n-body benchmark N=50,000,000

Each chart bar shows how many times more Code, one ↓ n-body program used, compared to the program that used least Code.

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
1.0PHP #3 11 min11 min2,5921082  0% 1% 1% 100%
1.1Ruby JRuby #2 7 min7 min655,2681137  36% 21% 24% 23%
1.1Ruby #2 24 min24 min5,0841137  22% 0% 79% 1%
1.1Fortran Intel #4 22.6022.615201172  1% 0% 100% 1%
1.1C gcc 20.1920.197161173  0% 0% 100% 0%
1.1C gcc #6 20.5920.607881180  1% 0% 100% 0%
1.1Python 3 16 min16 min4,2401181  0% 0% 100% 1%
1.1C gcc #3 21.3021.317841208  1% 100% 0% 0%
1.1Python 3 #2 16 min16 min6,0801228  6% 100% 2% 7%
1.1OCaml 75.2375.256001239  1% 0% 0% 100%
1.2F# Mono 25.9926.0046,8601259  1% 0% 100% 1%
1.2C gcc #2 25.2725.287281263  100% 0% 1% 0%
1.2Dart #2 34.0233.7421,4721274  1% 55% 45% 1%
1.2Fortran Intel #3 25.2225.235161299  0% 1% 100% 0%
1.2Pascal Free Pascal 34.6934.7081308  1% 0% 100% 0%
1.2Go 23.1423.137601310  0% 1% 100% 1%
1.2Pascal Free Pascal #2 37.2037.2281322  0% 1% 1% 100%
1.3Scala 23.4523.4028,8321358  1% 1% 100% 1%
1.3Lisp SBCL 46.0246.037,8521363  0% 0% 100% 0%
1.3Fortran Intel 20.9020.915201389  1% 0% 0% 100%
1.3Lisp SBCL #2 38.4138.437,8521398  0% 1% 100% 0%
1.3Erlang HiPE #3 269.21269.3027,7761399  53% 1% 1% 47%
1.3Perl #2 20 min20 min2,5521401  1% 0% 0% 100%
1.3C# Mono 38.5838.5939,4241403  100% 0% 0% 1%
1.3C# Mono #2 23.1623.1738,7521410  1% 0% 0% 100%
1.3Pascal Free Pascal #3 47.1847.1981418  0% 1% 1% 100%
1.3Dart #3 38.6738.3321,5521420  1% 1% 1% 100%
1.3Java  #2 24.3424.3124,1561424  1% 1% 1% 100%
1.3C++ g++ #4 20.3020.316281428  1% 0% 0% 100%
1.3C gcc #5 21.0721.085801429  1% 0% 0% 100%
1.3Clojure #2 38.1036.8354,6801440  98% 2% 3% 1%
1.4Rust 24.5724.586,0241474  100% 0% 0% 1%
1.4C gcc #4 10.3810.397361490  0% 100% 1% 1%
1.4Fortran Intel #2 20.5320.545241496  0% 1% 1% 100%
1.4Racket 116.11116.1036,5361496  0% 100% 1% 1%
1.4C++ g++ #8 9.139.147961544  1% 100% 0% 0%
1.4C++ g++ #7 9.129.138761545  0% 0% 100% 1%
1.5Ada 2005 GNAT 24.8224.831,7241608  1% 0% 0% 100%
1.5Fortran Intel #5 10.7510.765201659  1% 0% 100% 1%
1.5C++ g++ 20.5720.588041659  0% 100% 1% 0%
1.5C++ g++ #6 20.1120.128081668  1% 2% 1% 100%
1.6Racket #2 55.3255.3320,9281689  1% 43% 58% 0%
1.6Haskell GHC 30.9329.1712,4001706  2% 100% 2% 2%
1.6Ada 2005 GNAT #3 25.5925.601,7121740  0% 0% 100% 0%
1.6C++ g++ #5 12.4812.491,2081749  100% 0% 0% 1%
1.6C++ g++ #3 19.8719.881,2281763  1% 0% 0% 100%
1.7Haskell GHC #2 27.1026.373,6441874  100% 2% 1% 2%
2.1Clojure 34.6033.2654,2762324  98% 2% 2% 3%
2.3Ada 2005 GNAT #5 18.0418.051,6322436  1% 0% 0% 100%
C# Mono #8 Failed1343
C# Mono #5 Failed1485
C# Mono #3 Failed1305
C# Mono #7 Failed1539
C# Mono #6 Failed1289
C# Mono #4 Failed1461
Java  Failed1424
"wrong" (different) algorithm / less comparable programs
2.1C++ g++ #2 12.2912.301,2082288

 n-body benchmark : Double-precision N-body simulation

You can write your own program for this task and contribute to the benchmarks game by following these general instructions.

More specifically:

ndiff -abserr 1.0e-8 program output N = 1000 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.

Each program should model the orbits of Jovian planets, using the same simple symplectic-integrator - see the Java program.

For background information see N-body problem. Useful symplectic integrators are freely available, for example the HNBody Symplectic Integration Package.

Thanks to Mark C. Lewis for this benchmark.

Revised BSD license

  Home   Conclusions   License   Play