Ivo schrieb am Sam, 06 Mai 2000:
> > > > Computational speed, and cache size seem to be the most important
> > > > factors. But anything you buy today will have no problem encoding
> > > > (even with "lame -h") at faster than real time.
> > > > My 600mhz athalon is about 5x.
>
> The ~0.3x I get on my Pentium 133Mhz is with -h and CBR, but my surprise
> is at the realtime ability of a 200Mhz... I mean, 200/133 != 3 ;)
> Even so, 266/133 != 3 neither...
> What's the cause of this, or am I wrong here that 200Mhz can reach realtime?
>
> Ivo
OK, here an example of a wave encoded with actual LAME 3.80 (CVS) version
like "lame -h test.wav". The song is named "Angel" from Mezzanine by Massive
Attack, duration 6:20.
Linux, gcc 2.95.2 compiled, Pentium 166 MMX (200MHz):
duration 6:30, rate 0.9744
Win95, Intel4.5 compiled, Pentium 166 MMX (200MHz):
duration 6:47, rate 0.9345
Win95, Intel4.5 compiled, Pentium 133:
duration 10:23, rate 0.6103
So, when you get only rates around 0.3x, then there are following possibilities:
a) your test song is hard to encode
b) you use an older, slower version of LAME
c) your compiler does some strange things
d) your Pentium runs at half speed
Robert
--
e-mail: [EMAIL PROTECTED]
homepage: http://linux.unixcity.de/catwalk/index.html
--
MP3 ENCODER mailing list ( http://geek.rcc.se/mp3encoder/ )
