55 min55 min3,316482  0% 0% 0% 100%
887,901Python 3 #2 59 min59 min40,080797  0% 0% 1% 100%
C++ g++ Failed1059
Haskell GHC #3 Timed Out1h 00 min1153
Hack #3 Failed1150
Perl #2 Failed565
Python 3 Timed Out1h 00 min1108
"wrong" (different) algorithm / less comparable programs
9,466C++ g++ #6 37.8637.88364894
10,061C# Mono #4 40.2440.2621,608710
11,244Java  #3 44.9844.9940,3801633
11,413C# Mono #5 45.6545.6724,9841400
13,091Lisp SBCL 52.3652.3845,2161607

 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