[vorbis] Windows XP and MP3

[Segher Boessenkool]

Adam Ottley wrote:
> 
> On April 13, 2001 12:36 pm, you wrote:
> > Segher Boessenkool wrote:
> 
> > Maybe it's because I was just looking at the task manager,
> > but still, Winamp mp3 oscilates between 0% and 2% while
> > Winamp ogg is at 5%-6%.
> >
> I've been getting some wild differences here.  I've found Wintop to be the
> best gauge of CPU use in Win9x (Wintop is in the kerneltoys package, just do
> a search on microsoft.com for it), and I get a much smaller difference
> between the Winamp 2.22 Mp3 decoder and Ogg beta 4 in Winamp.  On my P2-400,
> Mp3 runs about 6-7% where Ogg is about 8%.  I also tried it on a vanilla

This is too _small_ a difference to be realistic.

> P200, and Mp3 took ~20-22% where Ogg was ~24-25%.  Both were in Win98.

These numbers are _way_ too high for a 200 MHz cpu, even if it is a P5.

> In Linux, I tested "mpg123 -t" vs. "ogg123 -d null" using the time program,
> and mpg123 was twice as fast as ogg123 at decoding two same-length files.

This sounds about right.

> I guess that your results with Mp3 vary with which decoder you use.  I once

Sure. And version of the decoder, and compiler and compiler flags used, etc.

> tried out the decoder Winamp started using with 2.666, and it used a little
> bit more CPU than 2.22.  On the other hand, The mpg123-based plugin by Naoki
> Shibata had slightly less CPU use, about 5-6%.

This on the P200? That's still a bit high...

Cheers,

Segher

--- >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.