Commit Graph

98 Commits

Author SHA1 Message Date
Michael Niedermayer
f9bef2bec9 Merge remote-tracking branch 'qatar/master'
* qatar/master:
  x86: more AVX2 framework

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-14 16:13:57 +02:00
Michael Niedermayer
e3e0e3d0c9 Merge commit 'c6908d6b4b377a04a5d055ba874bdbcf06c80497'
* commit 'c6908d6b4b377a04a5d055ba874bdbcf06c80497':
  x86inc: FMA3/4 Support

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-14 16:06:22 +02:00
Michael Niedermayer
9ac124c889 Merge commit '206895708ea2b464755d340e44501daf9a07c310'
* commit '206895708ea2b464755d340e44501daf9a07c310':
  x86inc: Remove our FMA4 support

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-14 15:54:23 +02:00
Michael Niedermayer
12e4493f9c Merge commit 'c108ba0175d4fc3a3253a8b0f782fbfb96ba5098'
* commit 'c108ba0175d4fc3a3253a8b0f782fbfb96ba5098':
  x86inc: Use VEX-encoded instructions in AVX functions

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-14 15:48:34 +02:00
Jason Garrett-Glaser
a3fabc6cb3 x86: more AVX2 framework
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-14 12:41:56 +01:00
Jason Garrett-Glaser
c6908d6b4b x86inc: FMA3/4 Support
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-14 12:41:54 +01:00
Derek Buitenhuis
206895708e x86inc: Remove our FMA4 support
This is so we can sync to x264's version of FMA4 support.

This partialy reverts commit 79687079a9.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-14 12:39:29 +01:00
Henrik Gramner
c108ba0175 x86inc: Use VEX-encoded instructions in AVX functions
Automatically use VEX-encoding in AVX/AVX2/XOP/FMA3/FMA4
functions for all instructions that exists in a VEX-encoded
version.

This change makes it easier to extend existing code to use AVX2.

Also add support for AVX emulation of a few instructions that
were missing before.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-14 12:36:11 +01:00
Michael Niedermayer
31d0d35560 Merge remote-tracking branch 'qatar/master'
* qatar/master:
  x86inc: Remove .rodata kludges

Conflicts:
	libavutil/x86/x86inc.asm

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-09 14:29:42 +02:00
Henrik Gramner
ad7d7d4f6a x86inc: Remove .rodata kludges
The Mach-O bug was fixed in yasm 0.8.0 and we don't
support versions that old anymore.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-09 07:44:30 -04:00
Michael Niedermayer
19c3890819 Merge commit '3e2fa991db7ef172579422accd61624d52777e5a'
* commit '3e2fa991db7ef172579422accd61624d52777e5a':
  x86inc: remove misaligned cpu flag

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 12:02:21 +02:00
Michael Niedermayer
31d9aa6b2e Merge commit '71155665414b551ad350622d5abed20e58371fbf'
* commit '71155665414b551ad350622d5abed20e58371fbf':
  x86inc: various minor backports from x264

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:57:39 +02:00
Michael Niedermayer
3f965ab95d Merge commit '47f9d7ce5493e119e09d1227d017414feaaf8d97'
* commit '47f9d7ce5493e119e09d1227d017414feaaf8d97':
  x86inc: Check for __OUTPUT_FORMAT__ having a value of "x64"

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:37:22 +02:00
Michael Niedermayer
1f17619fe4 Merge commit 'bbe4a6db44f0b55b424a5cc9d3e89cd88e250450'
* commit 'bbe4a6db44f0b55b424a5cc9d3e89cd88e250450':
  x86inc: Utilize the shadow space on 64-bit Windows

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:23:00 +02:00
Michael Niedermayer
17d9c7c208 Merge commit '3fb78e99a04d0ed8db834d813d933eb86c37142a'
* commit '3fb78e99a04d0ed8db834d813d933eb86c37142a':
  x86inc: create xm# and ym#, analagous to m#

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:15:17 +02:00
Michael Niedermayer
3352fdb292 Merge commit '49ebe3f9fe02174ae7e14548001fd146ed375cc2'
* commit '49ebe3f9fe02174ae7e14548001fd146ed375cc2':
  x86inc: fix some corner cases of SWAP

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:07:03 +02:00
Michael Niedermayer
006c0fcfea Merge commit '63f0d623100bdb0c6081456127f4b6713e83d3db'
* commit '63f0d623100bdb0c6081456127f4b6713e83d3db':
  x86inc: Use SSE instead of SSE2 for copying data

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 11:01:40 +02:00
Michael Niedermayer
faafffaf82 Merge commit 'ad76e6e7e193b98e7335156422d35467816f9ef1'
* commit 'ad76e6e7e193b98e7335156422d35467816f9ef1':
  x86inc: Set ELF hidden visibility for global constants

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 10:52:51 +02:00
Michael Niedermayer
c1488fab3d Merge commit '25cb0c1a1e66edacc1667acf6818f524c0997f10'
* commit '25cb0c1a1e66edacc1667acf6818f524c0997f10':
  x86inc: activate REP_RET automatically

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-10-08 10:27:30 +02:00
Henrik Gramner
3e2fa991db x86inc: remove misaligned cpu flag
Prevents a crash if the misaligned exception mask bit is
cleared for some reason.

