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

 spectral-norm benchmark N=550

Each chart bar shows how many times more Code, one ↓ spectral-norm 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
1.0Python 3 #2 0.110.11?394  100% 0% 0% 0% 0% 0% 8% 0%
1.0Nuitka #2 0.100.11?394  8% 0% 91% 0% 0% 0% 0% 0%
1.0Python development version #2 0.100.10?394  0% 0% 100% 0% 0% 0% 10% 0%
1.1Numba #2 1.311.34131,484416  15% 9% 10% 8% 8% 9% 13% 99%
1.3Nuitka #6 2.112.1111,264498  100% 0% 0% 0% 2% 0% 0% 0%
1.3Python development version #6 2.162.178,872498  0% 0% 100% 0% 2% 0% 0% 1%
1.3RustPython #6 54.4754.4915,896498  0% 1% 1% 1% 0% 1% 100% 1%
1.3MicroPython #6 6.216.224,200498  0% 100% 0% 0% 0% 0% 0% 1%
1.3Python 2 #6 2.362.366,640498  0% 0% 0% 0% 1% 100% 0% 0%
1.3PyPy 2 #6 0.170.17?498  0% 100% 0% 19% 6% 12% 0% 0%
1.3Pyston #6 1.301.308,048498  0% 99% 2% 0% 0% 0% 1% 2%
1.3Graal #6 8.102.65921,616498  8% 0% 65% 70% 69% 1% 96% 2%
1.3Python 3 #6 2.152.1610,384498  100% 1% 0% 0% 0% 0% 0% 0%
1.3Jython #6 10.417.383,660498  10% 10% 9% 8% 58% 6% 26% 17%
1.3PyPy 3 #6 0.180.18?498  0% 100% 15% 0% 0% 0% 6% 0%
1.5Python development version #5 2.210.6056,516575  41% 46% 33% 48% 54% 67% 53% 42%
1.5PyPy 3 #5 2.241.3090,768575  48% 29% 23% 24% 18% 16% 14% 16%
1.5Nuitka #5 2.610.7058,040575  46% 53% 41% 30% 38% 67% 55% 64%
1.5Python 3 #5 2.480.6555,220575  59% 50% 20% 38% 59% 56% 55% 55%
1.5Jython #8 8.795.593,540594  23% 31% 26% 41% 10% 8% 8% 11%
1.5Nuitka #8 2.122.1311,392594  0% 0% 1% 0% 0% 0% 0% 100%
1.5RustPython #8 66.8066.8115,136594  1% 100% 1% 0% 0% 1% 0% 0%
1.5Graal #8 1.970.96729,476594  26% 26% 57% 35% 19% 12% 1% 36%
1.5Python 2 #8 2.702.716,592594  0% 0% 0% 100% 0% 2% 1% 0%
1.5Pyston #8 1.431.438,160594  3% 1% 0% 1% 1% 1% 1% 100%
1.5Python development version #8 2.152.159,364594  0% 0% 0% 0% 1% 0% 2% 100%
1.5Python 3 #8 2.212.2110,452594  0% 0% 0% 100% 0% 0% 0% 1%
1.5PyPy 3 #8 0.090.09?594  0% 18% 100% 0% 11% 0% 0% 11%
1.5PyPy 2 #8 0.090.09?594  0% 0% 0% 100% 18% 0% 0% 0%
1.5Pyston #5 1.400.3943,572595  55% 68% 57% 37% 37% 37% 37% 39%
1.5Python 2 #5 4.231.1311,728595  78% 71% 51% 30% 25% 35% 40% 59%
1.5PyPy 2 #5 1.120.70333,172595  32% 30% 46% 26% 10% 6% 13% 8%
1.6Python 3 #3 0.320.331,792642  100% 3% 0% 0% 0% 0% 3% 0%
1.6Nuitka #3 0.310.353,456642  100% 0% 0% 0% 0% 0% 0% 6%
1.6Python development version #3 0.310.322,560642  6% 0% 0% 100% 0% 6% 3% 0%
1.7Numba 1.391.41130,424667  21% 13% 15% 17% 14% 18% 99% 14%
missing benchmark programs
IronPython No program
Cython No program
Shedskin No program
Grumpy No program

 spectral-norm benchmark : Eigenvalue using the power method

diff program output N = 100 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 calculate the spectral norm of an infinite matrix A, with entries a11=1, a12=1/2, a21=1/3, a13=1/4, a22=1/5, a31=1/6, etc

For more information see challenge #3 in Eric W. Weisstein, "Hundred-Dollar, Hundred-Digit Challenge Problems" and "Spectral Norm".

From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/Hundred-DollarHundred-DigitChallengeProblems.html
http://mathworld.wolfram.com/SpectralNorm.html

Thanks to Sebastien Loisel for this benchmark.

Revised BSD license

  Home   Conclusions   License   Play