vs

 1 : Are the Python 3 programs faster? At a glance.

Each chart bar shows, for one unidentified benchmark, how much the fastest Python 3 program used compared to the fastest PyPy 3 program.

(Memory use is only compared for tasks that require memory to be allocated.)


These are not the only compilers and interpreters. These are not the only programs that could be written. These are not the only tasks that could be solved. These are just 10 tiny examples.

 2 : Are the Python 3 programs faster? Approximately.

Each table row shows, for one named benchmark, how much the fastest Python 3 program used compared to the fastest PyPy 3 program.

(Memory use is only compared for tasks that require memory to be allocated.)

 Python 3 used what fraction? used how many times more? 
Benchmark Time Memory Code
 pidigits1/115 ±
 regex-dna1/5 ±
 iobench1/4 ±
 reverse-complement †1/4?±
 templates †1/4 ±
 spectral-norm±?1/2
 binary-trees±1/2±
 k-nucleotide †±?±
 fasta-redux †± ±
 chameneos-redux± ±
 pystone †?±
 jsonbench ±
 fibonacci ±
 fasta † ±
 fannkuch-redux ±
 meteor-contest † ±
 fib50 ±
 richards ±
 n-body † ±
 thread-ring †135×?±
 Python 3 used what fraction? used how many times more? 
Time-used  |-  |---  25% median  75%  ---|  -|
(Elapsed secs)1/1151/1151/2135×

† possible mismatch - one-core program compared to multi-core program.

± read the measurements and then read the program source code.

 3 : Are the Python 3 programs faster? Measurements.

These are not the only tasks that could be solved. These are just 10 tiny examples. These are not the only compilers and interpreters. These are not the only programs that could be written.

For each named benchmark, measurements of the fastest Python 3 program are shown for comparison against measurements of the fastest PyPy 3 program.

Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
 pidigits 
Python 30.030.03?379  0% 0% 100% 0%
PyPy 33.073.1079,396322  8% 99% 4% 4%
 regex-dna 
Python 30.050.05?524  0% 100% 0% 0%
PyPy 30.230.231,116524  9% 4% 100% 4%
 iobench 
Python 35.495.508,472367  25% 23% 100% 18%
PyPy 321.5021.5777,836367  10% 48% 6% 59%
 reverse-complement 
Python 30.020.02?449  0% 0% 100% 33% †
PyPy 30.090.09?449  11% 0% 0% 100% †
 templates 
Python 31.071.1119,692322  83% 26% 3% 6% †
PyPy 34.204.24117,700322  14% 100% 9% 11% †
 spectral-norm 
Python 30.120.12?394  14% 100% 15% 0%
PyPy 30.160.16?594  7% 25% 94% 13%
 binary-trees 
Python 33.270.9662,884706  88% 88% 85% 94%
PyPy 31.991.06135,232741  43% 76% 48% 41%
 k-nucleotide 
Python 30.120.13?594  100% 8% 14% 8% †
PyPy 30.140.14?594  7% 0% 100% 0% †
 fasta-redux 
Python 30.290.291,7761115  10% 3% 100% 3% †
PyPy 30.290.291,1081115  7% 7% 100% 7% †
 chameneos-redux 
Python 3166.3596.308,8201191  51% 46% 41% 46%
PyPy 3147.2178.1969,7201191  49% 44% 47% 44%
 pystone 
Python 30.260.271,8082303  7% 100% 4% 0% †
PyPy 30.130.14?2303  8% 7% 100% 8% †
 jsonbench 
Python 33.623.8012,268322  100% 5% 4% 5%
PyPy 31.691.7184,332322  8% 3% 99% 5%
 fibonacci 
Python 30.670.679,364182  5% 100% 6% 2%
PyPy 30.280.281,012182  11% 7% 97% 4%
 fasta 
Python 310.174.9090,4482016  70% 79% 66% 51% †
PyPy 31.941.9669,6601698  7% 4% 2% 96% †
 fannkuch-redux 
Python 312.113.6652,808894  96% 93% 93% 95%
PyPy 33.361.3682,7401271  60% 89% 57% 62%
 meteor-contest 
Python 33.403.468,8521443  44% 5% 64% 4% †
PyPy 31.001.0176,4201540  9% 7% 100% 6% †
 fib50 
Python 33.743.758,908136  37% 26% 33% 100%
PyPy 30.920.9272,408136  13% 4% 100% 4%
 richards 
Python 31.121.129,0682434  6% 100% 2% 0%
PyPy 30.270.271,1002434  4% 18% 7% 89%
 n-body 
Python 344.2944.338,7961315  7% 100% 3% 4% †
PyPy 36.796.8269,3321315  14% 10% 100% 9% †
 thread-ring 
Python 327.2421.6413,344448  31% 36% 27% 34% †
PyPy 30.160.16?407  6% 6% 12% 94% †
 mandelbrot 
Python 374.0819.52181,9363832  98% 98% 98% 99%
No program
 binary-trees-redux
   No programs

† possible mismatch - one-core program compared to multi-core program.

 4 : Are there other Python 3 programs for these benchmarks?

Remember - those are just the fastest Python 3 and PyPy 3 programs measured on this OS/machine. Check if there are other implementations of these benchmark programs for Python 3.

Maybe one of those other Python 3 programs is fastest on a different OS/machine.

 5 : Are there other faster programs for these benchmarks?

Remember - those are just the fastest Python 3 and PyPy 3 programs measured on this OS/machine. Check if there are faster implementations of these benchmark programs for other programming languages.

Maybe one of those other programs is fastest on a different OS/machine.

 Python 3 : the new Python 

Python 3.3.1 (default, Apr 11 2013, 12:45:45)
[GCC 4.7.2] on linux

"3.x is the newest branch of Python and the intended future of the language."

"Van Rossum: Python is not too slow"

Home Page: Python 3.3.1 was released on April 7th, 2013.

Revised BSD license

  Home   Conclusions   License   Play