| Commit message (Collapse) | Author | Age |
| |
|
|
|
|
|
|
|
|
|
|
|
| |
We can't pop into pc on ARMv4t when using thumb: the T bit won't be
modified if we are returning to a thumb function
Code running on ARMv4t should use the new ldrpc / ldmpc macros instead
of ldr pc, [sp], #4 and ldm(cond) sp!, {regs, pc}
No modification on pure ARM builds and ARMv5+
Note: USE_THUMB is currently never defined, no targets can currently be
built with -mthumb, see FS#6734
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@26756 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@22577 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
for one function even when building for ARMv6.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21917 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
compiler for use in asm files, and use it in arm jpeg idct. See apps/apps.make, apps/core_asmdefs.c, and apps/recorder/jpeg_idct_arm.S for details.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21831 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21620 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21612 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
16-bit constants at a time with ldrd. Not useful for ARMv4, since one load per constant would still be needed, and limited range of ldrsh would force multiple copies of table.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21535 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
from usat for final output.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21526 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
| |
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21520 a1c6a512-1295-4272-9138-f99709370657
|
| |
|
|
|
|
| |
about inline asm, change loop condition to be a bit safer in case of bad values being passed.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21349 a1c6a512-1295-4272-9138-f99709370657
|
|
|
For >8-point vertical IDCT, transpose the coefficients while decoding them, so that the vertical IDCT can read in rows rather than columns. This improves speed a bit for this size even using the C IDCT.
Remove inline ARM asm, replacing it with an external file containing pure asm IDCT functions.
Add jpeg_ prefix to JPEG IDCT functions since some of them will now be visible globally.
git-svn-id: svn://svn.rockbox.org/rockbox/trunk@21345 a1c6a512-1295-4272-9138-f99709370657
|