x64 ArchLinux : Intel® i5-7200U® 
Python Interpreters Benchmarks      [[ Play ]]

- 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 x64 dual-core

 spectral-norm benchmark N=550

Each chart bar shows how many times more Code, one ↓ spectral-norm program used, compared to the program that used least Code.

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	sort	sort
×	Program Source Code	CPU secs	Elapsed secs	Memory KB	Code B	≈ CPU Load
1.0	Nuitka #2	0.23	0.48	16,608	394	100% 100% 100% 100%
1.0	Nuitka #2	0.26	0.62	14,984	394	100% 100% 100% 100%
1.0	Pyston #2	0.42	0.42	57,532	394	0% 10% 83% 12%
1.0	Pyston #2	0.42	0.42	55,652	394	2% 0% 0% 100%
1.0	Nuitka #2	0.23	0.56	15,008	394	100% 100% 100% 100%
1.0	Python 3 #2	0.14	0.15	?	394	13% 100% 0% 0%
1.0	Python 3 #2	0.15	0.15	?	394	7% 0% 100% 0%
1.0	Pyston #2	0.42	0.42	56,036	394	0% 0% 0% 100%
1.0	Python 2 #2	0.08	0.08	?	394	0% 13% 0% 89%
1.0	Python 2 #2	0.08	0.08	?	394	0% 0% 11% 100%
1.0	Python 3 #2	0.15	0.15	?	394	0% 0% 100% 0%
1.0	Python 2 #2	0.09	0.14	?	394	7% 29% 67% 7%
1.3	Python 2 #6	2.80	2.80	6,664	498	2% 2% 100% 2%
1.3	IronPython #6	4.45	4.62	71,112	498	46% 1% 48% 1%
1.3	MicroPython #6	7.29	7.31	4,504	498	100% 9% 3% 3%
1.3	MicroPython #6	7.20	7.30	4,472	498	58% 34% 4% 16%
1.3	Python 2 #6	2.81	2.82	6,724	498	2% 1% 100% 1%
1.3	Pyston #6	2.21	2.21	27,340	498	2% 98% 0% 0%
1.3	Pyston #6	2.20	2.21	27,500	498	0% 0% 100% 0%
1.3	Jython #6	9.57	6.83	284,740	498	43% 37% 27% 33%
1.3	Jython #6	9.96	6.90	294,640	498	31% 36% 56% 21%
1.3	MicroPython #6	7.23	7.25	4,472	498	47% 8% 56% 6%
1.3	Graal #6	38.31	20.54	534,956	498	54% 26% 43% 72%
1.3	Graal #6	34.14	18.74	534,676	498	56% 55% 67% 20%
1.3	PyPy 2 #6	0.25	0.25	1,088	498	12% 100% 0% 0%
1.3	Python 2 #6	2.80	2.80	6,720	498	1% 3% 1% 100%
1.3	Jython #6	9.82	6.89	290,672	498	30% 38% 31% 44%
1.3	Graal #6	36.55	19.59	549,552	498	54% 14% 52% 80%
1.3	Pyston #6	2.33	2.33	27,464	498	0% 100% 0% 0%
1.3	IronPython #6	4.34	4.59	74,580	498	1% 2% 13% 79%
1.3	Python development version #6	3.54	3.54	8,012	498	5% 11% 1% 90%
1.3	IronPython #6	4.35	4.61	70,740	498	7% 57% 1% 29%
1.3	Python development version #6	3.54	3.69	8,064	498	95% 1% 6% 1%
1.3	PyPy 3 #6	0.31	0.32	996	498	6% 94% 3% 0%
1.3	PyPy 2 #6	0.26	0.26	1,092	498	7% 100% 4% 8%
1.3	PyPy 3 #6	0.31	0.31	976	498	9% 100% 0% 0%
1.3	Nuitka #6	3.01	3.01	10,532	498	8% 100% 8% 1%
1.3	Nuitka #6	3.03	3.03	10,116	498	6% 100% 3% 0%
1.3	Python 3 #6	3.71	3.72	9,080	498	6% 99% 1% 1%
1.3	Nuitka #6	3.02	3.03	10,316	498	5% 100% 4% 0%
1.3	Python 3 #6	3.68	3.85	9,140	498	100% 0% 0% 1%
1.3	Python 3 #6	3.71	3.79	9,140	498	46% 0% 57% 1%
1.3	Python development version #6	3.60	3.60	7,876	498	5% 1% 100% 1%
1.3	PyPy 3 #6	0.31	0.31	1,084	498	6% 0% 0% 100%
1.3	PyPy 2 #6	0.25	0.25	976	498	4% 100% 4% 0%
1.3	RustPython #6	152.97	153.63	19,056	498	17% 18% 71% 19%
1.5	PyPy 3 #5	2.42	1.41	85,988	575	38% 40% 64% 37%
