summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMartin Schröder <martin@oneiros.de>2008-02-03 14:02:22 +0000
committerMartin Schröder <martin@oneiros.de>2008-02-03 14:02:22 +0000
commit8d602fb9d17450cd3195527e717053d2e1e8d651 (patch)
treeb63d2d45212f1b87fc1d6e7fc29e0752f73cfed7
parenta637ef3866e1d89fbb06407d83f53740ccd31dbc (diff)
Import libpng 1.2.24 (from pdftex)
git-svn-id: svn://tug.org/texlive/trunk@6492 c570f23f-e606-0410-a88d-b1316a301751
-rw-r--r--Build/source/libs/libpng/ANNOUNCE45
-rw-r--r--Build/source/libs/libpng/CHANGES313
-rw-r--r--Build/source/libs/libpng/INSTALL27
-rw-r--r--Build/source/libs/libpng/KNOWNBUG28
-rw-r--r--Build/source/libs/libpng/LICENSE4
-rw-r--r--Build/source/libs/libpng/README22
-rw-r--r--Build/source/libs/libpng/Y2KINFO4
-rw-r--r--Build/source/libs/libpng/libpng-1.2.24.txt (renamed from Build/source/libs/libpng/libpng-1.2.18.txt)137
-rw-r--r--Build/source/libs/libpng/libpng.3174
-rw-r--r--Build/source/libs/libpng/libpngpf.36
-rw-r--r--Build/source/libs/libpng/png.54
-rw-r--r--Build/source/libs/libpng/png.c123
-rw-r--r--Build/source/libs/libpng/png.h176
-rw-r--r--Build/source/libs/libpng/pngconf.h152
-rw-r--r--Build/source/libs/libpng/pngerror.c59
-rw-r--r--Build/source/libs/libpng/pnggccrd.c5387
-rw-r--r--Build/source/libs/libpng/pngget.c92
-rw-r--r--Build/source/libs/libpng/pngpread.c175
-rw-r--r--Build/source/libs/libpng/pngread.c132
-rw-r--r--Build/source/libs/libpng/pngrtran.c83
-rw-r--r--Build/source/libs/libpng/pngrutil.c138
-rw-r--r--Build/source/libs/libpng/pngset.c153
-rw-r--r--Build/source/libs/libpng/pngtest.c32
-rw-r--r--Build/source/libs/libpng/pngtrans.c10
-rw-r--r--Build/source/libs/libpng/pngvcrd.c3905
-rw-r--r--Build/source/libs/libpng/pngwio.c2
-rw-r--r--Build/source/libs/libpng/pngwrite.c64
-rw-r--r--Build/source/libs/libpng/pngwutil.c100
28 files changed, 1196 insertions, 10351 deletions
diff --git a/Build/source/libs/libpng/ANNOUNCE b/Build/source/libs/libpng/ANNOUNCE
index aaf5d4a0d13..c49c7b6bd61 100644
--- a/Build/source/libs/libpng/ANNOUNCE
+++ b/Build/source/libs/libpng/ANNOUNCE
@@ -1,5 +1,5 @@
-Libpng 1.2.18 - May 15, 2007
+Libpng 1.2.24 - December 14, 2007
This is a public release of libpng, intended for use in production codes.
@@ -8,38 +8,51 @@ Files available for download:
Source files with LF line endings (for Unix/Linux) and with a
"configure" script
- libpng-1.2.18.tar.gz
- libpng-1.2.18.tar.bz2
+ libpng-1.2.24.tar.gz
+ libpng-1.2.24.tar.bz2
Source files with LF line endings (for Unix/Linux) without the
"configure" script
- libpng-1.2.18-no-config.tar.gz
- libpng-1.2.18-no-config.tar.bz2
+ libpng-1.2.24-no-config.tar.gz
+ libpng-1.2.24-no-config.tar.bz2
Source files with CRLF line endings (for Windows), without the
"configure" script
- lpng1218.zip
- lpng1218.tar.bz2
+ lpng1224.zip
+ lpng1224.tar.bz2
Project files
- libpng-1.2.18-project-netware.zip
- libpng-1.2.18-project-wince.zip
+ libpng-1.2.24-project-netware.zip
+ libpng-1.2.24-project-wince.zip
Other information:
- libpng-1.2.18-README.txt
- libpng-1.2.18-KNOWNBUGS.txt
- libpng-1.2.18-LICENSE.txt
- libpng-1.2.18-Y2K-compliance.txt
+ libpng-1.2.24-README.txt
+ libpng-1.2.24-KNOWNBUGS.txt
+ libpng-1.2.24-LICENSE.txt
+ libpng-1.2.24-Y2K-compliance.txt
-Changes since the last public release (1.2.17):
+Changes since the last public release (1.2.23):
+
+version 1.2.24 [December 14, 2007]
+
+ Moved misplaced test for malloc failure in png_set_sPLT(). This bug was
+ introduced in libpng-1.2.20.
