Statistics
| Branch: | Revision:

ffmpeg / postproc / yuv2rgb_altivec.c @ 42225a30

History | View | Annotate | Download (29.4 KB)

# Date Author Comment
9c445fbe 04/27/2006 09:42 PM Alan Curry

Fix some bugs handling input that is not aligned at 16 bytes or has
stride!=width.

Originally committed as revision 18323 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

340ea251 03/13/2006 03:46 AM Alan Curry

Support all 4 of ARGB/RGBA/BGRA/ABGR unscaled conversions, with more
consistent naming of functions

Originally committed as revision 17845 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

cd92221a 02/18/2006 01:08 AM Alan Curry

Just a comment update, replacing a FIXME to reflect the new expectation of
how altivec_yuv2packedX is supposed to be used

Originally committed as revision 17643 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

cbddd5df 02/17/2006 05:01 AM Alan Curry

Fix vec_clip for gcc's that don't handle (vector signed short){16} according
to spec; also convert a few vec_splat's to vec_splat_{s,u}*

Originally committed as revision 17639 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

d33d485e 02/11/2006 02:16 PM Alan Curry

Move the v{Y,C}CoeffsBank vectors into the SwsContext, filling them in just
once when the scaler is initialized, instead of building them and freeing
them over and over. This gives massive performance improvements.
patch by Alan Curry, pacman*at*TheWorld*dot*com...

7d20ebff 02/09/2006 12:29 AM Alan Curry

Correct RGB vs. BGR confusion, the macros vec_mstrgb24 and vec_mstbgr24 each
do the opposite of what they say.
The vec_mstrgb24 and vec_mstbgr24 macros should be opposites and not perform
the same things.
patch by Alan Curry, pacman_at_world_dot_std_dot_com...

3845b56d 02/08/2006 01:14 PM Alan Curry

altivec_yuv2packedX() ignores the requested output format and unconditionally
outputs RGBA. This patch supports 6 output formats and prints an error message
if it is asked to provide an output format it is not capable of.
patch by Alan Curry, pacman_at_world_dot_std_dot_com...

5edb653b 02/08/2006 08:20 AM Alan Curry

AltiVec operations need to have memory aligned on 16-byte boundaries.
patch by Alan Curry, pacman at world dot std dot com

Originally committed as revision 17559 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

be9d060d 02/08/2006 08:16 AM Alan Curry

vYCoeffsBank and vCCoeffsBank are allocated and initialized using incorrect
sizes based on the image width instead of height.
patch by Alan Curry, pacman at world dot std dot com

Originally committed as revision 17558 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

b2d374c9 11/14/2005 12:30 AM Diego Biurrun

Unify include paths, -I.. is in CFLAGS.

Originally committed as revision 16986 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

582552fb 10/05/2004 07:11 PM Luca Barbato

postproc/yuv2rgb_altivec.c compile fix
yuv2rgb_altivec_init_tables does initialize the SwsContext vectors.
missing vec_splat.
patch by (Luca Barbato <lu_zero at gentoo dot org>) and (Romain Dolbeau <dolbeau at irisa dot fr>)

Originally committed as revision 13565 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

95d45b1e 07/17/2004 08:53 AM Alex Beregszaszi

simplify the init

Originally committed as revision 12838 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

84fdd642 07/17/2004 07:01 AM Alex Beregszaszi

some fixes

Originally committed as revision 12837 to svn://svn.mplayerhq.hu/mplayer/trunk/postproc

a31de956 06/27/2004 12:07 AM Michael Niedermayer

altivec yuv->rgb converter
orginal patch by (Marc Hoffman <mmh at pleasantst dot com>)
critical fixes by (Reza Jelveh <reza.jelveh at tu-harburg dot de>)

known bugs/issues, which should be fixed ASAP by someone who has a ppc:
0..255 vs. 16..235
unneeded recalculation of tables...