Ronald S. Bultje
6341838f3c
Use word-writing instead of dword-writing (with two cached but otherwise ...
unchanged bytes) in the horizontal simple loopfilter. This makes the filter
quite a bit faster in itself (~30 cycles less on Core1), probably mostly
because we don't need a complex 4x4 transpose, but only a simple byte
interleave. Also allows using pextrw on SSE4, which speeds up even more
(e.g. 25% faster on Core i7).
Originally committed as revision 24638 to svn://svn.ffmpeg.org/ffmpeg/trunk
2010-07-31 23:13:15 +00:00
2010-07-11 22:52:55 +00:00
2010-07-19 22:38:23 +00:00
2010-07-06 17:48:23 +00:00
2010-07-31 14:50:51 +00:00
2010-07-11 22:52:55 +00:00
2010-06-04 04:46:26 +00:00
2010-07-22 00:39:49 +00:00
2010-07-31 14:50:51 +00:00
2010-06-23 19:20:46 +00:00
2010-07-19 22:38:23 +00:00
2010-03-18 15:00:17 +00:00
2010-07-18 20:06:42 +00:00
2010-07-06 17:48:23 +00:00
2010-07-06 17:48:23 +00:00
2010-07-06 16:58:54 +00:00
2010-07-22 00:39:49 +00:00
2010-04-20 14:45:34 +00:00
2010-06-23 19:20:46 +00:00
2010-07-01 10:29:47 +00:00
2010-07-01 10:29:47 +00:00
2010-03-06 22:36:36 +00:00
2010-07-29 22:45:21 +00:00
2010-04-20 14:45:34 +00:00
2010-04-20 14:45:34 +00:00
2010-07-31 14:50:51 +00:00
2010-05-11 00:22:50 +00:00
2010-06-24 08:53:32 +00:00
2010-03-14 17:50:12 +00:00
2010-07-21 10:02:03 +00:00
2010-07-11 22:53:01 +00:00
2010-05-28 07:01:34 +00:00
2010-04-17 02:04:30 +00:00
2010-04-20 14:45:34 +00:00
2010-04-20 14:45:34 +00:00
2010-04-20 14:45:34 +00:00
2010-07-31 23:13:15 +00:00
2010-07-31 23:13:15 +00:00
2010-07-23 21:46:30 +00:00
2010-07-21 22:45:16 +00:00
2010-07-11 22:53:01 +00:00
6341838f3c