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 gcc #5 38.269.75340910  100% 99% 99% 95%
1.0Ada 2005 GNAT #3 39.299.871,6562100  100% 100% 100% 100%
1.3C++ g++ #5 50.0312.881,0361440  99% 99% 100% 99%
1.4Rust 52.0613.2910,9321191  99% 98% 100% 95%
1.4C++ g++ #4 52.4813.371,0361439  100% 100% 99% 95%
1.4Haskell GHC #3 54.3613.893,4241153  98% 98% 100% 95%
1.5C gcc #2 54.7714.243441557  91% 98% 100% 96%
1.6Scala #2 60.3615.4223,1041017  98% 97% 98% 98%
1.7Lisp SBCL #4 63.6016.3226,1881518  100% 99% 98% 93%
1.7Java  64.3816.3319,9081282  98% 100% 98% 99%
1.7Pascal Free Pascal 67.5416.936961018  100% 100% 100% 100%
1.9Fortran Intel #3 75.1818.8512,4641148  100% 100% 100% 100%
2.1Haskell GHC #5 80.2520.473,712834  98% 99% 95% 100%
2.7Go 103.1825.97760900  99% 99% 100% 100%
2.8OCaml #3 0.0127.0818,9601017  100% 100% 100% 100%
2.8C gcc #4 27.2627.273161183  0% 0% 1% 100%
2.8C++ g++ #7 27.2727.282841150  0% 100% 0% 1%
3.0C# Mono #3 114.9829.2819,7881096  99% 99% 98% 98%
3.4F# Mono #3 125.0432.7623,212945  93% 98% 95% 97%
3.4OCaml #4 0.0133.609,4281004  100% 100% 100% 100%
3.8Clojure #3 144.5937.0253,3361491  97% 98% 99% 97%
4.9C gcc #3 47.9847.99316567  0% 100% 1% 1%
5.9C gcc 57.8857.90316508  0% 100% 1% 1%
5.9C++ g++ #3 57.9157.93284593  1% 0% 0% 100%
6.0Lisp SBCL #5 58.9858.9922,576674  1% 1% 100% 1%
6.6C# Mono #2 64.4964.5118,616564  1% 0% 100% 0%
6.8Fortran Intel 66.4266.43520590  0% 1% 1% 100%
7.3Lisp SBCL #3 71.4071.4117,736821  1% 0% 0% 100%
7.4F# Mono #4 72.0872.1119,124612  0% 1% 100% 1%
7.7Java  #2 75.3675.3220,052514  1% 1% 100% 0%
7.8Dart #2 76.6076.0120,856495  0% 2% 2% 100%
7.9Clojure #2 258.8076.9156,9041088  85% 85% 83% 83%
8.5OCaml #2 83.3483.36604473  0% 1% 1% 100%
8.6Racket #3 5 min83.7717,1601096  99% 100% 99% 100%
8.9Haskell GHC #4 89.3686.6210,088658  2% 1% 1% 100%
9.1C# Mono 88.8288.8418,624520  0% 100% 1% 0%
10Scala 100.0099.9422,296459  1% 99% 0% 1%
10F# Mono #2 102.17102.2020,968548  0% 100% 0% 1%
11Erlang HiPE 6 min102.5312,9441038  100% 98% 98% 100%
15Haskell GHC #2 7 min143.655,020808  75% 76% 75% 75%
16OCaml 154.52154.55604524  1% 1% 1% 100%
17F# Mono 168.29168.2423,536551  1% 51% 50% 1%
19Lisp SBCL #2 182.57182.6943,728513  0% 1% 1% 100%
31Racket #2 5 min5 min16,876903  0% 0% 30% 70%
32Racket 5 min5 min15,364649  0% 1% 41% 60%
52Haskell GHC 10 min8 min9,592553  25% 44% 18% 42%
61Perl #2 39 min9 min12,380565  100% 100% 99% 99%
65PHP #3 41 min10 min10,5161150  100% 99% 99% 100%
65Python 3 #4 41 min10 min27,972944  99% 98% 99% 98%
80Ruby JRuby #2 46 min13 min784,8201426  95% 89% 88% 90%
104Python 3 #2 1h 06 min16 min27,840797  99% 99% 98% 100%
114Python 3 1h 13 min18 min27,8881108  100% 99% 99% 98%
116Ruby #2 1h 13 min18 min18,5281426  98% 96% 100% 97%
252PHP #2 40 min40 min2,556441  99% 1% 1% 2%
269Python 3 #6 43 min43 min4,200385  0% 0% 1% 100%
289Perl 46 min46 min1,768457  21% 0% 79% 1%
290Ruby 47 min47 min5,172384  97% 1% 4% 0%
313Ruby JRuby 50 min50 min658,916384  32% 20% 19% 32%
326PHP 53 min53 min2,588482  0% 1% 1% 100%
C++ g++ Failed1059
"wrong" (different) algorithm / less comparable programs
1.2Java  #3 46.2911.7622,5801633
1.4Lisp SBCL 53.3213.4833,3401607
3.0C# Mono #5 113.5828.8921,0721400
3.7C++ g++ #6 36.5036.52284894
8.8C# Mono #4 86.1686.1718,884710
64Python 3 #3 2454.61623.5531,936773

 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