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

 k-nucleotide benchmark N=10,000

Each chart bar shows how many times slower, one ↓ k-nucleotide 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 development version #2 0.080.05?801  33% 33% 20% 20% 60% 60% 20% 17%
1.1Nuitka #2 0.080.06?801  25% 17% 0% 0% 17% 80% 29% 0%
1.1Pyston #2 0.090.06?801  25% 29% 17% 17% 29% 67% 17% 33%
1.1Nuitka #3 0.110.06?2011  33% 17% 17% 0% 29% 20% 17% 80%
1.1Python development version #3 0.120.06?2011  29% 17% 33% 38% 17% 20% 17% 83%
1.2Python development version #8 0.140.06?777  67% 43% 38% 43% 17% 17% 29% 33%
1.2Pyston #3 0.140.06?2011  44% 25% 33% 71% 14% 33% 29% 17%
1.2Nuitka #8 0.130.07?777  38% 29% 25% 14% 17% 67% 0% 29%
1.2Pyston #8 0.140.07?777  29% 25% 33% 17% 20% 17% 14% 57%
1.3Python development version 0.070.07?594  22% 0% 12% 0% 12% 17% 88% 0%
1.3Cython 0.070.07?618  0% 0% 0% 100% 12% 0% 0% 0%
1.4Python 3 #2 0.100.07?801  17% 14% 38% 88% 25% 12% 83% 22%
1.4Python 2 0.070.07?593  100% 0% 0% 0% 0% 0% 0% 0%
1.5Nuitka 0.080.08?594  0% 0% 100% 0% 11% 0% 0% 0%
1.5Python 3 #3 0.170.08?2011  25% 38% 38% 88% 22% 25% 62% 44%
1.8Python 3 #8 0.220.10?777  78% 20% 38% 30% 22% 38% 38% 67%
2.1PyPy 2 0.090.11?593  0% 0% 0% 0% 0% 0% 0% 82%
2.2PyPy 3 0.100.12?594  0% 0% 92% 0% 0% 0% 8% 0%
2.3Python 3 0.120.12?594  23% 8% 9% 9% 73% 100% 15% 0%
2.4Python 2 #8 0.130.13?777  8% 21% 8% 0% 7% 21% 38% 8%
2.5Python 2 #2 0.060.13?801  0% 23% 0% 13% 0% 8% 0% 0%
5.3PyPy 2 #2 0.230.282,564801  4% 7% 7% 63% 0% 4% 4% 0%
5.5PyPy 2 #8 0.290.292,568777  17% 7% 3% 0% 3% 59% 3% 10%
8.5PyPy 3 #8 0.510.4573,304777  7% 2% 72% 9% 11% 7% 2% 4%
8.6PyPy 3 #3 0.640.4673,2722011  11% 9% 9% 11% 7% 9% 9% 80%
8.7PyPy 3 #2 0.430.4672,840801  2% 4% 74% 4% 0% 0% 2% 9%
15Graal 2.140.81612,300594  30% 4% 63% 58% 44% 52% 25% 6%
41Jython 4.892.153,448593  34% 52% 20% 30% 23% 31% 21% 16%
120RustPython 6.336.3426,260594  100% 0% 0% 0% 0% 0% 0% 0%
missing benchmark programs
IronPython No program
Shedskin No program
Numba No program
MicroPython No program
Grumpy No program

 k-nucleotide benchmark : Hashtable update and k-nucleotide strings

diff program output for this 250KB input file (generated with the fasta program N = 25000) 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.

We use FASTA files generated by the fasta benchmark as input for this benchmark. Note: the file may include both lowercase and uppercase codes.

Each program should

In practice, less brute-force would be used to calculate k-nucleotide frequencies, for example Virus Classification using k-nucleotide Frequencies and A Fast Algorithm for the Exhaustive Analysis of 12-Nucleotide-Long DNA Sequences. Applications to Human Genomics (105KB pdf).

Revised BSD license

  Home   Conclusions   License   Play