From: Pedro Vasconcelos <pbv_at_st-andrews.ac.uk>
Date: Fri, 15 Jul 2005 20:17:15 +0100

On Fri, 15 Jul 2005 12:06:53 -0600
Ryan Jackson <rdjackso_at_gmail.com> wrote:

>
> Incidentally, any idea which other parts of Tremor could be optimized?
> I have some Q9 and Q10 files that still have buffering problems on
> playback (can't be decoded fast enough).

The optimizations that I made were fairly straightforward: writing short
asm routines for 32-bit arithmetic in the hooks provided and placing
some critical arrays in the fast IRAM.

>From discussions with Thom, I presume there should a big scope for
optimizations in the actual algorithms used, particularly in the MDCT
code. Unfortunately I don't know enough digital signal processing to do
it and don't have spare time at the moment to go out and learn more :-(

The other difficulty is the lack of profiling in the actual iriver
hardware. I have done Tremor profiling on my P4 to get an idea of what
were the critical functions, but the Coldfire is very diferent (cache,
pipelines, etc) so it all guesswork.

By the way, I usually use Q5-Q6 but did some tests some time ago with
"tough" Q10 files (harpsichord music) that average above 500kpbs and
they played with no drop-outs. Maybe you could you send me a (short)
sample of your problem files?

Pedro
_______________________________________________
http://cool.haxx.se/mailman/listinfo/rockbox
Received on 2005-07-15