Re: [glob2-devel] Simon's idea on gradiens

[simon schuler]

Hi

Nuage wrote:
> Now, the CVS is using the same code, but I put my working implementation of your
> idea into comment. When you have a chance to get this code, please run some wide
> tests to find out the fastest and cleanest way.
>
> It's not that I don't want to add your idea now. But it increases the
> complexitly of the code much, and maybe, another totaly different idea may
> increase the speed more significalty.
>
> So if you either find a simpler way, or a bit faster way, we'll definitively
> take it. You got the idea ?
>   
I also feared that perhaps it could prevent other (better) 
optimizations, so it's perfectly OK if it's not included before some 
more gradient testing is done.
I have had yet another completely different optimization idea yesterday. 
It's more complicated but could be implemented much cleaner. I don't 
know yet how much performance benefit it would give. I'll try to 
implement this and then run some more tests...

simon