Michael Niedermayer
70d6ce783c
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: Don't clobber callee saved registers in scalarproduct
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-12-21 01:19:59 +01:00
Michael Niedermayer
4fa91b88c6
Merge commit ' b254490bda'
...
* commit 'b254490bda ':
vc1: arm: Add NEON no_rnd chroma MC
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-12-20 23:33:15 +01:00
Michael Niedermayer
69278d94c4
Merge commit ' 832e190632'
...
* commit '832e190632 ':
vc1: arm: Add NEON assembly
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-12-20 23:12:16 +01:00
Martin Storsjö
d307e408d4
arm: Don't clobber callee saved registers in scalarproduct
...
q4-q7/d8-d15 are supposed to not be clobbered by the callee.
CC: libav-stable@libav.org
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-12-20 20:48:30 +02:00
Mason Carter
b254490bda
vc1: arm: Add NEON no_rnd chroma MC
...
Apply David Conrad's old patch to the modern codebase.
http://ffmpeg.org/pipermail/ffmpeg-devel/2009-April/059877.html
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-12-20 14:53:42 +02:00
Mason Carter
832e190632
vc1: arm: Add NEON assembly
...
For:
ff_vc1_inv_trans_{8,4}x{8,4}_{dc_,}neon
ff_put_pixels8x8_neon
ff_put_vc1_mspel_mc{0,1,2,3}{0,1,2,3}_neon (except for 00)
Based on ARM assembly code in libavcodec/arm by Rob Clark and Mans
Rullgard.
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-12-20 14:53:39 +02:00
Michael Niedermayer
8e70fdab36
Merge commit ' 4958f35a2e'
...
* commit '4958f35a2e ':
dsputil: Move apply_window_int16 to ac3dsp
Conflicts:
libavcodec/arm/ac3dsp_init_arm.c
libavcodec/arm/ac3dsp_neon.S
libavcodec/x86/ac3dsp_init.c
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-12-09 04:12:40 +01:00
Diego Biurrun
4958f35a2e
dsputil: Move apply_window_int16 to ac3dsp
...
The (optimized) functions are used nowhere else.
2013-12-08 17:57:15 +01:00
Ronald S. Bultje
f574b4da56
vp8: use 2 registers for dst_stride and src_stride in neon bilin filter.
2013-09-28 20:25:29 -04:00
Thilo Borgmann
d814a839ac
Reinstate proper FFmpeg license for all files.
2013-08-30 15:47:38 +00:00
Michael Niedermayer
e1c3e6277f
Merge commit ' f0389eb777'
...
* commit 'f0389eb777 ':
arm: fmtconvert: Split armv6 fmtconvert code off from vfp code
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-08-29 16:10:39 +02:00
Michael Niedermayer
99e7c702db
Merge commit ' bd549cbaac'
...
* commit 'bd549cbaac ':
arm: dcadsp: Move synth filter initialization to dcadsp file
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-08-29 16:00:45 +02:00
Diego Biurrun
f0389eb777
arm: fmtconvert: Split armv6 fmtconvert code off from vfp code
2013-08-29 11:24:14 +02:00
Diego Biurrun
bd549cbaac
arm: dcadsp: Move synth filter initialization to dcadsp file
2013-08-29 11:24:14 +02:00
Michael Niedermayer
6067186f3a
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: h264chroma: Do not compile h264_chroma_mc* dependent on h264 decoder
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-08-24 11:30:57 +02:00
Michael Niedermayer
f9418d156f
Merge commit ' 8506ff97c9'
...
* commit '8506ff97c9 ':
vp56: Mark VP6-only optimizations as such.
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-08-24 11:04:11 +02:00
Diego Biurrun
f407856968
arm: h264chroma: Do not compile h264_chroma_mc* dependent on h264 decoder
...
The functions are used by all codecs that enable the h264chroma component
and the file is already compiled conditional on h264chroma being enabled.
2013-08-23 17:21:14 +02:00
Diego Biurrun
8506ff97c9
vp56: Mark VP6-only optimizations as such.
...
