Rockbox mail archiveSubject: Re: Optimized bitswap
Re: Optimized bitswap
From: Linus Nielsen Feltzing <linus_at_haxx.se>
Date: Sun, 18 Aug 2002 22:18:11 +0200
On Sun, 18 Aug 2002 22:10:37 +0200, Magnus Holmgren wrote:
> How much?
Player: 12MHz, Recorder: 11.0592MHz
> Yes, playback is fine. No other problems noticed (but I haven't
> tested *that* much yet).
It shows best when playing high-bitrate songs, since the bitswap
pretty much determines the watermark level.
> And maybe word fetches are faster than byte fetches? E.g., aren't
> there architectures that always fetches e.g. longs, even for byte
All accesses take the same time, bytes, words, longwords. However,
your loop would probably (if GCC delivers) read a word of MP3 data
and keep it in a register for the two table lookups. I based my
"calculations" on that assumption.
> Are there any L1 caches that could keep (much of) the table in
No caches, unfortunately.
-- Linus Nielsen Feltzing, linus_at_haxx.se on 2002-08-18Received on 2002-08-18