n-body benchmark N=5,000,000

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

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.

    sortsort sort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0MicroPython 105.20109.114,4001315  7% 84% 14% 4%
1.0MicroPython 104.84109.374,4721315  1% 97% 2% 4%
1.0MicroPython 104.92107.864,4841315  32% 65% 6% 2%
1.5Python 2 50.9450.996,6161337  2% 17% 80% 6%
1.5Python 2 53.1753.336,6921337  30% 28% 64% 20%
1.5Python 2 48.9348.956,7401337  1% 0% 0% 100%
1.8Python development version 46.4546.487,9561315  6% 20% 1% 81%
1.8Python development version 45.6345.668,0001315  7% 9% 2% 93%
1.8Python development version 45.7345.768,1161315  7% 8% 2% 94%
1.9Cython 11.5812.128,4881392  100% 1% 0% 0%
1.9Cython 11.6212.038,5361392  79% 0% 23% 0%
1.9Cython 11.5811.988,5681392  76% 1% 26% 0%
2.0Python 3 46.5648.708,8721315  100% 1% 0% 1%
2.0Python 3 46.9249.088,8721315  100% 1% 1% 1%
2.0Python 3 47.3448.748,8801315  67% 28% 6% 5%
2.2Nuitka 39.0239.059,6721315  1% 39% 1% 62%
2.2Nuitka 38.9739.019,7641315  62% 1% 39% 1%
2.2Nuitka 39.4539.489,8321315  1% 1% 1% 100%
6.0Pyston 29.4429.4526,5961337  0% 53% 0% 47%
6.1Pyston 29.4929.4926,6481337  0% 0% 100% 0%
6.1Pyston 31.0531.0626,7241337  2% 0% 98% 0%
14IronPython 55.2154.6763,0401337  0% 66% 0% 34%
14IronPython 56.3756.6963,3241337  30% 0% 68% 0%
15IronPython 55.0055.1965,2081337  69% 7% 11% 12%
16PyPy 3 4.864.8968,8361315  15% 14% 95% 9%
16PyPy 3 4.854.8868,8401315  100% 16% 13% 10%
16PyPy 3 4.604.8268,9401315  3% 99% 5% 3%
17PyPy 2 5.105.2175,0401337  20% 55% 21% 68%
17PyPy 2 4.944.9775,2361337  12% 16% 17% 100%
17PyPy 2 5.185.3875,2441337  31% 77% 17% 38%
22Numba 59.7460.0196,7361333  0% 0% 100% 0%
22Numba 59.6259.6297,3761333  0% 26% 0% 74%
22Numba 58.4358.4497,4921333  0% 100% 0% 0%
68Jython 72.5868.57297,2521337  34% 21% 30% 21%
68Jython 71.2367.65297,4361337  28% 28% 24% 26%
68Jython 74.2070.26299,0881337  20% 25% 33% 28%
103Graal 6.626.46451,1841315  6% 100% 3% 1%
103Graal 6.646.47451,1961315  5% 81% 3% 20%
103Graal 6.636.48451,2001315  8% 100% 1% 1%
missing benchmark programs
Shedskin No program
Grumpy No program
RustPython No program

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

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.

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