Most of our VP56 optimizations are VP6-only and will stay that way.
So avoid compiling them for VP5-only builds.
2013-08-23 14:42:19 +02:00
Michael Niedermayer
e1a5ee25e0
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: Add assembly version of h264_find_start_code_candidate
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-08-08 12:52:35 +02:00
Ben Avison
45e10e5c8d
arm: Add assembly version of h264_find_start_code_candidate
...
Before After
Mean StdDev Mean StdDev Change
This function 508.8 23.4 185.4 9.0 +174.4%
Overall 3068.5 31.7 2752.1 29.4 +11.5%
In combination with the preceding patch:
Before After
Mean StdDev Mean StdDev Change
Overall 2925.6 26.2 2752.1 29.4 +6.3%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-08-08 12:08:34 +03:00
Michael Niedermayer
0815b23062
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: Comment out unused labels in simple_idct_arm
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-25 10:15:08 +02:00
Martin Storsjö
54ba52077c
arm: Comment out unused labels in simple_idct_arm
...
When building for iOS in thumb mode, gas-preprocessor.pl doesn't
mark unused labels as thumb functions (as it does for other
local labels, where it can figure out that they are functions
due to being referenced in branch instructions). This leads to
linker warnings for some of those local labels, such as:
ld: warning: ARM function not 4-byte aligned: __a_evaluation from
libavcodec/libavcodec.a(simple_idct_arm.o)
Therefore, comment them out since they don't have any function.
They do still have a value in documenting key points in the
assembly source though.
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-24 22:43:21 +03:00
Martin Storsjö
69e6702c01
arm: Mangle external symbols properly in new vfp assembly files
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 14:48:30 +03:00
Martin Storsjö
47d57f24e3
arm: Mangle external symbols properly in new vfp assembly files
...
Reviewed-by: Kostya Shishkov
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 13:16:21 +02:00
Michael Niedermayer
23f250d2bc
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: Add VFP-accelerated version of qmf_32_subbands
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 12:11:23 +02:00
Michael Niedermayer
c30eb74d18
Merge commit ' 8b9eba664e'
...
* commit '8b9eba664e ':
arm: Add VFP-accelerated version of fft16
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 12:05:39 +02:00
Michael Niedermayer
bacba8e5d1
Merge commit ' ba6836c966'
...
* commit 'ba6836c966 ':
arm: Add VFP-accelerated version of dca_lfe_fir
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 12:04:28 +02:00
Michael Niedermayer
2305a6775d
Merge commit ' b63bb251ea'
...
* commit 'b63bb251ea ':
arm: Add VFP-accelerated version of imdct_half
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 11:57:05 +02:00
Michael Niedermayer
3cab228005
Merge commit ' d6e4f5fef0'
...
* commit 'd6e4f5fef0 ':
arm: Add VFP-accelerated version of int32_to_float_fmul_array8
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 11:55:40 +02:00
Michael Niedermayer
877bbe05ce
Merge commit ' ce9ed10ac2'
...
* commit 'ce9ed10ac2 ':
arm: Add VFP-accelerated version of int32_to_float_fmul_scalar
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 11:42:19 +02:00
Michael Niedermayer
0129026c4e
Merge commit ' 41ef1d360b'
...
* commit '41ef1d360b ':
arm: Add VFP-accelerated version of synth_filter_float
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-07-22 11:41:37 +02:00
Ben Avison
ff30d12159
arm: Add VFP-accelerated version of qmf_32_subbands
...
Before After
Mean StdDev Mean StdDev Change
This function 1323.0 98.0 746.2 60.6 +77.3%
Overall 15400.0 336.4 14147.5 288.4 +8.9%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:44 +03:00
Martin Storsjö
8b9eba664e
arm: Add VFP-accelerated version of fft16
...
Before After
Mean StdDev Mean StdDev Change
This function 1389.3 4.2 967.8 35.1 +43.6%
Overall 15577.5 83.2 15400.0 336.4 +1.2%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:41 +03:00
Martin Storsjö
ba6836c966
arm: Add VFP-accelerated version of dca_lfe_fir
...