+ Ifdef out avg_row etc from png.h and pngwrite.c when PNG_NO_WRITE_FILTER
+ Do not use png_ptr->free_fn and png_ptr->mem_fn in png_destroy_read_struct()
+ when png_ptr is NULL (Marshall Clow).
+ Updated handling of symbol prefixes in Makefile.am and configure.ac (Mike
+ Frysinger).
+ Removed a useless test and fixed incorrect test in png_set_cHRM_fixed()
+ (David Hill).
+ Make sure not to redefine _BSD_SOURCE in pngconf.h
+ Revised gather.sh and makefile.std in contrib/pngminim to avoid compiling
+ unused files.
-version 1.2.18 [May 15, 2007]
- Reverted the recent change to symbol-handling in configure script
Send comments/corrections/commendations to png-mng-implement at lists.sf.net
(subscription required; visit
diff --git a/Build/source/libs/libpng/CHANGES b/Build/source/libs/libpng/CHANGES
index ff2f37942c0..a6e5856aa04 100644
--- a/Build/source/libs/libpng/CHANGES
+++ b/Build/source/libs/libpng/CHANGES
@@ -1480,7 +1480,7 @@ version 1.2.9beta5 [March 4, 2006]
Restored scripts/makefile.elf which was inadvertently deleted.
version 1.2.9beta6 [March 6, 2006]
- Fixed typo (18) in configuration files.
+ Fixed typo (RELEASE) in configuration files.
version 1.2.9beta7 [March 7, 2006]
Removed libpng.vers and libpng.sym from libpng12_la_SOURCES in Makefile.am
@@ -1669,7 +1669,7 @@ version 1.2.15rc2 [December 21, 2006]
Added scripts/makefile.nommx
version 1.2.15rc3 [December 25, 2006]
- Fixed shared library numbering error that was intruduced in 1.2.15beta6.
+ Fixed shared library numbering error that was introduced in 1.2.15beta6.
version 1.2.15rc4 [December 27, 2006]
Fixed handling of rgb_to_gray when png_ptr->color.gray isn't set.
@@ -1677,7 +1677,7 @@ version 1.2.15rc4 [December 27, 2006]
version 1.2.15rc5 [December 31, 2006]
Revised handling of rgb_to_gray.
-version 1.2.15 [January 5, 2007]
+version 1.0.23, 1.2.15 [January 5, 2007]
Added some (unsigned long) typecasts in pngtest.c to avoid printing errors.
version 1.2.16beta1 [January 6, 2007]
@@ -1686,7 +1686,7 @@ version 1.2.16beta1 [January 6, 2007]
version 1.2.16beta2 [January 16, 2007]
Revised scripts/CMakeLists.txt
-version 1.2.16 [January 31, 2007]
+version 1.0.24, 1.2.16 [January 31, 2007]
No changes.
version 1.2.17beta1 [March 6, 2007]
@@ -1723,12 +1723,315 @@ version 1.2.17rc4 [May 10, 2007]
version 1.0.25 [May 15, 2007]
version 1.2.17 [May 15, 2007]
Added "png_ptr->num_trans=0" before error return in png_handle_tRNS,
- to eliminate a vulnerability (CVE-2007-2554, CERT VU#684664)
+ to eliminate a vulnerability (CVE-2007-2445, CERT VU#684664)
version 1.0.26 [May 15, 2007]
version 1.2.18 [May 15, 2007]
Reverted the libpng-1.2.17rc3 change to symbol-handling in configure script
+version 1.2.19beta1 [May 18, 2007]
+ Changed "const static" to "static PNG_CONST" everywhere, mostly undoing
+ change of libpng-1.2.17beta2. Changed other "const" to "PNG_CONST"
+ Changed some handling of unused parameters, to avoid compiler warnings.