1.5	Python development version #5	8.71	2.46	48,168	575	93% 90% 93% 89%
1.5	Python development version #5	8.64	2.45	48,248	575	92% 92% 91% 90%
1.5	PyPy 3 #5	2.37	1.25	87,500	575	46% 68% 38% 46%
1.5	Python development version #5	8.80	2.48	48,304	575	92% 92% 89% 92%
1.5	PyPy 3 #5	2.43	1.27	85,968	575	44% 42% 74% 38%
1.5	PyPy 3 #8	0.20	0.21	1,072	594	5% 0% 5% 95%
1.5	IronPython #8	4.00	4.19	57,200	594	0% 92% 1% 1%
1.5	PyPy 3 #8	0.20	0.21	1,092	594	0% 5% 5% 100%
1.5	IronPython #8	3.98	4.16	57,520	594	0% 63% 8% 24%
1.5	IronPython #8	3.99	4.18	61,472	594	92% 0% 1% 1%
1.5	Python 3 #8	4.71	4.71	8,840	594	5% 100% 1% 0%
1.5	Jython #8	8.41	4.96	294,976	594	31% 64% 46% 29%
1.5	Python development version #8	4.25	4.26	7,988	594	6% 1% 1% 100%
1.5	Jython #8	8.37	4.87	297,264	594	51% 45% 38% 38%
1.5	Python development version #8	4.23	4.24	7,928	594	5% 100% 1% 1%
1.5	Python development version #8	4.28	4.29	7,820	594	5% 0% 100% 1%
1.5	PyPy 2 #8	0.20	0.20	?	594	5% 100% 0% 5%
1.5	PyPy 2 #8	0.20	0.21	1,088	594	100% 0% 0% 0%
1.5	PyPy 2 #8	0.20	0.23	980	594	90% 13% 0% 0%
1.5	PyPy 3 #8	0.25	0.27	984	594	11% 11% 85% 0%
1.5	Jython #8	8.08	4.77	294,356	594	43% 34% 60% 31%
1.5	Graal #8	20.43	10.93	524,288	594	48% 72% 54% 31%
1.5	Graal #8	18.33	9.78	553,204	594	61% 67% 63% 4%
1.5	Python 3 #8	4.62	4.62	9,036	594	5% 100% 0% 1%
1.5	Python 3 #8	4.62	4.83	8,884	594	100% 0% 0% 0%
1.5	Graal #8	22.74	13.69	519,948	594	69% 84% 86% 75%
1.5	Pyston #8	1.69	1.69	27,440	594	100% 1% 0% 0%
1.5	Pyston #8	1.73	1.73	27,432	594	1% 0% 2% 98%
1.5	Python 2 #8	3.12	3.12	6,864	594	1% 2% 100% 1%
1.5	Python 2 #8	3.16	3.16	6,796	594	2% 1% 100% 1%
1.5	Nuitka #8	3.05	3.14	10,192	594	69% 32% 2% 0%
1.5	Python 2 #8	3.15	3.15	6,932	594	2% 3% 1% 100%
1.5	Nuitka #8	3.01	3.15	10,168	594	100% 7% 1% 1%
1.5	Nuitka #8	2.99	3.13	10,180	594	100% 4% 0% 1%
1.5	Pyston #8	1.69	1.69	27,568	594	0% 100% 0% 0%
1.5	Pyston #5	4.82	1.50	158,392	595	88% 79% 76% 77%
1.5	PyPy 2 #5	1.57	0.89	88,324	595	40% 63% 36% 47%
1.5	PyPy 2 #5	1.53	0.86	88,444	595	36% 41% 63% 42%
1.5	Python 2 #5	6.34	1.95	41,648	595	92% 92% 91% 93%
1.5	Pyston #5	4.75	1.43	158,316	595	86% 81% 85% 82%
1.5	Pyston #5	4.79	1.49	158,188	595	88% 79% 76% 79%
1.5	PyPy 2 #5	1.51	0.85	88,188	595	46% 42% 63% 37%
1.5	Python 2 #5	6.38	1.84	41,668	595	90% 93% 91% 92%
1.5	Python 2 #5	6.45	1.89	41,868	595	95% 91% 92% 93%
1.6	Nuitka #3	0.46	0.46	37,412	642	4% 2% 100% 0%
1.6	Nuitka #3	0.45	0.47	27,620	642	98% 0% 0% 4%
1.6	Python 3 #3	0.46	0.46	31,100	642	4% 2% 100% 2%
1.6	Nuitka #3	0.46	0.46	35,584	642	4% 0% 100% 0%
1.6	Python 3 #3	0.45	0.46	35,516	642	4% 4% 100% 0%
1.6	Python 3 #3	0.46	0.46	35,596	642	7% 0% 100% 0%
1.7	Numba	0.92	0.92	84,664	663	0% 3% 49% 48%
1.7	Numba	0.91	0.91	84,284	663	0% 0% 0% 100%
1.7	Numba	0.93	0.93	83,916	663	1% 0% 0% 99%
missing benchmark programs
	Cython	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.

  Home   Conclusions   License   Play