Commit Graph

718 Commits

Author SHA1 Message Date
Michael Niedermayer
cb416a7d79 Merge commit '4c81613df499ba81d64ea102b38d0c6686cc304c'
* commit '4c81613df499ba81d64ea102b38d0c6686cc304c':
  arm: mlpdsp: handle pic offset calculation in a macro

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-12-10 00:51:26 +01:00
Michael Niedermayer
824932dc47 Merge commit '581c7f0e12b1fa39f73d683e54d6ecda0772c5a9'
* commit '581c7f0e12b1fa39f73d683e54d6ecda0772c5a9':
  arm: make ff_mlp_filter_channel_arm and ff_mlp_rematrix_channel_arm position independent

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-12-10 00:39:00 +01:00
Janne Grunau
4c81613df4 arm: mlpdsp: handle pic offset calculation in a macro
Makes the code easier to read since it hides different offset
calculations for arm and thumb mode.
2014-12-09 22:00:08 +01:00
Janne Grunau
581c7f0e12 arm: make ff_mlp_filter_channel_arm and ff_mlp_rematrix_channel_arm position independent
No significant difference in used cpu cycles on a cortex-a9.
2014-12-09 22:00:08 +01:00
Michael Niedermayer
16e65419ed Merge commit 'f963f80399deb1a2b44c1bac3af7123e8a0c9e46'
* commit 'f963f80399deb1a2b44c1bac3af7123e8a0c9e46':
  arm: Use .data.rel.ro for const data with relocations

Conflicts:
	configure

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-12-09 11:58:13 +01:00
Martin Storsjö
f963f80399 arm: Use .data.rel.ro for const data with relocations
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-12-09 11:43:25 +02:00
Michael Niedermayer
5054d2a92b Merge commit 'b280c6202b28b371a8d96850194fd69d7ad5dcc0'
* commit 'b280c6202b28b371a8d96850194fd69d7ad5dcc0':
  arm: fft_vfp: Unify the behaviour in ff_fft_calc_vfp between arm/thumb

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-12-08 12:42:47 +01:00
Michael Niedermayer
8554a10992 Merge commit 'ae81576414f2d2083d3118fb4abe1ebc5a7a4c54'
* commit 'ae81576414f2d2083d3118fb4abe1ebc5a7a4c54':
  arm: fft_vfp: Add a missing "endconst" when building in thumb mode

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-12-08 12:31:33 +01:00
Martin Storsjö
b280c6202b arm: fft_vfp: Unify the behaviour in ff_fft_calc_vfp between arm/thumb
Don't include the function pointer table in the code segment
in arm mode.

This shouldn't have any significant performance effect. It does
end up as a few more instructions than before, for ARM, but
only at the entry to this function, not within the fft functions
themselves.

Signed-off-by: Martin Storsjö <martin@martin.st>
2014-12-08 12:29:53 +02:00
Martin Storsjö
ae81576414 arm: fft_vfp: Add a missing "endconst" when building in thumb mode
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-12-08 12:29:49 +02:00
Michael Niedermayer
ea41e6d637 Merge commit '9c12c6ff9539e926df0b2a2299e915ae71872600'
* commit '9c12c6ff9539e926df0b2a2299e915ae71872600':
  motion_est: convert stride to ptrdiff_t

Conflicts:
	libavcodec/me_cmp.c
	libavcodec/ppc/me_cmp.c
	libavcodec/x86/me_cmp_init.c

