On May 27, 2006, at 12:16 PM, Francesco Romani wrote:
On Sat, 27 May 2006 09:08:08 -0500
[EMAIL PROTECTED] wrote:
[...]
Performance is pretty good. I transcoded a VOB to mpeg4/mp3 with
ffmpeg and averaged 38 fps (on a G5 dual 2.0).
Uhm, this sound quite strange to me since I got _at least_ ~40 fps
in similar circustances on a single-core/single-processor Athlon64
3200+.
(No CPU flame intended, I like G4/G5s! :) )
It's the first time I've ever run transcode, so I was just using some
of the performance metrics I've seen in the mailing archive. ~40 felt
pretty good when I saw lots of complaints getting more than 10 fps!
And I'm not worried about a flame... it's just a computer. It's
already 3 years old so I think it's doing okay.
Maybe we could add a benchmark page to the wiki. I'd be happy to run
benchmarks on my machine against some reference movie file if anyone
thinks that would be helpful. At minimum we could help catch
performance regressions between code changes.
Any benefit to compiling transcode from CVS HEAD? Are there specific
branches considered relatively stable outside of the tarball release?
Well, if you're a transcode enthusiast and you like to live on the
bleeding
edge, or if you want development, or finally if you want help
debugging/testing, there is a lot of benefits using CVS HEAD since CVS
is changed a lot since 1.0.2, and changes won't end here, there is
still
a lot to do planned or on going before 1.1.0 release, and even more
after.
If I help anywhere it will be in cleaning up the command-line
switches (or documenting when/why someone would use them). My head is
still spinning from reading the man page.
Changelog is already pretty huge, I'll extract only a few highlights:
- completely rewritten aclib (low-level asm-acclerated routine
library),
with new optimizations for i386/amd64. Unfortunately, there is
nothing
for Altivec because we (current active developers) lack of hardware,
and because I lack expertise :P
Altivec is deprecated for the Mac line anyway. We'll be happy to take
advantage of any and all i386 optimizations!
[big snip]
That changelog looks pretty serious. Does HEAD even compile and work
with all those architectural changes going on? Is there a stable branch?
Uh, just one last word. I've introduced a simple WAV I/O support
library;
of course I'd like to expand and improve it, but unfortunately I'm
not fast
enough in designing/coding/testing and days are "only" 24hr long ;)
Well, enough drama: the problem is that library isn't tested at all on
big-endian systems (lack of hardware!), and I seriously suspect
that's broken
on those system.
For interested people, there is a tarball with wavlib alone
avalaible here:
http://fromani.exit1.org/
(duh, this version is pretty outdated, I'll updated ASAP. If
someone is
interested just let me know so I'll speedup update process :P)
My Powermac is big endian (PPC) so I could lend a hand with this
test. Just drop me a note here or send me a direct email.
cr
