mirror
/
libbpg
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

libbpg-0.9.6

This commit is contained in:
King_DuckZ 2015-10-27 11:46:00 +01:00
parent 3035b41edf
commit 35a8402710
248 changed files with 232891 additions and 100 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
ChangeLog
View File

@ -1,5 +1,11 @@
version 0.9.6:
- Faster encoding (x265 is the default encoder and is built in bpgenc).
- Added monochrome support to x265.
- Fixed metadata handling.
version 0.9.5:
- Added animation support.
- added bpgview utility.
- bpgenc: fixed support of some JPEG parameter combinations

59
Makefile
View File

@ -4,10 +4,10 @@
#
# Enable compilation of Javascript decoder with Emscripten
#USE_EMCC=y
# Enable x265 for the encoder (you must install it before)
#USE_X265=y
# Enable x265 for the encoder
USE_X265=y
# Enable the JCTVC code (best quality but slow) for the encoder
USE_JCTVC=y
#USE_JCTVC=y
# Compile bpgview (SDL and SDL_image libraries needed)
USE_BPGVIEW=y
# Enable it to use bit depths > 12 (need more tests to validate encoder)
@ -23,8 +23,8 @@ prefix=/usr/local
#################################
ifdef CONFIG_WIN32
#CROSS_PREFIX:=x86_64-w64-mingw32-
CROSS_PREFIX=i686-w64-mingw32-
CROSS_PREFIX:=x86_64-w64-mingw32-
#CROSS_PREFIX=i686-w64-mingw32-
EXE:=.exe
else
CROSS_PREFIX:=
@ -97,9 +97,41 @@ BPGENC_OBJS:=bpgenc.o
BPGENC_LIBS:=
ifdef USE_X265
BPGENC_OBJS+=x265_glue.o
BPGENC_LIBS+= -lx265
X265_LIBS:=./x265.out/8bit/libx265.a ./x265.out/10bit/libx265.a ./x265.out/12bit/libx265.a
BPGENC_OBJS+=x265_glue.o $(X265_LIBS)
bpgenc.o: CFLAGS+=-DUSE_X265
x265_glue.o: CFLAGS+=-I./x265/source -I./x265.out/8bit
x265_glue.o: $(X265_LIBS)
ifdef CONFIG_WIN32
CMAKE_OPTS:=-DCMAKE_TOOLCHAIN_FILE=../../x265/build/msys/toolchain-x86_64-w64-mingw32.cmake
else
CMAKE_OPTS:=
endif
x265.out:
mkdir -p x265.out/8bit x265.out/10bit x265.out/12bit
cd x265.out/12bit && cmake ../../x265/source $(CMAKE_OPTS) -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
cd x265.out/10bit && cmake ../../x265/source $(CMAKE_OPTS) -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN10=ON
cd x265.out/8bit && cmake ../../x265/source $(CMAKE_OPTS) -DLINKED_10BIT=ON -DLINKED_12BIT=ON -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
# use this target to manually rebuild x265
x265_make: | x265.out
$(MAKE) -C x265.out/12bit
$(MAKE) -C x265.out/10bit
$(MAKE) -C x265.out/8bit
x265_clean:
rm -rf x265.out
$(X265_LIBS): x265_make
else
x265_clean:
endif # USE_X265
ifdef USE_JCTVC
@ -133,10 +165,9 @@ endif # USE_JCTVC
ifdef CONFIG_WIN32
LDFLAGS+=-static
BPGDEC_LIBS:=-Wl,-dy -lpng -lz -Wl,-dn
BPGENC_LIBS+=-Wl,-dy -lpng -ljpeg -lz -Wl,-dn
BPGVIEW_LIBS:=-lmingw32 -lSDLmain -Wl,-dy -lSDL_image -lSDL -Wl,-dn -mwindows
BPGDEC_LIBS:=-lpng -lz
BPGENC_LIBS+=-lpng -ljpeg -lz
BPGVIEW_LIBS:=-lmingw32 -lSDLmain -lSDL_image -lSDL -mwindows
else
@ -171,10 +202,10 @@ bpgdec.js: $(LIBBPG_JS_OBJS) post.js
$(EMCC) $(EMLDFLAGS) -s TOTAL_MEMORY=33554432 -o $@ $(LIBBPG_JS_OBJS)
bpgdec8.js: $(LIBBPG_JS8_OBJS) post.js
$(EMCC) $(EMLDFLAGS) -s TOTAL_MEMORY=16777216 -o $@ $(LIBBPG_JS8_OBJS)
$(EMCC) $(EMLDFLAGS) -s TOTAL_MEMORY=33554432 -o $@ $(LIBBPG_JS8_OBJS)
bpgdec8a.js: $(LIBBPG_JS8A_OBJS) post.js
$(EMCC) $(EMLDFLAGS) -s TOTAL_MEMORY=16777216 -o $@ $(LIBBPG_JS8A_OBJS)
$(EMCC) $(EMLDFLAGS) -s TOTAL_MEMORY=33554432 -o $@ $(LIBBPG_JS8A_OBJS)
size:
strip bpgdec
@ -187,7 +218,7 @@ install: bpgenc bpgdec
CLEAN_DIRS=doc html libavcodec libavutil \
jctvc jctvc/TLibEncoder jctvc/TLibVideoIO jctvc/TLibCommon jctvc/libmd5
clean:
clean: x265_clean
rm -f $(PROGS) *.o *.a *.d *~ $(addsuffix /*.o, $(CLEAN_DIRS)) \
$(addsuffix /*.d, $(CLEAN_DIRS)) $(addsuffix /*~, $(CLEAN_DIRS)) \
$(addsuffix /*.a, $(CLEAN_DIRS))

103
README
View File

@ -8,12 +8,6 @@ BPG Image library and utilities
options should be OK for Linux). Type 'make' to compile and 'make
install' to install the compiled binaries.
- x265 usage: for much increased compression speed (but lower
quality), you can compile and install x265 and then enable its use
in the Makefile. x265 supports by default only 8 bits per component
and does not support monochrome encoding yet (hence no alpha nor
grayscale images can be encoded with it).
- bpgview: in order to compile it you need to install the SDL and
SDL_image libraries.
@ -27,24 +21,57 @@ BPG Image library and utilities
- The BPG file format is specified in doc/bpg_spec.txt.
2) BPG encoder
2) Compilation and Installation Notes
-------------------------------------
2.1) Linux
----------
- Edit the Makefile to change the compile options (the default
compile options should be OK). Type 'make' to compile and 'make
install' to install the compiled binaries.
- Use 'make -j N' where N is the number of CPU cores to compile faster.
- The following packages must be installed: SDL-devel
SDL_image-devel yasm. It is recommended to use yasm version >= 1.3.0
to have a faster compilation.
- Only a 64 bit target is supported because x265 needs it for bit
depths > 8.
2.2) Windows
------------
- Only cross-compilation from Linux is supported.
- The following packages need to be installed: mingw64-gcc
mingw64-libpng mingw64-libjpeg-turbo mingw64-SDL mingw64-SDL_image
yasm. It is recommended to use yasm version >= 1.3.0 to have a
faster compilation.
- Only a 64 bit target is supported because x265 needs it for bit
depths > 8.
3) BPG encoder
--------------
The BPG command line encoder is 'bpgenc'. It takes JPEG or PNG images
as input.
- Speed: by default bpgenc uses the JCTVC encoder which has a high
quality but is slow. If you compiled with x265, you can have a much
faster encoding with the '-e x265' option. With x265 you can also
select the encoding speed with the '-m' option (1 = fast, but larger
image, 9 = slower but smaller image). Warning: x265 does not support
monochrome (and alpha) yet, so you must use the JCTVC encoder for
these cases.
- Speed: by default bpgenc uses the x265. You can compile the much
slower but more efficient JCTVC encoder and select it with the '-e
jctvc' option. With x265 you can select the encoding speed with the
'-m' option (1 = fast, but larger image, 9 = slower but smaller
image).
- Bit depth: the default bit depth is 8. You can increase it to 10
('-b 10' option) to slightly increase the compression ratio. For web
publishing it is generally not a good idea because the Javascript
decoder uses more memory.
decoder uses more memory. The compiled x265 encoder supports the bit
depth of 8, 10 and 12. The slower JCTVC encoder can be compiled to
support higher bit depths (up to 14) by enabling the Makefile
define: USE_JCTVC_HIGH_BIT_DEPTH.
- Lossless compression is supported as a bonus thru the HEVC lossless
capabilities. Use a PNG input in this case unless you know what you
@ -60,15 +87,8 @@ as input.
- the JCTVC encoder gives smaller images than the x265 encoder
with lossless compression.
- There is a difference of interpretation of the quantizer parameter
(-q option) between the x265 and JCTVC encoder. The default value is
optimized for the JCTVC encoder, not for x265. We will try to align
the x265 value to JCTVC in the future.
- By default, the JCTVC encoder is limited to a precision of 12
bits. You can enable high bit depths (up to 14) by enabling the
Makefile define: USE_JCTVC_HIGH_BIT_DEPTH. The encoder is sligthly
slower in this case.
- There is a small difference of interpretation of the quantizer
parameter (-q option) between the x265 and JCTVC encoder.
- Color space and chroma format:
@ -125,11 +145,11 @@ as input.
with the '-keepmetadata' option. For JPEG input, EXIF, ICCP and XMP
are copied. For PNG input, ICCP is copied.
- Objective comparisons: the JCTVC encoder is tuned for PSNR only, not
for SSIM, so you should use PSNR when making objective comparison
with other formats. x265 is tuned by default for SSIM.
- Objective comparisons: x265 is tuned by default for SSIM. the JCTVC
encoder is tuned for PSNR only, not for SSIM, so you should use PSNR
when making objective comparison with other formats.
3) BPG decoder
4) BPG decoder
--------------
The BPG command line decoder is bpgdec. It outputs a PNG or PPM
@ -141,7 +161,7 @@ no decoded image is output).
- The '-b' option selects the bit depth (8 or 16) of the PNG
output. It is independent of the internal BPG bit depth.
4) BPG viewer
5) BPG viewer
-------------
The BPG image viewer uses the SDL library to display BPG images and
@ -149,7 +169,7 @@ other image formats supported by the SDL_image library. The available
keys are displayed by launching bpgview without parameters. bpgview
supports BPG animations.
5) BPG decoding library
6) BPG decoding library
-----------------------
BPG images can be decoded in any program with the libbpg
@ -161,7 +181,7 @@ provided as a static one.
Currently there is no similar library for encoding so you should
invoke the bpgenc utility.
6) Javascript decoder
7) Javascript decoder
---------------------
The following Javascript decoders are available, sorted by increasing size:
@ -193,7 +213,7 @@ be avoided, as with animated GIFs.
asm.js gives an interesting speed boost, so we hope that more browsers
will support this Javascript subset.
7) FFmpeg modifications
8) FFmpeg modifications
-----------------------
- Completed support of chroma_format_idc = 0 (monochrome mode).
@ -217,16 +237,25 @@ will support this Javascript subset.
- Stripped FFmpeg from all codecs except HEVC and the necessary
support code.
8) Licensing
------------
9) x265 modifications
---------------------
- Support of monochrome format (some part not used by BPG may be
missing).
- Support of static build.
10) Licensing
-------------
- libbpg and bpgdec are released under the LGPL license (the FFmpeg
part is under the LGPL, the BPG specific part is released under the
BSD license).
- bpgenc is released under the BSD license (it includes the JCTVC code
which is released under the BSD license. The BPG specific part is
released under the BSD license).
- bpgenc is released under the GPL version 2 license. The BPG specific
code is released under the BSD license. The JCTVC code is released
under the BSD license. The x265 code is released under the GPL
version 2 license.
- BPG relies on the HEVC compression technology which may be protected
by patents in some countries. Most devices already include or will

2
VERSION
View File

@ -1 +1 @@
0.9.5
0.9.6

30
bpgenc.c
View File

@ -1893,10 +1893,12 @@ static int build_modified_sps(uint8_t **pout_buf, int *pout_buf_len,
int vui_hrd_parameters_present_flag, bitstream_restriction_flag;
sar_present = get_bits(gb, 1);
sar_idx = get_bits(gb, 8);
if (sar_idx == 255) {
skip_bits(gb, 16); /* sar_num */
skip_bits(gb, 16); /* sar_den */
if (sar_present) {
sar_idx = get_bits(gb, 8);
if (sar_idx == 255) {
skip_bits(gb, 16); /* sar_num */
skip_bits(gb, 16); /* sar_den */
}
}
overscan_info_present_flag = get_bits(gb, 1);
@ -2159,38 +2161,38 @@ static int build_modified_hevc(uint8_t **pout_buf,
}
typedef enum {
#if defined(USE_JCTVC)
HEVC_ENCODER_JCTVC,
#endif
#if defined(USE_X265)
HEVC_ENCODER_X265,
#endif
#if defined(USE_JCTVC)
HEVC_ENCODER_JCTVC,
#endif
HEVC_ENCODER_COUNT,
} HEVCEncoderEnum;
static char *hevc_encoder_name[HEVC_ENCODER_COUNT] = {
#if defined(USE_JCTVC)
"jctvc",
#endif
#if defined(USE_X265)
"x265",
#endif
#if defined(USE_JCTVC)
"jctvc",
#endif
};
static HEVCEncoder *hevc_encoder_tab[HEVC_ENCODER_COUNT] = {
#if defined(USE_JCTVC)
&jctvc_encoder,
#endif
#if defined(USE_X265)
&x265_hevc_encoder,
#endif
#if defined(USE_JCTVC)
&jctvc_encoder,
#endif
};
#define IMAGE_HEADER_MAGIC 0x425047fb
#define DEFAULT_OUTFILENAME "out.bpg"
#define DEFAULT_QP 28
#define DEFAULT_QP 29
#define DEFAULT_BIT_DEPTH 8
#ifdef RExt__HIGH_BIT_DEPTH_SUPPORT

4
doc/bpg_spec.txt
View File

@ -79,9 +79,7 @@ heic_file() {
picture_data_length ue7(32)
if (extension_present_flag)
extension_data_length ue7(32)
if (extension_present_flag) {
extension_data_length ue7(32)
extension_data()
}

6
html/bpgdec.js
View File

File diff suppressed because one or more lines are too long

6
html/bpgdec8.js
View File

File diff suppressed because one or more lines are too long

8
html/bpgdec8a.js
View File

File diff suppressed because one or more lines are too long

1
libbpg.c
View File

@ -1786,6 +1786,7 @@ static int bpg_decode_header(BPGHeaderData *h,
md = av_malloc(sizeof(BPGExtensionData));
md->tag = tag;
md->buf_len = buf_len;
md->next = NULL;
*plast_md = md;
plast_md = &md->next;

343
x265/COPYING Normal file
View File

@ -0,0 +1,343 @@
GNU GENERAL PUBLIC LICENSE
Version 2, June 1991
Copyright (C) 1989, 1991 Free Software Foundation, Inc.
59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The licenses for most software are designed to take away your
freedom to share and change it. By contrast, the GNU General Public
License is intended to guarantee your freedom to share and change free
software--to make sure the software is free for all its users. This
General Public License applies to most of the Free Software
Foundation's software and to any other program whose authors commit to
using it. (Some other Free Software Foundation software is covered by
the GNU Library General Public License instead.) You can apply it to
your programs, too.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
this service if you wish), that you receive source code or can get it
if you want it, that you can change the software or use pieces of it
in new free programs; and that you know you can do these things.
To protect your rights, we need to make restrictions that forbid
anyone to deny you these rights or to ask you to surrender the rights.
These restrictions translate to certain responsibilities for you if you
distribute copies of the software, or if you modify it.
For example, if you distribute copies of such a program, whether
gratis or for a fee, you must give the recipients all the rights that
you have. You must make sure that they, too, receive or can get the
source code. And you must show them these terms so they know their
rights.
We protect your rights with two steps: (1) copyright the software, and
(2) offer you this license which gives you legal permission to copy,
distribute and/or modify the software.
Also, for each author's protection and ours, we want to make certain
that everyone understands that there is no warranty for this free
software. If the software is modified by someone else and passed on, we
want its recipients to know that what they have is not the original, so
that any problems introduced by others will not reflect on the original
authors' reputations.
Finally, any free program is threatened constantly by software
patents. We wish to avoid the danger that redistributors of a free
program will individually obtain patent licenses, in effect making the
program proprietary. To prevent this, we have made it clear that any
patent must be licensed for everyone's free use or not licensed at all.
The precise terms and conditions for copying, distribution and
modification follow.
GNU GENERAL PUBLIC LICENSE
TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
0. This License applies to any program or other work which contains
a notice placed by the copyright holder saying it may be distributed
under the terms of this General Public License. The "Program", below,
refers to any such program or work, and a "work based on the Program"
means either the Program or any derivative work under copyright law:
that is to say, a work containing the Program or a portion of it,
either verbatim or with modifications and/or translated into another
language. (Hereinafter, translation is included without limitation in
the term "modification".) Each licensee is addressed as "you".
Activities other than copying, distribution and modification are not
covered by this License; they are outside its scope. The act of
running the Program is not restricted, and the output from the Program
is covered only if its contents constitute a work based on the
Program (independent of having been made by running the Program).
Whether that is true depends on what the Program does.
1. You may copy and distribute verbatim copies of the Program's
source code as you receive it, in any medium, provided that you
conspicuously and appropriately publish on each copy an appropriate
copyright notice and disclaimer of warranty; keep intact all the
notices that refer to this License and to the absence of any warranty;
and give any other recipients of the Program a copy of this License
along with the Program.
You may charge a fee for the physical act of transferring a copy, and
you may at your option offer warranty protection in exchange for a fee.
2. You may modify your copy or copies of the Program or any portion
of it, thus forming a work based on the Program, and copy and
distribute such modifications or work under the terms of Section 1
above, provided that you also meet all of these conditions:
a) You must cause the modified files to carry prominent notices
stating that you changed the files and the date of any change.
b) You must cause any work that you distribute or publish, that in
whole or in part contains or is derived from the Program or any
part thereof, to be licensed as a whole at no charge to all third
parties under the terms of this License.
c) If the modified program normally reads commands interactively
when run, you must cause it, when started running for such
interactive use in the most ordinary way, to print or display an
announcement including an appropriate copyright notice and a
notice that there is no warranty (or else, saying that you provide
a warranty) and that users may redistribute the program under
these conditions, and telling the user how to view a copy of this
License. (Exception: if the Program itself is interactive but
does not normally print such an announcement, your work based on
the Program is not required to print an announcement.)
These requirements apply to the modified work as a whole. If
identifiable sections of that work are not derived from the Program,
and can be reasonably considered independent and separate works in
themselves, then this License, and its terms, do not apply to those
sections when you distribute them as separate works. But when you
distribute the same sections as part of a whole which is a work based
on the Program, the distribution of the whole must be on the terms of
this License, whose permissions for other licensees extend to the
entire whole, and thus to each and every part regardless of who wrote it.
Thus, it is not the intent of this section to claim rights or contest
your rights to work written entirely by you; rather, the intent is to
exercise the right to control the distribution of derivative or
collective works based on the Program.
In addition, mere aggregation of another work not based on the Program
with the Program (or with a work based on the Program) on a volume of
a storage or distribution medium does not bring the other work under
the scope of this License.
3. You may copy and distribute the Program (or a work based on it,
under Section 2) in object code or executable form under the terms of
Sections 1 and 2 above provided that you also do one of the following:
a) Accompany it with the complete corresponding machine-readable
source code, which must be distributed under the terms of Sections
1 and 2 above on a medium customarily used for software interchange; or,
b) Accompany it with a written offer, valid for at least three
years, to give any third party, for a charge no more than your
cost of physically performing source distribution, a complete
machine-readable copy of the corresponding source code, to be
distributed under the terms of Sections 1 and 2 above on a medium
customarily used for software interchange; or,
c) Accompany it with the information you received as to the offer
to distribute corresponding source code. (This alternative is
allowed only for noncommercial distribution and only if you
received the program in object code or executable form with such
an offer, in accord with Subsection b above.)
The source code for a work means the preferred form of the work for
making modifications to it. For an executable work, complete source
code means all the source code for all modules it contains, plus any
associated interface definition files, plus the scripts used to
control compilation and installation of the executable. However, as a
special exception, the source code distributed need not include
anything that is normally distributed (in either source or binary
form) with the major components (compiler, kernel, and so on) of the
operating system on which the executable runs, unless that component
itself accompanies the executable.
If distribution of executable or object code is made by offering
access to copy from a designated place, then offering equivalent
access to copy the source code from the same place counts as
distribution of the source code, even though third parties are not
compelled to copy the source along with the object code.
4. You may not copy, modify, sublicense, or distribute the Program
except as expressly provided under this License. Any attempt
otherwise to copy, modify, sublicense or distribute the Program is
void, and will automatically terminate your rights under this License.
However, parties who have received copies, or rights, from you under
this License will not have their licenses terminated so long as such
parties remain in full compliance.
5. You are not required to accept this License, since you have not
signed it. However, nothing else grants you permission to modify or
distribute the Program or its derivative works. These actions are
prohibited by law if you do not accept this License. Therefore, by
modifying or distributing the Program (or any work based on the
Program), you indicate your acceptance of this License to do so, and
all its terms and conditions for copying, distributing or modifying
the Program or works based on it.
6. Each time you redistribute the Program (or any work based on the
Program), the recipient automatically receives a license from the
original licensor to copy, distribute or modify the Program subject to
these terms and conditions. You may not impose any further
restrictions on the recipients' exercise of the rights granted herein.
You are not responsible for enforcing compliance by third parties to
this License.
7. If, as a consequence of a court judgment or allegation of patent
infringement or for any other reason (not limited to patent issues),
conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot
distribute so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you
may not distribute the Program at all. For example, if a patent
license would not permit royalty-free redistribution of the Program by
all those who receive copies directly or indirectly through you, then
the only way you could satisfy both it and this License would be to
refrain entirely from distribution of the Program.
If any portion of this section is held invalid or unenforceable under
any particular circumstance, the balance of the section is intended to
apply and the section as a whole is intended to apply in other
circumstances.
It is not the purpose of this section to induce you to infringe any
patents or other property right claims or to contest validity of any
such claims; this section has the sole purpose of protecting the
integrity of the free software distribution system, which is
implemented by public license practices. Many people have made
generous contributions to the wide range of software distributed
through that system in reliance on consistent application of that
system; it is up to the author/donor to decide if he or she is willing
to distribute software through any other system and a licensee cannot
impose that choice.
This section is intended to make thoroughly clear what is believed to
be a consequence of the rest of this License.
8. If the distribution and/or use of the Program is restricted in
certain countries either by patents or by copyrighted interfaces, the
original copyright holder who places the Program under this License
may add an explicit geographical distribution limitation excluding
those countries, so that distribution is permitted only in or among
countries not thus excluded. In such case, this License incorporates
the limitation as if written in the body of this License.
9. The Free Software Foundation may publish revised and/or new versions
of the General Public License from time to time. Such new versions will
be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the Program
specifies a version number of this License which applies to it and "any
later version", you have the option of following the terms and conditions
either of that version or of any later version published by the Free
Software Foundation. If the Program does not specify a version number of
this License, you may choose any version ever published by the Free Software
Foundation.
10. If you wish to incorporate parts of the Program into other free
programs whose distribution conditions are different, write to the author
to ask for permission. For software which is copyrighted by the Free
Software Foundation, write to the Free Software Foundation; we sometimes
make exceptions for this. Our decision will be guided by the two goals
of preserving the free status of all derivatives of our free software and
of promoting the sharing and reuse of software generally.
NO WARRANTY
11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN
OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS
TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE
PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
REPAIR OR CORRECTION.
12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
POSSIBILITY OF SUCH DAMAGES.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
convey the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; if not, write to the Free Software
Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
Also add information on how to contact you by electronic and paper mail.
If the program is interactive, make it output a short notice like this
when it starts in an interactive mode:
Gnomovision version 69, Copyright (C) year name of author
Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
This is free software, and you are welcome to redistribute it
under certain conditions; type `show c' for details.
The hypothetical commands `show w' and `show c' should show the appropriate
parts of the General Public License. Of course, the commands you use may
be called something other than `show w' and `show c'; they could even be
mouse-clicks or menu items--whatever suits your program.
You should also get your employer (if you work as a programmer) or your
school, if any, to sign a "copyright disclaimer" for the program, if
necessary. Here is a sample; alter the names:
Yoyodyne, Inc., hereby disclaims all copyright interest in the program
`Gnomovision' (which makes passes at compilers) written by James Hacker.
<signature of Ty Coon>, 1 April 1989
Ty Coon, President of Vice
This General Public License does not permit incorporating your program into
proprietary programs. If your program is a subroutine library, you may
consider it more useful to permit linking proprietary applications with the
library. If this is what you want to do, use the GNU Library General
Public License instead of this License.
This program is also available under a commercial proprietary license.
For more information, contact us at license @ x265.com.

71
x265/build/README.txt Normal file
View File

@ -0,0 +1,71 @@
= Mandatory Prerequisites =
* GCC, MSVC (9, 10, 11, 12), Xcode or Intel C/C++
* CMake 2.8.8 or later http://www.cmake.org
* On linux, ccmake is helpful, usually a package named cmake-curses-gui
Note: MSVC12 requires cmake 2.8.11 or later
= Optional Prerequisites =
1. Yasm 1.2.0 or later, to compile assembly primitives (performance)
For Windows, download the latest yasm executable
http://yasm.tortall.net/Download.html and copy the EXE into
C:\Windows or somewhere else in your %PATH% that a 32-bit app (cmake)
can find it. If it is not in the path, you must manually tell cmake
where to find it. Note: you do not need the vsyasm packages, x265
does not use them. You only need the yasm executable itself.
On Linux, the packaged yasm may be older than 1.2, in which case
so you will need get the latest source and build it yourself.
Once YASM is properly installed, run cmake to regenerate projects. If you
do not see the below line in the cmake output, YASM is not in the PATH.
-- Found Yasm 1.3.0 to build assembly primitives
Now build the encoder and run x265 -V:
x265 [info]: using cpu capabilities: MMX, SSE2, ...
If cpu capabilities line says 'none!', then the encoder was built
without yasm.
2. VisualLeakDetector (Windows Only)
Download from https://vld.codeplex.com/releases and install. May need
to re-login in order for it to be in your %PATH%. Cmake will find it
and enable leak detection in debug builds without any additional work.
If VisualLeakDetector is not installed, cmake will complain a bit, but
it is completely harmless.
= Build Instructions Linux =
1. Use cmake to generate Makefiles: cmake ../source
2. Build x265: make
Or use our shell script which runs cmake then opens the curses GUI to
configure build options
1. cd build/linux ; ./make-Makefiles.bash
2. make
= Build Instructions Windows =
We recommend you use one of the make-solutions.bat files in the appropriate
build/ sub-folder for your preferred compiler. They will open the cmake-gui
to configure build options, click configure until no more red options remain,
then click generate and exit. There should now be an x265.sln file in the
same folder, open this in Visual Studio and build it.
= Version number considerations =
Note that cmake will update X265_VERSION each time cmake runs, if you are
building out of a Mercurial source repository. If you are building out of
a release source package, the version will not change. If Mercurial is not
found, the version will be "unknown".

3
x265/build/linux/make-Makefiles.bash Executable file
View File

@ -0,0 +1,3 @@
#!/bin/bash
# Run this from within a bash shell
cmake -G "Unix Makefiles" ../../source && ccmake ../../source

41
x265/build/linux/multilib.sh Executable file
View File

@ -0,0 +1,41 @@
#!/bin/sh
mkdir -p 8bit 10bit 12bit
cd 12bit
cmake ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
make ${MAKEFLAGS}
cd ../10bit
cmake ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
make ${MAKEFLAGS}
cd ../8bit
ln -sf ../10bit/libx265.a libx265_main10.a
ln -sf ../12bit/libx265.a libx265_main12.a
cmake ../../../source -DEXTRA_LIB="x265_main10.a;x265_main12.a" -DEXTRA_LINK_FLAGS=-L. -DLINKED_10BIT=ON -DLINKED_12BIT=ON
make ${MAKEFLAGS}
# rename the 8bit library, then combine all three into libx265.a
mv libx265.a libx265_main.a
uname=`uname`
if [ "$uname" = "Linux" ]
then
# On Linux, we use GNU ar to combine the static libraries together
ar -M <<EOF
CREATE libx265.a
ADDLIB libx265_main.a
ADDLIB libx265_main10.a
ADDLIB libx265_main12.a
SAVE
END
EOF
else
# Mac/BSD libtool
libtool -static -o libx265.a libx265_main.a libx265_main10.a libx265_main12.a 2>/dev/null
fi

3
x265/build/msys/make-Makefiles.sh Normal file
View File

@ -0,0 +1,3 @@
#!/bin/sh
# Run this from within an MSYS bash shell
cmake -G "MSYS Makefiles" ../../source && cmake-gui ../../source

8
x265/build/msys/make-x86_64-w64-mingw32-Makefiles.sh Normal file
View File

@ -0,0 +1,8 @@
#!/bin/sh
# This will generate a cross-compile environment, compiling an x86_64
# Win64 target from a 32bit MinGW32 host environment. If your MinGW
# install is 64bit, you can use the native compiler batch file:
# make-Makefiles.sh
cmake -G "MSYS Makefiles" -DCMAKE_TOOLCHAIN_FILE=toolchain-x86_64-w64-mingw32.cmake ../../source && cmake-gui ../../source

29
x265/build/msys/multilib.sh Executable file
View File

@ -0,0 +1,29 @@
#!/bin/sh
mkdir -p 8bit 10bit 12bit
cd 12bit
cmake -G "MSYS Makefiles" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
make ${MAKEFLAGS}
cp libx265.a ../8bit/libx265_main12.a
cd ../10bit
cmake -G "MSYS Makefiles" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
make ${MAKEFLAGS}
cp libx265.a ../8bit/libx265_main10.a
cd ../8bit
cmake -G "MSYS Makefiles" ../../../source -DEXTRA_LIB="x265_main10.a;x265_main12.a" -DEXTRA_LINK_FLAGS=-L. -DLINKED_10BIT=ON -DLINKED_12BIT=ON
make ${MAKEFLAGS}
# rename the 8bit library, then combine all three into libx265.a using GNU ar
mv libx265.a libx265_main.a
ar -M <<EOF
CREATE libx265.a
ADDLIB libx265_main.a
ADDLIB libx265_main10.a
ADDLIB libx265_main12.a
SAVE
END
EOF

9
x265/build/msys/toolchain-mingw32.cmake Normal file
View File

@ -0,0 +1,9 @@
# cmake -DCMAKE_TOOLCHAIN_FILE=toolchain-mingw32.cmake
# this one is important
SET(CMAKE_SYSTEM_NAME Windows)
# specify the cross compiler
SET(CMAKE_C_COMPILER i686-w64-mingw32-gcc)
SET(CMAKE_CXX_COMPILER i686-w64-mingw32-g++)
SET(CMAKE_RC_COMPILER i686-w64-mingw32-windres)
SET(CMAKE_ASM_YASM_COMPILER yasm)

6
x265/build/msys/toolchain-x86_64-w64-mingw32.cmake Normal file
View File

@ -0,0 +1,6 @@
SET(CMAKE_SYSTEM_NAME Windows)
SET(CMAKE_C_COMPILER x86_64-w64-mingw32-gcc)
SET(CMAKE_CXX_COMPILER x86_64-w64-mingw32-g++)
SET(CMAKE_RC_COMPILER x86_64-w64-mingw32-windres)
SET(CMAKE_RANLIB x86_64-w64-mingw32-ranlib)
SET(CMAKE_ASM_YASM_COMPILER yasm)

14
x265/build/vc10-x86/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS100COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 10 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS100COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc10-x86/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 10" ..\..\source && cmake-gui ..\..\source

14
x265/build/vc10-x86_64/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS100COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 10 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS100COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc10-x86_64/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 10 Win64" ..\..\source && cmake-gui ..\..\source

44
x265/build/vc10-x86_64/multilib.bat Normal file
View File

@ -0,0 +1,44 @@
@echo off
if "%VS100COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 10 not detected"
exit 1
)
call "%VS100COMNTOOLS%\..\..\VC\vcvarsall.bat"
@mkdir 12bit
@mkdir 10bit
@mkdir 8bit
@cd 12bit
cmake -G "Visual Studio 10 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main12.lib
)
@cd ..\10bit
cmake -G "Visual Studio 10 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main10.lib
)
@cd ..\8bit
if not exist x265-static-main10.lib (
msg "%username%" "10bit build failed"
exit 1
)
if not exist x265-static-main12.lib (
msg "%username%" "12bit build failed"
exit 1
)
cmake -G "Visual Studio 10 Win64" ../../../source -DEXTRA_LIB="x265-static-main10.lib;x265-static-main12.lib" -DLINKED_10BIT=ON -DLINKED_12BIT=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
:: combine static libraries (ignore warnings caused by winxp.cpp hacks)
move Release\x265-static.lib x265-static-main.lib
LIB.EXE /ignore:4006 /ignore:4221 /OUT:Release\x265-static.lib x265-static-main.lib x265-static-main10.lib x265-static-main12.lib
)
pause

14
x265/build/vc11-x86/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS110COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 11 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS110COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc11-x86/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 11" ..\..\source && cmake-gui ..\..\source

14
x265/build/vc11-x86_64/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS110COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 11 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS110COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc11-x86_64/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 11 Win64" ..\..\source && cmake-gui ..\..\source

44
x265/build/vc11-x86_64/multilib.bat Normal file
View File

@ -0,0 +1,44 @@
@echo off
if "%VS110COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 11 not detected"
exit 1
)
call "%VS110COMNTOOLS%\..\..\VC\vcvarsall.bat"
@mkdir 12bit
@mkdir 10bit
@mkdir 8bit
@cd 12bit
cmake -G "Visual Studio 11 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main12.lib
)
@cd ..\10bit
cmake -G "Visual Studio 11 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main10.lib
)
@cd ..\8bit
if not exist x265-static-main10.lib (
msg "%username%" "10bit build failed"
exit 1
)
if not exist x265-static-main12.lib (
msg "%username%" "12bit build failed"
exit 1
)
cmake -G "Visual Studio 11 Win64" ../../../source -DEXTRA_LIB="x265-static-main10.lib;x265-static-main12.lib" -DLINKED_10BIT=ON -DLINKED_12BIT=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
:: combine static libraries (ignore warnings caused by winxp.cpp hacks)
move Release\x265-static.lib x265-static-main.lib
LIB.EXE /ignore:4006 /ignore:4221 /OUT:Release\x265-static.lib x265-static-main.lib x265-static-main10.lib x265-static-main12.lib
)
pause

14
x265/build/vc12-x86/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS120COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 12 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS120COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc12-x86/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 12" ..\..\source && cmake-gui ..\..\source

14
x265/build/vc12-x86_64/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS120COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 12 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS120COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc12-x86_64/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 12 Win64" ..\..\source && cmake-gui ..\..\source

44
x265/build/vc12-x86_64/multilib.bat Normal file
View File

@ -0,0 +1,44 @@
@echo off
if "%VS120COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 12 not detected"
exit 1
)
call "%VS120COMNTOOLS%\..\..\VC\vcvarsall.bat"
@mkdir 12bit
@mkdir 10bit
@mkdir 8bit
@cd 12bit
cmake -G "Visual Studio 12 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main12.lib
)
@cd ..\10bit
cmake -G "Visual Studio 12 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main10.lib
)
@cd ..\8bit
if not exist x265-static-main10.lib (
msg "%username%" "10bit build failed"
exit 1
)
if not exist x265-static-main12.lib (
msg "%username%" "12bit build failed"
exit 1
)
cmake -G "Visual Studio 12 Win64" ../../../source -DEXTRA_LIB="x265-static-main10.lib;x265-static-main12.lib" -DLINKED_10BIT=ON -DLINKED_12BIT=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
:: combine static libraries (ignore warnings caused by winxp.cpp hacks)
move Release\x265-static.lib x265-static-main.lib
LIB.EXE /ignore:4006 /ignore:4221 /OUT:Release\x265-static.lib x265-static-main.lib x265-static-main10.lib x265-static-main12.lib
)
pause

14
x265/build/vc9-x86/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS90COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 9 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS90COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc9-x86/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 9 2008" ..\..\source && cmake-gui ..\..\source

14
x265/build/vc9-x86_64/build-all.bat Normal file
View File

@ -0,0 +1,14 @@
@echo off
if "%VS90COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 9 not detected"
exit 1
)
if not exist x265.sln (
call make-solutions.bat
)
if exist x265.sln (
call "%VS90COMNTOOLS%\..\..\VC\vcvarsall.bat"
MSBuild /property:Configuration="Release" x265.sln
MSBuild /property:Configuration="Debug" x265.sln
MSBuild /property:Configuration="RelWithDebInfo" x265.sln
)

6
x265/build/vc9-x86_64/make-solutions.bat Normal file
View File

@ -0,0 +1,6 @@
@echo off
::
:: run this batch file to create a Visual Studio solution file for this project.
:: See the cmake documentation for other generator targets
::
cmake -G "Visual Studio 9 2008 Win64" ..\..\source && cmake-gui ..\..\source

44
x265/build/vc9-x86_64/multilib.bat Normal file
View File

@ -0,0 +1,44 @@
@echo off
if "%VS90COMNTOOLS%" == "" (
msg "%username%" "Visual Studio 9 not detected"
exit 1
)
call "%VS90COMNTOOLS%\..\..\VC\vcvarsall.bat"
@mkdir 12bit
@mkdir 10bit
@mkdir 8bit
@cd 12bit
cmake -G "Visual Studio 9 2008 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF -DMAIN12=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main12.lib
)
@cd ..\10bit
cmake -G "Visual Studio 9 2008 Win64" ../../../source -DHIGH_BIT_DEPTH=ON -DEXPORT_C_API=OFF -DENABLE_SHARED=OFF -DENABLE_CLI=OFF
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
copy/y Release\x265-static.lib ..\8bit\x265-static-main10.lib
)
@cd ..\8bit
if not exist x265-static-main10.lib (
msg "%username%" "10bit build failed"
exit 1
)
if not exist x265-static-main12.lib (
msg "%username%" "12bit build failed"
exit 1
)
cmake -G "Visual Studio 9 2008 Win64" ../../../source -DEXTRA_LIB="x265-static-main10.lib;x265-static-main12.lib" -DLINKED_10BIT=ON -DLINKED_12BIT=ON
if exist x265.sln (
MSBuild /property:Configuration="Release" x265.sln
:: combine static libraries (ignore warnings caused by winxp.cpp hacks)
move Release\x265-static.lib x265-static-main.lib
LIB.EXE /ignore:4006 /ignore:4221 /OUT:Release\x265-static.lib x265-static-main.lib x265-static-main10.lib x265-static-main12.lib
)
pause

2
x265/build/xcode/make-project.sh Executable file
View File

@ -0,0 +1,2 @@
#!/bin/sh
cmake -G "Xcode" ../../source && ccmake ../../source

561
x265/doc/intra/intra-16x16.txt Normal file
View File

@ -0,0 +1,561 @@
--- 16x16, Mode= 2 [F]---
[ 0]: Fact= 0: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact= 0: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 2]: Fact= 0: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 3]: Fact= 0: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 4]: Fact= 0: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 5]: Fact= 0: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[ 6]: Fact= 0: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[ 7]: Fact= 0: -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[ 8]: Fact= 0: -10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25, *
[ 9]: Fact= 0: -11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26, *
[10]: Fact= 0: -12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27, *
[11]: Fact= 0: -13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28, *
[12]: Fact= 0: -14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29, *
[13]: Fact= 0: -15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29,-30, *
[14]: Fact= 0: -16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29,-30,-31, *
[15]: Fact= 0: -17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29,-30,-31,-32, *
--- 16x16, Mode= 3 [F]---
[ 0]: Fact=26: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact=20: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 2]: Fact=14: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 3]: Fact= 8: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 4]: Fact= 2: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 5]: Fact=28: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 6]: Fact=22: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[ 7]: Fact=16: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[ 8]: Fact=10: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[ 9]: Fact= 4: -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25, *
[10]: Fact=30: -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25, *
[11]: Fact=24: -10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26, *
[12]: Fact=18: -11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27, *
[13]: Fact=12: -12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28, *
[14]: Fact= 6: -13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29, *
[15]: Fact= 0: -14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27,-28,-29, *
--- 16x16, Mode= 4 [F]---
[ 0]: Fact=21: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact=10: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 2]: Fact=31: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 3]: Fact=20: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 4]: Fact= 9: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 5]: Fact=30: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 6]: Fact=19: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 7]: Fact= 8: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[ 8]: Fact=29: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[ 9]: Fact=18: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[10]: Fact= 7: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[11]: Fact=28: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[12]: Fact=17: -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25, *
[13]: Fact= 6: -10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26, *
[14]: Fact=27: -10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26, *
[15]: Fact=16: -11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25,-26,-27, *
--- 16x16, Mode= 5 [F]---
[ 0]: Fact=17: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact= 2: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 2]: Fact=19: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 3]: Fact= 4: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 4]: Fact=21: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 5]: Fact= 6: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 6]: Fact=23: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 7]: Fact= 8: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 8]: Fact=25: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[ 9]: Fact=10: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[10]: Fact=27: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[11]: Fact=12: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[12]: Fact=29: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[13]: Fact=14: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[14]: Fact=31: -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24, *
[15]: Fact=16: -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23,-24,-25, *
--- 16x16, Mode= 6 [F]---
[ 0]: Fact=13: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact=26: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 2]: Fact= 7: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 3]: Fact=20: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 4]: Fact= 1: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 5]: Fact=14: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 6]: Fact=27: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 7]: Fact= 8: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 8]: Fact=21: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[ 9]: Fact= 2: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[10]: Fact=15: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[11]: Fact=28: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[12]: Fact= 9: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[13]: Fact=22: -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22, *
[14]: Fact= 3: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
[15]: Fact=16: -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21,-22,-23, *
--- 16x16, Mode= 7 [F]---
[ 0]: Fact= 9: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact=18: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 2]: Fact=27: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 3]: Fact= 4: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 4]: Fact=13: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 5]: Fact=22: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 6]: Fact=31: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 7]: Fact= 8: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 8]: Fact=17: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[ 9]: Fact=26: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[10]: Fact= 3: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[11]: Fact=12: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[12]: Fact=21: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[13]: Fact=30: -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20, *
[14]: Fact= 7: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
[15]: Fact=16: -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19,-20,-21, *
--- 16x16, Mode= 8 [F]---
[ 0]: Fact= 5: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact=10: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 2]: Fact=15: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 3]: Fact=20: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 4]: Fact=25: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 5]: Fact=30: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 6]: Fact= 3: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 7]: Fact= 8: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 8]: Fact=13: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[ 9]: Fact=18: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[10]: Fact=23: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[11]: Fact=28: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18, *
[12]: Fact= 1: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[13]: Fact= 6: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[14]: Fact=11: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
[15]: Fact=16: -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17,-18,-19, *
--- 16x16, Mode= 9 [ ]---
[ 0]: Fact= 2: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 1]: Fact= 4: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 2]: Fact= 6: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 3]: Fact= 8: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 4]: Fact=10: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 5]: Fact=12: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 6]: Fact=14: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 7]: Fact=16: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 8]: Fact=18: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[ 9]: Fact=20: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[10]: Fact=22: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[11]: Fact=24: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[12]: Fact=26: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[13]: Fact=28: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[14]: Fact=30: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
[15]: Fact= 0: -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16,-17, *
--- 16x16, Mode=10 [ ]---
[ 0]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 2]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 3]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 4]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 5]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 6]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 7]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 8]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 9]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[10]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[11]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[12]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[13]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[14]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[15]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
--- 16x16, Mode=11 [ ]---
[ 0]: Fact=30: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=28: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 2]: Fact=26: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 3]: Fact=24: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 4]: Fact=22: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 5]: Fact=20: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 6]: Fact=18: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 7]: Fact=16: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 8]: Fact=14: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 9]: Fact=12: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[10]: Fact=10: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[11]: Fact= 8: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[12]: Fact= 6: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[13]: Fact= 4: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[14]: Fact= 2: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[15]: Fact= 0: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
--- 16x16, Mode=12 [F]---
[ 0]: Fact=27: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=22: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 2]: Fact=17: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 3]: Fact=12: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 4]: Fact= 7: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 5]: Fact= 2: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 6]: Fact=29: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 7]: Fact=24: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 8]: Fact=19: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 9]: Fact=14: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[10]: Fact= 9: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[11]: Fact= 4: 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[12]: Fact=31: 13, 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[13]: Fact=26: 13, 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[14]: Fact=21: 13, 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[15]: Fact=16: 13, 6, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
--- 16x16, Mode=13 [F]---
[ 0]: Fact=23: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=14: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 2]: Fact= 5: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 3]: Fact=28: 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 4]: Fact=19: 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 5]: Fact=10: 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 6]: Fact= 1: 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 7]: Fact=24: 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 8]: Fact=15: 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 9]: Fact= 6: 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[10]: Fact=29: 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[11]: Fact=20: 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[12]: Fact=11: 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[13]: Fact= 2: 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[14]: Fact=25: 14, 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[15]: Fact=16: 14, 11, 7, 4, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
--- 16x16, Mode=14 [F]---
[ 0]: Fact=19: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact= 6: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 2]: Fact=25: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 3]: Fact=12: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 4]: Fact=31: 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 5]: Fact=18: 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 6]: Fact= 5: 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 7]: Fact=24: 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 8]: Fact=11: 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 9]: Fact=30: 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[10]: Fact=17: 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[11]: Fact= 4: 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[12]: Fact=23: 12, 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[13]: Fact=10: 12, 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[14]: Fact=29: 15, 12, 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[15]: Fact=16: 15, 12, 10, 7, 5, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
--- 16x16, Mode=15 [F]---
[ 0]: Fact=15: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=30: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 2]: Fact=13: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 3]: Fact=28: 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 4]: Fact=11: 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 5]: Fact=26: 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 6]: Fact= 9: 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 7]: Fact=24: 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 8]: Fact= 7: 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 9]: Fact=22: 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[10]: Fact= 5: 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[11]: Fact=20: 11, 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[12]: Fact= 3: 11, 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[13]: Fact=18: 13, 11, 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[14]: Fact= 1: 13, 11, 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[15]: Fact=16: 15, 13, 11, 9, 8, 6, 4, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, *
--- 16x16, Mode=16 [F]---
[ 0]: Fact=11: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=22: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 2]: Fact= 1: 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 3]: Fact=12: 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 4]: Fact=23: 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 5]: Fact= 2: 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 6]: Fact=13: 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 7]: Fact=24: 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 8]: Fact= 3: 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 9]: Fact=14: 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[10]: Fact=25: 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[11]: Fact= 4: 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[12]: Fact=15: 12, 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[13]: Fact=26: 14, 12, 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[14]: Fact= 5: 14, 12, 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[15]: Fact=16: 15, 14, 12, 11, 9, 8, 6, 5, 3, 2, 0, -1, -2, -3, -4, -5, -6, *
--- 16x16, Mode=17 [F]---
[ 0]: Fact= 6: 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15,-16, *
[ 1]: Fact=12: 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14,-15, *
[ 2]: Fact=18: 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 3]: Fact=24: 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 4]: Fact=30: 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 5]: Fact= 4: 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 6]: Fact=10: 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 7]: Fact=16: 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 8]: Fact=22: 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 9]: Fact=28: 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[10]: Fact= 2: 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[11]: Fact= 8: 11, 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, -7, *
[12]: Fact=14: 12, 11, 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, -6, *
[13]: Fact=20: 14, 12, 11, 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, -5, *
[14]: Fact=26: 15, 14, 12, 11, 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, -4, *
[15]: Fact= 0: 15, 14, 12, 11, 10, 9, 7, 6, 5, 4, 2, 1, 0, -1, -2, -3, *
--- 16x16, Mode=18 [F]---
[ 0]: Fact= 0: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 1]: Fact= 0: -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 2]: Fact= 0: -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 3]: Fact= 0: -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 4]: Fact= 0: -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 5]: Fact= 0: -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 6]: Fact= 0: -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 7]: Fact= 0: -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 8]: Fact= 0: -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 9]: Fact= 0: -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, 6, *
[10]: Fact= 0: -10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, 5, *
[11]: Fact= 0: -11,-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, 4, *
[12]: Fact= 0: -12,-11,-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, 3, *
[13]: Fact= 0: -13,-12,-11,-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, 2, *
[14]: Fact= 0: -14,-13,-12,-11,-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, 1, *
[15]: Fact= 0: -15,-14,-13,-12,-11,-10, -9, -8, -7, -6, -5, -4, -3, -2, -1, 0, *
--- 16x16, Mode=19 [F]---
[ 0]: Fact= 6: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=12: -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 2]: Fact=18: -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 3]: Fact=24: -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 4]: Fact=30: -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 5]: Fact= 4: -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 6]: Fact=10: -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 7]: Fact=16: -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 8]: Fact=22: -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 9]: Fact=28: -10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[10]: Fact= 2: -10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[11]: Fact= 8: -11,-10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, 7, *
[12]: Fact=14: -12,-11,-10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, 6, *
[13]: Fact=20: -14,-12,-11,-10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, 5, *
[14]: Fact=26: -15,-14,-12,-11,-10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, 4, *
[15]: Fact= 0: -15,-14,-12,-11,-10, -9, -7, -6, -5, -4, -2, -1, 0, 1, 2, 3, *
--- 16x16, Mode=20 [F]---
[ 0]: Fact=11: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=22: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 2]: Fact= 1: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 3]: Fact=12: -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 4]: Fact=23: -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 5]: Fact= 2: -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 6]: Fact=13: -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 7]: Fact=24: -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 8]: Fact= 3: -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 9]: Fact=14: -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[10]: Fact=25: -11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[11]: Fact= 4: -11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[12]: Fact=15: -12,-11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[13]: Fact=26: -14,-12,-11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[14]: Fact= 5: -14,-12,-11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[15]: Fact=16: -15,-14,-12,-11, -9, -8, -6, -5, -3, -2, 0, 1, 2, 3, 4, 5, 6, *
--- 16x16, Mode=21 [F]---
[ 0]: Fact=15: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=30: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 2]: Fact=13: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 3]: Fact=28: -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 4]: Fact=11: -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 5]: Fact=26: -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 6]: Fact= 9: -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 7]: Fact=24: -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 8]: Fact= 7: -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 9]: Fact=22: -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[10]: Fact= 5: -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[11]: Fact=20: -11, -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[12]: Fact= 3: -11, -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[13]: Fact=18: -13,-11, -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[14]: Fact= 1: -13,-11, -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[15]: Fact=16: -15,-13,-11, -9, -8, -6, -4, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, *
--- 16x16, Mode=22 [F]---
[ 0]: Fact=19: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact= 6: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 2]: Fact=25: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 3]: Fact=12: -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 4]: Fact=31: -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 5]: Fact=18: -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 6]: Fact= 5: -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 7]: Fact=24: -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 8]: Fact=11: -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 9]: Fact=30: -10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[10]: Fact=17: -10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[11]: Fact= 4: -10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[12]: Fact=23: -12,-10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[13]: Fact=10: -12,-10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[14]: Fact=29: -15,-12,-10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[15]: Fact=16: -15,-12,-10, -7, -5, -2, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, *
--- 16x16, Mode=23 [F]---
[ 0]: Fact=23: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=14: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 2]: Fact= 5: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 3]: Fact=28: -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 4]: Fact=19: -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 5]: Fact=10: -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 6]: Fact= 1: -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 7]: Fact=24: -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 8]: Fact=15: -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 9]: Fact= 6: -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[10]: Fact=29: -11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[11]: Fact=20: -11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[12]: Fact=11: -11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[13]: Fact= 2: -11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[14]: Fact=25: -14,-11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[15]: Fact=16: -14,-11, -7, -4, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, *
--- 16x16, Mode=24 [F]---
[ 0]: Fact=27: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=22: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 2]: Fact=17: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 3]: Fact=12: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 4]: Fact= 7: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 5]: Fact= 2: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 6]: Fact=29: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 7]: Fact=24: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 8]: Fact=19: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[ 9]: Fact=14: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[10]: Fact= 9: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[11]: Fact= 4: -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
[12]: Fact=31: -13, -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[13]: Fact=26: -13, -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[14]: Fact=21: -13, -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[15]: Fact=16: -13, -6, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, *
--- 16x16, Mode=25 [ ]---
[ 0]: Fact=30: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact=28: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 2]: Fact=26: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 3]: Fact=24: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 4]: Fact=22: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 5]: Fact=20: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 6]: Fact=18: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 7]: Fact=16: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 8]: Fact=14: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 9]: Fact=12: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[10]: Fact=10: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[11]: Fact= 8: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[12]: Fact= 6: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[13]: Fact= 4: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[14]: Fact= 2: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[15]: Fact= 0: 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, *
--- 16x16, Mode=26 [ ]---
[ 0]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 1]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 2]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 3]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 4]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 5]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 6]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 7]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 8]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[ 9]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[10]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[11]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[12]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[13]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[14]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
[15]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, *
--- 16x16, Mode=27 [ ]---
[ 0]: Fact= 2: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact= 4: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 2]: Fact= 6: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 3]: Fact= 8: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 4]: Fact=10: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 5]: Fact=12: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 6]: Fact=14: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 7]: Fact=16: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 8]: Fact=18: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 9]: Fact=20: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[10]: Fact=22: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[11]: Fact=24: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[12]: Fact=26: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[13]: Fact=28: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[14]: Fact=30: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[15]: Fact= 0: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
--- 16x16, Mode=28 [F]---
[ 0]: Fact= 5: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact=10: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 2]: Fact=15: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 3]: Fact=20: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 4]: Fact=25: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 5]: Fact=30: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 6]: Fact= 3: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 7]: Fact= 8: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 8]: Fact=13: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 9]: Fact=18: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[10]: Fact=23: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[11]: Fact=28: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[12]: Fact= 1: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[13]: Fact= 6: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[14]: Fact=11: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[15]: Fact=16: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
--- 16x16, Mode=29 [F]---
[ 0]: Fact= 9: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact=18: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 2]: Fact=27: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 3]: Fact= 4: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 4]: Fact=13: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 5]: Fact=22: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 6]: Fact=31: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 7]: Fact= 8: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 8]: Fact=17: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 9]: Fact=26: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[10]: Fact= 3: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[11]: Fact=12: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[12]: Fact=21: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[13]: Fact=30: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[14]: Fact= 7: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[15]: Fact=16: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
--- 16x16, Mode=30 [F]---
[ 0]: Fact=13: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact=26: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 2]: Fact= 7: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 3]: Fact=20: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 4]: Fact= 1: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 5]: Fact=14: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 6]: Fact=27: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 7]: Fact= 8: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 8]: Fact=21: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 9]: Fact= 2: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[10]: Fact=15: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[11]: Fact=28: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[12]: Fact= 9: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[13]: Fact=22: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[14]: Fact= 3: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[15]: Fact=16: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
--- 16x16, Mode=31 [F]---
[ 0]: Fact=17: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact= 2: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 2]: Fact=19: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 3]: Fact= 4: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 4]: Fact=21: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 5]: Fact= 6: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 6]: Fact=23: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 7]: Fact= 8: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 8]: Fact=25: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 9]: Fact=10: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[10]: Fact=27: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[11]: Fact=12: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[12]: Fact=29: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[13]: Fact=14: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[14]: Fact=31: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[15]: Fact=16: 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, *
--- 16x16, Mode=32 [F]---
[ 0]: Fact=21: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact=10: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 2]: Fact=31: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 3]: Fact=20: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 4]: Fact= 9: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 5]: Fact=30: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 6]: Fact=19: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 7]: Fact= 8: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[ 8]: Fact=29: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[ 9]: Fact=18: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[10]: Fact= 7: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[11]: Fact=28: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[12]: Fact=17: 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, *
[13]: Fact= 6: 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, *
[14]: Fact=27: 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, *
[15]: Fact=16: 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, *
--- 16x16, Mode=33 [F]---
[ 0]: Fact=26: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact=20: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 2]: Fact=14: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 3]: Fact= 8: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 4]: Fact= 2: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 5]: Fact=28: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 6]: Fact=22: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[ 7]: Fact=16: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[ 8]: Fact=10: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[ 9]: Fact= 4: 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, *
[10]: Fact=30: 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, *
[11]: Fact=24: 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, *
[12]: Fact=18: 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, *
[13]: Fact=12: 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, *
[14]: Fact= 6: 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, *
[15]: Fact= 0: 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, *
--- 16x16, Mode=34 [F]---
[ 0]: Fact= 0: 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, *
[ 1]: Fact= 0: 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, *
[ 2]: Fact= 0: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, *
[ 3]: Fact= 0: 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, *
[ 4]: Fact= 0: 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, *
[ 5]: Fact= 0: 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, *
[ 6]: Fact= 0: 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, *
[ 7]: Fact= 0: 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, *
[ 8]: Fact= 0: 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, *
[ 9]: Fact= 0: 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, *
[10]: Fact= 0: 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, *
[11]: Fact= 0: 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, *
[12]: Fact= 0: 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, *
[13]: Fact= 0: 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, *
[14]: Fact= 0: 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, *
[15]: Fact= 0: 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, *