See: 9c669672c7
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-11-24 12:13:00 +01:00
Vittorio Giovara
9c12c6ff95 motion_est: convert stride to ptrdiff_t
CC: libav-stable@libav.org
Bug-Id: CID 700556 / CID 700557 / CID 700558
2014-11-24 01:30:10 +00:00
James Almer
3cec54b7d7 x86/flacdsp: add SSE2 and AVX decorrelate functions
Two to four times faster depending on instruction set, block size and channel count.
2014-11-13 13:47:55 -03:00
James Almer
c99a882814 avcodec/idctdsp: change {put,add}_pixels_clamped to ptrdiff_t line_size
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-24 21:43:19 -03:00
Bernd Kuhls
6b733be755 Fix compile error on arm4/arm5 platform
Since these commits
http://git.videolan.org/?p=ffmpeg.git;a=commitdiff;h=adf8227cf4e7b4fccb2ad88e1e09b6dc00dd00ed
http://git.videolan.org/?p=ffmpeg.git;a=commitdiff;h=db7f1c7c5a1d37e7f4da64a79a97bea1c4b6e9f8

compilation on arm4/arm5 fails:

libavcodec/libavcodec.so: undefined reference to
`ff_startcode_find_candidate_armv6'

Because libavcodec/arm/Makefile contains
ARMV6-OBJS-$(CONFIG_STARTCODE)         += arm/startcode_armv6.o
function ff_startcode_find_candidate_armv6 is not included for older ARM
archs. The bug was found during automatic buildroot builds:

http://autobuild.buildroot.net/results/ec7/ec71e4f16ee9106747dff5f15999cbd17903e76f//build-end.log
Quote from configure summary:
ARCH                      arm (armv4t)
big-endian                no
runtime cpu detection     yes
ARMv5TE enabled           no
ARMv6 enabled             no
ARMv6T2 enabled           no

http://autobuild.buildroot.net/results/be7/be72eb182eaccf0064a32c9dfc2ac1c0d6555506/build-end.log
ARCH                      arm (armv5te)
big-endian                no
runtime cpu detection     yes
ARMv5TE enabled           yes
ARMv6 enabled             no
ARMv6T2 enabled           no

This patch provides the necessary #if clauses as discussed with Michael:
https://ffmpeg.org/pipermail/ffmpeg-devel/2014-September/163329.html

Signed-off-by: Bernd Kuhls <bernd.kuhls@t-online.de>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-09-23 21:11:05 +02:00
Michael Niedermayer
5db23c07a3 Merge commit '95c0cec03acec0a80cc1c7db48f3b2355d9e767b'
* commit '95c0cec03acec0a80cc1c7db48f3b2355d9e767b':
  idctdsp: Add global function pointers for {add|put}_pixels_clamped functions

Conflicts:
	libavcodec/arm/idctdsp_init_arm.c
	libavcodec/dct.h
	libavcodec/idctdsp.c
	libavcodec/jrevdct.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-09-03 03:19:40 +02:00
Diego Biurrun
95c0cec03a idctdsp: Add global function pointers for {add|put}_pixels_clamped functions
These function pointers already existed in the ARM code. Adding them globally
allows calls to the function pointers to access arch-optimized versions of the
functions transparently.
2014-09-02 14:41:13 -07:00
Michael Niedermayer
3bb2297351 Merge commit 'efd26bedec9a345a5960dbfcbaec888418f2d4e6'
* commit 'efd26bedec9a345a5960dbfcbaec888418f2d4e6':
  build: Add explanatory comments to (optimization) blocks in the Makefiles

Conflicts:
	libavcodec/ppc/Makefile
	libavcodec/x86/Makefile

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-15 20:25:12 +02:00
Michael Niedermayer
c1df467d73 Merge commit '835f798c7d20bca89eb4f3593846251ad0d84e4b'
* commit '835f798c7d20bca89eb4f3593846251ad0d84e4b':
  mpegvideo: cosmetics: Lowercase ugly uppercase MPV_ function name prefixes

