[MEncoder-users] Fwd: Questions on Mencoder performace

[Eli Crumrine]

larrystotler at netscape.net | Tue, 06 Jun 2006 02:01:42 -0400

> -----Original Message-----
> From: Corey Hickey <bugfood-ml at fatooh.org>
> 
> >This thread is a bit confusing because there are two
> >somewhat-separate performance topics we're talking about: encoding
> >and decoding.
> 
> Well, actually, I was looking for info on why a 2.4Ghz mobile 
> Celeron(p4) w/ 256k L2 is only about 30-50% faster than a P3 Xeon 
> 500Mhz on pass + and why it was only about 200-250% faster on 
> pass=2:bitrate=1536.  I was also trying to see if it had to do with
> the hardware like a memory bottleneck or too small L2 cache or the
> encoding settings.  I noticed no difference between 512k L2 Xeons and
> 2048k L2 Xeons.  However, if smaller than 512 is a problem, then that
> may be a bottleneck.

I don't have the exact differences (they are readily available online),
but PIV celerons are significantly worse-performing than their
full-fledged (Northwood core) brethren.  Their architecture is quite
different besides just cache size - as you have found they do not
perform anywhere near as well as their clock speed would imply.

If you are interested, I'd be happy to run benchmarks on my P4 2ghz
(512k L2, 400mhz fsb) to see the differences between it and a
faster-clocked celeron.

-- 
Eli C.
2006:06:08