1089
x265/doc/intra/intra-32x32.txt Normal file
View File

File diff suppressed because it is too large Load Diff

166
x265/doc/intra/intra-4x4.txt Normal file
View File

@ -0,0 +1,166 @@
--- 4x4, Mode= 2 --- [refPix]
[ 0]: Fact= 0: 10, 11, 12, 13 *
[ 1]: Fact= 0: 11, 12, 13, 14 *
[ 2]: Fact= 0: 12, 13, 14, 15 *
[ 3]: Fact= 0: 13, 14, 15, 16 *
--- 4x4, Mode= 3 ---
[ 0]: Fact=26: 9, 10, 11, 12, 13 *
[ 1]: Fact=20: 10, 11, 12, 13, 14 *
[ 2]: Fact=14: 11, 12, 13, 14, 15 *
[ 3]: Fact= 8: 12, 13, 14, 15, 16 *
--- 4x4, Mode= 4 ---
[ 0]: Fact=21: 9, 10, 11, 12, 13 *
[ 1]: Fact=10: 10, 11, 12, 13, 14 *
[ 2]: Fact=31: 10, 11, 12, 13, 14 *
[ 3]: Fact=20: 11, 12, 13, 14, 15 *
--- 4x4, Mode= 5 ---
[ 0]: Fact=17: 9, 10, 11, 12, 13 *
[ 1]: Fact= 2: 10, 11, 12, 13, 14 *
[ 2]: Fact=19: 10, 11, 12, 13, 14 *
[ 3]: Fact= 4: 11, 12, 13, 14, 15 *
--- 4x4, Mode= 6 ---
[ 0]: Fact=13: 9, 10, 11, 12, 13 *
[ 1]: Fact=26: 9, 10, 11, 12, 13 *
[ 2]: Fact= 7: 10, 11, 12, 13, 14 *
[ 3]: Fact=20: 10, 11, 12, 13, 14 *
--- 4x4, Mode= 7 ---
[ 0]: Fact= 9: 9, 10, 11, 12, 13 *
[ 1]: Fact=18: 9, 10, 11, 12, 13 *
[ 2]: Fact=27: 9, 10, 11, 12, 13 *
[ 3]: Fact= 4: 10, 11, 12, 13, 14 *
--- 4x4, Mode= 8 ---
[ 0]: Fact= 5: 9, 10, 11, 12, 13 *
[ 1]: Fact=10: 9, 10, 11, 12, 13 *
[ 2]: Fact=15: 9, 10, 11, 12, 13 *
[ 3]: Fact=20: 9, 10, 11, 12, 13 *
--- 4x4, Mode= 9 ---
[ 0]: Fact= 2: 9, 10, 11, 12, 13 *
[ 1]: Fact= 4: 9, 10, 11, 12, 13 *
[ 2]: Fact= 6: 9, 10, 11, 12, 13 *
[ 3]: Fact= 8: 9, 10, 11, 12, 13 *
--- 4x4, Mode=10 --- filtPix
[ 0]: Fact= 0: 9, 10, 11, 12 *
[ 1]: Fact= 0: 9, 10, 11, 12 *
[ 2]: Fact= 0: 9, 10, 11, 12 *
[ 3]: Fact= 0: 9, 10, 11, 12 *
--- 4x4, Mode=11 ---
[ 0]: Fact=30: 0, 9, 10, 11, 12 *
[ 1]: Fact=28: 0, 9, 10, 11, 12 *
[ 2]: Fact=26: 0, 9, 10, 11, 12 *
[ 3]: Fact=24: 0, 9, 10, 11, 12 *
--- 4x4, Mode=12 ---
[ 0]: Fact=27: 0, 9, 10, 11, 12 *
[ 1]: Fact=22: 0, 9, 10, 11, 12 *
[ 2]: Fact=17: 0, 9, 10, 11, 12 *
[ 3]: Fact=12: 0, 9, 10, 11, 12 *
--- 4x4, Mode=13 ---
[ 0]: Fact=23: 0, 9, 10, 11, 12 *
[ 1]: Fact=14: 0, 9, 10, 11, 12 *
[ 2]: Fact= 5: 0, 9, 10, 11, 12 *
[ 3]: Fact=28: 4, 0, 9, 10, 11 *
--- 4x4, Mode=14 ---
[ 0]: Fact=19: 0, 9, 10, 11, 12 *
[ 1]: Fact= 6: 0, 9, 10, 11, 12 *
[ 2]: Fact=25: 2, 0, 9, 10, 11 *
[ 3]: Fact=12: 2, 0, 9, 10, 11 *
--- 4x4, Mode=15 ---
[ 0]: Fact=15: 0, 9, 10, 11, 12 *
[ 1]: Fact=30: 2, 0, 9, 10, 11 *
[ 2]: Fact=13: 2, 0, 9, 10, 11 *
[ 3]: Fact=28: 4, 2, 0, 9, 10 *
--- 4x4, Mode=16 ---
[ 0]: Fact=11: 0, 9, 10, 11, 12 *
[ 1]: Fact=22: 2, 0, 9, 10, 11 *
[ 2]: Fact= 1: 2, 0, 9, 10, 11 *
[ 3]: Fact=12: 3, 2, 0, 9, 10 *
--- 4x4, Mode=17 ---
[ 0]: Fact= 6: 0, 9, 10, 11, 12 *
[ 1]: Fact=12: 1, 0, 9, 10, 11 *
[ 2]: Fact=18: 2, 1, 0, 9, 10 *
[ 3]: Fact=24: 4, 2, 1, 0, 9 *
--- 4x4, Mode=18 ---
[ 0]: Fact= 0: 0, 1, 2, 3 *
[ 1]: Fact= 0: 9, 0, 1, 2 *
[ 2]: Fact= 0: 10, 9, 0, 1 *
[ 3]: Fact= 0: 11, 10, 9, 0 *
--- 4x4, Mode=19 ---
[ 0]: Fact= 6: 0, 1, 2, 3, 4 *
[ 1]: Fact=12: 9, 0, 1, 2, 3 *
[ 2]: Fact=18: 10, 9, 0, 1, 2 *
[ 3]: Fact=24: 12, 10, 9, 0, 1 *
--- 4x4, Mode=20 ---
[ 0]: Fact=11: 0, 1, 2, 3, 4 *
[ 1]: Fact=22: 10, 0, 1, 2, 3 *
[ 2]: Fact= 1: 10, 0, 1, 2, 3 *
[ 3]: Fact=12: 11, 10, 0, 1, 2 *
--- 4x4, Mode=21 ---
[ 0]: Fact=15: 0, 1, 2, 3, 4 *
[ 1]: Fact=30: 10, 0, 1, 2, 3 *
[ 2]: Fact=13: 10, 0, 1, 2, 3 *
[ 3]: Fact=28: 12, 10, 0, 1, 2 *
--- 4x4, Mode=22 ---
[ 0]: Fact=19: 0, 1, 2, 3, 4 *
[ 1]: Fact= 6: 0, 1, 2, 3, 4 *
[ 2]: Fact=25: 10, 0, 1, 2, 3 *
[ 3]: Fact=12: 10, 0, 1, 2, 3 *
--- 4x4, Mode=23 ---
[ 0]: Fact=23: 0, 1, 2, 3, 4 *
[ 1]: Fact=14: 0, 1, 2, 3, 4 *
[ 2]: Fact= 5: 0, 1, 2, 3, 4 *
[ 3]: Fact=28: 12, 0, 1, 2, 3 *
--- 4x4, Mode=24 ---
[ 0]: Fact=27: 0, 1, 2, 3, 4 *
[ 1]: Fact=22: 0, 1, 2, 3, 4 *
[ 2]: Fact=17: 0, 1, 2, 3, 4 *
[ 3]: Fact=12: 0, 1, 2, 3, 4 *
--- 4x4, Mode=25 ---
[ 0]: Fact=30: 0, 1, 2, 3, 4 *
[ 1]: Fact=28: 0, 1, 2, 3, 4 *
[ 2]: Fact=26: 0, 1, 2, 3, 4 *
[ 3]: Fact=24: 0, 1, 2, 3, 4 *
--- 4x4, Mode=26 ---
[ 0]: Fact= 0: 1, 2, 3, 4, *
[ 1]: Fact= 0: 1, 2, 3, 4, *
[ 2]: Fact= 0: 1, 2, 3, 4, *
[ 3]: Fact= 0: 1, 2, 3, 4, *
--- 4x4, Mode=27 ---
[ 0]: Fact= 2: 1, 2, 3, 4, 5, *
[ 1]: Fact= 4: 1, 2, 3, 4, 5, *
[ 2]: Fact= 6: 1, 2, 3, 4, 5, *
[ 3]: Fact= 8: 1, 2, 3, 4, 5, *
--- 4x4, Mode=28 ---
[ 0]: Fact= 5: 1, 2, 3, 4, 5, *
[ 1]: Fact=10: 1, 2, 3, 4, 5, *
[ 2]: Fact=15: 1, 2, 3, 4, 5, *
[ 3]: Fact=20: 1, 2, 3, 4, 5, *
--- 4x4, Mode=29 ---
[ 0]: Fact= 9: 1, 2, 3, 4, 5, *
[ 1]: Fact=18: 1, 2, 3, 4, 5, *
[ 2]: Fact=27: 1, 2, 3, 4, 5, *
[ 3]: Fact= 4: 2, 3, 4, 5, 6, *
--- 4x4, Mode=30 ---
[ 0]: Fact=13: 1, 2, 3, 4, 5, *
[ 1]: Fact=26: 1, 2, 3, 4, 5, *
[ 2]: Fact= 7: 2, 3, 4, 5, 6, *
[ 3]: Fact=20: 2, 3, 4, 5, 6, *
--- 4x4, Mode=31 ---
[ 0]: Fact=17: 1, 2, 3, 4, 5, *
[ 1]: Fact= 2: 2, 3, 4, 5, 6, *
[ 2]: Fact=19: 2, 3, 4, 5, 6, *
[ 3]: Fact= 4: 3, 4, 5, 6, 7, *
--- 4x4, Mode=32 ---
[ 0]: Fact=21: 1, 2, 3, 4, 5, *
[ 1]: Fact=10: 2, 3, 4, 5, 6, *
[ 2]: Fact=31: 2, 3, 4, 5, 6, *
[ 3]: Fact=20: 3, 4, 5, 6, 7, *
--- 4x4, Mode=33 ---
[ 0]: Fact=26: 1, 2, 3, 4, 5, *
[ 1]: Fact=20: 2, 3, 4, 5, 6, *
[ 2]: Fact=14: 3, 4, 5, 6, 7, *
[ 3]: Fact= 8: 4, 5, 6, 7, 8, *
--- 4x4, Mode=34 ---
[ 0]: Fact= 0: 2, 3, 4, 5, *
[ 1]: Fact= 0: 3, 4, 5, 6, *
[ 2]: Fact= 0: 4, 5, 6, 7, *
[ 3]: Fact= 0: 5, 6, 7, 8, *

298
x265/doc/intra/intra-8x8.txt Normal file
View File

@ -0,0 +1,298 @@
--- 8x8, Mode= 2 ---
[ 0]: Fact= 0: -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact= 0: -3, -4, -5, -6, -7, -8, -9,-10, *
[ 2]: Fact= 0: -4, -5, -6, -7, -8, -9,-10,-11, *
[ 3]: Fact= 0: -5, -6, -7, -8, -9,-10,-11,-12, *
[ 4]: Fact= 0: -6, -7, -8, -9,-10,-11,-12,-13, *
[ 5]: Fact= 0: -7, -8, -9,-10,-11,-12,-13,-14, *
[ 6]: Fact= 0: -8, -9,-10,-11,-12,-13,-14,-15, *
[ 7]: Fact= 0: -9,-10,-11,-12,-13,-14,-15,-16, *
--- 8x8, Mode= 3 ---
[ 0]: Fact=26: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact=20: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 2]: Fact=14: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 3]: Fact= 8: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 4]: Fact= 2: -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 5]: Fact=28: -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 6]: Fact=22: -6, -7, -8, -9,-10,-11,-12,-13,-14, *
[ 7]: Fact=16: -7, -8, -9,-10,-11,-12,-13,-14,-15, *
--- 8x8, Mode= 4 ---
[ 0]: Fact=21: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact=10: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 2]: Fact=31: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 3]: Fact=20: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 4]: Fact= 9: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 5]: Fact=30: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 6]: Fact=19: -5, -6, -7, -8, -9,-10,-11,-12,-13, *
[ 7]: Fact= 8: -6, -7, -8, -9,-10,-11,-12,-13,-14, *
--- 8x8, Mode= 5 ---
[ 0]: Fact=17: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact= 2: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 2]: Fact=19: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 3]: Fact= 4: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 4]: Fact=21: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 5]: Fact= 6: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 6]: Fact=23: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
[ 7]: Fact= 8: -5, -6, -7, -8, -9,-10,-11,-12,-13, *
--- 8x8, Mode= 6 ---
[ 0]: Fact=13: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact=26: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 2]: Fact= 7: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 3]: Fact=20: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 4]: Fact= 1: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 5]: Fact=14: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 6]: Fact=27: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
[ 7]: Fact= 8: -4, -5, -6, -7, -8, -9,-10,-11,-12, *
--- 8x8, Mode= 7 ---
[ 0]: Fact= 9: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact=18: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 2]: Fact=27: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 3]: Fact= 4: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 4]: Fact=13: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 5]: Fact=22: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 6]: Fact=31: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 7]: Fact= 8: -3, -4, -5, -6, -7, -8, -9,-10,-11, *
--- 8x8, Mode= 8 ---
[ 0]: Fact= 5: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact=10: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 2]: Fact=15: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 3]: Fact=20: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 4]: Fact=25: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 5]: Fact=30: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 6]: Fact= 3: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
[ 7]: Fact= 8: -2, -3, -4, -5, -6, -7, -8, -9,-10, *
--- 8x8, Mode= 9 ---
[ 0]: Fact= 2: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 1]: Fact= 4: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 2]: Fact= 6: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 3]: Fact= 8: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 4]: Fact=10: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 5]: Fact=12: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 6]: Fact=14: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
[ 7]: Fact=16: -1, -2, -3, -4, -5, -6, -7, -8, -9, *
--- 8x8, Mode=10 ---
[ 0]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 2]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 3]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 4]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 5]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 6]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
[ 7]: Fact= 0: -1, -2, -3, -4, -5, -6, -7, -8, *
--- 8x8, Mode=11 ---
[ 0]: Fact=30: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact=28: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 2]: Fact=26: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 3]: Fact=24: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 4]: Fact=22: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 5]: Fact=20: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 6]: Fact=18: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 7]: Fact=16: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
--- 8x8, Mode=12 ---
[ 0]: Fact=27: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact=22: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 2]: Fact=17: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 3]: Fact=12: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 4]: Fact= 7: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 5]: Fact= 2: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 6]: Fact=29: 6, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 7]: Fact=24: 6, 0, -1, -2, -3, -4, -5, -6, -7, *
--- 8x8, Mode=13 ---
[ 0]: Fact=23: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact=14: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 2]: Fact= 5: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 3]: Fact=28: 4, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 4]: Fact=19: 4, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 5]: Fact=10: 4, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 6]: Fact= 1: 4, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 7]: Fact=24: 7, 4, 0, -1, -2, -3, -4, -5, -6, *
--- 8x8, Mode=14 ---
[ 0]: Fact=19: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact= 6: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 2]: Fact=25: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 3]: Fact=12: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 4]: Fact=31: 5, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 5]: Fact=18: 5, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 6]: Fact= 5: 5, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 7]: Fact=24: 7, 5, 2, 0, -1, -2, -3, -4, -5, *
--- 8x8, Mode=15 ---
[ 0]: Fact=15: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact=30: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 2]: Fact=13: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 3]: Fact=28: 4, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 4]: Fact=11: 4, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 5]: Fact=26: 6, 4, 2, 0, -1, -2, -3, -4, -5, *
[ 6]: Fact= 9: 6, 4, 2, 0, -1, -2, -3, -4, -5, *
[ 7]: Fact=24: 8, 6, 4, 2, 0, -1, -2, -3, -4, *
--- 8x8, Mode=16 ---
[ 0]: Fact=11: 0, -1, -2, -3, -4, -5, -6, -7, -8, *
[ 1]: Fact=22: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 2]: Fact= 1: 2, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 3]: Fact=12: 3, 2, 0, -1, -2, -3, -4, -5, -6, *
[ 4]: Fact=23: 5, 3, 2, 0, -1, -2, -3, -4, -5, *
[ 5]: Fact= 2: 5, 3, 2, 0, -1, -2, -3, -4, -5, *
[ 6]: Fact=13: 6, 5, 3, 2, 0, -1, -2, -3, -4, *
[ 7]: Fact=24: 8, 6, 5, 3, 2, 0, -1, -2, -3, *
--- 8x8, Mode=17 ---
[ 0]: Fact= 6: 0, -1, -2, -3, -4, -5, -6, -7, -8, x
[ 1]: Fact=12: 1, 0, -1, -2, -3, -4, -5, -6, -7, *
[ 2]: Fact=18: 2, 1, 0, -1, -2, -3, -4, -5, -6, *
[ 3]: Fact=24: 4, 2, 1, 0, -1, -2, -3, -4, -5, *
[ 4]: Fact=30: 5, 4, 2, 1, 0, -1, -2, -3, -4, *
[ 5]: Fact= 4: 5, 4, 2, 1, 0, -1, -2, -3, -4, *
[ 6]: Fact=10: 6, 5, 4, 2, 1, 0, -1, -2, -3, *
[ 7]: Fact=16: 7, 6, 5, 4, 2, 1, 0, -1, -2, *
--- 8x8, Mode=18 ---
[ 0]: Fact= 0: 0, 1, 2, 3, 4, 5, 6, 7, *
[ 1]: Fact= 0: -1, 0, 1, 2, 3, 4, 5, 6, *
[ 2]: Fact= 0: -2, -1, 0, 1, 2, 3, 4, 5, *
[ 3]: Fact= 0: -3, -2, -1, 0, 1, 2, 3, 4, *
[ 4]: Fact= 0: -4, -3, -2, -1, 0, 1, 2, 3, *
[ 5]: Fact= 0: -5, -4, -3, -2, -1, 0, 1, 2, *
[ 6]: Fact= 0: -6, -5, -4, -3, -2, -1, 0, 1, *
[ 7]: Fact= 0: -7, -6, -5, -4, -3, -2, -1, 0, *
--- 8x8, Mode=19 ---
[ 0]: Fact= 6: 0, 1, 2, 3, 4, 5, 6, 7, 8, x
[ 1]: Fact=12: -1, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 2]: Fact=18: -2, -1, 0, 1, 2, 3, 4, 5, 6, *
[ 3]: Fact=24: -4, -2, -1, 0, 1, 2, 3, 4, 5, *
[ 4]: Fact=30: -5, -4, -2, -1, 0, 1, 2, 3, 4, *
[ 5]: Fact= 4: -5, -4, -2, -1, 0, 1, 2, 3, 4, *
[ 6]: Fact=10: -6, -5, -4, -2, -1, 0, 1, 2, 3, *
[ 7]: Fact=16: -7, -6, -5, -4, -2, -1, 0, 1, 2, *
--- 8x8, Mode=20 ---
[ 0]: Fact=11: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact=22: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 2]: Fact= 1: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 3]: Fact=12: -3, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 4]: Fact=23: -5, -3, -2, 0, 1, 2, 3, 4, 5, *
[ 5]: Fact= 2: -5, -3, -2, 0, 1, 2, 3, 4, 5, *
[ 6]: Fact=13: -6, -5, -3, -2, 0, 1, 2, 3, 4, *
[ 7]: Fact=24: -8, -6, -5, -3, -2, 0, 1, 2, 3, *
--- 8x8, Mode=21 ---
[ 0]: Fact=15: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact=30: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 2]: Fact=13: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 3]: Fact=28: -4, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 4]: Fact=11: -4, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 5]: Fact=26: -6, -4, -2, 0, 1, 2, 3, 4, 5, *
[ 6]: Fact= 9: -6, -4, -2, 0, 1, 2, 3, 4, 5, *
[ 7]: Fact=24: -8, -6, -4, -2, 0, 1, 2, 3, 4, *
--- 8x8, Mode=22 ---
[ 0]: Fact=19: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact= 6: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 2]: Fact=25: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 3]: Fact=12: -2, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 4]: Fact=31: -5, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 5]: Fact=18: -5, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 6]: Fact= 5: -5, -2, 0, 1, 2, 3, 4, 5, 6, *
[ 7]: Fact=24: -7, -5, -2, 0, 1, 2, 3, 4, 5, *
--- 8x8, Mode=23 ---
[ 0]: Fact=23: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact=14: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 2]: Fact= 5: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 3]: Fact=28: -4, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 4]: Fact=19: -4, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 5]: Fact=10: -4, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 6]: Fact= 1: -4, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 7]: Fact=24: -7, -4, 0, 1, 2, 3, 4, 5, 6, *
--- 8x8, Mode=24 ---
[ 0]: Fact=27: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact=22: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 2]: Fact=17: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 3]: Fact=12: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 4]: Fact= 7: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 5]: Fact= 2: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 6]: Fact=29: -6, 0, 1, 2, 3, 4, 5, 6, 7, *
[ 7]: Fact=24: -6, 0, 1, 2, 3, 4, 5, 6, 7, *
--- 8x8, Mode=25 ---
[ 0]: Fact=30: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact=28: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 2]: Fact=26: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 3]: Fact=24: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 4]: Fact=22: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 5]: Fact=20: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 6]: Fact=18: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
[ 7]: Fact=16: 0, 1, 2, 3, 4, 5, 6, 7, 8, *
--- 8x8, Mode=26 ---
[ 0]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 1]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 2]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 3]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 4]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 5]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 6]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
[ 7]: Fact= 0: 1, 2, 3, 4, 5, 6, 7, 8, *
--- 8x8, Mode=27 ---
[ 0]: Fact= 2: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact= 4: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 2]: Fact= 6: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 3]: Fact= 8: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 4]: Fact=10: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 5]: Fact=12: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 6]: Fact=14: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 7]: Fact=16: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
--- 8x8, Mode=28 ---
[ 0]: Fact= 5: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact=10: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 2]: Fact=15: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 3]: Fact=20: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 4]: Fact=25: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 5]: Fact=30: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 6]: Fact= 3: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 7]: Fact= 8: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
--- 8x8, Mode=29 ---
[ 0]: Fact= 9: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact=18: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 2]: Fact=27: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 3]: Fact= 4: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 4]: Fact=13: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 5]: Fact=22: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 6]: Fact=31: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 7]: Fact= 8: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
--- 8x8, Mode=30 ---
[ 0]: Fact=13: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact=26: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 2]: Fact= 7: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 3]: Fact=20: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 4]: Fact= 1: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 5]: Fact=14: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 6]: Fact=27: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 7]: Fact= 8: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
--- 8x8, Mode=31 ---
[ 0]: Fact=17: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact= 2: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 2]: Fact=19: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 3]: Fact= 4: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 4]: Fact=21: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 5]: Fact= 6: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 6]: Fact=23: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 7]: Fact= 8: 5, 6, 7, 8, 9, 10, 11, 12, 13, *
--- 8x8, Mode=32 ---
[ 0]: Fact=21: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact=10: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 2]: Fact=31: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 3]: Fact=20: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 4]: Fact= 9: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 5]: Fact=30: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 6]: Fact=19: 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 7]: Fact= 8: 6, 7, 8, 9, 10, 11, 12, 13, 14, *
--- 8x8, Mode=33 ---
[ 0]: Fact=26: 1, 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact=20: 2, 3, 4, 5, 6, 7, 8, 9, 10, *
[ 2]: Fact=14: 3, 4, 5, 6, 7, 8, 9, 10, 11, *
[ 3]: Fact= 8: 4, 5, 6, 7, 8, 9, 10, 11, 12, *
[ 4]: Fact= 2: 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 5]: Fact=28: 5, 6, 7, 8, 9, 10, 11, 12, 13, *
[ 6]: Fact=22: 6, 7, 8, 9, 10, 11, 12, 13, 14, *
[ 7]: Fact=16: 7, 8, 9, 10, 11, 12, 13, 14, 15, *
--- 8x8, Mode=34 ---
[ 0]: Fact= 0: 2, 3, 4, 5, 6, 7, 8, 9, *
[ 1]: Fact= 0: 3, 4, 5, 6, 7, 8, 9, 10, *
[ 2]: Fact= 0: 4, 5, 6, 7, 8, 9, 10, 11, *
[ 3]: Fact= 0: 5, 6, 7, 8, 9, 10, 11, 12, *
[ 4]: Fact= 0: 6, 7, 8, 9, 10, 11, 12, 13, *
[ 5]: Fact= 0: 7, 8, 9, 10, 11, 12, 13, 14, *
[ 6]: Fact= 0: 8, 9, 10, 11, 12, 13, 14, 15, *
[ 7]: Fact= 0: 9, 10, 11, 12, 13, 14, 15, 16, *

109
x265/doc/reST/Makefile Normal file
View File

@ -0,0 +1,109 @@
# Makefile for (Sphinx based) restructured text documentation
#
# You can set these variables from the command line.
SPHINXOPTS =
SPHINXBUILD = sphinx-build
PAPER =
QCOLLECTIONGENERATOR = qcollectiongenerator
# Internal variables.
PAPEROPT_a4 = -D latex_paper_size=a4
PAPEROPT_letter = -D latex_paper_size=letter
ALLSPHINXOPTS = -d build/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) .
.PHONY: help clean distclean html web pickle htmlhelp qthelp qhc latex changes linkcheck
help:
@echo "Please use \`make <target>' where <target> is one of"
@echo " html to make standalone HTML files"
@echo " pickle to make pickle files"
@echo " json to make JSON files"
@echo " htmlhelp to make HTML files and a HTML help project"
@echo " qthelp to make HTML files and a qthelp project"
@echo " qhc to make QHC file"
@echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
@echo " man to make manpages"
@echo " changes to make an overview over all changed/added/deprecated items"
@echo " linkcheck to check all external links for integrity"
clean:
-rm -rf build/*
distclean: clean
-rmdir build/
html:
mkdir -p build/html build/doctrees
$(SPHINXBUILD) -b html $(ALLSPHINXOPTS) build/html
@echo
@echo "Build finished. The HTML pages are in build/html."
zip: html
(cd build ; zip TortoiseHg.html.zip -r html)
pickle:
mkdir -p build/pickle build/doctrees
$(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) build/pickle
@echo
@echo "Build finished; now you can process the pickle files."
web: pickle
json:
mkdir -p build/json build/doctrees
$(SPHINXBUILD) -b json $(ALLSPHINXOPTS) build/json
@echo
@echo "Build finished; now you can process the JSON files."
htmlhelp:
mkdir -p build/htmlhelp build/doctrees
$(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) build/htmlhelp
@echo
@echo "Build finished; now you can run HTML Help Workshop with the" \
".hhp project file in build/htmlhelp."
qthelp:
mkdir -p build/qthelp build/doctrees
$(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) build/qthelp
@echo
@echo "Build finished; now you can run "qcollectiongenerator" with the" \
".qhcp project file in build/qthelp, like this:"
@echo "# qcollectiongenerator build/qthelp/foo.qhcp"
@echo "To view the help file:"
@echo "# assistant -collectionFile build/qthelp/foo.qhc"
qhc: qthelp
$(QCOLLECTIONGENERATOR) build/qthelp/TortoiseHg.qhcp
@echo "Build finished. To view the help file:"
@echo "# assistant -collectionFile build/qthelp/TortoiseHg.qhc"
latex:
mkdir -p build/latex build/doctrees
$(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) build/latex
@echo
@echo "Build finished; the LaTeX files are in build/latex."
@echo "Run \`make all-pdf' or \`make all-ps' in that directory to" \
"run these through (pdf)latex."
man:
mkdir -p build/man build/doctrees
$(SPHINXBUILD) -b man $(ALLSPHINXOPTS) build/man
@echo
@echo "Build finished; the manpages are in build/man."
@echo "Run \`man -l build/man/x265.1' or \`man -l build/man/libx265.3'" \
"to view them."
changes:
mkdir -p build/changes build/doctrees
$(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) build/changes
@echo
@echo "The overview file is in build/changes."
linkcheck:
mkdir -p build/linkcheck build/doctrees
$(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) build/linkcheck
@echo
@echo "Link check complete; look for any errors in the above output " \
"or in build/linkcheck/output.txt."

511
x265/doc/reST/api.rst Normal file
View File

@ -0,0 +1,511 @@
*********************************
Application Programming Interface
*********************************
Introduction
============
x265 is written primarily in C++ and x86 assembly language but the
public facing programming interface is C for the widest possible
portability. This C interface is wholly defined within :file:`x265.h`
in the source/ folder of our source tree. All of the functions and
variables and enumerations meant to be used by the end-user are present
in this header.
Where possible, x265 has tried to keep its public API as close as
possible to x264's public API. So those familiar with using x264 through
its C interface will find x265 quite familiar.
This file is meant to be read in-order; the narrative follows linearly
through the various sections
Build Considerations
====================
The choice of Main or Main10 profile encodes is made at compile time;
the internal pixel depth influences a great deal of variable sizes and
thus 8 and 10bit pixels are handled as different build options
(primarily to maintain the performance of the 8bit builds). libx265
exports a variable **x265_max_bit_depth** which indicates how the
library was compiled (it will contain a value of 8 or 10). Further,
**x265_version_str** is a pointer to a string indicating the version of
x265 which was compiled, and **x265_build_info_str** is a pointer to a
string identifying the compiler and build options.
.. Note::
**x265_version_str** is only updated when **cmake** runs. If you are
making binaries for others to use, it is recommended to run
**cmake** prior to **make** in your build scripts.
x265 will accept input pixels of any depth between 8 and 16 bits
regardless of the depth of its internal pixels (8 or 10). It will shift
and mask input pixels as required to reach the internal depth. If
downshifting is being performed using our CLI application (to 8 bits),
the :option:`--dither` option may be enabled to reduce banding. This
feature is not available through the C interface.
Encoder
=======
The primary object in x265 is the encoder object, and this is
represented in the public API as an opaque typedef **x265_encoder**.
Pointers of this type are passed to most encoder functions.
A single encoder generates a single output bitstream from a sequence of
raw input pictures. Thus if you need multiple output bitstreams you
must allocate multiple encoders. You may pass the same input pictures
to multiple encoders, the encode function does not modify the input
picture structures (the pictures are copied into the encoder as the
first step of encode).
Encoder allocation is a reentrant function, so multiple encoders may be
safely allocated in a single process. The encoder access functions are
not reentrant for a single encoder, so the recommended use case is to
allocate one client thread per encoder instance (one thread for all
encoder instances is possible, but some encoder access functions are
blocking and thus this would be less efficient).
.. Note::
There is one caveat to having multiple encoders within a single
process. All of the encoders must use the same maximum CTU size
because many global variables are configured based on this size.
Encoder allocation will fail if a mis-matched CTU size is attempted.
If no encoders are open, **x265_cleanup()** can be called to reset
the configured CTU size so a new size can be used.
An encoder is allocated by calling **x265_encoder_open()**::
/* x265_encoder_open:
* create a new encoder handler, all parameters from x265_param are copied */
x265_encoder* x265_encoder_open(x265_param *);
The returned pointer is then passed to all of the functions pertaining
to this encode. A large amount of memory is allocated during this
function call, but the encoder will continue to allocate memory as the
first pictures are passed to the encoder; until its pool of picture
structures is large enough to handle all of the pictures it must keep
internally. The pool size is determined by the lookahead depth, the
number of frame threads, and the maximum number of references.
As indicated in the comment, **x265_param** is copied internally so the user
may release their copy after allocating the encoder. Changes made to
their copy of the param structure have no affect on the encoder after it
has been allocated.
Param
=====
The **x265_param** structure describes everything the encoder needs to
know about the input pictures and the output bitstream and most
everything in between.
The recommended way to handle these param structures is to allocate them
from libx265 via::
/* x265_param_alloc:
* Allocates an x265_param instance. The returned param structure is not
* special in any way, but using this method together with x265_param_free()
* and x265_param_parse() to set values by name allows the application to treat
* x265_param as an opaque data struct for version safety */
x265_param *x265_param_alloc();
In this way, your application does not need to know the exact size of
the param structure (the build of x265 could potentially be a bit newer
than the copy of :file:`x265.h` that your application compiled against).
Next you perform the initial *rough cut* configuration of the encoder by
chosing a performance preset and optional tune factor
**x265_preset_names** and **x265_tune_names** respectively hold the
string names of the presets and tune factors (see :ref:`presets
<preset-tune-ref>` for more detail on presets and tune factors)::
/* returns 0 on success, negative on failure (e.g. invalid preset/tune name). */
int x265_param_default_preset(x265_param *, const char *preset, const char *tune);
Now you may optionally specify a profile. **x265_profile_names**
contains the string names this function accepts::
/* (can be NULL, in which case the function will do nothing)
* returns 0 on success, negative on failure (e.g. invalid profile name). */
int x265_param_apply_profile(x265_param *, const char *profile);
Finally you configure any remaining options by name using repeated calls to::
/* x265_param_parse:
* set one parameter by name.
* returns 0 on success, or returns one of the following errors.
* note: BAD_VALUE occurs only if it can't even parse the value,
* numerical range is not checked until x265_encoder_open().
* value=NULL means "true" for boolean options, but is a BAD_VALUE for non-booleans. */
#define X265_PARAM_BAD_NAME (-1)
#define X265_PARAM_BAD_VALUE (-2)
int x265_param_parse(x265_param *p, const char *name, const char *value);
See :ref:`string options <string-options-ref>` for the list of options (and their
descriptions) which can be set by **x265_param_parse()**.
After the encoder has been created, you may release the param structure::
/* x265_param_free:
* Use x265_param_free() to release storage for an x265_param instance
* allocated by x265_param_alloc() */
void x265_param_free(x265_param *);
.. Note::
Using these methods to allocate and release the param structures
helps future-proof your code in many ways, but the x265 API is
versioned in such a way that we prevent linkage against a build of
x265 that does not match the version of the header you are compiling
against (unless you use x265_api_query() to acquire the library's
interfaces). This is function of the X265_BUILD macro.
**x265_encoder_parameters()** may be used to get a copy of the param
structure from the encoder after it has been opened, in order to see the
changes made to the parameters for auto-detection and other reasons::
/* x265_encoder_parameters:
* copies the current internal set of parameters to the pointer provided
* by the caller. useful when the calling application needs to know
* how x265_encoder_open has changed the parameters.
* note that the data accessible through pointers in the returned param struct
* (e.g. filenames) should not be modified by the calling application. */
void x265_encoder_parameters(x265_encoder *, x265_param *);
**x265_encoder_reconfig()** may be used to reconfigure encoder parameters mid-encode::
/* x265_encoder_reconfig:
* used to modify encoder parameters.
* various parameters from x265_param are copied.
* this takes effect immediately, on whichever frame is encoded next;
* returns 0 on success, negative on parameter validation error.
*
* not all parameters can be changed; see the actual function for a
* detailed breakdown. since not all parameters can be changed, moving
* from preset to preset may not always fully copy all relevant parameters,
* but should still work usably in practice. however, more so than for
* other presets, many of the speed shortcuts used in ultrafast cannot be
* switched out of; using reconfig to switch between ultrafast and other
* presets is not recommended without a more fine-grained breakdown of
* parameters to take this into account. */
int x265_encoder_reconfig(x265_encoder *, x265_param *);
Pictures
========
Raw pictures are passed to the encoder via the **x265_picture** structure.
Just like the param structure we recommend you allocate this structure
from the encoder to avoid potential size mismatches::
/* x265_picture_alloc:
* Allocates an x265_picture instance. The returned picture structure is not
* special in any way, but using this method together with x265_picture_free()
* and x265_picture_init() allows some version safety. New picture fields will
* always be added to the end of x265_picture */
x265_picture *x265_picture_alloc();
Regardless of whether you allocate your picture structure this way or
whether you simply declare it on the stack, your next step is to
initialize the structure via::
/***
* Initialize an x265_picture structure to default values. It sets the pixel
* depth and color space to the encoder's internal values and sets the slice
* type to auto - so the lookahead will determine slice type.
*/
void x265_picture_init(x265_param *param, x265_picture *pic);
x265 does not perform any color space conversions, so the raw picture's
color space (chroma sampling) must match the color space specified in
the param structure used to allocate the encoder. **x265_picture_init**
initializes this field to the internal color space and it is best to
leave it unmodified.
The picture bit depth is initialized to be the encoder's internal bit
depth but this value should be changed to the actual depth of the pixels
being passed into the encoder. If the picture bit depth is more than 8,
the encoder assumes two bytes are used to represent each sample
(little-endian shorts).
The user is responsible for setting the plane pointers and plane strides
(in units of bytes, not pixels). The presentation time stamp (**pts**)
is optional, depending on whether you need accurate decode time stamps
(**dts**) on output.
If you wish to override the lookahead or rate control for a given
picture you may specify a slicetype other than X265_TYPE_AUTO, or a
forceQP value other than 0.
x265 does not modify the picture structure provided as input, so you may
reuse a single **x265_picture** for all pictures passed to a single
encoder, or even all pictures passed to multiple encoders.
Structures allocated from the library should eventually be released::
/* x265_picture_free:
* Use x265_picture_free() to release storage for an x265_picture instance
* allocated by x265_picture_alloc() */
void x265_picture_free(x265_picture *);
Analysis Buffers
================
Analysis information can be saved and reused to between encodes of the
same video sequence (generally for multiple bitrate encodes). The best
results are attained by saving the analysis information of the highest
bitrate encode and reuse it in lower bitrate encodes.
When saving or loading analysis data, buffers must be allocated for
every picture passed into the encoder using::
/* x265_alloc_analysis_data:
* Allocate memory to hold analysis meta data, returns 1 on success else 0 */
int x265_alloc_analysis_data(x265_picture*);
Note that this is very different from the typical semantics of
**x265_picture**, which can be reused many times. The analysis buffers must
be re-allocated for every input picture.
Analysis buffers passed to the encoder are owned by the encoder until
they pass the buffers back via an output **x265_picture**. The user is
responsible for releasing the buffers when they are finished with them
via::
/* x265_free_analysis_data:
* Use x265_free_analysis_data to release storage of members allocated by
* x265_alloc_analysis_data */
void x265_free_analysis_data(x265_picture*);
Encode Process
==============
The output of the encoder is a series of NAL packets, which are always
returned concatenated in consecutive memory. HEVC streams have SPS and
PPS and VPS headers which describe how the following packets are to be
decoded. If you specified :option:`--repeat-headers` then those headers
will be output with every keyframe. Otherwise you must explicitly query
those headers using::
/* x265_encoder_headers:
* return the SPS and PPS that will be used for the whole stream.
* *pi_nal is the number of NAL units outputted in pp_nal.
* returns negative on error, total byte size of payload data on success
* the payloads of all output NALs are guaranteed to be sequential in memory. */
int x265_encoder_headers(x265_encoder *, x265_nal **pp_nal, uint32_t *pi_nal);
Now we get to the main encode loop. Raw input pictures are passed to the
encoder in display order via::
/* x265_encoder_encode:
* encode one picture.
* *pi_nal is the number of NAL units outputted in pp_nal.
* returns negative on error, zero if no NAL units returned.
* the payloads of all output NALs are guaranteed to be sequential in memory. */
int x265_encoder_encode(x265_encoder *encoder, x265_nal **pp_nal, uint32_t *pi_nal, x265_picture *pic_in, x265_picture *pic_out);
These pictures are queued up until the lookahead is full, and then the
frame encoders in turn are filled, and then finally you begin receiving
a output NALs (corresponding to a single output picture) with each input
picture you pass into the encoder.
Once the pipeline is completely full, **x265_encoder_encode()** will
block until the next output picture is complete.
.. note::
Optionally, if the pointer of a second **x265_picture** structure is
provided, the encoder will fill it with data pertaining to the
output picture corresponding to the output NALs, including the
recontructed image, POC and decode timestamp. These pictures will be
in encode (or decode) order.
When the last of the raw input pictures has been sent to the encoder,
**x265_encoder_encode()** must still be called repeatedly with a
*pic_in* argument of 0, indicating a pipeline flush, until the function
returns a value less than or equal to 0 (indicating the output bitstream
is complete).
At any time during this process, the application may query running
statistics from the encoder::
/* x265_encoder_get_stats:
* returns encoder statistics */
void x265_encoder_get_stats(x265_encoder *encoder, x265_stats *, uint32_t statsSizeBytes);
Cleanup
=======
Finally, the encoder must be closed in order to free all of its
resources. An encoder that has been flushed cannot be restarted and
reused. Once **x265_encoder_close()** has been called, the encoder
handle must be discarded::
/* x265_encoder_close:
* close an encoder handler */
void x265_encoder_close(x265_encoder *);
When the application has completed all encodes, it should call
**x265_cleanup()** to free process global, particularly if a memory-leak
detection tool is being used. **x265_cleanup()** also resets the saved
CTU size so it will be possible to create a new encoder with a different
CTU size::
/* x265_cleanup:
* release library static allocations, reset configured CTU size */
void x265_cleanup(void);
Multi-library Interface
=======================
If your application might want to make a runtime bit-depth selection, it
will need to use one of these bit-depth introspection interfaces which
returns an API structure containing the public function entry points and
constants.
Instead of directly using all of the **x265_** methods documented above,
you query an x265_api structure from your libx265 and then use the
function pointers of the same name (minus the **x265_** prefix) within
that structure. For instance **x265_param_default()** becomes
**api->param_default()**.
x265_api_get
------------
The first bit-depth instrospecton method is x265_api_get(). It designed
for applications that might statically link with libx265, or will at
least be tied to a particular SONAME or API version::
/* x265_api_get:
* Retrieve the programming interface for a linked x265 library.
* May return NULL if no library is available that supports the
* requested bit depth. If bitDepth is 0, the function is guarunteed
* to return a non-NULL x265_api pointer from the system default
* libx265 */
const x265_api* x265_api_get(int bitDepth);
Like **x265_encoder_encode()**, this function has the build number
automatically appended to the function name via macros. This ties your
application to a particular binary API version of libx265 (the one you
compile against). If you attempt to link with a libx265 with a different
API version number, the link will fail.
Obviously this has no meaningful effect on applications which statically
link to libx265.
x265_api_query
--------------
The second bit-depth introspection method is designed for applications
which need more flexibility in API versioning. If you use
**x265_api_query()** and dynamically link to libx265 at runtime (using
dlopen() on POSIX or LoadLibrary() on Windows) your application is no
longer directly tied to the API version that it was compiled against::
/* x265_api_query:
* Retrieve the programming interface for a linked x265 library, like
* x265_api_get(), except this function accepts X265_BUILD as the second
* argument rather than using the build number as part of the function name.
* Applications which dynamically link to libx265 can use this interface to
* query the library API and achieve a relative amount of version skew
* flexibility. The function may return NULL if the library determines that
* the apiVersion that your application was compiled against is not compatible
* with the library you have linked with.
*
* api_major_version will be incremented any time non-backward compatible
* changes are made to any public structures or functions. If
* api_major_version does not match X265_MAJOR_VERSION from the x265.h your
* application compiled against, your application must not use the returned
* x265_api pointer.
*
* Users of this API *must* also validate the sizes of any structures which
* are not treated as opaque in application code. For instance, if your
* application dereferences a x265_param pointer, then it must check that
* api->sizeof_param matches the sizeof(x265_param) that your application
* compiled with. */
const x265_api* x265_api_query(int bitDepth, int apiVersion, int* err);
A number of validations must be performed on the returned API structure
in order to determine if it is safe for use by your application. If you
do not perform these checks, your application is liable to crash::
if (api->api_major_version != X265_MAJOR_VERSION) /* do not use */
if (api->sizeof_param != sizeof(x265_param)) /* do not use */
if (api->sizeof_picture != sizeof(x265_picture)) /* do not use */
if (api->sizeof_stats != sizeof(x265_stats)) /* do not use */
if (api->sizeof_zone != sizeof(x265_zone)) /* do not use */
etc.
Note that if your application does not directly allocate or dereference
one of these structures, if it treats the structure as opaque or does
not use it at all, then it can skip the size check for that structure.
In particular, if your application uses api->param_alloc(),
api->param_free(), api->param_parse(), etc and never directly accesses
any x265_param fields, then it can skip the check on the
sizeof(x265_parm) and thereby ignore changes to that structure (which
account for a large percentage of X265_BUILD bumps).
Build Implications
------------------
By default libx265 will place all of its internal C++ classes and
functions within an x265 namespace and export all of the C functions
documented in this file. Obviously this prevents 8bit and 10bit builds
of libx265 from being statically linked into a single binary, all of
those symbols would collide.
However, if you set the EXPORT_C_API cmake option to OFF then libx265
will use a bit-depth specific namespace and prefix for its assembly
functions (x265_8bit, x265_10bit or x265_12bit) and export no C
functions.
In this way you can build one or more libx265 libraries without any
exported C interface and link them into a libx265 build that does export
a C interface. The build which exported the C functions becomes the
*default* bit depth for the combined library, and the other bit depths
are available via the bit-depth introspection methods.
.. Note::
When setting EXPORT_C_API cmake option to OFF, it is recommended to
also set ENABLE_SHARED and ENABLE_CLI to OFF to prevent build
problems. We only need the static library from these builds.
If an application requests a bit-depth that is not supported by the
default library or any of the additionally linked libraries, the
introspection method will fall-back to an attempt to dynamically bind a
shared library with a name appropriate for the requested bit-depth::
8-bit: libx265_main
10-bit: libx265_main10
12-bit: libx265_main12
If the profile-named library is not found, it will then try to bind a
generic libx265 in the hopes that it is a multilib library with all bit
depths.
Packaging and Distribution
--------------------------
We recommend that packagers distribute a single combined shared/static
library build which includes all the bit depth libraries linked
together. See the multilib scripts in our :file:`build/` subdirectories
for examples of how to affect these combined library builds. It is the
packager's discretion which bit-depth exports the public C functions and
thus becomes the default bit-depth for the combined library.
.. Note::
Windows packagers might want to build libx265 with WINXP_SUPPORT
enabled. This makes the resulting binaries functional on XP and
Vista. Without this flag, the minimum supported host O/S is Windows
7. Also note that binaries built with WINXP_SUPPORT will *not* have
NUMA support and they will have slightly less performance.
STATIC_LINK_CRT is also recommended so end-users will not need to
install any additional MSVC C runtime libraries.

1770
x265/doc/reST/cli.rst Normal file
View File

File diff suppressed because it is too large Load Diff

26
x265/doc/reST/conf.py Normal file
View File

@ -0,0 +1,26 @@
# -*- coding: utf-8 -*-
#
# -- General configuration -----------------------------------------------------
source_suffix = '.rst'
# Name of the master file
master_doc = 'index'
# General information about the project.
project = u'x265'
# This is the Copyright Information that will appear on the bottom of the document
copyright = u'2014 MulticoreWare Inc'
# -- Options for HTML output ---------------------------------------------------
html_theme = "default"
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
('index', 'libx265', 'Full x265 Documentation',
['MulticoreWare Inc'], 3),
('x265', 'x265', 'x265 CLI Documentation',
['MulticoreWare Inc'], 1)
]

11
x265/doc/reST/index.rst Normal file
View File

@ -0,0 +1,11 @@
x265 Documentation
======================
.. toctree::
:maxdepth: 2
introduction
cli
api
threading
presets
lossless

82
x265/doc/reST/introduction.rst Normal file
View File

@ -0,0 +1,82 @@
************
Introduction
************
Increasing demand for high definition and ultra-high definition video,
along with an increasing desire for video on demand has led to
exponential growth in demand for bandwidth and storage requirements.
These challenges can be met by the new High Efficiency Video Coding
(HEVC) standard, also known as H.265. The x265 HEVC encoder project was
launched by MulticoreWare in 2013, aiming to provide the most efficient,
highest performance HEVC video encoder.
About HEVC
==========
The High Efficiency Video Coding (HEVC) was developed by the ISO/IEC
Moving Picture Experts Group (MPEG) and ITU-T Video Coding Experts Group
(VCEG), through their Joint Collaborative Team on Video Coding (JCT-VC).
HEVC is also known as ISO/IEC 23008-2 MPEG-H Part 2 and ITU-T H.265.
HEVC provides superior video quality and up to twice the data
compression as the previous standard (H.264/MPEG-4 AVC). HEVC can
support 8K Ultra High Definition video, with a picture size up to
8192x4320 pixels.
About x265
==========
The primary objective of x265 is to become the best H.265/HEVC encoder
available anywhere, offering the highest compression efficiency and the
highest performance on a wide variety of hardware platforms. The x265
encoder is available as an open source library, published under the
GPLv2 license. It is also available under a commercial license, enabling
commercial companies to utilize and distribute x265 in their solutions
without being subject to the restrictions of the GPL license.
x265 is developed by `MulticoreWare <http://www.multicorewareinc.com>`_,
leaders in high performance software solutions, with backing from
leading video technology providers including `Telestream
<http://www.telestream.com>`_ and `Doremi Labs
<http://www.doremilabs.com>`_ (and other companies who want to remain
anonymous at this time), and with contributions from open source
developers. x265 leverages many of the outstanding video encoding
features and optimizations from the x264 AVC encoder project.
The x265 software is available for free under the GNU GPL 2 license,
from https://bitbucket.org/multicoreware/x265. For commercial companies
that wish to distribute x265 without being subject to the open source
requirements of the GPL 2 license, commercial licenses are available
with competitive terms. Contact license @ x265.com to inquire about
commercial license terms.
While x265 is primarily designed as a video encoder software library, a
command-line executable is provided to facilitate testing and
development. We expect x265 to be utilized in many leading video
hardware and software products and services in the coming months.
LEGAL NOTICES
=============
The x265 software is owned and copyrighted by MulticoreWare, Inc.
MulticoreWare is committed to offering the x265 software under the GNU
GPL v2 license. Companies who do not wish to integrate the x265
Software in their products under the terms of the GPL license can
contact MulticoreWare (license @ x265.com) to obtain a commercial
license agreement. Companies who use x265 under the GPL may also wish
to work with MulticoreWare to accelerate the development of specific
features or optimized support for specific hardware or software
platforms, or to contract for support.
The GNU GPL v2 license or the x265 commercial license agreement govern
your rights to access the copyrighted x265 software source code, but do
not cover any patents that may be applicable to the function of binary
executable software created from the x265 source code. You are
responsible for understanding the laws in your country, and for
licensing all applicable patent rights needed for use or distribution of
software applications created from the x265 source code. A good place
to start is with the `Motion Picture Experts Group - Licensing Authority
- HEVC Licensing Program <http://www.mpegla.com/main/PID/HEVC/default.aspx>`_.
x265 is a registered trademark of MulticoreWare, Inc. The x265 logo is
a trademark of MulticoreWare, and may only be used with explicit written
permission. All rights reserved.

