| commit | d236065b3690e8c7d9508a1483f3353d188d0786 | |
| author | jethead71 <jethead71@a1c6a512-1295-4272-9138-f99709370657> | |
| Sun, 2 May 2010 02:44:45 +0000 (2 02:44 +0000) | ||
| committer | jethead71 <jethead71@a1c6a512-1295-4272-9138-f99709370657> | |
| Sun, 2 May 2010 02:44:45 +0000 (2 02:44 +0000) | ||
| tree | 836772d5973a0782d1a1dd4345e5508234b92fe6 | treesnapshot (tar.gz zip) |
| parent | fcc23246bc1f7dc57c9fc812c0ff0701cfc144e5 | commitdiff |
Do some SPC codec optimizing for ARMv6 (as a training exercise), tweak realtime BRR for all CPU that use it, add Gaussian ASM optimization for all ARM that can use it. Add some LIKELY/UNLIKELY branch hints. On Gigabeat-S gives +22% speedup. For Gigabeat F, about +5% speedup. For less-powerful players, no real change aside possibly from branch hints.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25771 a1c6a512-1295-4272-9138-f99709370657
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25771 a1c6a512-1295-4272-9138-f99709370657
| apps/codecs/libspc/spc_codec.h | diffblobblamehistory | |
| apps/codecs/libspc/spc_dsp.c | diffblobblamehistory |