xine-lib/src/post/deinterlace/plugins, branch 1.2.6

Only compile MMX/SSE code on x86/x86_64.

2014-05-18T20:25:45+00:00

The greedy2frame code uses MMX or SSE instructions. Only compile this code on architectures where they exist.

Fix FSF address in a bunch of files

2013-07-03T20:05:54+00:00

Fixed greedy2frame_template_sse2.c when only 4 registers are available

2012-06-15T09:55:28+00:00

Fix building on non-x86 systems

2012-06-10T06:45:02+00:00

Fixed compiling DeinterlaceGreedy2Frame_SSE2() when only 5 GP registers are available

2012-05-25T08:57:48+00:00

Added SSE2 version of DeinterlaceGreedy2Frame

2012-05-22T08:18:17+00:00

Removed incorrect .align

2012-05-22T08:07:00+00:00

Simplify mmx constant loading

2012-05-22T08:03:45+00:00

Renamed DeinterlaceGreedy2Frame_SSE() to DeinterlaceGreedy2Frame_MMXEXT()

2012-05-22T07:59:31+00:00

simplify greedy2frame deinterlacer a bit

2012-04-15T19:13:26+00:00

Cuts roughly 10% of the instructions (with sse), results should be
identical.
Not sure why it was that complicated in the first place, the
simplification is possible because the code gave a score of 1 to top and
bottom comparisons, and 2 for the middle one, and weaved when all scores
added together were more than 2. This is equivalent to weave when
(cmp(m) AND (cmp(b) OR cmp(t))) which is a much better match for the
available hw instructions. This also reduces the number of constant
loads a lot, and the patch moves up some memory loads a bit which can
never hurt.