+ "if (unused == NULL) return;" becomes "unused = unused".
+
+version 1.2.19beta2 [May 18, 2007]
+ Only use the valid bits of tRNS value in png_do_expand() (Brian Cartier)
+
+version 1.2.19beta3 [May 19, 2007]
+ Add some "png_byte" typecasts in png_check_keyword() and write new_key
+ instead of key in zTXt chunk (Kevin Ryde).
+
+version 1.2.19beta4 [May 21, 2007]
+ Add png_snprintf() function and use it in place of sprint() for improved
+ defense against buffer overflows.
+
+version 1.2.19beta5 [May 21, 2007]
+ Fixed png_handle_tRNS() to only use the valid bits of tRNS value.
+ Changed handling of more unused parameters, to avoid compiler warnings.
+ Removed some PNG_CONST in pngwutil.c to avoid compiler warnings.
+
+version 1.2.19beta6 [May 22, 2007]
+ Added some #ifdef PNG_MMX_CODE_SUPPORTED where needed in pngvcrd.c
+ Added a special "_MSC_VER" case that defines png_snprintf to _snprintf
+
+version 1.2.19beta7 [May 22, 2007]
+ Squelched png_squelch_warnings() in pnggccrd.c and added an
+ #ifdef PNG_MMX_CODE_SUPPORTED block around the declarations that caused
+ the warnings that png_squelch_warnings was squelching.
+
+version 1.2.19beta8 [May 22, 2007]
+ Removed __MMX__ from test in pngconf.h.
+
+version 1.2.19beta9 [May 23, 2007]
+ Made png_squelch_warnings() available via PNG_SQUELCH_WARNINGS macro.
+ Revised png_squelch_warnings() so it might work.
+ Updated makefile.sgcc and makefile.solaris; added makefile.solaris-x86.
+
+version 1.2.19beta10 [May 24, 2007]
+ Resquelched png_squelch_warnings(), use "__attribute__((used))" instead.
+
+version 1.2.19beta11 [May 28, 2007]
+ Return 0 from png_get_sPLT() and png_get_unknown_chunks() if png_ptr is NULL;
+ changed three remaining instances of png_strcpy() to png_strncpy() (David
+ Hill).
+ Make test for NULL row_buf at the beginning of png_do_read_transformations
+ unconditional.
+
+version 1.2.19beta12 [May 28, 2007]
+ Revised pnggccrd.c.
+
+version 1.2.19beta13 [June 14, 2007]
+ Prefer PNG_USE_PNGVCRD when _MSC_VER is defined in pngconf.h
+
+version 1.2.19beta14 [June 16, 2007]
+ Fix bug with handling of 16-bit transparency, introduced in 1.2.19beta2
+
+version 1.2.19beta15 [June 17, 2007]
+ Revised pnggccrd.c.
+
+version 1.2.19beta16 [June 18, 2007]
+ Revised pnggccrd.c again.
+ Updated contrib/gregbook.
+ Changed '#include "pnggccrd.c"' to 'include "$srcdir/pnggccrd.c"'
+ in configure.ac
+
+version 1.2.19beta17 [June 19, 2007]
+ Revised many of the makefiles, to set -DPNG_NO_MMX_CODE where needed
+ and to not use -O3 unless -DPNG_NO_MMX_CODE is also set.
+
+version 1.2.19beta18 [June 23, 2007]
+ Replaced some C++ style comments with C style comments in pnggccrd.c.
+ Copied optimized C code from pnggccrd.c to pngrutil.c, removed dependency
+ on pnggccrd.o from many makefiles.
+ Added sl and dylib to list of extensions be installed by Makefile.am
+
+version 1.2.19beta19 [June 28, 2007]
+ Fixed testing PNG_RGB_TO_GRAY_ERR & PNG_RGB_TO_GRAY_WARN in pngrtran.c
+ More cleanup of pnggccrd.c and pngvcrd.c
+
+version 1.2.19beta20 [June 29, 2007]
+ Rebuilt Makefile.in and configure using libtool-1.5.24.
