Java Faster Than C++?

jg21 writes "The Java platform has a stigma of being a poor performer, but these new performance benchmark tests suggest otherwise. CS major Keith Lea took time out from his studies at student at Rensselaer Polytechnic Institute in upstate New York's Tech Valley to take the benchmark code for C++ and Java from Doug Bagley's now outdated (Fall 2001) "Great Computer Language Shootout" and run the tests himself. His conclusions include 'no one should ever run the client JVM when given the choice,' and 'Java is significantly faster than optimized C++ in many cases.' Very enterprising performance benchmarking work. Lea is planning next on updating the benchmarks with VC++ compiler on Windows, with JDK 1.5 beta, and might also test with Intel C++ Compiler. This is all great - the more people who know about present-day Java performance, the better.""

Comments

every year this happens...

[Sebastopol]

When the following two pieces of code are written in Java, I'll take it seriously:

1) a java compiler for java (funny that the java binaries are written in C++ and compiled with a compiler written in C++)

2) id's next game engine

Riiiiiiight

[SmallFurryCreature]

I only know one thing. That the 2 java programs I use, freenet and azureus, are horrible monsters, nice ideas but badly implemented.

Compared to similar applications written in real languages (meaning any language that is not java) they are crash prone, give idiotic debug statements, suck up memory and easily get the "too many open files" error on linux.

I guess this is like "Windows nowadays is very stable" bit. You can show all the benchmarks and tests but I will let my daily experience be the judge and use reports such as this as the toilet paper it is.

To be fair, freenet does work on linux and windows as does Azureus. This is for me the only selling point.

Perhaps java is faster then C++, it is hard for me too judge. But until Java developers start writing better programs, Sun makes sure Java is really cross platform, and games (the ultimated performance applications) start being written in java I will file this with all the other reports on how java will take over the world and is the best, fastest, easiest.

Largest Prime

[Boyceterous]

ever discovered with Java: 1 (still waiting on that next one, I guess it's garbage-collecting) Can we build a grid-based garbage collector?

Only one?

[Matthew Weigel]

Am I the only one who thinks michael uses Slashdot to post stupid crap that just supports his own uninformed bias?

Geff K writes with more integrity

[node159]

Honestly, the guy has no clue what he is doing, the numbers are completely meaningless. I mean here is my review with just as much scientific integrity:

Test Results
------------
Java: 30 GigaQuads
C++: 3000000000000000000 GigaQuads

Sumary
-------
Java: sux balls
C++: is god

I digress, back to reality now.

None of the tests used any form of GUI testing, this is what the end user will mosty be dealing with so here it is, Swing is crap, its slow, ugly, and just a bad hack job. Eclips (the main opensource IDE) uses SWT instead of Swing to avoid these problems, for the uniformed, SWT simply does C calls to the OS to display the os's GUI library (this of course is at the expense of cross platform compatability).

When it comes down to it a JIT compilere has the advantage of being able to optimize for memory size and what not, but then again JET compilers can spend all the time they want getting the code tweaked just right so its neither here nor there, even though experience has shown that the later tends to be faster as the system specs are generaly too similar nowdays (Umm try running java on a 16Mb machine :). And anyway, commonly used code is converted to native code if they are called often enough so other parts are mute aswell.

In summary, JIT will always be a bit slowere because of the initial overheard, as for Swing, well thanks Sun you can have that pile of steaming shit back.

Re:The Great Computer Language Shootout

[Digital Avatar]

Of course not. They just saw a link and say, "Ooooh, this guy is helpful"... +1 Informative! Of course, neither of us should really bother mentioning this, since it's well known that slashdotheads never read the fucking article, so why should they be expected to follow a link? Never think too highly of slashdotters, and you'll never be disappointed.

Re:Java sucks, pass it on

[mrshowtime]

Funny how nobody can say anything negative about anything on slashdot without being labelled a troll. Java has crashed my computer for the past several years, and now it's crashing my cellphone. Either there are a lot of sucky Java Coders, or the language itself sucks.