generic-library/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
67,576 Commits 24 Branches 241 Tags 173 MiB
5e8e2f3861
Commit Graph

1847 Commits

Author SHA1 Message Date
Michael Niedermayer
581b5f0b9b Merge commit 'e3fcb14347466095839c2a3c47ebecff02da891e' 
* commit 'e3fcb14347466095839c2a3c47ebecff02da891e':
  dsputil: Split off IDCT bits into their own context

Conflicts:
	configure
	libavcodec/aic.c
	libavcodec/arm/Makefile
	libavcodec/arm/dsputil_init_arm.c
	libavcodec/arm/dsputil_init_armv6.c
	libavcodec/asvdec.c
	libavcodec/dnxhdenc.c
	libavcodec/dsputil.c
	libavcodec/dvdec.c
	libavcodec/dxva2_mpeg2.c
	libavcodec/intrax8.c
	libavcodec/mdec.c
	libavcodec/mjpegdec.c
	libavcodec/mjpegenc_common.h
	libavcodec/mpegvideo.c
	libavcodec/ppc/dsputil_altivec.h
	libavcodec/ppc/dsputil_ppc.c
	libavcodec/ppc/idctdsp.c
	libavcodec/x86/Makefile
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/dsputil_mmx.c
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-07-01 15:22:11 +02:00
Diego Biurrun
79793f8337 Update Fiona's name in copyright statements. 2014-07-01 03:26:51 -07:00
Diego Biurrun
e3fcb14347 dsputil: Split off IDCT bits into their own context 2014-06-30 07:58:46 -07:00
Michael Niedermayer
5bca5f87d1 Revert "x86/videodsp: add emulated_edge_mc_mmxext" 
The commit causes minor out of array reads and was mainly intended for
future optimizations which turned out not to be meassurably faster.
Itself it was just 1 cpu cycle faster

Approved-by: jamrial

This reverts commit 057d2704e7.
 2014-06-28 05:39:07 +02:00
Michael Niedermayer
09a7a4704e Merge commit 'd2869aea0494d3a20d53d5034cd41dbb488eb133' 
* commit 'd2869aea0494d3a20d53d5034cd41dbb488eb133':
  dsputil: Move MMX/SSE2-optimized IDCT bits to the x86 subdirectory

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-27 03:05:33 +02:00
Diego Biurrun
d2869aea04 dsputil: Move MMX/SSE2-optimized IDCT bits to the x86 subdirectory 2014-06-26 16:15:07 -07:00
James Almer
057d2704e7 x86/videodsp: add emulated_edge_mc_mmxext 
This also changes hfix8_mmx and above to use mmx regs instead of
gprs, and makes emulated_edge_mc_sse and emulated_edge_mc_sse2 use
mmxext hfix and hvar functions instead of mmx where possible.

This is mostly in preparation for an ssse3 version.

Signed-off-by: James Almer <jamrial@gmail.com>

code is about 1 cpu cycle faster approximately

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-26 17:58:57 +02:00
Michael Niedermayer
11ba0c8207 Merge commit '5ab03e41e553452118113d0c224fa32b325e45e5' 
* commit '5ab03e41e553452118113d0c224fa32b325e45e5':
  x86: h264dsp: Fix link failure with optimizations disabled

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-26 02:58:59 +02:00
Diego Biurrun
5ab03e41e5 x86: h264dsp: Fix link failure with optimizations disabled 
With optimzations disabled compilers have trouble doing dead code
elimination on 'if (foo && 0)' expressions, while 'if (0 && foo)'
still works, so use the latter to avoid problems.

Bug-Id: 707
 2014-06-25 15:24:51 -07:00
Michael Niedermayer
1ace0ca60f avcodec/x86/hevc_idct: fix function name in comment 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-25 18:22:25 +02:00
plepere
9ba6b17add avcodec/x86/hevc_idct: fix number of sse registers 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-25 14:59:23 +02:00
plepere
942e22c651 avcodec/x86/hevc: add avx2 dc idct 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-25 14:49:44 +02:00
Michael Niedermayer
eab2509f8c avcodec/x86/h264_qpel_10bit: locally define pb_0 
somehow old llvm-gcc manages to ignore the alignment from ff_pb_0 causing a crash on freebsd

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-24 02:13:43 +02:00
James Almer
476bd3c7e4 x86/dsputil: move put_signed_pixels_clamped out of bswapdsp.asm 
It's still a dsputil function

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-23 22:11:18 +02:00
Michael Niedermayer
d7463c6813 Merge commit 'fab9df63a3156ffe1f9490aafaea41e03ef60ddf' 
* commit 'fab9df63a3156ffe1f9490aafaea41e03ef60ddf':
  dsputil: Split off global motion compensation bits into a separate context

Conflicts:
	libavcodec/dsputil.c
	libavcodec/dsputil.h
	libavcodec/ppc/dsputil_altivec.h
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/dsputil_mmx.c
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-23 21:10:10 +02:00
Diego Biurrun
fab9df63a3 dsputil: Split off global motion compensation bits into a separate context 2014-06-23 09:58:17 -07:00
Michael Niedermayer
35bb74900b Merge commit 'c67b449bebbe0b35c73b203683e77a0a649bc765' 
* commit 'c67b449bebbe0b35c73b203683e77a0a649bc765':
  dsputil: Split bswap*_buf() off into a separate context

Conflicts:
	configure
	libavcodec/4xm.c
	libavcodec/ac3dec.c
	libavcodec/ac3dec.h
	libavcodec/apedec.c
	libavcodec/eamad.c
	libavcodec/flacenc.c
	libavcodec/fraps.c
	libavcodec/huffyuv.c
	libavcodec/huffyuvdec.c
	libavcodec/motionpixels.c
	libavcodec/truemotion2.c
	libavcodec/x86/Makefile
	libavcodec/x86/dsputil_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-23 13:31:26 +02:00
Diego Biurrun
c67b449beb dsputil: Split bswap*_buf() off into a separate context 2014-06-22 18:22:31 -07:00
James Almer
c172683bf4 x86/dsputil: remove redundant global motion compensation code 
The SSE version has been no different than the mmx one since commit a41bf09d

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-23 02:15:06 +02:00
James Almer
6ec3dc97fc x86/audiodsp: move asm code out of dsputil 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-22 19:53:09 +02:00
Michael Niedermayer
99497b4683 Merge commit '9a9e2f1c8aa4539a261625145e5c1f46a8106ac2' 
* commit '9a9e2f1c8aa4539a261625145e5c1f46a8106ac2':
  dsputil: Split audio operations off into a separate context

