How big is the measured performance difference?
Each chart bar shows how many times more Time or how many times more Memory one unidentified ↓ mandelbrot program used, compared to the program that used least Time or the program that used least Memory.
mandelbrot benchmark N=16,000
This table shows 5 measurements - CPU Time, Elapsed Time, Memory, Code and ~ CPU Load.
Compare how much Memory the mandelbrot 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 | ATS #3 | 22.10 | 5.53 | 28,976 | 2780 | 100% 100% 100% 100% |
| 1.1 | C GNU gcc #6 | 24.38 | 6.11 | 27,248 | 879 | 100% 100% 100% 100% |
| 1.1 | C++ GNU g++ #5 | 24.67 | 6.17 | 30,436 | 858 | 100% 100% 100% 100% |
| 1.7 | Ada 2005 GNAT #3 | 36.65 | 9.24 | 33,116 | 1805 | 99% 99% 99% 100% |
| 2.0 | Java 6 -server #3 | 43.12 | 10.95 | 48,920 | 903 | 98% 98% 99% 98% |
| 2.1 | Java 6 steady state #3 | 45.33 | 11.40 | 182,964 | 970 | 99% 100% 100% 99% |
| 2.3 | Scala | 49.68 | 12.65 | 44,488 | 737 | 98% 99% 98% 97% |
| 2.5 | Haskell GHC #2 | 54.32 | 13.63 | 34,932 | 772 | 99% 100% 100% 100% |
| 3.0 | C# Mono | 66.16 | 16.63 | 38,620 | 798 | 99% 100% 99% 99% |
| 3.2 | Lua LuaJIT #6 | 64.26 | 17.69 | 19,632 | 607 | 95% 85% 92% 90% |
| 3.6 | Lisp SBCL | 75.03 | 19.67 | 36,716 | 1002 | 100% 94% 95% 94% |
| 4.9 | ATS #2 | 27.30 | 27.30 | 464 | 1531 | 0% 1% 0% 100% |
| 6.7 | Lisaac | 36.91 | 36.91 | 472 | 653 | 100% 0% 0% 0% |
| 7.7 | Java 6 -server | 42.41 | 42.40 | 12,048 | 665 | 0% 0% 100% 0% |
| 8.4 | Go 6g 8g #3 | 133.98 | 46.32 | 118,876 | 695 | 70% 71% 69% 69% |
| 8.6 | ATS | 47.80 | 47.80 | 464 | 601 | 100% 0% 0% 0% |
| 8.8 | Lua LuaJIT | 48.70 | 48.70 | 1,064 | 353 | 100% 0% 0% 0% |
| 9.1 | C GNU gcc #2 | 50.16 | 50.16 | 488 | 400 | 0% 0% 100% 0% |
| 9.7 | Scala #2 | 53.86 | 53.88 | 12,632 | 454 | 100% 0% 0% 0% |
| 10 | Lua LuaJIT #2 | 55.51 | 55.51 | 852 | 367 | 0% 100% 0% 0% |
| 10 | Fortran Intel | 56.84 | 56.84 | 32,392 | 485 | 0% 0% 0% 100% |
| 10 | Clean #2 | 57.18 | 57.18 | 508 | 506 | 0% 0% 0% 100% |
| 11 | Ada 2005 GNAT #2 | 59.90 | 59.91 | 1,132 | 572 | 0% 0% 100% 0% |
| 11 | Ada 2005 GNAT | 60.39 | 60.40 | 1,136 | 611 | 0% 0% 100% 0% |
| 11 | OCaml #2 | 230.92 | 60.54 | 57,616 | 929 | 94% 100% 97% 94% |
| 12 | Go 6g 8g #6 | 257.14 | 64.42 | 31,128 | 723 | 100% 100% 100% 100% |
| 14 | OCaml #3 | 77.78 | 77.78 | 840 | 441 | 0% 0% 0% 100% |
| 14 | Pascal Free Pascal #3 | 78.28 | 78.28 | 52 | 530 | 0% 0% 0% 100% |
| 15 | C# Mono #2 | 82.20 | 82.20 | 4,952 | 484 | 0% 0% 100% 0% |