Conflicts:
	libavcodec/h261dec.c
	libavcodec/intrax8.c
	libavcodec/mjpegenc.c
	libavcodec/mpeg12dec.c
	libavcodec/mpeg12enc.c
	libavcodec/mpeg4videoenc.c
	libavcodec/mpegvideo.c
	libavcodec/mpegvideo.h
	libavcodec/mpegvideo_enc.c
	libavcodec/rv10.c
	libavcodec/x86/mpegvideoenc.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-15 20:11:56 +02:00
Diego Biurrun
efd26bedec build: Add explanatory comments to (optimization) blocks in the Makefiles 2014-08-15 02:55:21 -07:00
Diego Biurrun
835f798c7d mpegvideo: cosmetics: Lowercase ugly uppercase MPV_ function name prefixes 2014-08-15 01:26:33 -07:00
James Almer
a8592db9bb avcodec/idctdsp: make add/put_pixels_clamped_c internal functions
This reduces code duplication and differences with the fork.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-13 01:44:41 +02:00
Michael Niedermayer
305f72aee7 avcodec: Change get_pixels() to ptrdiff_t linesize
Found-by: ubitux
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-06 15:50:54 +02:00
Michael Niedermayer
bf7ed956ff Merge commit 'adf8227cf4e7b4fccb2ad88e1e09b6dc00dd00ed'
* commit 'adf8227cf4e7b4fccb2ad88e1e09b6dc00dd00ed':
  vc-1: Add platform-specific start code search routine to VC1DSPContext.

Conflicts:
	configure
	libavcodec/arm/vc1dsp_init_arm.c
	libavcodec/vc1dsp.c
	libavcodec/vc1dsp.h

See: 9d8ecdd8ca
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-05 13:00:41 +02:00
Michael Niedermayer
77aafadc56 Merge commit 'db7f1c7c5a1d37e7f4da64a79a97bea1c4b6e9f8'
* commit 'db7f1c7c5a1d37e7f4da64a79a97bea1c4b6e9f8':
  h264: Move start code search functions into separate source files.

Conflicts:
	libavcodec/arm/Makefile
	libavcodec/arm/h264dsp_init_arm.c
	libavcodec/h264_parser.c
	libavcodec/h264dsp.c
	libavcodec/startcode.c
	libavcodec/startcode.h

See: 270cede3f3
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-05 12:46:10 +02:00
Ben Avison
adf8227cf4 vc-1: Add platform-specific start code search routine to VC1DSPContext.
Initialise VC1DSPContext for parser as well as for decoder.
Note, the VC-1 code doesn't actually use the function pointer yet.

Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2014-08-04 22:22:54 +02:00
Ben Avison
db7f1c7c5a h264: Move start code search functions into separate source files.
This permits re-use with parsers for codecs which use similar start codes.

Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2014-08-04 22:22:54 +02:00
Michael Niedermayer
b051a1bbb9 avcodec/arm/idctdsp_init_arm*: Only select non bitexact IDCTs by default when bitexact is not set
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-27 14:21:36 +02:00
Michael Niedermayer
2904d052b7 Merge commit '7fb993d338d88f2f62e0a358b6c9f3eb9a3a08ac'
* commit '7fb993d338d88f2f62e0a358b6c9f3eb9a3a08ac':
  qpeldsp: Mark source pointer in qpel_mc_func function pointer const

Conflicts:
	libavcodec/h264qpel_template.c
	libavcodec/x86/cavsdsp.c
	libavcodec/x86/rv40dsp_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-25 13:05:08 +02:00
Diego Biurrun
7fb993d338 qpeldsp: Mark source pointer in qpel_mc_func function pointer const 2014-07-25 02:52:54 -07:00
Michael Niedermayer
7cdb3b2b79 Merge commit '6869612f5c7d4d2f20f69a5658328a761deadb1c'
* commit '6869612f5c7d4d2f20f69a5658328a761deadb1c':
  arm: Macroize the test for 'setend' CPU instruction support

