lame benchmarks (pun intended)

[unusedunused]

thats nothing new to me that Pa6 is slow.its a embedded CPU with less performance /MHZ.
some years ago i post on amigaworld links that show on some rare benchmarks that pa6 is slow.of course there are few benchmarks for pa6 because they want not show that it is slow i guess ;-)

but the fact that Apple choose is X86 depend i guess too that pa6 is not fast.Apple miss long time a fast and power save notebook CPU from motorola and pa6 does not fill the gap, so they give up PPC.

What's interesting about this benchmark is that it takes my Q9450 8 seconds to perform the same test.

Code: [Select]


karlos@Megaburken-II:~/Desktop$ time lame AKsack.wav
LAME 3.98.2 64bits (http://www.mp3dev.org/)
Using polyphase lowpass filter, transition band: 16538 Hz - 17071 Hz
Encoding AKsack.wav to AKsack.wav.mp3
Encoding as 44.1 kHz j-stereo MPEG-1 Layer III (11x) 128 kbps qval=3
    Frame          |  CPU time/estim | REAL time/estim | play/CPU |    ETA
 10529/10529 (100%)|    0:08/    0:08|    0:08/    0:08|   33.665x|    0:00
-------------------------------------------------------------------------------
   kbps        MS  %     long switch short %
  128.0      100.0        76.1  13.4  10.5
Writing LAME Tag...done
ReplayGain: +0.5dB

real    0m8.175s
user    0m8.120s
sys     0m0.060s

Those old PPC machines don't look too shabby under the circumstances.

you use a non SSE Version on windows.On my I5 760 (2.8 GHZ 3.3 GHZ turbo boost) it need 4 sec.see the output of CPU features (CPU features: SSE (ASM used), SSE2 (ASM used)).lame seem not run on multi core.Because i choose in windows shell 1 CPU.speed is same 4 sec.also i get only CPU load 25% seem 1 Core is active and the 3 cores (75% sleep).I guess multithread is not need in lame , because the frontend do it and start more lame threads at once.

my results are 4.5* faster as X1000 or in numbers, when i downlclock my X86 from  (3.3 GHZ /4.5) = 0.733 GHZ ore 733 MHZ it is as fast as X1000.

this is the result i get with that files for 64 bit from that page

http://lame.sourceforge.net/links.php#Binaries

i go to this

http://www.rarewares.org/mp3-lame-bundle.php

-------------------
C:\Users\pc>E:\tmp\lame.exe E:\AKsack.wav
LAME 3.99.4 64bits (http://lame.sf.net)
CPU features: SSE (ASM used), SSE2 (ASM used)
Using polyphase lowpass filter, transition band: 16538 Hz - 17071 Hz
Encoding E:\AKsack.wav to E:\AKsack.mp3
Encoding as 44.1 kHz j-stereo MPEG-1 Layer III (11x) 128 kbps qval=3
    Frame          |  CPU time/estim | REAL time/estim | play/CPU |    ETA
 10529/10529 (100%)|    0:04/    0:04|    0:04/    0:04|   55.937x|    0:00
-------------------------------------------------------------------------------
   kbps        MS  %     long switch short %
  128.0      100.0        74.4  13.4  12.2
Writing LAME Tag...done
ReplayGain: +0.5dB

C:\Users\pc>
------

[unusedunused]

Tested with WinUAE. Lame 3.99.3 compiles it in 58 secs.

:laughing:

whre you have download the 3.99.3 ?
I have only 3.98.4 find

here on I5 760 need 32 sec in winuae.on 68k it use of course no SSE or any asm code line.time is simular to the 1. mac mini result, so another argument, that this test use no altivec on Mac mini and the values of 18 sec with altivec can be true.

The I5 I7 give a big speedup to the old Core DUO or QUAD.but when buy a new system today you can only buy new I5 for low price or better.and X1000 is tell as a new system.My system is over 1 year old.

but winuae can use native X86 lame.you need only execute winuaelame program with parameters to start the native lame you install in X86