162
x265/doc/reST/lossless.rst Normal file
View File

@ -0,0 +1,162 @@
Lossless
--------
Lossless Encoding
=================
x265 can encode HEVC bitstreams that are entirely lossless (the
reconstructed images are bit-exact to the source images) by using the
:option:`--lossless` option. Lossless operation is theoretically
simple. Rate control, by definition, is disabled and the encoder
disables all quality metrics since they would only waste CPU cycles.
Instead, x265 reports only a compression factor at the end of the
encode.
In HEVC, lossless coding means bypassing both the DCT transforms and
bypassing quantization (often referred to as transquant bypass). Normal
predictions are still allowed, so the encoder will find optimal inter or
intra predictions and then losslessly code the residual (with transquant
bypass).
All :option:`--preset` options are capable of generating lossless video
streams, but in general the slower the preset the better the compression
ratio (and the slower the encode). Here are some examples::
./x265 ../test-720p.y4m o.bin --preset ultrafast --lossless
... <snip> ...
encoded 721 frames in 238.38s (3.02 fps), 57457.94 kb/s
./x265 ../test-720p.y4m o.bin --preset faster --lossless
... <snip> ...
x265 [info]: lossless compression ratio 3.11::1
encoded 721 frames in 258.46s (2.79 fps), 56787.65 kb/s
./x265 ../test-720p.y4m o.bin --preset slow --lossless
... <snip> ...
x265 [info]: lossless compression ratio 3.36::1
encoded 721 frames in 576.73s (1.25 fps), 52668.25 kb/s
./x265 ../test-720p.y4m o.bin --preset veryslow --lossless
x265 [info]: lossless compression ratio 3.76::1
encoded 721 frames in 6298.22s (0.11 fps), 47008.65 kb/s
.. Note::
In HEVC, only QP=4 is truly lossless quantization, and thus when
encoding losslesly x265 uses QP=4 internally in its RDO decisions.
Near-lossless Encoding
======================
Near-lossless conditions are a quite a bit more interesting. Normal ABR
rate control will allow one to scale the bitrate up to the point where
quantization is entirely bypassed (QP <= 4), but even at this point
there is a lot of SSIM left on the table because of the DCT transforms,
which are not lossless::
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 40000 --ssim
encoded 721 frames in 326.62s (2.21 fps), 39750.56 kb/s, SSIM Mean Y: 0.9990703 (30.317 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 50000 --ssim
encoded 721 frames in 349.27s (2.06 fps), 44326.84 kb/s, SSIM Mean Y: 0.9994134 (32.316 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 60000 --ssim
encoded 721 frames in 360.04s (2.00 fps), 45394.50 kb/s, SSIM Mean Y: 0.9994823 (32.859 dB)
For the encoder to get over this quality plateau, one must enable
lossless coding at the CU level with :option:`--cu-lossless`. It tells
the encoder to evaluate trans-quant bypass as a coding option for each
CU, and to pick the option with the best rate-distortion
characteristics.
The :option:`--cu-lossless` option is very expensive, computationally,
and it only has a positive effect when the QP is extremely low, allowing
RDO to spend a large amount of bits to make small improvements to
quality. So this option should only be enabled when you are encoding
near-lossless bitstreams::
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 40000 --ssim --cu-lossless
encoded 721 frames in 500.51s (1.44 fps), 40017.10 kb/s, SSIM Mean Y: 0.9997790 (36.557 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 50000 --ssim --cu-lossless
encoded 721 frames in 524.60s (1.37 fps), 46083.37 kb/s, SSIM Mean Y: 0.9999432 (42.456 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 60000 --ssim --cu-lossless
encoded 721 frames in 523.63s (1.38 fps), 46552.92 kb/s, SSIM Mean Y: 0.9999489 (42.917 dB)
.. Note::
It is not unusual for bitrate to drop as you increase lossless coding.
Having "perfectly coded" reference blocks reduces residual in later
frames. It is quite possible for a near-lossless encode to spend
more bits than a lossless encode.
Enabling psycho-visual rate distortion will improve lossless coding.
:option:`--psy-rd` influences the RDO decisions in favor of energy
(detail) preservation over bit cost and results in more blocks being
losslessly coded. Our psy-rd feature is not yet assembly optimized, so
this makes the encodes run even slower::
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 40000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 581.83s (1.24 fps), 40112.15 kb/s, SSIM Mean Y: 0.9998632 (38.638 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 50000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 587.54s (1.23 fps), 46284.55 kb/s, SSIM Mean Y: 0.9999663 (44.721 dB)
./x265 ../test-720p.y4m o.bin --preset medium --bitrate 60000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 592.93s (1.22 fps), 46839.51 kb/s, SSIM Mean Y: 0.9999707 (45.334 dB)
:option:`--cu-lossless` will also be more effective at slower
presets which perform RDO at more levels and thus may find smaller
blocks that would benefit from lossless coding::
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 40000 --ssim --cu-lossless
encoded 721 frames in 12969.25s (0.06 fps), 37331.96 kb/s, SSIM Mean Y: 0.9998108 (37.231 dB)
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 50000 --ssim --cu-lossless
encoded 721 frames in 46217.84s (0.05 fps), 42976.28 kb/s, SSIM Mean Y: 0.9999482 (42.856 dB)
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 60000 --ssim --cu-lossless
encoded 721 frames in 13738.17s (0.05 fps), 43864.21 kb/s, SSIM Mean Y: 0.9999633 (44.348 dB)
And with psy-rd and a slow preset together, very high SSIMs are
possible::
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 40000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 11675.81s (0.06 fps), 37819.45 kb/s, SSIM Mean Y: 0.9999181 (40.867 dB)
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 50000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 12414.56s (0.06 fps), 42815.75 kb/s, SSIM Mean Y: 0.9999758 (46.168 dB)
./x265 ../test-720p.y4m o.bin --preset veryslow --bitrate 60000 --ssim --cu-lossless --psy-rd 1.0
encoded 721 frames in 11684.89s (0.06 fps), 43324.48 kb/s, SSIM Mean Y: 0.9999793 (46.835 dB)
It's important to note in the end that it is easier (less work) for the
encoder to encode the video losslessly than it is to encode it
near-losslessly. If the encoder knows up front the encode must be
lossless, it does not need to evaluate any lossy coding methods. The
encoder only needs to find the most efficient prediction for each block
and then entropy code the residual.
It is not feasible for :option:`--cu-lossless` to turn itself on when
the encoder determines it is encoding a near-lossless bitstream (ie:
when rate control nearly disables all quantization) because the feature
requires a flag to be enabled in the stream headers. At the time the
stream headers are being coded we do not know whether
:option:`--cu-lossless` would be a help or a hinder. If very few or no
blocks end up being coded as lossless, then having the feature enabled
is a net loss in compression efficiency because it adds a flag that must
be coded for every CU. So ignoring even the performance aspects of the
feature, it can be a compression loss if enabled without being used. So
it is up to the user to only enable this feature when they are coding at
near-lossless quality.
Transform Skip
==============
A somewhat related feature, :option:`--tskip` tells the encoder to
evaluate transform-skip (bypass DCT but with quantization still enabled)
when coding small 4x4 transform blocks. This feature is intended to
improve the coding efficiency of screen content (aka: text on a screen)
and is not really intended for lossless coding. This feature should
only be enabled if the content has a lot of very sharp edges in it, and
is mostly unrelated to lossless coding.

