Commit graph

10 commits

Author SHA1 Message Date
Andree Buschmann
6cf66eb08c Refacture parts of libfaad filterbank. Faster windowing for 8-short-window sequences.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@27380 a1c6a512-1295-4272-9138-f99709370657
2010-07-11 12:33:35 +00:00
Michael Giacomelli
93caf52db5 Use new MDCT library for libfaad. Speeds up AAC-LC by 2.5MHz.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@24781 a1c6a512-1295-4272-9138-f99709370657
2010-02-20 00:29:31 +00:00
Michael Giacomelli
0a1baa36b1 Fix FS#10174 by correcting an oversimplification of the AAC window switching code I introduced with the unified IMDCT library. Should significantly improve accuracy for all AAC files.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@20821 a1c6a512-1295-4272-9138-f99709370657
2009-04-29 17:44:02 +00:00
Michael Giacomelli
46f85c4c54 Combine the Vorbis, WMA and AAC IMDCT functions and put them into the codeclib. Combined IMDCT is now based on existing Tremor transform. Reduces CPU for 192k AAC by 21MHz on Coldfire, and 5MHz on PP5024. WMA and Vorbis should have no functional changes since they already used this code. Further optimization is possible and would benefit all 3 codecs.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18412 a1c6a512-1295-4272-9138-f99709370657
2008-09-04 18:02:10 +00:00
Michael Giacomelli
54903eb7fa Use WMA windowing optimizations for AAC. Saves about 3.5MHz on Coldfire, and about 2 MHz on ARM. Thanks to amiconn for help with Coldfire ASM improvements. Next step: dump faad IMDCT.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18238 a1c6a512-1295-4272-9138-f99709370657
2008-08-10 20:19:38 +00:00
Michael Giacomelli
b9eb18260f Too much on the last commit.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18085 a1c6a512-1295-4272-9138-f99709370657
2008-07-17 18:36:47 +00:00
Michael Giacomelli
1334738071 Use Tremor IMDCT for WMA. Gives a ~20% speedup on ARM and coldfire. All my test samples gave equivilent or better accuracy (>>16 bit), but there may still be problems. Code becomes somewhat less readable since the IMDCT has bits of Vorbis in it, but this is not a serious issue and the old ffmpeg transform remains in SVN if anyone wants it. Also, WMA now passes Vorbis as the fastest transform codec on ARM, although MPC remains the fastest lossy codec overall.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@18084 a1c6a512-1295-4272-9138-f99709370657
2008-07-17 17:43:49 +00:00
Magnus Holmgren
3fa5e5f592 Apply a bunch of simple AAC decoder optimizations. Biggest speedup is on ColdFire targets, but ARM targets benefits too. Allows realtime playback of some AAC files on Iriver targets (H1x0, H3x0). Remove support for some rarely used AAC profiles to reduce code size a bit.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@11038 a1c6a512-1295-4272-9138-f99709370657
2006-09-24 19:00:29 +00:00
Dave Chapman
798a4f3533 Changes to make libfaad compile in Rockbox. Also remove compiler warnings, use some IRAM (IRAM usage needs reviewing) and drastically reduce the stack usage
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7700 a1c6a512-1295-4272-9138-f99709370657
2005-10-31 20:33:27 +00:00
Dave Chapman
65de1cc6af Initial check-in of unmodified libfaad (part of the FAAD2 project). This is the last version of libfaad available under the GPL - the state of FAAD2 CVS at midnight on 2005-02-01
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7699 a1c6a512-1295-4272-9138-f99709370657
2005-10-31 18:56:29 +00:00