Conflicts:
	configure
	libavcodec/takdec.c
	libavcodec/x86/Makefile
	libavcodec/x86/dsputil.asm
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/dsputil_mmx.c
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-22 17:58:28 +02:00
Diego Biurrun
9a9e2f1c8a dsputil: Split audio operations off into a separate context 2014-06-22 06:20:15 -07:00
Michael Niedermayer
33f83a2157 avcodec/x86/rv40dsp_init: fix () in macros 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-20 21:36:43 +02:00
James Almer
a5ce608fc7 x86/blockdsp: restore author attribution 
See commits
649c00c96d
5fecfb7d58
73b02e2460

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 18:31:44 +02:00
Michael Niedermayer
08c5859f17 avcodec: add simpleauto idct 
This will pick the "best" simple idct compatible idct

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 14:28:01 +02:00
James Almer
454c019cb5 x86/hevc_idct: fix movd parameter size in DC_ADD_INIT 
Fixes compilation with NASM x86_64

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 13:18:13 +02:00
James Almer
fe782233aa x86/blockdsp: move asm code out of dsputil 
Also replace INLINE_<opt> with EXTERNAL_<opt> that were wrongly
changed by commit 2b05db4f81

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 13:09:03 +02:00
Michael Niedermayer
042a82ca37 avcodec/x86/lossless_videodsp: Fix size of values read for left/left_top 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 05:53:41 +02:00
Michael Niedermayer
2b05db4f81 Merge commit 'e74433a8e6fc00c8dbde293c97a3e45384c2c1d9' 
* commit 'e74433a8e6fc00c8dbde293c97a3e45384c2c1d9':
  dsputil: Split clear_block*/fill_block* off into a separate context

Conflicts:
	configure
	libavcodec/asvdec.c
	libavcodec/dnxhddec.c
	libavcodec/dnxhdenc.c
	libavcodec/dsputil.h
	libavcodec/eamad.c
	libavcodec/intrax8.c
	libavcodec/mjpegdec.c
	libavcodec/ppc/dsputil_ppc.c
	libavcodec/vc1dec.c
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/dsputil_mmx.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-19 04:54:38 +02:00
Diego Biurrun
e74433a8e6 dsputil: Split clear_block*/fill_block* off into a separate context 2014-06-18 14:07:23 -07:00
plepere
92cccb7bcd avcodec/hevc: new idct + asm 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-17 13:23:36 +02:00
Christophe Gisquet
9107612818 x86util: add and use RSHIFT/LSHIFT macros 
Those macros take a byte number as shift argument, as this argument
differs between MMX and SSE2 instructions.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-15 13:19:27 +02:00
Ronald S. Bultje
385a3420d1 vp9/x86: fix overwrite in ipred_vl_4x4_ssse3. 
Fixes track ticket 3717.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-12 04:11:20 +02:00
Christophe Gisquet
508e7a5c16 x86: huffyuv: fix {add,diff}_int16 
They used an extra, undeclared register. Fixes a crash in
fate-vsynth3-ffvhuff444p16

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-12 00:26:19 +02:00
Michael Niedermayer
1a2ff62859 Merge commit '570d4b21863b6254d6bbca9c528bede471bb4478' 
* commit '570d4b21863b6254d6bbca9c528bede471bb4478':
  x86: h264: Don't keep data in the redzone across function calls on 64 bit unix

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-10 18:35:49 +02:00
Martin Storsjö
570d4b2186 x86: h264: Don't keep data in the redzone across function calls on 64 bit unix 
We know that the called function (ff_chroma_inter_body_mmxext)
doesn't touch the redzone, and thus will be kept intact - thus,
this doesn't fix any bug per se.

However, valgrind's memcheck tool intentionally assumes that the
redzone is clobbered on every function call and function return
(see a long comment in valgrind/memcheck/mc_main.c). This avoids
false positives in that tool, at the cost of an extra stack pointer
adjustment.

The other alternative would be a valgrind suppression for this issue,
but that's an extra burden for everybody that wants to run libavcodec
within valgrind.

Signed-off-by: Martin Storsjö <martin@martin.st>
 2014-06-10 16:31:48 +03:00
Michael Niedermayer
06f576c4ab avcodec/x86/dct_init: fix build failure with clang && disable-optimizations 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-09 19:32:41 +02:00
James Almer
6d408495b5 x86/dct32: don't build ff_dct32_float_sse on x86_64 
There's an SSE2 version already, and technically the SSE version
on x86_64 was wrong (using pshufd and pshuflw, SSE2 instructions).

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-09 00:51:43 +02:00
James Almer
fc8db12a73 x86/vp9: inital AVX2 intra_pred 
tos3k-vp9-b10000.webm on a Core i5-4200U @1.6GHz

1219 decicycles in ff_vp9_ipred_dc_32x32_ssse3, 131070 runs, 2 skips
439 decicycles in ff_vp9_ipred_dc_32x32_avx2, 131070 runs, 2 skips

3570 decicycles in ff_vp9_ipred_dc_top_32x32_ssse3, 4096 runs, 0 skips
2494 decicycles in ff_vp9_ipred_dc_top_32x32_avx2, 4096 runs, 0 skips

1419 decicycles in ff_vp9_ipred_dc_left_32x32_ssse3, 16384 runs, 0 skips
717 decicycles in ff_vp9_ipred_dc_left_32x32_avx2, 16384 runs, 0 skips

2737 decicycles in ff_vp9_ipred_tm_32x32_avx, 1024 runs, 0 skips
2088 decicycles in ff_vp9_ipred_tm_32x32_avx2, 1024 runs, 0 skips

3090 decicycles in ff_vp9_ipred_v_32x32_avx, 512 runs, 0 skips
2226 decicycles in ff_vp9_ipred_v_32x32_avx2, 512 runs, 0 skips

1565 decicycles in ff_vp9_ipred_h_32x32_avx, 1024 runs, 0 skips
922 decicycles in ff_vp9_ipred_h_32x32_avx2, 1024 runs, 0 skips

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-08 02:37:20 +02:00
James Almer
ec98f80af4 x86/dsputil: move some mmx init code inside dsputil_init_mmx() 
This reduces differences with the fork