+ Fixed typo in pnggccrd.c
+
+version 1.2.19beta21 [June 30, 2007]
+ More revision of pnggccrd.c
+ Added "test" target to Makefile.in and Makefile.am
+
+version 1.2.19beta22 [July 3, 2007]
+ Added info about pngrutil/pnggccrd/pngvcrd to png_get_header_version()
+ Fix type definition of dummy_value_a, b in pnggccrd.c
+
+version 1.2.19beta23 [July 10, 2007]
+ Revert change to type definition of dummy_value_a, b in pnggccrd.c
+ Make sure __PIC__ is defined in pnggccrd.c when PIC is defined.
+ Require gcc-4.1 or better to use PNG_HAVE_MMX_FILTER_ROW on x86_64 platforms
+
+version 1.2.19beta24 [July 14, 2007]
+ Added PNG_NO_READ_FILTER, PNG_NO_WRITE_FILTER, PNG_NO_WARNING macros.
+ Added contrib/pngminim to demonstrate building minimal encoder and decoder
+
+version 1.2.19beta25 [July 15, 2007]
+ Removed the new PNG_NO_READ_FILTER macro since it would make the library
+ unable to read valid PNG files, and filtering is at the heart of the
+ PNG format.
+
+version 1.2.19beta26 [July 16, 2007]
+ Changed "png_free(str)" to "png_free(png_ptr,str)" in pngrutil.c WinCE
+ code (Yves Piguet). This bug was introduced in libpng-1.2.14.
+ Updated scripts/CMakeLists.txt
+ Relocated a misplaced #endif in pnggccrd.c
+
+version 1.2.19beta27 [July 17, 2007]
+ Fixed incorrect stride and number of bytes copied (was 4 instead of
+ 6 bytes) in the cleanup loop of pnggccrd.c and pngvcrd.c for handling
+ the end of 48-bit interlaced rows (Glenn R-P).
+
+version 1.2.19beta28 [July 19, 2007]
+ Removed requirement for gcc-4.1 or better to use PNG_HAVE_MMX_FILTER_ROW
+ on x86_64 platforms
+ Added png_warning() in pngrutil.c for short iCCP, iTXt, sPLT, or zTXT chunks.
+ Revised pngtest.c so warnings are displayed regardless of PNG_NO_STDIO.
+
+version 1.2.19beta29 [July 20, 2007]
+ Fix typo in pnggccrd.c (%%eax should be %%ax in secondloop48)
+
+version 1.2.19beta30 [July 26, 2007]
+ Revised pnggccrd.c
+
+version 1.2.19beta31 [July 27, 2007]
+ Fix typos in pnggccrd.c
+
+version 1.0.27rc1 and 1.2.19rc1 [July 31, 2007]
+ Disable PNG_MMX_CODE_SUPPORTED when PNG_ASSEMBLER_CODE_SUPPORTED is off.
+ Enable PNG_MMX_READ_FILTER_* by default, except when gcc-3.x is being
+ used (they were inadvertently disabled in libpng-1.2.19beta23).
+ Fix some debugging statements in pnggccrd.c and pngrutil.c
+ Added information about disabling the MMX code in libpng documentation.
+
+version 1.0.27rc2 and 1.2.19rc2 [August 4, 2007]
+ Removed some "#if 0" blocks.
+ Made a global struct local in pngvcrd.c to make it thread safe.
+ Issue a png_error() if application attempts to transform a row tht
+ has not been initialized.
+
+version 1.0.27rc3 and 1.2.19rc3 [August 9, 2007]
+ Slightly revised pngvcrd.c
+
+version 1.0.27rc4 and 1.2.19rc4 [August 9, 2007]
+ Revised pnggccrd.c debugging change of rc1, which was broken.
+ Revised scripts/CMakeLists.txt
+ Change default to PNG_NO_GLOBAL_ARRAYS for MSVC.
+ Turn off PNG_FLAG_ROW_INIT flag when setting transforms that expand pixels.
+
+version 1.0.27rc5 and 1.2.19rc5 [August 10, 2007]
+ Fix typo (missing '"') in pnggccrd.c
+ Revise handling of png_strtod in recent versions of WINCE
+
+version 1.0.27rc6 and 1.2.19rc6 [August 15, 2007]
+ Fix typo (missing ',') in contrib/gregbook/readpng2.c
+ Undid row initialization error exit added to rc2 and rc4.
+
+version 1.0.27 and 1.2.19 [August 18, 2007]
+ Conditionally restored row initialization error exit.
