- 09 Dec, 2015 1 commit
-
-
Ganesh Ajjanagadde authored
This gets rid of virtually useless hardcoded tables hackery. The reason it is useless is that a 320 element lut is anyway placed regardless of --enable-hardcoded-tables, from which all necessary tables are trivially derived at runtime at very low cost: sample benchmark (x86-64, Haswell, GNU/Linux, single run is really what is relevant here since looping drastically changes the bench). Fluctuations are on the order of 10% for the single run test: 39400 decicycles in aacsbr_tableinit, 1 runs, 0 skips 25325 decicycles in aacsbr_tableinit, 2 runs, 0 skips 18475 decicycles in aacsbr_tableinit, 4 runs, 0 skips 15008 decicycles in aacsbr_tableinit, 8 runs, 0 skips 13016 decicycles in aacsbr_tableinit, 16 runs, 0 skips 12005 decicycles in aacsbr_tableinit, 32 runs, 0 skips 11546 decicycles in aacsbr_tableinit, 64 runs, 0 skips 11506 decicycles in aacsbr_tableinit, 128 runs, 0 skips 11500 decicycles in aacsbr_tableinit, 256 runs, 0 skips 11183 decicycles in aacsbr_tableinit, 509 runs, 3 skips Tested with FATE with/without --enable-hardcoded-tables. Reviewed-by: Rostislav Pehlivanov <atomnuker@gmail.com> Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
-
- 20 Jul, 2015 1 commit
-
-
Jovan Zelincevic authored
Create tables for fixed point code. Signed-off-by: Nedeljko Babic <nedeljko.babic@imgtec.com> Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
-
- 06 Sep, 2014 1 commit
-
-
Reimar Döffinger authored
For sbr_qmf_window_us there is even a question if it maybe should be fully hardcoded all the time. Since half of it is coded, it ends up in .data and not .bss. Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>
-
- 25 Sep, 2012 2 commits
-
-
Derek Buitenhuis authored
This code runs on the host and should not use libm.h, which is meant for the target. This reverts commit 2768b717.
-
Derek Buitenhuis authored
Needed for cbrtf fallback on systems which lack it. Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
-
- 19 Mar, 2011 1 commit
-
-
Mans Rullgard authored
Signed-off-by: Mans Rullgard <mans@mansr.com>
-
- 27 Jun, 2010 2 commits
-
-
Diego Pettenò authored
Two macros (WRITE_ARRAY and WRITE_ARRAY_2D) take the prefix (modifiers) (not all tables are static, and they might not be constant either), the type, and the name of the array. It'll be copied with same name and type, and with the correct size of the currently-defined object. Originally committed as revision 23821 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
Diego Pettenò authored
This drops one parameter from the functions' macros, and require structures to be typedeffed, but ensures that it is possible to map 1-to-1 the type to the function name. Originally committed as revision 23820 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 01 Apr, 2010 1 commit
-
-
Reimar Döffinger authored
Originally committed as revision 22761 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 14 Mar, 2010 1 commit
-
-
Reimar Döffinger authored
Originally committed as revision 22527 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 26 Nov, 2009 1 commit
-
-
Reimar Döffinger authored
Originally committed as revision 20627 to svn://svn.ffmpeg.org/ffmpeg/trunk
-
- 28 Oct, 2009 1 commit
-
-
Reimar Döffinger authored
Reduces .bss size by about 194 kB. Originally committed as revision 20400 to svn://svn.ffmpeg.org/ffmpeg/trunk
-