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-06 05:26:04 +02:00
Christophe Gisquet
ccff45a0d3 apedsp: move to llauddsp 
APE is not the sole codec using scalarproduct_and_madd_int16.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-05 20:31:59 +02:00
Michael Niedermayer
d5c9d055ea avcodec/x86/dsputilenc_mmx: fix build without yasm 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-04 05:39:03 +02:00
James Almer
625ffa1457 x86/motion_est: sad_{x, y}2_mmxext functions are bitexact 
Only the xy2 functions aren't.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-04 00:48:35 +02:00
Timothy Gu
108dec3055 x86: dsputilenc: convert hf_noise*_mmx to yasm 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Several bugfixes by: Christophe Gisquet <christophe.gisquet@gmail.com>
See: [FFmpeg-devel] [WIP] [PATCH 4/4] x86: dsputilenc: convert hf_noise*_mmx to yasm
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-03 23:59:43 +02:00
Christophe Gisquet
dcd2a6ca36 x86: hevc_mc: remove unneeded shift 
The immediate value may be 0.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-01 23:34:33 +02:00
Christophe Gisquet
09fc28aed1 x86: hevcdsp_init: fix macro usage 
The macro was not using the parameter but unconditionally using sse4.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-01 23:20:07 +02:00
James Almer
e1bd40fe6b x86/motion_est: enable sad16_sse2 on k10 CPUs 
The check is meant for k8 CPUs. sad16_sse2 is ~20% faster than sad16_mmxext on k10.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-06-01 02:10:32 +02:00
James Almer
f128342df2 build: fix compilation of svq1enc_mmx.c with --disable-mmx 
It's needed for ff_svq1enc_init_x86() even if simd functions are disabled.

Alternatively, svq1enc_init.c could be made and the relevant code moved there.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-31 00:38:24 +02:00
James Almer
4ac41a52e2 x86/huffyuvdsp: fix some prototypes 
Remove duplicate prototypes and fix int -> intptr_t in another

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-31 00:29:00 +02:00
Christophe Gisquet
d136fe6fd7 x86: huffyuvdsp: fewer functions for x86_64 
When there are 2 functions that are <= SSE2, only one is needed for x86_64.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 21:39:06 +02:00
Timothy Gu
154cee9292 x86: dsputilenc: convert ff_sse{8, 16}_mmx() to yasm 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 16:57:52 +02:00
Timothy Gu
0b6292b7b8 x86: dsputilenc: move all the function prototypes together 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 16:18:10 +02:00
Christophe Gisquet
f743fa9c7f x86: huffyuvdsp: add_hfyu_left_pred_bgr32 
C   MMX   SSE2
Cycles: 3092  1053  578

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 15:20:36 +02:00
Michael Niedermayer
7be79c76d3 avcodec/huffyuvdsp: Change w to intptr in add_hfyu_median_pred() and add_hfyu_left_pred() 
This avoids potential issues with the high 32bits being random in x86-64 asm

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 15:12:58 +02:00
Christophe Gisquet
884078d2df x86: huffyuvdsp: add SSE2 median prediction 
From 5010c to 4566 on lagarith YUY2.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 14:57:57 +02:00
Michael Niedermayer
8c891d90ca avcodec/x86/qpeldsp_init: Restore author attribution 
See: 368f50359e
See: 44eb495128, and many others
See:
similarity index 83%
copy from libavcodec/x86/dsputil_init.c
copy to libavcodec/x86/qpeldsp_init.c
index ebbf97f..8f296a1 100644
--- a/libavcodec/x86/dsputil_init.c
+++ b/libavcodec/x86/qpeldsp_init.c
@@ -1,6 +1,5 @@
 /*
- * Copyright (c) 2000, 2001 Fabrice Bellard
- * Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at>
+ * quarterpel DSP functions
  *
  * This file is part of FFmpeg.
  *

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 04:05:29 +02:00
Michael Niedermayer
98a6806fdd Merge commit '368f50359eb328b0b9d67451f56fda20b3255f9a' 
* commit '368f50359eb328b0b9d67451f56fda20b3255f9a':
  dsputil: Split off quarterpel bits into their own context

Conflicts:
	configure
	libavcodec/dsputil.c
	libavcodec/h263dec.c
	libavcodec/mpegvideo.c
	libavcodec/mpegvideo_enc.c
	libavcodec/vc1dec.c
	libavcodec/vc1dsp.c
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/qpeldsp.asm

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 02:43:34 +02:00
Michael Niedermayer
40f3a87c10 Merge commit '054013a0fc6f2b52c60cee3e051be8cc7f82cef3' 
* commit '054013a0fc6f2b52c60cee3e051be8cc7f82cef3':
  dsputil: Move APE-specific bits into apedsp

Conflicts:
	libavcodec/arm/int_neon.S
	libavcodec/x86/dsputil.asm

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 00:59:15 +02:00
Michael Niedermayer
c814a6c778 avcodec/x86/svq1enc_mmx: Add author attribution 
See: 5900637219
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 00:30:05 +02:00
Michael Niedermayer
ea0931fb96 Merge commit '65d5d5865845f057cc6530a8d0f34db952d9009c' 
* commit '65d5d5865845f057cc6530a8d0f34db952d9009c':
  dsputil: Move SVQ1 encoding specific bits into svq1enc

Conflicts:
	libavcodec/x86/Makefile

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-30 00:01:45 +02:00
James Almer
02a3e327f1 x86/dsputilenc: add missing guards to ff_pix_sum16_xop 
XOP support was added in Yasm 1.0.0 and Nasm 2.06, and we still
support older versions.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 22:31:28 +02:00
Christophe Gisquet
99a319c4e7 x86: huffyuvdsp: port add_bytes to yasm 
C   MMX  SSE2
Cycles: 2972  587  302

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 21:56:00 +02:00
Christophe Gisquet
2267003981 x86: hpeldsp: better factorization 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 21:47:40 +02:00
Michael Niedermayer
7b4c46050e rename add_hfyu_left_prediction_int16 to add_hfyu_left_pred_int16 
This makes the naming more consistent with the 8bit variant

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 19:50:44 +02:00
Michael Niedermayer
550ae6c02f rename add_hfyu_median_prediction_int16 to add_hfyu_median_pred_int16 
This makes the naming more consistent with the 8bit variant

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 19:49:29 +02:00
Michael Niedermayer
40a4ab8ba4 rename sub_hfyu_median_prediction_int16 to sub_hfyu_median_pred_int16 
This makes the naming more consistent with the 8bit variant

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 19:48:23 +02:00
James Almer
05de4d3011 x86/dsputilenc: implement XOP version of pix_sum16 
SSE2: 137 cycles
XOP:   87 cycles
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 18:40:23 +02:00
Diego Biurrun
368f50359e dsputil: Split off quarterpel bits into their own context 2014-05-29 06:48:31 -07:00
Diego Biurrun
054013a0fc dsputil: Move APE-specific bits into apedsp 2014-05-29 06:41:15 -07:00
Diego Biurrun
65d5d58658 dsputil: Move SVQ1 encoding specific bits into svq1enc 2014-05-29 06:41:15 -07:00
Michael Niedermayer
b50559fc0b libavcodec/x86/dsputilenc: drop and 0xffff that should have becomei redundant 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-29 00:16:52 +02:00
James Almer
561bfc85eb x86/dsputilenc: implement SSE2 versions of pix_{sum16, norm1} 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-28 23:29:34 +02:00
Christophe Gisquet
0810608e23 x86: hevc_mc: better register allocation 
The xmm reg count was incorrect, and manual loading of the gprs
furthermore allows to noticeable reduce the number needed.