+
+version 1.2.20beta01 [August 19, 2007]
+ Fixed problem with compiling pnggccrd.c on Intel-Apple platforms.
+ Changed png_malloc() to png_malloc_warn() in png_set_sPLT().
+ Added PNG_NO_ERROR_TEXT feature, with demo in contrib/pngminim
+ Removed define PNG_WARN_UNINITIALIZED_ROW 1 /* 0: warning; 1: error */
+ because it caused some trouble.
+
+version 1.2.20beta02 [August 20, 2007]
+ Avoid compiling pnggccrd.c on Intel-Apple platforms.
+
+version 1.2.20beta03 [August 20, 2007]
+ Added "/D PNG_NO_MMX_CODE" to the non-mmx builds of projects/visualc6
+ and visualc71.
+
+version 1.2.20beta04 [August 21, 2007]
+ Revised pngvcrd.c for improved efficiency (Steve Snyder).
+
+version 1.2.20rc1 [August 23, 2007]
+ Revised pngconf.h to set PNG_NO_MMX_CODE for gcc-3.x compilers.
+
+version 1.2.20rc2 [August 27, 2007]
+ Revised scripts/CMakeLists.txt
+ Revised #ifdefs to ensure one and only one of pnggccrd.c, pngvcrd.c,
+ or part of pngrutil.c is selected.
+
+version 1.2.20rc3 [August 30, 2007]
+ Remove a little more code in pngwutil.c when PNG_NO_WRITE_FILTER is selected.
+ Added /D _CRT_SECURE_NO_WARNINGS to visual6c and visualc71 projects.
+ Compile png_mmx_support() in png.c even when PNG_NO_MMX_CODE is defined.
+ Restored a "superfluous" #ifdef that was removed from 1.2.20rc2 pnggccrd.c,
+ breaking the png_mmx_support() function.
+
+version 1.2.20rc4 [September 1, 2007]
+ Removed Intel contributions (MMX, Optimized C).
+
+version 1.2.20rc5 [September 2, 2007]
+ Restored configure and Makefile.in to rc3 and put a snippet of code in
+ pnggccrd.c, to ensure configure makes the same PNG_NO_MMX_CODE selection
+
+version 1.2.20rc6 [September 2, 2007]
+ Fixed bugs in scripts/CMakeLists.txt
+ Removed pngvcrd.c references from msvc projects.
+
+version 1.0.28 and 1.2.20 [September 8, 2007]
+ Removed "(NO READ SUPPORT)" from png_get_header_version() string.
+
+version 1.2.21beta1 [September 14, 2007]
+ Fixed various mistakes reported by George Cook and Jeff Phillips:
+ logical vs bitwise NOT in pngrtran.c, bug introduced in 1.2.19rc2
+ 16-bit cheap transparency expansion, bug introduced in 1.2.19beta2
+ errors with sizeof(unknown_chunk.name), bugs introduced in 1.2.19beta11
+ <= compare with unsigned var in pngset.c, should be ==.
+
+version 1.2.21beta2 [September 18, 2007]
+ Removed some extraneous typecasts.
+
+version 1.2.21rc1 [September 25, 2007]
+ Fixed potential out-of-bounds reads in png_handle_pCAL() and
+ png_handle_ztXt() ("flayer" results reported by Tavis Ormandy).
+
+version 1.2.21rc2 [September 26, 2007]
+ Fixed potential out-of-bounds reads in png_handle_sCAL(),
+ png_handle_iTXt(), and png_push_read_tEXt().
+ Remove some PNG_CONST declarations from pngwutil.c to avoid compiler warnings
+ Revised makefiles to update paths in libpng.pc properly.
+
+version 1.2.21rc3 [September 27, 2007]
+ Revised makefiles to update "Libs" in libpng.pc properly.
+
+version 1.0.29 and 1.2.21rc3 [October 4, 2007]
+ No changes.
+
+version 1.2.22beta1 [October 4, 2007]
+ Again, fixed logical vs bitwise NOT in pngrtran.c, bug introduced
+ in 1.2.19rc2
+
+version 1.2.22beta2 [October 5, 2007]
+ Fixed string length error in pngset.c (caused crashes while decoding iCCP)
+ Add terminating NULL after each instance of png_strncpy().
