[vorbis] RC3: I'm impressed

[Nathan I. Sharfi]

On Mon, 14 Jan 2002, Ed Sweetman wrote:

> > I'm sold on it too. I encode at -q 4.99 and it simply sounds great. Oggenc
> > for Win32 is slower but it isn't optimized in any sort of way, from what I
> > have seen.
> >
>
> Is anyone working on optimizing the libs ?  Would be nice to see ogg
> decoding down to the same level as mp3 decoding if it's even feasible.
> Perhaps using something like the libmmxnow that avifile uses to detect which
> routines to use on different chipsets for the x86 arch at least.
>
>
> --- >8 ----
> List archives:  http://www.xiph.org/archives/
> Ogg project homepage: http://www.xiph.org/ogg/
> To unsubscribe from this list, send a message to 'vorbis-request at xiph.org'
> containing only the word 'unsubscribe' in the body.  No subject is needed.
> Unsubscribe messages sent to the list will be ignored/filtered.
>

We might get a bit of speedup with Visual Studio.NET's /G6 (optimize for
ppro/pII/pIII), but there's no telling at this point. the oggenc.exe that's
published for Windows is optimized for speed (at least as far as MSVC++ 6
will do, at any rate).

If you want more speed, someone'll have to spring for Intel's optimizing
compiler. I don't know if AMD has its own, however.

<p>--- >8 ----
List archives:  http://www.xiph.org/archives/
Ogg project homepage: http://www.xiph.org/ogg/
To unsubscribe from this list, send a message to 'vorbis-request at xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is needed.
Unsubscribe messages sent to the list will be ignored/filtered.