Vorbis dev - Feb 2002 - Slightly OT: Vorbis encoding benchmarks

I've been talking to some people about benchmarks for different
operating systems and CPUs, and it would seem that a good way to gain
some exposure for Ogg Vorbis would be to push oggenc as a benchmarking
application when sites such as ExtremeTech, AnandTech, Ars Technica,
etc. post system comparisons.

I know that MP3 encoding is used as a common "media" benchmark, so it
would be nice to get oggenc out there.  In order to be a good CPU/memory
bandwidth benchmark it would need to reduce the amount of disk access to
the start/end of the process, and possibly have variable sized memory
buffers for processing.

Anyway, just a thought as a way to gain exposure for Ogg Vorbis.

Brian

<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-dev-request@xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is
needed.
Unsubscribe messages sent to the list will be ignored/filtered.

On Tue, 12 Feb 2002, Brian Hook wrote:
> I've been talking to some people about benchmarks for different
> operating systems and CPUs, and it would seem that a good way to gain
> some exposure for Ogg Vorbis would be to push oggenc as a benchmarking
> application when sites such as ExtremeTech, AnandTech, Ars Technica,
> etc. post system comparisons.
<p>Sounds like an interesting idea.  Several people have wandered into
#vorbis
asking about this because they were curious how much CPU they needed to be
able to encode for streaming.

<p>> I know that MP3 encoding is used as a common "media"
benchmark, so it
> would be nice to get oggenc out there.  In order to be a good CPU/memory
> bandwidth benchmark it would need to reduce the amount of disk access to
> the start/end of the process, and possibly have variable sized memory
> buffers for processing.
<p>Does this mean that oggenc should periodically load big chunks of the
PCM data
from disk into memory?  Or would benchmarkers really want an oggenc flag that
forces it to preload the whole WAV into memory and buffer all of the Vorbis
output until the end?


---
Stan Seibert

<p><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-dev-request@xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is
needed.
Unsubscribe messages sent to the list will be ignored/filtered.

On Tue, Feb 12, 2002 at 02:29:21PM -0800, Brian Hook
wrote:
> I know that MP3 encoding is used as a common "media" benchmark,
so it
> would be nice to get oggenc out there.  In order to be a good CPU/memory
> bandwidth benchmark it would need to reduce the amount of disk access to
> the start/end of the process, and possibly have variable sized memory
> buffers for processing.
I'm pretty sure I saw some Linux benchmarking site use oggenc as part
of the comparison between the P4 and new athlon.

--- >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-dev-request@xiph.org'
containing only the word 'unsubscribe' in the body.  No subject is
needed.
Unsubscribe messages sent to the list will be ignored/filtered.