Re: Lua is faster than Java?

[Mike Pall <mikelu-0507@...>]

Hi,

Tim Gogolin wrote:
> Yes, I realize that making performance claims without mentioning  
> system details is not particularly useful. For the record, that 5%  
> improvement came on a Dual 2Ghz G5, running an optimized (gcc 4)  
> build of the lua engine.  But regardless of platform specifics, I  
> wasn't expecting that much of an improvement after only 30 seconds of  
> playing with the code :-)

Right on. That's exactly what I was hinting at. There are many
more of these optimizations opportunities. Have a look at this
ancient message:

  http://lua-users.org/lists/lua-l/2004-09/msg00549.html
  
[Alas, most of the mentioned benchmarks have been phased out
and the archive stripped the attachment boundaries. :-/ ]

BTW: Missing benchmarks reduce the score a lot more. Look
at the total scores and ask yourself why C is not on top.
We can still aim for #1. :-)

> So apparently there really are trivial changes we could do to  
> improve lua's performance in these benchmarks... Is this enough of  
> a well known resource that it would be worth improving lua's  
> performance for?

Yes, the 'great computer language shootout' results are
cited very often (and often wrong so). There are more than
100.000 references on Google. A bad score is a real PR disaster.

All that is really needed is someone who organizes the
collection, review and submission of any improvements and
missing benchmarks for Lua. The GCLSO site already has
an automated tracker for submitting new programs, but one
is advised to read their mailing list and try to submit
only 'clean' and 'conforming' programs.

I would be so grateful if anyone with some spare time could
step forward and offer to do this. Thank you!


BTW: Other language communities regularly feature 'coding sprints'
as a by-program of workshops and conferences. Maybe the Lua
community should start something like this, too. It's also
feasible in a decentralized manner via IRC.

Bye,
     Mike