Re: For loop benchmarks between Octave versions

[Julien Bect]

Le 17/06/2014 17:41, John W. Eaton a écrit :
> On 06/17/2014 11:11 AM, Julien Bect wrote:
> > The runtime dropped to 2.16 when I added inline.
> Consistently?

Well, as far as I can tell from the small number of tests that I did : 
yes, consistently.

> Could you look at the generated assembly code and see whether the 
> "inline" keyword is really needed to get this trivial function to be 
> inlined?

I'm afraid that's beyond my skills.

> What compiler optimization flags are you using?

I use gcc 4.7.3 i686-linux-gnu on Ubuntu 13.04

I have configured with --enable-jit --disable-doc

and didn't change any other option.