+
+version 1.2.22beta3 [October 6, 2007]
+ Fix two off-by-one terminating NULL after png_strncpy().
+
+version 1.2.22beta4 [October 7, 2007]
+ Changed some 0 to '\0'.
+
+version 1.0.30rc1 and 1.2.22rc1 [October 8, 2007]
+ No changes.
+
+version 1.0.30 and 1.2.22 [October 13, 2007]
+ No changes.
+
+version 1.2.23beta01 [October 15, 2007]
+ Reduced number of invocations of png_strlen() in pngset.c.
+ Changed [azAZ09_] to [_abcde...89] in Makefile.am for better localization.
+
+version 1.2.23beta02 [October 16, 2007]
+ Eliminated png_strncpy() and png_strcpy() (Pierre Poissinger)
+ Changed $AN to $(AN) in Makefile.am.
+
+version 1.2.23beta03 [October 16, 2007]
+ Fixed off-by-one error in pngset.c
+ Restore statement to set last character of buffer to \0 in pngerror.c
+
+version 1.2.23beta04 [October 23, 2007]
+ Reject attempt to set all-zero cHRM values.
+
+version 1.2.23beta05 [October 26, 2007]
+ Add missing quotes in projects/visualc6, lost in version 1.2.20rc3
+
+version 1.2.23rc01 [November 2, 2007]
+ No changes.
+
+version 1.2.23 [November 6, 2007]
+ No changes.
+
+version 1.2.24beta01 [November 19, 2007]
+ Moved misplaced test for malloc failure in png_set_sPLT(). This bug was
+ introduced in libpng-1.2.20beta01.
+ Ifdef out avg_row etc from png.h and pngwrite.c when PNG_NO_WRITE_FILTER
+ Do not use png_ptr->free_fn and png_ptr->mem_fn in png_destroy_read_struct()
+ when png_ptr is NULL (Marshall Clow).
+ Updated handling of symbol prefixes in Makefile.am and configure.ac (Mike
+ Frysinger).
+
+version 1.2.24beta02 [November 30, 2007]
+ Removed a useless test and fixed incorrect test in png_set_cHRM_fixed()
+ (David Hill).
+
+version 1.2.24rc01 [December 7, 2007]
+ No changes.
+
+version 1.2.24 [December 14, 2007]
+ Make sure not to redefine _BSD_SOURCE in pngconf.h
+ Revised gather.sh and makefile.std in contrib/pngminim to avoid compiling
+ unused files.
+
Send comments/corrections/commendations to png-mng-implement at lists.sf.net
(subscription required; visit
https://lists.sourceforge.net/lists/listinfo/png-mng-implement
diff --git a/Build/source/libs/libpng/INSTALL b/Build/source/libs/libpng/INSTALL
index 01ef8b87c56..78c9e02936f 100644
--- a/Build/source/libs/libpng/INSTALL
+++ b/Build/source/libs/libpng/INSTALL
@@ -1,5 +1,5 @@
-Installing libpng version 1.2.18 - May 15, 2007
+Installing libpng version 1.2.24 - December 14, 2007
On Unix/Linux and similar systems, you can simply type
@@ -44,7 +44,7 @@ to have access to the zlib.h and zconf.h include files that
correspond to the version of zlib that's installed.
You can rename the directories that you downloaded (they
-might be called "libpng-1.2.18" or "lpng109" and "zlib-1.2.1"
+might be called "libpng-1.2.24" or "lpng109" and "zlib-1.2.1"
or "zlib121") so that you have directories called "zlib" and "libpng".
