Ubuntu : Intel® Q6600® quad-core
Computer Language Benchmarks Game      Help

- all benchmarks - binary-trees chameneos-redux fannkuch fasta k-nucleotide mandelbrot meteor-contest n-body pidigits regex-dna reverse-complement spectral-norm thread-ring - all languages - Ada 2005 GNAT ATS C GNU gcc C# Mono C++ GNU g++ Clean Erlang HiPE F# Mono Fortran Intel Go 6g 8g Haskell GHC Java 6 -server Java 6 -Xint Java 6 steady state JavaScript TraceMonkey JavaScript V8 Lisaac Lisp SBCL Lua Lua LuaJIT Mozart/Oz OCaml Pascal Free Pascal Perl PHP Python 3 Python CPython Ruby 1.9 Ruby JRuby Ruby MRI Scala Scheme PLT Smalltalk VisualWorks

 How big is the measured performance difference?

Each chart bar shows how many times more Time or how many times more Memory one unidentified ↓ thread-ring program used, compared to the program that used least Time or the program that used least Memory.

 thread-ring benchmark N=50,000,000

This table shows 5 measurements - CPU Time, Elapsed Time, Memory, Code and ~ CPU Load.

Compare how much Memory the thread-ring programs used - sort Memory KB. Compare how much Code the programs used - sort Code B

Column × shows how many times more each program used compared to the program that used least.

		sort	sort	sort	sort
×	Program Source Code	CPU secs	Elapsed secs	Memory KB	Code B	~ CPU Load
1.0	C GNU gcc #3	5.13	5.13	16,760	607	0% 100% 0% 0%
1.6	Haskell GHC #3	8.47	8.47	2,932	274	0% 0% 0% 100%
3.1	Mozart/Oz	15.91	15.91	4,356	340	0% 0% 0% 100%
4.1	Go 6g 8g #3	21.04	21.04	3,048	347	0% 0% 0% 100%
4.1	Go 6g 8g	21.09	21.09	3,084	309	0% 0% 100% 0%
6.1	Java 6 -server #4	30.61	31.53	119,832	894	32% 29% 19% 16%
6.9	Erlang HiPE	35.57	35.58	6,452	273	0% 2% 0% 98%
7.0	Smalltalk VisualWorks #2	35.87	35.86	13,088	566	0% 0% 100% 0%
18	Scheme PLT	91.14	91.14	19,648	262	0% 100% 0% 0%
27	Pascal Free Pascal	124.66	139.58	2,556	523	43% 33% 3% 4%
31	C GNU gcc #2	158.43	158.85	2,532	575	9% 10% 30% 48%
34	C GNU gcc	164.71	172.16	4,536	487	36% 2% 10% 46%
34	C++ GNU g++ #2	163.36	174.21	5,120	588	5% 55% 33% 0%
34	ATS	166.90	175.72	4,600	1090	5% 29% 59% 0%
36	OCaml #3	185.42	186.10	2,968	296	20% 35% 15% 27%
37	OCaml #2	188.29	189.07	4,964	350	34% 27% 23% 7%
43	C++ GNU g++	257.79	218.23	3,124	636	31% 30% 18% 30%
43	Scala	6 min	218.78	155,780	339	48% 48% 42% 40%
48	Python CPython #2	240.25	246.42	7,204	287	3% 49% 42% 2%
49	Python 3 #2	247.36	250.06	8,364	288	50% 9% 3% 33%
55	Lisp SBCL	295.73	283.83	58,444	618	30% 19% 13% 38%
59	Java 6 -server #3	5 min	5 min	118,132	530	1% 36% 47% 13%
66	Lisp SBCL #2	6 min	5 min	58,176	571	27% 27% 21% 27%
71	Ada 2005 GNAT #2	7 min	6 min	8,928	560	32% 28% 31% 26%
71	Java 6 -Xint #3	6 min	6 min	29,380	530	6% 22% 54% 14%
81	Go 6g 8g #2	7 min	6 min	3,116	333	21% 43% 7% 32%
84	Ada 2005 GNAT	10 min	7 min	8,792	602	39% 34% 23% 32%
94	C# Mono	13 min	8 min	11,400	476	39% 33% 46% 39%
98	Ruby JRuby #2	12 min	8 min	91,128	228	50% 16% 25% 50%
100	Ruby JRuby	8 min	8 min	96,344	342	40% 7% 5% 47%
103	Perl #3	8 min	8 min	488,940	489	37% 17% 7% 36%
131	F# Mono	18 min	11 min	13,108	472	33% 38% 42% 40%
133	OCaml	11 min	11 min	5,656	282	40% 33% 6% 15%
196	Java 6 -Xint #4	16 min	16 min	42,128	894	26% 33% 21% 14%
300	Ruby MRI #2	25 min	25 min	10,332	228	0% 0% 100% 0%
570	Ruby MRI	48 min	48 min	8,396	342	0% 0% 0% 100%
	Lisaac	Make Error			810
	Perl	Timed Out	2h 00 min		353
	Ruby 1.9 #2	Failed			228
	Ruby 1.9	Failed			342
interesting alternative programs
0.2	Java 6 -server #6	1.27	1.27	105,164	543
0.7	Lua LuaJIT #3	3.76	3.76	900	264
0.9	Lua LuaJIT #2	4.53	4.53	924	284
1.0	Java 6 -server #2	5.08	5.09	102,376	693
1.1	Lua LuaJIT	5.83	5.83	956	255
3.1	Lua #2	15.75	15.76	1,292	284
3.2	Lua #3	16.25	16.25	1,272	264
3.2	Java 6 -server #5	16.07	16.45	98,708	432
3.3	Lua	17.18	17.19	1,328	255
3.7	Python CPython #3	19.02	19.02	3,100	272
3.9	Python 3 #3	20.13	20.13	4,172	270
missing programs
	Clean	No program
	Fortran Intel	No program
	Java 6 steady state	No program
	JavaScript TraceMonkey	No program
	JavaScript V8	No program
	Lua	No program
	Lua LuaJIT	No program
	PHP	No program

 thread-ring benchmark : Switch from thread to thread passing one token

diff program output N = 1000 with this output file to check your program is correct before contributing.

Each program should create and keep alive 503 threads, explicity or implicitly linked in a ring, and pass a token between one thread and the next thread at least N times.

Each program should

• create 503 linked threads (named 1 to 503)
• thread 503 should be linked to thread 1, forming an unbroken ring
• pass a token to thread 1
• pass the token from thread to thread N times
• print the name of the last thread (1 to 503) to take the token

Similar benchmarks are described in Performance Measurements of Threads in Java and Processes in Erlang, 1998; and A Benchmark Test for BCPL Style Coroutines, 2004. For some language implementations increasing the number of threads quickly results in Death by Concurrency.

Programs may use kernel threads, lightweight threads; but coroutines, cooperative threads and other programs with custom schedulers will be listed as interesting alternative implementations. Briefly say what concurrency technique is used in the program header comment.