In message <EHEOLOLLINEMBNHDJDFLOEDDHEAA.andy@...>
"Andy Mucho" <andy@...> wrote:

> Go for the AAN DCT.. Using that I'm currently at 0.31 MegaPixels per second
> (about 8fps) using 8:1 compressed images. That's still in a complete C++
> implementation with no assembler yet. I see maybe a marginal increase in the
> DCT core, though the compiler has done a pretty cool job.
> I expect with some hand tweaking to push this to maybe 10fps, and maybe then
> eek some more speed through other optimisations.

Hmm, I have now implemented AAN DCT and my decoder now takes on a 233Mhz
StrongARM 2.9cs to decode a 17kb 240x160 Jpeg to 32768 colours with
ordered dithering. This speed comes quite near to another jpeg implemenation
on this computer which i believe is quite good optimized.
When I take only the difference in clock speed into account, it would
take about 0.4s on gba.
This is of course somewhat different to your figures, therefore i am
wondering if you just stated the speed of your dct core or that of
the complete decoder.
My dct core seems to take about 0.3cs for the above picture, which means
that there is certainly still a lot of room for optimisation in other
areas...

--
exoticorn/icebird