| 15 | Go 6g 8g #5 | 5 min | 85.07 | 32,272 | 714 | 100% 100% 100% 100% |
| 22 | Erlang HiPE | 7 min | 120.04 | 659,180 | 534 | 89% 87% 85% 90% |
| 29 | F# Mono | 158.32 | 158.40 | 7,008 | 528 | 100% 0% 0% 0% |
| 35 | Lua #6 | 11 min | 192.83 | 20,004 | 607 | 81% 95% 84% 85% |
| 39 | Java 6 -Xint #3 | 14 min | 214.66 | 47,108 | 903 | 100% 100% 100% 100% |
| 43 | C++ GNU g++ #3 | 240.29 | 240.27 | 1,108 | 414 | 0% 100% 0% 0% |
| 47 | Go 6g 8g | 262.71 | 262.71 | 632 | 509 | 43% 59% 3% 1% |
| 93 | Lua | 8 min | 8 min | 1,072 | 353 | 0% 100% 0% 0% |
| 104 | Lua #2 | 9 min | 9 min | 908 | 367 | 0% 0% 100% 0% |
| 112 | Java 6 -Xint | 10 min | 10 min | 10,328 | 665 | 0% 0% 100% 0% |
| 129 | PHP #3 | 47 min | 11 min | 111,076 | 863 | 100% 100% 100% 100% |
| 141 | Python CPython #5 | 51 min | 12 min | 18,824 | 425 | 100% 100% 100% 100% |
| 151 | Scheme PLT #2 | 13 min | 13 min | 8,572 | 508 | 28% 0% 72% 0% |
| 196 | Smalltalk VisualWorks #2 | 18 min | 18 min | 12,740 | 467 | 0% 0% 0% 100% |
| 247 | Python 3 #2 | 54 min | 22 min | 5,504 | 777 | 47% 100% 47% 47% |
| 260 | Perl | 1h 32 min | 23 min | 291,628 | 550 | 97% 97% 97% 97% |
| 398 | Mozart/Oz | 36 min | 36 min | 6,684 | 559 | 0% 0% 100% 0% |
| 531 | PHP | 49 min | 49 min | 3,632 | 443 | 0% 0% 100% 0% |
| 565 | Python CPython | 52 min | 52 min | 2,832 | 287 | 0% 100% 0% 0% |
| 613 | PHP #2 | 56 min | 56 min | 3,308 | 395 | 0% 0% 100% 0% |
| 961 | Perl #2 | 1h 28 min | 1h 28 min | 3,028 | 311 | 0% 0% 0% 100% |
| 1,567 | Ruby 1.9 | 2h 24 min | 2h 24 min | 2,768 | 313 | 0% 0% 100% 0% |
| 2,113 | Ruby MRI | 3h 14 min | 3h 14 min | 1,568 | 313 | 0% 100% 0% 0% |
| Fortran Intel #2 | Bad Output | 813 | ||||
| Fortran Intel #3 | Bad Output | 754 | ||||
| Haskell GHC | Make Error | 627 | ||||
| JavaScript TraceMonkey | Failed | 387 | ||||
| JavaScript V8 | Failed | 387 | ||||
| Lisp SBCL #2 | Failed | 653 | ||||
| Python 3 #3 | Failed | 304 | ||||
| Ruby JRuby | Timed Out | 1h 00 min | 313 |
mandelbrot benchmark : Generate Mandelbrot set portable bitmap file
cmp program output N = 200 with this 5KB output file to check your program is correct before contributing.
Each program should plot the Mandelbrot set [-1.5-i,0.5+i] on an N-by-N bitmap. Write output byte-by-byte in portable bitmap format.
For more information see Eric W. Weisstein, "Mandelbrot Set." From MathWorld--A Wolfram Web Resource.
http://mathworld.wolfram.com/MandelbrotSet.html
Thanks to Greg Buchholz for this benchmark.