The modified functions are used in weighted prediction, so only a
few samples like WP_* exhibit a change. For this one and Win64
(some widths removed because of too few occurrences):

WP_A_Toshiba_3.bit, ff_hevc_put_hevc_uni_w
         16    32
before: 2194  3872
after:  2119  3767

WP_B_Toshiba_3.bit, ff_hevc_put_hevc_bi_w
         16    32    64
before: 2819  4960  9396
after:  2617  4788  9150

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-28 17:39:34 +02:00
Michael Niedermayer
48a6916308 Merge commit '512f3ffe9b4bb86767c2b1176554407c75fe1a5c' 
* commit '512f3ffe9b4bb86767c2b1176554407c75fe1a5c':
  dsputil: Split off HuffYUV encoding bits into their own context

Conflicts:
	configure
	libavcodec/dsputil.c
	libavcodec/dsputil.h
	libavcodec/huffyuv.h
	libavcodec/huffyuvenc.c
	libavcodec/pngenc.c
	libavcodec/x86/dsputilenc_mmx.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-28 00:03:59 +02:00
Michael Niedermayer
e2abc0d5ca Merge commit '0d439fbede03854eac8a978cccf21a3425a3c82d' 
* commit '0d439fbede03854eac8a978cccf21a3425a3c82d':
  dsputil: Split off HuffYUV decoding bits into their own context

Conflicts:
	configure
	libavcodec/dsputil.c
	libavcodec/dsputil.h
	libavcodec/huffyuv.h
	libavcodec/huffyuvdec.c
	libavcodec/lagarith.c
	libavcodec/vble.c
	libavcodec/x86/Makefile
	libavcodec/x86/dsputil.asm
	libavcodec/x86/dsputil_init.c
	libavcodec/x86/dsputil_mmx.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-27 23:16:06 +02:00
Diego Biurrun
512f3ffe9b dsputil: Split off HuffYUV encoding bits into their own context 
Also shorten HuffYUV context member names to avoid clutter.
 2014-05-27 08:54:53 -07:00
Diego Biurrun
0d439fbede dsputil: Split off HuffYUV decoding bits into their own context 
Also shorten HuffYUV context member names to avoid clutter.
 2014-05-27 08:52:34 -07:00
James Almer
5863207086 x86/dsputilenc: use HADDD in ff_sse16_sse2 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-27 15:12:50 +02:00
James Almer
e64e079ece x86/dsputilenc: implement SSE2 version of diff_pixels 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-27 05:55:11 +02:00
Michael Niedermayer
a0c5cd3475 avcodec/x86/dsputilenc: set the count of SSE registers correctly for get_pixels 
Found-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-27 05:52:25 +02:00
Christophe Gisquet
86ae0da60c x86: hpeldsp: propagate changes across codecs 
Some codecs still use mmx versions, so have them use the versions
with newer instruction sets.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-26 15:37:04 +02:00
Michael Niedermayer
a3950a90f6 Revert "x86: dsputilenc: convert ff_sse{8, 16}_mmx() to yasm" 
This reverts commit ad733089b0.

breaks with --disable-yasm
revert requested by: Christophe Gisquet <christophe.gisquet@gmail.com>
 2014-05-25 19:42:18 +02:00
Timothy Gu
ad733089b0 x86: dsputilenc: convert ff_sse{8, 16}_mmx() to yasm 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-25 16:30:08 +02:00
James Almer
d94e255dd1 x86/dsputilenc: make the SUM_ABS_DCTELEM macro more readable 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-25 02:03:54 +02:00
James Almer
61eea421b2 x86/dsputilenc: port sum_abs_dctelem functions to yasm 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-24 21:46:25 +02:00
Christophe Gisquet
81aa0f4604 x86: hpeldsp: implement SSSE3 version of _xy2 
Loading pb_1 rather than pw_8192 was benchmarked to be more efficient.
Loading of the 2 yields no advantage. Loading of one saves ~11 cycles.

decicycles count:
put8:  3223(mmx)    -> 2387
avg8:  2863(mmxext) -> 2125
put16: 4356(sse2)   -> 3553
avg16: 4481(sse2)   -> 3513

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-24 15:15:56 +02:00
Christophe Gisquet
9722a6a3f3 x86: hpeldsp: implement SSE2 put_pixels16_xy2 
This is obviously equivalent to the avg version, without the avg.

3223(mmx) -> 2006(sse2)

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-24 03:45:17 +02:00
Christophe Gisquet
f0aca50e0b x86: hpeldsp: implement SSE2 versions 
Those are mostly used in codecs older than H.264, eg MPEG-2.

put16 versions:
      mmx  mmx2  sse2
x2:  1888  1185   552
y2:  1778  1092   510

avg16 xy2: 3509(mmx2) -> 2169(sse2)

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-24 03:29:48 +02:00
James Almer
7538ad2248 x86/hevc_deblock: improve chroma functions register allocation 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-24 01:16:26 +02:00
James Almer
584327f22f x86/dsputil: fix argument declaration in vector_clipf 
Should fix fate failures in msvc x86_64

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-23 23:10:17 +02:00
James Almer
518cbf9b4a x86/dsputil: fix VECTOR_CLIP_INT32 macro 
The inline loop was incrementing and using the value of %%i
the wrong way.

