| Commit message (Collapse) | Author | Age |
| |
|
|
|
|
| |
faster than the C code both on ARM7TDMI (tested on PP5002 and PP5022) and on ARM1136JF-S (tested on Gigabeat S). If it is slower on ARM9*, it should be disabled for ARM9 only.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25937 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
|
|
| |
Using current gcc it only makes decoding a tiny bit slower
Using eabi gcc it makes no speed difference
Tested on fuzev1
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@25929 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
identical implementations, always have LUT in iram (gives a *tiny* speedup on coldfire), make the clz based function return the same value as the non clz based function for 0 input to be safe (slows down flac ~2% on the gigabeat S)
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@23858 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
one flac 8 sample by 12%.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@23783 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
never defined for the sim.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@14711 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@8931 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7817 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
implementation by Mark Arigo.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7814 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7678 a1c6a512-1295-4272-9138-f99709370657
|
|
|
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@7656 a1c6a512-1295-4272-9138-f99709370657
|