Magnus Holmgren wrote:
> By using the fft_FPU_FXCH code, as well as TAKEHIRO_IEEE754_HACK, I
> managed to get speed to within about 50 percent of the 3.80 DLL I use
> with CDEx (I've no idea on the options used there). How much of a
> speed-up could ASM_QUANTIZE give?
Well, now I know the main reason for my slow exe. The free Borland
compiler is apparantly completely void of any optimizations (not
surprising really). When using DJGPP - without any optimizations - I get
a lame of about the same speed as with Borland C++. (And the fact that
optimization options made next to no difference at all is a rather
convincing detail too, though I must say the large difference surpised
me a little. :)
--
Magnus Holmgren
--
MP3 ENCODER mailing list ( http://geek.rcc.se/mp3encoder/ )