182
x265/doc/reST/presets.rst Normal file
View File

@ -0,0 +1,182 @@
Preset Options
--------------
.. _presets:
Presets
=======
x265 has a number of predefined :option:`--preset` options that make
trade-offs between encode speed (encoded frames per second) and
compression efficiency (quality per bit in the bitstream). The default
preset is medium, it does a reasonably good job of finding the best
possible quality without spending enormous CPU cycles looking for the
absolute most efficient way to achieve that quality. As you go higher
than medium, the encoder takes shortcuts to improve performance at the
expense of quality and compression efficiency. As you go lower than
medium, the encoder tries harder and harder to achieve the best quailty
per bit compression ratio.
The presets adjust encoder parameters to affect these trade-offs.
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| | ultrafast | superfast | veryfast | faster | fast | medium | slow | slower | veryslow | placebo |
+==============+===========+===========+==========+========+======+========+======+========+==========+=========+
| ctu | 32 | 32 | 32 | 64 | 64 | 64 | 64 | 64 | 64 | 64 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| min-cu-size | 16 | 8 | 8 | 8 | 8 | 8 | 8 | 8 | 8 | 8 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| bframes | 3 | 3 | 4 | 4 | 4 | 4 | 4 | 8 | 8 | 8 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| b-adapt | 0 | 0 | 0 | 0 | 0 | 2 | 2 | 2 | 2 | 2 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| rc-lookahead | 5 | 10 | 15 | 15 | 15 | 20 | 25 | 30 | 40 | 60 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| scenecut | 0 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 | 40 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| refs | 1 | 1 | 1 | 1 | 2 | 3 | 3 | 3 | 5 | 5 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| me | dia | hex | hex | hex | hex | hex | star | star | star | star |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| merange | 57 | 57 | 57 | 57 | 57 | 57 | 57 | 57 | 57 | 92 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| subme | 0 | 1 | 1 | 2 | 2 | 2 | 3 | 3 | 4 | 5 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| rect | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| amp | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| max-merge | 2 | 2 | 2 | 2 | 2 | 2 | 3 | 3 | 4 | 5 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| early-skip | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 | 0 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| fast-intra | 1 | 1 | 1 | 1 | 1 | 0 | 0 | 0 | 0 | 0 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| b-intra | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| sao | 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| signhide | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| weightp | 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| weightb | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| aq-mode | 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| cuTree | 0 | 0 | 0 | 0 | 1 | 1 | 1 | 1 | 1 | 1 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| rdLevel | 2 | 2 | 2 | 2 | 2 | 3 | 4 | 6 | 6 | 6 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| rdoq-level | 0 | 0 | 0 | 0 | 0 | 0 | 2 | 2 | 2 | 2 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| tu-intra | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 3 | 4 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
| tu-inter | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 2 | 3 | 4 |
+--------------+-----------+-----------+----------+--------+------+--------+------+--------+----------+---------+
Placebo mode enables transform-skip prediction evaluation.
.. _tunings:
Tuning
======
There are a few :option:`--tune` options available, which are applied
after the preset.
.. Note::
The *psnr* and *ssim* tune options disable all optimizations that
sacrafice metric scores for perceived visual quality (also known as
psycho-visual optimizations). By default x265 always tunes for
highest perceived visual quality but if one intends to measure an
encode using PSNR or SSIM for the purpose of benchmarking, we highly
recommend you configure x265 to tune for that particular metric.
+--------------+-----------------------------------------------------+
| --tune | effect |
+==============+=====================================================+
| psnr | disables adaptive quant, psy-rd, and cutree |
+--------------+-----------------------------------------------------+
| ssim | enables adaptive quant auto-mode, disables psy-rd |
+--------------+-----------------------------------------------------+
| grain | improves retention of film grain. more below |
+--------------+-----------------------------------------------------+
| fastdecode | no loop filters, no weighted pred, no intra in B |
+--------------+-----------------------------------------------------+
| zerolatency | no lookahead, no B frames, no cutree |
+--------------+-----------------------------------------------------+
Film Grain Retention
~~~~~~~~~~~~~~~~~~~~
:option:`--tune` *grain* tries to improve the retention of film grain in
the reconstructed output. It disables rate distortion optimizations in
quantization, and increases the default psy-rd.
* :option:`--psy-rd` 0.5
* :option:`--rdoq-level` 0
* :option:`--psy-rdoq` 0
It lowers the strength of adaptive quantization, so residual energy can
be more evenly distributed across the (noisy) picture:
* :option:`--aq-strength` 0.3
And it similarly tunes rate control to prevent the slice QP from
swinging too wildly from frame to frame:
* :option:`--ipratio` 1.1
* :option:`--pbratio` 1.1
* :option:`--qcomp` 0.8
And lastly it reduces the strength of deblocking to prevent grain being
blurred on block boundaries:
* :option:`--deblock` -2
Fast Decode
~~~~~~~~~~~
:option:`--tune` *fastdecode* disables encoder features which tend to be
bottlenecks for the decoder. It is intended for use with 4K content at
high bitrates which can cause decoders to struggle. It disables both
HEVC loop filters, which tend to be process bottlenecks:
* :option:`--no-deblock`
* :option:`--no-sao`
It disables weighted prediction, which tend to be bandwidth bottlenecks:
* :option:`--no-weightp`
* :option:`--no-weightb`
And it disables intra blocks in B frames with :option:`--no-b-intra`
since intra predicted blocks cause serial dependencies in the decoder.
Zero Latency
~~~~~~~~~~~~
There are two halves to the latency problem. There is latency at the
decoder and latency at the encoder. :option:`--tune` *zerolatency*
removes latency from both sides. The decoder latency is removed by:
* :option:`--bframes` 0
Encoder latency is removed by:
* :option:`--b-adapt` 0
* :option:`--rc-lookahead` 0
* :option:`--no-scenecut`
* :option:`--no-cutree`
* :option:`--frame-threads` 1
With all of these settings x265_encoder_encode() will run synchronously,
the picture passed as pic_in will be encoded and returned as NALs. These
settings disable frame parallelism, which is an important component for
x265 performance. If you can tolerate any latency on the encoder, you
can increase performance by increasing the number of frame threads. Each
additional frame thread adds one frame of latency.

266
x265/doc/reST/threading.rst Normal file
View File

@ -0,0 +1,266 @@
*********
Threading
*********
.. _pools:
Thread Pools
============
x265 creates one or more thread pools per encoder, one pool per NUMA
node (typically a CPU socket). :option:`--pools` specifies the number of
pools and the number of threads per pool the encoder will allocate. By
default x265 allocates one thread per (hyperthreaded) CPU core on each
NUMA node.
If you are running multiple encoders on a system with multiple NUMA
nodes, it is recommended to isolate each of them to a single node in
order to avoid the NUMA overhead of remote memory access.
Work distribution is job based. Idle worker threads scan the job
providers assigned to their thread pool for jobs to perform. When no
jobs are available, the idle worker threads block and consume no CPU
cycles.
Objects which desire to distribute work to worker threads are known as
job providers (and they derive from the JobProvider class). The thread
pool has a method to **poke** awake a blocked idle thread, and job
providers are recommended to call this method when they make new jobs
available.
Worker jobs are not allowed to block except when absolutely necessary
for data locking. If a job becomes blocked, the work function is
expected to drop that job so the worker thread may go back to the pool
and find more work.
On Windows, the native APIs offer sufficient functionality to discover
the NUMA topology and enforce the thread affinity that libx265 needs (so
long as you have not chosen to target XP or Vista), but on POSIX systems
it relies on libnuma for this functionality. If your target POSIX system
is single socket, then building without libnuma is a perfectly
reasonable option, as it will have no effect on the runtime behavior. On
a multiple-socket system, a POSIX build of libx265 without libnuma will
be less work efficient, but will still function correctly. You lose the
work isolation effect that keeps each frame encoder from only using the
threads of a single socket and so you incur a heavier context switching
cost.
Wavefront Parallel Processing
=============================
New with HEVC, Wavefront Parallel Processing allows each row of CTUs to
be encoded in parallel, so long as each row stays at least two CTUs
behind the row above it, to ensure the intra references and other data
of the blocks above and above-right are available. WPP has almost no
effect on the analysis and compression of each CTU and so it has a very
small impact on compression efficiency relative to slices or tiles. The
compression loss from WPP has been found to be less than 1% in most of
our tests.
WPP has three effects which can impact efficiency. The first is the row
starts must be signaled in the slice header, the second is each row must
be padded to an even byte in length, and the third is the state of the
entropy coder is transferred from the second CTU of each row to the
first CTU of the row below it. In some conditions this transfer of
state actually improves compression since the above-right state may have
better locality than the end of the previous row.
Parabola Research have published an excellent HEVC
`animation <http://www.parabolaresearch.com/blog/2013-12-01-hevc-wavefront-animation.html>`_
which visualizes WPP very well. It even correctly visualizes some of
WPPs key drawbacks, such as:
1. the low thread utilization at the start and end of each frame
2. a difficult block may stall the wave-front and it takes a while for
the wave-front to recover.
3. 64x64 CTUs are big! there are much fewer rows than with H.264 and
similar codecs
Because of these stall issues you rarely get the full parallelisation
benefit one would expect from row threading. 30% to 50% of the
theoretical perfect threading is typical.
In x265 WPP is enabled by default since it not only improves performance
at encode but it also makes it possible for the decoder to be threaded.
If WPP is disabled by :option:`--no-wpp` the frame will be encoded in
scan order and the entropy overheads will be avoided. If frame
threading is not disabled, the encoder will change the default frame
thread count to be higher than if WPP was enabled. The exact formulas
are described in the next section.
Bonded Task Groups
==================
If a worker thread job has work which can be performed in parallel by
many threads, it may allocate a bonded task group and enlist the help of
other idle worker threads from the same thread pool. Those threads will
cooperate to complete the work of the bonded task group and then return
to their idle states. The larger and more uniform those tasks are, the
better the bonded task group will perform.
Parallel Mode Analysis
~~~~~~~~~~~~~~~~~~~~~~
When :option:`--pmode` is enabled, each CU (at all depths from 64x64 to
8x8) will distribute its analysis work to the thread pool via a bonded
task group. Each analysis job will measure the cost of one prediction
for the CU: merge, skip, intra, inter (2Nx2N, Nx2N, 2NxN, and AMP).
At slower presets, the amount of increased parallelism from pmode is
often enough to be able to reduce or disable frame parallelism while
achieving the same overall CPU utilization. Reducing frame threads is
often beneficial to ABR and VBV rate control.
Parallel Motion Estimation
~~~~~~~~~~~~~~~~~~~~~~~~~~
When :option:`--pme` is enabled all of the analysis functions which
perform motion searches to reference frames will distribute those motion
searches to other worker threads via a bonded task group (if more than
two motion searches are required).
Frame Threading
===============
Frame threading is the act of encoding multiple frames at the same time.
It is a challenge because each frame will generally use one or more of
the previously encoded frames as motion references and those frames may
still be in the process of being encoded themselves.
Previous encoders such as x264 worked around this problem by limiting
the motion search region within these reference frames to just one
macroblock row below the coincident row being encoded. Thus a frame
could be encoded at the same time as its reference frames so long as it
stayed one row behind the encode progress of its references (glossing
over a few details).
x265 has the same frame threading mechanism, but we generally have much
less frame parallelism to exploit than x264 because of the size of our
CTU rows. For instance, with 1080p video x264 has 68 16x16 macroblock
rows available each frame while x265 only has 17 64x64 CTU rows.
The second extenuating circumstance is the loop filters. The pixels used
for motion reference must be processed by the loop filters and the loop
filters cannot run until a full row has been encoded, and it must run a
full row behind the encode process so that the pixels below the row
being filtered are available. On top of this, HEVC has two loop filters:
deblocking and SAO, which must be run in series with a row lag between
them. When you add up all the row lags each frame ends up being 3 CTU
rows behind its reference frames (the equivalent of 12 macroblock rows
for x264). And keep in mind the wave-front progression pattern; by the
time the reference frame finishes the third row of CTUs, nearly half of
the CTUs in the frame may be compressed (depending on the display aspect
ratio).
The third extenuating circumstance is that when a frame being encoded
becomes blocked by a reference frame row being available, that frame's
wave-front becomes completely stalled and when the row becomes available
again it can take quite some time for the wave to be restarted, if it
ever does. This makes WPP less effective when frame parallelism is in
use.
:option:`--merange` can have a negative impact on frame parallelism. If
the range is too large, more rows of CTU lag must be added to ensure
those pixels are available in the reference frames.
.. note::
Even though the merange is used to determine the amount of reference
pixels that must be available in the reference frames, the actual
motion search is not necessarily centered around the coincident
block. The motion search is actually centered around the motion
predictor, but the available pixel area (mvmin, mvmax) is determined
by merange and the interpolation filter half-heights.
When frame threading is disabled, the entirety of all reference frames
are always fully available (by definition) and thus the available pixel
area is not restricted at all, and this can sometimes improve
compression efficiency. Because of this, the output of encodes with
frame parallelism disabled will not match the output of encodes with
frame parallelism enabled; but when enabled the number of frame threads
should have no effect on the output bitstream except when using ABR or
VBV rate control or noise reduction.
When :option:`--nr` is enabled, the outputs of each number of frame threads
will be deterministic but none of them will match becaue each frame
encoder maintains a cumulative noise reduction state.
VBV introduces non-determinism in the encoder, at this point in time,
regardless of the amount of frame parallelism.
By default frame parallelism and WPP are enabled together. The number of
frame threads used is auto-detected from the (hyperthreaded) CPU core
count, but may be manually specified via :option:`--frame-threads`
+-------+--------+
| Cores | Frames |
+=======+========+
| > 32 | 6..8 |
+-------+--------+
| >= 16 | 5 |
+-------+--------+
| >= 8 | 3 |
+-------+--------+
| >= 4 | 2 |
+-------+--------+
If WPP is disabled, then the frame thread count defaults to **min(cpuCount, ctuRows / 2)**
Over-allocating frame threads can be very counter-productive. They
each allocate a large amount of memory and because of the limited number
of CTU rows and the reference lag, you generally get limited benefit
from adding frame encoders beyond the auto-detected count, and often
the extra frame encoders reduce performance.
Given these considerations, you can understand why the faster presets
lower the max CTU size to 32x32 (making twice as many CTU rows available
for WPP and for finer grained frame parallelism) and reduce
:option:`--merange`
Each frame encoder runs in its own thread (allocated separately from the
worker pool). This frame thread has some pre-processing responsibilities
and some post-processing responsibilities for each frame, but it spends
the bulk of its time managing the wave-front processing by making CTU
rows available to the worker threads when their dependencies are
resolved. The frame encoder threads spend nearly all of their time
blocked in one of 4 possible locations:
1. blocked, waiting for a frame to process
2. blocked on a reference frame, waiting for a CTU row of reconstructed
and loop-filtered reference pixels to become available
3. blocked waiting for wave-front completion
4. blocked waiting for the main thread to consume an encoded frame
Lookahead
=========
The lookahead module of x265 (the lowres pre-encode which determines
scene cuts and slice types) uses the thread pool to distribute the
lowres cost analysis to worker threads. It will use bonded task groups
to perform batches of frame cost estimates, and it may optionally use
bonded task groups to measure single frame cost estimates using slices.
(see :option:`--lookahead-slices`)
The main slicetypeDecide() function itself is also performed by a worker
thread if your encoder has a thread pool, else it runs within the
context of the thread which calls the x265_encoder_encode().
SAO
===
The Sample Adaptive Offset loopfilter has a large effect on encode
performance because of the peculiar way it must be analyzed and coded.
SAO flags and data are encoded at the CTU level before the CTU itself is
coded, but SAO analysis (deciding whether to enable SAO and with what
parameters) cannot be performed until that CTU is completely analyzed
(reconstructed pixels are available) as well as the CTUs to the right
and below. So in effect the encoder must perform SAO analysis in a
wavefront at least a full row behind the CTU compression wavefront.
This extra latency forces the encoder to save the encode data of every
CTU until the entire frame has been analyzed, at which point a function
can code the final slice bitstream with the decided SAO flags and data
interleaved between each CTU. This second pass over the CTUs can be
expensive, particularly at large resolutions and high bitrates.

49
x265/doc/reST/x265.rst Normal file
View File

@ -0,0 +1,49 @@
x265 CLI Documentation
######################
SYNOPSIS
========
**x265** [options] infile [-o] outfile
Bit depth: 8
**x265-10bit** [options] infile [-o] outfile
Bit depth: 10
infile can be YUV or Y4M
outfile is raw HEVC bitstream
DESCRIPTION
===========
.. toctree::
:maxdepth: 2
introduction
OPTIONS
=======
.. toctree::
:maxdepth: 2
cli
presets
lossless
SEE ALSO
========
**libx265**\(3)
Online documentation: http://x265.readthedocs.org/en/default/cli.html

232
x265/doc/uncrustify/codingstyle.cfg Normal file
View File

@ -0,0 +1,232 @@
align_func_params=true
align_keep_tabs=false
align_left_shift=true
align_mix_var_proto=false
align_nl_cont=false
align_number_left=false
align_oc_decl_colon=false
align_on_operator=false
align_on_tabstop=false
align_right_cmt_mix=false
align_single_line_brace=false
align_single_line_func=false
align_var_def_attribute=false
align_var_def_colon=false
align_var_def_inline=false
align_with_tabs=false
cmt_c_group=true
cmt_c_nl_end=false
cmt_c_nl_start=true
cmt_cpp_group=true
cmt_cpp_nl_end=false
cmt_cpp_nl_start=false
cmt_cpp_to_c=false
cmt_indent_multi=false
cmt_insert_before_preproc=false
cmt_multi_check_last=true
cmt_reflow_mode=1
cmt_sp_before_star_cont=0
cmt_star_cont=true
cmt_width=130
#code_width=130
eat_blanks_after_open_brace=true
eat_blanks_before_close_brace=true
indent_access_spec_body=false
indent_align_assign=false
indent_align_string=false
indent_bool_paren=false
indent_brace_parent=false
indent_braces=false
indent_braces_no_class=false
indent_braces_no_func=false
indent_braces_no_struct=false
indent_class=true
indent_class_colon=false
indent_cmt_with_tabs=false
indent_col1_comment=false
indent_columns=4
indent_comma_paren=false
indent_else_if=false
indent_extern=false
indent_first_bool_expr=false
indent_func_call_param=false
indent_func_class_param=false
indent_func_ctor_var_param=false
indent_func_def_param=false
indent_func_param_double=false
indent_func_proto_param=false
indent_namespace=false
indent_paren_nl=false
indent_preserve_sql=false
indent_relative_single_line_comments=false
indent_square_nl=false
indent_template_param=false
indent_var_def_cont=false
indent_with_tabs=0
input_tab_size=2
ls_for_split_full=true
ls_func_split_full=true
mod_add_long_ifdef_else_comment=10
mod_add_long_ifdef_endif_comment=10
mod_full_brace_do=add
mod_full_brace_for=add
mod_full_brace_if=ignore
mod_full_brace_if_chain=false
mod_full_brace_while=add
mod_full_paren_if_bool=false
mod_move_case_break=false
mod_paren_on_return=remove
mod_pawn_semicolon=false
mod_remove_empty_return=true
mod_remove_extra_semicolon=true
mod_sort_import=false
mod_sort_include=false
mod_sort_using=false
newlines=lf
nl_after_access_spec=2
#nl_after_brace_close=ignore
#nl_after_brace_open=ignore
nl_after_brace_open_cmt=true
nl_after_case=false
nl_after_class=2
nl_after_for=add
nl_after_func_body=2
nl_after_func_body_one_liner=2
nl_after_if=ignore
nl_after_multiline_comment=true
nl_after_return=false
nl_after_semicolon=true
nl_after_struct=2
nl_after_switch=add
nl_after_vbrace_close=false
nl_after_vbrace_open=false
nl_after_vbrace_open_empty=false
nl_after_while=add
nl_assign_brace=add
nl_assign_leave_one_liners=true
nl_before_access_spec=2
nl_before_block_comment=2
nl_before_case=false
nl_brace_else=add
nl_brace_while=add
nl_case_colon_brace=add
nl_class_brace=add
nl_class_init_args=ignore
nl_class_leave_one_liners=true
nl_collapse_empty_body=false
nl_create_for_one_liner=false
nl_create_if_one_liner=false
nl_create_while_one_liner=false
nl_define_macro=false
nl_do_brace=add
nl_ds_struct_enum_close_brace=false
nl_ds_struct_enum_cmt=false
nl_else_brace=add
nl_else_if=remove
nl_elseif_brace=add
nl_end_of_file=add
nl_end_of_file_min=1
nl_enum_brace=add
nl_enum_leave_one_liners=true
nl_fdef_brace=add
nl_for_brace=add
nl_func_decl_end=remove
nl_func_decl_start=remove
nl_func_def_paren=remove
nl_func_def_start=remove
nl_func_leave_one_liners=true
nl_func_paren=remove
nl_func_proto_type_name=remove
nl_func_type_name=remove
nl_func_type_name_class=remove
nl_func_var_def_blk=2
nl_getset_leave_one_liners=true
nl_if_brace=add
nl_if_leave_one_liners=true
nl_max=2
nl_multi_line_cond=false
nl_multi_line_define=false
nl_namespace_brace=remove
nl_return_expr=remove
nl_squeeze_ifdef=false
nl_start_of_file=remove
nl_struct_brace=add
nl_switch_brace=add
nl_template_class=add
nl_while_brace=add
pp_define_at_level=false
pp_if_indent_code=false
pp_indent=remove
pp_indent_at_level=false
pp_region_indent_code=false
sp_addr=remove
sp_after_angle=remove
sp_after_cast=remove
sp_after_class_colon=add
sp_after_comma=add
sp_after_dc=remove
sp_after_new=add
sp_after_operator=add
sp_after_operator_sym=remove
sp_after_type=ignore
sp_angle_paren=remove
sp_angle_word=add
sp_arith=add
sp_assign=add
sp_assign_default=add
sp_attribute_paren=remove
sp_balance_nested_parens=false
sp_before_angle=remove
sp_before_case_colon=remove
sp_before_class_colon=add
sp_before_comma=remove
sp_before_dc=remove
sp_before_nl_cont=add
sp_before_semi=remove
sp_before_semi_for=remove
sp_before_semi_for_empty=remove
sp_before_sparen=add
sp_before_square=remove
sp_before_squares=ignore
sp_before_tr_emb_cmt=add
sp_bool=add
sp_brace_else=add
sp_cmt_cpp_start=ignore
sp_compare=add
sp_cond_colon=add
sp_cond_question=add
sp_cpp_cast_paren=remove
sp_defined_paren=remove
sp_deref=remove
sp_else_brace=add
sp_endif_cmt=add
sp_enum_assign=add
sp_fparen_brace=add
sp_func_call_paren=remove
sp_func_class_paren=remove
sp_func_def_paren=remove
sp_func_proto_paren=remove
sp_incdec=remove
sp_inside_angle=remove
sp_inside_braces=add
#sp_inside_braces_empty=remove
sp_inside_fparen=remove
sp_inside_fparens=remove
sp_inside_paren=remove
sp_inside_paren_cast=remove
sp_inside_sparen=remove
sp_inside_square=remove
sp_inv=remove
sp_member=remove
sp_not=remove
sp_paren_brace=add
sp_paren_paren=remove
sp_pp_concat=add
sp_sign=remove
sp_sizeof_paren=remove
sp_special_semi=ignore
sp_template_angle=remove
tok_split_gte=false
utf8_bom=remove
utf8_byte=false
utf8_force=false

14
x265/readme.rst Normal file
View File

@ -0,0 +1,14 @@
=================
x265 HEVC Encoder
=================
| **Read:** | Online `documentation <http://x265.readthedocs.org/en/default/>`_ | Developer `wiki <http://bitbucket.org/multicoreware/x265/wiki/>`_
| **Download:** | `releases <http://ftp.videolan.org/pub/videolan/x265/>`_
| **Interact:** | #x265 on freenode.irc.net | `x265-devel@videolan.org <http://mailman.videolan.org/listinfo/x265-devel>`_ | `Report an issue <https://bitbucket.org/multicoreware/x265/issues?status=new&status=open>`_
`x265 <https://www.videolan.org/developers/x265.html>`_ is an open
source HEVC encoder. See the developer wiki for instructions for
downloading and building the source.
x265 is free to use under the `GNU GPL <http://www.gnu.org/licenses/gpl-2.0.html>`_
and is also available under a commercial `license <http://x265.org>`_

586
x265/source/CMakeLists.txt Normal file
View File

@ -0,0 +1,586 @@
# vim: syntax=cmake
if(NOT CMAKE_BUILD_TYPE)
# default to Release build for GCC builds
set(CMAKE_BUILD_TYPE Release CACHE STRING
"Choose the type of build, options are: None(CMAKE_CXX_FLAGS or CMAKE_C_FLAGS used) Debug Release RelWithDebInfo MinSizeRel."
FORCE)
endif()
message(STATUS "cmake version ${CMAKE_VERSION}")
if(POLICY CMP0025)
cmake_policy(SET CMP0025 OLD) # report Apple's Clang as just Clang
endif()
if(POLICY CMP0042)
cmake_policy(SET CMP0042 NEW) # MACOSX_RPATH
endif()
if(POLICY CMP0054)
cmake_policy(SET CMP0054 OLD) # Only interpret if() arguments as variables or keywords when unquoted
endif()
project (x265)
cmake_minimum_required (VERSION 2.8.8) # OBJECT libraries require 2.8.8
include(CheckIncludeFiles)
include(CheckFunctionExists)
include(CheckSymbolExists)
include(CheckCXXCompilerFlag)
option(FPROFILE_GENERATE "Compile executable to generate usage data" OFF)
option(FPROFILE_USE "Compile executable using generated usage data" OFF)
option(NATIVE_BUILD "Target the build CPU" OFF)
option(STATIC_LINK_CRT "Statically link C runtime for release builds" OFF)
mark_as_advanced(FPROFILE_USE FPROFILE_GENERATE NATIVE_BUILD)
# X265_BUILD must be incremented each time the public API is changed
set(X265_BUILD 75)
configure_file("${PROJECT_SOURCE_DIR}/x265.def.in"
"${PROJECT_BINARY_DIR}/x265.def")
configure_file("${PROJECT_SOURCE_DIR}/x265_config.h.in"
"${PROJECT_BINARY_DIR}/x265_config.h")
SET(CMAKE_MODULE_PATH "${PROJECT_SOURCE_DIR}/cmake" "${CMAKE_MODULE_PATH}")
# System architecture detection
string(TOLOWER "${CMAKE_SYSTEM_PROCESSOR}" SYSPROC)
set(X86_ALIASES x86 i386 i686 x86_64 amd64)
list(FIND X86_ALIASES "${SYSPROC}" X86MATCH)
set(POWER_ALIASES ppc64 ppc64le)
list(FIND POWER_ALIASES "${SYSPROC}" POWERMATCH)
if("${SYSPROC}" STREQUAL "" OR X86MATCH GREATER "-1")
message(STATUS "Detected x86 target processor")
set(X86 1)
add_definitions(-DX265_ARCH_X86=1)
if("${CMAKE_SIZEOF_VOID_P}" MATCHES 8)
set(X64 1)
add_definitions(-DX86_64=1)
endif()
elseif(POWERMATCH GREATER "-1")
message(STATUS "Detected POWER target processor")
set(POWER 1)
add_definitions(-DX265_ARCH_POWER=1)
elseif(${SYSPROC} STREQUAL "armv6l")
message(STATUS "Detected ARM target processor")
set(ARM 1)
add_definitions(-DX265_ARCH_ARM=1 -DHAVE_ARMV6=1)
else()
message(STATUS "CMAKE_SYSTEM_PROCESSOR value `${CMAKE_SYSTEM_PROCESSOR}` is unknown")
message(STATUS "Please add this value near ${CMAKE_CURRENT_LIST_FILE}:${CMAKE_CURRENT_LIST_LINE}")
endif()
if(UNIX)
list(APPEND PLATFORM_LIBS pthread)
find_library(LIBRT rt)
if(LIBRT)
list(APPEND PLATFORM_LIBS rt)
endif()
mark_as_advanced(LIBRT)
find_library(LIBDL dl)
if(LIBDL)
list(APPEND PLATFORM_LIBS dl)
endif()
option(ENABLE_LIBNUMA "Enable libnuma usage (Linux only)" ON)
if(ENABLE_LIBNUMA)
find_package(Numa)
if(NUMA_FOUND)
link_directories(${NUMA_LIBRARY_DIR})
list(APPEND CMAKE_REQUIRED_LIBRARIES numa)
check_symbol_exists(numa_node_of_cpu numa.h NUMA_V2)
if(NUMA_V2)
add_definitions(-DHAVE_LIBNUMA)
message(STATUS "libnuma found, building with support for NUMA nodes")
list(APPEND PLATFORM_LIBS numa)
include_directories(${NUMA_INCLUDE_DIR})
endif()
endif()
mark_as_advanced(NUMA_FOUND)
endif(ENABLE_LIBNUMA)
option(NO_ATOMICS "Use a slow mutex to replace atomics" OFF)
if(NO_ATOMICS)
add_definitions(-DNO_ATOMICS=1)
endif(NO_ATOMICS)
endif(UNIX)
if(X64 AND NOT WIN32)
option(ENABLE_PIC "Enable Position Independent Code" ON)
else()
option(ENABLE_PIC "Enable Position Independent Code" OFF)
endif(X64 AND NOT WIN32)
# Compiler detection
if(CMAKE_GENERATOR STREQUAL "Xcode")
set(XCODE 1)
endif()
if(APPLE)
add_definitions(-DMACOS)
endif()
if(${CMAKE_CXX_COMPILER_ID} STREQUAL "Clang")
set(CLANG 1)
endif()
if(${CMAKE_CXX_COMPILER_ID} STREQUAL "Intel")
set(INTEL_CXX 1)
endif()
if(${CMAKE_CXX_COMPILER_ID} STREQUAL "GNU")
set(GCC 1)
endif()
if(INTEL_CXX AND WIN32)
# treat icl roughly like MSVC
set(MSVC 1)
endif()
if(MSVC)
if(STATIC_LINK_CRT)
set(CompilerFlags CMAKE_CXX_FLAGS_RELEASE CMAKE_C_FLAGS_RELEASE)
foreach(CompilerFlag ${CompilerFlags})
string(REPLACE "/MD" "/MT" ${CompilerFlag} "${${CompilerFlag}}")
endforeach()
endif(STATIC_LINK_CRT)
add_definitions(/W4) # Full warnings
add_definitions(/Ob2) # always inline
add_definitions(/MP) # multithreaded build
# disable Microsofts suggestions for proprietary secure APIs
add_definitions(/D_CRT_SECURE_NO_WARNINGS)
check_include_files(stdint.h HAVE_STDINT_H)
if(NOT HAVE_STDINT_H)
include_directories(compat/msvc)
endif()
endif(MSVC)
check_include_files(inttypes.h HAVE_INT_TYPES_H)
if(HAVE_INT_TYPES_H)
add_definitions(-DHAVE_INT_TYPES_H=1)
endif()
if(INTEL_CXX AND UNIX)
set(GCC 1) # treat icpc roughly like gcc
elseif(CLANG)
set(GCC 1) # treat clang roughly like gcc
elseif(CMAKE_COMPILER_IS_GNUCXX)
set(GCC 1)
endif()
if(GCC)
add_definitions(-Wall -Wextra -Wshadow)
add_definitions(-D__STDC_LIMIT_MACROS=1)
if(ENABLE_PIC)
add_definitions(-fPIC)
endif(ENABLE_PIC)
if(NATIVE_BUILD)
if(INTEL_CXX)
add_definitions(-xhost)
else()
add_definitions(-march=native)
endif()
elseif(X86 AND NOT X64)
add_definitions(-march=i686)
endif()
if(ARM)
add_definitions(-march=armv6 -mfloat-abi=hard -mfpu=vfp)
endif()
if(FPROFILE_GENERATE)
if(INTEL_CXX)
add_definitions(-prof-gen -prof-dir="${CMAKE_CURRENT_BINARY_DIR}")
list(APPEND LINKER_OPTIONS "-prof-gen")
else()
check_cxx_compiler_flag(-fprofile-generate CC_HAS_PROFILE_GENERATE)
if(CC_HAS_PROFILE_GENERATE)
add_definitions(-fprofile-generate)
list(APPEND LINKER_OPTIONS "-fprofile-generate")
endif(CC_HAS_PROFILE_GENERATE)
endif(INTEL_CXX)
endif(FPROFILE_GENERATE)
if(FPROFILE_USE)
if(INTEL_CXX)
add_definitions(-prof-use -prof-dir="${CMAKE_CURRENT_BINARY_DIR}")
list(APPEND LINKER_OPTIONS "-prof-use")
else()
check_cxx_compiler_flag(-fprofile-use CC_HAS_PROFILE_USE)
check_cxx_compiler_flag(-fprofile-correction CC_HAS_PROFILE_CORRECTION)
check_cxx_compiler_flag(-Wno-error=coverage-mismatch CC_HAS_COVMISMATCH)
if(CC_HAS_PROFILE_USE)
add_definitions(-fprofile-use)
list(APPEND LINKER_OPTIONS "-fprofile-use")
endif(CC_HAS_PROFILE_USE)
if(CC_HAS_PROFILE_CORRECTION)
# auto-correct corrupted counters (happens a lot with x265)
add_definitions(-fprofile-correction)
endif(CC_HAS_PROFILE_CORRECTION)
if(CC_HAS_COVMISMATCH)
# ignore coverage mismatches (also happens a lot)
add_definitions(-Wno-error=coverage-mismatch)
endif(CC_HAS_COVMISMATCH)
endif(INTEL_CXX)
endif(FPROFILE_USE)
if(STATIC_LINK_CRT)
add_definitions(-static)
list(APPEND LINKER_OPTIONS "-static")
endif(STATIC_LINK_CRT)
check_cxx_compiler_flag(-Wno-strict-overflow CC_HAS_NO_STRICT_OVERFLOW)
check_cxx_compiler_flag(-Wno-narrowing CC_HAS_NO_NARROWING)
check_cxx_compiler_flag(-Wno-array-bounds CC_HAS_NO_ARRAY_BOUNDS)
if (CC_HAS_NO_ARRAY_BOUNDS)
add_definitions(-Wno-array-bounds) # these are unhelpful
endif()
check_cxx_compiler_flag(-ffast-math CC_HAS_FAST_MATH)
if (CC_HAS_FAST_MATH)
add_definitions(-ffast-math)
endif()
check_cxx_compiler_flag(-mstackrealign CC_HAS_STACK_REALIGN)
if (CC_HAS_STACK_REALIGN)
add_definitions(-mstackrealign)
endif()
# Disable exceptions. Reduce executable size, increase compability.
check_cxx_compiler_flag(-fno-exceptions CC_HAS_FNO_EXCEPTIONS_FLAG)
if(CC_HAS_FNO_EXCEPTIONS_FLAG)
add_definitions(-fno-exceptions)
endif()
set(FSANITIZE "" CACHE STRING "-fsanitize options for GCC/clang")
if(FSANITIZE)
add_definitions(-fsanitize=${FSANITIZE})
# clang and gcc need the sanitize options to be passed at link
# time so the appropriate ASAN/TSAN runtime libraries can be
# linked.
list(APPEND LINKER_OPTIONS "-fsanitize=${FSANITIZE}")
endif()
option(ENABLE_AGGRESSIVE_CHECKS "Enable stack protection and -ftrapv" OFF)
if(ENABLE_AGGRESSIVE_CHECKS)
# use with care, -ftrapv can cause testbench SIGILL exceptions
# since it is testing corner cases of signed integer math
add_definitions(-DUSING_FTRAPV=1)
check_cxx_compiler_flag(-fsanitize=undefined-trap CC_HAS_CATCH_UNDEFINED) # clang
check_cxx_compiler_flag(-ftrapv CC_HAS_FTRAPV) # gcc
check_cxx_compiler_flag(-fstack-protector-all CC_HAS_STACK_PROTECT) # gcc
if(CC_HAS_FTRAPV)
add_definitions(-ftrapv)
endif()
if(CC_HAS_CATCH_UNDEFINED)
add_definitions(-fsanitize=undefined-trap -fsanitize-undefined-trap-on-error)
endif()
if(CC_HAS_STACK_PROTECT)
add_definitions(-fstack-protector-all)
if(MINGW)
list(APPEND PLATFORM_LIBS ssp)
endif()
endif()
endif(ENABLE_AGGRESSIVE_CHECKS)
execute_process(COMMAND ${CMAKE_CXX_COMPILER} -dumpversion OUTPUT_VARIABLE CC_VERSION)
endif(GCC)
find_package(Yasm)
if(YASM_FOUND AND X86)
if (YASM_VERSION_STRING VERSION_LESS "1.2.0")
message(STATUS "Yasm version ${YASM_VERSION_STRING} is too old. 1.2.0 or later required")
option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" OFF)
else()
message(STATUS "Found Yasm ${YASM_VERSION_STRING} to build assembly primitives")
option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" ON)
endif()
else()
option(ENABLE_ASSEMBLY "Enable use of assembly coded primitives" OFF)
endif()
# no need to have slow encoding on x86
if(X86 AND NOT ENABLE_ASSEMBLY)
message(FATAL_ERROR "Yasm 1.2.0 or later must be installed")
endif()
option(CHECKED_BUILD "Enable run-time sanity checks (debugging)" OFF)
if(CHECKED_BUILD)
add_definitions(-DCHECKED_BUILD=1)
endif()
# Build options
set(LIB_INSTALL_DIR lib CACHE STRING "Install location of libraries")
set(BIN_INSTALL_DIR bin CACHE STRING "Install location of executables")
set(EXTRA_LIB "" CACHE STRING "Extra libraries to link against")
set(EXTRA_LINK_FLAGS "" CACHE STRING "Extra link flags")
if(EXTRA_LINK_FLAGS)
list(APPEND LINKER_OPTIONS ${EXTRA_LINK_FLAGS})
endif()
option(LINKED_8BIT "8bit libx265 is being linked with this library" OFF)
option(LINKED_10BIT "10bit libx265 is being linked with this library" OFF)
option(LINKED_12BIT "12bit libx265 is being linked with this library" OFF)
mark_as_advanced(EXTRA_LIB EXTRA_LINK_FLAGS)
if(X64)
# NOTE: We only officially support high-bit-depth compiles of x265
# on 64bit architectures. Main10 plus large resolution plus slow
# preset plus 32bit address space usually means malloc failure. You
# can disable this if(X64) check if you desparately need a 32bit
# build with 10bit/12bit support, but this violates the "shrink wrap
# license" so to speak. If it breaks you get to keep both halves.
# You will need to disable assembly manually.
option(HIGH_BIT_DEPTH "Store pixel samples as 16bit values (Main10/Main12)" OFF)
endif(X64)
if(HIGH_BIT_DEPTH)
option(MAIN12 "Support Main12 instead of Main10" OFF)
if(MAIN12)
add_definitions(-DHIGH_BIT_DEPTH=1 -DX265_DEPTH=12)
else()
add_definitions(-DHIGH_BIT_DEPTH=1 -DX265_DEPTH=10)
endif()
else(HIGH_BIT_DEPTH)
add_definitions(-DHIGH_BIT_DEPTH=0 -DX265_DEPTH=8)
endif(HIGH_BIT_DEPTH)
# this option can only be used when linking multiple libx265 libraries
# together, and some alternate API access method is implemented.
option(EXPORT_C_API "Implement public C programming interface" ON)
mark_as_advanced(EXPORT_C_API)
if(EXPORT_C_API)
set(X265_NS x265)
add_definitions(-DEXPORT_C_API=1)
elseif(HIGH_BIT_DEPTH)
if(MAIN12)
set(X265_NS x265_12bit)
else()
set(X265_NS x265_10bit)
endif()
add_definitions(-DEXPORT_C_API=0)
else()
set(X265_NS x265_8bit)
add_definitions(-DEXPORT_C_API=0)
endif()
add_definitions(-DX265_NS=${X265_NS})
option(WARNINGS_AS_ERRORS "Stop compiles on first warning" OFF)
if(WARNINGS_AS_ERRORS)
if(GCC)
add_definitions(-Werror)
elseif(MSVC)
add_definitions(/WX)
endif()
endif(WARNINGS_AS_ERRORS)
if(WIN32)
# Visual leak detector
find_package(VLD QUIET)
if(VLD_FOUND)
add_definitions(-DHAVE_VLD)
include_directories(${VLD_INCLUDE_DIRS})
list(APPEND PLATFORM_LIBS ${VLD_LIBRARIES})
link_directories(${VLD_LIBRARY_DIRS})
endif()
option(WINXP_SUPPORT "Make binaries compatible with Windows XP and Vista" OFF)
if(WINXP_SUPPORT)
# force use of workarounds for CONDITION_VARIABLE and atomic
# intrinsics introduced after XP
add_definitions(-D_WIN32_WINNT=_WIN32_WINNT_WINXP -D_WIN32_WINNT_WIN7=0x0601)
else(WINXP_SUPPORT)
# default to targeting Windows 7 for the NUMA APIs
add_definitions(-D_WIN32_WINNT=_WIN32_WINNT_WIN7)
endif(WINXP_SUPPORT)
endif()
include(version) # determine X265_VERSION and X265_LATEST_TAG
include_directories(. common encoder "${PROJECT_BINARY_DIR}")
option(ENABLE_PPA "Enable PPA profiling instrumentation" OFF)
if(ENABLE_PPA)
add_definitions(-DENABLE_PPA)
list(APPEND PLATFORM_LIBS PPA)
if(UNIX)
list(APPEND PLATFORM_LIBS dl)
endif(UNIX)
add_subdirectory(profile/PPA)
endif(ENABLE_PPA)
option(ENABLE_VTUNE "Enable Vtune profiling instrumentation" OFF)
if(ENABLE_VTUNE)
add_definitions(-DENABLE_VTUNE)
include_directories($ENV{VTUNE_AMPLIFIER_XE_2015_DIR}/include)
list(APPEND PLATFORM_LIBS vtune)
link_directories($ENV{VTUNE_AMPLIFIER_XE_2015_DIR}/lib64)
if(WIN32)
list(APPEND PLATFORM_LIBS libittnotify.lib)
else()
list(APPEND PLATFORM_LIBS libittnotify.a dl)
endif()
add_subdirectory(profile/vtune)
endif(ENABLE_VTUNE)
option(DETAILED_CU_STATS "Enable internal profiling of encoder work" OFF)
if(DETAILED_CU_STATS)
add_definitions(-DDETAILED_CU_STATS)
endif(DETAILED_CU_STATS)
add_subdirectory(encoder)
add_subdirectory(common)
if((MSVC_IDE OR XCODE) AND ENABLE_ASSEMBLY)
# this is required because of this cmake bug
# http://www.cmake.org/Bug/print_bug_page.php?bug_id=8170
if(WIN32)
set(SUFFIX obj)
else()
set(SUFFIX o)
endif()
foreach(ASM ${MSVC_ASMS})
set(YASM_SRC ${CMAKE_CURRENT_SOURCE_DIR}/common/x86/${ASM})
list(APPEND YASM_SRCS ${YASM_SRC})
list(APPEND YASM_OBJS ${ASM}.${SUFFIX})
add_custom_command(
OUTPUT ${ASM}.${SUFFIX}
COMMAND ${YASM_EXECUTABLE} ARGS ${YASM_FLAGS} ${YASM_SRC} -o ${ASM}.${SUFFIX}
DEPENDS ${YASM_SRC})
endforeach()
endif()
source_group(ASM FILES ${YASM_SRCS})
add_library(x265-static STATIC $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${YASM_OBJS} ${YASM_SRCS})
if(NOT MSVC)
set_target_properties(x265-static PROPERTIES OUTPUT_NAME x265)
endif()
if(EXTRA_LIB)
target_link_libraries(x265-static ${EXTRA_LIB})
endif()
install(TARGETS x265-static
LIBRARY DESTINATION ${LIB_INSTALL_DIR}
ARCHIVE DESTINATION ${LIB_INSTALL_DIR})
install(FILES x265.h "${PROJECT_BINARY_DIR}/x265_config.h" DESTINATION include)
if(CMAKE_RC_COMPILER)
# The resource compiler does not need CFLAGS or macro defines. It
# often breaks them
string(REPLACE "<FLAGS>" "" CMAKE_RC_COMPILE_OBJECT "${CMAKE_RC_COMPILE_OBJECT}")
string(REPLACE "<DEFINES>" "" CMAKE_RC_COMPILE_OBJECT "${CMAKE_RC_COMPILE_OBJECT}")
# convert X265_LATEST_TAG (ex: 0.7) and X265_TAG_DISTANCE (ex: 103) to
# @X265_VERSION_MAJOR@,@X265_VERSION_MINOR@,@X265_BRANCH_ID@,@X265_TAG_DISTANCE@
string(REPLACE "." ";" VERSION_LIST "${X265_LATEST_TAG}")
list(GET VERSION_LIST 0 X265_VERSION_MAJOR)
list(GET VERSION_LIST 1 X265_VERSION_MINOR)
set(X265_BRANCH_ID 0) # TODO: 0 - stable, 1 - default or other
set(X265_RC_FILE "${CMAKE_CURRENT_BINARY_DIR}/x265.rc")
configure_file("${CMAKE_CURRENT_SOURCE_DIR}/x265.rc.in" "${X265_RC_FILE}" @ONLY)
endif()
if(NOT (MSVC_IDE OR XCODE))
add_custom_target(clean-generated COMMAND ${CMAKE_COMMAND} -P ${CMAKE_CURRENT_SOURCE_DIR}/cmake/clean-generated.cmake)
endif()
option(ENABLE_SHARED "Build shared library" ON)
if(ENABLE_SHARED)
add_library(x265-shared SHARED "${PROJECT_BINARY_DIR}/x265.def" ${YASM_OBJS}
${X265_RC_FILE} $<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common>)
target_link_libraries(x265-shared ${PLATFORM_LIBS})
if(MSVC)
set_target_properties(x265-shared PROPERTIES OUTPUT_NAME libx265)
else()
set_target_properties(x265-shared PROPERTIES OUTPUT_NAME x265)
endif()
if(UNIX)
set_target_properties(x265-shared PROPERTIES VERSION ${X265_BUILD})
if(APPLE)
set_target_properties(x265-shared PROPERTIES MACOSX_RPATH 1)
else()
list(APPEND LINKER_OPTIONS "-Wl,-Bsymbolic,-znoexecstack")
endif()
endif()
set_target_properties(x265-shared PROPERTIES SOVERSION ${X265_BUILD})
if(X265_LATEST_TAG)
if(WINDOWS)
set_target_properties(x265-shared PROPERTIES VERSION ${X265_LATEST_TAG})
endif()
# shared library is not installed if a tag is not found
install(TARGETS x265-shared
LIBRARY DESTINATION ${LIB_INSTALL_DIR}
ARCHIVE DESTINATION ${LIB_INSTALL_DIR}
RUNTIME DESTINATION ${BIN_INSTALL_DIR})
endif()
if(EXTRA_LIB)
target_link_libraries(x265-shared ${EXTRA_LIB})
endif()
if(LINKER_OPTIONS)
# set_target_properties can't do list expansion
string(REPLACE ";" " " LINKER_OPTION_STR "${LINKER_OPTIONS}")
set_target_properties(x265-shared PROPERTIES LINK_FLAGS "${LINKER_OPTION_STR}")
endif()
endif()
if(X265_LATEST_TAG)
# convert lists of link libraries into -lstdc++ -lm etc..
foreach(LIB ${CMAKE_CXX_IMPLICIT_LINK_LIBRARIES} ${PLATFORM_LIBS})
if(IS_ABSOLUTE ${LIB} AND EXISTS ${LIB})
list(APPEND PLIBLIST "${LIB}")
else()
list(APPEND PLIBLIST "-l${LIB}")
endif()
endforeach()
if(PLIBLIST)
# blacklist of libraries that should not be in Libs.private
list(REMOVE_ITEM PLIBLIST "-lc" "-lpthread")
string(REPLACE ";" " " PRIVATE_LIBS "${PLIBLIST}")
else()
set(PRIVATE_LIBS "")
endif(PLIBLIST)
# Produce a pkg-config file
configure_file("x265.pc.in" "x265.pc" @ONLY)
install(FILES "${CMAKE_CURRENT_BINARY_DIR}/x265.pc"
DESTINATION "${LIB_INSTALL_DIR}/pkgconfig")
endif()
if(NOT WIN32)
configure_file("${CMAKE_CURRENT_SOURCE_DIR}/cmake/cmake_uninstall.cmake.in"
"${CMAKE_CURRENT_BINARY_DIR}/cmake/cmake_uninstall.cmake"
IMMEDIATE @ONLY)
add_custom_target(uninstall
"${CMAKE_COMMAND}" -P "${CMAKE_CURRENT_BINARY_DIR}/cmake/cmake_uninstall.cmake")
endif()
# Main CLI application
set(ENABLE_CLI ON CACHE BOOL "Build standalone CLI application")
if(ENABLE_CLI)
file(GLOB InputFiles input/input.cpp input/yuv.cpp input/y4m.cpp input/*.h)
file(GLOB OutputFiles output/output.cpp output/reconplay.cpp output/*.h
output/yuv.cpp output/y4m.cpp # recon
output/raw.cpp) # muxers
source_group(input FILES ${InputFiles})
source_group(output FILES ${OutputFiles})
check_include_files(getopt.h HAVE_GETOPT_H)
if(NOT HAVE_GETOPT_H)
if(MSVC)
set_source_files_properties(compat/getopt/getopt.c PROPERTIES COMPILE_FLAGS "/wd4100 /wd4131 -DHAVE_STRING_H=1")
endif(MSVC)
include_directories(compat/getopt)
set(GETOPT compat/getopt/getopt.c compat/getopt/getopt.h)
endif(NOT HAVE_GETOPT_H)
if(WIN32)
set(ExportDefs "${PROJECT_BINARY_DIR}/x265.def")
endif(WIN32)
if(XCODE)
# Xcode seems unable to link the CLI with libs, so link as one targget
add_executable(cli ../COPYING ${InputFiles} ${OutputFiles} ${GETOPT}
x265.cpp x265.h x265cli.h x265-extras.h x265-extras.cpp
$<TARGET_OBJECTS:encoder> $<TARGET_OBJECTS:common> ${YASM_OBJS} ${YASM_SRCS})
else()
add_executable(cli ../COPYING ${InputFiles} ${OutputFiles} ${GETOPT} ${X265_RC_FILE}
${ExportDefs} x265.cpp x265.h x265cli.h x265-extras.h x265-extras.cpp)
if(WIN32 OR NOT ENABLE_SHARED OR INTEL_CXX)
# The CLI cannot link to the shared library on Windows, it
# requires internal APIs not exported from the DLL
target_link_libraries(cli x265-static ${PLATFORM_LIBS})
else()
target_link_libraries(cli x265-shared ${PLATFORM_LIBS})
endif()
endif()
set_target_properties(cli PROPERTIES OUTPUT_NAME x265)
if(LINKER_OPTIONS)
# set_target_properties can't do list expansion
string(REPLACE ";" " " LINKER_OPTION_STR "${LINKER_OPTIONS}")
set_target_properties(cli PROPERTIES LINK_FLAGS "${LINKER_OPTION_STR}")
endif()
install(TARGETS cli DESTINATION ${BIN_INSTALL_DIR})
endif(ENABLE_CLI)
if(ENABLE_ASSEMBLY AND NOT XCODE)
option(ENABLE_TESTS "Enable Unit Tests" OFF)
if(ENABLE_TESTS)
add_subdirectory(test)
endif()
endif()

68
x265/source/cmake/CMakeASM_YASMInformation.cmake Normal file
View File

@ -0,0 +1,68 @@
set(ASM_DIALECT "_YASM")
set(CMAKE_ASM${ASM_DIALECT}_SOURCE_FILE_EXTENSIONS asm)
if(X64)
list(APPEND ASM_FLAGS -DARCH_X86_64=1)
if(ENABLE_PIC)
list(APPEND ASM_FLAGS -DPIC)
endif()
if(APPLE)
set(ARGS -f macho64 -m amd64 -DPREFIX)
elseif(UNIX AND NOT CYGWIN)
set(ARGS -f elf64 -m amd64)
else()
set(ARGS -f win64 -m amd64)
endif()
else()
list(APPEND ASM_FLAGS -DARCH_X86_64=0)
if(APPLE)
set(ARGS -f macho -DPREFIX)
elseif(UNIX AND NOT CYGWIN)
set(ARGS -f elf32)
else()
set(ARGS -f win32 -DPREFIX)
endif()
endif()
if(GCC)
list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=1)
else()
list(APPEND ASM_FLAGS -DHAVE_ALIGNED_STACK=0)
endif()
if(HIGH_BIT_DEPTH)
if(MAIN12)
list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=12 -DX265_NS=${X265_NS})
else()
list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=1 -DBIT_DEPTH=10 -DX265_NS=${X265_NS})
endif()
else()
list(APPEND ASM_FLAGS -DHIGH_BIT_DEPTH=0 -DBIT_DEPTH=8 -DX265_NS=${X265_NS})
endif()
list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS}")
if(CMAKE_BUILD_TYPE MATCHES Release)
list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_RELEASE}")
elseif(CMAKE_BUILD_TYPE MATCHES Debug)
list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_DEBUG}")
elseif(CMAKE_BUILD_TYPE MATCHES MinSizeRel)
list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_MINSIZEREL}")
elseif(CMAKE_BUILD_TYPE MATCHES RelWithDebInfo)
list(APPEND ASM_FLAGS "${CMAKE_ASM_YASM_FLAGS_RELWITHDEBINFO}")
endif()
set(YASM_FLAGS ${ARGS} ${ASM_FLAGS} PARENT_SCOPE)
