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

 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
1.0PyPy 3 #8 0.080.10?594  0% 0% 0% 0% 0% 80% 0% 0%
1.1PyPy 2 #8 0.090.11?594  0% 0% 0% 0% 82% 0% 0% 0%
1.6Python 3 #2 0.160.16?394  6% 73% 17% 0% 94% 0% 7% 0%
1.9PyPy 2 #6 0.170.19?498  95% 0% 0% 0% 0% 0% 0% 0%
2.0PyPy 3 #6 0.180.20?498  5% 0% 0% 0% 63% 5% 0% 21%
4.5Python 3 #3 0.450.4627,212642  23% 20% 14% 21% 100% 17% 15% 9%
5.3Pyston #5 1.940.5413,900595  74% 73% 83% 69% 41% 33% 10% 15%
6.8Python development version #5 2.600.6915,092575  56% 61% 49% 48% 57% 57% 46% 41%
6.9PyPy 2 #5 1.280.7085,756595  17% 32% 15% 10% 22% 31% 26% 22%
9.5Graal #8 1.970.96729,476594  26% 26% 57% 35% 19% 12% 1% 36%
10PyPy 3 #5 2.001.0686,520575  37% 33% 30% 31% 10% 7% 39% 8%
11Python 2 #5 4.231.1311,728595  78% 71% 51% 30% 25% 35% 40% 59%
13Numba #2 1.311.34131,484416  15% 9% 10% 8% 8% 9% 13% 99%
14Numba 1.391.41130,424667  21% 13% 15% 17% 14% 18% 99% 14%
15Pyston #6 1.471.488,844498  21% 15% 14% 75% 34% 8% 9% 6%
16Python 3 #5 6.011.6012,756575  57% 67% 70% 56% 58% 32% 59% 56%
17Pyston #8 1.761.768,892594  11% 4% 100% 3% 10% 3% 5% 4%
20Python development version #6 2.042.0410,092498  13% 7% 100% 9% 11% 8% 10% 7%
23Python 2 #6 2.362.366,640498  0% 0% 0% 0% 1% 100% 0% 0%
24Python development version #8 2.402.4010,060594  100% 27% 17% 17% 18% 21% 16% 20%
26Graal #6 8.102.65921,616498  8% 0% 65% 70% 69% 1% 96% 2%
27Python 2 #8 2.702.716,592594  0% 0% 0% 100% 0% 2% 1% 0%
36Python 3 #6 3.603.638,116498  19% 100% 18% 13% 13% 11% 9% 10%
46Python 3 #8 4.624.638,192594  28% 30% 26% 100% 29% 27% 27% 25%
55Jython #8 8.795.593,540594  23% 31% 26% 41% 10% 8% 8% 11%
57MicroPython #6 5.775.784,524498  1% 0% 0% 1% 0% 1% 0% 100%
73Jython #6 10.417.383,660498  10% 10% 9% 8% 58% 6% 26% 17%
1,066RustPython #6 107.65107.6616,504498  1% 0% 0% 0% 100% 1% 0% 0%
1,109RustPython #8 111.92111.9814,592594  76% 0% 0% 0% 25% 1% 0% 0%
missing benchmark programs
IronPython No program
Cython No program
Nuitka 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