Your directory structure should look like this:
@@ -101,15 +101,9 @@ include
CMakeLists.txt => "cmake" script
makefile.std => Generic UNIX makefile (cc, creates static libpng.a)
makefile.elf => Linux/ELF makefile symbol versioning,
- gcc, creates libpng12.so.0.1.2.18)
+ gcc, creates libpng12.so.0.1.2.24)
makefile.linux => Linux/ELF makefile
- (gcc, creates libpng12.so.0.1.2.18)
- makefile.gcmmx => Linux/ELF makefile
- (gcc, creates libpng12.so.0.1.2.18,
- uses assembler code tuned for Intel MMX platform)
- makefile.nommx => Linux/ELF makefile
- (gcc, creates libpng12.so.0.1.2.18
- does not use Intel MMX assembler code)
+ (gcc, creates libpng12.so.0.1.2.24)
makefile.gcc => Generic makefile (gcc, creates static libpng.a)
makefile.knr => Archaic UNIX Makefile that converts files with
ansi2knr (Requires ansi2knr.c from
@@ -131,12 +125,14 @@ include
makefile.openbsd => OpenBSD makefile
makefile.sgi => Silicon Graphics IRIX makefile (cc, creates static lib)
makefile.sggcc => Silicon Graphics (gcc,
- creates libpng12.so.0.1.2.18)
+ creates libpng12.so.0.1.2.24)
makefile.sunos => Sun makefile
makefile.solaris => Solaris 2.X makefile (gcc,
- creates libpng12.so.0.1.2.18)
+ creates libpng12.so.0.1.2.24)
+ makefile.solaris-x86 => Solaris/intelMMX 2.X makefile (gcc,
+ creates libpng12.so.0.1.2.24)
makefile.so9 => Solaris 9 makefile (gcc,
- creates libpng12.so.0.1.2.18)
+ creates libpng12.so.0.1.2.24)
makefile.32sunu => Sun Ultra 32-bit makefile
makefile.64sunu => Sun Ultra 64-bit makefile
makefile.sco => For SCO OSr5 ELF and Unixware 7 with Native cc
@@ -152,10 +148,7 @@ include
makefile.tc3 => Turbo C 3.0 makefile
makefile.dj2 => DJGPP 2 makefile
makefile.msc => Microsoft C makefile
- makefile.vcawin32 => makefile for Microsoft Visual C++ 5.0 and later (uses
- assembler code tuned for Intel MMX platform)
- makefile.vcwin32 => makefile for Microsoft Visual C++ 4.0 and later (does
- not use assembler code)
+ makefile.vcwin32 => makefile for Microsoft Visual C++ 4.0 and later
makefile.os2 => OS/2 Makefile (gcc and emx, requires pngos2.def)
pngos2.def => OS/2 module definition file used by makefile.os2
makefile.watcom => Watcom 10a+ Makefile, 32-bit flat memory model
diff --git a/Build/source/libs/libpng/KNOWNBUG b/Build/source/libs/libpng/KNOWNBUG
index 7052ccd067a..d39dd1ec313 100644
--- a/Build/source/libs/libpng/KNOWNBUG
+++ b/Build/source/libs/libpng/KNOWNBUG
@@ -1,28 +1,22 @@
-Known bugs in libpng version 1.2.18
+Known bugs in libpng version 1.2.24
-1. April 22, 2001: pnggccrd.c has been reported to crash on NetBSD when
- reading interlaced PNG files, when assembler code is enabled but running
- on a non-MMX i386 platform.
-
- STATUS: Under investigation. The change to pnggccrd.c in libpng-1.2.1
- fixed a problem under FreeBSD but not the problem with NetBSD, which
- still fails as of libpng-1.2.2rc1.
-
-2. February 23, 2006: The custom makefiles don't build libpng with -lz.
+1. February 23, 2006: The custom makefiles don't build libpng with -lz.
STATUS: This is a subject of debate. The change will probably be made
- as a part of a major overhaul of the makefiles in libpng version 1.3.0.
+ as a part of a major overhaul of the makefiles in libpng version 1.4.0.
-3. February 24, 2006: The Makefile generated by the "configure" script
+2. February 24, 2006: The Makefile generated by the "configure" script
fails to install symbolic links
libpng12.so => libpng12.so.0.1.2.9betaN
that are generated by the custom makefiles.
- STATUS: For now, system library builders should use the custom makefiles.
+3. September 4, 2007: There is a report that pngtest crashes on MacOS 10.
-4. March 2007: Building 1.2.16 with PNG_ASSEMBLER_CODE_SUPPORTED;
- PNG_MMX_CODE_SUPPORTED results in multiple definitions of png_combine_row,
- png_do_read_interlace, and png_read_filter_row
+ STATUS: workarounds are
+ 1) Compile without optimization (crashes are observed with
+ -arch i386 and -O2 or -O3, using gcc-4.0.1).
+ 2) Compile pngtest.c with PNG_DEBUG defined (the bug goes away if
+ you try to look at it).
+ 3) Ignore the crash. The library itself seems to be OK.
