[MEncoder-users] Fwd: Questions on Mencoder performace
Corey Hickey
bugfood-ml at fatooh.org
Tue Jun 6 19:11:33 CEST 2006
larrystotler at netscape.net wrote:
> -----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 know specifically about your systems, but I wouldn't expect much
performance out of a P4. I did some rough tests with lavc and x264 a
while back and found that a 1.2 GHz Athlon Thunderbird was outperforming
a 1.7 GHz P4 by 10-20%. As far as I know early Athlon processors were
roughly equivalent to late P3s, clock-for-clock, so the numbers you
posted don't seem out of line.
>> H.264 is indeed higher quality, but yes, for decoding, it's quite a bit
>> slower than MPEG-4. If MPEG-4 is still too slow for you, then try
> MPEG-2
>> or MPEG-1. Decoding is faster, but, of course, the encoding isn't as
>> efficient and they won't look quite as good.
>
> I notice very little difference if any between an MPEG2 source file and
> the XviD that takes about 1/8 of the space. That why I do everything at
> 1536. Some things would probably look fine at 768 or 1024, but that
> would mean testing each file and checking the quality(like bubbles -
> they show good). With slow systems, it takes too long to see if a lower
> bitrate with a smaller file size would give me the quality I am looking
> for.
Higher bitrates will take more CPU power, regardless. For a fixed
bitrate, MPEG-2 and MPEG-1 take less processing than MPEG-4. As for RC's
advice about the performance gain being offset by needing higher
bitrates, that may well be the case.
-Corey
More information about the MEncoder-users
mailing list