string(REPLACE ";" " " CMAKE_ASM_YASM_COMPILER_ARG1 "${ARGS}")
# This section exists to override the one in CMakeASMInformation.cmake
# (the default Information file). This removes the <FLAGS>
# thing so that your C compiler flags that have been set via
# set_target_properties don't get passed to yasm and confuse it.
if(NOT CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT)
string(REPLACE ";" " " STR_ASM_FLAGS "${ASM_FLAGS}")
set(CMAKE_ASM${ASM_DIALECT}_COMPILE_OBJECT "<CMAKE_ASM${ASM_DIALECT}_COMPILER> ${STR_ASM_FLAGS} -o <OBJECT> <SOURCE>")
endif()
include(CMakeASMInformation)
set(ASM_DIALECT)

5
x265/source/cmake/CMakeDetermineASM_YASMCompiler.cmake Normal file
View File

@ -0,0 +1,5 @@
set(ASM_DIALECT "_YASM")
set(CMAKE_ASM${ASM_DIALECT}_COMPILER ${YASM_EXECUTABLE})
set(CMAKE_ASM${ASM_DIALECT}_COMPILER_INIT ${_CMAKE_TOOLCHAIN_PREFIX}yasm)
include(CMakeDetermineASMCompiler)
set(ASM_DIALECT)

3
x265/source/cmake/CMakeTestASM_YASMCompiler.cmake Normal file
View File

@ -0,0 +1,3 @@
set(ASM_DIALECT "_YASM")
include(CMakeTestASMCompiler)
set(ASM_DIALECT)

43
x265/source/cmake/FindNuma.cmake Normal file
View File

@ -0,0 +1,43 @@
# Module for locating libnuma
#
# Read-only variables:
# NUMA_FOUND
# Indicates that the library has been found.
#
# NUMA_INCLUDE_DIR
# Points to the libnuma include directory.
#
# NUMA_LIBRARY_DIR
# Points to the directory that contains the libraries.
# The content of this variable can be passed to link_directories.
#
# NUMA_LIBRARY
# Points to the libnuma that can be passed to target_link_libararies.
#
# Copyright (c) 2015 Steve Borho
include(FindPackageHandleStandardArgs)
find_path(NUMA_ROOT_DIR
NAMES include/numa.h
PATHS ENV NUMA_ROOT
DOC "NUMA root directory")
find_path(NUMA_INCLUDE_DIR
NAMES numa.h
HINTS ${NUMA_ROOT_DIR}
PATH_SUFFIXES include
DOC "NUMA include directory")
find_library(NUMA_LIBRARY
NAMES numa
HINTS ${NUMA_ROOT_DIR}
DOC "NUMA library")
if (NUMA_LIBRARY)
get_filename_component(NUMA_LIBRARY_DIR ${NUMA_LIBRARY} PATH)
endif()
mark_as_advanced(NUMA_INCLUDE_DIR NUMA_LIBRARY_DIR NUMA_LIBRARY)
find_package_handle_standard_args(NUMA REQUIRED_VARS NUMA_ROOT_DIR NUMA_INCLUDE_DIR NUMA_LIBRARY)

126
x265/source/cmake/FindVLD.cmake Normal file
View File

@ -0,0 +1,126 @@
# Module for locating Visual Leak Detector.
#
# Customizable variables:
# VLD_ROOT_DIR
# This variable points to the Visual Leak Detector root directory. By
# default, the module looks for the installation directory by examining the
# Program Files/Program Files (x86) folders and the VLDROOT environment
# variable.
#
# Read-only variables:
# VLD_FOUND
# Indicates that the library has been found.
#
# VLD_INCLUDE_DIRS
# Points to the Visual Leak Detector include directory.
#
# VLD_LIBRARY_DIRS
# Points to the Visual Leak Detector directory that contains the libraries.
# The content of this variable can be passed to link_directories.
#
# VLD_LIBRARIES
# Points to the Visual Leak Detector libraries that can be passed to
# target_link_libararies.
#
#
# Copyright (c) 2012 Sergiu Dotenco
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
INCLUDE (FindPackageHandleStandardArgs)
SET (_VLD_POSSIBLE_LIB_SUFFIXES lib)
# Version 2.0 uses vld_x86 and vld_x64 instead of simply vld as library names
IF (CMAKE_SIZEOF_VOID_P EQUAL 4)
LIST (APPEND _VLD_POSSIBLE_LIB_SUFFIXES lib/Win32)
ELSEIF (CMAKE_SIZEOF_VOID_P EQUAL 8)
LIST (APPEND _VLD_POSSIBLE_LIB_SUFFIXES lib/Win64)
ENDIF (CMAKE_SIZEOF_VOID_P EQUAL 4)
SET (PFILES "ProgramFiles")
SET (PFILES_X86 "ProgramFiles(x86)") # hack to avoid escaping issues in cmake 3.1
FIND_PATH (VLD_ROOT_DIR
NAMES include/vld.h
PATHS ENV VLDROOT
"$ENV{PFILES}/Visual Leak Detector"
"$ENV{PFILES_X86}/Visual Leak Detector"
"[HKEY_LOCAL_MACHINE\\SOFTWARE\\Microsoft\\Windows\\CurrentVersion\\Uninstall\\Visual Leak Detector;InstallLocation]"
"[HKEY_LOCAL_MACHINE\\SOFTWARE\\Wow6432Node\\Microsoft\\Windows\\CurrentVersion\\Uninstall\\Visual Leak Detector;InstallLocation]"
DOC "VLD root directory")
FIND_PATH (VLD_INCLUDE_DIR
NAMES vld.h
HINTS ${VLD_ROOT_DIR}
PATH_SUFFIXES include
DOC "VLD include directory")
FIND_LIBRARY (VLD_LIBRARY_DEBUG
NAMES vld
HINTS ${VLD_ROOT_DIR}
PATH_SUFFIXES ${_VLD_POSSIBLE_LIB_SUFFIXES}
DOC "VLD debug library")
IF (VLD_ROOT_DIR)
SET (_VLD_VERSION_FILE ${VLD_ROOT_DIR}/CHANGES.txt)
IF (EXISTS ${_VLD_VERSION_FILE})
SET (_VLD_VERSION_REGEX
"Visual Leak Detector \\(VLD\\) Version (([0-9]+)\\.([0-9]+)([a-z]|(.([0-9]+)))?)")
FILE (STRINGS ${_VLD_VERSION_FILE} _VLD_VERSION_TMP REGEX
${_VLD_VERSION_REGEX})
STRING (REGEX REPLACE ${_VLD_VERSION_REGEX} "\\1" _VLD_VERSION_TMP
"${_VLD_VERSION_TMP}")
STRING (REGEX REPLACE "([0-9]+).([0-9]+).*" "\\1" VLD_VERSION_MAJOR
"${_VLD_VERSION_TMP}")
STRING (REGEX REPLACE "([0-9]+).([0-9]+).*" "\\2" VLD_VERSION_MINOR
"${_VLD_VERSION_TMP}")
SET (VLD_VERSION ${VLD_VERSION_MAJOR}.${VLD_VERSION_MINOR})
IF ("${_VLD_VERSION_TMP}" MATCHES "^([0-9]+).([0-9]+).([0-9]+)$")
# major.minor.patch version numbering scheme
STRING (REGEX REPLACE "([0-9]+).([0-9]+).([0-9]+)" "\\3"
VLD_VERSION_PATCH "${_VLD_VERSION_TMP}")
SET (VLD_VERSION "${VLD_VERSION}.${VLD_VERSION_PATCH}")
SET (VLD_VERSION_COUNT 3)
ELSE ("${_VLD_VERSION_TMP}" MATCHES "^([0-9]+).([0-9]+).([0-9]+)$")
# major.minor version numbering scheme. The trailing letter is ignored.
SET (VLD_VERSION_COUNT 2)
ENDIF ("${_VLD_VERSION_TMP}" MATCHES "^([0-9]+).([0-9]+).([0-9]+)$")
ENDIF (EXISTS ${_VLD_VERSION_FILE})
ENDIF (VLD_ROOT_DIR)
IF (VLD_LIBRARY_DEBUG)
SET (VLD_LIBRARY debug ${VLD_LIBRARY_DEBUG} CACHE DOC "VLD library")
GET_FILENAME_COMPONENT (_VLD_LIBRARY_DIR ${VLD_LIBRARY_DEBUG} PATH)
SET (VLD_LIBRARY_DIR ${_VLD_LIBRARY_DIR} CACHE PATH "VLD library directory")
ENDIF (VLD_LIBRARY_DEBUG)
SET (VLD_INCLUDE_DIRS ${VLD_INCLUDE_DIR})
SET (VLD_LIBRARY_DIRS ${VLD_LIBRARY_DIR})
SET (VLD_LIBRARIES ${VLD_LIBRARY})
MARK_AS_ADVANCED (VLD_INCLUDE_DIR VLD_LIBRARY_DIR VLD_LIBRARY_DEBUG VLD_LIBRARY)
FIND_PACKAGE_HANDLE_STANDARD_ARGS (VLD REQUIRED_VARS VLD_ROOT_DIR
VLD_INCLUDE_DIR VLD_LIBRARY VERSION_VAR VLD_VERSION)

25
x265/source/cmake/FindYasm.cmake Normal file
View File

@ -0,0 +1,25 @@
include(FindPackageHandleStandardArgs)
# Simple path search with YASM_ROOT environment variable override
find_program(YASM_EXECUTABLE
NAMES yasm yasm-1.2.0-win32 yasm-1.2.0-win64 yasm yasm-1.3.0-win32 yasm-1.3.0-win64
HINTS $ENV{YASM_ROOT} ${YASM_ROOT}
PATH_SUFFIXES bin
)
if(YASM_EXECUTABLE)
execute_process(COMMAND ${YASM_EXECUTABLE} --version
OUTPUT_VARIABLE yasm_version
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
if(yasm_version MATCHES "^yasm ([0-9\\.]*)")
set(YASM_VERSION_STRING "${CMAKE_MATCH_1}")
endif()
unset(yasm_version)
endif()
# Provide standardized success/failure messages
find_package_handle_standard_args(yasm
REQUIRED_VARS YASM_EXECUTABLE
VERSION_VAR YASM_VERSION_STRING)

10
x265/source/cmake/clean-generated.cmake Normal file
View File

@ -0,0 +1,10 @@
set(generated "${CMAKE_CURRENT_BINARY_DIR}/x265.rc"
"${CMAKE_CURRENT_BINARY_DIR}/x265.pc"
"${CMAKE_CURRENT_BINARY_DIR}/x265.def"
"${CMAKE_CURRENT_BINARY_DIR}/x265_config.h")
foreach(file ${generated})
if(EXISTS ${file})
file(REMOVE ${file})
endif()
endforeach(file)

19
x265/source/cmake/cmake_uninstall.cmake.in Normal file
View File

@ -0,0 +1,19 @@
if(NOT EXISTS "@CMAKE_CURRENT_BINARY_DIR@/install_manifest.txt")
message(FATAL_ERROR "Cannot find install manifest: '@CMAKE_CURRENT_BINARY_DIR@/install_manifest.txt'")
endif()
file(READ "@CMAKE_CURRENT_BINARY_DIR@/install_manifest.txt" files)
string(REGEX REPLACE "\n" ";" files "${files}")
foreach(file ${files})
message(STATUS "Uninstalling $ENV{DESTDIR}${file}")
if(EXISTS "$ENV{DESTDIR}${file}" OR IS_SYMLINK "$ENV{DESTDIR}${file}")
exec_program("@CMAKE_COMMAND@" ARGS "-E remove \"$ENV{DESTDIR}${file}\""
OUTPUT_VARIABLE rm_out
RETURN_VALUE rm_retval)
if(NOT "${rm_retval}" STREQUAL 0)
message(FATAL_ERROR "Problem when removing '$ENV{DESTDIR}${file}'")
endif(NOT "${rm_retval}" STREQUAL 0)
else()
message(STATUS "File '$ENV{DESTDIR}${file}' does not exist.")
endif()
endforeach(file)

90
x265/source/cmake/version.cmake Normal file
View File

@ -0,0 +1,90 @@
if(CMAKE_VERSION VERSION_LESS "2.8.10")
find_program(HG_EXECUTABLE hg)
else()
find_package(Hg QUIET)
endif()
find_package(Git QUIET) # present in 2.8.8
# defaults, in case everything below fails
set(X265_VERSION "unknown")
set(X265_LATEST_TAG "0.0")
set(X265_TAG_DISTANCE "0")
if(EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/../.hg_archival.txt)
# read the lines of the archive summary file to extract the version
file(READ ${CMAKE_CURRENT_SOURCE_DIR}/../.hg_archival.txt archive)
STRING(REGEX REPLACE "\n" ";" archive "${archive}")
foreach(f ${archive})
string(FIND "${f}" ": " pos)
string(SUBSTRING "${f}" 0 ${pos} key)
string(SUBSTRING "${f}" ${pos} -1 value)
string(SUBSTRING "${value}" 2 -1 value)
set(hg_${key} ${value})
endforeach()
if(DEFINED hg_tag)
set(X265_VERSION ${hg_tag})
set(X265_LATEST_TAG ${hg_tag})
set(X265_TAG_DISTANCE "0")
elseif(DEFINED hg_node)
string(SUBSTRING "${hg_node}" 0 16 hg_id)
set(X265_VERSION "${hg_latesttag}+${hg_latesttagdistance}-${hg_id}")
endif()
elseif(HG_EXECUTABLE AND EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/../.hg)
if(EXISTS "${HG_EXECUTABLE}.bat")
# mercurial source installs on Windows require .bat extension
set(HG_EXECUTABLE "${HG_EXECUTABLE}.bat")
endif()
message(STATUS "hg found at ${HG_EXECUTABLE}")
execute_process(COMMAND
${HG_EXECUTABLE} log -r. --template "{latesttag}"
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE X265_LATEST_TAG
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
execute_process(COMMAND
${HG_EXECUTABLE} log -r. --template "{latesttagdistance}"
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE X265_TAG_DISTANCE
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
execute_process(
COMMAND
${HG_EXECUTABLE} log -r. --template "{node|short}"
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE HG_REVISION_ID
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
if(X265_LATEST_TAG MATCHES "^r")
string(SUBSTRING ${X265_LATEST_TAG} 1 -1 X265_LATEST_TAG)
endif()
if(X265_TAG_DISTANCE STREQUAL "0")
set(X265_VERSION "${X265_LATEST_TAG}")
else()
set(X265_VERSION "${X265_LATEST_TAG}+${X265_TAG_DISTANCE}-${HG_REVISION_ID}")
endif()
elseif(GIT_EXECUTABLE AND EXISTS ${CMAKE_CURRENT_SOURCE_DIR}/../.git)
execute_process(
COMMAND
${GIT_EXECUTABLE} describe --tags --abbrev=0
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE X265_LATEST_TAG
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
execute_process(
COMMAND
${GIT_EXECUTABLE} describe --tags
WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
OUTPUT_VARIABLE X265_VERSION
ERROR_QUIET
OUTPUT_STRIP_TRAILING_WHITESPACE
)
endif()
message(STATUS "x265 version ${X265_VERSION}")

127
x265/source/common/CMakeLists.txt Normal file
View File

@ -0,0 +1,127 @@
# vim: syntax=cmake
list(APPEND VFLAGS "-DX265_VERSION=${X265_VERSION}")
if(EXTRA_LIB)
if(LINKED_8BIT)
list(APPEND VFLAGS "-DLINKED_8BIT=1")
endif(LINKED_8BIT)
if(LINKED_10BIT)
list(APPEND VFLAGS "-DLINKED_10BIT=1")
endif(LINKED_10BIT)
if(LINKED_12BIT)
list(APPEND VFLAGS "-DLINKED_12BIT=1")
endif(LINKED_12BIT)
endif(EXTRA_LIB)
if(ENABLE_ASSEMBLY)
set_source_files_properties(threading.cpp primitives.cpp PROPERTIES COMPILE_FLAGS -DENABLE_ASSEMBLY=1)
list(APPEND VFLAGS "-DENABLE_ASSEMBLY=1")
set(SSE3 vec/dct-sse3.cpp)
set(SSSE3 vec/dct-ssse3.cpp)
set(SSE41 vec/dct-sse41.cpp)
if(MSVC AND X86)
set(PRIMITIVES ${SSE3} ${SSSE3} ${SSE41})
set(WARNDISABLE "/wd4100") # unreferenced formal parameter
if(INTEL_CXX)
add_definitions(/Qwd111) # statement is unreachable
add_definitions(/Qwd128) # loop is unreachable
add_definitions(/Qwd177) # declared function is unused
add_definitions(/Qwd185) # dynamic initialization in unreachable code
add_definitions(/Qwd280) # conditional expression is constant
endif()
if(X64)
set_source_files_properties(${SSE3} ${SSSE3} ${SSE41} PROPERTIES COMPILE_FLAGS "${WARNDISABLE}")
else()
# x64 implies SSE4, so only add /arch:SSE2 if building for Win32
set_source_files_properties(${SSE3} ${SSSE3} ${SSE41} PROPERTIES COMPILE_FLAGS "${WARNDISABLE} /arch:SSE2")
endif()
endif()
if(GCC AND X86)
if(CLANG)
# llvm intrinsic headers cause shadow warnings
set(WARNDISABLE "-Wno-shadow -Wno-unused-parameter")
else()
set(WARNDISABLE "-Wno-unused-parameter")
endif()
if(INTEL_CXX OR CLANG OR (NOT CC_VERSION VERSION_LESS 4.3))
set(PRIMITIVES ${SSE3} ${SSSE3} ${SSE41})
set_source_files_properties(${SSE3} PROPERTIES COMPILE_FLAGS "${WARNDISABLE} -msse3")
set_source_files_properties(${SSSE3} PROPERTIES COMPILE_FLAGS "${WARNDISABLE} -mssse3")
set_source_files_properties(${SSE41} PROPERTIES COMPILE_FLAGS "${WARNDISABLE} -msse4.1")
endif()
endif()
set(VEC_PRIMITIVES vec/vec-primitives.cpp ${PRIMITIVES})
source_group(Intrinsics FILES ${VEC_PRIMITIVES})
set(C_SRCS asm-primitives.cpp pixel.h mc.h ipfilter8.h blockcopy8.h dct8.h loopfilter.h)
set(A_SRCS pixel-a.asm const-a.asm cpu-a.asm ssd-a.asm mc-a.asm
mc-a2.asm pixel-util8.asm blockcopy8.asm
pixeladd8.asm dct8.asm)
if(HIGH_BIT_DEPTH)
set(A_SRCS ${A_SRCS} sad16-a.asm intrapred16.asm ipfilter16.asm loopfilter.asm)
else()
set(A_SRCS ${A_SRCS} sad-a.asm intrapred8.asm intrapred8_allangs.asm ipfilter8.asm loopfilter.asm)
endif()
if(NOT X64)
set(A_SRCS ${A_SRCS} pixel-32.asm)
endif()
if(MSVC_IDE OR XCODE)
# MSVC requires custom build rules in the main cmake script for yasm
set(MSVC_ASMS "${A_SRCS}" CACHE INTERNAL "yasm sources")
set(A_SRCS)
endif()
enable_language(ASM_YASM)
foreach(SRC ${A_SRCS} ${C_SRCS})
set(ASM_PRIMITIVES ${ASM_PRIMITIVES} x86/${SRC})
endforeach()
source_group(Assembly FILES ${ASM_PRIMITIVES})
endif(ENABLE_ASSEMBLY)
# set_target_properties can't do list expansion
string(REPLACE ";" " " VERSION_FLAGS "${VFLAGS}")
set_source_files_properties(version.cpp PROPERTIES COMPILE_FLAGS ${VERSION_FLAGS})
check_symbol_exists(strtok_r "string.h" HAVE_STRTOK_R)
if(HAVE_STRTOK_R)
set_source_files_properties(param.cpp PROPERTIES COMPILE_FLAGS -DHAVE_STRTOK_R=1)
endif()
if(GCC AND CC_HAS_NO_NARROWING)
set_source_files_properties(cpu.cpp PROPERTIES COMPILE_FLAGS -Wno-narrowing)
endif()
if(WIN32)
set(WINXP winxp.h winxp.cpp)
endif(WIN32)
add_library(common OBJECT
${ASM_PRIMITIVES} ${VEC_PRIMITIVES} ${WINXP}
primitives.cpp primitives.h
pixel.cpp dct.cpp ipfilter.cpp intrapred.cpp loopfilter.cpp
constants.cpp constants.h
cpu.cpp cpu.h version.cpp
threading.cpp threading.h
threadpool.cpp threadpool.h
wavefront.h wavefront.cpp
md5.cpp md5.h
bitstream.h bitstream.cpp
yuv.cpp yuv.h
shortyuv.cpp shortyuv.h
picyuv.cpp picyuv.h
common.cpp common.h
param.cpp param.h
frame.cpp frame.h
framedata.cpp framedata.h
cudata.cpp cudata.h
slice.cpp slice.h
lowres.cpp lowres.h mv.h
piclist.cpp piclist.h
predict.cpp predict.h
scalinglist.cpp scalinglist.h
quant.cpp quant.h contexts.h
deblock.cpp deblock.h)

129
x265/source/common/bitstream.cpp Normal file
View File

@ -0,0 +1,129 @@
#include "common.h"
#include "bitstream.h"
using namespace X265_NS;
#if defined(_MSC_VER)
#pragma warning(disable: 4244)
#endif
#define MIN_FIFO_SIZE 1000
Bitstream::Bitstream()
{
m_fifo = X265_MALLOC(uint8_t, MIN_FIFO_SIZE);
m_byteAlloc = MIN_FIFO_SIZE;
resetBits();
}
void Bitstream::push_back(uint8_t val)
{
if (!m_fifo)
return;
if (m_byteOccupancy >= m_byteAlloc)
{
/** reallocate buffer with doubled size */
uint8_t *temp = X265_MALLOC(uint8_t, m_byteAlloc * 2);
if (temp)
{
memcpy(temp, m_fifo, m_byteOccupancy);
X265_FREE(m_fifo);
m_fifo = temp;
m_byteAlloc *= 2;
}
else
{
x265_log(NULL, X265_LOG_ERROR, "Unable to realloc bitstream buffer");
return;
}
}
m_fifo[m_byteOccupancy++] = val;
}
void Bitstream::write(uint32_t val, uint32_t numBits)
{
X265_CHECK(numBits <= 32, "numBits out of range\n");
X265_CHECK(numBits == 32 || ((val & (~0u << numBits)) == 0), "numBits & val out of range\n");
uint32_t totalPartialBits = m_partialByteBits + numBits;
uint32_t nextPartialBits = totalPartialBits & 7;
uint8_t nextHeldByte = val << (8 - nextPartialBits);
uint32_t writeBytes = totalPartialBits >> 3;
if (writeBytes)
{
/* topword aligns m_partialByte with the msb of val */
uint32_t topword = (numBits - nextPartialBits) & ~7;
#if USING_FTRAPV
uint32_t write_bits = (topword < 32 ? m_partialByte << topword : 0) | (val >> nextPartialBits);
#else
uint32_t write_bits = (m_partialByte << topword) | (val >> nextPartialBits);
#endif
switch (writeBytes)
{
case 4: push_back(write_bits >> 24);
case 3: push_back(write_bits >> 16);
case 2: push_back(write_bits >> 8);
case 1: push_back(write_bits);
}
m_partialByte = nextHeldByte;
m_partialByteBits = nextPartialBits;
}
else
{
m_partialByte |= nextHeldByte;
m_partialByteBits = nextPartialBits;
}
}
void Bitstream::writeByte(uint32_t val)
{
// Only CABAC will call writeByte, the fifo must be byte aligned
X265_CHECK(!m_partialByteBits, "expecting m_partialByteBits = 0\n");
push_back(val);
}
void Bitstream::writeAlignOne()
{
uint32_t numBits = (8 - m_partialByteBits) & 0x7;
write((1 << numBits) - 1, numBits);
}
void Bitstream::writeAlignZero()
{
if (m_partialByteBits)
{
push_back(m_partialByte);
m_partialByte = 0;
m_partialByteBits = 0;
}
}
void Bitstream::writeByteAlignment()
{
write(1, 1);
writeAlignZero();
}
void SyntaxElementWriter::writeUvlc(uint32_t code)
{
uint32_t length = 1;
uint32_t temp = ++code;
X265_CHECK(temp, "writing -1 code, will cause infinite loop\n");
while (1 != temp)
{
temp >>= 1;
length += 2;
}
// Take care of cases where length > 32
m_bitIf->write(0, length >> 1);
m_bitIf->write(code, (length + 1) >> 1);
}

158
x265/source/common/bitstream.h Normal file
View File

@ -0,0 +1,158 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_BITSTREAM_H
#define X265_BITSTREAM_H 1
namespace X265_NS {
// private namespace
class BitInterface
{
public:
virtual void write(uint32_t val, uint32_t numBits) = 0;
virtual void writeByte(uint32_t val) = 0;
virtual void resetBits() = 0;
virtual uint32_t getNumberOfWrittenBits() const = 0;
virtual void writeAlignOne() = 0;
virtual void writeAlignZero() = 0;
virtual ~BitInterface() {}
};
class BitCounter : public BitInterface
{
protected:
uint32_t m_bitCounter;
public:
BitCounter() : m_bitCounter(0) {}
void write(uint32_t, uint32_t num) { m_bitCounter += num; }
void writeByte(uint32_t) { m_bitCounter += 8; }
void resetBits() { m_bitCounter = 0; }
uint32_t getNumberOfWrittenBits() const { return m_bitCounter; }
void writeAlignOne() { }
void writeAlignZero() { }
};
class Bitstream : public BitInterface
{
public:
Bitstream();
~Bitstream() { X265_FREE(m_fifo); }
void resetBits() { m_partialByteBits = m_byteOccupancy = 0; m_partialByte = 0; }
uint32_t getNumberOfWrittenBytes() const { return m_byteOccupancy; }
uint32_t getNumberOfWrittenBits() const { return m_byteOccupancy * 8 + m_partialByteBits; }
const uint8_t* getFIFO() const { return m_fifo; }
void write(uint32_t val, uint32_t numBits);
void writeByte(uint32_t val);
void writeAlignOne(); // insert one bits until the bitstream is byte-aligned
void writeAlignZero(); // insert zero bits until the bitstream is byte-aligned
void writeByteAlignment(); // insert 1 bit, then pad to byte-align with zero
private:
uint8_t *m_fifo;
uint32_t m_byteAlloc;
uint32_t m_byteOccupancy;
uint32_t m_partialByteBits;
uint8_t m_partialByte;
void push_back(uint8_t val);
};
static const uint8_t bitSize[256] =
{
1, 1, 3, 3, 5, 5, 5, 5, 7, 7, 7, 7, 7, 7, 7, 7,
9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9,
11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,
11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,
13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15,
};
static inline int bs_size_ue(unsigned int val)
{
return bitSize[val + 1];
}
static inline int bs_size_ue_big(unsigned int val)
{
if (val < 255)
return bitSize[val + 1];
else
return bitSize[(val + 1) >> 8] + 16;
}
static inline int bs_size_se(int val)
{
int tmp = 1 - val * 2;
if (tmp < 0) tmp = val * 2;
if (tmp < 256)
return bitSize[tmp];
else
return bitSize[tmp >> 8] + 16;
}
class SyntaxElementWriter
{
public:
BitInterface* m_bitIf;
SyntaxElementWriter() : m_bitIf(NULL) {}
/* silently discard the name of the syntax element */
inline void WRITE_CODE(uint32_t code, uint32_t length, const char *) { writeCode(code, length); }
inline void WRITE_UVLC(uint32_t code, const char *) { writeUvlc(code); }
inline void WRITE_SVLC(int32_t code, const char *) { writeSvlc(code); }
inline void WRITE_FLAG(bool flag, const char *) { writeFlag(flag); }
void writeCode(uint32_t code, uint32_t length) { m_bitIf->write(code, length); }
void writeUvlc(uint32_t code);
void writeSvlc(int32_t code) { uint32_t ucode = (code <= 0) ? -code << 1 : (code << 1) - 1; writeUvlc(ucode); }
void writeFlag(bool code) { m_bitIf->write(code, 1); }
};
}
#endif // ifndef X265_BITSTREAM_H

219
x265/source/common/common.cpp Normal file
View File

@ -0,0 +1,219 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Deepthi Nandakumar <deepthi@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "slice.h"
#include "threading.h"
#include "x265.h"
#if _WIN32
#include <sys/types.h>
#include <sys/timeb.h>
#else
#include <sys/time.h>
#endif
namespace X265_NS {
#if CHECKED_BUILD || _DEBUG
int g_checkFailures;
#endif
int64_t x265_mdate(void)
{
#if _WIN32
struct timeb tb;
ftime(&tb);
return ((int64_t)tb.time * 1000 + (int64_t)tb.millitm) * 1000;
#else
struct timeval tv_date;
gettimeofday(&tv_date, NULL);
return (int64_t)tv_date.tv_sec * 1000000 + (int64_t)tv_date.tv_usec;
#endif
}
#define X265_ALIGNBYTES 32
#if _WIN32
#if defined(__MINGW32__) && !defined(__MINGW64_VERSION_MAJOR)
#define _aligned_malloc __mingw_aligned_malloc
#define _aligned_free __mingw_aligned_free
#include "malloc.h"
#endif
void *x265_malloc(size_t size)
{
return _aligned_malloc(size, X265_ALIGNBYTES);
}
void x265_free(void *ptr)
{
if (ptr) _aligned_free(ptr);
}
#else // if _WIN32
void *x265_malloc(size_t size)
{
void *ptr;
if (posix_memalign((void**)&ptr, X265_ALIGNBYTES, size) == 0)
return ptr;
else
return NULL;
}
void x265_free(void *ptr)
{
if (ptr) free(ptr);
}
#endif // if _WIN32
/* Not a general-purpose function; multiplies input by -1/6 to convert
* qp to qscale. */
int x265_exp2fix8(double x)
{
int i = (int)(x * (-64.f / 6.f) + 512.5f);
if (i < 0) return 0;
if (i > 1023) return 0xffff;
return (x265_exp2_lut[i & 63] + 256) << (i >> 6) >> 8;
}
void general_log(const x265_param* param, const char* caller, int level, const char* fmt, ...)
{
if (param && level > param->logLevel)
return;
const int bufferSize = 4096;
char buffer[bufferSize];
int p = 0;
const char* log_level;
switch (level)
{
case X265_LOG_ERROR:
log_level = "error";
break;
case X265_LOG_WARNING:
log_level = "warning";
break;
case X265_LOG_INFO:
log_level = "info";
break;
case X265_LOG_DEBUG:
log_level = "debug";
break;
case X265_LOG_FULL:
log_level = "full";
break;
default:
log_level = "unknown";
break;
}
if (caller)
p += sprintf(buffer, "%-4s [%s]: ", caller, log_level);
va_list arg;
va_start(arg, fmt);
vsnprintf(buffer + p, bufferSize - p, fmt, arg);
va_end(arg);
fputs(buffer, stderr);
}
double x265_ssim2dB(double ssim)
{
double inv_ssim = 1 - ssim;
if (inv_ssim <= 0.0000000001) /* Max 100dB */
return 100;
return -10.0 * log10(inv_ssim);
}
/* The qscale - qp conversion is specified in the standards.
* Approx qscale increases by 12% with every qp increment */
double x265_qScale2qp(double qScale)
{
return 12.0 + 6.0 * (double)X265_LOG2(qScale / 0.85);
}
double x265_qp2qScale(double qp)
{
return 0.85 * pow(2.0, (qp - 12.0) / 6.0);
}
uint32_t x265_picturePlaneSize(int csp, int width, int height, int plane)
{
uint32_t size = (uint32_t)(width >> x265_cli_csps[csp].width[plane]) * (height >> x265_cli_csps[csp].height[plane]);
return size;
}
char* x265_slurp_file(const char *filename)
{
if (!filename)
return NULL;
int bError = 0;
size_t fSize;
char *buf = NULL;
FILE *fh = fopen(filename, "rb");
if (!fh)
{
x265_log(NULL, X265_LOG_ERROR, "unable to open file %s\n", filename);
return NULL;
}
bError |= fseek(fh, 0, SEEK_END) < 0;
bError |= (fSize = ftell(fh)) <= 0;
bError |= fseek(fh, 0, SEEK_SET) < 0;
if (bError)
goto error;
buf = X265_MALLOC(char, fSize + 2);
if (!buf)
{
x265_log(NULL, X265_LOG_ERROR, "unable to allocate memory\n");
goto error;
}
bError |= fread(buf, 1, fSize, fh) != fSize;
if (buf[fSize - 1] != '\n')
buf[fSize++] = '\n';
buf[fSize] = 0;
fclose(fh);
if (bError)
{
x265_log(NULL, X265_LOG_ERROR, "unable to read the file\n");
X265_FREE(buf);
buf = NULL;
}
return buf;
error:
fclose(fh);
return NULL;
}
}

441
x265/source/common/common.h Normal file
View File

@ -0,0 +1,441 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Deepthi Nandakumar <deepthi@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_COMMON_H
#define X265_COMMON_H
#include <algorithm>
#include <climits>
#include <cmath>
#include <cstdarg>
#include <cstddef>
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <cctype>
#include <ctime>
#include <stdint.h>
#include <memory.h>
#include <assert.h>
#include "x265.h"
#if ENABLE_PPA && ENABLE_VTUNE
#error "PPA and VTUNE cannot both be enabled. Disable one of them."
#endif
#if ENABLE_PPA
#include "profile/PPA/ppa.h"
#define ProfileScopeEvent(x) PPAScopeEvent(x)
#define THREAD_NAME(n,i)
#define PROFILE_INIT() PPA_INIT()
#define PROFILE_PAUSE()
#define PROFILE_RESUME()
#elif ENABLE_VTUNE
#include "profile/vtune/vtune.h"
#define ProfileScopeEvent(x) VTuneScopeEvent _vtuneTask(x)
#define THREAD_NAME(n,i) vtuneSetThreadName(n, i)
#define PROFILE_INIT() vtuneInit()
#define PROFILE_PAUSE() __itt_pause()
#define PROFILE_RESUME() __itt_resume()
#else
#define ProfileScopeEvent(x)
#define THREAD_NAME(n,i)
#define PROFILE_INIT()
#define PROFILE_PAUSE()
#define PROFILE_RESUME()
#endif
#define FENC_STRIDE 64
#define NUM_INTRA_MODE 35
#if defined(__GNUC__)
#define ALIGN_VAR_8(T, var) T var __attribute__((aligned(8)))
#define ALIGN_VAR_16(T, var) T var __attribute__((aligned(16)))
#define ALIGN_VAR_32(T, var) T var __attribute__((aligned(32)))
#if defined(__MINGW32__)
#define fseeko fseeko64
#endif
#elif defined(_MSC_VER)
#define ALIGN_VAR_8(T, var) __declspec(align(8)) T var
#define ALIGN_VAR_16(T, var) __declspec(align(16)) T var
#define ALIGN_VAR_32(T, var) __declspec(align(32)) T var
#define fseeko _fseeki64
#endif // if defined(__GNUC__)
#if HAVE_INT_TYPES_H
#define __STDC_FORMAT_MACROS
#include <inttypes.h>
#define X265_LL "%" PRIu64
#else
#define X265_LL "%lld"
#endif
#if _DEBUG && defined(_MSC_VER)
#define DEBUG_BREAK() __debugbreak()
#elif __APPLE_CC__
#define DEBUG_BREAK() __builtin_trap()
#else
#define DEBUG_BREAK() abort()
#endif
/* If compiled with CHECKED_BUILD perform run-time checks and log any that
* fail, both to stderr and to a file */
#if CHECKED_BUILD || _DEBUG
namespace X265_NS { extern int g_checkFailures; }
#define X265_CHECK(expr, ...) if (!(expr)) { \
x265_log(NULL, X265_LOG_ERROR, __VA_ARGS__); \
FILE *fp = fopen("x265_check_failures.txt", "a"); \
if (fp) { fprintf(fp, "%s:%d\n", __FILE__, __LINE__); fprintf(fp, __VA_ARGS__); fclose(fp); } \
g_checkFailures++; DEBUG_BREAK(); \
}
#if _MSC_VER
#pragma warning(disable: 4127) // some checks have constant conditions
#endif
#else
#define X265_CHECK(expr, ...)
#endif
#if HIGH_BIT_DEPTH
typedef uint16_t pixel;
typedef uint32_t sum_t;
typedef uint64_t sum2_t;
typedef uint64_t pixel4;
typedef int64_t ssum2_t;
#else
typedef uint8_t pixel;
typedef uint16_t sum_t;
typedef uint32_t sum2_t;
typedef uint32_t pixel4;
typedef int32_t ssum2_t; // Signed sum
#endif // if HIGH_BIT_DEPTH
#if X265_DEPTH <= 10
typedef uint32_t sse_ret_t;
#else
typedef uint64_t sse_ret_t;
#endif
#ifndef NULL
#define NULL 0
#endif
#define MAX_UINT 0xFFFFFFFFU // max. value of unsigned 32-bit integer
#define MAX_INT 2147483647 // max. value of signed 32-bit integer
#define MAX_INT64 0x7FFFFFFFFFFFFFFFLL // max. value of signed 64-bit integer
#define MAX_DOUBLE 1.7e+308 // max. value of double-type value
#define QP_MIN 0
#define QP_MAX_SPEC 51 /* max allowed signaled QP in HEVC */
#define QP_MAX_MAX 69 /* max allowed QP to be output by rate control */
#define MIN_QPSCALE 0.21249999999999999
#define MAX_MAX_QPSCALE 615.46574234477100
#define BITS_FOR_POC 8
template<typename T>
inline T x265_min(T a, T b) { return a < b ? a : b; }
template<typename T>
inline T x265_max(T a, T b) { return a > b ? a : b; }
template<typename T>
inline T x265_clip3(T minVal, T maxVal, T a) { return x265_min(x265_max(minVal, a), maxVal); }
template<typename T> /* clip to pixel range, 0..255 or 0..1023 */
inline pixel x265_clip(T x) { return (pixel)x265_min<T>(T((1 << X265_DEPTH) - 1), x265_max<T>(T(0), x)); }
typedef int16_t coeff_t; // transform coefficient
#define X265_MIN(a, b) ((a) < (b) ? (a) : (b))
#define X265_MAX(a, b) ((a) > (b) ? (a) : (b))
#define COPY1_IF_LT(x, y) if ((y) < (x)) (x) = (y);
#define COPY2_IF_LT(x, y, a, b) \
if ((y) < (x)) \
{ \
(x) = (y); \
(a) = (b); \
}
#define COPY3_IF_LT(x, y, a, b, c, d) \
if ((y) < (x)) \
{ \
(x) = (y); \
(a) = (b); \
(c) = (d); \
}
#define COPY4_IF_LT(x, y, a, b, c, d, e, f) \
if ((y) < (x)) \
{ \
(x) = (y); \
(a) = (b); \
(c) = (d); \
(e) = (f); \
}
#define X265_MIN3(a, b, c) X265_MIN((a), X265_MIN((b), (c)))
#define X265_MAX3(a, b, c) X265_MAX((a), X265_MAX((b), (c)))
#define X265_MIN4(a, b, c, d) X265_MIN((a), X265_MIN3((b), (c), (d)))
#define X265_MAX4(a, b, c, d) X265_MAX((a), X265_MAX3((b), (c), (d)))
#define QP_BD_OFFSET (6 * (X265_DEPTH - 8))
#define MAX_CHROMA_LAMBDA_OFFSET 36
// arbitrary, but low because SATD scores are 1/4 normal
#define X265_LOOKAHEAD_QP (12 + QP_BD_OFFSET)
#define X265_LOOKAHEAD_MAX 250
// Use the same size blocks as x264. Using larger blocks seems to give artificially
// high cost estimates (intra and inter both suffer)
#define X265_LOWRES_CU_SIZE 8
#define X265_LOWRES_CU_BITS 3
#define X265_MALLOC(type, count) (type*)x265_malloc(sizeof(type) * (count))
#define X265_FREE(ptr) x265_free(ptr)
#define CHECKED_MALLOC(var, type, count) \
{ \
var = (type*)x265_malloc(sizeof(type) * (count)); \
if (!var) \
{ \
x265_log(NULL, X265_LOG_ERROR, "malloc of size %d failed\n", sizeof(type) * (count)); \
goto fail; \
} \
}
#define CHECKED_MALLOC_ZERO(var, type, count) \
{ \
var = (type*)x265_malloc(sizeof(type) * (count)); \
if (var) \
memset((void*)var, 0, sizeof(type) * (count)); \
else \
{ \
x265_log(NULL, X265_LOG_ERROR, "malloc of size %d failed\n", sizeof(type) * (count)); \
goto fail; \
} \
}
#if defined(_MSC_VER)
#define X265_LOG2F(x) (logf((float)(x)) * 1.44269504088896405f)
#define X265_LOG2(x) (log((double)(x)) * 1.4426950408889640513713538072172)
#else
#define X265_LOG2F(x) log2f(x)
#define X265_LOG2(x) log2(x)
#endif
#define NUM_CU_DEPTH 4 // maximum number of CU depths
#define NUM_FULL_DEPTH 5 // maximum number of full depths
#define MIN_LOG2_CU_SIZE 3 // log2(minCUSize)
#define MAX_LOG2_CU_SIZE 6 // log2(maxCUSize)
#define MIN_CU_SIZE (1 << MIN_LOG2_CU_SIZE) // minimum allowable size of CU
#define MAX_CU_SIZE (1 << MAX_LOG2_CU_SIZE) // maximum allowable size of CU
#define LOG2_UNIT_SIZE 2 // log2(unitSize)
#define UNIT_SIZE (1 << LOG2_UNIT_SIZE) // unit size of CU partition
#define MAX_NUM_PARTITIONS 256
#define NUM_4x4_PARTITIONS (1U << (g_unitSizeDepth << 1)) // number of 4x4 units in max CU size
#define MIN_PU_SIZE 4
#define MIN_TU_SIZE 4
#define MAX_NUM_SPU_W (MAX_CU_SIZE / MIN_PU_SIZE) // maximum number of SPU in horizontal line
#define MAX_LOG2_TR_SIZE 5
#define MAX_LOG2_TS_SIZE 2 // TODO: RExt
#define MAX_TR_SIZE (1 << MAX_LOG2_TR_SIZE)
#define MAX_TS_SIZE (1 << MAX_LOG2_TS_SIZE)
#define COEF_REMAIN_BIN_REDUCTION 3 // indicates the level at which the VLC
// transitions from Golomb-Rice to TU+EG(k)
#define SBH_THRESHOLD 4 // fixed sign bit hiding controlling threshold
#define C1FLAG_NUMBER 8 // maximum number of largerThan1 flag coded in one chunk: 16 in HM5
#define C2FLAG_NUMBER 1 // maximum number of largerThan2 flag coded in one chunk: 16 in HM5
#define SAO_ENCODING_RATE 0.75
#define SAO_ENCODING_RATE_CHROMA 0.5
#define MLS_GRP_NUM 64 // Max number of coefficient groups, max(16, 64)
#define MLS_CG_SIZE 4 // Coefficient group size of 4x4
#define MLS_CG_BLK_SIZE (MLS_CG_SIZE * MLS_CG_SIZE)
#define MLS_CG_LOG2_SIZE 2
#define QUANT_IQUANT_SHIFT 20 // Q(QP%6) * IQ(QP%6) = 2^20
#define QUANT_SHIFT 14 // Q(4) = 2^14
#define SCALE_BITS 15 // Inherited from TMuC, presumably for fractional bit estimates in RDOQ
#define MAX_TR_DYNAMIC_RANGE 15 // Maximum transform dynamic range (excluding sign bit)
#define SHIFT_INV_1ST 7 // Shift after first inverse transform stage
#define SHIFT_INV_2ND 12 // Shift after second inverse transform stage
#define AMVP_DECIMATION_FACTOR 4
#define SCAN_SET_SIZE 16
#define LOG2_SCAN_SET_SIZE 4
#define ALL_IDX -1
#define PLANAR_IDX 0
#define VER_IDX 26 // index for intra VERTICAL mode
#define HOR_IDX 10 // index for intra HORIZONTAL mode
#define DC_IDX 1 // index for intra DC mode
#define NUM_CHROMA_MODE 5 // total number of chroma modes
#define DM_CHROMA_IDX 36 // chroma mode index for derived from luma intra mode
#define MDCS_ANGLE_LIMIT 4 // distance from true angle that horiz or vertical scan is allowed
#define MDCS_LOG2_MAX_SIZE 3 // TUs with log2 of size greater than this can only use diagonal scan
#define MAX_NUM_REF_PICS 16 // max. number of pictures used for reference
#define MAX_NUM_REF 16 // max. number of entries in picture reference list
#define REF_NOT_VALID -1
#define AMVP_NUM_CANDS 2 // number of AMVP candidates
#define MRG_MAX_NUM_CANDS 5 // max number of final merge candidates
#define CHROMA_H_SHIFT(x) (x == X265_CSP_I420 || x == X265_CSP_I422)
#define CHROMA_V_SHIFT(x) (x == X265_CSP_I420)
#define X265_MAX_PRED_MODE_PER_CTU 85 * 2 * 8
#define MAX_NUM_TR_COEFFS MAX_TR_SIZE * MAX_TR_SIZE // Maximum number of transform coefficients, for a 32x32 transform
#define MAX_NUM_TR_CATEGORIES 16 // 32, 16, 8, 4 transform categories each for luma and chroma
namespace X265_NS {
enum { SAO_NUM_OFFSET = 4 };
enum SaoMergeMode
{
SAO_MERGE_NONE,
SAO_MERGE_LEFT,
SAO_MERGE_UP
};
struct SaoCtuParam
{
SaoMergeMode mergeMode;
int typeIdx;
uint32_t bandPos; // BO band position
int offset[SAO_NUM_OFFSET];
void reset()
{
mergeMode = SAO_MERGE_NONE;
typeIdx = -1;
bandPos = 0;
offset[0] = 0;
offset[1] = 0;
offset[2] = 0;
offset[3] = 0;
}
};
struct SAOParam
{
SaoCtuParam* ctuParam[3];
bool bSaoFlag[2];
int numCuInWidth;
SAOParam()
{
for (int i = 0; i < 3; i++)
ctuParam[i] = NULL;
}
~SAOParam()
{
delete[] ctuParam[0];
delete[] ctuParam[1];
delete[] ctuParam[2];
}
};
/* Stores inter analysis data for a single frame */
struct analysis_inter_data
{
int32_t* ref;
uint8_t* depth;
uint8_t* modes;
uint32_t* bestMergeCand;
};
/* Stores intra analysis data for a single frame. This struct needs better packing */
struct analysis_intra_data
{
uint8_t* depth;
uint8_t* modes;
char* partSizes;
uint8_t* chromaModes;
};
enum TextType
{
TEXT_LUMA = 0, // luma
TEXT_CHROMA_U = 1, // chroma U
TEXT_CHROMA_V = 2, // chroma V
MAX_NUM_COMPONENT = 3
};
// coefficient scanning type used in ACS
enum ScanType
{
SCAN_DIAG = 0, // up-right diagonal scan
SCAN_HOR = 1, // horizontal first scan
SCAN_VER = 2, // vertical first scan
NUM_SCAN_TYPE = 3
};
enum SignificanceMapContextType
{
CONTEXT_TYPE_4x4 = 0,
CONTEXT_TYPE_8x8 = 1,
CONTEXT_TYPE_NxN = 2,
CONTEXT_NUMBER_OF_TYPES = 3
};
/* located in pixel.cpp */
void extendPicBorder(pixel* recon, intptr_t stride, int width, int height, int marginX, int marginY);
/* located in common.cpp */
int64_t x265_mdate(void);
#define x265_log(param, ...) general_log(param, "x265", __VA_ARGS__)
void general_log(const x265_param* param, const char* caller, int level, const char* fmt, ...);
int x265_exp2fix8(double x);
double x265_ssim2dB(double ssim);
double x265_qScale2qp(double qScale);
double x265_qp2qScale(double qp);
uint32_t x265_picturePlaneSize(int csp, int width, int height, int plane);
void* x265_malloc(size_t size);
void x265_free(void *ptr);
char* x265_slurp_file(const char *filename);
/* located in primitives.cpp */
void x265_setup_primitives(x265_param* param);
void x265_report_simd(x265_param* param);
}
#include "constants.h"
#endif // ifndef X265_COMMON_H

582
x265/source/common/constants.cpp Normal file
View File

@ -0,0 +1,582 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "constants.h"
#include "threading.h"
namespace X265_NS {
#if X265_DEPTH == 12
// lambda = pow(2, (double)q / 6 - 2) * (1 << (12 - 8));
double x265_lambda_tab[QP_MAX_MAX + 1] =
{
4.0000, 4.4898, 5.0397, 5.6569, 6.3496,
7.1272, 8.0000, 8.9797, 10.0794, 11.3137,
12.6992, 14.2544, 16.0000, 17.9594, 20.1587,
22.6274, 25.3984, 28.5088, 32.0000, 35.9188,
40.3175, 45.2548, 50.7968, 57.0175, 64.0000,
71.8376, 80.6349, 90.5097, 101.5937, 114.0350,
128.0000, 143.6751, 161.2699, 181.0193, 203.1873,
228.0701, 256.0000, 287.3503, 322.5398, 362.0387,
406.3747, 456.1401, 512.0000, 574.7006, 645.0796,
724.0773, 812.7493, 912.2803, 1024.0000, 1149.4011,
1290.1592, 1448.1547, 1625.4987, 1824.5606, 2048.0000,
2298.8023, 2580.3183, 2896.3094, 3250.9974, 3649.1211,
4096.0000, 4597.6045, 5160.6366, 5792.6188, 6501.9947,
7298.2423, 8192.0000, 9195.2091, 10321.2732, 11585.2375
};
// lambda2 = pow(lambda, 2) * scale (0.85);
double x265_lambda2_tab[QP_MAX_MAX + 1] =
{
13.6000, 17.1349, 21.5887, 27.2000, 34.2699,
43.1773, 54.4000, 68.5397, 86.3546, 108.8000,
137.0794, 172.7092, 217.6000, 274.1588, 345.4185,
435.2000, 548.3176, 690.8369, 870.4000, 1096.6353,
1381.6739, 1740.8000, 2193.2706, 2763.3478, 3481.6000,
4386.5411, 5526.6955, 6963.2000, 8773.0822, 11053.3910,
13926.4000, 17546.1645, 22106.7819, 27852.8000, 35092.3291,
44213.5641, 55705.6000, 70184.6579, 88427.1282, 111411.2000,
140369.3159, 176854.2563, 222822.4000, 280738.6324, 353708.5127,
445644.8001, 561477.2648, 707417.0237, 891289.6000, 1122954.5277,
1414834.0484, 1782579.2003, 2245909.0566, 2829668.0981, 3565158.4000,
4491818.1146, 5659336.1938, 7130316.8013, 8983636.2264, 11318672.3923,
14260633.6000, 17967272.4585, 22637344.7751, 28521267.1953, 35934544.9165,
45274689.5567, 57042534.4000, 71869089.8338, 90549379.1181, 114085068.8008
};
#elif X265_DEPTH == 10
// lambda = pow(2, (double)q / 6 - 2) * (1 << (X265_DEPTH - 8));
double x265_lambda_tab[QP_MAX_MAX + 1] =
{
1.0000, 1.1225, 1.2599, 1.4142, 1.5874,
1.7818, 2.0000, 2.2449, 2.5198, 2.8284,
3.1748, 3.5636, 4.0000, 4.4898, 5.0397,
5.6569, 6.3496, 7.1272, 8.0000, 8.9797,
10.0794, 11.3137, 12.6992, 14.2544, 16.0000,
17.9594, 20.1587, 22.6274, 25.3984, 28.5088,
32.0000, 35.9188, 40.3175, 45.2548, 50.7968,
57.0175, 64.0000, 71.8376, 80.6349, 90.5097,
101.5937, 114.0350, 128.0000, 143.6751, 161.2699,
181.0193, 203.1873, 228.0701, 256.0000, 287.3503,
322.5398, 362.0387, 406.3747, 456.1401, 512.0000,
574.7006, 645.0796, 724.0773, 812.7493, 912.2803,
1024.0000, 1149.4011, 1290.1592, 1448.1547, 1625.4987,
1824.5606, 2048.0000, 2298.8023, 2580.3183, 2896.3094,
};
// lambda2 = pow(lambda, 2) * scale (0.85);
double x265_lambda2_tab[QP_MAX_MAX + 1] =
{
0.8500, 1.0709, 1.3493, 1.7000, 2.1419,
2.6986, 3.4000, 4.2837, 5.3972, 6.8000,
8.5675, 10.7943, 13.6000, 17.1349, 21.5887,
27.2000, 34.2699, 43.1773, 54.4000, 68.5397,
86.3546, 108.8000, 137.0794, 172.7092, 217.6000,
274.1588, 345.4185, 435.2000, 548.3176, 690.8369,
870.4000, 1096.6353, 1381.6739, 1740.8000, 2193.2706,
2763.3478, 3481.6000, 4386.5411, 5526.6955, 6963.2000,
8773.0823, 11053.3910, 13926.4000, 17546.1645, 22106.7820,
27852.8000, 35092.3290, 44213.5640, 55705.6000, 70184.6580,
88427.1280, 111411.2000, 140369.3161, 176854.2561, 222822.4000,
280738.6321, 353708.5122, 445644.8000, 561477.2643, 707417.0243,
891289.6000, 1122954.5286, 1414834.0486, 1782579.2000, 2245909.0572,
2829668.0973, 3565158.4000, 4491818.1144, 5659336.1946, 7130316.8000,
};
#else /* !HIGH_BIT_DEPTH */
// lambda = pow(2, (double)q / 6 - 2);
double x265_lambda_tab[QP_MAX_MAX + 1] =
{
0.2500, 0.2806, 0.3150, 0.3536, 0.3969,
0.4454, 0.5000, 0.5612, 0.6300, 0.7071,
0.7937, 0.8909, 1.0000, 1.1225, 1.2599,
1.4142, 1.5874, 1.7818, 2.0000, 2.2449,
2.5198, 2.8284, 3.1748, 3.5636, 4.0000,
4.4898, 5.0397, 5.6569, 6.3496, 7.1272,
8.0000, 8.9797, 10.0794, 11.3137, 12.6992,
14.2544, 16.0000, 17.9594, 20.1587, 22.6274,
25.3984, 28.5088, 32.0000, 35.9188, 40.3175,
45.2548, 50.7968, 57.0175, 64.0000, 71.8376,
80.6349, 90.5097, 101.5937, 114.0350, 128.0000,
143.6751, 161.2699, 181.0193, 203.1873, 228.0701,
256.0000, 287.3503, 322.5398, 362.0387, 406.3747,
456.1401, 512.0000, 574.7006, 645.0796, 724.0773
};
// lambda2 = pow(lambda, 2) * scale (0.85);
double x265_lambda2_tab[QP_MAX_MAX + 1] =
{
0.0531, 0.0669, 0.0843, 0.1063, 0.1339,
0.1687, 0.2125, 0.2677, 0.3373, 0.4250,
0.5355, 0.6746, 0.8500, 1.0709, 1.3493,
1.7000, 2.1419, 2.6986, 3.4000, 4.2837,
5.3970, 6.8000, 8.5675, 10.7943, 13.6000,
17.1345, 21.5887, 27.2004, 34.2699, 43.1773,
54.4000, 68.5397, 86.3551, 108.7998, 137.0792,
172.7097, 217.6000, 274.1590, 345.4172, 435.1993,
548.3169, 690.8389, 870.4000, 1096.6362, 1381.6757,
1740.7974, 2193.2676, 2763.3460, 3481.6000, 4386.5446,
5526.6890, 6963.2049, 8773.0879, 11053.3840, 13926.4000,
17546.1542, 22106.7835, 27852.7889, 35092.3170, 44213.5749,
55705.6000, 70184.6657, 88427.1342, 111411.2172, 140369.3373,
176854.2222, 222822.4000, 280738.6627, 353708.5368, 445644.7459
};
#endif
const uint16_t x265_chroma_lambda2_offset_tab[MAX_CHROMA_LAMBDA_OFFSET+1] =
{
16, 20, 25, 32, 40, 50,
64, 80, 101, 128, 161, 203,
256, 322, 406, 512, 645, 812,
1024, 1290, 1625, 2048, 2580, 3250,
4096, 5160, 6501, 8192, 10321, 13003,
16384, 20642, 26007, 32768, 41285, 52015,
65535
};
int g_ctuSizeConfigured = 0;
uint32_t g_maxLog2CUSize = MAX_LOG2_CU_SIZE;
uint32_t g_maxCUSize = MAX_CU_SIZE;
uint32_t g_unitSizeDepth = NUM_CU_DEPTH;
uint32_t g_maxCUDepth = NUM_CU_DEPTH - 1;
uint32_t g_zscanToRaster[MAX_NUM_PARTITIONS] = { 0, };
uint32_t g_rasterToZscan[MAX_NUM_PARTITIONS] = { 0, };
const uint8_t g_zscanToPelX[MAX_NUM_PARTITIONS] =
{
0, 4, 0, 4, 8, 12, 8, 12, 0, 4, 0, 4, 8, 12, 8, 12,
16, 20, 16, 20, 24, 28, 24, 28, 16, 20, 16, 20, 24, 28, 24, 28,
0, 4, 0, 4, 8, 12, 8, 12, 0, 4, 0, 4, 8, 12, 8, 12,
16, 20, 16, 20, 24, 28, 24, 28, 16, 20, 16, 20, 24, 28, 24, 28,
32, 36, 32, 36, 40, 44, 40, 44, 32, 36, 32, 36, 40, 44, 40, 44,
48, 52, 48, 52, 56, 60, 56, 60, 48, 52, 48, 52, 56, 60, 56, 60,
32, 36, 32, 36, 40, 44, 40, 44, 32, 36, 32, 36, 40, 44, 40, 44,
48, 52, 48, 52, 56, 60, 56, 60, 48, 52, 48, 52, 56, 60, 56, 60,
0, 4, 0, 4, 8, 12, 8, 12, 0, 4, 0, 4, 8, 12, 8, 12,
16, 20, 16, 20, 24, 28, 24, 28, 16, 20, 16, 20, 24, 28, 24, 28,
0, 4, 0, 4, 8, 12, 8, 12, 0, 4, 0, 4, 8, 12, 8, 12,
16, 20, 16, 20, 24, 28, 24, 28, 16, 20, 16, 20, 24, 28, 24, 28,
32, 36, 32, 36, 40, 44, 40, 44, 32, 36, 32, 36, 40, 44, 40, 44,
48, 52, 48, 52, 56, 60, 56, 60, 48, 52, 48, 52, 56, 60, 56, 60,
32, 36, 32, 36, 40, 44, 40, 44, 32, 36, 32, 36, 40, 44, 40, 44,
48, 52, 48, 52, 56, 60, 56, 60, 48, 52, 48, 52, 56, 60, 56, 60
};
const uint8_t g_zscanToPelY[MAX_NUM_PARTITIONS] =
{
0, 0, 4, 4, 0, 0, 4, 4, 8, 8, 12, 12, 8, 8, 12, 12,
0, 0, 4, 4, 0, 0, 4, 4, 8, 8, 12, 12, 8, 8, 12, 12,
16, 16, 20, 20, 16, 16, 20, 20, 24, 24, 28, 28, 24, 24, 28, 28,
16, 16, 20, 20, 16, 16, 20, 20, 24, 24, 28, 28, 24, 24, 28, 28,
0, 0, 4, 4, 0, 0, 4, 4, 8, 8, 12, 12, 8, 8, 12, 12,
0, 0, 4, 4, 0, 0, 4, 4, 8, 8, 12, 12, 8, 8, 12, 12,
16, 16, 20, 20, 16, 16, 20, 20, 24, 24, 28, 28, 24, 24, 28, 28,
16, 16, 20, 20, 16, 16, 20, 20, 24, 24, 28, 28, 24, 24, 28, 28,
32, 32, 36, 36, 32, 32, 36, 36, 40, 40, 44, 44, 40, 40, 44, 44,
32, 32, 36, 36, 32, 32, 36, 36, 40, 40, 44, 44, 40, 40, 44, 44,
48, 48, 52, 52, 48, 48, 52, 52, 56, 56, 60, 60, 56, 56, 60, 60,
48, 48, 52, 52, 48, 48, 52, 52, 56, 56, 60, 60, 56, 56, 60, 60,
32, 32, 36, 36, 32, 32, 36, 36, 40, 40, 44, 44, 40, 40, 44, 44,
32, 32, 36, 36, 32, 32, 36, 36, 40, 40, 44, 44, 40, 40, 44, 44,
48, 48, 52, 52, 48, 48, 52, 52, 56, 56, 60, 60, 56, 56, 60, 60,
48, 48, 52, 52, 48, 48, 52, 52, 56, 56, 60, 60, 56, 56, 60, 60
};
void initZscanToRaster(uint32_t maxFullDepth, uint32_t depth, uint32_t startVal, uint32_t*& curIdx)
{
uint32_t stride = 1 << maxFullDepth;
if (depth > maxFullDepth)
{
curIdx[0] = startVal;
curIdx++;
}
else
{
int step = stride >> depth;
initZscanToRaster(maxFullDepth, depth + 1, startVal, curIdx);
initZscanToRaster(maxFullDepth, depth + 1, startVal + step, curIdx);
initZscanToRaster(maxFullDepth, depth + 1, startVal + step * stride, curIdx);
initZscanToRaster(maxFullDepth, depth + 1, startVal + step * stride + step, curIdx);
}
}
void initRasterToZscan(uint32_t maxFullDepth)
{
uint32_t numPartitions = 1 << (maxFullDepth * 2);
for (uint32_t i = 0; i < numPartitions; i++)
g_rasterToZscan[g_zscanToRaster[i]] = i;
}
const int16_t g_lumaFilter[4][NTAPS_LUMA] =
{
{ 0, 0, 0, 64, 0, 0, 0, 0 },
{ -1, 4, -10, 58, 17, -5, 1, 0 },
{ -1, 4, -11, 40, 40, -11, 4, -1 },
{ 0, 1, -5, 17, 58, -10, 4, -1 }
};
const int16_t g_chromaFilter[8][NTAPS_CHROMA] =
{
{ 0, 64, 0, 0 },
{ -2, 58, 10, -2 },
{ -4, 54, 16, -2 },
{ -6, 46, 28, -4 },
{ -4, 36, 36, -4 },
{ -4, 28, 46, -6 },
{ -2, 16, 54, -4 },
{ -2, 10, 58, -2 }
};
const int16_t g_t4[4][4] =
{
{ 64, 64, 64, 64 },
{ 83, 36, -36, -83 },
{ 64, -64, -64, 64 },
{ 36, -83, 83, -36 }
};
const int16_t g_t8[8][8] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64 },
{ 89, 75, 50, 18, -18, -50, -75, -89 },
{ 83, 36, -36, -83, -83, -36, 36, 83 },
{ 75, -18, -89, -50, 50, 89, 18, -75 },
{ 64, -64, -64, 64, 64, -64, -64, 64 },
{ 50, -89, 18, 75, -75, -18, 89, -50 },
{ 36, -83, 83, -36, -36, 83, -83, 36 },
{ 18, -50, 75, -89, 89, -75, 50, -18 }
};
const int16_t g_t16[16][16] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64 },
{ 90, 87, 80, 70, 57, 43, 25, 9, -9, -25, -43, -57, -70, -80, -87, -90 },
{ 89, 75, 50, 18, -18, -50, -75, -89, -89, -75, -50, -18, 18, 50, 75, 89 },
{ 87, 57, 9, -43, -80, -90, -70, -25, 25, 70, 90, 80, 43, -9, -57, -87 },
{ 83, 36, -36, -83, -83, -36, 36, 83, 83, 36, -36, -83, -83, -36, 36, 83 },
{ 80, 9, -70, -87, -25, 57, 90, 43, -43, -90, -57, 25, 87, 70, -9, -80 },
{ 75, -18, -89, -50, 50, 89, 18, -75, -75, 18, 89, 50, -50, -89, -18, 75 },
{ 70, -43, -87, 9, 90, 25, -80, -57, 57, 80, -25, -90, -9, 87, 43, -70 },
{ 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64 },
{ 57, -80, -25, 90, -9, -87, 43, 70, -70, -43, 87, 9, -90, 25, 80, -57 },
{ 50, -89, 18, 75, -75, -18, 89, -50, -50, 89, -18, -75, 75, 18, -89, 50 },
{ 43, -90, 57, 25, -87, 70, 9, -80, 80, -9, -70, 87, -25, -57, 90, -43 },
{ 36, -83, 83, -36, -36, 83, -83, 36, 36, -83, 83, -36, -36, 83, -83, 36 },
{ 25, -70, 90, -80, 43, 9, -57, 87, -87, 57, -9, -43, 80, -90, 70, -25 },
{ 18, -50, 75, -89, 89, -75, 50, -18, -18, 50, -75, 89, -89, 75, -50, 18 },
{ 9, -25, 43, -57, 70, -80, 87, -90, 90, -87, 80, -70, 57, -43, 25, -9 }
};
const int16_t g_t32[32][32] =
{
{ 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64, 64 },
{ 90, 90, 88, 85, 82, 78, 73, 67, 61, 54, 46, 38, 31, 22, 13, 4, -4, -13, -22, -31, -38, -46, -54, -61, -67, -73, -78, -82, -85, -88, -90, -90 },
{ 90, 87, 80, 70, 57, 43, 25, 9, -9, -25, -43, -57, -70, -80, -87, -90, -90, -87, -80, -70, -57, -43, -25, -9, 9, 25, 43, 57, 70, 80, 87, 90 },
{ 90, 82, 67, 46, 22, -4, -31, -54, -73, -85, -90, -88, -78, -61, -38, -13, 13, 38, 61, 78, 88, 90, 85, 73, 54, 31, 4, -22, -46, -67, -82, -90 },
{ 89, 75, 50, 18, -18, -50, -75, -89, -89, -75, -50, -18, 18, 50, 75, 89, 89, 75, 50, 18, -18, -50, -75, -89, -89, -75, -50, -18, 18, 50, 75, 89 },
{ 88, 67, 31, -13, -54, -82, -90, -78, -46, -4, 38, 73, 90, 85, 61, 22, -22, -61, -85, -90, -73, -38, 4, 46, 78, 90, 82, 54, 13, -31, -67, -88 },
{ 87, 57, 9, -43, -80, -90, -70, -25, 25, 70, 90, 80, 43, -9, -57, -87, -87, -57, -9, 43, 80, 90, 70, 25, -25, -70, -90, -80, -43, 9, 57, 87 },
