generic-library/ffmpeg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
74,132 Commits 24 Branches 241 Tags
Commit Graph

1982 Commits

Author SHA1 Message Date
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 ad733089b024e4a3ff8f024d247a032f79a50ac8.

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