Python Interpreters Benchmarks
x64 ArchLinux : AMD® Ryzen 7 4700U®

 chameneos-redux benchmark N=6,000,000

Each chart bar shows how many times slower, one ↓ chameneos-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.

     sortsortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0MicroPython #2 104.41137.624,4441191  14% 15% 14% 15% 3% 1% 1% 1%
1.0MicroPython 106.40142.474,3401191  13% 11% 10% 10% 11% 9% 9% 9%
1.5Pyston #2 151.46230.9814,3161191  9% 6% 6% 6% 8% 8% 7% 8%
1.6Nuitka 166.14249.9714,7001191  10% 9% 8% 8% 7% 5% 6% 6%
1.7Nuitka #2 173.21268.3314,6561191  8% 3% 3% 3% 14% 14% 15% 14%
2.1RustPython 220.28215.7015,0081191  18% 19% 18% 19% 8% 15% 10% 10%
2.2RustPython #2 225.46218.1714,9961191  20% 18% 16% 19% 20% 20% 17% 20%
2.4Python development version #2 251.45184.8013,4841191  20% 21% 16% 23% 13% 17% 12% 10%
2.4Python development version 252.58184.2813,5041191  19% 19% 16% 18% 16% 16% 18% 10%
2.5Cython 265.20221.398,2321203  6% 9% 7% 6% 8% 7% 10% 8%
2.8Python 3 296.43215.338,7281191  19% 14% 14% 13% 14% 15% 14% 14%
3.1Python 3 #2 5 min230.168,4841191  26% 25% 25% 25% 26% 26% 25% 25%
missing benchmark programs
Python 2 No program
PyPy 2 No program
PyPy 3 No program
Jython No program
IronPython No program
Shedskin No program
Numba No program
Grumpy No program
Graal No program

 chameneos-redux benchmark : Symmetrical thread rendezvous requests

ndiff program output N = 600 with this output file to check your program output has the correct format 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.

The text-part and spelled-out numbers in the program output should match the expected output exactly. Thread scheduling may cause small differences in the other numbers, so program output is checked with ndiff -fields 2-10

Each program should

The chameneos benchmark is an adaptation of "Chameneos, a Concurrency Game for Java, Ada and Others" 100KB pdf (which includes example implementations in Java, Ada and C).

Programs may use pre-emptive kernel threads or pre-emptive lightweight threads; but programs that use non pre-emptive threads (coroutines, cooperative threads) and any programs that use custom schedulers, will be listed as interesting alternative implementations. Briefly say what concurrency technique is used in the program header comment.

Revised BSD license

  Home   Conclusions   License   Play