vs

 1 : Are the PyPy programs faster? At a glance.

Each chart bar shows, for one unidentified benchmark, how much the fastest PyPy program used compared to the fastest Pyston 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 PyPy programs faster? Approximately.

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

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

 PyPy used what fraction? used how many times more? 
Benchmark Time Memory Code
 jsonbench1/24 ±
 n-body1/6 ±
 thread-ring1/5 ±
 fannkuch-redux1/3 ±
 spectral-norm1/2 
 fasta1/2 ±
 meteor-contest1/2 ±
 pystone±?±
 richards± ±
 k-nucleotide±?±
 binary-trees±1/2±
 chameneos-redux± ±
 templates † ±
 reverse-complement?±
 iobench ±
 regex-dna?±
 pidigits ±
 fibonacci?±
 PyPy used what fraction? used how many times more? 
Time-used  |-  |---  25% median  75%  ---|  -|
(Elapsed secs)1/241/241/2±

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

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

 3 : Are the PyPy 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 PyPy program are shown for comparison against measurements of the fastest Pyston program.

Program Source Code CPU secs Elapsed secs Memory KB Code B ≈ CPU Load
 jsonbench 
PyPy1.091.1181,060322  5% 2% 2% 97%
Pyston26.4626.4641,828322  100% 0% 0% 0%
 n-body 
PyPy4.734.9774,4681337  100% 1% 0% 0%
Pyston29.4929.4926,6481337  0% 0% 100% 0%
 thread-ring 
PyPy0.150.15?407  7% 0% 0% 100%
Pyston0.790.7928,572407  0% 99% 0% 0%
 fannkuch-redux 
PyPy3.151.0981,9721009  73% 93% 69% 67%
Pyston10.422.89157,5841009  87% 90% 89% 96%
 spectral-norm 
PyPy0.200.20?594  5% 100% 0% 5%
Pyston0.420.4256,036394  0% 0% 0% 100%
 fasta 
PyPy2.442.4678,424900  5% 2% 1% 99%
Pyston4.634.6332,960900  0% 26% 0% 74%
 meteor-contest 
PyPy0.940.9582,4401579  4% 0% 100% 2%
Pyston1.741.7430,1561485  0% 0% 99% 0%
 pystone 
PyPy0.120.12?2301  0% 14% 100% 0%
Pyston0.170.17?2301  100% 0% 0% 0%
 richards 
PyPy0.250.251,0602423  4% 0% 100% 0%
Pyston0.320.322,1362423  0% 0% 0% 97%
 k-nucleotide 
PyPy0.120.12?593  0% 0% 100% 0%
Pyston0.100.10?593  100% 0% 0% 0%
 binary-trees 
PyPy1.830.8789,104743  48% 45% 79% 46%
Pyston1.950.65169,224743  69% 67% 94% 70%
 chameneos-redux 
PyPy176.5486.1674,2761192  51% 40% 46% 47%
Pyston106.6458.3066,8841192  31% 34% 26% 36%
 templates 
PyPy2.952.9795,124307  8% 18% 99% 2% †
Pyston1.851.8558,360307  0% 100% 1% 1% †
 reverse-complement 
PyPy0.080.09?455  0% 0% 100% 0%
Pyston0.050.05?455  0% 0% 17% 100%
 iobench 
PyPy35.0335.4784,900370  29% 1% 74% 0%
Pyston20.3420.3426,752370  100% 0% 0% 0%
 regex-dna 
PyPy0.140.14?501  7% 100% 0% 0%
Pyston0.080.08?501  13% 0% 0% 100%
 pidigits 
PyPy2.942.9685,488322  5% 1% 1% 100%
Pyston0.910.9126,480322  100% 0% 0% 1%
 fibonacci 
PyPy0.260.271,068181  4% 0% 100% 0%
Pyston0.060.06?181  0% 0% 0% 100%
 fasta-redux 
PyPy0.250.271,0561115  7% 96% 0% 0%
No program
 mandelbrot 
No program
Pyston68.1318.05138,7123832  94% 95% 97% 93%
 fib50
   No programs
 binary-trees-redux
   No programs

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

 4 : Are there other PyPy programs for these benchmarks?

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

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

 5 : Are there other faster programs for these benchmarks?

Remember - those are just the fastest PyPy and Pyston 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.

 PyPy : the old PyPy 

 

Revised BSD license

  Home   Conclusions   License   Play