ffmpeg - Mirror of FFmpeg git repo

	Commit message (Collapse)	Author	Age	Files	Lines
*	rv40dsp: implement prescaled versions for biweight.	Christophe GISQUET	2012-04-10	1	-2/+2
\| \| \| \| \| \| \| \| \| \|	Quite often, the original weights are multiple of 512. By prescaling them by 1/512 when they are computed (once per frame), no intermediate shifting is needed, and no prescaling on each call either. The x86 code already used that trick. Signed-off-by: Ronald S. Bultje <[email protected]>
*	rv34: change most "int stride" into "ptrdiff_t stride".	Ronald S. Bultje	2012-02-20	1	-6/+6
\| \| \| \| \| \|	This prevents having to sign-extend on 64-bit systems with 32-bit ints, such as x86-64. Also fixes crashes on systems where we don't do it and arguments are not in registers, such as Win64 for all weight functions.
*	rv40: NEON optimised weak loop filter	Mans Rullgard	2011-12-16	1	-0/+9
\| \| \| \|	Signed-off-by: Mans Rullgard <[email protected]>
*	rv40: NEON optimised loop filter strength selection	Mans Rullgard	2011-12-14	1	-0/+10
\| \| \| \|	Signed-off-by: Mans Rullgard <[email protected]>
*	rv40: NEON optimised rv40 qpel motion compensation	Mans Rullgard	2011-12-07	1	-0/+75
\| \| \| \| \| \|	Based on patch by Janne Grunau. Signed-off-by: Mans Rullgard <[email protected]>
*	rv40: NEON optimised weighted prediction	Janne Grunau	2011-12-06	1	-0/+6
\| \| \| \|	Signed-off-by: Mans Rullgard <[email protected]>
*	rv40: NEON optimised chroma MC	Janne Grunau	2011-12-06	1	-0/+38
	Signed-off-by: Mans Rullgard <[email protected]>