{ 85, 46, -13, -67, -90, -73, -22, 38, 82, 88, 54, -4, -61, -90, -78, -31, 31, 78, 90, 61, 4, -54, -88, -82, -38, 22, 73, 90, 67, 13, -46, -85 },
{ 83, 36, -36, -83, -83, -36, 36, 83, 83, 36, -36, -83, -83, -36, 36, 83, 83, 36, -36, -83, -83, -36, 36, 83, 83, 36, -36, -83, -83, -36, 36, 83 },
{ 82, 22, -54, -90, -61, 13, 78, 85, 31, -46, -90, -67, 4, 73, 88, 38, -38, -88, -73, -4, 67, 90, 46, -31, -85, -78, -13, 61, 90, 54, -22, -82 },
{ 80, 9, -70, -87, -25, 57, 90, 43, -43, -90, -57, 25, 87, 70, -9, -80, -80, -9, 70, 87, 25, -57, -90, -43, 43, 90, 57, -25, -87, -70, 9, 80 },
{ 78, -4, -82, -73, 13, 85, 67, -22, -88, -61, 31, 90, 54, -38, -90, -46, 46, 90, 38, -54, -90, -31, 61, 88, 22, -67, -85, -13, 73, 82, 4, -78 },
{ 75, -18, -89, -50, 50, 89, 18, -75, -75, 18, 89, 50, -50, -89, -18, 75, 75, -18, -89, -50, 50, 89, 18, -75, -75, 18, 89, 50, -50, -89, -18, 75 },
{ 73, -31, -90, -22, 78, 67, -38, -90, -13, 82, 61, -46, -88, -4, 85, 54, -54, -85, 4, 88, 46, -61, -82, 13, 90, 38, -67, -78, 22, 90, 31, -73 },
{ 70, -43, -87, 9, 90, 25, -80, -57, 57, 80, -25, -90, -9, 87, 43, -70, -70, 43, 87, -9, -90, -25, 80, 57, -57, -80, 25, 90, 9, -87, -43, 70 },
{ 67, -54, -78, 38, 85, -22, -90, 4, 90, 13, -88, -31, 82, 46, -73, -61, 61, 73, -46, -82, 31, 88, -13, -90, -4, 90, 22, -85, -38, 78, 54, -67 },
{ 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64, 64, -64, -64, 64 },
{ 61, -73, -46, 82, 31, -88, -13, 90, -4, -90, 22, 85, -38, -78, 54, 67, -67, -54, 78, 38, -85, -22, 90, 4, -90, 13, 88, -31, -82, 46, 73, -61 },
{ 57, -80, -25, 90, -9, -87, 43, 70, -70, -43, 87, 9, -90, 25, 80, -57, -57, 80, 25, -90, 9, 87, -43, -70, 70, 43, -87, -9, 90, -25, -80, 57 },
{ 54, -85, -4, 88, -46, -61, 82, 13, -90, 38, 67, -78, -22, 90, -31, -73, 73, 31, -90, 22, 78, -67, -38, 90, -13, -82, 61, 46, -88, 4, 85, -54 },
{ 50, -89, 18, 75, -75, -18, 89, -50, -50, 89, -18, -75, 75, 18, -89, 50, 50, -89, 18, 75, -75, -18, 89, -50, -50, 89, -18, -75, 75, 18, -89, 50 },
{ 46, -90, 38, 54, -90, 31, 61, -88, 22, 67, -85, 13, 73, -82, 4, 78, -78, -4, 82, -73, -13, 85, -67, -22, 88, -61, -31, 90, -54, -38, 90, -46 },
{ 43, -90, 57, 25, -87, 70, 9, -80, 80, -9, -70, 87, -25, -57, 90, -43, -43, 90, -57, -25, 87, -70, -9, 80, -80, 9, 70, -87, 25, 57, -90, 43 },
{ 38, -88, 73, -4, -67, 90, -46, -31, 85, -78, 13, 61, -90, 54, 22, -82, 82, -22, -54, 90, -61, -13, 78, -85, 31, 46, -90, 67, 4, -73, 88, -38 },
{ 36, -83, 83, -36, -36, 83, -83, 36, 36, -83, 83, -36, -36, 83, -83, 36, 36, -83, 83, -36, -36, 83, -83, 36, 36, -83, 83, -36, -36, 83, -83, 36 },
{ 31, -78, 90, -61, 4, 54, -88, 82, -38, -22, 73, -90, 67, -13, -46, 85, -85, 46, 13, -67, 90, -73, 22, 38, -82, 88, -54, -4, 61, -90, 78, -31 },
{ 25, -70, 90, -80, 43, 9, -57, 87, -87, 57, -9, -43, 80, -90, 70, -25, -25, 70, -90, 80, -43, -9, 57, -87, 87, -57, 9, 43, -80, 90, -70, 25 },
{ 22, -61, 85, -90, 73, -38, -4, 46, -78, 90, -82, 54, -13, -31, 67, -88, 88, -67, 31, 13, -54, 82, -90, 78, -46, 4, 38, -73, 90, -85, 61, -22 },
{ 18, -50, 75, -89, 89, -75, 50, -18, -18, 50, -75, 89, -89, 75, -50, 18, 18, -50, 75, -89, 89, -75, 50, -18, -18, 50, -75, 89, -89, 75, -50, 18 },
{ 13, -38, 61, -78, 88, -90, 85, -73, 54, -31, 4, 22, -46, 67, -82, 90, -90, 82, -67, 46, -22, -4, 31, -54, 73, -85, 90, -88, 78, -61, 38, -13 },
{ 9, -25, 43, -57, 70, -80, 87, -90, 90, -87, 80, -70, 57, -43, 25, -9, -9, 25, -43, 57, -70, 80, -87, 90, -90, 87, -80, 70, -57, 43, -25, 9 },
{ 4, -13, 22, -31, 38, -46, 54, -61, 67, -73, 78, -82, 85, -88, 90, -90, 90, -90, 88, -85, 82, -78, 73, -67, 61, -54, 46, -38, 31, -22, 13, -4 }
};
const uint8_t g_chromaScale[ChromaQPMappingTableSize] =
{
0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 29, 30, 31, 32, 33, 33, 34, 34, 35, 35, 36, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51,
51, 51, 51, 51, 51, 51, 51, 51, 51, 51, 51, 51
};
const uint8_t g_chroma422IntraAngleMappingTable[AngleMapping422TableSize] =
{ 0, 1, 2, 2, 2, 2, 3, 5, 7, 8, 10, 12, 13, 15, 17, 18, 19, 20, 21, 22, 23, 23, 24, 24, 25, 25, 26, 27, 27, 28, 28, 29, 29, 30, 31, DM_CHROMA_IDX };
const uint8_t g_log2Size[MAX_CU_SIZE + 1] =
{
0, 0, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3,
4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4,
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
6
};
const uint16_t g_scan2x2[][2*2] =
{
{ 0, 2, 1, 3 },
{ 0, 1, 2, 3 },
};
const uint16_t g_scan8x8[NUM_SCAN_TYPE][8 * 8] =
{
{ 0, 8, 1, 16, 9, 2, 24, 17, 10, 3, 25, 18, 11, 26, 19, 27, 32, 40, 33, 48, 41, 34, 56, 49, 42, 35, 57, 50, 43, 58, 51, 59,
4, 12, 5, 20, 13, 6, 28, 21, 14, 7, 29, 22, 15, 30, 23, 31, 36, 44, 37, 52, 45, 38, 60, 53, 46, 39, 61, 54, 47, 62, 55, 63 },
{ 0, 1, 2, 3, 8, 9, 10, 11, 16, 17, 18, 19, 24, 25, 26, 27, 4, 5, 6, 7, 12, 13, 14, 15, 20, 21, 22, 23, 28, 29, 30, 31,
32, 33, 34, 35, 40, 41, 42, 43, 48, 49, 50, 51, 56, 57, 58, 59, 36, 37, 38, 39, 44, 45, 46, 47, 52, 53, 54, 55, 60, 61, 62, 63 },
{ 0, 8, 16, 24, 1, 9, 17, 25, 2, 10, 18, 26, 3, 11, 19, 27, 32, 40, 48, 56, 33, 41, 49, 57, 34, 42, 50, 58, 35, 43, 51, 59,
4, 12, 20, 28, 5, 13, 21, 29, 6, 14, 22, 30, 7, 15, 23, 31, 36, 44, 52, 60, 37, 45, 53, 61, 38, 46, 54, 62, 39, 47, 55, 63 }
};
ALIGN_VAR_16(const uint16_t, g_scan4x4[NUM_SCAN_TYPE + 1][4 * 4]) =
{
{ 0, 4, 1, 8, 5, 2, 12, 9, 6, 3, 13, 10, 7, 14, 11, 15 },
{ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 },
{ 0, 4, 8, 12, 1, 5, 9, 13, 2, 6, 10, 14, 3, 7, 11, 15 },
{ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }
};
const uint16_t g_scan16x16[16 * 16] =
{
0, 16, 1, 32, 17, 2, 48, 33, 18, 3, 49, 34, 19, 50, 35, 51,
64, 80, 65, 96, 81, 66, 112, 97, 82, 67, 113, 98, 83, 114, 99, 115,
4, 20, 5, 36, 21, 6, 52, 37, 22, 7, 53, 38, 23, 54, 39, 55,
128, 144, 129, 160, 145, 130, 176, 161, 146, 131, 177, 162, 147, 178, 163, 179,
68, 84, 69, 100, 85, 70, 116, 101, 86, 71, 117, 102, 87, 118, 103, 119,
8, 24, 9, 40, 25, 10, 56, 41, 26, 11, 57, 42, 27, 58, 43, 59,
192,208, 193,224,209, 194,240,225,210, 195,241,226,211,242,227,243,
132, 148, 133, 164, 149, 134, 180, 165, 150, 135, 181, 166, 151, 182, 167, 183,
72, 88, 73, 104, 89, 74, 120, 105, 90, 75, 121, 106, 91, 122, 107, 123,
12, 28, 13, 44, 29, 14, 60, 45, 30, 15, 61, 46, 31, 62, 47, 63,
196,212, 197,228,213, 198,244,229,214, 199,245,230,215,246,231,247,
136, 152, 137, 168, 153, 138, 184, 169, 154, 139, 185, 170, 155, 186, 171, 187,
76, 92, 77, 108, 93, 78, 124, 109, 94, 79, 125, 110, 95, 126, 111, 127,
200,216,201,232,217,202,248,233,218,203,249,234,219,250,235,251,
140, 156, 141, 172, 157, 142, 188, 173, 158, 143, 189, 174, 159, 190, 175, 191,
204,220,205,236,221,206,252,237,222,207,253,238,223,254,239,255
};
const uint16_t g_scan8x8diag[8 * 8] =
{
0, 8, 1, 16, 9, 2, 24, 17,
10, 3, 32, 25, 18, 11, 4, 40,
33, 26, 19, 12, 5, 48, 41, 34,
27, 20, 13, 6, 56, 49, 42, 35,
28, 21, 14, 7, 57, 50, 43, 36,
29, 22, 15, 58, 51, 44, 37, 30,
23, 59, 52, 45, 38, 31, 60, 53,
46, 39, 61, 54, 47, 62, 55, 63
};
const uint16_t g_scan32x32[32 * 32] =
{
0,32,1,64,33,2,96,65,34,3,97,66,35,98,67,99,128,160,129,192,161,130,224,193,162,131,225,194,163,226,195,227,
4,36,5,68,37,6,100,69,38,7,101,70,39,102,71,103,256,288,257,320,289,258,352,321,290,259,353,322,291,354,323,355,
132,164,133,196,165,134,228,197,166,135,229,198,167,230,199,231,8,40,9,72,41,10,104,73,42,11,105,74,43,106,75,107,
384,416,385,448,417,386,480,449,418,387,481,450,419,482,451,483,260,292,261,324,293,262,356,325,294,263,357,326,295,358,327,359,
136,168,137,200,169,138,232,201,170,139,233,202,171,234,203,235,12,44,13,76,45,14,108,77,46,15,109,78,47,110,79,111,
512,544,513,576,545,514,608,577,546,515,609,578,547,610,579,611,388,420,389,452,421,390,484,453,422,391,485,454,423,486,455,487,
264,296,265,328,297,266,360,329,298,267,361,330,299,362,331,363,140,172,141,204,173,142,236,205,174,143,237,206,175,238,207,239,
16,48,17,80,49,18,112,81,50,19,113,82,51,114,83,115,640,672,641,704,673,642,736,705,674,643,737,706,675,738,707,739,
516,548,517,580,549,518,612,581,550,519,613,582,551,614,583,615,392,424,393,456,425,394,488,457,426,395,489,458,427,490,459,491,
268,300,269,332,301,270,364,333,302,271,365,334,303,366,335,367,144,176,145,208,177,146,240,209,178,147,241,210,179,242,211,243,
20,52,21,84,53,22,116,85,54,23,117,86,55,118,87,119,768,800,769,832,801,770,864,833,802,771,865,834,803,866,835,867,
644,676,645,708,677,646,740,709,678,647,741,710,679,742,711,743,520,552,521,584,553,522,616,585,554,523,617,586,555,618,587,619,
396,428,397,460,429,398,492,461,430,399,493,462,431,494,463,495,272,304,273,336,305,274,368,337,306,275,369,338,307,370,339,371,
148,180,149,212,181,150,244,213,182,151,245,214,183,246,215,247,24,56,25,88,57,26,120,89,58,27,121,90,59,122,91,123,
896,928,897,960,929,898,992,961,930,899,993,962,931,994,963,995,772,804,773,836,805,774,868,837,806,775,869,838,807,870,839,871,
648,680,649,712,681,650,744,713,682,651,745,714,683,746,715,747,524,556,525,588,557,526,620,589,558,527,621,590,559,622,591,623,
400,432,401,464,433,402,496,465,434,403,497,466,435,498,467,499,276,308,277,340,309,278,372,341,310,279,373,342,311,374,343,375,
152,184,153,216,185,154,248,217,186,155,249,218,187,250,219,251,28,60,29,92,61,30,124,93,62,31,125,94,63,126,95,127,
900,932,901,964,933,902,996,965,934,903,997,966,935,998,967,999,776,808,777,840,809,778,872,841,810,779,873,842,811,874,843,875,
652,684,653,716,685,654,748,717,686,655,749,718,687,750,719,751,528,560,529,592,561,530,624,593,562,531,625,594,563,626,595,627,
404,436,405,468,437,406,500,469,438,407,501,470,439,502,471,503,280,312,281,344,313,282,376,345,314,283,377,346,315,378,347,379,
156,188,157,220,189,158,252,221,190,159,253,222,191,254,223,255,904,936,905,968,937,906,1000,969,938,907,1001,970,939,1002,971,1003,
780,812,781,844,813,782,876,845,814,783,877,846,815,878,847,879,656,688,657,720,689,658,752,721,690,659,753,722,691,754,723,755,
532,564,533,596,565,534,628,597,566,535,629,598,567,630,599,631,408,440,409,472,441,410,504,473,442,411,505,474,443,506,475,507,
284,316,285,348,317,286,380,349,318,287,381,350,319,382,351,383,908,940,909,972,941,910,1004,973,942,911,1005,974,943,1006,975,1007,
784,816,785,848,817,786,880,849,818,787,881,850,819,882,851,883,660,692,661,724,693,662,756,725,694,663,757,726,695,758,727,759,
536,568,537,600,569,538,632,601,570,539,633,602,571,634,603,635,412,444,413,476,445,414,508,477,446,415,509,478,447,510,479,511,
912,944,913,976,945,914,1008,977,946,915,1009,978,947,1010,979,1011,788,820,789,852,821,790,884,853,822,791,885,854,823,886,855,887,
664,696,665,728,697,666,760,729,698,667,761,730,699,762,731,763,540,572,541,604,573,542,636,605,574,543,637,606,575,638,607,639,
916,948,917,980,949,918,1012,981,950,919,1013,982,951,1014,983,1015,792,824,793,856,825,794,888,857,826,795,889,858,827,890,859,891,
668,700,669,732,701,670,764,733,702,671,765,734,703,766,735,767,920,952,921,984,953,922,1016,985,954,923,1017,986,955,1018,987,1019,
796,828,797,860,829,798,892,861,830,799,893,862,831,894,863,895,924,956,925,988,957,926,1020,989,958,927,1021,990,959,1022,991,1023
};
const uint16_t* const g_scanOrder[NUM_SCAN_TYPE][NUM_SCAN_SIZE] =
{
{ g_scan4x4[0], g_scan8x8[0], g_scan16x16, g_scan32x32 },
{ g_scan4x4[1], g_scan8x8[1], g_scan16x16, g_scan32x32 },
{ g_scan4x4[2], g_scan8x8[2], g_scan16x16, g_scan32x32 }
};
const uint16_t* const g_scanOrderCG[NUM_SCAN_TYPE][NUM_SCAN_SIZE] =
{
{ g_scan4x4[0], g_scan2x2[0], g_scan4x4[0], g_scan8x8diag },
{ g_scan4x4[1], g_scan2x2[1], g_scan4x4[0], g_scan8x8diag },
{ g_scan4x4[2], g_scan2x2[0], g_scan4x4[0], g_scan8x8diag }
};
// Table used for encoding the last coefficient position. The index is the position.
// The low 4 bits are the number of "1" in the prefix and the high 4 bits are the number
// of bits in the suffix.
const uint8_t g_lastCoeffTable[32] =
{
0x00, 0x01, 0x02, 0x03, 0x14, 0x14, 0x15, 0x15,
0x26, 0x26, 0x26, 0x26, 0x27, 0x27, 0x27, 0x27,
0x38, 0x38, 0x38, 0x38, 0x38, 0x38, 0x38, 0x38,
0x39, 0x39, 0x39, 0x39, 0x39, 0x39, 0x39, 0x39,
};
// Rice parameters for absolute transform levels
const uint8_t g_goRiceRange[5] = { 7, 14, 26, 46, 78 };
const uint8_t g_lpsTable[64][4] =
{
{ 128, 176, 208, 240 },
{ 128, 167, 197, 227 },
{ 128, 158, 187, 216 },
{ 123, 150, 178, 205 },
{ 116, 142, 169, 195 },
{ 111, 135, 160, 185 },
{ 105, 128, 152, 175 },
{ 100, 122, 144, 166 },
{ 95, 116, 137, 158 },
{ 90, 110, 130, 150 },
{ 85, 104, 123, 142 },
{ 81, 99, 117, 135 },
{ 77, 94, 111, 128 },
{ 73, 89, 105, 122 },
{ 69, 85, 100, 116 },
{ 66, 80, 95, 110 },
{ 62, 76, 90, 104 },
{ 59, 72, 86, 99 },
{ 56, 69, 81, 94 },
{ 53, 65, 77, 89 },
{ 51, 62, 73, 85 },
{ 48, 59, 69, 80 },
{ 46, 56, 66, 76 },
{ 43, 53, 63, 72 },
{ 41, 50, 59, 69 },
{ 39, 48, 56, 65 },
{ 37, 45, 54, 62 },
{ 35, 43, 51, 59 },
{ 33, 41, 48, 56 },
{ 32, 39, 46, 53 },
{ 30, 37, 43, 50 },
{ 29, 35, 41, 48 },
{ 27, 33, 39, 45 },
{ 26, 31, 37, 43 },
{ 24, 30, 35, 41 },
{ 23, 28, 33, 39 },
{ 22, 27, 32, 37 },
{ 21, 26, 30, 35 },
{ 20, 24, 29, 33 },
{ 19, 23, 27, 31 },
{ 18, 22, 26, 30 },
{ 17, 21, 25, 28 },
{ 16, 20, 23, 27 },
{ 15, 19, 22, 25 },
{ 14, 18, 21, 24 },
{ 14, 17, 20, 23 },
{ 13, 16, 19, 22 },
{ 12, 15, 18, 21 },
{ 12, 14, 17, 20 },
{ 11, 14, 16, 19 },
{ 11, 13, 15, 18 },
{ 10, 12, 15, 17 },
{ 10, 12, 14, 16 },
{ 9, 11, 13, 15 },
{ 9, 11, 12, 14 },
{ 8, 10, 12, 14 },
{ 8, 9, 11, 13 },
{ 7, 9, 11, 12 },
{ 7, 9, 10, 12 },
{ 7, 8, 10, 11 },
{ 6, 8, 9, 11 },
{ 6, 7, 9, 10 },
{ 6, 7, 8, 9 },
{ 2, 2, 2, 2 }
};
const uint8_t x265_exp2_lut[64] =
{
0, 3, 6, 8, 11, 14, 17, 20, 23, 26, 29, 32, 36, 39, 42, 45,
48, 52, 55, 58, 62, 65, 69, 72, 76, 80, 83, 87, 91, 94, 98, 102,
106, 110, 114, 118, 122, 126, 130, 135, 139, 143, 147, 152, 156, 161, 165, 170,
175, 179, 184, 189, 194, 198, 203, 208, 214, 219, 224, 229, 234, 240, 245, 250
};
/* bFilter = g_intraFilterFlags[dir] & trSize */
const uint8_t g_intraFilterFlags[NUM_INTRA_MODE] =
{
0x38, 0x00,
0x38, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x20, 0x00, 0x20, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
0x38, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30, 0x20, 0x00, 0x20, 0x30, 0x30, 0x30, 0x30, 0x30, 0x30,
0x38,
};
/* Contains how much to increment shared depth buffer for different ctu sizes to get next best depth
* here, depth 0 = 64x64, depth 1 = 32x32, depth 2 = 16x16 and depth 3 = 8x8
* if ctu = 64, depth buffer size is 256 combination of depth values 0, 1, 2, 3
* if ctu = 32, depth buffer size is 64 combination of depth values 1, 2, 3
* if ctu = 16, depth buffer size is 16 combination of depth values 2, 3 */
const uint32_t g_depthInc[3][4] =
{
{ 16, 4, 0, 0},
{ 64, 16, 4, 1},
{256, 64, 16, 4}
};
/* g_depthScanIdx [y][x] */
const uint32_t g_depthScanIdx[8][8] =
{
{ 0, 1, 4, 5, 16, 17, 20, 21, },
{ 2, 3, 6, 7, 18, 19, 22, 23, },
{ 8, 9, 12, 13, 24, 25, 28, 29, },
{ 10, 11, 14, 15, 26, 27, 30, 31, },
{ 32, 33, 36, 37, 48, 49, 52, 53, },
{ 34, 35, 38, 39, 50, 51, 54, 55, },
{ 40, 41, 44, 45, 56, 57, 60, 61, },
{ 42, 43, 46, 47, 58, 59, 62, 63, }
};
}

103
x265/source/common/constants.h Normal file
View File

@ -0,0 +1,103 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_CONSTANTS_H
#define X265_CONSTANTS_H
#include "common.h"
namespace X265_NS {
// private namespace
extern int g_ctuSizeConfigured;
void initZscanToRaster(uint32_t maxFullDepth, uint32_t depth, uint32_t startVal, uint32_t*& curIdx);
void initRasterToZscan(uint32_t maxFullDepth);
extern double x265_lambda_tab[QP_MAX_MAX + 1];
extern double x265_lambda2_tab[QP_MAX_MAX + 1];
extern const uint16_t x265_chroma_lambda2_offset_tab[MAX_CHROMA_LAMBDA_OFFSET + 1];
enum { ChromaQPMappingTableSize = 70 };
enum { AngleMapping422TableSize = 36 };
extern const uint8_t g_chromaScale[ChromaQPMappingTableSize];
extern const uint8_t g_chroma422IntraAngleMappingTable[AngleMapping422TableSize];
// flexible conversion from relative to absolute index
extern uint32_t g_zscanToRaster[MAX_NUM_PARTITIONS];
extern uint32_t g_rasterToZscan[MAX_NUM_PARTITIONS];
// conversion of partition index to picture pel position
extern const uint8_t g_zscanToPelX[MAX_NUM_PARTITIONS];
extern const uint8_t g_zscanToPelY[MAX_NUM_PARTITIONS];
extern const uint8_t g_log2Size[MAX_CU_SIZE + 1]; // from size to log2(size)
// global variable (CTU width/height, max. CU depth)
extern uint32_t g_maxLog2CUSize;
extern uint32_t g_maxCUSize;
extern uint32_t g_maxCUDepth;
extern uint32_t g_unitSizeDepth; // Depth at which 4x4 unit occurs from max CU size
extern const int16_t g_t4[4][4];
extern const int16_t g_t8[8][8];
extern const int16_t g_t16[16][16];
extern const int16_t g_t32[32][32];
// Subpel interpolation defines and constants
#define NTAPS_LUMA 8 // Number of taps for luma
#define NTAPS_CHROMA 4 // Number of taps for chroma
#define IF_INTERNAL_PREC 14 // Number of bits for internal precision
#define IF_FILTER_PREC 6 // Log2 of sum of filter taps
#define IF_INTERNAL_OFFS (1 << (IF_INTERNAL_PREC - 1)) // Offset used internally
#define SLFASE_CONSTANT 0x5f4e4a53
extern const int16_t g_lumaFilter[4][NTAPS_LUMA]; // Luma filter taps
extern const int16_t g_chromaFilter[8][NTAPS_CHROMA]; // Chroma filter taps
// Scanning order & context mapping table
#define NUM_SCAN_SIZE 4
extern const uint16_t* const g_scanOrder[NUM_SCAN_TYPE][NUM_SCAN_SIZE];
extern const uint16_t* const g_scanOrderCG[NUM_SCAN_TYPE][NUM_SCAN_SIZE];
extern const uint16_t g_scan8x8diag[8 * 8];
extern const uint16_t g_scan4x4[NUM_SCAN_TYPE + 1][4 * 4]; // +1 for safe buffer area for codeCoeffNxN assembly optimize, there have up to 15 bytes beyond bound read
extern const uint8_t g_lastCoeffTable[32];
extern const uint8_t g_goRiceRange[5]; // maximum value coded with Rice codes
// CABAC tables
extern const uint8_t g_lpsTable[64][4];
extern const uint8_t x265_exp2_lut[64];
// Intra tables
extern const uint8_t g_intraFilterFlags[NUM_INTRA_MODE];
extern const uint32_t g_depthInc[3][4];
extern const uint32_t g_depthScanIdx[8][8];
}
#endif

311
x265/source/common/contexts.h Normal file
View File

@ -0,0 +1,311 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_CONTEXTS_H
#define X265_CONTEXTS_H
#include "common.h"
#define NUM_SPLIT_FLAG_CTX 3 // number of context models for split flag
#define NUM_SKIP_FLAG_CTX 3 // number of context models for skip flag
#define NUM_MERGE_FLAG_EXT_CTX 1 // number of context models for merge flag of merge extended
#define NUM_MERGE_IDX_EXT_CTX 1 // number of context models for merge index of merge extended
#define NUM_PART_SIZE_CTX 4 // number of context models for partition size
#define NUM_PRED_MODE_CTX 1 // number of context models for prediction mode
#define NUM_ADI_CTX 1 // number of context models for intra prediction
#define NUM_CHROMA_PRED_CTX 2 // number of context models for intra prediction (chroma)
#define NUM_INTER_DIR_CTX 5 // number of context models for inter prediction direction
#define NUM_MV_RES_CTX 2 // number of context models for motion vector difference
#define NUM_REF_NO_CTX 2 // number of context models for reference index
#define NUM_TRANS_SUBDIV_FLAG_CTX 3 // number of context models for transform subdivision flags
#define NUM_QT_CBF_CTX 7 // number of context models for QT CBF
#define NUM_QT_ROOT_CBF_CTX 1 // number of context models for QT ROOT CBF
#define NUM_DELTA_QP_CTX 3 // number of context models for dQP
#define NUM_SIG_CG_FLAG_CTX 2 // number of context models for MULTI_LEVEL_SIGNIFICANCE
#define NUM_SIG_FLAG_CTX 42 // number of context models for sig flag
#define NUM_SIG_FLAG_CTX_LUMA 27 // number of context models for luma sig flag
#define NUM_SIG_FLAG_CTX_CHROMA 15 // number of context models for chroma sig flag
#define NUM_CTX_LAST_FLAG_XY 18 // number of context models for last coefficient position
#define NUM_CTX_LAST_FLAG_XY_LUMA 15 // number of context models for last coefficient position of luma
#define NUM_CTX_LAST_FLAG_XY_CHROMA 3 // number of context models for last coefficient position of chroma
#define NUM_ONE_FLAG_CTX 24 // number of context models for greater than 1 flag
#define NUM_ONE_FLAG_CTX_LUMA 16 // number of context models for greater than 1 flag of luma
#define NUM_ONE_FLAG_CTX_CHROMA 8 // number of context models for greater than 1 flag of chroma
#define NUM_ABS_FLAG_CTX 6 // number of context models for greater than 2 flag
#define NUM_ABS_FLAG_CTX_LUMA 4 // number of context models for greater than 2 flag of luma
#define NUM_ABS_FLAG_CTX_CHROMA 2 // number of context models for greater than 2 flag of chroma
#define NUM_MVP_IDX_CTX 1 // number of context models for MVP index
#define NUM_SAO_MERGE_FLAG_CTX 1 // number of context models for SAO merge flags
#define NUM_SAO_TYPE_IDX_CTX 1 // number of context models for SAO type index
#define NUM_TRANSFORMSKIP_FLAG_CTX 1 // number of context models for transform skipping
#define NUM_TQUANT_BYPASS_FLAG_CTX 1
#define CNU 154 // dummy initialization value for unused context models 'Context model Not Used'
// Offset for context
#define OFF_SPLIT_FLAG_CTX (0)
#define OFF_SKIP_FLAG_CTX (OFF_SPLIT_FLAG_CTX + NUM_SPLIT_FLAG_CTX)
#define OFF_MERGE_FLAG_EXT_CTX (OFF_SKIP_FLAG_CTX + NUM_SKIP_FLAG_CTX)
#define OFF_MERGE_IDX_EXT_CTX (OFF_MERGE_FLAG_EXT_CTX + NUM_MERGE_FLAG_EXT_CTX)
#define OFF_PART_SIZE_CTX (OFF_MERGE_IDX_EXT_CTX + NUM_MERGE_IDX_EXT_CTX)
#define OFF_PRED_MODE_CTX (OFF_PART_SIZE_CTX + NUM_PART_SIZE_CTX)
#define OFF_ADI_CTX (OFF_PRED_MODE_CTX + NUM_PRED_MODE_CTX)
#define OFF_CHROMA_PRED_CTX (OFF_ADI_CTX + NUM_ADI_CTX)
#define OFF_DELTA_QP_CTX (OFF_CHROMA_PRED_CTX + NUM_CHROMA_PRED_CTX)
#define OFF_INTER_DIR_CTX (OFF_DELTA_QP_CTX + NUM_DELTA_QP_CTX)
#define OFF_REF_NO_CTX (OFF_INTER_DIR_CTX + NUM_INTER_DIR_CTX)
#define OFF_MV_RES_CTX (OFF_REF_NO_CTX + NUM_REF_NO_CTX)
#define OFF_QT_CBF_CTX (OFF_MV_RES_CTX + NUM_MV_RES_CTX)
#define OFF_TRANS_SUBDIV_FLAG_CTX (OFF_QT_CBF_CTX + NUM_QT_CBF_CTX)
#define OFF_QT_ROOT_CBF_CTX (OFF_TRANS_SUBDIV_FLAG_CTX + NUM_TRANS_SUBDIV_FLAG_CTX)
#define OFF_SIG_CG_FLAG_CTX (OFF_QT_ROOT_CBF_CTX + NUM_QT_ROOT_CBF_CTX)
#define OFF_SIG_FLAG_CTX (OFF_SIG_CG_FLAG_CTX + 2 * NUM_SIG_CG_FLAG_CTX)
#define OFF_CTX_LAST_FLAG_X (OFF_SIG_FLAG_CTX + NUM_SIG_FLAG_CTX)
#define OFF_CTX_LAST_FLAG_Y (OFF_CTX_LAST_FLAG_X + NUM_CTX_LAST_FLAG_XY)
#define OFF_ONE_FLAG_CTX (OFF_CTX_LAST_FLAG_Y + NUM_CTX_LAST_FLAG_XY)
#define OFF_ABS_FLAG_CTX (OFF_ONE_FLAG_CTX + NUM_ONE_FLAG_CTX)
#define OFF_MVP_IDX_CTX (OFF_ABS_FLAG_CTX + NUM_ABS_FLAG_CTX)
#define OFF_SAO_MERGE_FLAG_CTX (OFF_MVP_IDX_CTX + NUM_MVP_IDX_CTX)
#define OFF_SAO_TYPE_IDX_CTX (OFF_SAO_MERGE_FLAG_CTX + NUM_SAO_MERGE_FLAG_CTX)
#define OFF_TRANSFORMSKIP_FLAG_CTX (OFF_SAO_TYPE_IDX_CTX + NUM_SAO_TYPE_IDX_CTX)
#define OFF_TQUANT_BYPASS_FLAG_CTX (OFF_TRANSFORMSKIP_FLAG_CTX + 2 * NUM_TRANSFORMSKIP_FLAG_CTX)
#define MAX_OFF_CTX_MOD (OFF_TQUANT_BYPASS_FLAG_CTX + NUM_TQUANT_BYPASS_FLAG_CTX)
extern "C" const uint32_t PFX(entropyStateBits)[128];
namespace X265_NS {
// private namespace
extern const uint32_t g_entropyBits[128];
extern const uint8_t g_nextState[128][2];
#define sbacGetMps(S) ((S) & 1)
#define sbacGetState(S) ((S) >> 1)
#define sbacNext(S, V) (g_nextState[(S)][(V)])
#define sbacGetEntropyBits(S, V) (g_entropyBits[(S) ^ (V)])
#define sbacGetEntropyBitsTrm(V) (g_entropyBits[126 ^ (V)])
#define MAX_NUM_CHANNEL_TYPE 2
static const uint32_t ctxCbf[3][5] = { { 1, 0, 0, 0, 0 }, { 2, 3, 4, 5, 6 }, { 2, 3, 4, 5, 6 } };
static const uint32_t significanceMapContextSetStart[MAX_NUM_CHANNEL_TYPE][3] = { { 0, 9, 21 }, { 0, 9, 12 } };
static const uint32_t significanceMapContextSetSize[MAX_NUM_CHANNEL_TYPE][3] = { { 9, 12, 6 }, { 9, 3, 3 } };
static const uint32_t nonDiagonalScan8x8ContextOffset[MAX_NUM_CHANNEL_TYPE] = { 6, 0 };
static const uint32_t notFirstGroupNeighbourhoodContextOffset[MAX_NUM_CHANNEL_TYPE] = { 3, 0 };
// initial probability for cu_transquant_bypass flag
static const uint8_t INIT_CU_TRANSQUANT_BYPASS_FLAG[3][NUM_TQUANT_BYPASS_FLAG_CTX] =
{
{ 154 },
{ 154 },
{ 154 },
};
// initial probability for split flag
static const uint8_t INIT_SPLIT_FLAG[3][NUM_SPLIT_FLAG_CTX] =
{
{ 107, 139, 126, },
{ 107, 139, 126, },
{ 139, 141, 157, },
};
static const uint8_t INIT_SKIP_FLAG[3][NUM_SKIP_FLAG_CTX] =
{
{ 197, 185, 201, },
{ 197, 185, 201, },
{ CNU, CNU, CNU, },
};
static const uint8_t INIT_MERGE_FLAG_EXT[3][NUM_MERGE_FLAG_EXT_CTX] =
{
{ 154, },
{ 110, },
{ CNU, },
};
static const uint8_t INIT_MERGE_IDX_EXT[3][NUM_MERGE_IDX_EXT_CTX] =
{
{ 137, },
{ 122, },
{ CNU, },
};
static const uint8_t INIT_PART_SIZE[3][NUM_PART_SIZE_CTX] =
{
{ 154, 139, 154, 154 },
{ 154, 139, 154, 154 },
{ 184, CNU, CNU, CNU },
};
static const uint8_t INIT_PRED_MODE[3][NUM_PRED_MODE_CTX] =
{
{ 134, },
{ 149, },
{ CNU, },
};
static const uint8_t INIT_INTRA_PRED_MODE[3][NUM_ADI_CTX] =
{
{ 183, },
{ 154, },
{ 184, },
};
static const uint8_t INIT_CHROMA_PRED_MODE[3][NUM_CHROMA_PRED_CTX] =
{
{ 152, 139, },
{ 152, 139, },
{ 63, 139, },
};
static const uint8_t INIT_INTER_DIR[3][NUM_INTER_DIR_CTX] =
{
{ 95, 79, 63, 31, 31, },
{ 95, 79, 63, 31, 31, },
{ CNU, CNU, CNU, CNU, CNU, },
};
static const uint8_t INIT_MVD[3][NUM_MV_RES_CTX] =
{
{ 169, 198, },
{ 140, 198, },
{ CNU, CNU, },
};
static const uint8_t INIT_REF_PIC[3][NUM_REF_NO_CTX] =
{
{ 153, 153 },
{ 153, 153 },
{ CNU, CNU },
};
static const uint8_t INIT_DQP[3][NUM_DELTA_QP_CTX] =
{
{ 154, 154, 154, },
{ 154, 154, 154, },
{ 154, 154, 154, },
};
static const uint8_t INIT_QT_CBF[3][NUM_QT_CBF_CTX] =
{
{ 153, 111, 149, 92, 167, 154, 154 },
{ 153, 111, 149, 107, 167, 154, 154 },
{ 111, 141, 94, 138, 182, 154, 154 },
};
static const uint8_t INIT_QT_ROOT_CBF[3][NUM_QT_ROOT_CBF_CTX] =
{
{ 79, },
{ 79, },
{ CNU, },
};
static const uint8_t INIT_LAST[3][NUM_CTX_LAST_FLAG_XY] =
{
{ 125, 110, 124, 110, 95, 94, 125, 111, 111, 79, 125, 126, 111, 111, 79,
108, 123, 93 },
{ 125, 110, 94, 110, 95, 79, 125, 111, 110, 78, 110, 111, 111, 95, 94,
108, 123, 108 },
{ 110, 110, 124, 125, 140, 153, 125, 127, 140, 109, 111, 143, 127, 111, 79,
108, 123, 63 },
};
static const uint8_t INIT_SIG_CG_FLAG[3][2 * NUM_SIG_CG_FLAG_CTX] =
{
{ 121, 140,
61, 154, },
{ 121, 140,
61, 154, },
{ 91, 171,
134, 141, },
};
static const uint8_t INIT_SIG_FLAG[3][NUM_SIG_FLAG_CTX] =
{
{ 170, 154, 139, 153, 139, 123, 123, 63, 124, 166, 183, 140, 136, 153, 154, 166, 183, 140, 136, 153, 154, 166, 183, 140, 136, 153, 154, 170, 153, 138, 138, 122, 121, 122, 121, 167, 151, 183, 140, 151, 183, 140, },
{ 155, 154, 139, 153, 139, 123, 123, 63, 153, 166, 183, 140, 136, 153, 154, 166, 183, 140, 136, 153, 154, 166, 183, 140, 136, 153, 154, 170, 153, 123, 123, 107, 121, 107, 121, 167, 151, 183, 140, 151, 183, 140, },
{ 111, 111, 125, 110, 110, 94, 124, 108, 124, 107, 125, 141, 179, 153, 125, 107, 125, 141, 179, 153, 125, 107, 125, 141, 179, 153, 125, 140, 139, 182, 182, 152, 136, 152, 136, 153, 136, 139, 111, 136, 139, 111, },
};
static const uint8_t INIT_ONE_FLAG[3][NUM_ONE_FLAG_CTX] =
{
{ 154, 196, 167, 167, 154, 152, 167, 182, 182, 134, 149, 136, 153, 121, 136, 122, 169, 208, 166, 167, 154, 152, 167, 182, },
{ 154, 196, 196, 167, 154, 152, 167, 182, 182, 134, 149, 136, 153, 121, 136, 137, 169, 194, 166, 167, 154, 167, 137, 182, },
{ 140, 92, 137, 138, 140, 152, 138, 139, 153, 74, 149, 92, 139, 107, 122, 152, 140, 179, 166, 182, 140, 227, 122, 197, },
};
static const uint8_t INIT_ABS_FLAG[3][NUM_ABS_FLAG_CTX] =
{
{ 107, 167, 91, 107, 107, 167, },
{ 107, 167, 91, 122, 107, 167, },
{ 138, 153, 136, 167, 152, 152, },
};
static const uint8_t INIT_MVP_IDX[3][NUM_MVP_IDX_CTX] =
{
{ 168 },
{ 168 },
{ CNU },
};
static const uint8_t INIT_SAO_MERGE_FLAG[3][NUM_SAO_MERGE_FLAG_CTX] =
{
{ 153, },
{ 153, },
{ 153, },
};
static const uint8_t INIT_SAO_TYPE_IDX[3][NUM_SAO_TYPE_IDX_CTX] =
{
{ 160, },
{ 185, },
{ 200, },
};
static const uint8_t INIT_TRANS_SUBDIV_FLAG[3][NUM_TRANS_SUBDIV_FLAG_CTX] =
{
{ 224, 167, 122, },
{ 124, 138, 94, },
{ 153, 138, 138, },
};
static const uint8_t INIT_TRANSFORMSKIP_FLAG[3][2 * NUM_TRANSFORMSKIP_FLAG_CTX] =
{
{ 139, 139 },
{ 139, 139 },
{ 139, 139 },
};
}
#endif // ifndef X265_CONTEXTS_H

374
x265/source/common/cpu.cpp Normal file
View File

@ -0,0 +1,374 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Loren Merritt <lorenm@u.washington.edu>
* Laurent Aimar <fenrir@via.ecp.fr>
* Fiona Glaser <fiona@x264.com>
* Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "cpu.h"
#include "common.h"
#if MACOS || SYS_FREEBSD
#include <sys/types.h>
#include <sys/sysctl.h>
#endif
#if SYS_OPENBSD
#include <sys/param.h>
#include <sys/sysctl.h>
#include <machine/cpu.h>
#endif
#if X265_ARCH_ARM && !defined(HAVE_NEON)
#include <signal.h>
#include <setjmp.h>
static sigjmp_buf jmpbuf;
static volatile sig_atomic_t canjump = 0;
static void sigill_handler(int sig)
{
if (!canjump)
{
signal(sig, SIG_DFL);
raise(sig);
}
canjump = 0;
siglongjmp(jmpbuf, 1);
}
#endif // if X265_ARCH_ARM
namespace X265_NS {
const cpu_name_t cpu_names[] =
{
#if X265_ARCH_X86
#define MMX2 X265_CPU_MMX | X265_CPU_MMX2 | X265_CPU_CMOV
{ "MMX2", MMX2 },
{ "MMXEXT", MMX2 },
{ "SSE", MMX2 | X265_CPU_SSE },
#define SSE2 MMX2 | X265_CPU_SSE | X265_CPU_SSE2
{ "SSE2Slow", SSE2 | X265_CPU_SSE2_IS_SLOW },
{ "SSE2", SSE2 },
{ "SSE2Fast", SSE2 | X265_CPU_SSE2_IS_FAST },
{ "SSE3", SSE2 | X265_CPU_SSE3 },
{ "SSSE3", SSE2 | X265_CPU_SSE3 | X265_CPU_SSSE3 },
{ "SSE4.1", SSE2 | X265_CPU_SSE3 | X265_CPU_SSSE3 | X265_CPU_SSE4 },
{ "SSE4", SSE2 | X265_CPU_SSE3 | X265_CPU_SSSE3 | X265_CPU_SSE4 },
{ "SSE4.2", SSE2 | X265_CPU_SSE3 | X265_CPU_SSSE3 | X265_CPU_SSE4 | X265_CPU_SSE42 },
#define AVX SSE2 | X265_CPU_SSE3 | X265_CPU_SSSE3 | X265_CPU_SSE4 | X265_CPU_SSE42 | X265_CPU_AVX
{ "AVX", AVX },
{ "XOP", AVX | X265_CPU_XOP },
{ "FMA4", AVX | X265_CPU_FMA4 },
{ "AVX2", AVX | X265_CPU_AVX2 },
{ "FMA3", AVX | X265_CPU_FMA3 },
#undef AVX
#undef SSE2
#undef MMX2
{ "Cache32", X265_CPU_CACHELINE_32 },
{ "Cache64", X265_CPU_CACHELINE_64 },
{ "LZCNT", X265_CPU_LZCNT },
{ "BMI1", X265_CPU_BMI1 },
{ "BMI2", X265_CPU_BMI1 | X265_CPU_BMI2 },
{ "SlowCTZ", X265_CPU_SLOW_CTZ },
{ "SlowAtom", X265_CPU_SLOW_ATOM },
{ "SlowPshufb", X265_CPU_SLOW_PSHUFB },
{ "SlowPalignr", X265_CPU_SLOW_PALIGNR },
{ "SlowShuffle", X265_CPU_SLOW_SHUFFLE },
{ "UnalignedStack", X265_CPU_STACK_MOD4 },
#elif X265_ARCH_ARM
{ "ARMv6", X265_CPU_ARMV6 },
{ "NEON", X265_CPU_NEON },
{ "FastNeonMRC", X265_CPU_FAST_NEON_MRC },
#endif // if X265_ARCH_X86
{ "", 0 },
};
#if X265_ARCH_X86
extern "C" {
/* cpu-a.asm */
int PFX(cpu_cpuid_test)(void);
void PFX(cpu_cpuid)(uint32_t op, uint32_t *eax, uint32_t *ebx, uint32_t *ecx, uint32_t *edx);
void PFX(cpu_xgetbv)(uint32_t op, uint32_t *eax, uint32_t *edx);
}
#if defined(_MSC_VER)
#pragma warning(disable: 4309) // truncation of constant value
#endif
uint32_t cpu_detect(void)
{
uint32_t cpu = 0;
uint32_t eax, ebx, ecx, edx;
uint32_t vendor[4] = { 0 };
uint32_t max_extended_cap, max_basic_cap;
#if !X86_64
if (!PFX(cpu_cpuid_test)())
return 0;
#endif
PFX(cpu_cpuid)(0, &eax, vendor + 0, vendor + 2, vendor + 1);
max_basic_cap = eax;
if (max_basic_cap == 0)
return 0;
PFX(cpu_cpuid)(1, &eax, &ebx, &ecx, &edx);
if (edx & 0x00800000)
cpu |= X265_CPU_MMX;
else
return cpu;
if (edx & 0x02000000)
cpu |= X265_CPU_MMX2 | X265_CPU_SSE;
if (edx & 0x00008000)
cpu |= X265_CPU_CMOV;
else
return cpu;
if (edx & 0x04000000)
cpu |= X265_CPU_SSE2;
if (ecx & 0x00000001)
cpu |= X265_CPU_SSE3;
if (ecx & 0x00000200)
cpu |= X265_CPU_SSSE3;
if (ecx & 0x00080000)
cpu |= X265_CPU_SSE4;
if (ecx & 0x00100000)
cpu |= X265_CPU_SSE42;
/* Check OXSAVE and AVX bits */
if ((ecx & 0x18000000) == 0x18000000)
{
/* Check for OS support */
PFX(cpu_xgetbv)(0, &eax, &edx);
if ((eax & 0x6) == 0x6)
{
cpu |= X265_CPU_AVX;
if (ecx & 0x00001000)
cpu |= X265_CPU_FMA3;
}
}
if (max_basic_cap >= 7)
{
PFX(cpu_cpuid)(7, &eax, &ebx, &ecx, &edx);
/* AVX2 requires OS support, but BMI1/2 don't. */
if ((cpu & X265_CPU_AVX) && (ebx & 0x00000020))
cpu |= X265_CPU_AVX2;
if (ebx & 0x00000008)
{
cpu |= X265_CPU_BMI1;
if (ebx & 0x00000100)
cpu |= X265_CPU_BMI2;
}
}
if (cpu & X265_CPU_SSSE3)
cpu |= X265_CPU_SSE2_IS_FAST;
PFX(cpu_cpuid)(0x80000000, &eax, &ebx, &ecx, &edx);
max_extended_cap = eax;
if (max_extended_cap >= 0x80000001)
{
PFX(cpu_cpuid)(0x80000001, &eax, &ebx, &ecx, &edx);
if (ecx & 0x00000020)
cpu |= X265_CPU_LZCNT; /* Supported by Intel chips starting with Haswell */
if (ecx & 0x00000040) /* SSE4a, AMD only */
{
int family = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
cpu |= X265_CPU_SSE2_IS_FAST; /* Phenom and later CPUs have fast SSE units */
if (family == 0x14)
{
cpu &= ~X265_CPU_SSE2_IS_FAST; /* SSSE3 doesn't imply fast SSE anymore... */
cpu |= X265_CPU_SSE2_IS_SLOW; /* Bobcat has 64-bit SIMD units */
cpu |= X265_CPU_SLOW_PALIGNR; /* palignr is insanely slow on Bobcat */
}
if (family == 0x16)
{
cpu |= X265_CPU_SLOW_PSHUFB; /* Jaguar's pshufb isn't that slow, but it's slow enough
* compared to alternate instruction sequences that this
* is equal or faster on almost all such functions. */
}
}
if (cpu & X265_CPU_AVX)
{
if (ecx & 0x00000800) /* XOP */
cpu |= X265_CPU_XOP;
if (ecx & 0x00010000) /* FMA4 */
cpu |= X265_CPU_FMA4;
}
if (!strcmp((char*)vendor, "AuthenticAMD"))
{
if (edx & 0x00400000)
cpu |= X265_CPU_MMX2;
if (!(cpu & X265_CPU_LZCNT))
cpu |= X265_CPU_SLOW_CTZ;
if ((cpu & X265_CPU_SSE2) && !(cpu & X265_CPU_SSE2_IS_FAST))
cpu |= X265_CPU_SSE2_IS_SLOW; /* AMD CPUs come in two types: terrible at SSE and great at it */
}
}
if (!strcmp((char*)vendor, "GenuineIntel"))
{
PFX(cpu_cpuid)(1, &eax, &ebx, &ecx, &edx);
int family = ((eax >> 8) & 0xf) + ((eax >> 20) & 0xff);
int model = ((eax >> 4) & 0xf) + ((eax >> 12) & 0xf0);
if (family == 6)
{
/* 6/9 (pentium-m "banias"), 6/13 (pentium-m "dothan"), and 6/14 (core1 "yonah")
* theoretically support sse2, but it's significantly slower than mmx for
* almost all of x264's functions, so let's just pretend they don't. */
if (model == 9 || model == 13 || model == 14)
{
cpu &= ~(X265_CPU_SSE2 | X265_CPU_SSE3);
X265_CHECK(!(cpu & (X265_CPU_SSSE3 | X265_CPU_SSE4)), "unexpected CPU ID %d\n", cpu);
}
/* Detect Atom CPU */
else if (model == 28)
{
cpu |= X265_CPU_SLOW_ATOM;
cpu |= X265_CPU_SLOW_CTZ;
cpu |= X265_CPU_SLOW_PSHUFB;
}
/* Conroe has a slow shuffle unit. Check the model number to make sure not
* to include crippled low-end Penryns and Nehalems that don't have SSE4. */
else if ((cpu & X265_CPU_SSSE3) && !(cpu & X265_CPU_SSE4) && model < 23)
cpu |= X265_CPU_SLOW_SHUFFLE;
}
}
if ((!strcmp((char*)vendor, "GenuineIntel") || !strcmp((char*)vendor, "CyrixInstead")) && !(cpu & X265_CPU_SSE42))
{
/* cacheline size is specified in 3 places, any of which may be missing */
PFX(cpu_cpuid)(1, &eax, &ebx, &ecx, &edx);
int cache = (ebx & 0xff00) >> 5; // cflush size
if (!cache && max_extended_cap >= 0x80000006)
{
PFX(cpu_cpuid)(0x80000006, &eax, &ebx, &ecx, &edx);
cache = ecx & 0xff; // cacheline size
}
if (!cache && max_basic_cap >= 2)
{
// Cache and TLB Information
static const char cache32_ids[] = { 0x0a, 0x0c, 0x41, 0x42, 0x43, 0x44, 0x45, 0x82, 0x83, 0x84, 0x85, 0 };
static const char cache64_ids[] = { 0x22, 0x23, 0x25, 0x29, 0x2c, 0x46, 0x47, 0x49, 0x60, 0x66, 0x67,
0x68, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7c, 0x7f, 0x86, 0x87, 0 };
uint32_t buf[4];
int max, i = 0;
do
{
PFX(cpu_cpuid)(2, buf + 0, buf + 1, buf + 2, buf + 3);
max = buf[0] & 0xff;
buf[0] &= ~0xff;
for (int j = 0; j < 4; j++)
{
if (!(buf[j] >> 31))
while (buf[j])
{
if (strchr(cache32_ids, buf[j] & 0xff))
cache = 32;
if (strchr(cache64_ids, buf[j] & 0xff))
cache = 64;
buf[j] >>= 8;
}
}
}
while (++i < max);
}
if (cache == 32)
cpu |= X265_CPU_CACHELINE_32;
else if (cache == 64)
cpu |= X265_CPU_CACHELINE_64;
else
x265_log(NULL, X265_LOG_WARNING, "unable to determine cacheline size\n");
}
#if BROKEN_STACK_ALIGNMENT
cpu |= X265_CPU_STACK_MOD4;
#endif
return cpu;
}
#elif X265_ARCH_ARM
extern "C" {
void PFX(cpu_neon_test)(void);
int PFX(cpu_fast_neon_mrc_test)(void);
}
uint32_t cpu_detect(void)
{
int flags = 0;
#if HAVE_ARMV6
flags |= X265_CPU_ARMV6;
// don't do this hack if compiled with -mfpu=neon
#if !HAVE_NEON
static void (* oldsig)(int);
oldsig = signal(SIGILL, sigill_handler);
if (sigsetjmp(jmpbuf, 1))
{
signal(SIGILL, oldsig);
return flags;
}
canjump = 1;
PFX(cpu_neon_test)();
canjump = 0;
signal(SIGILL, oldsig);
#endif // if !HAVE_NEON
flags |= X265_CPU_NEON;
// fast neon -> arm (Cortex-A9) detection relies on user access to the
// cycle counter; this assumes ARMv7 performance counters.
// NEON requires at least ARMv7, ARMv8 may require changes here, but
// hopefully this hacky detection method will have been replaced by then.
// Note that there is potential for a race condition if another program or
// x264 instance disables or reinits the counters while x264 is using them,
// which may result in incorrect detection and the counters stuck enabled.
// right now Apple does not seem to support performance counters for this test
#ifndef __MACH__
flags |= PFX(cpu_fast_neon_mrc_test)() ? X265_CPU_FAST_NEON_MRC : 0;
#endif
// TODO: write dual issue test? currently it's A8 (dual issue) vs. A9 (fast mrc)
#endif // if HAVE_ARMV6
return flags;
}
#else // if X265_ARCH_X86
uint32_t cpu_detect(void)
{
return 0;
}
#endif // if X265_ARCH_X86
}

64
x265/source/common/cpu.h Normal file
View File

@ -0,0 +1,64 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Loren Merritt <lorenm@u.washington.edu>
* Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_CPU_H
#define X265_CPU_H
#include "common.h"
/* All assembly functions are prefixed with X265_NS (macro expanded) */
#define PFX3(prefix, name) prefix ## _ ## name
#define PFX2(prefix, name) PFX3(prefix, name)
#define PFX(name) PFX2(X265_NS, name)
// from cpu-a.asm, if ASM primitives are compiled, else primitives.cpp
extern "C" void PFX(cpu_emms)(void);
extern "C" void PFX(safe_intel_cpu_indicator_init)(void);
#if _MSC_VER && _WIN64
#define x265_emms() PFX(cpu_emms)()
#elif _MSC_VER
#include <mmintrin.h>
#define x265_emms() _mm_empty()
#elif __GNUC__
// Cannot use _mm_empty() directly without compiling all the source with
// a fixed CPU arch, which we would like to avoid at the moment
#define x265_emms() PFX(cpu_emms)()
#else
#define x265_emms() PFX(cpu_emms)()
#endif
namespace X265_NS {
uint32_t cpu_detect(void);
struct cpu_name_t
{
char name[16];
uint32_t flags;
};
extern const cpu_name_t cpu_names[];
}
#endif // ifndef X265_CPU_H

2035
x265/source/common/cudata.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

362
x265/source/common/cudata.h Normal file
View File

@ -0,0 +1,362 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_CUDATA_H
#define X265_CUDATA_H
#include "common.h"
#include "slice.h"
#include "mv.h"
namespace X265_NS {
// private namespace
class FrameData;
class Slice;
struct TUEntropyCodingParameters;
struct CUDataMemPool;
enum PartSize
{
SIZE_2Nx2N, // symmetric motion partition, 2Nx2N
SIZE_2NxN, // symmetric motion partition, 2Nx N
SIZE_Nx2N, // symmetric motion partition, Nx2N
SIZE_NxN, // symmetric motion partition, Nx N
SIZE_2NxnU, // asymmetric motion partition, 2Nx( N/2) + 2Nx(3N/2)
SIZE_2NxnD, // asymmetric motion partition, 2Nx(3N/2) + 2Nx( N/2)
SIZE_nLx2N, // asymmetric motion partition, ( N/2)x2N + (3N/2)x2N
SIZE_nRx2N, // asymmetric motion partition, (3N/2)x2N + ( N/2)x2N
NUM_SIZES
};
enum PredMode
{
MODE_NONE = 0,
MODE_INTER = (1 << 0),
MODE_INTRA = (1 << 1),
MODE_SKIP = (1 << 2) | MODE_INTER
};
// motion vector predictor direction used in AMVP
enum MVP_DIR
{
MD_LEFT = 0, // MVP of left block
MD_ABOVE, // MVP of above block
MD_ABOVE_RIGHT, // MVP of above right block
MD_BELOW_LEFT, // MVP of below left block
MD_ABOVE_LEFT, // MVP of above left block
MD_COLLOCATED // MVP of temporal neighbour
};
struct CUGeom
{
enum {
INTRA = 1<<0, // CU is intra predicted
PRESENT = 1<<1, // CU is not completely outside the frame
SPLIT_MANDATORY = 1<<2, // CU split is mandatory if CU is inside frame and can be split
LEAF = 1<<3, // CU is a leaf node of the CTU
SPLIT = 1<<4, // CU is currently split in four child CUs.
};
// (1 + 4 + 16 + 64) = 85.
enum { MAX_GEOMS = 85 };
uint32_t log2CUSize; // Log of the CU size.
uint32_t childOffset; // offset of the first child CU from current CU
uint32_t absPartIdx; // Part index of this CU in terms of 4x4 blocks.
uint32_t numPartitions; // Number of 4x4 blocks in the CU
uint32_t flags; // CU flags.
uint32_t depth; // depth of this CU relative from CTU
};
struct MVField
{
MV mv;
int refIdx;
};
// Structure that keeps the neighbour's MV information.
struct InterNeighbourMV
{
// Neighbour MV. The index represents the list.
MV mv[2];
// Collocated right bottom CU addr.
uint32_t cuAddr[2];
// For spatial prediction, this field contains the reference index
// in each list (-1 if not available).
//
// For temporal prediction, the first value is used for the
// prediction with list 0. The second value is used for the prediction
// with list 1. For each value, the first four bits are the reference index
// associated to the PMV, and the fifth bit is the list associated to the PMV.
// if both reference indices are -1, then unifiedRef is also -1
union { int16_t refIdx[2]; int32_t unifiedRef; };
};
typedef void(*cucopy_t)(uint8_t* dst, uint8_t* src); // dst and src are aligned to MIN(size, 32)
typedef void(*cubcast_t)(uint8_t* dst, uint8_t val); // dst is aligned to MIN(size, 32)
// Partition count table, index represents partitioning mode.
const uint32_t nbPartsTable[8] = { 1, 2, 2, 4, 2, 2, 2, 2 };
// Partition table.
// First index is partitioning mode. Second index is partition index.
// Third index is 0 for partition sizes, 1 for partition offsets. The
// sizes and offsets are encoded as two packed 4-bit values (X,Y).
// X and Y represent 1/4 fractions of the block size.
const uint32_t partTable[8][4][2] =
{
// XY
{ { 0x44, 0x00 }, { 0x00, 0x00 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_2Nx2N.
{ { 0x42, 0x00 }, { 0x42, 0x02 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_2NxN.
{ { 0x24, 0x00 }, { 0x24, 0x20 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_Nx2N.
{ { 0x22, 0x00 }, { 0x22, 0x20 }, { 0x22, 0x02 }, { 0x22, 0x22 } }, // SIZE_NxN.
{ { 0x41, 0x00 }, { 0x43, 0x01 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_2NxnU.
{ { 0x43, 0x00 }, { 0x41, 0x03 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_2NxnD.
{ { 0x14, 0x00 }, { 0x34, 0x10 }, { 0x00, 0x00 }, { 0x00, 0x00 } }, // SIZE_nLx2N.
{ { 0x34, 0x00 }, { 0x14, 0x30 }, { 0x00, 0x00 }, { 0x00, 0x00 } } // SIZE_nRx2N.
};
// Partition Address table.
// First index is partitioning mode. Second index is partition address.
const uint32_t partAddrTable[8][4] =
{
{ 0x00, 0x00, 0x00, 0x00 }, // SIZE_2Nx2N.
{ 0x00, 0x08, 0x08, 0x08 }, // SIZE_2NxN.
{ 0x00, 0x04, 0x04, 0x04 }, // SIZE_Nx2N.
{ 0x00, 0x04, 0x08, 0x0C }, // SIZE_NxN.
{ 0x00, 0x02, 0x02, 0x02 }, // SIZE_2NxnU.
{ 0x00, 0x0A, 0x0A, 0x0A }, // SIZE_2NxnD.
{ 0x00, 0x01, 0x01, 0x01 }, // SIZE_nLx2N.
{ 0x00, 0x05, 0x05, 0x05 } // SIZE_nRx2N.
};
// Holds part data for a CU of a given size, from an 8x8 CU to a CTU
class CUData
{
public:
static cubcast_t s_partSet[NUM_FULL_DEPTH]; // pointer to broadcast set functions per absolute depth
static uint32_t s_numPartInCUSize;
FrameData* m_encData;
const Slice* m_slice;
cucopy_t m_partCopy; // pointer to function that copies m_numPartitions elements
cubcast_t m_partSet; // pointer to function that sets m_numPartitions elements
cucopy_t m_subPartCopy; // pointer to function that copies m_numPartitions/4 elements, may be NULL
cubcast_t m_subPartSet; // pointer to function that sets m_numPartitions/4 elements, may be NULL
uint32_t m_cuAddr; // address of CTU within the picture in raster order
uint32_t m_absIdxInCTU; // address of CU within its CTU in Z scan order
uint32_t m_cuPelX; // CU position within the picture, in pixels (X)
uint32_t m_cuPelY; // CU position within the picture, in pixels (Y)
uint32_t m_numPartitions; // maximum number of 4x4 partitions within this CU
uint32_t m_chromaFormat;
uint32_t m_hChromaShift;
uint32_t m_vChromaShift;
/* Per-part data, stored contiguously */
int8_t* m_qp; // array of QP values
uint8_t* m_log2CUSize; // array of cu log2Size TODO: seems redundant to depth
uint8_t* m_lumaIntraDir; // array of intra directions (luma)
uint8_t* m_tqBypass; // array of CU lossless flags
int8_t* m_refIdx[2]; // array of motion reference indices per list
uint8_t* m_cuDepth; // array of depths
uint8_t* m_predMode; // array of prediction modes
uint8_t* m_partSize; // array of partition sizes
uint8_t* m_mergeFlag; // array of merge flags
uint8_t* m_interDir; // array of inter directions
uint8_t* m_mvpIdx[2]; // array of motion vector predictor candidates or merge candidate indices [0]
uint8_t* m_tuDepth; // array of transform indices
uint8_t* m_transformSkip[3]; // array of transform skipping flags per plane
uint8_t* m_cbf[3]; // array of coded block flags (CBF) per plane
uint8_t* m_chromaIntraDir; // array of intra directions (chroma)
enum { BytesPerPartition = 21 }; // combined sizeof() of all per-part data
coeff_t* m_trCoeff[3]; // transformed coefficient buffer per plane
MV* m_mv[2]; // array of motion vectors per list
MV* m_mvd[2]; // array of coded motion vector deltas per list
enum { TMVP_UNIT_MASK = 0xF0 }; // mask for mapping index to into a compressed (reference) MV field
const CUData* m_cuAboveLeft; // pointer to above-left neighbor CTU
const CUData* m_cuAboveRight; // pointer to above-right neighbor CTU
const CUData* m_cuAbove; // pointer to above neighbor CTU
const CUData* m_cuLeft; // pointer to left neighbor CTU
CUData();
void initialize(const CUDataMemPool& dataPool, uint32_t depth, int csp, int instance);
static void calcCTUGeoms(uint32_t ctuWidth, uint32_t ctuHeight, uint32_t maxCUSize, uint32_t minCUSize, CUGeom cuDataArray[CUGeom::MAX_GEOMS]);
void initCTU(const Frame& frame, uint32_t cuAddr, int qp);
void initSubCU(const CUData& ctu, const CUGeom& cuGeom, int qp);
void initLosslessCU(const CUData& cu, const CUGeom& cuGeom);
void copyPartFrom(const CUData& cu, const CUGeom& childGeom, uint32_t subPartIdx);
void setEmptyPart(const CUGeom& childGeom, uint32_t subPartIdx);
void copyToPic(uint32_t depth) const;
/* RD-0 methods called only from encodeResidue */
void copyFromPic(const CUData& ctu, const CUGeom& cuGeom);
void updatePic(uint32_t depth) const;
void setPartSizeSubParts(PartSize size) { m_partSet(m_partSize, (uint8_t)size); }
void setPredModeSubParts(PredMode mode) { m_partSet(m_predMode, (uint8_t)mode); }
void clearCbf() { m_partSet(m_cbf[0], 0); m_partSet(m_cbf[1], 0); m_partSet(m_cbf[2], 0); }
/* these functions all take depth as an absolute depth from CTU, it is used to calculate the number of parts to copy */
void setQPSubParts(int8_t qp, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth]((uint8_t*)m_qp + absPartIdx, (uint8_t)qp); }
void setTUDepthSubParts(uint8_t tuDepth, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth](m_tuDepth + absPartIdx, tuDepth); }
void setLumaIntraDirSubParts(uint8_t dir, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth](m_lumaIntraDir + absPartIdx, dir); }
void setChromIntraDirSubParts(uint8_t dir, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth](m_chromaIntraDir + absPartIdx, dir); }
void setCbfSubParts(uint8_t cbf, TextType ttype, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth](m_cbf[ttype] + absPartIdx, cbf); }
void setCbfPartRange(uint8_t cbf, TextType ttype, uint32_t absPartIdx, uint32_t coveredPartIdxes) { memset(m_cbf[ttype] + absPartIdx, cbf, coveredPartIdxes); }
void setTransformSkipSubParts(uint8_t tskip, TextType ttype, uint32_t absPartIdx, uint32_t depth) { s_partSet[depth](m_transformSkip[ttype] + absPartIdx, tskip); }
void setTransformSkipPartRange(uint8_t tskip, TextType ttype, uint32_t absPartIdx, uint32_t coveredPartIdxes) { memset(m_transformSkip[ttype] + absPartIdx, tskip, coveredPartIdxes); }