Misaligned SSE functions are only used on AMD Phenom CPUs
and the benefit is miniscule. They also require modifying
the MXCSR control register and by removing those functions
we can get rid of that complexity altogether.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:27:38 -04:00
Jason Garrett-Glaser
7115566541 x86inc: various minor backports from x264
Small backports that sneaked into other asm commits in x264.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:27:22 -04:00
Derek Buitenhuis
47f9d7ce54 x86inc: Check for __OUTPUT_FORMAT__ having a value of "x64"
This is also a valid value for WIN64.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:27:08 -04:00
Henrik Gramner
bbe4a6db44 x86inc: Utilize the shadow space on 64-bit Windows
Store XMM6 and XMM7 in the shadow space in functions that
clobbers them. This way we don't have to adjust the stack
pointer as often, reducing the number of instructions as
well as code size.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:25:35 -04:00
Loren Merritt
3fb78e99a0 x86inc: create xm# and ym#, analagous to m#
For when we want to mix simd sizes within one function.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:25:19 -04:00
Loren Merritt
49ebe3f9fe x86inc: fix some corner cases of SWAP
SWAP with >=3 named (rather than numbered) args
PERMUTE followed by SWAP with 2 named args
used to produce the wrong permutation

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:25:06 -04:00
Henrik Gramner
63f0d62310 x86inc: Use SSE instead of SSE2 for copying data
Reduces code size because movaps/movups is one byte
shorter than movdqa/movdqu.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:24:33 -04:00
Henrik Gramner
ad76e6e7e1 x86inc: Set ELF hidden visibility for global constants
Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:24:13 -04:00
Loren Merritt
25cb0c1a1e x86inc: activate REP_RET automatically
Now RET checks whether it immediately follows a branch, so the
programmer dosen't have to keep track of that condition. REP_RET
is still needed manually when it's a branch target, but that's
much rarer.

The implementation involves lots of spurious labels, but that's OK
because we strip them.

Signed-off-by: Derek Buitenhuis <derek.buitenhuis@gmail.com>
2013-10-07 06:17:59 -04:00
Ronald S. Bultje
c07ac8d467 VP9 MC (ssse3) optimizations.
Decoding time of ped1080p.webm goes from 20.7sec to 11.3sec.
2013-10-02 21:03:15 -04:00
Christophe Gisquet
2e81acc687 x86inc: Fix number of operands for cmp* instructions
cmp{p,s}{s,d} instructions do take an imm8 operand.

Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-04-09 23:55:30 +02:00
Christophe Gisquet
0b467a6e83 x264asm: fix cmp* number of arguments
cmp{p,s}{s,d} instructions do take an imm8 operand.

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2013-04-05 16:42:12 +02:00
Ronald S. Bultje
0c0828ecc5 x86: Use simple nop codes for <= sse (rather than <= mmx)
The "CentaurHauls family 6 model 9 stepping 8" family of CPUs
(flags: fpu vme de pse tsc msr cx8 sep mtrr pge mov pat mmx fxsr sse
up rng rng_en ace ace_en) SIGILLs on long nop codes.

Signed-off-by: Martin Storsjö <martin@martin.st>
2013-02-19 22:33:19 +02:00
Ronald S. Bultje
b582af1ed7 Use simple nop codes for <= sse (rather than <= mmx).
The "CPU: CentaurHauls family 6 model 9 stepping 8" family of CPUs
(flags: fpu vme de pse tsc msr cx8 sep mtrr pge mov pat mmx fxsr sse
up rng rng_en ace ace_en) SIGILLs on long nop codes.

Change-Id: I7e7c52a2191006df30a9aadbc40d481a1db89106
2013-02-11 23:38:57 +01:00
Michael Niedermayer
b45e0c2573 Merge commit 'd633d12b2cc999cee3ac25bf9a810fe7ff03726d'
* commit 'd633d12b2cc999cee3ac25bf9a810fe7ff03726d':
  x86inc: Add cvisible macro for C functions with public prefix

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-01-19 13:11:41 +01:00
Michael Niedermayer
1b03e09198 Merge commit 'ef5d41a5534b65f03d02f2e11a503ab8416bfc3b'
* commit 'ef5d41a5534b65f03d02f2e11a503ab8416bfc3b':
  x86inc: Rename "program_name" to "private_prefix"
  configure: Run SHFLAGS through ldflags_filter()

Conflicts:
	configure

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2013-01-19 13:01:06 +01:00
Diego Biurrun
d633d12b2c x86inc: Add cvisible macro for C functions with public prefix
This allows defining externally visible library symbols.

Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-01-18 22:02:03 +01:00
Diego Biurrun
ef5d41a553 x86inc: Rename "program_name" to "private_prefix"
The new name is more descriptive and will allow defining a separate
public prefix for externally visible library symbols.

Signed-off-by: Diego Biurrun <diego@biurrun.de>
2013-01-18 20:29:53 +01:00
Michael Niedermayer
7e90053822 Merge remote-tracking branch 'qatar/master'
* qatar/master:
  mpegvideo: increase edge_emu_buffer size for VC1
  lavc: merge latest x86inc.asm fixes with x264

Conflicts:
	libavcodec/mpegvideo.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-12-20 02:51:35 +01:00
Ronald S. Bultje
a34d9ad969 lavc: merge latest x86inc.asm fixes with x264
Unbreak NASM support.

Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2012-12-19 07:27:33 +01:00
Michael Niedermayer
a01fe55077 Merge commit 'c0dc57f1264dad1e121772d03abdb9e14ed8857f'
* commit 'c0dc57f1264dad1e121772d03abdb9e14ed8857f':
  asyncts: merge two conditions
  x86inc: fully concatenate tokens to fix macro expansion for nasm
  h264: initialize frame-mt context copies properly

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-12-14 15:43:46 +01:00
Janne Grunau
0995ad8db4 x86inc: fully concatenate tokens to fix macro expansion for nasm
Fixes build errors with nasm introduced in 6f40e9f070 for stack
memory alignment. Noticed by BugMaster.
2012-12-13 23:57:09 +01:00
Michael Niedermayer
7897919a88 Merge remote-tracking branch 'qatar/master'
* qatar/master:
  aacdec: Fix an off-by-one overwrite when switching to LTP profile from MAIN.
  x86inc: fix stack alignment on win64
  rtpproto: Remove unused defines

Conflicts:
	libavcodec/aacdec.c

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-12-13 12:23:48 +01:00
Ronald S. Bultje
140367aff9 x86inc: fix stack alignment on win64
Signed-off-by: Martin Storsjö <martin@martin.st>
2012-12-12 21:30:49 +02:00
Ronald S. Bultje
ce58642ed0 x86inc: support stack mem allocation and re-alignment in PROLOGUE.
Use this in VP8/H264-8bit loopfilter functions so they can be used if
there is no aligned stack (e.g. MSVC 32bit or ICC 10.x).

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2012-12-12 10:37:52 +01:00
Ronald S. Bultje
6f40e9f070 x86inc: support stack mem allocation and re-alignment in PROLOGUE
Use this in VP8/H264-8bit loopfilter functions so they can be used if
there is no aligned stack (e.g. MSVC 32bit or ICC 10.x).

Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
2012-12-12 05:23:46 +01:00
Michael Niedermayer
54a71f2e6c Merge commit 'b519298a1578e0c895d53d4b4ed8867b1c031a56'
* commit 'b519298a1578e0c895d53d4b4ed8867b1c031a56':
  pixdesc: fix yuva 10bit bit depth
  avconv: deprecate the -vol option
  x86: af_volume: add SSE2/SSSE3/AVX-optimized s32 volume scaling
  x86: af_volume: add SSE2-optimized s16 volume scaling

Conflicts:
	ffmpeg.c
	tests/ref/lavfi/pixdesc
	tests/ref/lavfi/pixfmts_copy
	tests/ref/lavfi/pixfmts_null
	tests/ref/lavfi/pixfmts_scale
	tests/ref/lavfi/pixfmts_vflip

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-12-06 15:55:47 +01:00
Justin Ruggles
b30a363331 x86: af_volume: add SSE2/SSSE3/AVX-optimized s32 volume scaling 2012-12-05 11:23:37 -05:00
Michael Niedermayer
da501ea857 Merge commit '802713c4e7b41bc2deed754d78649945c3442063'
* commit '802713c4e7b41bc2deed754d78649945c3442063':
  mss2: prevent potential uninitialized reads
  mss2: reindent after last commit
  mss2: fix handling of unmasked implicit WMV9 rectangles
  configure: add lavu dependency to lavr/lavfi .pc files
  x86inc: Set program_name outside of x86inc.asm

Conflicts:
	configure

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-11-12 10:57:06 +01:00
Diego Biurrun
f0d124f005 x86inc: Set program_name outside of x86inc.asm
This reduces the local difference to the x264 upstream version.
2012-11-11 11:06:19 +01:00
Michael Niedermayer
1dad486714 Merge commit '9ce02e14f01de50fcc6f7f459544b140be66d615'
* commit '9ce02e14f01de50fcc6f7f459544b140be66d615':
  x86: ac3dsp: port to cpuflags
  x86util: Add cpuflags_mmxext alias for cpuflags_mmx2
  x86inc: Only define program_name if the macro is unset

Conflicts:
	libavcodec/x86/ac3dsp.asm

Merged-by: Michael Niedermayer <michaelni@gmx.at>
2012-11-03 13:38:38 +01:00