Disassembly of ff_vector_clip_int32_sse2 before and after
this patch:

    movdqa (%rdx),%xmm0      |  movdqa (%rdx),%xmm0
    movdqa 0x10(%rdx),%xmm1  |  movdqa 0x10(%rdx),%xmm1
    movdqa 0x20(%rdx),%xmm2  |  movdqa 0x20(%rdx),%xmm2
    movdqa 0x30(%rdx),%xmm3  |  movdqa 0x30(%rdx),%xmm3
[...]                        |
    movdqa %xmm0,(%rcx)      |  movdqa %xmm0,(%rcx)
    movdqa %xmm1,0x10(%rcx)  |  movdqa %xmm1,0x10(%rcx)
    movdqa %xmm2,0x20(%rcx)  |  movdqa %xmm2,0x20(%rcx)
    movdqa %xmm3,0x30(%rcx)  |  movdqa %xmm3,0x30(%rcx)
    movdqa (%rdx),%xmm0      |  movdqa 0x40(%rdx),%xmm0
    movdqa 0x20(%rdx),%xmm1  |  movdqa 0x50(%rdx),%xmm1
    movdqa 0x40(%rdx),%xmm2  |  movdqa 0x60(%rdx),%xmm2
    movdqa 0x60(%rdx),%xmm3  |  movdqa 0x70(%rdx),%xmm3
[...]                        |
    movdqa %xmm0,(%rcx)      |  movdqa %xmm0,0x40(%rcx)
    movdqa %xmm1,0x20(%rcx)  |  movdqa %xmm1,0x50(%rcx)
    movdqa %xmm2,0x40(%rcx)  |  movdqa %xmm2,0x60(%rcx)
    movdqa %xmm3,0x60(%rcx)  |  movdqa %xmm3,0x70(%rcx)
    add    $0x80,%rdx        |  add    $0x80,%rdx
    add    $0x80,%rcx        |  add    $0x80,%rcx

Other versions were unaffected.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-23 22:59:55 +02:00
James Almer
6a4832caae x86/diracdsp: mark all functions as yasm 
No inline asm dirac code remains in the tree, so replace every relevant check.
This also moves all the dirac functions from dsputil_mmx.c to diracdsp_mmx.c

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-23 15:02:42 +02:00
James Almer
1d36defe94 x86/dsputil: port ff_vector_clipf_sse to yasm 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-23 00:08:21 +02:00
Christophe Gisquet
c081ca851c x86: hpeldsp: avg_pixels_xy2 for mmx2&3dnow 
This is a port of the inline assembly of the mmx version to use the
pavg(us|)b instruction.

        8    16
mmx   1498  4355
mmx2  1242  3509

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-22 20:17:49 +02:00
Christophe Gisquet
17ac998055 x86: hpeldsp: mark _xy2 versions as approximate 
Currently, only the mmx version is bitexact, the others (mmxext and
3dnow) are not, in spite of their naming.

Therefore, make their name more obvious. Also restore a comment that
was removed in 71155d7b.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-22 20:17:45 +02:00
Christophe Gisquet
f8de35ebc4 x86: hpeldsp: kill hpeldsp_mmx.c 
before:
1987 decicycles in 8_x2, 262121 runs, 23 skips

after:
1902 decicycles in 8_x2, 262112 runs, 32 skips

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-22 20:17:40 +02:00
James Almer
80ee2dfcf6 x86/dsputil: port ff_put_signed_pixels_clamped_mmx to yasm 
Also add an SSE2 version

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-21 23:33:45 +02:00
James Almer
7b05267239 x86/dsputil: port clear_block functions to yasm 
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-21 23:33:45 +02:00
Michael Niedermayer
3d4e365073 avcodec/x86/hpeldsp_init: remove redundant if() 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-21 13:38:27 +02:00
Hendrik Leppkes
cd9e08e110 hpeldsp: fix build without inline asm 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-21 13:37:38 +02:00
Christophe Gisquet
d1a32c3f49 x86: kill fpel_mmx.c 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-21 03:25:08 +02:00
James Almer
d43c303038 x86/hevc_deblock: use constants instead of generating values at runtime 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-19 23:09:33 +02:00
James Almer
057ebf1222 x86/hevc_deblock: remove some duplicated instructions 
Also remove a couple unnecessary cmps

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-18 23:28:17 +02:00
Christophe Gisquet
f1793fe9cd x86: hevc_mc: specify coefficients registers 
By default, macro EPEL_FILTER loads the coefficients inconditionally
into m14/m15. This forces an unneeded higher register count.

Reduce that count by making them parameters of EPEL_FILTER.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-18 16:23:58 +02:00
Carl Eugen Hoyos
ef2713747f Fix compilation of libavcodec/x86/hevc_deblock.asm with nasm. 
Suggested-by: Reimar
 2014-05-17 12:50:55 +02:00
James Almer
be1fbc02b8 x86/hevc_deblock: use movhps instead of shuffling values 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-17 05:40:14 +02:00
James Almer
8aac77fede x86/hevc_deblock: fix label names 
Also remove some unnecessary jmps

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-17 05:40:08 +02:00
James Almer
521eaea63a x86/hevc_deblock: fix usage of ABS1 
The second argument is a temp register for non-SSSE3 cases

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-17 05:39:55 +02:00
James Almer
45110d2290 x86/hevc_deblock: merge movs with other instructions 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-17 05:39:34 +02:00
plepere
ef7c4cd001 avcodec/x86/hevc: updated to use x86util macros 
Reviewed-by: James Almer <jamrial@gmail.com>
Reviewed-by: Ronald S. Bultje
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-16 21:11:07 +02:00
plepere
de7b89fd43 avcodec/x86/hevc: added DBF assembly functions 
Reviewed-by: James Almer <jamrial@gmail.com>
Reviewed-by: Ronald S. Bultje
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-16 21:11:03 +02:00
Michael Niedermayer
bebce653e5 avcodec/x86/dsputil_mmx: Fix build with clang-usan 
Found-by: Katerina Barone-Adesi
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-15 23:56:39 +02:00
Christophe Gisquet
d1310c591e x86: sbrdsp: implement SSE qmf_deint_neg 
From 133 (unrolled av_intfloat32 C) to 59 cycles on Arrandale/Win64.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-15 23:11:18 +02:00
Hendrik Leppkes
87f2d8079a hevcdsp: correctly indicate that hevc_put_hevc_bi_epel_h uses 9 GPRs 
Fixes FATE on Windows.

Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-12 17:00:48 +02:00
James Almer
8e07800001 hevcdsp: include stddef.h for ptrdiff_t definition 
Including stdint.h was enough for systems like Mingw, but apparently not for Linux.
This should fix make checkheaders failures on every platform

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-10 18:23:30 +02:00
James Almer
fa23190a7a hevcdsp: add missing header include 
Fixes make checkheaders

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-10 14:55:03 +02:00
Michael Niedermayer
341cacb9ac avcodec/x86/hevcdsp_init: fix build failure with --disable-mmx 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-09 05:16:27 +02:00
plepere
63832e01c3 hvcodec/x86/hevcdsp: make macros more modular to support functions that are not sse4 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-09 00:14:50 +02:00
Matt Oliver
1898c2f49d inline asm: fix arrays as named constraints. 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-07 15:02:45 +02:00
Michael Niedermayer
fc7d0d8201 avcodec/x86/hevcdsp_init: fix SSE4 checks 
Found-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-06 18:27:49 +02:00
Michael Niedermayer
7be230b5fa avcodec/x86/Makefile: remove duplicate line 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-06 18:23:42 +02:00
Michael Niedermayer
3b3db02f2e avcodec/x86/hevcdsp_init: fix build on 32bit 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-06 18:23:42 +02:00
plepere
7a2491c436 HEVC : added assembly MC functions 
pretty print x86

Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-06 18:23:36 +02:00
Matt Oliver
ac9869ffb0 x86/mpegaudiodsp.c: msvc compilation error without sse/avx_external 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-06 14:15:02 +02:00
Michael Niedermayer
ebf2c2c3a8 avcodec/lossless_videodsp: fix incompatible pointer type warning 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-05-05 05:49:18 +02:00
Matt Oliver
3c3e02b8d1 x86/cavdsp: prevent named constraints appearing twice. 2014-05-03 17:47:55 +02:00
James Almer
5ac10d40fb x86/mpegaudiodsp: define apply_window_mp3 as SSE 
None of the handwritten asm in this function seems to be SSE2

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-25 00:38:01 +02:00
Hendrik Leppkes
5809c2a99d vc1dsp: fix build without inline asm 
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-22 14:01:53 +02:00
Clément Bœsch
62d31307c1 avcodec/x86/vp9lpf: add a comment above a bunch of SWAP. 2014-04-20 21:33:58 +02:00
Clément Bœsch
f0d368d758 avcodec/x86/vp9lpf: merge a few movs with other instructions. 2014-04-20 21:29:11 +02:00
Christophe Gisquet
319235c67c vc1dsp: introduce cases for 8x8 and 16x16 
This allows further unrolling the DSP implementation where possible.

x86 and ARM DSP modified by simply moving the multiple calls from vc1dec
to the DSP code. Decoding improvements should only occurs because of the
compiler actually able to unroll more.

Decoding time: ~8.80s -> 8.64s (ie around 2%)

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-20 18:25:36 +02:00
Clément Bœsch
010732b73a vp9/x86: simplify FILTER_INIT. 
In the 2 FILTER_INIT usages, the source is already preloaded so that
extra complexity taken from FILTER_UPDATE is not necessary.

Also add forgotten "mask" argument in FILTER_{INIT,UPDATE} comments.
 2014-04-19 17:30:33 +02:00
Clément Bœsch
b8d002dc95 vp9/x86: clarify mixed splatb. 2014-04-19 17:00:51 +02:00
Carl Eugen Hoyos
b38910c979 Fix compilation with !HAVE_6REGS. 
Can be tested with:
$ ./configure --cc='cc -m32' --disable-optimizations --enable-pic
 2014-04-19 09:56:01 +02:00
Carl Eugen Hoyos
72c93abaad Use MANGLE in cavsdsp.c to save two registers using gcc. 
Fixes compilation with !HAVE_6REGS.
 2014-04-19 09:54:26 +02:00
James Almer
197fe392db x86/dsputil: use HADDD where applicable 
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-17 14:15:35 +02:00
James Almer
76ed71a72b x86: move horizontal add macros to x86util 
Also port relevant AVX2/XOP optimizations from x264 with permission
to relicense to LGPL from the corresponding authors

Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-17 14:15:09 +02:00
Michael Niedermayer
46d5625f44 avcodec/x86/idct_sse2_xvid: fix non C99 inline function 
Found-by: Matt Oliver <protogonoi@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-14 18:04:57 +02:00
James Almer
0f524b6c69 x86/synth_filter: remove the fma3 version ifdefs 
This fixes compilation failures with --disable-fma3

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
 2014-04-13 11:29:28 +02:00
Timothy Gu
71c32ed533 DNxHD: convert inline asm to yasm 2014-04-11 12:09:09 +02:00
Timothy Gu
676856204b DNxHD: make get_pixel_8x4_sym accept ptrdiff_t as stride 2014-04-11 12:09:09 +02:00
Matt Oliver
d1e6e5c887 avcodec/x86: Exclude broken get_cabac under icl. 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-10 17:47:22 +02:00
Matt Oliver
158a80cc0b Remove leal op to fix icl inline asm. 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-07 13:02:54 +02:00
Hendrik Leppkes
fc7e02f0ff dcadsp: fix SSE code to not use SSE2 instructions. 
movq from SSE register to memory is an SSE2 instruction.
Instead, use SSE movlps, which does the same thing.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-06 18:31:22 +02:00
Michael Niedermayer
e6f69b324e Merge commit '57b5b84e208ad61ffdd74ad849bed212deb92bc5' 
* commit '57b5b84e208ad61ffdd74ad849bed212deb92bc5':
  x86: dsputil: Move ff_apply_window_int16_* bits to ac3dsp, where they belong

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 19:36:21 +02:00
Michael Niedermayer
e3c3f277a9 Merge commit 'c2c5be57494e6117086771bca34c8cd4c72c8e99' 
* commit 'c2c5be57494e6117086771bca34c8cd4c72c8e99':
  x86: h264_qpel: Simplify an #if conditional

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 19:30:44 +02:00
Michael Niedermayer
ebb21887b8 Merge commit '01c5779f56cf708e6cb88b11cfdc248cae7e2ee8' 
* commit '01c5779f56cf708e6cb88b11cfdc248cae7e2ee8':
  x86: Drop some unnecessary YASM ifdefs

Conflicts:
	libavfilter/x86/vf_yadif_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 19:16:39 +02:00
Michael Niedermayer
874f27a8f7 Merge commit 'b42f49e42f8cde25a788b2d13d03e99ca2956647' 
* commit 'b42f49e42f8cde25a788b2d13d03e99ca2956647':
  x86: dsputil: Eliminate some unnecessary dsputil_x86.h #includes

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 19:05:00 +02:00
Michael Niedermayer
5440151fa4 Merge commit '3dc6272bed7890a49080e18eacf3c7a4a6594b0d' 
* commit '3dc6272bed7890a49080e18eacf3c7a4a6594b0d':
  Remove a number of unnecessary dsputil.h #includes

