Python Interpreters Benchmarks
x64 ArchLinux : Intel® i5-7200U®

 spectral-norm benchmark N=550

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

    sort sortsort
  ×   Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
1.0Python 2 #2 0.090.10?394  0% 100% 0% 0%
1.5Nuitka #2 0.140.15?394  100% 0% 0% 0%
1.6Python 3 #2 0.150.16?394  6% 56% 17% 69%
2.2PyPy 2 #8 0.190.221,036594  95% 5% 0% 0%
2.3PyPy 3 #8 0.200.231,036594  91% 0% 0% 0%
2.7PyPy 2 #6 0.250.271,040498  8% 4% 4% 93%
3.1PyPy 3 #6 0.310.311,040498  12% 6% 97% 3%
4.5Python 3 #3 0.440.4530,272642  4% 4% 100% 7%
4.6Nuitka #3 0.450.4638,940642  4% 0% 100% 2%
5.2Pyston #2 0.510.5247,428394  9% 13% 88% 2%
8.6PyPy 2 #5 1.460.8688,912595  66% 41% 37% 38%
12Graal #8 1.361.21469,688594  91% 9% 3% 19%
14PyPy 3 #5 2.361.3786,232575  45% 70% 40% 44%
15Pyston #5 4.701.4632,328595  84% 80% 89% 78%
18Python 2 #5 6.091.7811,916595  82% 94% 84% 90%
19Pyston #8 1.791.8724,632594  100% 1% 0% 1%
20Nuitka #5 6.672.0113,780575  85% 88% 84% 83%
21Python development version #5 7.152.0812,836575  88% 85% 87% 90%
21Python 3 #5 7.332.1412,592575  86% 90% 83% 90%
23Pyston #6 2.272.2824,424498  5% 2% 4% 97%
29Python 2 #6 2.852.856,968498  5% 1% 100% 1%
30Nuitka #6 3.043.0410,264498  5% 1% 100% 1%
31Python 2 #8 3.103.106,992594  6% 1% 100% 2%
32Nuitka #8 3.173.179,964594  6% 2% 3% 100%
32Python development version #6 3.243.257,904498  6% 1% 1% 100%
33Python 3 #6 3.303.318,492498  5% 2% 2% 100%
38Python development version #8 3.823.837,992594  5% 100% 1% 2%
40Python 3 #8 4.034.038,768594  6% 100% 1% 1%
64Jython #8 10.846.383,528594  68% 23% 54% 32%
68MicroPython #6 6.836.844,288498  6% 1% 1% 100%
81Jython #6 12.118.133,516498  54% 32% 31% 42%
116Graal #6 23.2111.64549,268498  76% 66% 27% 39%
1,499RustPython #6 149.75149.9318,840498  6% 1% 100% 1%
missing benchmark programs
IronPython No program
Cython No program
Shedskin No program
Numba 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