before:
5225 decicycles in IDCT, 32756 runs, 12 skips

after:
5057 decicycles in IDCT, 32765 runs, 3 skips
Reviewed-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

This also tests LINEAR_CORE_FLT_SSE

Found-by: jamrial
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

The code was missing 1 bit in the src format
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

* commit 'e2834567':
  On2 AVC decoder

Conflicts:
	Changelog
	configure
	libavcodec/avcodec.h
	libavcodec/codec_desc.c
	libavcodec/version.h
Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit 'd7eb8f90':
  fic: Make warning message more accurate
  fic: Remove redundant clips
  fic: Simplify alpha blending

See: 14da7f9eMerged-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

The equations can't overflow or underflow anyway.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Fixes Ticket3564
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Fix trac ticket #3523.

Restore the old name, which was more meaningful and consistent with the
names of the other examples.

Fixes assertion failure
Fixes Ticket3575
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

* commit 'b0bdc2a7':
  avutil: move av_get_time_base_q() after include rational.h

See: c7251fecMerged-by: Michael Niedermayer <michaelni@gmx.at>

* commit '502512ea':
  avutil: Add av_get_time_base_q()

Conflicts:
	doc/APIchanges
	libavutil/utils.c
	libavutil/version.h

See: dac7e8a9Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit '9155c595':
  fic: Support rendering cursors

Not merged as the commit is missing changes that where replied to with "done" on ffmpeg-devel
Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit '40b331e1':
  fic: Use proper quantization matrix index

See: 6d149d28Merged-by: Michael Niedermayer <michaelni@gmx.at>

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

* commit '3956a5e0':
  aarch64: NEON vorbis_inverse_coupling
Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit '8f9fe6ae':
  aarch64: NEON fixed/floating point MPADSP apply_window
Merged-by: Michael Niedermayer <michaelni@gmx.at>

Fix compilation
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

* commit 'f4d5a2cc':
  aarch64: NEON float to s16 audio conversion
Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit 'ee2bc597':
  aarch64: NEON float (i)MDCT
Merged-by: Michael Niedermayer <michaelni@gmx.at>

* commit '650c4300':
  aarch64: NEON float FFT
Merged-by: Michael Niedermayer <michaelni@gmx.at>

Fix compilation
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

This fixes usage of AV_TIME_BASE_Q in C++ applications, which
cannot use compound literals directly in their code.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>

This fixes usage of AV_TIME_BASE_Q in C++ applications, which
cannot use compound literals directly in their code.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>

The matrices are not zigzagged.

Fixes artefacting.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

The matrices are not zigzagged.

Fixes artefacting.
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>

From the ARMv7 NEON version. 16 times faster as the C version, overall
more than 12% faster vorbis decoding on Apple's A7.

30%/25% (fixed/float) faster mp3 decoding on Apple's A7. The floating
point decoder is approximately 7% faster.

Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>