Conflicts:
	libavcodec/h264pred.c
	libavcodec/vc1dsp.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 18:54:15 +02:00
James Almer
a1ac12bddd x86/dcadsp: add ff_dca_lfe_fir0_fma3 
~10% faster than the SSE version.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 13:55:59 +02:00
James Almer
7d2116dd09 x86/synth_filter: compile avx and fma3 functions unconditionally 
Fixes compilation failures with "--disable-{avx,fma3} --disable-optimizations"

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 05:15:27 +02:00
Michael Niedermayer
490d53e335 avcodec/x86/dcadsp_init: fix compilation failure without FMA3 
alternatively the call could be put under #if or the #if
over the function removed

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-05 00:11:48 +02:00
Michael Niedermayer
51fd962c0b Merge commit 'c74b86699c86bdf62e8570f41d8a38be5710baa3' 
* commit 'c74b86699c86bdf62e8570f41d8a38be5710baa3':
  x86/synth_filter: add synth_filter_fma3
  x86/synth_filter: add synth_filter_avx
  x86/synth_filter: add synth_filter_sse

Conflicts:
	libavcodec/x86/dcadsp.asm
	libavcodec/x86/dcadsp_init.c

See: 6467209836
See: 68c3ed936a
See: 7fd64e3e36
See: aa1f38015c
See: dfd865e51b
Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-04 23:40:08 +02:00
Christophe Gisquet
dfd865e51b x86/synth_filter: remove the main loop when it's not needed 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-04 22:35:45 +02:00
Diego Biurrun
57b5b84e20 x86: dsputil: Move ff_apply_window_int16_* bits to ac3dsp, where they belong 2014-04-04 19:08:05 +02:00
Diego Biurrun
c2c5be5749 x86: h264_qpel: Simplify an #if conditional 
The extra conditions are covered by previous #ifs and conditional compilation.
 2014-04-04 19:08:05 +02:00
Diego Biurrun
01c5779f56 x86: Drop some unnecessary YASM ifdefs 
Dead code elimination is enough to avoid undefined references in these cases.
 2014-04-04 19:08:05 +02:00
Diego Biurrun
b42f49e42f x86: dsputil: Eliminate some unnecessary dsputil_x86.h #includes 2014-04-04 19:08:05 +02:00
Diego Biurrun
3dc6272bed Remove a number of unnecessary dsputil.h #includes 2014-04-04 19:08:05 +02:00
James Almer
c74b86699c x86/synth_filter: add synth_filter_fma3 
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
 2014-04-04 17:40:51 +02:00
James Almer
81e02fae6e x86/synth_filter: add synth_filter_avx 
Sandy Bridge Win64:
180 cycles in ff_synth_filter_inner_sse2
150 cycles in ff_synth_filter_inner_avx

Also switch some instructions to a three operand format to avoid
assembly errors with Yasm 1.1.0 or older.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
 2014-04-04 17:40:51 +02:00
James Almer
2025d8026f x86/synth_filter: add synth_filter_sse 
Build only on x86_32 targets.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
 2014-04-04 17:40:51 +02:00
Michael Niedermayer
fb61ed1e9f Merge commit 'ac4b32df71bd932838043a4838b86d11e169707f' 
* commit 'ac4b32df71bd932838043a4838b86d11e169707f':
  On2 VP7 decoder

Conflicts:
	Changelog
	libavcodec/arm/h264pred_init_arm.c
	libavcodec/arm/vp8dsp.h
	libavcodec/arm/vp8dsp_init_arm.c
	libavcodec/arm/vp8dsp_init_armv6.c
	libavcodec/arm/vp8dsp_init_neon.c
	libavcodec/avcodec.h
	libavcodec/h264pred.c
	libavcodec/version.h
	libavcodec/vp8.c
	libavcodec/vp8.h
	libavcodec/vp8data.h
	libavcodec/vp8dsp.c
	libavcodec/vp8dsp.h
	libavcodec/x86/h264_intrapred_init.c
	libavcodec/x86/vp8dsp_init.c

See: 89f2f5dbd7 and others
Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-04-04 14:46:10 +02:00
Peter Ross
ac4b32df71 On2 VP7 decoder 
Further performance improvements and security fixes by
Vittorio Giovara, Luca Barbato and Diego Biurrun.

Signed-off-by: Vittorio Giovara <vittorio.giovara@gmail.com>
Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
Signed-off-by: Diego Biurrun <diego@biurrun.de>
 2014-04-04 04:00:11 +02:00
Matt Oliver
0f2588d7e5 Use intel compliant CDQ instead of CLTD in inline asm. 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-30 23:14:36 +02:00
Clément Bœsch
c4148a6668 x86/vp9mc: add vp9 namespace. 2014-03-29 18:13:15 +01:00
Timothy Gu
9d34dce05b x86: convert DNxHDenc inline asm to yasm 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-27 23:16:17 +01:00
Timothy Gu
cb11b9e89e dnxhdenc: make get_pixel_8x4_sym accept ptrdiff_t as stride 
Signed-off-by: Timothy Gu <timothygu99@gmail.com>
Reviewed-by: "Ronald S. Bultje" <rsbultje@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-27 23:09:10 +01:00
Michael Niedermayer
4998a72b49 Merge remote-tracking branch 'qatar/master' 
* qatar/master:
  x86: hpeldsp: Keep all rnd_template instantiations in hpeldsp_init

Conflicts:
	libavcodec/x86/rnd_mmx.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-26 16:55:46 +01:00
Michael Niedermayer
0371eaebcd Merge commit 'aba70bb5387f12dfa5e6cd8cb861c9c7e668151f' 
* commit 'aba70bb5387f12dfa5e6cd8cb861c9c7e668151f':
  Add missing headers to make template files compile (more) standalone

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-26 14:50:55 +01:00
Diego Biurrun
efc7290eb6 x86: hpeldsp: Keep all rnd_template instantiations in hpeldsp_init 
There is no point in having a separate file just for the instantiation
that provides the public functions.
 2014-03-26 04:31:27 -07:00
Diego Biurrun
aba70bb538 Add missing headers to make template files compile (more) standalone 2014-03-26 04:31:27 -07:00
Diego Biurrun
d0aabeab23 x86: h264_qpel: Fix typo in CALL_2X_PIXELS macro invocation 
This fixes FATE with mmxext CPUFLAGS set.
 2014-03-26 12:00:01 +01:00
Peter Ross
a490970af2 libavcodec/*/vp8dsp_init: indent 
Signed-off-by: Peter Ross <pross@xvid.org>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-25 13:29:29 +01:00
Peter Ross
89f2f5dbd7 On2 VP7 decoder 
Signed-off-by: Peter Ross <pross@xvid.org>
Reviewed-by: BBB
previous patch reviewed by jason
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-25 13:29:05 +01:00
Michael Niedermayer
c25d2cd20b avcodec/x86/mpegvideoenc_template: fix integer overflow 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-25 00:15:52 +01:00
Michael Niedermayer
c8246d3766 avcodec/x86/h264_qpel: Fix typo introduced by 322a1dda97 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-23 15:04:53 +01:00
Michael Niedermayer
74fed968d1 Merge commit '82dd1026cfc1d72b04019185bea4c1c9621ace3f' 
* commit '82dd1026cfc1d72b04019185bea4c1c9621ace3f':
  x86: dsputil: Move hpeldsp-related declarations to a separate header