Conflicts:
	libavcodec/arm/h264dsp_init_arm.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-22 12:46:13 +02:00
Ben Avison
6869612f5c arm: Macroize the test for 'setend' CPU instruction support
Signed-off-by: Diego Biurrun <diego@biurrun.de>
2014-07-21 15:08:01 -07:00
Michael Niedermayer
d986c414de Merge commit '81b9bf319226fe03436c80aaa8a2c91767cab7ce'
* commit '81b9bf319226fe03436c80aaa8a2c91767cab7ce':
  dct-test: Move arch-specific bits into arch-specific subdirectories

Conflicts:
	libavcodec/dct-test.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-21 13:33:51 +02:00
Diego Biurrun
81b9bf3192 dct-test: Move arch-specific bits into arch-specific subdirectories 2014-07-21 01:10:11 -07:00
Michael Niedermayer
110420aac0 Merge commit '4de8b60684ce13dff3e3d372dae4f49b9e53f755'
* commit '4de8b60684ce13dff3e3d372dae4f49b9e53f755':
  idct: Move arm-specific declarations to a header in the arm directory

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-21 01:56:22 +02:00
Diego Biurrun
4de8b60684 idct: Move arm-specific declarations to a header in the arm directory 2014-07-20 13:02:17 -07:00
Michael Niedermayer
521f569734 Merge commit '8b0dd4942aac320d1ca3c40fa7ea1be342c71273'
* commit '8b0dd4942aac320d1ca3c40fa7ea1be342c71273':
  idctdsp: prettyprinting cosmetics

Conflicts:
	libavcodec/idctdsp.c
	libavcodec/ppc/idctdsp.c
	libavcodec/x86/idctdsp_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 22:16:04 +02:00
Michael Niedermayer
42d326353c Merge commit 'b4987f72197e0c62cf2633bf835a9c32d2a445ae'
* commit 'b4987f72197e0c62cf2633bf835a9c32d2a445ae':
  idct: Convert IDCT permutation #defines to an enum

Conflicts:
	libavcodec/idctdsp.c
	libavcodec/x86/cavsdsp.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 22:01:17 +02:00
Diego Biurrun
8b0dd4942a idctdsp: prettyprinting cosmetics 2014-07-18 07:51:03 -07:00
Diego Biurrun
b4987f7219 idct: Convert IDCT permutation #defines to an enum
Also rename the enum values to be consistent with other DCT permutations.
2014-07-18 07:51:03 -07:00
Michael Niedermayer
d13effb0b4 Merge commit '7e18a727d2c2a19f22fcf68875d1b05fd2eafcef'
* commit '7e18a727d2c2a19f22fcf68875d1b05fd2eafcef':
  arm: cosmetics: Consistently use lowercase for shift operators

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 13:17:29 +02:00
Michael Niedermayer
cd4497d8c5 Merge commit 'fe67f3fbb5f9f6a6b60f837f6bc5e087ac11f3bf'
* commit 'fe67f3fbb5f9f6a6b60f837f6bc5e087ac11f3bf':
  arm: cosmetics: Fix a misaligned asm operand

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 12:44:03 +02:00
Martin Storsjö
7e18a727d2 arm: cosmetics: Consistently use lowercase for shift operators
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-07-18 11:17:40 +03:00
Martin Storsjö
fe67f3fbb5 arm: cosmetics: Fix a misaligned asm operand
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-07-18 11:17:35 +03:00
Michael Niedermayer
c27adb37ef Merge commit '87552d54d3337c3241e8a9e1a05df16eaa821496'
* commit '87552d54d3337c3241e8a9e1a05df16eaa821496':
  armv6: Accelerate ff_fft_calc for general case (nbits != 4)

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 03:12:02 +02:00
Ben Avison
87552d54d3 armv6: Accelerate ff_fft_calc for general case (nbits != 4)
The previous implementation targeted DTS Coherent Acoustics, which only
requires nbits == 4 (fft16()). This case was (and still is) linked directly
rather than being indirected through ff_fft_calc_vfp(), but now the full
range from radix-4 up to radix-65536 is available. This benefits other codecs
such as AAC and AC3.