bool setQPSubCUs(int8_t qp, uint32_t absPartIdx, uint32_t depth);
void setPUInterDir(uint8_t dir, uint32_t absPartIdx, uint32_t puIdx);
void setPUMv(int list, const MV& mv, int absPartIdx, int puIdx);
void setPURefIdx(int list, int8_t refIdx, int absPartIdx, int puIdx);
uint8_t getCbf(uint32_t absPartIdx, TextType ttype, uint32_t tuDepth) const { return (m_cbf[ttype][absPartIdx] >> tuDepth) & 0x1; }
uint8_t getQtRootCbf(uint32_t absPartIdx) const { return m_cbf[0][absPartIdx] || m_cbf[1][absPartIdx] || m_cbf[2][absPartIdx]; }
int8_t getRefQP(uint32_t currAbsIdxInCTU) const;
uint32_t getInterMergeCandidates(uint32_t absPartIdx, uint32_t puIdx, MVField (*candMvField)[2], uint8_t* candDir) const;
void clipMv(MV& outMV) const;
int getPMV(InterNeighbourMV *neighbours, uint32_t reference_list, uint32_t refIdx, MV* amvpCand, MV* pmv) const;
void getNeighbourMV(uint32_t puIdx, uint32_t absPartIdx, InterNeighbourMV* neighbours) const;
void getIntraTUQtDepthRange(uint32_t tuDepthRange[2], uint32_t absPartIdx) const;
void getInterTUQtDepthRange(uint32_t tuDepthRange[2], uint32_t absPartIdx) const;
uint32_t getBestRefIdx(uint32_t subPartIdx) const { return ((m_interDir[subPartIdx] & 1) << m_refIdx[0][subPartIdx]) |
(((m_interDir[subPartIdx] >> 1) & 1) << (m_refIdx[1][subPartIdx] + 16)); }
uint32_t getPUOffset(uint32_t puIdx, uint32_t absPartIdx) const { return (partAddrTable[(int)m_partSize[absPartIdx]][puIdx] << (g_unitSizeDepth - m_cuDepth[absPartIdx]) * 2) >> 4; }
uint32_t getNumPartInter(uint32_t absPartIdx) const { return nbPartsTable[(int)m_partSize[absPartIdx]]; }
bool isIntra(uint32_t absPartIdx) const { return m_predMode[absPartIdx] == MODE_INTRA; }
bool isInter(uint32_t absPartIdx) const { return !!(m_predMode[absPartIdx] & MODE_INTER); }
bool isSkipped(uint32_t absPartIdx) const { return m_predMode[absPartIdx] == MODE_SKIP; }
bool isBipredRestriction() const { return m_log2CUSize[0] == 3 && m_partSize[0] != SIZE_2Nx2N; }
void getPartIndexAndSize(uint32_t puIdx, uint32_t& absPartIdx, int& puWidth, int& puHeight) const;
void getMvField(const CUData* cu, uint32_t absPartIdx, int picList, MVField& mvField) const;
void getAllowedChromaDir(uint32_t absPartIdx, uint32_t* modeList) const;
int getIntraDirLumaPredictor(uint32_t absPartIdx, uint32_t* intraDirPred) const;
uint32_t getSCUAddr() const { return (m_cuAddr << g_unitSizeDepth * 2) + m_absIdxInCTU; }
uint32_t getCtxSplitFlag(uint32_t absPartIdx, uint32_t depth) const;
uint32_t getCtxSkipFlag(uint32_t absPartIdx) const;
void getTUEntropyCodingParameters(TUEntropyCodingParameters &result, uint32_t absPartIdx, uint32_t log2TrSize, bool bIsLuma) const;
const CUData* getPULeft(uint32_t& lPartUnitIdx, uint32_t curPartUnitIdx) const;
const CUData* getPUAbove(uint32_t& aPartUnitIdx, uint32_t curPartUnitIdx) const;
const CUData* getPUAboveLeft(uint32_t& alPartUnitIdx, uint32_t curPartUnitIdx) const;
const CUData* getPUAboveRight(uint32_t& arPartUnitIdx, uint32_t curPartUnitIdx) const;
const CUData* getPUBelowLeft(uint32_t& blPartUnitIdx, uint32_t curPartUnitIdx) const;
const CUData* getQpMinCuLeft(uint32_t& lPartUnitIdx, uint32_t currAbsIdxInCTU) const;
const CUData* getQpMinCuAbove(uint32_t& aPartUnitIdx, uint32_t currAbsIdxInCTU) const;
const CUData* getPUAboveRightAdi(uint32_t& arPartUnitIdx, uint32_t curPartUnitIdx, uint32_t partUnitOffset) const;
const CUData* getPUBelowLeftAdi(uint32_t& blPartUnitIdx, uint32_t curPartUnitIdx, uint32_t partUnitOffset) const;
protected:
template<typename T>
void setAllPU(T *p, const T& val, int absPartIdx, int puIdx);
int8_t getLastCodedQP(uint32_t absPartIdx) const;
int getLastValidPartIdx(int absPartIdx) const;
bool hasEqualMotion(uint32_t absPartIdx, const CUData& candCU, uint32_t candAbsPartIdx) const;
/* Check whether the current PU and a spatial neighboring PU are in same merge region */
bool isDiffMER(int xN, int yN, int xP, int yP) const { return ((xN >> 2) != (xP >> 2)) || ((yN >> 2) != (yP >> 2)); }
// add possible motion vector predictor candidates
bool getDirectPMV(MV& pmv, InterNeighbourMV *neighbours, uint32_t picList, uint32_t refIdx) const;
bool getIndirectPMV(MV& outMV, InterNeighbourMV *neighbours, uint32_t reference_list, uint32_t refIdx) const;
void getInterNeighbourMV(InterNeighbourMV *neighbour, uint32_t partUnitIdx, MVP_DIR dir) const;
bool getColMVP(MV& outMV, int& outRefIdx, int picList, int cuAddr, int absPartIdx) const;
bool getCollocatedMV(int cuAddr, int partUnitIdx, InterNeighbourMV *neighbour) const;
MV scaleMvByPOCDist(const MV& inMV, int curPOC, int curRefPOC, int colPOC, int colRefPOC) const;
void deriveLeftRightTopIdx(uint32_t puIdx, uint32_t& partIdxLT, uint32_t& partIdxRT) const;
uint32_t deriveCenterIdx(uint32_t puIdx) const;
uint32_t deriveRightBottomIdx(uint32_t puIdx) const;
uint32_t deriveLeftBottomIdx(uint32_t puIdx) const;
};
// TU settings for entropy encoding
struct TUEntropyCodingParameters
{
const uint16_t *scan;
const uint16_t *scanCG;
ScanType scanType;
uint32_t log2TrSizeCG;
uint32_t firstSignificanceMapContext;
};
struct CUDataMemPool
{
uint8_t* charMemBlock;
coeff_t* trCoeffMemBlock;
MV* mvMemBlock;
CUDataMemPool() { charMemBlock = NULL; trCoeffMemBlock = NULL; mvMemBlock = NULL; }
bool create(uint32_t depth, uint32_t csp, uint32_t numInstances)
{
uint32_t numPartition = NUM_4x4_PARTITIONS >> (depth * 2);
uint32_t cuSize = g_maxCUSize >> depth;
uint32_t sizeL = cuSize * cuSize;
uint32_t sizeC = sizeL >> (CHROMA_H_SHIFT(csp) + CHROMA_V_SHIFT(csp));
CHECKED_MALLOC(trCoeffMemBlock, coeff_t, (sizeL + sizeC * 2) * numInstances);
CHECKED_MALLOC(charMemBlock, uint8_t, numPartition * numInstances * CUData::BytesPerPartition);
CHECKED_MALLOC(mvMemBlock, MV, numPartition * 4 * numInstances);
return true;
fail:
return false;
}
void destroy()
{
X265_FREE(trCoeffMemBlock);
X265_FREE(mvMemBlock);
X265_FREE(charMemBlock);
}
};
}
#endif // ifndef X265_CUDATA_H

1010
x265/source/common/dct.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

555
x265/source/common/deblock.cpp Normal file
View File

@ -0,0 +1,555 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "deblock.h"
#include "framedata.h"
#include "picyuv.h"
#include "slice.h"
#include "mv.h"
using namespace X265_NS;
#define DEBLOCK_SMALLEST_BLOCK 8
#define DEFAULT_INTRA_TC_OFFSET 2
void Deblock::deblockCTU(const CUData* ctu, const CUGeom& cuGeom, int32_t dir)
{
uint8_t blockStrength[MAX_NUM_PARTITIONS];
memset(blockStrength, 0, sizeof(uint8_t) * cuGeom.numPartitions);
deblockCU(ctu, cuGeom, dir, blockStrength);
}
static inline uint8_t bsCuEdge(const CUData* cu, uint32_t absPartIdx, int32_t dir)
{
if (dir == Deblock::EDGE_VER)
{
if (cu->m_cuPelX + g_zscanToPelX[absPartIdx] > 0)
{
uint32_t tempPartIdx;
const CUData* tempCU = cu->getPULeft(tempPartIdx, absPartIdx);
return tempCU ? 2 : 0;
}
}
else
{
if (cu->m_cuPelY + g_zscanToPelY[absPartIdx] > 0)
{
uint32_t tempPartIdx;
const CUData* tempCU = cu->getPUAbove(tempPartIdx, absPartIdx);
return tempCU ? 2 : 0;
}
}
return 0;
}
/* Deblocking filter process in CU-based (the same function as conventional's)
* param Edge the direction of the edge in block boundary (horizonta/vertical), which is added newly */
void Deblock::deblockCU(const CUData* cu, const CUGeom& cuGeom, const int32_t dir, uint8_t blockStrength[])
{
uint32_t absPartIdx = cuGeom.absPartIdx;
uint32_t depth = cuGeom.depth;
if (cu->m_predMode[absPartIdx] == MODE_NONE)
return;
if (cu->m_cuDepth[absPartIdx] > depth)
{
for (uint32_t subPartIdx = 0; subPartIdx < 4; subPartIdx++)
{
const CUGeom& childGeom = *(&cuGeom + cuGeom.childOffset + subPartIdx);
if (childGeom.flags & CUGeom::PRESENT)
deblockCU(cu, childGeom, dir, blockStrength);
}
return;
}
uint32_t numUnits = 1 << (cuGeom.log2CUSize - LOG2_UNIT_SIZE);
setEdgefilterPU(cu, absPartIdx, dir, blockStrength, numUnits);
setEdgefilterTU(cu, absPartIdx, 0, dir, blockStrength);
setEdgefilterMultiple(cu, absPartIdx, dir, 0, bsCuEdge(cu, absPartIdx, dir), blockStrength, numUnits);
uint32_t numParts = cuGeom.numPartitions;
for (uint32_t partIdx = absPartIdx; partIdx < absPartIdx + numParts; partIdx++)
{
uint32_t bsCheck = !(partIdx & (1 << dir));
if (bsCheck && blockStrength[partIdx])
blockStrength[partIdx] = getBoundaryStrength(cu, dir, partIdx, blockStrength);
}
const uint32_t partIdxIncr = DEBLOCK_SMALLEST_BLOCK >> LOG2_UNIT_SIZE;
uint32_t shiftFactor = (dir == EDGE_VER) ? cu->m_hChromaShift : cu->m_vChromaShift;
uint32_t chromaMask = ((DEBLOCK_SMALLEST_BLOCK << shiftFactor) >> LOG2_UNIT_SIZE) - 1;
uint32_t e0 = (dir == EDGE_VER ? g_zscanToPelX[absPartIdx] : g_zscanToPelY[absPartIdx]) >> LOG2_UNIT_SIZE;
for (uint32_t e = 0; e < numUnits; e += partIdxIncr)
{
edgeFilterLuma(cu, absPartIdx, depth, dir, e, blockStrength);
if (cu->m_chromaFormat != X265_CSP_I400 && !((e0 + e) & chromaMask))
edgeFilterChroma(cu, absPartIdx, depth, dir, e, blockStrength);
}
}
static inline uint32_t calcBsIdx(const CUData* cu, uint32_t absPartIdx, int32_t dir, int32_t edgeIdx, int32_t baseUnitIdx)
{
uint32_t numUnits = cu->m_slice->m_sps->numPartInCUSize;
if (dir)
return g_rasterToZscan[g_zscanToRaster[absPartIdx] + edgeIdx * numUnits + baseUnitIdx];
else
return g_rasterToZscan[g_zscanToRaster[absPartIdx] + baseUnitIdx * numUnits + edgeIdx];
}
void Deblock::setEdgefilterMultiple(const CUData* cu, uint32_t scanIdx, int32_t dir, int32_t edgeIdx, uint8_t value, uint8_t blockStrength[], uint32_t numUnits)
{
X265_CHECK(numUnits > 0, "numUnits edge filter check\n");
for (uint32_t i = 0; i < numUnits; i++)
{
const uint32_t bsidx = calcBsIdx(cu, scanIdx, dir, edgeIdx, i);
blockStrength[bsidx] = value;
}
}
void Deblock::setEdgefilterTU(const CUData* cu, uint32_t absPartIdx, uint32_t tuDepth, int32_t dir, uint8_t blockStrength[])
{
uint32_t log2TrSize = cu->m_log2CUSize[absPartIdx] - tuDepth;
if (cu->m_tuDepth[absPartIdx] > tuDepth)
{
uint32_t qNumParts = 1 << (log2TrSize - LOG2_UNIT_SIZE - 1) * 2;
for (uint32_t qIdx = 0; qIdx < 4; ++qIdx, absPartIdx += qNumParts)
setEdgefilterTU(cu, absPartIdx, tuDepth + 1, dir, blockStrength);
return;
}
uint32_t numUnits = 1 << (log2TrSize - LOG2_UNIT_SIZE);
setEdgefilterMultiple(cu, absPartIdx, dir, 0, 2, blockStrength, numUnits);
}
void Deblock::setEdgefilterPU(const CUData* cu, uint32_t absPartIdx, int32_t dir, uint8_t blockStrength[], uint32_t numUnits)
{
const uint32_t hNumUnits = numUnits >> 1;
const uint32_t qNumUnits = numUnits >> 2;
switch (cu->m_partSize[absPartIdx])
{
case SIZE_2NxN:
if (EDGE_HOR == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, hNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_Nx2N:
if (EDGE_VER == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, hNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_NxN:
setEdgefilterMultiple(cu, absPartIdx, dir, hNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_2NxnU:
if (EDGE_HOR == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, qNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_nLx2N:
if (EDGE_VER == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, qNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_2NxnD:
if (EDGE_HOR == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, numUnits - qNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_nRx2N:
if (EDGE_VER == dir)
setEdgefilterMultiple(cu, absPartIdx, dir, numUnits - qNumUnits, 1, blockStrength, numUnits);
break;
case SIZE_2Nx2N:
default:
break;
}
}
uint8_t Deblock::getBoundaryStrength(const CUData* cuQ, int32_t dir, uint32_t partQ, const uint8_t blockStrength[])
{
// Calculate block index
uint32_t partP;
const CUData* cuP = (dir == EDGE_VER ? cuQ->getPULeft(partP, partQ) : cuQ->getPUAbove(partP, partQ));
// Set BS for Intra MB : BS = 2
if (cuP->isIntra(partP) || cuQ->isIntra(partQ))
return 2;
// Set BS for not Intra MB : BS = 1 or 0
if (blockStrength[partQ] > 1 &&
(cuQ->getCbf(partQ, TEXT_LUMA, cuQ->m_tuDepth[partQ]) ||
cuP->getCbf(partP, TEXT_LUMA, cuP->m_tuDepth[partP])))
return 1;
static const MV zeroMv(0, 0);
const Slice* const sliceQ = cuQ->m_slice;
const Slice* const sliceP = cuP->m_slice;
const Frame* refP0 = sliceP->m_refFrameList[0][cuP->m_refIdx[0][partP]];
const Frame* refQ0 = sliceQ->m_refFrameList[0][cuQ->m_refIdx[0][partQ]];
const MV& mvP0 = refP0 ? cuP->m_mv[0][partP] : zeroMv;
const MV& mvQ0 = refQ0 ? cuQ->m_mv[0][partQ] : zeroMv;
if (sliceQ->isInterP() && sliceP->isInterP())
{
return ((refP0 != refQ0) ||
(abs(mvQ0.x - mvP0.x) >= 4) || (abs(mvQ0.y - mvP0.y) >= 4)) ? 1 : 0;
}
// (sliceQ->isInterB() || sliceP->isInterB())
const Frame* refP1 = sliceP->m_refFrameList[1][cuP->m_refIdx[1][partP]];
const Frame* refQ1 = sliceQ->m_refFrameList[1][cuQ->m_refIdx[1][partQ]];
const MV& mvP1 = refP1 ? cuP->m_mv[1][partP] : zeroMv;
const MV& mvQ1 = refQ1 ? cuQ->m_mv[1][partQ] : zeroMv;
if (((refP0 == refQ0) && (refP1 == refQ1)) || ((refP0 == refQ1) && (refP1 == refQ0)))
{
if (refP0 != refP1) // Different L0 & L1
{
if (refP0 == refQ0)
return ((abs(mvQ0.x - mvP0.x) >= 4) || (abs(mvQ0.y - mvP0.y) >= 4) ||
(abs(mvQ1.x - mvP1.x) >= 4) || (abs(mvQ1.y - mvP1.y) >= 4)) ? 1 : 0;
else
return ((abs(mvQ1.x - mvP0.x) >= 4) || (abs(mvQ1.y - mvP0.y) >= 4) ||
(abs(mvQ0.x - mvP1.x) >= 4) || (abs(mvQ0.y - mvP1.y) >= 4)) ? 1 : 0;
}
else // Same L0 & L1
{
return (((abs(mvQ0.x - mvP0.x) >= 4) || (abs(mvQ0.y - mvP0.y) >= 4) ||
(abs(mvQ1.x - mvP1.x) >= 4) || (abs(mvQ1.y - mvP1.y) >= 4)) &&
((abs(mvQ1.x - mvP0.x) >= 4) || (abs(mvQ1.y - mvP0.y) >= 4) ||
(abs(mvQ0.x - mvP1.x) >= 4) || (abs(mvQ0.y - mvP1.y) >= 4))) ? 1 : 0;
}
}
// for all different Ref_Idx
return 1;
}
static inline int32_t calcDP(pixel* src, intptr_t offset)
{
return abs(static_cast<int32_t>(src[-offset * 3]) - 2 * src[-offset * 2] + src[-offset]);
}
static inline int32_t calcDQ(pixel* src, intptr_t offset)
{
return abs(static_cast<int32_t>(src[0]) - 2 * src[offset] + src[offset * 2]);
}
static inline bool useStrongFiltering(intptr_t offset, int32_t beta, int32_t tc, pixel* src)
{
int16_t m4 = (int16_t)src[0];
int16_t m3 = (int16_t)src[-offset];
int16_t m7 = (int16_t)src[offset * 3];
int16_t m0 = (int16_t)src[-offset * 4];
int32_t strong = abs(m0 - m3) + abs(m7 - m4);
return (strong < (beta >> 3)) && (abs(m3 - m4) < ((tc * 5 + 1) >> 1));
}
/* Deblocking for the luminance component with strong or weak filter
* \param src pointer to picture data
* \param offset offset value for picture data
* \param tc tc value
* \param maskP indicator to enable filtering on partP
* \param maskQ indicator to enable filtering on partQ
* \param maskP1 decision weak filter/no filter for partP
* \param maskQ1 decision weak filter/no filter for partQ */
static inline void pelFilterLumaStrong(pixel* src, intptr_t srcStep, intptr_t offset, int32_t tc, int32_t maskP, int32_t maskQ)
{
int32_t tc2 = 2 * tc;
int32_t tcP = (tc2 & maskP);
int32_t tcQ = (tc2 & maskQ);
for (int32_t i = 0; i < UNIT_SIZE; i++, src += srcStep)
{
int16_t m4 = (int16_t)src[0];
int16_t m3 = (int16_t)src[-offset];
int16_t m5 = (int16_t)src[offset];
int16_t m2 = (int16_t)src[-offset * 2];
int16_t m6 = (int16_t)src[offset * 2];
int16_t m1 = (int16_t)src[-offset * 3];
int16_t m7 = (int16_t)src[offset * 3];
int16_t m0 = (int16_t)src[-offset * 4];
src[-offset * 3] = (pixel)(x265_clip3(-tcP, tcP, ((2 * m0 + 3 * m1 + m2 + m3 + m4 + 4) >> 3) - m1) + m1);
src[-offset * 2] = (pixel)(x265_clip3(-tcP, tcP, ((m1 + m2 + m3 + m4 + 2) >> 2) - m2) + m2);
src[-offset] = (pixel)(x265_clip3(-tcP, tcP, ((m1 + 2 * m2 + 2 * m3 + 2 * m4 + m5 + 4) >> 3) - m3) + m3);
src[0] = (pixel)(x265_clip3(-tcQ, tcQ, ((m2 + 2 * m3 + 2 * m4 + 2 * m5 + m6 + 4) >> 3) - m4) + m4);
src[offset] = (pixel)(x265_clip3(-tcQ, tcQ, ((m3 + m4 + m5 + m6 + 2) >> 2) - m5) + m5);
src[offset * 2] = (pixel)(x265_clip3(-tcQ, tcQ, ((m3 + m4 + m5 + 3 * m6 + 2 * m7 + 4) >> 3) - m6) + m6);
}
}
/* Weak filter */
static inline void pelFilterLuma(pixel* src, intptr_t srcStep, intptr_t offset, int32_t tc, int32_t maskP, int32_t maskQ,
int32_t maskP1, int32_t maskQ1)
{
int32_t thrCut = tc * 10;
int32_t tc2 = tc >> 1;
maskP1 &= maskP;
maskQ1 &= maskQ;
for (int32_t i = 0; i < UNIT_SIZE; i++, src += srcStep)
{
int16_t m4 = (int16_t)src[0];
int16_t m3 = (int16_t)src[-offset];
int16_t m5 = (int16_t)src[offset];
int16_t m2 = (int16_t)src[-offset * 2];
int32_t delta = (9 * (m4 - m3) - 3 * (m5 - m2) + 8) >> 4;
if (abs(delta) < thrCut)
{
delta = x265_clip3(-tc, tc, delta);
src[-offset] = x265_clip(m3 + (delta & maskP));
src[0] = x265_clip(m4 - (delta & maskQ));
if (maskP1)
{
int16_t m1 = (int16_t)src[-offset * 3];
int32_t delta1 = x265_clip3(-tc2, tc2, ((((m1 + m3 + 1) >> 1) - m2 + delta) >> 1));
src[-offset * 2] = x265_clip(m2 + delta1);
}
if (maskQ1)
{
int16_t m6 = (int16_t)src[offset * 2];
int32_t delta2 = x265_clip3(-tc2, tc2, ((((m6 + m4 + 1) >> 1) - m5 - delta) >> 1));
src[offset] = x265_clip(m5 + delta2);
}
}
}
}
/* Deblocking of one line/column for the chrominance component
* \param src pointer to picture data
* \param offset offset value for picture data
* \param tc tc value
* \param maskP indicator to disable filtering on partP
* \param maskQ indicator to disable filtering on partQ */
static inline void pelFilterChroma(pixel* src, intptr_t srcStep, intptr_t offset, int32_t tc, int32_t maskP, int32_t maskQ)
{
for (int32_t i = 0; i < UNIT_SIZE; i++, src += srcStep)
{
int16_t m4 = (int16_t)src[0];
int16_t m3 = (int16_t)src[-offset];
int16_t m5 = (int16_t)src[offset];
int16_t m2 = (int16_t)src[-offset * 2];
int32_t delta = x265_clip3(-tc, tc, ((((m4 - m3) * 4) + m2 - m5 + 4) >> 3));
src[-offset] = x265_clip(m3 + (delta & maskP));
src[0] = x265_clip(m4 - (delta & maskQ));
}
}
void Deblock::edgeFilterLuma(const CUData* cuQ, uint32_t absPartIdx, uint32_t depth, int32_t dir, int32_t edge, const uint8_t blockStrength[])
{
PicYuv* reconPic = cuQ->m_encData->m_reconPic;
pixel* src = reconPic->getLumaAddr(cuQ->m_cuAddr, absPartIdx);
intptr_t stride = reconPic->m_stride;
const PPS* pps = cuQ->m_slice->m_pps;
intptr_t offset, srcStep;
int32_t maskP = -1;
int32_t maskQ = -1;
int32_t betaOffset = pps->deblockingFilterBetaOffsetDiv2 << 1;
int32_t tcOffset = pps->deblockingFilterTcOffsetDiv2 << 1;
bool bCheckNoFilter = pps->bTransquantBypassEnabled;
if (dir == EDGE_VER)
{
offset = 1;
srcStep = stride;
src += (edge << LOG2_UNIT_SIZE);
}
else // (dir == EDGE_HOR)
{
offset = stride;
srcStep = 1;
src += (edge << LOG2_UNIT_SIZE) * stride;
}
uint32_t numUnits = cuQ->m_slice->m_sps->numPartInCUSize >> depth;
for (uint32_t idx = 0; idx < numUnits; idx++)
{
uint32_t partQ = calcBsIdx(cuQ, absPartIdx, dir, edge, idx);
uint32_t bs = blockStrength[partQ];
if (!bs)
continue;
// Derive neighboring PU index
uint32_t partP;
const CUData* cuP = (dir == EDGE_VER ? cuQ->getPULeft(partP, partQ) : cuQ->getPUAbove(partP, partQ));
if (bCheckNoFilter)
{
// check if each of PUs is lossless coded
maskP = cuP->m_tqBypass[partP] - 1;
maskQ = cuQ->m_tqBypass[partQ] - 1;
if (!(maskP | maskQ))
continue;
}
int32_t qpQ = cuQ->m_qp[partQ];
int32_t qpP = cuP->m_qp[partP];
int32_t qp = (qpP + qpQ + 1) >> 1;
int32_t indexB = x265_clip3(0, QP_MAX_SPEC, qp + betaOffset);
const int32_t bitdepthShift = X265_DEPTH - 8;
int32_t beta = s_betaTable[indexB] << bitdepthShift;
intptr_t unitOffset = idx * srcStep << LOG2_UNIT_SIZE;
int32_t dp0 = calcDP(src + unitOffset , offset);
int32_t dq0 = calcDQ(src + unitOffset , offset);
int32_t dp3 = calcDP(src + unitOffset + srcStep * 3, offset);
int32_t dq3 = calcDQ(src + unitOffset + srcStep * 3, offset);
int32_t d0 = dp0 + dq0;
int32_t d3 = dp3 + dq3;
int32_t d = d0 + d3;
if (d >= beta)
continue;
int32_t indexTC = x265_clip3(0, QP_MAX_SPEC + DEFAULT_INTRA_TC_OFFSET, int32_t(qp + DEFAULT_INTRA_TC_OFFSET * (bs - 1) + tcOffset));
int32_t tc = s_tcTable[indexTC] << bitdepthShift;
bool sw = (2 * d0 < (beta >> 2) &&
2 * d3 < (beta >> 2) &&
useStrongFiltering(offset, beta, tc, src + unitOffset ) &&
useStrongFiltering(offset, beta, tc, src + unitOffset + srcStep * 3));
if (sw)
pelFilterLumaStrong(src + unitOffset, srcStep, offset, tc, maskP, maskQ);
else
{
int32_t sideThreshold = (beta + (beta >> 1)) >> 3;
int32_t dp = dp0 + dp3;
int32_t dq = dq0 + dq3;
int32_t maskP1 = (dp < sideThreshold ? -1 : 0);
int32_t maskQ1 = (dq < sideThreshold ? -1 : 0);
pelFilterLuma(src + unitOffset, srcStep, offset, tc, maskP, maskQ, maskP1, maskQ1);
}
}
}
void Deblock::edgeFilterChroma(const CUData* cuQ, uint32_t absPartIdx, uint32_t depth, int32_t dir, int32_t edge, const uint8_t blockStrength[])
{
int32_t chFmt = cuQ->m_chromaFormat, chromaShift;
intptr_t offset, srcStep;
const PPS* pps = cuQ->m_slice->m_pps;
int32_t maskP = -1;
int32_t maskQ = -1;
int32_t tcOffset = pps->deblockingFilterTcOffsetDiv2 << 1;
X265_CHECK(((dir == EDGE_VER)
? ((g_zscanToPelX[absPartIdx] + edge * UNIT_SIZE) >> cuQ->m_hChromaShift)
: ((g_zscanToPelY[absPartIdx] + edge * UNIT_SIZE) >> cuQ->m_vChromaShift)) % DEBLOCK_SMALLEST_BLOCK == 0,
"invalid edge\n");
PicYuv* reconPic = cuQ->m_encData->m_reconPic;
intptr_t stride = reconPic->m_strideC;
intptr_t srcOffset = reconPic->getChromaAddrOffset(cuQ->m_cuAddr, absPartIdx);
bool bCheckNoFilter = pps->bTransquantBypassEnabled;
if (dir == EDGE_VER)
{
chromaShift = cuQ->m_vChromaShift;
srcOffset += (edge << (LOG2_UNIT_SIZE - cuQ->m_hChromaShift));
offset = 1;
srcStep = stride;
}
else // (dir == EDGE_HOR)
{
chromaShift = cuQ->m_hChromaShift;
srcOffset += edge * stride << (LOG2_UNIT_SIZE - cuQ->m_vChromaShift);
offset = stride;
srcStep = 1;
}
pixel* srcChroma[2];
srcChroma[0] = reconPic->m_picOrg[1] + srcOffset;
srcChroma[1] = reconPic->m_picOrg[2] + srcOffset;
uint32_t numUnits = cuQ->m_slice->m_sps->numPartInCUSize >> (depth + chromaShift);
for (uint32_t idx = 0; idx < numUnits; idx++)
{
uint32_t partQ = calcBsIdx(cuQ, absPartIdx, dir, edge, idx << chromaShift);
uint32_t bs = blockStrength[partQ];
if (bs <= 1)
continue;
// Derive neighboring PU index
uint32_t partP;
const CUData* cuP = (dir == EDGE_VER ? cuQ->getPULeft(partP, partQ) : cuQ->getPUAbove(partP, partQ));
if (bCheckNoFilter)
{
// check if each of PUs is lossless coded
maskP = (cuP->m_tqBypass[partP] ? 0 : -1);
maskQ = (cuQ->m_tqBypass[partQ] ? 0 : -1);
if (!(maskP | maskQ))
continue;
}
int32_t qpQ = cuQ->m_qp[partQ];
int32_t qpP = cuP->m_qp[partP];
int32_t qpA = (qpP + qpQ + 1) >> 1;
intptr_t unitOffset = idx * srcStep << LOG2_UNIT_SIZE;
for (uint32_t chromaIdx = 0; chromaIdx < 2; chromaIdx++)
{
int32_t qp = qpA + pps->chromaQpOffset[chromaIdx];
if (qp >= 30)
qp = chFmt == X265_CSP_I420 ? g_chromaScale[qp] : X265_MIN(qp, QP_MAX_SPEC);
int32_t indexTC = x265_clip3(0, QP_MAX_SPEC + DEFAULT_INTRA_TC_OFFSET, int32_t(qp + DEFAULT_INTRA_TC_OFFSET + tcOffset));
const int32_t bitdepthShift = X265_DEPTH - 8;
int32_t tc = s_tcTable[indexTC] << bitdepthShift;
pixel* srcC = srcChroma[chromaIdx];
pelFilterChroma(srcC + unitOffset, srcStep, offset, tc, maskP, maskQ);
}
}
}
const uint8_t Deblock::s_tcTable[54] =
{
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2,
2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 8, 9, 10, 11, 13, 14, 16, 18, 20, 22, 24
};
const uint8_t Deblock::s_betaTable[52] =
{
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17,
18, 20, 22, 24, 26, 28, 30, 32, 34, 36, 38, 40, 42, 44, 46, 48, 50, 52, 54, 56, 58, 60, 62, 64
};

63
x265/source/common/deblock.h Normal file
View File

@ -0,0 +1,63 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_DEBLOCK_H
#define X265_DEBLOCK_H
#include "common.h"
namespace X265_NS {
// private namespace
class CUData;
struct CUGeom;
class Deblock
{
public:
enum { EDGE_VER, EDGE_HOR };
void deblockCTU(const CUData* ctu, const CUGeom& cuGeom, int32_t dir);
protected:
// CU-level deblocking function
void deblockCU(const CUData* cu, const CUGeom& cuGeom, const int32_t dir, uint8_t blockStrength[]);
// set filtering functions
void setEdgefilterTU(const CUData* cu, uint32_t absPartIdx, uint32_t tuDepth, int32_t dir, uint8_t blockStrength[]);
void setEdgefilterPU(const CUData* cu, uint32_t absPartIdx, int32_t dir, uint8_t blockStrength[], uint32_t numUnits);
void setEdgefilterMultiple(const CUData* cu, uint32_t absPartIdx, int32_t dir, int32_t edgeIdx, uint8_t value, uint8_t blockStrength[], uint32_t numUnits);
// get filtering functions
uint8_t getBoundaryStrength(const CUData* cuQ, int32_t dir, uint32_t partQ, const uint8_t blockStrength[]);
// filter luma/chroma functions
void edgeFilterLuma(const CUData* cuQ, uint32_t absPartIdx, uint32_t depth, int32_t dir, int32_t edge, const uint8_t blockStrength[]);
void edgeFilterChroma(const CUData* cuQ, uint32_t absPartIdx, uint32_t depth, int32_t dir, int32_t edge, const uint8_t blockStrength[]);
static const uint8_t s_tcTable[54];
static const uint8_t s_betaTable[52];
};
}
#endif // ifndef X265_DEBLOCK_H

129
x265/source/common/frame.cpp Normal file
View File

@ -0,0 +1,129 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "frame.h"
#include "picyuv.h"
#include "framedata.h"
using namespace X265_NS;
Frame::Frame()
{
m_bChromaExtended = false;
m_lowresInit = false;
m_reconRowCount.set(0);
m_countRefEncoders = 0;
m_encData = NULL;
m_reconPic = NULL;
m_quantOffsets = NULL;
m_next = NULL;
m_prev = NULL;
m_param = NULL;
memset(&m_lowres, 0, sizeof(m_lowres));
}
bool Frame::create(x265_param *param, float* quantOffsets)
{
m_fencPic = new PicYuv;
m_param = param;
if (m_fencPic->create(param->sourceWidth, param->sourceHeight, param->internalCsp) &&
m_lowres.create(m_fencPic, param->bframes, !!param->rc.aqMode))
{
if (quantOffsets)
{
int32_t cuCount = m_lowres.maxBlocksInRow * m_lowres.maxBlocksInCol;
m_quantOffsets = new float[cuCount];
}
return true;
}
return false;
}
bool Frame::allocEncodeData(x265_param *param, const SPS& sps)
{
m_encData = new FrameData;
m_reconPic = new PicYuv;
m_encData->m_reconPic = m_reconPic;
bool ok = m_encData->create(*param, sps) && m_reconPic->create(param->sourceWidth, param->sourceHeight, param->internalCsp);
if (ok)
{
/* initialize right border of m_reconpicYuv as SAO may read beyond the
* end of the picture accessing uninitialized pixels */
int maxHeight = sps.numCuInHeight * g_maxCUSize;
memset(m_reconPic->m_picOrg[0], 0, sizeof(pixel) * m_reconPic->m_stride * maxHeight);
if (m_reconPic->m_picCsp != X265_CSP_I400) {
memset(m_reconPic->m_picOrg[1], 0, sizeof(pixel) * m_reconPic->m_strideC * (maxHeight >> m_reconPic->m_vChromaShift));
memset(m_reconPic->m_picOrg[2], 0, sizeof(pixel) * m_reconPic->m_strideC * (maxHeight >> m_reconPic->m_vChromaShift));
}
/* use pre-calculated cu/pu offsets cached in the SPS structure */
m_reconPic->m_cuOffsetY = sps.cuOffsetY;
m_reconPic->m_buOffsetY = sps.buOffsetY;
if (m_reconPic->m_picCsp != X265_CSP_I400) {
m_reconPic->m_cuOffsetC = sps.cuOffsetC;
m_reconPic->m_buOffsetC = sps.buOffsetC;
}
}
return ok;
}
/* prepare to re-use a FrameData instance to encode a new picture */
void Frame::reinit(const SPS& sps)
{
m_bChromaExtended = false;
m_reconPic = m_encData->m_reconPic;
m_encData->reinit(sps);
}
void Frame::destroy()
{
if (m_encData)
{
m_encData->destroy();
delete m_encData;
m_encData = NULL;
}
if (m_fencPic)
{
m_fencPic->destroy();
delete m_fencPic;
m_fencPic = NULL;
}
if (m_reconPic)
{
m_reconPic->destroy();
delete m_reconPic;
m_reconPic = NULL;
}
if (m_quantOffsets)
{
delete[] m_quantOffsets;
}
m_lowres.destroy();
}

81
x265/source/common/frame.h Normal file
View File

@ -0,0 +1,81 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_FRAME_H
#define X265_FRAME_H
#include "common.h"
#include "lowres.h"
#include "threading.h"
namespace X265_NS {
// private namespace
class FrameData;
class PicYuv;
struct SPS;
#define IS_REFERENCED(frame) (frame->m_lowres.sliceType != X265_TYPE_B)
class Frame
{
public:
/* These two items will be NULL until the Frame begins to be encoded, at which point
* it will be assigned a FrameData instance, which comes with a reconstructed image PicYuv */
FrameData* m_encData;
PicYuv* m_reconPic;
/* Data associated with x265_picture */
PicYuv* m_fencPic;
int m_poc;
int64_t m_pts; // user provided presentation time stamp
int64_t m_reorderedPts;
int64_t m_dts;
int32_t m_forceqp; // Force to use the qp specified in qp file
void* m_userData; // user provided pointer passed in with this picture
Lowres m_lowres;
bool m_lowresInit; // lowres init complete (pre-analysis)
bool m_bChromaExtended; // orig chroma planes motion extended for weight analysis
float* m_quantOffsets; // points to quantOffsets in x265_picture
/* Frame Parallelism - notification between FrameEncoders of available motion reference rows */
ThreadSafeInteger m_reconRowCount; // count of CTU rows completely reconstructed and extended for motion reference
volatile uint32_t m_countRefEncoders; // count of FrameEncoder threads monitoring m_reconRowCount
Frame* m_next; // PicList doubly linked list pointers
Frame* m_prev;
x265_param* m_param; // Points to the latest param set for the frame.
x265_analysis_data m_analysisData;
Frame();
bool create(x265_param *param, float* quantOffsets);
bool allocEncodeData(x265_param *param, const SPS& sps);
void reinit(const SPS& sps);
void destroy();
};
}
#endif // ifndef X265_FRAME_H

69
x265/source/common/framedata.cpp Normal file
View File

@ -0,0 +1,69 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "framedata.h"
#include "picyuv.h"
using namespace X265_NS;
FrameData::FrameData()
{
memset(this, 0, sizeof(*this));
}
bool FrameData::create(const x265_param& param, const SPS& sps)
{
m_param = &param;
m_slice = new Slice;
m_picCTU = new CUData[sps.numCUsInFrame];
m_cuMemPool.create(0, param.internalCsp, sps.numCUsInFrame);
for (uint32_t ctuAddr = 0; ctuAddr < sps.numCUsInFrame; ctuAddr++)
m_picCTU[ctuAddr].initialize(m_cuMemPool, 0, param.internalCsp, ctuAddr);
CHECKED_MALLOC(m_cuStat, RCStatCU, sps.numCUsInFrame);
CHECKED_MALLOC(m_rowStat, RCStatRow, sps.numCuInHeight);
reinit(sps);
return true;
fail:
return false;
}
void FrameData::reinit(const SPS& sps)
{
memset(m_cuStat, 0, sps.numCUsInFrame * sizeof(*m_cuStat));
memset(m_rowStat, 0, sps.numCuInHeight * sizeof(*m_rowStat));
}
void FrameData::destroy()
{
delete [] m_picCTU;
delete m_slice;
delete m_saoParam;
m_cuMemPool.destroy();
X265_FREE(m_cuStat);
X265_FREE(m_rowStat);
}

152
x265/source/common/framedata.h Normal file
View File

@ -0,0 +1,152 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Author: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_FRAMEDATA_H
#define X265_FRAMEDATA_H
#include "common.h"
#include "slice.h"
#include "cudata.h"
namespace X265_NS {
// private namespace
class PicYuv;
class JobProvider;
#define INTER_MODES 4 // 2Nx2N, 2NxN, Nx2N, AMP modes
#define INTRA_MODES 3 // DC, Planar, Angular modes
/* Current frame stats for 2 pass */
struct FrameStats
{
int mvBits; /* MV bits (MV+Ref+Block Type) */
int coeffBits; /* Texture bits (DCT coefs) */
int miscBits;
int intra8x8Cnt;
int inter8x8Cnt;
int skip8x8Cnt;
/* CU type counts stored as percentage */
double percent8x8Intra;
double percent8x8Inter;
double percent8x8Skip;
double avgLumaDistortion;
double avgChromaDistortion;
double avgPsyEnergy;
double avgResEnergy;
double percentIntraNxN;
double percentSkipCu[NUM_CU_DEPTH];
double percentMergeCu[NUM_CU_DEPTH];
double percentIntraDistribution[NUM_CU_DEPTH][INTRA_MODES];
double percentInterDistribution[NUM_CU_DEPTH][3]; // 2Nx2N, RECT, AMP modes percentage
uint64_t cntIntraNxN;
uint64_t totalCu;
uint64_t totalCtu;
uint64_t lumaDistortion;
uint64_t chromaDistortion;
uint64_t psyEnergy;
uint64_t resEnergy;
uint64_t cntSkipCu[NUM_CU_DEPTH];
uint64_t cntMergeCu[NUM_CU_DEPTH];
uint64_t cntInter[NUM_CU_DEPTH];
uint64_t cntIntra[NUM_CU_DEPTH];
uint64_t cuInterDistribution[NUM_CU_DEPTH][INTER_MODES];
uint64_t cuIntraDistribution[NUM_CU_DEPTH][INTRA_MODES];
FrameStats()
{
memset(this, 0, sizeof(FrameStats));
}
};
/* Per-frame data that is used during encodes and referenced while the picture
* is available for reference. A FrameData instance is attached to a Frame as it
* comes out of the lookahead. Frames which are not being encoded do not have a
* FrameData instance. These instances are re-used once the encoded frame has
* no active references. They hold the Slice instance and the 'official' CTU
* data structures. They are maintained in a free-list pool along together with
* a reconstructed image PicYuv in order to conserve memory. */
class FrameData
{
public:
Slice* m_slice;
SAOParam* m_saoParam;
const x265_param* m_param;
FrameData* m_freeListNext;
PicYuv* m_reconPic;
bool m_bHasReferences; /* used during DPB/RPS updates */
int m_frameEncoderID; /* the ID of the FrameEncoder encoding this frame */
JobProvider* m_jobProvider;
CUDataMemPool m_cuMemPool;
CUData* m_picCTU;
/* Rate control data used during encode and by references */
struct RCStatCU
{
uint32_t totalBits; /* total bits to encode this CTU */
uint32_t vbvCost; /* sum of lowres costs for 16x16 sub-blocks */
uint32_t intraVbvCost; /* sum of lowres intra costs for 16x16 sub-blocks */
uint64_t avgCost[4]; /* stores the avg cost of CU's in frame for each depth */
uint32_t count[4]; /* count and avgCost only used by Analysis at RD0..4 */
double baseQp; /* Qp of Cu set from RateControl/Vbv (only used by frame encoder) */
};
struct RCStatRow
{
uint32_t numEncodedCUs; /* ctuAddr of last encoded CTU in row */
uint32_t encodedBits; /* sum of 'totalBits' of encoded CTUs */
uint32_t satdForVbv; /* sum of lowres (estimated) costs for entire row */
uint32_t intraSatdForVbv; /* sum of lowres (estimated) intra costs for entire row */
uint32_t diagSatd;
uint32_t diagIntraSatd;
double diagQp;
double diagQpScale;
double sumQpRc;
double sumQpAq;
};
RCStatCU* m_cuStat;
RCStatRow* m_rowStat;
FrameStats m_frameStats; // stats of current frame for multi-pass encodes
double m_avgQpRc; /* avg QP as decided by rate-control */
double m_avgQpAq; /* avg QP as decided by AQ in addition to rate-control */
double m_rateFactor; /* calculated based on the Frame QP */
FrameData();
bool create(const x265_param& param, const SPS& sps);
void reinit(const SPS& sps);
void destroy();
inline CUData* getPicCTU(uint32_t ctuAddr) { return &m_picCTU[ctuAddr]; }
};
}
#endif // ifndef X265_FRAMEDATA_H

270
x265/source/common/intrapred.cpp Normal file
View File

@ -0,0 +1,270 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Min Chen <chenm003@163.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "primitives.h"
using namespace X265_NS;
namespace {
template<int tuSize>
void intraFilter(const pixel* samples, pixel* filtered) /* 1:2:1 filtering of left and top reference samples */
{
const int tuSize2 = tuSize << 1;
pixel topLeft = samples[0], topLast = samples[tuSize2], leftLast = samples[tuSize2 + tuSize2];
// filtering top
for (int i = 1; i < tuSize2; i++)
filtered[i] = ((samples[i] << 1) + samples[i - 1] + samples[i + 1] + 2) >> 2;
filtered[tuSize2] = topLast;
// filtering top-left
filtered[0] = ((topLeft << 1) + samples[1] + samples[tuSize2 + 1] + 2) >> 2;
// filtering left
filtered[tuSize2 + 1] = ((samples[tuSize2 + 1] << 1) + topLeft + samples[tuSize2 + 2] + 2) >> 2;
for (int i = tuSize2 + 2; i < tuSize2 + tuSize2; i++)
filtered[i] = ((samples[i] << 1) + samples[i - 1] + samples[i + 1] + 2) >> 2;
filtered[tuSize2 + tuSize2] = leftLast;
}
static void dcPredFilter(const pixel* above, const pixel* left, pixel* dst, intptr_t dststride, int size)
{
// boundary pixels processing
dst[0] = (pixel)((above[0] + left[0] + 2 * dst[0] + 2) >> 2);
for (int x = 1; x < size; x++)
dst[x] = (pixel)((above[x] + 3 * dst[x] + 2) >> 2);
dst += dststride;
for (int y = 1; y < size; y++)
{
*dst = (pixel)((left[y] + 3 * *dst + 2) >> 2);
dst += dststride;
}
}
template<int width>
void intra_pred_dc_c(pixel* dst, intptr_t dstStride, const pixel* srcPix, int /*dirMode*/, int bFilter)
{
int k, l;
int dcVal = width;
for (int i = 0; i < width; i++)
dcVal += srcPix[1 + i] + srcPix[2 * width + 1 + i];
dcVal = dcVal / (width + width);
for (k = 0; k < width; k++)
for (l = 0; l < width; l++)
dst[k * dstStride + l] = (pixel)dcVal;
if (bFilter)
dcPredFilter(srcPix + 1, srcPix + (2 * width + 1), dst, dstStride, width);
}
template<int log2Size>
void planar_pred_c(pixel* dst, intptr_t dstStride, const pixel* srcPix, int /*dirMode*/, int /*bFilter*/)
{
const int blkSize = 1 << log2Size;
const pixel* above = srcPix + 1;
const pixel* left = srcPix + (2 * blkSize + 1);
pixel topRight = above[blkSize];
pixel bottomLeft = left[blkSize];
for (int y = 0; y < blkSize; y++)
for (int x = 0; x < blkSize; x++)
dst[y * dstStride + x] = (pixel) (((blkSize - 1 - x) * left[y] + (blkSize - 1 -y) * above[x] + (x + 1) * topRight + (y + 1) * bottomLeft + blkSize) >> (log2Size + 1));
}
template<int width>
void intra_pred_ang_c(pixel* dst, intptr_t dstStride, const pixel *srcPix0, int dirMode, int bFilter)
{
int width2 = width << 1;
// Flip the neighbours in the horizontal case.
int horMode = dirMode < 18;
pixel neighbourBuf[129];
const pixel *srcPix = srcPix0;
if (horMode)
{
neighbourBuf[0] = srcPix[0];
for (int i = 0; i < width << 1; i++)
{
neighbourBuf[1 + i] = srcPix[width2 + 1 + i];
neighbourBuf[width2 + 1 + i] = srcPix[1 + i];
}
srcPix = neighbourBuf;
}
// Intra prediction angle and inverse angle tables.
const int8_t angleTable[17] = { -32, -26, -21, -17, -13, -9, -5, -2, 0, 2, 5, 9, 13, 17, 21, 26, 32 };
const int16_t invAngleTable[8] = { 4096, 1638, 910, 630, 482, 390, 315, 256 };
// Get the prediction angle.
int angleOffset = horMode ? 10 - dirMode : dirMode - 26;
int angle = angleTable[8 + angleOffset];
// Vertical Prediction.
if (!angle)
{
for (int y = 0; y < width; y++)
for (int x = 0; x < width; x++)
dst[y * dstStride + x] = srcPix[1 + x];
if (bFilter)
{
int topLeft = srcPix[0], top = srcPix[1];
for (int y = 0; y < width; y++)
dst[y * dstStride] = x265_clip((int16_t)(top + ((srcPix[width2 + 1 + y] - topLeft) >> 1)));
}
}
else // Angular prediction.
{
// Get the reference pixels. The reference base is the first pixel to the top (neighbourBuf[1]).
pixel refBuf[64];
const pixel *ref;
// Use the projected left neighbours and the top neighbours.
if (angle < 0)
{
// Number of neighbours projected.
int nbProjected = -((width * angle) >> 5) - 1;
pixel *ref_pix = refBuf + nbProjected + 1;
// Project the neighbours.
int invAngle = invAngleTable[- angleOffset - 1];
int invAngleSum = 128;
for (int i = 0; i < nbProjected; i++)
{
invAngleSum += invAngle;
ref_pix[- 2 - i] = srcPix[width2 + (invAngleSum >> 8)];
}
// Copy the top-left and top pixels.
for (int i = 0; i < width + 1; i++)
ref_pix[-1 + i] = srcPix[i];
ref = ref_pix;
}
else // Use the top and top-right neighbours.
ref = srcPix + 1;
// Pass every row.
int angleSum = 0;
for (int y = 0; y < width; y++)
{
angleSum += angle;
int offset = angleSum >> 5;
int fraction = angleSum & 31;
if (fraction) // Interpolate
for (int x = 0; x < width; x++)
dst[y * dstStride + x] = (pixel)(((32 - fraction) * ref[offset + x] + fraction * ref[offset + x + 1] + 16) >> 5);
else // Copy.
for (int x = 0; x < width; x++)
dst[y * dstStride + x] = ref[offset + x];
}
}
// Flip for horizontal.
if (horMode)
{
for (int y = 0; y < width - 1; y++)
{
for (int x = y + 1; x < width; x++)
{
pixel tmp = dst[y * dstStride + x];
dst[y * dstStride + x] = dst[x * dstStride + y];
dst[x * dstStride + y] = tmp;
}
}
}
}
template<int log2Size>
void all_angs_pred_c(pixel *dest, pixel *refPix, pixel *filtPix, int bLuma)
{
const int size = 1 << log2Size;
for (int mode = 2; mode <= 34; mode++)
{
pixel *srcPix = (g_intraFilterFlags[mode] & size ? filtPix : refPix);
pixel *out = dest + ((mode - 2) << (log2Size * 2));
intra_pred_ang_c<size>(out, size, srcPix, mode, bLuma);
// Optimize code don't flip buffer
bool modeHor = (mode < 18);
// transpose the block if this is a horizontal mode
if (modeHor)
{
for (int k = 0; k < size - 1; k++)
{
for (int l = k + 1; l < size; l++)
{
pixel tmp = out[k * size + l];
out[k * size + l] = out[l * size + k];
out[l * size + k] = tmp;
}
}
}
}
}
}
namespace X265_NS {
// x265 private namespace
void setupIntraPrimitives_c(EncoderPrimitives& p)
{
p.cu[BLOCK_4x4].intra_filter = intraFilter<4>;
p.cu[BLOCK_8x8].intra_filter = intraFilter<8>;
p.cu[BLOCK_16x16].intra_filter = intraFilter<16>;
p.cu[BLOCK_32x32].intra_filter = intraFilter<32>;
p.cu[BLOCK_4x4].intra_pred[PLANAR_IDX] = planar_pred_c<2>;
p.cu[BLOCK_8x8].intra_pred[PLANAR_IDX] = planar_pred_c<3>;
p.cu[BLOCK_16x16].intra_pred[PLANAR_IDX] = planar_pred_c<4>;
p.cu[BLOCK_32x32].intra_pred[PLANAR_IDX] = planar_pred_c<5>;
p.cu[BLOCK_4x4].intra_pred[DC_IDX] = intra_pred_dc_c<4>;
p.cu[BLOCK_8x8].intra_pred[DC_IDX] = intra_pred_dc_c<8>;
p.cu[BLOCK_16x16].intra_pred[DC_IDX] = intra_pred_dc_c<16>;
p.cu[BLOCK_32x32].intra_pred[DC_IDX] = intra_pred_dc_c<32>;
for (int i = 2; i < NUM_INTRA_MODE; i++)
{
p.cu[BLOCK_4x4].intra_pred[i] = intra_pred_ang_c<4>;
p.cu[BLOCK_8x8].intra_pred[i] = intra_pred_ang_c<8>;
p.cu[BLOCK_16x16].intra_pred[i] = intra_pred_ang_c<16>;
p.cu[BLOCK_32x32].intra_pred[i] = intra_pred_ang_c<32>;
}
p.cu[BLOCK_4x4].intra_pred_allangs = all_angs_pred_c<2>;
p.cu[BLOCK_8x8].intra_pred_allangs = all_angs_pred_c<3>;
p.cu[BLOCK_16x16].intra_pred_allangs = all_angs_pred_c<4>;
p.cu[BLOCK_32x32].intra_pred_allangs = all_angs_pred_c<5>;
}
}

520
x265/source/common/ipfilter.cpp Normal file
View File

@ -0,0 +1,520 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Deepthi Devaki <deepthidevaki@multicorewareinc.com>,
* Rajesh Paulraj <rajesh@multicorewareinc.com>
* Praveen Kumar Tiwari <praveen@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "primitives.h"
#include "x265.h"
using namespace X265_NS;
#if _MSC_VER
#pragma warning(disable: 4127) // conditional expression is constant, typical for templated functions
#endif
namespace {
// file local namespace
template<int width, int height>
void filterPixelToShort_c(const pixel* src, intptr_t srcStride, int16_t* dst, intptr_t dstStride)
{
int shift = IF_INTERNAL_PREC - X265_DEPTH;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int16_t val = src[col] << shift;
dst[col] = val - (int16_t)IF_INTERNAL_OFFS;
}
src += srcStride;
dst += dstStride;
}
}
static void extendCURowColBorder(pixel* txt, intptr_t stride, int width, int height, int marginX)
{
for (int y = 0; y < height; y++)
{
#if HIGH_BIT_DEPTH
for (int x = 0; x < marginX; x++)
{
txt[-marginX + x] = txt[0];
txt[width + x] = txt[width - 1];
}
#else
memset(txt - marginX, txt[0], marginX);
memset(txt + width, txt[width - 1], marginX);
#endif
txt += stride;
}
}
template<int N, int width, int height>
void interp_horiz_pp_c(const pixel* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int coeffIdx)
{
const int16_t* coeff = (N == 4) ? g_chromaFilter[coeffIdx] : g_lumaFilter[coeffIdx];
int headRoom = IF_FILTER_PREC;
int offset = (1 << (headRoom - 1));
uint16_t maxVal = (1 << X265_DEPTH) - 1;
int cStride = 1;
src -= (N / 2 - 1) * cStride;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * cStride] * coeff[0];
sum += src[col + 1 * cStride] * coeff[1];
sum += src[col + 2 * cStride] * coeff[2];
sum += src[col + 3 * cStride] * coeff[3];
if (N == 8)
{
sum += src[col + 4 * cStride] * coeff[4];
sum += src[col + 5 * cStride] * coeff[5];
sum += src[col + 6 * cStride] * coeff[6];
sum += src[col + 7 * cStride] * coeff[7];
}
int16_t val = (int16_t)((sum + offset) >> headRoom);
if (val < 0) val = 0;
if (val > maxVal) val = maxVal;
dst[col] = (pixel)val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_horiz_ps_c(const pixel* src, intptr_t srcStride, int16_t* dst, intptr_t dstStride, int coeffIdx, int isRowExt)
{
const int16_t* coeff = (N == 4) ? g_chromaFilter[coeffIdx] : g_lumaFilter[coeffIdx];
int headRoom = IF_INTERNAL_PREC - X265_DEPTH;
int shift = IF_FILTER_PREC - headRoom;
int offset = -IF_INTERNAL_OFFS << shift;
int blkheight = height;
src -= N / 2 - 1;
if (isRowExt)
{
src -= (N / 2 - 1) * srcStride;
blkheight += N - 1;
}
int row, col;
for (row = 0; row < blkheight; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0] * coeff[0];
sum += src[col + 1] * coeff[1];
sum += src[col + 2] * coeff[2];
sum += src[col + 3] * coeff[3];
if (N == 8)
{
sum += src[col + 4] * coeff[4];
sum += src[col + 5] * coeff[5];
sum += src[col + 6] * coeff[6];
sum += src[col + 7] * coeff[7];
}
int16_t val = (int16_t)((sum + offset) >> shift);
dst[col] = val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_vert_pp_c(const pixel* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int coeffIdx)
{
const int16_t* c = (N == 4) ? g_chromaFilter[coeffIdx] : g_lumaFilter[coeffIdx];
int shift = IF_FILTER_PREC;
int offset = 1 << (shift - 1);
uint16_t maxVal = (1 << X265_DEPTH) - 1;
src -= (N / 2 - 1) * srcStride;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * srcStride] * c[0];
sum += src[col + 1 * srcStride] * c[1];
sum += src[col + 2 * srcStride] * c[2];
sum += src[col + 3 * srcStride] * c[3];
if (N == 8)
{
sum += src[col + 4 * srcStride] * c[4];
sum += src[col + 5 * srcStride] * c[5];
sum += src[col + 6 * srcStride] * c[6];
sum += src[col + 7 * srcStride] * c[7];
}
int16_t val = (int16_t)((sum + offset) >> shift);
val = (val < 0) ? 0 : val;
val = (val > maxVal) ? maxVal : val;
dst[col] = (pixel)val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_vert_ps_c(const pixel* src, intptr_t srcStride, int16_t* dst, intptr_t dstStride, int coeffIdx)
{
const int16_t* c = (N == 4) ? g_chromaFilter[coeffIdx] : g_lumaFilter[coeffIdx];
int headRoom = IF_INTERNAL_PREC - X265_DEPTH;
int shift = IF_FILTER_PREC - headRoom;
int offset = -IF_INTERNAL_OFFS << shift;
src -= (N / 2 - 1) * srcStride;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * srcStride] * c[0];
sum += src[col + 1 * srcStride] * c[1];
sum += src[col + 2 * srcStride] * c[2];
sum += src[col + 3 * srcStride] * c[3];
if (N == 8)
{
sum += src[col + 4 * srcStride] * c[4];
sum += src[col + 5 * srcStride] * c[5];
sum += src[col + 6 * srcStride] * c[6];
sum += src[col + 7 * srcStride] * c[7];
}
int16_t val = (int16_t)((sum + offset) >> shift);
dst[col] = val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_vert_sp_c(const int16_t* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int coeffIdx)
{
int headRoom = IF_INTERNAL_PREC - X265_DEPTH;
int shift = IF_FILTER_PREC + headRoom;
int offset = (1 << (shift - 1)) + (IF_INTERNAL_OFFS << IF_FILTER_PREC);
uint16_t maxVal = (1 << X265_DEPTH) - 1;
const int16_t* coeff = (N == 8 ? g_lumaFilter[coeffIdx] : g_chromaFilter[coeffIdx]);
src -= (N / 2 - 1) * srcStride;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * srcStride] * coeff[0];
sum += src[col + 1 * srcStride] * coeff[1];
sum += src[col + 2 * srcStride] * coeff[2];
sum += src[col + 3 * srcStride] * coeff[3];
if (N == 8)
{
sum += src[col + 4 * srcStride] * coeff[4];
sum += src[col + 5 * srcStride] * coeff[5];
sum += src[col + 6 * srcStride] * coeff[6];
sum += src[col + 7 * srcStride] * coeff[7];
}
int16_t val = (int16_t)((sum + offset) >> shift);
val = (val < 0) ? 0 : val;
val = (val > maxVal) ? maxVal : val;
dst[col] = (pixel)val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_vert_ss_c(const int16_t* src, intptr_t srcStride, int16_t* dst, intptr_t dstStride, int coeffIdx)
{
const int16_t* c = (N == 8 ? g_lumaFilter[coeffIdx] : g_chromaFilter[coeffIdx]);
int shift = IF_FILTER_PREC;
int row, col;
src -= (N / 2 - 1) * srcStride;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * srcStride] * c[0];
sum += src[col + 1 * srcStride] * c[1];
sum += src[col + 2 * srcStride] * c[2];
sum += src[col + 3 * srcStride] * c[3];
if (N == 8)
{
sum += src[col + 4 * srcStride] * c[4];
sum += src[col + 5 * srcStride] * c[5];
sum += src[col + 6 * srcStride] * c[6];
sum += src[col + 7 * srcStride] * c[7];
}
int16_t val = (int16_t)((sum) >> shift);
dst[col] = val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N>
