Java's performance far better that optimized C++

[Gaurav]

http://www.sys-con.com/story/print.cfm?storyid=45250

Any comments?

Thanks
Gaurav

 

[Roedy Green]

http://www.sys-con.com/story/print.cfm?storyid=45250

the key is obviously the improved method calls. This is done though
inlining. The big advantage hotspotting has is knowing what to
inline. Inlining everything just gobbles up RAM with no payback.

 

[David Hopwood]

the key is obviously the improved method calls. This is done though
inlining. The big advantage hotspotting has is knowing what to
inline. Inlining everything just gobbles up RAM with no payback.

Although note that gcc was run with -O2, which does not inline at all.
gcc -O3 would have been a more reasonable comparison.

A more interesting question: why does anyone pay any attention to
microbenchmarks?

David Hopwood <[email protected]>

 

[Jonas Geiregat]

http://www.sys-con.com/story/print.cfm?storyid=45250

Any comments?

Thanks
Gaurav

They forgot gcj.

 

[Keith A. Lewis]

http://www.sys-con.com/story/print.cfm?storyid=45250

Any comments?

Yeah, yahoos that don't proofread their subject line probably don't
have a clue. You also misspelled far. I followed up to comp.lang.c++
so you can get properly flamed for being a troll.

 

[Dave Monroe]

http://www.sys-con.com/story/print.cfm?storyid=45250

Any comments?

Thanks
Gaurav

Does 'apples and oranges' ring a bell?

Big cycle suckers can be better - unless you need small and efficient.

The answer is: it depends.

Benchmarks are management fodder, and often the source of bad decisions.

 

[EventHelix.com]

Not sure if GCC is the best optimized compiler. May be these tests
should be rerun with MS C++ compiler on Windows and Intel C++ 8.0 on
Linux.

Sandeep

 

[Roedy Green]

Benchmarks are management fodder, and often the source of bad decisions.

Focusing on benchmarks is often being penny wise and pound foolish.

What counts is getting the product out the door on time, bug free on
budget, and doing that release after release. Whether it runs 5%
faster nobody will notice.

In fact for many programs it has to run 100% faster for it to be even
psychologically noticeable.

If you have a bottleneck you will get far more return on your time and
money by profiling and tuning the critical section, especially
choosing a smarter algorithm, than you ever will by backing off to a
more manual language that introduces far more problems than it solves.

 

[JTK]

http://www.sys-con.com/story/print.cfm?storyid=45250

Any comments?

Just one:

BAAAAAAAAAAAAAAAAAAAAAAAAAHAHAHHAHAHAHAHHAAAAAAAAAAAAA!!!!!

Jesus von Neumann CHRIST you Javapologists, GIVE IT THE HELL UP ALREADY!

 

[Sudsy]

Just one:

BAAAAAAAAAAAAAAAAAAAAAAAAAHAHAHHAHAHAHAHHAAAAAAAAAAAAA!!!!!

Jesus von Neumann CHRIST you Javapologists, GIVE IT THE HELL UP ALREADY!

How about one which has some semblance of intelligence behind it...
Or perhaps signs of more than a couple of neurons firing...
Perchance more than it would take to jerk the knee?

 

[Anon Amous]

Consistently Stupid,
thank you for another meaningless comment.