Conflicts:
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 23:21:54 +01:00
Michael Niedermayer
9333bba6ed Merge commit '6655c933a887a2d20707fff657b614aa1d86a25b' 
* commit '6655c933a887a2d20707fff657b614aa1d86a25b':
  x86: dsputil: Move fpel declarations to a separate header

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 23:08:22 +01:00
Michael Niedermayer
77bc342975 Merge commit '322a1dda973e802db7b57f2007fad3efcd5bab81' 
* commit '322a1dda973e802db7b57f2007fad3efcd5bab81':
  dsputil: Refactor duplicated CALL_2X_PIXELS / PIXELS16 macros

Conflicts:
	libavcodec/arm/hpeldsp_init_arm.c
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 22:53:33 +01:00
Michael Niedermayer
d6d3cfb0aa Merge commit '600b854ad8173995518bd917e7f86120b5505088' 
* commit '600b854ad8173995518bd917e7f86120b5505088':
  imgconvert: Move ff_deinterlace_line_*_mmx declarations out of dsputil

Conflicts:
	libavcodec/imgconvert.c
	libavcodec/x86/dsputil_x86.h

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 22:17:54 +01:00
Michael Niedermayer
8fbc6e5911 Merge commit '1a8d0cf77ed2611e542ae98f341d4c43a04467bd' 
* commit '1a8d0cf77ed2611e542ae98f341d4c43a04467bd':
  x86: dsputil: Move inline assembly macros to a separate header

Conflicts:
	libavcodec/x86/dsputil_mmx.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 22:11:27 +01:00
Diego Biurrun
82dd1026cf x86: dsputil: Move hpeldsp-related declarations to a separate header 2014-03-22 06:17:29 -07:00
Diego Biurrun
6655c933a8 x86: dsputil: Move fpel declarations to a separate header 2014-03-22 06:17:29 -07:00
Diego Biurrun
322a1dda97 dsputil: Refactor duplicated CALL_2X_PIXELS / PIXELS16 macros 2014-03-22 06:17:29 -07:00
Diego Biurrun
600b854ad8 imgconvert: Move ff_deinterlace_line_*_mmx declarations out of dsputil 2014-03-22 06:17:29 -07:00
Diego Biurrun
1a8d0cf77e x86: dsputil: Move inline assembly macros to a separate header 2014-03-22 06:17:29 -07:00
Matt Oliver
cd5cf395f6 Additional icl inline asm fix. 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-22 14:07:03 +01:00
Michael Niedermayer
1cd107f637 avcodec/x86/snowdsp: add missing clobbers to inner_add_yblock_bw_8_obmc_16_bh_even_sse2() and inner_add_yblock_bw_16_obmc_32_sse2() 
Note, these functions are currently disabled

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-21 03:38:48 +01:00
Michael Niedermayer
e98bac82e5 Merge commit '82bb3048013201c0095d2853d4623633d912252f' 
* commit '82bb3048013201c0095d2853d4623633d912252f':
  dsputil: Use correct type in me_cmp_func function pointer

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-20 22:36:40 +01:00
Michael Niedermayer
011d83de48 Merge commit '0e083d7e43805db1a978cb57bfa25fda62e8ff18' 
* commit '0e083d7e43805db1a978cb57bfa25fda62e8ff18':
  build: Group general components separate from de/encoders in arch Makefiles

Conflicts:
	libavcodec/arm/Makefile
	libavcodec/x86/Makefile

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-20 22:26:31 +01:00
Michael Niedermayer
ba85bfabf3 Merge commit '5169e688956be3378adb3b16a93962fe0048f1c9' 
* commit '5169e688956be3378adb3b16a93962fe0048f1c9':
  dsputil: Propagate bit depth information to all (sub)init functions

Conflicts:
	libavcodec/arm/dsputil_init_arm.c
	libavcodec/arm/dsputil_init_armv5te.c
	libavcodec/arm/dsputil_init_armv6.c
	libavcodec/arm/dsputil_init_neon.c
	libavcodec/dsputil.c
	libavcodec/dsputil.h
	libavcodec/ppc/dsputil_ppc.c
	libavcodec/x86/dsputil_init.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-20 22:06:01 +01:00
Diego Biurrun
82bb304801 dsputil: Use correct type in me_cmp_func function pointer 2014-03-20 05:03:23 -07:00
Diego Biurrun
0e083d7e43 build: Group general components separate from de/encoders in arch Makefiles 
This is in line with how the top-level libavcodec Makefile is structured.
 2014-03-20 05:03:23 -07:00
Diego Biurrun
5169e68895 dsputil: Propagate bit depth information to all (sub)init functions 
This avoids recalculating the value over and over again.
 2014-03-20 05:03:23 -07:00
Carl Eugen Hoyos
57fdc74c34 Add one forgotten named inline asm operand in libavcodec/x86/motion_est.c. 2014-03-19 03:00:19 +01:00
Matt Oliver
8236747511 Automatically change MANGLE() into named inline asm operands when direct symbol reference in inline asm are not supported. 
This is part of the patch-set for intel C inline asm on windows support

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-18 23:39:30 +01:00
Matt Oliver
b2d3a45598 avcodec/x86/mlpdsp: Only use asm when non-local inline asm lables are supported 
This is part of the patch-set for intel C inline asm on windows support

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-18 23:37:50 +01:00
James Almer
aa1f38015c x86/synth_filter: improve FMA version 
Replace mulps+subps with fnmaddps, resulting in two less instructions inside the
inner loops.
About 1% faster FMA3 performance.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-17 21:04:15 +01:00
Matt Oliver
b73aae6fe9 avcodec/x86/idct_sse2_xvid: move offsets out of MANGLE() 
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
 2014-03-17 04:19:59 +01:00