The implementaion is based upon the C version, with each routine larger than
radix-16 calling a hierarchy of smaller FFT functions, then performing a
post-processing pass. This pass benefits a lot from loop unrolling to
counter the long pipelines in the VFP. A relaxed calling standard also
reduces the overhead of the call hierarchy, and avoiding the excessive
inlining performed by GCC probably helps with I-cache utilisation too.

I benchmarked the result by measuring the number of gperftools samples that
hit anywhere in the AAC decoder (starting from aac_decode_frame()) or
specifically in the FFT routines (fft4() to fft512() and pass()) for the
same sample AAC stream:

              Before          After
              Mean   StdDev   Mean   StdDev  Confidence  Change
Audio decode  2245.5 53.1     1599.6 43.8    100.0%      +40.4%
FFT routines  940.6  22.0     348.1  20.8    100.0%      +170.2%

Signed-off-by: Martin Storsjö <martin@martin.st>
2014-07-18 01:34:23 +03:00
Ben Avison
5c22e8e4ad armv6: Accelerate ff_imdct_half for general case (mdct_bits != 6)
The previous implementation targeted DTS Coherent Acoustics, which only
requires mdct_bits == 6. This relatively small size lent itself to
unrolling the loops a small number of times, and encoding offsets
calculated at assembly time within the load/store instructions of each
iteration.

In the more general case (codecs such as AAC and AC3) much larger arrays
are used - mdct_bits == [8, 9, 11]. The old method does not scale for
these cases, so more integer registers are used with non-unrolled versions
of the loops (and with some stack spillage). The postrotation filter loop
is still unrolled by a factor of 2 to permit the double-buffering of some
VFP registers to facilitate overlap of neighbouring iterations.

I benchmarked the result by measuring the number of gperftools samples
that hit anywhere in the AAC decoder (starting from aac_decode_frame())
or specifically in ff_imdct_half_c / ff_imdct_half_vfp, for the same
example AAC stream:

                  Before          After
                  Mean   StdDev   Mean   StdDev  Confidence  Change
aac_decode_frame  2368.1 35.8     2117.2 35.3    100.0%      +11.8%
ff_imdct_half_*   457.5  22.4     251.2  16.2    100.0%      +82.1%

Signed-off-by: Martin Storsjö <martin@martin.st>
2014-07-18 01:34:08 +03:00
Michael Niedermayer
3a2d1465c8 Merge commit '2d60444331fca1910510038dd3817bea885c2367'
* commit '2d60444331fca1910510038dd3817bea885c2367':
  dsputil: Split motion estimation compare bits off into their own context

Conflicts:
	configure
	libavcodec/Makefile
	libavcodec/arm/Makefile
	libavcodec/dvenc.c
	libavcodec/error_resilience.c
	libavcodec/h264.h
	libavcodec/h264_slice.c
	libavcodec/me_cmp.c
	libavcodec/me_cmp.h
	libavcodec/motion_est.c
	libavcodec/motion_est_template.c
	libavcodec/mpeg4videoenc.c
	libavcodec/mpegvideo.c
	libavcodec/mpegvideo_enc.c
	libavcodec/x86/Makefile
	libavcodec/x86/me_cmp_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-17 23:27:40 +02:00
Diego Biurrun
2d60444331 dsputil: Split motion estimation compare bits off into their own context 2014-07-17 09:07:10 -07:00
Michael Niedermayer
21dfabfa64 Merge commit 'adff0a8166345bb9513f0f658043fb6387e90122'
* commit 'adff0a8166345bb9513f0f658043fb6387e90122':
  arm: dsputil: Coalesce all init files

Conflicts:
	libavcodec/arm/Makefile
	libavcodec/arm/dsputil_arm.h
	libavcodec/arm/dsputil_init_arm.c
	libavcodec/arm/dsputil_init_armv6.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-16 20:09:25 +02:00