Re: [Linuxsampler-devel] MacOSX note release problem solved

[<le...@gr...>]

Le 25 mai 04, =E0 14:09, Jan Weil a =E9crit :

> Hi,
>
> Am Die, den 25.05.2004 schrieb St=E9phane Letz um 13:23:
>> Now most of the time is used in int to float conversion :
>>
>> float xm1_r =3DpSrc[pos_int+1];
>>
>
> Well, probably you already know this and actually it's float to int =
and
> it's on i386 but anyway, maybe this helps:
>
> http://www.eca.cx/lad/2001/Nov/0000.html
> http://mega-nerd.com/FPcast/

I know this code.


>
> The thread on LAD also mentions PPC. As far as I remember there have
> been more threads about this issue on LAD.
>
> Cheers,

I think a lot of int to flot conversion could be avoided in the code :=20=

the cubic interpolation used 4 samples that are int to float converted,=20=

and the *same* sample is converted 4 times when the computation window=20=

moves. This could be improved to only make one  int to float =20
conversion per sample


Stephane