Before After
Mean StdDev Mean StdDev Change
This function 868.2 33.5 436.0 27.0 +99.1%
Overall 15973.0 223.2 15577.5 83.2 +2.5%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:39 +03:00
Martin Storsjö
b63bb251ea
arm: Add VFP-accelerated version of imdct_half
...
Before After
Mean StdDev Mean StdDev Change
This function 2653.0 28.5 1108.8 51.4 +139.3%
Overall 17049.5 408.2 15973.0 223.2 +6.7%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:37 +03:00
Ben Avison
d6e4f5fef0
arm: Add VFP-accelerated version of int32_to_float_fmul_array8
...
Before After
Mean StdDev Mean StdDev Change
This function 366.2 18.3 277.8 13.7 +31.9%
Overall 18420.5 489.1 17049.5 408.2 +8.0%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:36 +03:00
Ben Avison
ce9ed10ac2
arm: Add VFP-accelerated version of int32_to_float_fmul_scalar
...
Before After
Mean StdDev Mean StdDev Change
This function 1175.0 4.4 366.2 18.3 +220.8%
Overall 19285.5 292.0 18420.5 489.1 +4.7%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:30 +03:00
Ben Avison
41ef1d360b
arm: Add VFP-accelerated version of synth_filter_float
...
Before After
Mean StdDev Mean StdDev Change
This function 9295.0 114.9 4853.2 83.5 +91.5%
Overall 23699.8 397.6 19285.5 292.0 +22.9%
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-22 10:15:17 +03:00
Christophe Gisquet
b6293e2798
fmtconvert: Explicitly use int32_t instead of int
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-07-17 11:02:47 +03:00
Michael Niedermayer
a40370661d
use Kostyas full name in copyrights
...
This fixes 2 files that where not part of the original change
See: de421b2085
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-06-02 11:25:56 +02:00
Michael Niedermayer
1a7ae6be2a
Merge remote-tracking branch 'qatar/master'
...
* qatar/master:
arm: Include hpeldsp_neon.o if h264qpel is enabled
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-05-30 11:21:45 +02:00
Michael Niedermayer
e119d1b345
Merge commit ' efb7968cfe'
...
* commit 'efb7968cfe ':
arm: Don't unconditionally build dsputil files
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-05-30 11:02:21 +02:00
Michael Niedermayer
0b539da4c7
Merge commit ' 36a7df8cf1'
...
* commit '36a7df8cf1 ':
arm: Only build the FFT init files if FFT is enabled
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-05-30 10:57:14 +02:00
Michael Niedermayer
3a0e21f037
Merge commit ' 186599ffe0'
...
* commit '186599ffe0 ':
build: cosmetics: Place unconditional before conditional OBJS lines
Conflicts:
libavcodec/x86/Makefile
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-05-30 10:49:43 +02:00
Michael Niedermayer
1bbbbb0a32
Merge commit ' 9b9b2e9f30'
...
* commit '9b9b2e9f30 ':
build: arm: cosmetics: Place all OBJS declarations in alphabetical order
Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-05-30 10:37:52 +02:00
Martin Storsjö
86113667c0
arm: Include hpeldsp_neon.o if h264qpel is enabled
...
A few of the h264qpel neon functions are shared with other
hpeldsp functions in this file.
This fixes standalone compilation of the h264 decoder on arm.
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-30 02:17:37 +03:00
Martin Storsjö
efb7968cfe
arm: Don't unconditionally build dsputil files
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-30 02:17:35 +03:00
Martin Storsjö
36a7df8cf1
arm: Only build the FFT init files if FFT is enabled
...
This fixes build errors in cases where FFT is disabled.
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-30 02:17:33 +03:00
Diego Biurrun
186599ffe0
build: cosmetics: Place unconditional before conditional OBJS lines
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-30 02:17:31 +03:00
Diego Biurrun
9b9b2e9f30
build: arm: cosmetics: Place all OBJS declarations in alphabetical order
...
Signed-off-by: Martin Storsjö <martin@martin.st>
2013-05-30 02:17:27 +03:00