Ubuntu : Intel® Q6600® quad-core
Computer Language Benchmarks Game      [[ Play ]]

- all benchmarks - n-body fannkuch-redux meteor-contest fasta fasta-redux spectral-norm reverse-complement mandelbrot k-nucleotide regex-dna pidigits chameneos-redux thread-ring binary-trees-redux binary-trees - all languages - Ada 2005 GNAT ATS C gcc Clojure C# Mono C++ g++ Dart Erlang HiPE F# Mono Fortran Intel Go Haskell GHC Java 7 Lisp SBCL OCaml Pascal Free Pascal Perl PHP Python 3 Racket Ruby 2.0 Ruby JRuby Scala x86 one core x64 quad-core x86 quad-core x64 one core

 spectral-norm benchmark N=5,500

Each chart bar shows how many times slower, one ↓ spectral-norm 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		sort	sort
×	Program Source Code	CPU secs	Elapsed secs	Memory KB	Code B	≈ CPU Load
1.0	C++ g++ #6	7.96	2.00	924	1044	100% 100% 100% 100%
1.0	Fortran Intel	7.93	2.00	1,316	568	99% 99% 100% 99%
1.0	Fortran Intel #3	7.91	2.00	1,296	638	99% 99% 99% 99%
1.0	C++ g++ #5	7.98	2.01	924	1044	100% 100% 100% 100%
1.0	C gcc #5	8.02	2.02	644	569	100% 100% 100% 100%
1.2	Ada 2005 GNAT #4	9.36	2.39	1,900	2762	99% 98% 98% 99%
1.2	C gcc #4	9.93	2.50	644	1139	100% 100% 100% 100%
1.3	ATS #4	10.61	2.70	608	2507	99% 99% 99% 97%
1.7	C++ g++ #8	13.56	3.41	644	1278	100% 100% 100% 100%
2.0	Ada 2005 GNAT #3	15.74	3.99	1,636	1702	99% 99% 98% 99%
2.0	C gcc #3	15.98	4.02	644	463	100% 99% 100% 100%
2.0	Lisp SBCL #2	15.75	4.02	4,488	906	98% 98% 99% 98%
2.0	Haskell GHC #4	15.72	4.06	1,248	984	97% 97% 97% 97%
2.1	Java 7  #2	16.39	4.21	14,740	950	97% 97% 98% 99%
2.2	Scala #2	17.04	4.47	18,772	720	94% 94% 94% 99%
2.3	Lisp SBCL #3	18.02	4.58	4,604	883	98% 99% 98% 99%
2.4	OCaml #3	17.99	4.79	3,092	938	99% 99% 99% 99%
2.7	Go #2	20.79	5.32	1,496	668	98% 98% 99% 97%
3.0	Racket #3	22.94	5.97	18,520	627	96% 96% 96% 98%
3.9	Fortran Intel #2	7.85	7.86	780	513	1% 1% 2% 100%
4.1	C# Mono #2	30.30	8.30	16,392	1063	94% 93% 89% 90%
4.9	Go #3	20.88	9.89	1,820	536	37% 79% 53% 43%
5.0	F# Mono #2	30.71	10.09	18,720	852	75% 88% 71% 72%
5.7	Erlang HiPE #2	45.01	11.51	14,436	747	99% 98% 98% 98%
7.8	Clojure #6	54.52	15.66	70,732	808	88% 87% 89% 86%
7.9	Go	15.75	15.75	1,740	411	0% 100% 0% 0%
7.9	Pascal Free Pascal	15.77	15.77	8	423	0% 100% 1% 1%
7.9	Clojure #7	55.37	15.80	70,508	762	88% 87% 88% 89%
8.1	Scala	16.53	16.23	18,188	404	0% 0% 2% 100%
8.4	Java 7	16.90	16.85	15,236	514	1% 0% 1% 100%
9.4	OCaml #2	18.85	18.86	1,644	377	0% 0% 0% 100%
10	Dart	20.04	20.05	38,900	477	0% 0% 100% 0%
10	C gcc	20.65	20.66	364	383	92% 0% 0% 8%
10	ATS	20.68	20.69	608	1138	0% 0% 100% 0%
11	Ada 2005 GNAT	21.76	21.78	1,232	710	97% 0% 0% 3%
12	Lisp SBCL	24.70	24.71	5,716	625	0% 0% 0% 100%
14	Racket #2	28.31	28.31	17,124	532	0% 0% 100% 0%
14	C++ g++	28.47	28.49	872	452	0% 0% 100% 0%
15	Racket	31.03	31.02	16,568	446	1% 0% 0% 100%
16	C# Mono	31.68	31.69	16,556	459	0% 100% 0% 0%
21	Haskell GHC #2	126.57	41.29	6,496	403	69% 69% 69% 100%
28	Erlang HiPE	56.68	56.69	14,912	507	100% 0% 0% 0%
52	PHP #3	6 min	103.89	14,232	1193	98% 98% 98% 99%
93	Ruby 2.0 #3	11 min	186.34	25,092	828	97% 95% 96% 96%
100	Ruby JRuby #2	12 min	199.43	597,500	776	98% 97% 97% 98%
115	Perl	229.81	229.89	3,860	333	96% 0% 0% 4%
134	Python 3 #5	17 min	268.32	27,732	437	99% 99% 99% 99%
134	Perl #3	17 min	269.36	7,976	846	100% 99% 99% 100%
161	Ruby JRuby #4	5 min	5 min	600,116	326	50% 1% 1% 50%
212	Ruby JRuby	7 min	7 min	599,536	292	22% 27% 28% 25%
218	PHP #2	7 min	7 min	4,792	397	0% 0% 0% 100%
390	Ruby 2.0 #4	13 min	13 min	5,536	326	0% 100% 0% 0%
492	Python 3 #6	16 min	16 min	5,204	328	48% 33% 0% 20%
511	Ruby 2.0	17 min	17 min	5,528	292	30% 36% 35% 0%
533	Perl #2	17 min	17 min	3,076	343	99% 0% 0% 1%
571	Python 3 #8	19 min	19 min	4,608	449	90% 10% 0% 0%
	Scala #3	Failed			982
	Scala #4	Failed			1006
"wrong" (different) algorithm / less comparable programs
1.0	C++ g++ #7	8.06	2.03	924	1283
2.0	C gcc #2	3.98	3.99	236,904	669
2.1	C++ g++ #2	16.44	4.13	924	1330
6.0	Python 3 #2	11.91	11.93	481,840	233

 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

Each program must implement 4 separate functions / procedures / methods like the C# program.

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