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.

    sort sortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0C++ g++ #7 27.2227.232841150  0% 1% 1% 100%
1.0C gcc #4 27.2627.273161183  0% 0% 1% 100%
1.4C gcc #5 37.8237.84340910  2% 2% 2% 100%
1.4Ada 2005 GNAT #3 39.2939.311,6242100  0% 1% 1% 100%
1.8C gcc #3 47.9847.99312567  0% 0% 1% 100%
1.8Rust #2 48.6248.646,9161180  1% 1% 0% 100%
1.8C++ g++ #5 49.9549.971,0361440  0% 0% 1% 100%
1.9C++ g++ #4 52.3852.393,0841439  0% 1% 1% 100%
2.0C gcc #2 54.7854.793481557  1% 1% 0% 100%
2.1C++ g++ #3 57.8657.87284593  1% 0% 0% 100%
2.1C gcc 57.8757.89316508  0% 0% 1% 100%
2.2Scala #2 59.0059.0125,1841017  1% 1% 0% 100%
2.2Lisp SBCL #5 59.0459.0522,576674  1% 0% 0% 100%
2.2Rust 60.0060.0231,496644  1% 0% 0% 100%
2.3Haskell GHC #3 62.2462.261,9881153  0% 0% 1% 100%
2.3Lisp SBCL #4 63.8563.8726,1881518  1% 1% 1% 100%
2.4C# Mono #2 64.4864.5018,616564  0% 1% 0% 100%
2.5Java  67.4867.5021,4481282  1% 1% 0% 100%
2.5Pascal Free Pascal 67.5467.576921018  1% 1% 0% 100%
2.5Fortran Intel 68.3068.32260590  0% 0% 0% 100%
2.5JavaScript V8 #3 68.8968.927,068539  1% 0% 0% 100%
2.6Lisp SBCL #3 69.4669.4817,736821  1% 1% 1% 100%
2.6Fortran Intel #3 69.6969.717,5801148  0% 0% 0% 100%
2.6OCaml #2 71.1071.12596473  0% 0% 0% 100%
2.6F# Mono #4 72.0872.1019,124612  0% 0% 0% 100%
2.8Haskell GHC #5 75.4275.441,976834  0% 0% 1% 100%
2.9JavaScript V8 #2 77.6477.677,060472  1% 0% 0% 100%
2.9Dart #2 77.6677.6814,788495  0% 1% 1% 100%
2.9Java  #2 78.0378.0519,996514  0% 1% 1% 100%
3.0Haskell GHC #4 82.4082.431,720658  0% 1% 0% 100%
3.2JavaScript V8 88.4688.499,068463  1% 1% 1% 100%
3.3C# Mono 88.8088.8318,624520  0% 1% 0% 100%
3.6Scala 97.6097.6322,360459  1% 0% 1% 100%
3.8F# Mono #2 102.17102.2020,688548  0% 1% 1% 100%
3.8Go 103.28103.32764900  0% 1% 1% 100%
3.9OCaml #3 0.00105.2618,6801017  0% 1% 0% 100%
4.2C# Mono #3 114.90114.9219,6241096  0% 1% 1% 100%
4.6F# Mono #3 125.08125.1122,688945  0% 1% 1% 100%
4.9OCaml 132.35132.39592524  0% 0% 0% 100%
4.9OCaml #4 0.00133.889,1361004  0% 0% 0% 100%
5.3Clojure #3 144.05144.1051,4761491  0% 1% 1% 100%
6.2F# Mono 167.89168.0021,524551  0% 1% 1% 100%
6.7Lisp SBCL #2 182.57182.6943,728513  0% 2% 1% 100%
9.3Haskell GHC #2 253.26253.363,284808  0% 1% 1% 100%
9.7Clojure #2 262.80262.9156,1361088  0% 1% 1% 100%
11Racket #2 5 min5 min16,856903  0% 1% 1% 100%
12Racket 5 min5 min15,368649  0% 0% 1% 100%
12Racket #3 5 min5 min17,1841096  0% 0% 1% 100%
14Erlang HiPE 6 min6 min10,1841038  1% 0% 0% 100%
16Haskell GHC 7 min7 min3,308553  0% 1% 1% 100%
22Smalltalk VisualWorks 10 min10 min21,952838  0% 0% 0% 100%
26Ruby JRuby 12 min12 min648,500384  0% 1% 1% 100%
69Ruby JRuby #2 31 min31 min638,7521426  0% 1% 1% 100%
78Lua 35 min35 min820462  0% 0% 0% 100%
89Perl 40 min40 min1,464457  0% 0% 0% 100%
94PHP #2 42 min42 min2,540441  0% 0% 0% 100%
98Python 3 #6 44 min44 min4,192385  0% 0% 0% 100%
101PHP #3 46 min46 min10,4121150  0% 0% 0% 100%
120PHP 54 min54 min2,572482  0% 0% 0% 100%
122Ruby 55 min55 min5,348384  0% 1% 1% 100%
392C CINT 2h 57 min2h 57 min5,116536  0% 0% 0% 100%
C++ g++ Failed1059
Perl #2 Failed565
Python 3 #2 Timed Out1h 00 min797
Python 3 Timed Out1h 00 min1108
Ruby #2 Timed Out1h 20 min1426
"wrong" (different) algorithm / less comparable programs
1.3C++ g++ #6 36.5036.51284894
1.7Java  #3 45.4345.4522,8681633
2.0Lisp SBCL 53.4453.4633,3401607
3.2C# Mono #4 86.3486.3618,880710
4.2C# Mono #5 114.29114.3221,0121400

 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