n-body benchmark N=50,000,000

Each chart bar shows how many times slower, one ↓ n-body 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
1.0Fortran Intel #5 9.059.055121659  1% 0% 1% 100%
1.0C++ g++ #8 9.359.354361544  1% 1% 1% 100%
1.1C++ g++ #7 9.799.794361545  0% 1% 1% 100%
1.1C++ g++ #3 9.929.928281763  0% 1% 0% 100%
1.1C gcc #4 10.1910.194321490  1% 0% 0% 100%
1.5C++ g++ #5 13.4513.451,0681749  1% 0% 1% 100%
1.7Ada 2005 GNAT #5 15.4315.441,4922427  1% 0% 0% 100%
2.1C++ g++ #6 19.3419.354321668  1% 1% 1% 100%
2.2C++ g++ 19.5419.544361659  1% 0% 1% 100%
2.2Fortran Intel #2 19.9519.965121496  0% 0% 0% 100%
2.2Fortran Intel 20.0620.065121389  0% 0% 0% 100%
2.3C gcc #6 20.5920.604321180  1% 0% 1% 100%
2.3C gcc #3 20.6620.674361208  1% 0% 0% 100%
2.3C gcc 20.8120.824361173  0% 1% 1% 100%
2.3C++ g++ #4 20.9320.943601428  1% 1% 0% 100%
2.3C gcc #5 20.9320.943601429  1% 0% 0% 100%
2.3Rust 20.9921.004,8241371  1% 0% 0% 100%
2.4Fortran Intel #3 21.5321.545121299  0% 0% 0% 100%
2.4C# Mono #3 21.7521.7622,3041305  1% 1% 0% 100%
2.4OCaml 21.8621.877201239  0% 1% 0% 100%
2.5C gcc #2 22.2022.214361263  0% 1% 1% 100%
2.5Fortran Intel #4 22.4722.485121172  0% 0% 0% 100%
2.5Haskell GHC #2 22.6522.662,3441874  0% 1% 1% 100%
2.5Java  #2 22.6722.6723,8121424  1% 0% 1% 100%
2.5C# Mono #2 22.6722.6822,1041410  1% 1% 1% 100%
2.5Rust #3 22.8622.864,8121367  0% 0% 1% 100%
2.5Go 22.9622.961,0361310  1% 0% 0% 100%
2.6Ada 2005 GNAT #3 23.2723.281,5001740  1% 0% 0% 100%
2.7C# Mono #6 24.4624.4721,9921289  0% 0% 0% 100%
2.8F# Mono 25.0925.1033,0161259  0% 0% 1% 100%
2.9Ada 2005 GNAT 25.9225.931,5001608  1% 0% 0% 100%
2.9Rust #2 26.1726.184,8241321  1% 0% 1% 100%
2.9Scala 26.4826.4828,6841358  1% 0% 1% 100%
2.9Lisp SBCL #2 26.6726.688,6561398  0% 1% 0% 100%
3.0Haskell GHC 27.4027.412,3601706  1% 0% 0% 100%
3.1Clojure 27.7127.7262,1602162  0% 1% 0% 100%
3.1Clojure #2 27.9627.9761,6681440  0% 1% 1% 100%
3.1Dart #3 28.1328.1417,1561420  1% 0% 1% 100%
3.1C# Mono #7 28.1428.1522,5721539  1% 0% 1% 100%
3.4Dart #2 30.5830.5917,5601274  1% 1% 0% 100%
3.4C# Mono #4 30.8130.8222,3521461  1% 0% 1% 100%
3.5C# Mono #5 31.5931.6022,7641485  1% 0% 0% 100%
3.8Pascal Free Pascal 34.7534.7681308  1% 0% 1% 100%
3.9Pascal Free Pascal #3 35.4035.4181418  1% 1% 0% 100%
4.0JavaScript V8 35.8135.829,3041287  1% 0% 1% 100%
4.1Pascal Free Pascal #2 37.0137.0281322  1% 0% 0% 100%
4.1JavaScript V8 #2 37.2237.249,1441527  4% 16% 4% 100%
4.2C# Mono 37.9737.9822,4041403  1% 0% 0% 100%
4.7Lisp SBCL 42.8542.878,6561363  1% 0% 0% 100%
6.0Racket #2 53.9153.9427,5281689  0% 1% 1% 100%
11Racket 103.92104.0128,5361496  0% 1% 1% 100%
13Erlang HiPE #3 119.80119.8412,1081399  0% 0% 0% 100%
21Smalltalk VisualWorks 192.75192.8042,8801652  0% 0% 0% 100%
42Ruby JRuby #2 6 min6 min752,5001137  1% 1% 1% 100%
50Lua #4 7 min7 min1,0401305  0% 0% 0% 100%
52Lua #2 7 min7 min1,0401193  0% 0% 0% 100%
57Lua 8 min8 min1,0361201  0% 0% 0% 100%
66Hack #5 9 min9 min87,4961432  0% 1% 1% 100%
73Ruby #2 11 min11 min7,1641137  1% 0% 0% 100%
78PHP #3 11 min11 min3,3401082  0% 0% 0% 100%
87Hack 13 min13 min87,2961288  0% 0% 1% 100%
101Hack #3 15 min15 min83,2001080  0% 0% 1% 100%
103Python 3 15 min15 min5,5721181  1% 0% 0% 100%
115Perl #2 17 min17 min2,6201401  0% 0% 0% 100%
"wrong" (different) algorithm / less comparable programs
1.5C++ g++ #2 13.3913.401,0682288
3.6JavaScript V8 #3 32.9832.999,0561505

 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