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

- all benchmarks - n-body fannkuch-redux meteor-contest fasta fasta-redux fibonacci fib50 spectral-norm reverse-complement mandelbrot k-nucleotide regex-dna pidigits chameneos-redux templates thread-ring binary-trees-redux binary-trees pystone richards iobench jsonbench - all languages - Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython

vs Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython x64 octa-core

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

Each chart bar shows, for one unidentified benchmark, how much the fastest Graal program used compared to the fastest Python 2 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 Graal programs faster? Approximately.

Each table row shows, for one named benchmark, how much the fastest Graal program used compared to the fastest Python 2 program.

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

Graal used what fraction? used how many times more?
Benchmark	Time	Memory	Code
n-body †	1/11		±
fasta †	1/3		2×
spectral-norm	±		±
meteor-contest †	±		±
fannkuch-redux	±		1/2
fibonacci †	±		±
jsonbench †	2×		±
iobench †	2×		±
richards †	2×		±
pidigits †	3×		±
fib50 †	4×		±
pystone †	4×	?	±
k-nucleotide †	11×	?	±

Graal used what fraction? used how many times more?
Time-used	|-	|---	25%	median	75%	---|	-|
(Elapsed secs)	1/11	1/11	±	2×	3×	6×	11×

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

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

 3 : Are the Graal 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 Graal program are shown for comparison against measurements of the fastest Python 2 program.

Program Source Code	CPU secs	Elapsed secs	Memory KB	Code B	≈ CPU Load
n-body
Graal	4.31	3.45	745,904	1315	81% 8% 0% 10% 13% 0% 10% 6% †
Python 2	38.78	38.78	6,684	1337	0% 0% 0% 0% 0% 1% 0% 100% †
fasta
Graal	4.07	2.11	760,276	1698	41% 26% 19% 19% 16% 37% 88% 48% †
Python 2	5.87	5.91	12,988	900	0% 0% 1% 0% 0% 99% 0% 0% †
spectral-norm
Graal	1.97	0.96	729,476	594	26% 26% 57% 35% 19% 12% 1% 36%
Python 2	4.23	1.13	11,728	595	78% 71% 51% 30% 25% 35% 40% 59%
meteor-contest
Graal	5.67	1.83	873,808	1540	11% 74% 44% 18% 51% 13% 20% 86% †
Python 2	2.14	2.14	6,828	1485	0% 0% 100% 0% 0% 0% 0% 1% †
fannkuch-redux
Graal	3.86	3.47	735,676	552	93% 75% 86% 90% 76% 86% 98% 70%
Python 2	11.02	2.85	11,460	1009	6% 4% 97% 95% 94% 0% 1% 96%
fibonacci
Graal	1.69	0.68	568,420	182	60% 19% 53% 28% 13% 90% 17% 47% †
Python 2	0.49	0.49	6,772	181	0% 100% 2% 0% 0% 0% 0% 0% †
jsonbench
Graal	19.56	6.72	1,188,928	322	72% 53% 27% 34% 41% 58% 50% 13% †
Python 2	4.25	4.26	15,884	322	0% 0% 100% 0% 0% 0% 0% 0% †
iobench
Graal	57.51	47.07	1,235,176	367	34% 24% 27% 23% 74% 34% 19% 19% †
Python 2	24.86	24.86	6,336	370	0% 0% 100% 0% 0% 0% 0% 0% †
richards
Graal	6.69	2.08	906,636	2434	76% 82% 1% 0% 6% 83% 9% 69% †
Python 2	0.87	0.87	6,348	2423	1% 0% 100% 0% 1% 0% 0% 0% †
pidigits
Graal	8.15	6.17	803,816	322	0% 93% 9% 0% 6% 16% 4% 7% †
Python 2	2.13	2.13	7,128	322	0% 0% 0% 0% 1% 0% 100% 0% †
fib50
Graal	15.77	10.47	895,300	136	62% 20% 20% 17% 43% 23% 26% 26% †
Python 2	2.40	2.40	37,872	130	0% 0% 100% 0% 0% 0% 0% 0% †
pystone
Graal	2.35	0.87	662,964	2300	1% 53% 74% 1% 45% 0% 34% 65% †
Python 2	0.20	0.20	?	2301	0% 0% 0% 0% 0% 100% 0% 0% †
k-nucleotide
Graal	2.14	0.81	612,300	594	30% 4% 63% 58% 44% 52% 25% 6% †
Python 2	0.07	0.07	?	593	100% 0% 0% 0% 0% 0% 0% 0% †
reverse-complement
Graal	0.49	0.28	1,012	449	26% 0% 25% 0% 11% 7% 21% 89%
Python 2	0.01		?	432
regex-dna
	No program
Python 2	0.03	0.03	?	501	100% 0% 0% 0% 0% 0% 0% 33%
fasta-redux
Graal	8.62	5.34	816,376	1115	34% 64% 16% 22% 26% 21% 42% 13%
	No program
thread-ring
	No program
Python 2	0.38	0.39	2,800	407	3% 3% 97% 0% 0% 0% 0% 0%
binary-trees
	No program
Python 2	2.02	0.47	16,340	743	54% 57% 56% 54% 64% 57% 63% 54%
mandelbrot
	No programs
chameneos-redux
	No programs
templates
	No programs
binary-trees-redux
	No programs

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

 4 : Are there other Graal programs for these benchmarks?

Remember - those are just the fastest Graal and Python 2 programs measured on this OS/machine. Check if there are other implementations of these benchmark programs for Graal.

Python 2 PyPy Python 3 Python dev PyPy 3 Jython IronPython Cython Nuitka Shedskin Numba Pyston MicroPython Grumpy Graal RustPython

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

 5 : Are there other faster programs for these benchmarks?

Remember - those are just the fastest Graal and Python 2 programs measured on this OS/machine. Check if there are faster implementations of these benchmark programs for other programming languages.

n-body fannkuch-redux meteor-contest fasta fasta-redux fibonacci fib50 spectral-norm reverse-complement mandelbrot k-nucleotide regex-dna pidigits chameneos-redux templates thread-ring binary-trees-redux binary-trees pystone richards iobench jsonbench

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

 Graal : Graal 

  Home   Conclusions   License   Play