void filterVertical_sp_c(const int16_t* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int width, int height, int coeffIdx)
{
int headRoom = IF_INTERNAL_PREC - X265_DEPTH;
int shift = IF_FILTER_PREC + headRoom;
int offset = (1 << (shift - 1)) + (IF_INTERNAL_OFFS << IF_FILTER_PREC);
uint16_t maxVal = (1 << X265_DEPTH) - 1;
const int16_t* coeff = (N == 8 ? g_lumaFilter[coeffIdx] : g_chromaFilter[coeffIdx]);
src -= (N / 2 - 1) * srcStride;
int row, col;
for (row = 0; row < height; row++)
{
for (col = 0; col < width; col++)
{
int sum;
sum = src[col + 0 * srcStride] * coeff[0];
sum += src[col + 1 * srcStride] * coeff[1];
sum += src[col + 2 * srcStride] * coeff[2];
sum += src[col + 3 * srcStride] * coeff[3];
if (N == 8)
{
sum += src[col + 4 * srcStride] * coeff[4];
sum += src[col + 5 * srcStride] * coeff[5];
sum += src[col + 6 * srcStride] * coeff[6];
sum += src[col + 7 * srcStride] * coeff[7];
}
int16_t val = (int16_t)((sum + offset) >> shift);
val = (val < 0) ? 0 : val;
val = (val > maxVal) ? maxVal : val;
dst[col] = (pixel)val;
}
src += srcStride;
dst += dstStride;
}
}
template<int N, int width, int height>
void interp_hv_pp_c(const pixel* src, intptr_t srcStride, pixel* dst, intptr_t dstStride, int idxX, int idxY)
{
short immedVals[(64 + 8) * (64 + 8)];
interp_horiz_ps_c<N, width, height>(src, srcStride, immedVals, width, idxX, 1);
filterVertical_sp_c<N>(immedVals + 3 * width, width, dst, dstStride, width, height, idxY);
}
}
namespace X265_NS {
// x265 private namespace
#define CHROMA_420(W, H) \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_hpp = interp_horiz_pp_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_hps = interp_horiz_ps_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_vpp = interp_vert_pp_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_vps = interp_vert_ps_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_vsp = interp_vert_sp_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].filter_vss = interp_vert_ss_c<4, W, H>; \
p.chroma[X265_CSP_I420].pu[CHROMA_420_ ## W ## x ## H].p2s = filterPixelToShort_c<W, H>;
#define CHROMA_422(W, H) \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_hpp = interp_horiz_pp_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_hps = interp_horiz_ps_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_vpp = interp_vert_pp_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_vps = interp_vert_ps_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_vsp = interp_vert_sp_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].filter_vss = interp_vert_ss_c<4, W, H>; \
p.chroma[X265_CSP_I422].pu[CHROMA_422_ ## W ## x ## H].p2s = filterPixelToShort_c<W, H>;
#define CHROMA_444(W, H) \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_hpp = interp_horiz_pp_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_hps = interp_horiz_ps_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_vpp = interp_vert_pp_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_vps = interp_vert_ps_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_vsp = interp_vert_sp_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].filter_vss = interp_vert_ss_c<4, W, H>; \
p.chroma[X265_CSP_I444].pu[LUMA_ ## W ## x ## H].p2s = filterPixelToShort_c<W, H>;
#define LUMA(W, H) \
p.pu[LUMA_ ## W ## x ## H].luma_hpp = interp_horiz_pp_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_hps = interp_horiz_ps_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_vpp = interp_vert_pp_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_vps = interp_vert_ps_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_vsp = interp_vert_sp_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_vss = interp_vert_ss_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].luma_hvpp = interp_hv_pp_c<8, W, H>; \
p.pu[LUMA_ ## W ## x ## H].convert_p2s = filterPixelToShort_c<W, H>;
void setupFilterPrimitives_c(EncoderPrimitives& p)
{
LUMA(4, 4);
LUMA(8, 8);
CHROMA_420(4, 4);
LUMA(4, 8);
CHROMA_420(2, 4);
LUMA(8, 4);
CHROMA_420(4, 2);
LUMA(16, 16);
CHROMA_420(8, 8);
LUMA(16, 8);
CHROMA_420(8, 4);
LUMA(8, 16);
CHROMA_420(4, 8);
LUMA(16, 12);
CHROMA_420(8, 6);
LUMA(12, 16);
CHROMA_420(6, 8);
LUMA(16, 4);
CHROMA_420(8, 2);
LUMA(4, 16);
CHROMA_420(2, 8);
LUMA(32, 32);
CHROMA_420(16, 16);
LUMA(32, 16);
CHROMA_420(16, 8);
LUMA(16, 32);
CHROMA_420(8, 16);
LUMA(32, 24);
CHROMA_420(16, 12);
LUMA(24, 32);
CHROMA_420(12, 16);
LUMA(32, 8);
CHROMA_420(16, 4);
LUMA(8, 32);
CHROMA_420(4, 16);
LUMA(64, 64);
CHROMA_420(32, 32);
LUMA(64, 32);
CHROMA_420(32, 16);
LUMA(32, 64);
CHROMA_420(16, 32);
LUMA(64, 48);
CHROMA_420(32, 24);
LUMA(48, 64);
CHROMA_420(24, 32);
LUMA(64, 16);
CHROMA_420(32, 8);
LUMA(16, 64);
CHROMA_420(8, 32);
CHROMA_422(4, 8);
CHROMA_422(4, 4);
CHROMA_422(2, 4);
CHROMA_422(2, 8);
CHROMA_422(8, 16);
CHROMA_422(8, 8);
CHROMA_422(4, 16);
CHROMA_422(8, 12);
CHROMA_422(6, 16);
CHROMA_422(8, 4);
CHROMA_422(2, 16);
CHROMA_422(16, 32);
CHROMA_422(16, 16);
CHROMA_422(8, 32);
CHROMA_422(16, 24);
CHROMA_422(12, 32);
CHROMA_422(16, 8);
CHROMA_422(4, 32);
CHROMA_422(32, 64);
CHROMA_422(32, 32);
CHROMA_422(16, 64);
CHROMA_422(32, 48);
CHROMA_422(24, 64);
CHROMA_422(32, 16);
CHROMA_422(8, 64);
CHROMA_444(4, 4);
CHROMA_444(8, 8);
CHROMA_444(4, 8);
CHROMA_444(8, 4);
CHROMA_444(16, 16);
CHROMA_444(16, 8);
CHROMA_444(8, 16);
CHROMA_444(16, 12);
CHROMA_444(12, 16);
CHROMA_444(16, 4);
CHROMA_444(4, 16);
CHROMA_444(32, 32);
CHROMA_444(32, 16);
CHROMA_444(16, 32);
CHROMA_444(32, 24);
CHROMA_444(24, 32);
CHROMA_444(32, 8);
CHROMA_444(8, 32);
CHROMA_444(64, 64);
CHROMA_444(64, 32);
CHROMA_444(32, 64);
CHROMA_444(64, 48);
CHROMA_444(48, 64);
CHROMA_444(64, 16);
CHROMA_444(16, 64);
p.extendRowBorder = extendCURowColBorder;
}
}

154
x265/source/common/loopfilter.cpp Normal file
View File

@ -0,0 +1,154 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Praveen Kumar Tiwari <praveen@multicorewareinc.com>
* Dnyaneshwar Gorade <dnyaneshwar@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "primitives.h"
#define PIXEL_MIN 0
#define PIXEL_MAX ((1 << X265_DEPTH) - 1)
namespace {
/* get the sign of input variable (TODO: this is a dup, make common) */
inline int8_t signOf(int x)
{
return (x >> 31) | ((int)((((uint32_t)-x)) >> 31));
}
static void calSign(int8_t *dst, const pixel *src1, const pixel *src2, const int endX)
{
for (int x = 0; x < endX; x++)
dst[x] = signOf(src1[x] - src2[x]);
}
static void processSaoCUE0(pixel * rec, int8_t * offsetEo, int width, int8_t* signLeft, intptr_t stride)
{
int x, y;
int8_t signRight, signLeft0;
int8_t edgeType;
for (y = 0; y < 2; y++)
{
signLeft0 = signLeft[y];
for (x = 0; x < width; x++)
{
signRight = ((rec[x] - rec[x + 1]) < 0) ? -1 : ((rec[x] - rec[x + 1]) > 0) ? 1 : 0;
edgeType = signRight + signLeft0 + 2;
signLeft0 = -signRight;
rec[x] = x265_clip(rec[x] + offsetEo[edgeType]);
}
rec += stride;
}
}
static void processSaoCUE1(pixel* rec, int8_t* upBuff1, int8_t* offsetEo, intptr_t stride, int width)
{
int x;
int8_t signDown;
int edgeType;
for (x = 0; x < width; x++)
{
signDown = signOf(rec[x] - rec[x + stride]);
edgeType = signDown + upBuff1[x] + 2;
upBuff1[x] = -signDown;
rec[x] = x265_clip(rec[x] + offsetEo[edgeType]);
}
}
static void processSaoCUE1_2Rows(pixel* rec, int8_t* upBuff1, int8_t* offsetEo, intptr_t stride, int width)
{
int x, y;
int8_t signDown;
int edgeType;
for (y = 0; y < 2; y++)
{
for (x = 0; x < width; x++)
{
signDown = signOf(rec[x] - rec[x + stride]);
edgeType = signDown + upBuff1[x] + 2;
upBuff1[x] = -signDown;
rec[x] = x265_clip(rec[x] + offsetEo[edgeType]);
}
rec += stride;
}
}
static void processSaoCUE2(pixel * rec, int8_t * bufft, int8_t * buff1, int8_t * offsetEo, int width, intptr_t stride)
{
int x;
for (x = 0; x < width; x++)
{
int8_t signDown = signOf(rec[x] - rec[x + stride + 1]);
int edgeType = signDown + buff1[x] + 2;
bufft[x + 1] = -signDown;
rec[x] = x265_clip(rec[x] + offsetEo[edgeType]);;
}
}
static void processSaoCUE3(pixel *rec, int8_t *upBuff1, int8_t *offsetEo, intptr_t stride, int startX, int endX)
{
int8_t signDown;
int8_t edgeType;
for (int x = startX + 1; x < endX; x++)
{
signDown = signOf(rec[x] - rec[x + stride]);
edgeType = signDown + upBuff1[x] + 2;
upBuff1[x - 1] = -signDown;
rec[x] = x265_clip(rec[x] + offsetEo[edgeType]);
}
}
static void processSaoCUB0(pixel* rec, const int8_t* offset, int ctuWidth, int ctuHeight, intptr_t stride)
{
#define SAO_BO_BITS 5
const int boShift = X265_DEPTH - SAO_BO_BITS;
int x, y;
for (y = 0; y < ctuHeight; y++)
{
for (x = 0; x < ctuWidth; x++)
{
rec[x] = x265_clip(rec[x] + offset[rec[x] >> boShift]);
}
rec += stride;
}
}
}
namespace X265_NS {
void setupLoopFilterPrimitives_c(EncoderPrimitives &p)
{
p.saoCuOrgE0 = processSaoCUE0;
p.saoCuOrgE1 = processSaoCUE1;
p.saoCuOrgE1_2Rows = processSaoCUE1_2Rows;
p.saoCuOrgE2[0] = processSaoCUE2;
p.saoCuOrgE2[1] = processSaoCUE2;
p.saoCuOrgE3[0] = processSaoCUE3;
p.saoCuOrgE3[1] = processSaoCUE3;
p.saoCuOrgB0 = processSaoCUB0;
p.sign = calSign;
}
}

165
x265/source/common/lowres.cpp Normal file
View File

@ -0,0 +1,165 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "picyuv.h"
#include "lowres.h"
#include "mv.h"
using namespace X265_NS;
bool Lowres::create(PicYuv *origPic, int _bframes, bool bAQEnabled)
{
isLowres = true;
bframes = _bframes;
width = origPic->m_picWidth / 2;
lines = origPic->m_picHeight / 2;
lumaStride = width + 2 * origPic->m_lumaMarginX;
if (lumaStride & 31)
lumaStride += 32 - (lumaStride & 31);
maxBlocksInRow = (width + X265_LOWRES_CU_SIZE - 1) >> X265_LOWRES_CU_BITS;
maxBlocksInCol = (lines + X265_LOWRES_CU_SIZE - 1) >> X265_LOWRES_CU_BITS;
int cuCount = maxBlocksInRow * maxBlocksInCol;
/* rounding the width to multiple of lowres CU size */
width = maxBlocksInRow * X265_LOWRES_CU_SIZE;
lines = maxBlocksInCol * X265_LOWRES_CU_SIZE;
size_t planesize = lumaStride * (lines + 2 * origPic->m_lumaMarginY);
size_t padoffset = lumaStride * origPic->m_lumaMarginY + origPic->m_lumaMarginX;
if (bAQEnabled)
{
CHECKED_MALLOC(qpAqOffset, double, cuCount);
CHECKED_MALLOC(invQscaleFactor, int, cuCount);
CHECKED_MALLOC(qpCuTreeOffset, double, cuCount);
}
CHECKED_MALLOC(propagateCost, uint16_t, cuCount);
/* allocate lowres buffers */
CHECKED_MALLOC_ZERO(buffer[0], pixel, 4 * planesize);
buffer[1] = buffer[0] + planesize;
buffer[2] = buffer[1] + planesize;
buffer[3] = buffer[2] + planesize;
lowresPlane[0] = buffer[0] + padoffset;
lowresPlane[1] = buffer[1] + padoffset;
lowresPlane[2] = buffer[2] + padoffset;
lowresPlane[3] = buffer[3] + padoffset;
CHECKED_MALLOC(intraCost, int32_t, cuCount);
CHECKED_MALLOC(intraMode, uint8_t, cuCount);
for (int i = 0; i < bframes + 2; i++)
{
for (int j = 0; j < bframes + 2; j++)
{
CHECKED_MALLOC(rowSatds[i][j], int32_t, maxBlocksInCol);
CHECKED_MALLOC(lowresCosts[i][j], uint16_t, cuCount);
}
}
for (int i = 0; i < bframes + 1; i++)
{
CHECKED_MALLOC(lowresMvs[0][i], MV, cuCount);
CHECKED_MALLOC(lowresMvs[1][i], MV, cuCount);
CHECKED_MALLOC(lowresMvCosts[0][i], int32_t, cuCount);
CHECKED_MALLOC(lowresMvCosts[1][i], int32_t, cuCount);
}
return true;
fail:
return false;
}
void Lowres::destroy()
{
X265_FREE(buffer[0]);
X265_FREE(intraCost);
X265_FREE(intraMode);
for (int i = 0; i < bframes + 2; i++)
{
for (int j = 0; j < bframes + 2; j++)
{
X265_FREE(rowSatds[i][j]);
X265_FREE(lowresCosts[i][j]);
}
}
for (int i = 0; i < bframes + 1; i++)
{
X265_FREE(lowresMvs[0][i]);
X265_FREE(lowresMvs[1][i]);
X265_FREE(lowresMvCosts[0][i]);
X265_FREE(lowresMvCosts[1][i]);
}
X265_FREE(qpAqOffset);
X265_FREE(invQscaleFactor);
X265_FREE(qpCuTreeOffset);
X265_FREE(propagateCost);
}
// (re) initialize lowres state
void Lowres::init(PicYuv *origPic, int poc)
{
bLastMiniGopBFrame = false;
bScenecut = false; // could be a scene-cut, until ruled out by flash detection
bKeyframe = false; // Not a keyframe unless identified by lookahead
frameNum = poc;
leadingBframes = 0;
indB = 0;
satdCost = (int64_t)-1;
memset(costEst, -1, sizeof(costEst));
memset(weightedCostDelta, 0, sizeof(weightedCostDelta));
if (qpAqOffset && invQscaleFactor)
memset(costEstAq, -1, sizeof(costEstAq));
for (int y = 0; y < bframes + 2; y++)
for (int x = 0; x < bframes + 2; x++)
rowSatds[y][x][0] = -1;
for (int i = 0; i < bframes + 1; i++)
{
lowresMvs[0][i][0].x = 0x7FFF;
lowresMvs[1][i][0].x = 0x7FFF;
}
for (int i = 0; i < bframes + 2; i++)
intraMbs[i] = 0;
/* downscale and generate 4 hpel planes for lookahead */
primitives.frameInitLowres(origPic->m_picOrg[0],
lowresPlane[0], lowresPlane[1], lowresPlane[2], lowresPlane[3],
origPic->m_stride, lumaStride, width, lines);
/* extend hpel planes for motion search */
extendPicBorder(lowresPlane[0], lumaStride, width, lines, origPic->m_lumaMarginX, origPic->m_lumaMarginY);
extendPicBorder(lowresPlane[1], lumaStride, width, lines, origPic->m_lumaMarginX, origPic->m_lumaMarginY);
extendPicBorder(lowresPlane[2], lumaStride, width, lines, origPic->m_lumaMarginX, origPic->m_lumaMarginY);
extendPicBorder(lowresPlane[3], lumaStride, width, lines, origPic->m_lumaMarginX, origPic->m_lumaMarginY);
fpelPlane[0] = lowresPlane[0];
}

159
x265/source/common/lowres.h Normal file
View File

@ -0,0 +1,159 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_LOWRES_H
#define X265_LOWRES_H
#include "primitives.h"
#include "common.h"
#include "picyuv.h"
#include "mv.h"
namespace X265_NS {
// private namespace
struct ReferencePlanes
{
ReferencePlanes() { memset(this, 0, sizeof(ReferencePlanes)); }
pixel* fpelPlane[3];
pixel* lowresPlane[4];
PicYuv* reconPic;
bool isWeighted;
bool isLowres;
intptr_t lumaStride;
intptr_t chromaStride;
struct {
int weight;
int offset;
int shift;
int round;
} w[3];
pixel* getLumaAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return fpelPlane[0] + reconPic->m_cuOffsetY[ctuAddr] + reconPic->m_buOffsetY[absPartIdx]; }
pixel* getCbAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return fpelPlane[1] + reconPic->m_cuOffsetC[ctuAddr] + reconPic->m_buOffsetC[absPartIdx]; }
pixel* getCrAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return fpelPlane[2] + reconPic->m_cuOffsetC[ctuAddr] + reconPic->m_buOffsetC[absPartIdx]; }
/* lowres motion compensation, you must provide a buffer and stride for QPEL averaged pixels
* in case QPEL is required. Else it returns a pointer to the HPEL pixels */
inline pixel *lowresMC(intptr_t blockOffset, const MV& qmv, pixel *buf, intptr_t& outstride)
{
if ((qmv.x | qmv.y) & 1)
{
int hpelA = (qmv.y & 2) | ((qmv.x & 2) >> 1);
pixel *frefA = lowresPlane[hpelA] + blockOffset + (qmv.x >> 2) + (qmv.y >> 2) * lumaStride;
int qmvx = qmv.x + (qmv.x & 1);
int qmvy = qmv.y + (qmv.y & 1);
int hpelB = (qmvy & 2) | ((qmvx & 2) >> 1);
pixel *frefB = lowresPlane[hpelB] + blockOffset + (qmvx >> 2) + (qmvy >> 2) * lumaStride;
primitives.pu[LUMA_8x8].pixelavg_pp(buf, outstride, frefA, lumaStride, frefB, lumaStride, 32);
return buf;
}
else
{
outstride = lumaStride;
int hpel = (qmv.y & 2) | ((qmv.x & 2) >> 1);
return lowresPlane[hpel] + blockOffset + (qmv.x >> 2) + (qmv.y >> 2) * lumaStride;
}
}
inline int lowresQPelCost(pixel *fenc, intptr_t blockOffset, const MV& qmv, pixelcmp_t comp)
{
if ((qmv.x | qmv.y) & 1)
{
ALIGN_VAR_16(pixel, subpelbuf[8 * 8]);
int hpelA = (qmv.y & 2) | ((qmv.x & 2) >> 1);
pixel *frefA = lowresPlane[hpelA] + blockOffset + (qmv.x >> 2) + (qmv.y >> 2) * lumaStride;
int qmvx = qmv.x + (qmv.x & 1);
int qmvy = qmv.y + (qmv.y & 1);
int hpelB = (qmvy & 2) | ((qmvx & 2) >> 1);
pixel *frefB = lowresPlane[hpelB] + blockOffset + (qmvx >> 2) + (qmvy >> 2) * lumaStride;
primitives.pu[LUMA_8x8].pixelavg_pp(subpelbuf, 8, frefA, lumaStride, frefB, lumaStride, 32);
return comp(fenc, FENC_STRIDE, subpelbuf, 8);
}
else
{
int hpel = (qmv.y & 2) | ((qmv.x & 2) >> 1);
pixel *fref = lowresPlane[hpel] + blockOffset + (qmv.x >> 2) + (qmv.y >> 2) * lumaStride;
return comp(fenc, FENC_STRIDE, fref, lumaStride);
}
}
};
/* lowres buffers, sizes and strides */
struct Lowres : public ReferencePlanes
{
pixel *buffer[4];
int frameNum; // Presentation frame number
int sliceType; // Slice type decided by lookahead
int width; // width of lowres frame in pixels
int lines; // height of lowres frame in pixel lines
int leadingBframes; // number of leading B frames for P or I
bool bScenecut; // Set to false if the frame cannot possibly be part of a real scenecut.
bool bKeyframe;
bool bLastMiniGopBFrame;
/* lookahead output data */
int64_t costEst[X265_BFRAME_MAX + 2][X265_BFRAME_MAX + 2];
int64_t costEstAq[X265_BFRAME_MAX + 2][X265_BFRAME_MAX + 2];
int32_t* rowSatds[X265_BFRAME_MAX + 2][X265_BFRAME_MAX + 2];
int intraMbs[X265_BFRAME_MAX + 2];
int32_t* intraCost;
uint8_t* intraMode;
int64_t satdCost;
uint16_t* lowresCostForRc;
uint16_t(*lowresCosts[X265_BFRAME_MAX + 2][X265_BFRAME_MAX + 2]);
int32_t* lowresMvCosts[2][X265_BFRAME_MAX + 1];
MV* lowresMvs[2][X265_BFRAME_MAX + 1];
uint32_t maxBlocksInRow;
uint32_t maxBlocksInCol;
/* used for vbvLookahead */
int plannedType[X265_LOOKAHEAD_MAX + 1];
int64_t plannedSatd[X265_LOOKAHEAD_MAX + 1];
int indB;
int bframes;
/* rate control / adaptive quant data */
double* qpAqOffset; // AQ QP offset values for each 16x16 CU
double* qpCuTreeOffset; // cuTree QP offset values for each 16x16 CU
int* invQscaleFactor; // qScale values for qp Aq Offsets
uint64_t wp_ssd[3]; // This is different than SSDY, this is sum(pixel^2) - sum(pixel)^2 for entire frame
uint64_t wp_sum[3];
/* cutree intermediate data */
uint16_t* propagateCost;
double weightedCostDelta[X265_BFRAME_MAX + 2];
bool create(PicYuv *origPic, int _bframes, bool bAqEnabled);
void destroy();
void init(PicYuv *origPic, int poc);
};
}
#endif // ifndef X265_LOWRES_H

268
x265/source/common/md5.cpp Normal file
View File

@ -0,0 +1,268 @@
/*****************************************************************************
* md5.cpp: Calculate MD5 for SEI
*****************************************************************************
* Copyright (C) 2011-2012 x265 project
*
* Authors: Min Chen <chenm003@163.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation;
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at chenm003@163.com.
*****************************************************************************/
#include "common.h"
#include "md5.h"
namespace X265_NS {
// private x265 namespace
#ifndef ARCH_BIG_ENDIAN
#define byteReverse(buf, len) /* Nothing */
#else
static void byteReverse(uint8_t_t *buf, unsigned int nSize)
{
int i;
uint32_t tmp;
for (i = 0; i < nSize; i++)
{
tmp = ((unsigned int)buf[3] << 8 | buf[2]) << 16 |
((unsigned int)buf[1] << 8 | buf[0]);
*(uint32_t*)buf = tmp;
buf += 4;
}
}
#endif // ifndef ARCH_BIG_ENDIAN
void MD5Transform(uint32_t *buf, uint32_t *in);
/*
* Start MD5 accumulation. Set bit count to 0 and buffer to mysterious
* initialization constants.
*/
void MD5Init(MD5Context *ctx)
{
ctx->buf[0] = 0x67452301;
ctx->buf[1] = 0xefcdab89;
ctx->buf[2] = 0x98badcfe;
ctx->buf[3] = 0x10325476;
ctx->bits[0] = 0;
ctx->bits[1] = 0;
}
/*
* Update context to reflect the concatenation of another buffer full
* of bytes.
*/
void MD5Update(MD5Context *ctx, uint8_t *buf, uint32_t len)
{
uint32_t t;
/* Update bitcount */
t = ctx->bits[0];
if ((ctx->bits[0] = t + ((uint32_t)len << 3)) < t)
ctx->bits[1]++; /* Carry from low to high */
ctx->bits[1] += len >> 29;
t = (t >> 3) & 0x3F; /* Bytes already in shsInfo->data */
/* Handle any leading odd-sized chunks */
if (t)
{
uint8_t *p = (uint8_t*)ctx->in + t;
t = 64 - t;
if (len < t)
{
memcpy(p, buf, len);
return;
}
memcpy(p, buf, t);
byteReverse(ctx->in, 16);
MD5Transform(ctx->buf, (uint32_t*)ctx->in);
buf += t;
len -= t;
}
/* Process data in 64-byte chunks */
while (len >= 64)
{
memcpy(ctx->in, buf, 64);
byteReverse(ctx->in, 16);
MD5Transform(ctx->buf, (uint32_t*)ctx->in);
buf += 64;
len -= 64;
}
/* Handle any remaining bytes of data. */
memcpy(ctx->in, buf, len);
}
/*
* Final wrapup - pad to 64-byte boundary with the bit pattern
* 1 0* (64-bit count of bits processed, MSB-first)
*/
void MD5Final(MD5Context *ctx, uint8_t *digest)
{
uint32_t count;
uint8_t *p;
/* Compute number of bytes mod 64 */
count = (ctx->bits[0] >> 3) & 0x3F;
/* Set the first char of padding to 0x80. This is safe since there is
always at least one byte free */
p = ctx->in + count;
*p++ = 0x80;
/* Bytes of padding needed to make 64 bytes */
count = 64 - 1 - count;
/* Pad out to 56 mod 64 */
if (count < 8)
{
/* Two lots of padding: Pad the first block to 64 bytes */
memset(p, 0, count);
byteReverse(ctx->in, 16);
MD5Transform(ctx->buf, (uint32_t*)ctx->in);
/* Now fill the next block with 56 bytes */
memset(ctx->in, 0, 56);
}
else
{
/* Pad block to 56 bytes */
memset(p, 0, count - 8);
}
byteReverse(ctx->in, 14);
/* Append length in bits and transform */
// CHECK_ME: Always use 32-bits operator
uint32_t *table = (uint32_t*)&ctx->in;
table[14] = ctx->bits[0];
table[15] = ctx->bits[1];
MD5Transform(ctx->buf, (uint32_t*)ctx->in);
byteReverse((uint8_t*)ctx->buf, 4);
memcpy(digest, ctx->buf, 16);
memset(ctx, 0, sizeof(*ctx)); /* In case it's sensitive */
}
/* The four core functions - F1 is optimized somewhat */
/* #define F1(x, y, z) (x & y | ~x & z) */
#define F1(x, y, z) (z ^ (x & (y ^ z)))
#define F2(x, y, z) F1(z, x, y)
#define F3(x, y, z) (x ^ y ^ z)
#define F4(x, y, z) (y ^ (x | ~z))
/* This is the central step in the MD5 algorithm. */
#define MD5STEP(f, w, x, y, z, data, s) \
(w += f(x, y, z) + data, w = w << s | w >> (32 - s), w += x)
/*
* The core of the MD5 algorithm, this alters an existing MD5 hash to
* reflect the addition of 16 longwords of new data. MD5Update blocks
* the data and converts bytes into longwords for this routine.
*/
void MD5Transform(uint32_t *buf, uint32_t *in)
{
register uint32_t a, b, c, d;
a = buf[0];
b = buf[1];
c = buf[2];
d = buf[3];
MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
buf[0] += a;
buf[1] += b;
buf[2] += c;
buf[3] += d;
}
}

79
x265/source/common/md5.h Normal file
View File

@ -0,0 +1,79 @@
/*****************************************************************************
* md5.h: Calculate MD5
*****************************************************************************
* Copyright (C) 2011-2012 x265 project
*
* Authors: Min Chen <chenm003@163.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation;
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at chenm003@163.com.
*****************************************************************************/
#ifndef X265_MD5_H
#define X265_MD5_H
#include "common.h"
namespace X265_NS {
//private x265 namespace
typedef struct MD5Context
{
uint32_t buf[4];
uint32_t bits[2];
unsigned char in[64];
} MD5Context;
void MD5Init(MD5Context *context);
void MD5Update(MD5Context *context, unsigned char *buf, uint32_t len);
void MD5Final(MD5Context *ctx, uint8_t *digest);
class MD5
{
public:
/**
* initialize digest state
*/
MD5()
{
MD5Init(&m_state);
}
/**
* compute digest over buf of length len.
* multiple calls may extend the digest over more data.
*/
void update(unsigned char *buf, unsigned len)
{
MD5Update(&m_state, buf, len);
}
/**
* flush any outstanding MD5 data, write the digest into digest.
*/
void finalize(unsigned char digest[16])
{
MD5Final(&m_state, digest);
}
private:
MD5Context m_state;
};
}
#endif // ifndef X265_MD5_H

111
x265/source/common/mv.h Normal file
View File

@ -0,0 +1,111 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_MV_H
#define X265_MV_H
#include "common.h"
#include "primitives.h"
namespace X265_NS {
// private x265 namespace
#if _MSC_VER
#pragma warning(disable: 4201) // non-standard extension used (nameless struct/union)
#endif
struct MV
{
public:
union {
struct { int16_t x, y; };
int32_t word;
};
MV() {}
MV(int32_t w) : word(w) {}
MV(int16_t _x, int16_t _y) : x(_x), y(_y) {}
MV& operator =(uint32_t w) { word = w; return *this; }
MV& operator +=(const MV& other) { x += other.x; y += other.y; return *this; }
MV& operator -=(const MV& other) { x -= other.x; y -= other.y; return *this; }
MV& operator >>=(int i) { x >>= i; y >>= i; return *this; }
#if USING_FTRAPV
/* avoid signed left-shifts when -ftrapv is enabled */
MV& operator <<=(int i) { x *= (1 << i); y *= (1 << i); return *this; }
MV operator <<(int i) const { return MV(x * (1 << i), y * (1 << i)); }
#else
MV& operator <<=(int i) { x <<= i; y <<= i; return *this; }
MV operator <<(int i) const { return MV(x << i, y << i); }
#endif
MV operator >>(int i) const { return MV(x >> i, y >> i); }
MV operator *(int16_t i) const { return MV(x * i, y * i); }
MV operator -(const MV& other) const { return MV(x - other.x, y - other.y); }
MV operator +(const MV& other) const { return MV(x + other.x, y + other.y); }
bool operator ==(const MV& other) const { return word == other.word; }
bool operator !=(const MV& other) const { return word != other.word; }
bool operator !() const { return !word; }
// Scale down a QPEL mv to FPEL mv, rounding up by one HPEL offset
MV roundToFPel() const { return MV((x + 2) >> 2, (y + 2) >> 2); }
// Scale up an FPEL mv to QPEL by shifting up two bits
MV toQPel() const { return *this << 2; }
bool inline notZero() const { return this->word != 0; }
bool inline isSubpel() const { return (this->word & 0x00030003) != 0; }
MV mvmin(const MV& m) const { return MV(x > m.x ? m.x : x, y > m.y ? m.y : y); }
MV mvmax(const MV& m) const { return MV(x < m.x ? m.x : x, y < m.y ? m.y : y); }
MV clipped(const MV& _min, const MV& _max) const
{
MV cl = mvmin(_max);
return cl.mvmax(_min);
}
// returns true if MV is within range (inclusive)
bool checkRange(const MV& _min, const MV& _max) const
{
return x >= _min.x && x <= _max.x && y >= _min.y && y <= _max.y;
}
};
}
#endif // ifndef X265_MV_H

1562
x265/source/common/param.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

62
x265/source/common/param.h Normal file
View File

@ -0,0 +1,62 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Deepthi Nandakumar <deepthi@multicorewareinc.com>
* Praveen Kumar Tiwari <praveen@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_PARAM_H
#define X265_PARAM_H
namespace X265_NS {
int x265_check_params(x265_param *param);
int x265_set_globals(x265_param *param);
void x265_print_params(x265_param *param);
void x265_print_reconfigured_params(x265_param* param, x265_param* reconfiguredParam);
void x265_param_apply_fastfirstpass(x265_param *p);
char* x265_param2string(x265_param *param);
int x265_atoi(const char *str, bool& bError);
double x265_atof(const char *str, bool& bError);
int parseCpuName(const char *value, bool& bError);
void setParamAspectRatio(x265_param *p, int width, int height);
void getParamAspectRatio(x265_param *p, int& width, int& height);
bool parseLambdaFile(x265_param *param);
/* this table is kept internal to avoid confusion, since log level indices start at -1 */
static const char * const logLevelNames[] = { "none", "error", "warning", "info", "debug", "full", 0 };
#if EXPORT_C_API
#define PARAM_NS
#else
/* declare param functions within private namespace */
void x265_param_free(x265_param *);
x265_param* x265_param_alloc();
void x265_param_default(x265_param *param);
int x265_param_default_preset(x265_param *, const char *preset, const char *tune);
int x265_param_apply_profile(x265_param *, const char *profile);
int x265_param_parse(x265_param *p, const char *name, const char *value);
#define PARAM_NS X265_NS
#endif
#define MAXPARAMSIZE 2000
}
#endif // ifndef X265_PARAM_H

151
x265/source/common/piclist.cpp Normal file
View File

@ -0,0 +1,151 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "piclist.h"
#include "frame.h"
using namespace X265_NS;
void PicList::pushFront(Frame& curFrame)
{
X265_CHECK(!curFrame.m_next && !curFrame.m_prev, "piclist: picture already in list\n"); // ensure frame is not in a list
curFrame.m_next = m_start;
curFrame.m_prev = NULL;
if (m_count)
{
m_start->m_prev = &curFrame;
m_start = &curFrame;
}
else
{
m_start = m_end = &curFrame;
}
m_count++;
}
void PicList::pushBack(Frame& curFrame)
{
X265_CHECK(!curFrame.m_next && !curFrame.m_prev, "piclist: picture already in list\n"); // ensure frame is not in a list
curFrame.m_next = NULL;
curFrame.m_prev = m_end;
if (m_count)
{
m_end->m_next = &curFrame;
m_end = &curFrame;
}
else
{
m_start = m_end = &curFrame;
}
m_count++;
}
Frame *PicList::popFront()
{
if (m_start)
{
Frame *temp = m_start;
m_count--;
if (m_count)
{
m_start = m_start->m_next;
m_start->m_prev = NULL;
}
else
{
m_start = m_end = NULL;
}
temp->m_next = temp->m_prev = NULL;
return temp;
}
else
return NULL;
}
Frame* PicList::getPOC(int poc)
{
Frame *curFrame = m_start;
while (curFrame && curFrame->m_poc != poc)
curFrame = curFrame->m_next;
return curFrame;
}
Frame *PicList::popBack()
{
if (m_end)
{
Frame* temp = m_end;
m_count--;
if (m_count)
{
m_end = m_end->m_prev;
m_end->m_next = NULL;
}
else
{
m_start = m_end = NULL;
}
temp->m_next = temp->m_prev = NULL;
return temp;
}
else
return NULL;
}
void PicList::remove(Frame& curFrame)
{
#if _DEBUG
Frame *tmp = m_start;
while (tmp && tmp != &curFrame)
{
tmp = tmp->m_next;
}
X265_CHECK(tmp == &curFrame, "piclist: pic being removed was not in list\n"); // verify pic is in this list
#endif
m_count--;
if (m_count)
{
if (m_start == &curFrame)
m_start = curFrame.m_next;
if (m_end == &curFrame)
m_end = curFrame.m_prev;
if (curFrame.m_next)
curFrame.m_next->m_prev = curFrame.m_prev;
if (curFrame.m_prev)
curFrame.m_prev->m_next = curFrame.m_next;
}
else
{
m_start = m_end = NULL;
}
curFrame.m_next = curFrame.m_prev = NULL;
}

80
x265/source/common/piclist.h Normal file
View File

@ -0,0 +1,80 @@
/*****************************************************************************
* Copyright (C) 2013 x265 project
*
* Authors: Gopu Govindaswamy <gopu@multicorewareinc.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_PICLIST_H
#define X265_PICLIST_H
#include "common.h"
namespace X265_NS {
class Frame;
class PicList
{
protected:
Frame* m_start;
Frame* m_end;
int m_count;
public:
PicList()
{
m_start = NULL;
m_end = NULL;
m_count = 0;
}
/** Push picture to end of the list */
void pushBack(Frame& pic);
/** Push picture to beginning of the list */
void pushFront(Frame& pic);
/** Pop picture from end of the list */
Frame* popBack();
/** Pop picture from beginning of the list */
Frame* popFront();
/** Find frame with specified POC */
Frame* getPOC(int poc);
/** Remove picture from list */
void remove(Frame& pic);
Frame* first() { return m_start; }
Frame* last() { return m_end; }
int size() { return m_count; }
bool empty() const { return !m_count; }
operator bool() const { return !!m_count; }
};
}
#endif // ifndef X265_PICLIST_H

427
x265/source/common/picyuv.cpp Normal file
View File

@ -0,0 +1,427 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#include "common.h"
#include "picyuv.h"
#include "slice.h"
#include "primitives.h"
using namespace X265_NS;
PicYuv::PicYuv()
{
m_picBuf[0] = NULL;
m_picBuf[1] = NULL;
m_picBuf[2] = NULL;
m_picOrg[0] = NULL;
m_picOrg[1] = NULL;
m_picOrg[2] = NULL;
m_cuOffsetY = NULL;
m_cuOffsetC = NULL;
m_buOffsetY = NULL;
m_buOffsetC = NULL;
m_maxLumaLevel = 0;
m_avgLumaLevel = 0;
}
bool PicYuv::create(uint32_t picWidth, uint32_t picHeight, uint32_t picCsp)
{
m_picWidth = picWidth;
m_picHeight = picHeight;
m_hChromaShift = CHROMA_H_SHIFT(picCsp);
m_vChromaShift = CHROMA_V_SHIFT(picCsp);
m_picCsp = picCsp;
uint32_t numCuInWidth = (m_picWidth + g_maxCUSize - 1) / g_maxCUSize;
uint32_t numCuInHeight = (m_picHeight + g_maxCUSize - 1) / g_maxCUSize;
m_lumaMarginX = g_maxCUSize + 32; // search margin and 8-tap filter half-length, padded for 32-byte alignment
m_lumaMarginY = g_maxCUSize + 16; // margin for 8-tap filter and infinite padding
m_stride = (numCuInWidth * g_maxCUSize) + (m_lumaMarginX << 1);
m_chromaMarginX = m_lumaMarginX; // keep 16-byte alignment for chroma CTUs
m_chromaMarginY = m_lumaMarginY >> m_vChromaShift;
m_strideC = ((numCuInWidth * g_maxCUSize) >> m_hChromaShift) + (m_chromaMarginX * 2);
int maxHeight = numCuInHeight * g_maxCUSize;
CHECKED_MALLOC(m_picBuf[0], pixel, m_stride * (maxHeight + (m_lumaMarginY * 2)));
m_picOrg[0] = m_picBuf[0] + m_lumaMarginY * m_stride + m_lumaMarginX;
if (m_picCsp != X265_CSP_I400) {
CHECKED_MALLOC(m_picBuf[1], pixel, m_strideC * ((maxHeight >> m_vChromaShift) + (m_chromaMarginY * 2)));
CHECKED_MALLOC(m_picBuf[2], pixel, m_strideC * ((maxHeight >> m_vChromaShift) + (m_chromaMarginY * 2)));
m_picOrg[1] = m_picBuf[1] + m_chromaMarginY * m_strideC + m_chromaMarginX;
m_picOrg[2] = m_picBuf[2] + m_chromaMarginY * m_strideC + m_chromaMarginX;
}
return true;
fail:
return false;
}
/* the first picture allocated by the encoder will be asked to generate these
* offset arrays. Once generated, they will be provided to all future PicYuv
* allocated by the same encoder. */
bool PicYuv::createOffsets(const SPS& sps)
{
uint32_t numPartitions = 1 << (g_unitSizeDepth * 2);
CHECKED_MALLOC(m_cuOffsetY, intptr_t, sps.numCuInWidth * sps.numCuInHeight);
if (m_picCsp != X265_CSP_I400) {
CHECKED_MALLOC(m_cuOffsetC, intptr_t, sps.numCuInWidth * sps.numCuInHeight);
}
for (uint32_t cuRow = 0; cuRow < sps.numCuInHeight; cuRow++)
{
for (uint32_t cuCol = 0; cuCol < sps.numCuInWidth; cuCol++)
{
m_cuOffsetY[cuRow * sps.numCuInWidth + cuCol] = m_stride * cuRow * g_maxCUSize + cuCol * g_maxCUSize;
if (m_picCsp != X265_CSP_I400) {
m_cuOffsetC[cuRow * sps.numCuInWidth + cuCol] = m_strideC * cuRow * (g_maxCUSize >> m_vChromaShift) + cuCol * (g_maxCUSize >> m_hChromaShift);
}
}
}
CHECKED_MALLOC(m_buOffsetY, intptr_t, (size_t)numPartitions);
if (m_picCsp != X265_CSP_I400) {
CHECKED_MALLOC(m_buOffsetC, intptr_t, (size_t)numPartitions);
}
for (uint32_t idx = 0; idx < numPartitions; ++idx)
{
intptr_t x = g_zscanToPelX[idx];
intptr_t y = g_zscanToPelY[idx];
m_buOffsetY[idx] = m_stride * y + x;
if (m_picCsp != X265_CSP_I400) {
m_buOffsetC[idx] = m_strideC * (y >> m_vChromaShift) + (x >> m_hChromaShift);
}
}
return true;
fail:
return false;
}
void PicYuv::destroy()
{
X265_FREE(m_picBuf[0]);
X265_FREE(m_picBuf[1]);
X265_FREE(m_picBuf[2]);
}
/* Copy pixels from an x265_picture into internal PicYuv instance.
* Shift pixels as necessary, mask off bits above X265_DEPTH for safety. */
void PicYuv::copyFromPicture(const x265_picture& pic, const x265_param& param, int padx, int pady)
{
/* m_picWidth is the width that is being encoded, padx indicates how many
* of those pixels are padding to reach multiple of MinCU(4) size.
*
* Internally, we need to extend rows out to a multiple of 16 for lowres
* downscale and other operations. But those padding pixels are never
* encoded.
*
* The same applies to m_picHeight and pady */
/* width and height - without padsize (input picture raw width and height) */
int width = m_picWidth - padx;
int height = m_picHeight - pady;
/* internal pad to multiple of 16x16 blocks */
uint8_t rem = width & 15;
padx = rem ? 16 - rem : padx;
rem = height & 15;
pady = rem ? 16 - rem : pady;
/* add one more row and col of pad for downscale interpolation, fixes
* warnings from valgrind about using uninitialized pixels */
padx++;
pady++;
X265_CHECK(pic.bitDepth >= 8, "pic.bitDepth check failure");
if (pic.bitDepth == 8)
{
#if (X265_DEPTH > 8)
{
pixel *yPixel = m_picOrg[0];
pixel *uPixel = m_picOrg[1];
pixel *vPixel = m_picOrg[2];
uint8_t *yChar = (uint8_t*)pic.planes[0];
uint8_t *uChar = (uint8_t*)pic.planes[1];
uint8_t *vChar = (uint8_t*)pic.planes[2];
int shift = (X265_DEPTH - 8);
primitives.planecopy_cp(yChar, pic.stride[0] / sizeof(*yChar), yPixel, m_stride, width, height, shift);
if (m_picCsp != X265_CSP_I400) {
primitives.planecopy_cp(uChar, pic.stride[1] / sizeof(*uChar), uPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift);
primitives.planecopy_cp(vChar, pic.stride[2] / sizeof(*vChar), vPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift);
}
}
#else /* Case for (X265_DEPTH == 8) */
// TODO: Does we need this path? may merge into above in future
{
pixel *yPixel = m_picOrg[0];
pixel *uPixel = m_picOrg[1];
pixel *vPixel = m_picOrg[2];
uint8_t *yChar = (uint8_t*)pic.planes[0];
uint8_t *uChar = (uint8_t*)pic.planes[1];
uint8_t *vChar = (uint8_t*)pic.planes[2];
for (int r = 0; r < height; r++)
{
memcpy(yPixel, yChar, width * sizeof(pixel));
yPixel += m_stride;
yChar += pic.stride[0] / sizeof(*yChar);
}
if (m_picCsp != X265_CSP_I400) {
for (int r = 0; r < height >> m_vChromaShift; r++)
{
memcpy(uPixel, uChar, (width >> m_hChromaShift) * sizeof(pixel));
memcpy(vPixel, vChar, (width >> m_hChromaShift) * sizeof(pixel));
uPixel += m_strideC;
vPixel += m_strideC;
uChar += pic.stride[1] / sizeof(*uChar);
vChar += pic.stride[2] / sizeof(*vChar);
}
}
}
#endif /* (X265_DEPTH > 8) */
}
else /* pic.bitDepth > 8 */
{
/* defensive programming, mask off bits that are supposed to be zero */
uint16_t mask = (1 << X265_DEPTH) - 1;
int shift = abs(pic.bitDepth - X265_DEPTH);
pixel *yPixel = m_picOrg[0];
pixel *uPixel = m_picOrg[1];
pixel *vPixel = m_picOrg[2];
uint16_t *yShort = (uint16_t*)pic.planes[0];
uint16_t *uShort = (uint16_t*)pic.planes[1];
uint16_t *vShort = (uint16_t*)pic.planes[2];
if (pic.bitDepth > X265_DEPTH)
{
/* shift right and mask pixels to final size */
primitives.planecopy_sp(yShort, pic.stride[0] / sizeof(*yShort), yPixel, m_stride, width, height, shift, mask);
if (m_picCsp != X265_CSP_I400) {
primitives.planecopy_sp(uShort, pic.stride[1] / sizeof(*uShort), uPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift, mask);
primitives.planecopy_sp(vShort, pic.stride[2] / sizeof(*vShort), vPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift, mask);
}
}
else /* Case for (pic.bitDepth <= X265_DEPTH) */
{
/* shift left and mask pixels to final size */
primitives.planecopy_sp_shl(yShort, pic.stride[0] / sizeof(*yShort), yPixel, m_stride, width, height, shift, mask);
if (m_picCsp != X265_CSP_I400) {
primitives.planecopy_sp_shl(uShort, pic.stride[1] / sizeof(*uShort), uPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift, mask);
primitives.planecopy_sp_shl(vShort, pic.stride[2] / sizeof(*vShort), vPixel, m_strideC, width >> m_hChromaShift, height >> m_vChromaShift, shift, mask);
}
}
}
/* extend the right edge if width was not multiple of the minimum CU size */
pixel *Y = m_picOrg[0];
pixel *U = m_picOrg[1];
pixel *V = m_picOrg[2];
uint64_t sumLuma;
m_maxLumaLevel = primitives.planeClipAndMax(Y, m_stride, width, height, &sumLuma, (pixel)param.minLuma, (pixel)param.maxLuma);
m_avgLumaLevel = (double)(sumLuma) / (m_picHeight * m_picWidth);
for (int r = 0; r < height; r++)
{
for (int x = 0; x < padx; x++)
Y[width + x] = Y[width - 1];
Y += m_stride;
}
if (m_picCsp != X265_CSP_I400) {
for (int r = 0; r < height >> m_vChromaShift; r++)
{
for (int x = 0; x < padx >> m_hChromaShift; x++)
{
U[(width >> m_hChromaShift) + x] = U[(width >> m_hChromaShift) - 1];
V[(width >> m_hChromaShift) + x] = V[(width >> m_hChromaShift) - 1];
}
U += m_strideC;
V += m_strideC;
}
}
/* extend the bottom if height was not multiple of the minimum CU size */
Y = m_picOrg[0] + (height - 1) * m_stride;
for (int i = 1; i <= pady; i++)
memcpy(Y + i * m_stride, Y, (width + padx) * sizeof(pixel));
if (m_picCsp != X265_CSP_I400) {
U = m_picOrg[1] + ((height >> m_vChromaShift) - 1) * m_strideC;
V = m_picOrg[2] + ((height >> m_vChromaShift) - 1) * m_strideC;
for (int j = 1; j <= pady >> m_vChromaShift; j++)
{
memcpy(U + j * m_strideC, U, ((width + padx) >> m_hChromaShift) * sizeof(pixel));
memcpy(V + j * m_strideC, V, ((width + padx) >> m_hChromaShift) * sizeof(pixel));
}
}
}
namespace X265_NS {
template<uint32_t OUTPUT_BITDEPTH_DIV8>
static void md5_block(MD5Context& md5, const pixel* plane, uint32_t n)
{
/* create a 64 byte buffer for packing pixel's into */
uint8_t buf[64 / OUTPUT_BITDEPTH_DIV8][OUTPUT_BITDEPTH_DIV8];
for (uint32_t i = 0; i < n; i++)
{
pixel pel = plane[i];
/* perform bitdepth and endian conversion */
for (uint32_t d = 0; d < OUTPUT_BITDEPTH_DIV8; d++)
buf[i][d] = (uint8_t)(pel >> (d * 8));
}
MD5Update(&md5, (uint8_t*)buf, n * OUTPUT_BITDEPTH_DIV8);
}
/* Update md5 with all samples in plane in raster order, each sample
* is adjusted to OUTBIT_BITDEPTH_DIV8 */
template<uint32_t OUTPUT_BITDEPTH_DIV8>
static void md5_plane(MD5Context& md5, const pixel* plane, uint32_t width, uint32_t height, intptr_t stride)
{
/* N is the number of samples to process per md5 update.
* All N samples must fit in buf */
uint32_t N = 32;
uint32_t width_modN = width % N;
uint32_t width_less_modN = width - width_modN;
for (uint32_t y = 0; y < height; y++)
{
/* convert pel's into uint32_t chars in little endian byte order.
* NB, for 8bit data, data is truncated to 8bits. */
for (uint32_t x = 0; x < width_less_modN; x += N)
md5_block<OUTPUT_BITDEPTH_DIV8>(md5, &plane[y * stride + x], N);
/* mop up any of the remaining line */
md5_block<OUTPUT_BITDEPTH_DIV8>(md5, &plane[y * stride + width_less_modN], width_modN);
}
}
void updateCRC(const pixel* plane, uint32_t& crcVal, uint32_t height, uint32_t width, intptr_t stride)
{
uint32_t crcMsb;
uint32_t bitVal;
uint32_t bitIdx;
for (uint32_t y = 0; y < height; y++)
{
for (uint32_t x = 0; x < width; x++)
{
// take CRC of first pictureData byte
for (bitIdx = 0; bitIdx < 8; bitIdx++)
{
crcMsb = (crcVal >> 15) & 1;
bitVal = (plane[y * stride + x] >> (7 - bitIdx)) & 1;
crcVal = (((crcVal << 1) + bitVal) & 0xffff) ^ (crcMsb * 0x1021);
}
#if _MSC_VER
#pragma warning(disable: 4127) // conditional expression is constant
#endif
// take CRC of second pictureData byte if bit depth is greater than 8-bits
if (X265_DEPTH > 8)
{
for (bitIdx = 0; bitIdx < 8; bitIdx++)
{
crcMsb = (crcVal >> 15) & 1;
bitVal = (plane[y * stride + x] >> (15 - bitIdx)) & 1;
crcVal = (((crcVal << 1) + bitVal) & 0xffff) ^ (crcMsb * 0x1021);
}
}
}
}
}
void crcFinish(uint32_t& crcVal, uint8_t digest[16])
{
uint32_t crcMsb;
for (int bitIdx = 0; bitIdx < 16; bitIdx++)
{
crcMsb = (crcVal >> 15) & 1;
crcVal = ((crcVal << 1) & 0xffff) ^ (crcMsb * 0x1021);
}
digest[0] = (crcVal >> 8) & 0xff;
digest[1] = crcVal & 0xff;
}
void updateChecksum(const pixel* plane, uint32_t& checksumVal, uint32_t height, uint32_t width, intptr_t stride, int row, uint32_t cuHeight)
{
uint8_t xor_mask;
for (uint32_t y = row * cuHeight; y < ((row * cuHeight) + height); y++)
{
for (uint32_t x = 0; x < width; x++)
{
xor_mask = (uint8_t)((x & 0xff) ^ (y & 0xff) ^ (x >> 8) ^ (y >> 8));
checksumVal = (checksumVal + ((plane[y * stride + x] & 0xff) ^ xor_mask)) & 0xffffffff;
if (X265_DEPTH > 8)
checksumVal = (checksumVal + ((plane[y * stride + x] >> 7 >> 1) ^ xor_mask)) & 0xffffffff;
}
}
}
void checksumFinish(uint32_t checksum, uint8_t digest[16])
{
digest[0] = (checksum >> 24) & 0xff;
digest[1] = (checksum >> 16) & 0xff;
digest[2] = (checksum >> 8) & 0xff;
digest[3] = checksum & 0xff;
}
void updateMD5Plane(MD5Context& md5, const pixel* plane, uint32_t width, uint32_t height, intptr_t stride)
{
/* choose an md5_plane packing function based on the system bitdepth */
typedef void(*MD5PlaneFunc)(MD5Context&, const pixel*, uint32_t, uint32_t, intptr_t);
MD5PlaneFunc md5_plane_func;
md5_plane_func = X265_DEPTH <= 8 ? (MD5PlaneFunc)md5_plane<1> : (MD5PlaneFunc)md5_plane<2>;
md5_plane_func(md5, plane, width, height, stride);
}
}

106
x265/source/common/picyuv.h Normal file
View File

@ -0,0 +1,106 @@
/*****************************************************************************
* Copyright (C) 2015 x265 project
*
* Authors: Steve Borho <steve@borho.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111, USA.
*
* This program is also available under a commercial proprietary license.
* For more information, contact us at license @ x265.com.
*****************************************************************************/
#ifndef X265_PICYUV_H
#define X265_PICYUV_H
#include "common.h"
#include "md5.h"
#include "x265.h"
namespace X265_NS {
// private namespace
class ShortYuv;
struct SPS;
class PicYuv
{
public:
pixel* m_picBuf[3]; // full allocated buffers, including margins
pixel* m_picOrg[3]; // pointers to plane starts
uint32_t m_picWidth;
uint32_t m_picHeight;
intptr_t m_stride;
intptr_t m_strideC;
uint32_t m_picCsp;
uint32_t m_hChromaShift;
uint32_t m_vChromaShift;
intptr_t* m_cuOffsetY; /* these four buffers are owned by the top-level encoder */
intptr_t* m_cuOffsetC;
intptr_t* m_buOffsetY;
intptr_t* m_buOffsetC;
uint32_t m_lumaMarginX;
uint32_t m_lumaMarginY;
uint32_t m_chromaMarginX;
uint32_t m_chromaMarginY;
uint16_t m_maxLumaLevel;
double m_avgLumaLevel;
PicYuv();
bool create(uint32_t picWidth, uint32_t picHeight, uint32_t csp);
bool createOffsets(const SPS& sps);
void destroy();
void copyFromPicture(const x265_picture&, const x265_param& param, int padx, int pady);
intptr_t getChromaAddrOffset(uint32_t ctuAddr, uint32_t absPartIdx) const { return m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
/* get pointer to CTU start address */
pixel* getLumaAddr(uint32_t ctuAddr) { return m_picOrg[0] + m_cuOffsetY[ctuAddr]; }
pixel* getCbAddr(uint32_t ctuAddr) { return m_picOrg[1] + m_cuOffsetC[ctuAddr]; }
pixel* getCrAddr(uint32_t ctuAddr) { return m_picOrg[2] + m_cuOffsetC[ctuAddr]; }
pixel* getChromaAddr(uint32_t chromaId, uint32_t ctuAddr) { return m_picOrg[chromaId] + m_cuOffsetC[ctuAddr]; }
pixel* getPlaneAddr(uint32_t plane, uint32_t ctuAddr) { return m_picOrg[plane] + (plane ? m_cuOffsetC[ctuAddr] : m_cuOffsetY[ctuAddr]); }
const pixel* getLumaAddr(uint32_t ctuAddr) const { return m_picOrg[0] + m_cuOffsetY[ctuAddr]; }
const pixel* getCbAddr(uint32_t ctuAddr) const { return m_picOrg[1] + m_cuOffsetC[ctuAddr]; }
const pixel* getCrAddr(uint32_t ctuAddr) const { return m_picOrg[2] + m_cuOffsetC[ctuAddr]; }
const pixel* getChromaAddr(uint32_t chromaId, uint32_t ctuAddr) const { return m_picOrg[chromaId] + m_cuOffsetC[ctuAddr]; }
const pixel* getPlaneAddr(uint32_t plane, uint32_t ctuAddr) const { return m_picOrg[plane] + (plane ? m_cuOffsetC[ctuAddr] : m_cuOffsetY[ctuAddr]); }
/* get pointer to CU start address */
pixel* getLumaAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return m_picOrg[0] + m_cuOffsetY[ctuAddr] + m_buOffsetY[absPartIdx]; }
pixel* getCbAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return m_picOrg[1] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
pixel* getCrAddr(uint32_t ctuAddr, uint32_t absPartIdx) { return m_picOrg[2] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
pixel* getChromaAddr(uint32_t chromaId, uint32_t ctuAddr, uint32_t absPartIdx) { return m_picOrg[chromaId] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
const pixel* getLumaAddr(uint32_t ctuAddr, uint32_t absPartIdx) const { return m_picOrg[0] + m_cuOffsetY[ctuAddr] + m_buOffsetY[absPartIdx]; }
const pixel* getCbAddr(uint32_t ctuAddr, uint32_t absPartIdx) const { return m_picOrg[1] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
const pixel* getCrAddr(uint32_t ctuAddr, uint32_t absPartIdx) const { return m_picOrg[2] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
const pixel* getChromaAddr(uint32_t chromaId, uint32_t ctuAddr, uint32_t absPartIdx) const { return m_picOrg[chromaId] + m_cuOffsetC[ctuAddr] + m_buOffsetC[absPartIdx]; }
};
void updateChecksum(const pixel* plane, uint32_t& checksumVal, uint32_t height, uint32_t width, intptr_t stride, int row, uint32_t cuHeight);
void updateCRC(const pixel* plane, uint32_t& crcVal, uint32_t height, uint32_t width, intptr_t stride);
void crcFinish(uint32_t & crc, uint8_t digest[16]);
void checksumFinish(uint32_t checksum, uint8_t digest[16]);
void updateMD5Plane(MD5Context& md5, const pixel* plane, uint32_t width, uint32_t height, intptr_t stride);
}
#endif // ifndef X265_PICYUV_H

1289
x265/source/common/pixel.cpp Normal file
View File

File diff suppressed because it is too large Load Diff

Some files were not shown because too many files have changed in this diff Show More