- STATUS: Investigating.
diff --git a/Build/source/libs/libpng/LICENSE b/Build/source/libs/libpng/LICENSE
index 1d62448c314..6b81b55a63c 100644
--- a/Build/source/libs/libpng/LICENSE
+++ b/Build/source/libs/libpng/LICENSE
@@ -8,7 +8,7 @@ COPYRIGHT NOTICE, DISCLAIMER, and LICENSE:
If you modify libpng you may insert additional notices immediately following
this sentence.
-libpng versions 1.2.6, August 15, 2004, through 1.2.18, May 15, 2007, are
+libpng versions 1.2.6, August 15, 2004, through 1.2.24, December 14, 2007, are
Copyright (c) 2004, 2006-2007 Glenn Randers-Pehrson, and are
distributed according to the same disclaimer and license as libpng-1.2.5
with the following individual added to the list of Contributing Authors
@@ -106,4 +106,4 @@ certification mark of the Open Source Initiative.
Glenn Randers-Pehrson
glennrp at users.sourceforge.net
-May 15, 2007
+December 14, 2007
diff --git a/Build/source/libs/libpng/README b/Build/source/libs/libpng/README
index 94d64aaecfc..6f84c69f0d8 100644
--- a/Build/source/libs/libpng/README
+++ b/Build/source/libs/libpng/README
@@ -1,4 +1,4 @@
-README for libpng version 1.2.18 - May 15, 2007 (shared library 12.0)
+README for libpng version 1.2.24 - December 14, 2007 (shared library 12.0)
See the note about version numbers near the top of png.h
See INSTALL for instructions on how to install libpng.
@@ -113,8 +113,8 @@ given in previous versions of this document. He and Andreas will read mail
addressed to the png-implement list, however.
Please do not send general questions about PNG. Send them to
-the (png-list at ccrc.wustl.edu, subscription required, write to
-majordomo at ccrc.wustl.edu with "subscribe png-list" in your message).
+the (png-mng-misc at lists.sourceforge.net, subscription required, visit
+https://lists.sourceforge.net/lists/listinfo/png-mng-implement to subscribe)
On the other hand,
please do not send libpng questions to that address, send them to me
or to the png-implement list. I'll
@@ -125,7 +125,7 @@ and ...". If in doubt, send questions to me. I'll bounce them
to others, if necessary.
Please do not send suggestions on how to change PNG. We have
-been discussing PNG for nine years now, and it is official and
+been discussing PNG for twelve years now, and it is official and
finished. If you have suggestions for libpng, however, I'll
gladly listen. Even if your suggestion is not used immediately,
it may be used later.
@@ -140,6 +140,7 @@ Files in this distribution:
TODO => Things not implemented in the current library
Y2KINFO => Statement of Y2K compliance
example.c => Example code for using libpng functions
+ libpng-*-*-diff.txt => Diff from previous release
libpng.3 => manual page for libpng (includes libpng.txt)
libpng.txt => Description of libpng and its functions
libpngpf.3 => manual page for libpng's private functions
@@ -147,7 +148,6 @@ Files in this distribution:
png.c => Basic interface functions common to library
png.h => Library function and interface declarations
pngconf.h => System specific library configuration
- pngasmrd.h => Header file for assembler-coded functions
pngerror.c => Error/warning message I/O functions
pngget.c => Functions for retrieving info from struct
pngmem.c => Memory handling functions
@@ -190,11 +190,11 @@ Files in this distribution:
descrip.mms => VMS makefile for MMS or MMK
makefile.std => Generic UNIX makefile (cc, creates static libpng.a)
makefile.elf => Linux/ELF makefile symbol versioning,
- gcc, creates libpng12.so.0.1.2.18)
+ gcc, creates libpng12.so.0.1.2.24)
makefile.linux => Linux/ELF makefile
- (gcc, creates libpng12.so.0.1.2.18)
+ (gcc, creates libpng12.so.0.1.2.24)
makefile.gcmmx => Linux/ELF makefile
- (gcc, creates libpng12.so.0.1.2.18,
+ (gcc, creates libpng12.so.0.1.2.24,
uses assembler code tuned for Intel MMX platform)
makefile.gcc => Generic makefile (gcc, creates static libpng.a)
makefile.knr => Archaic UNIX Makefile that converts files with
@@ -216,12 +216,12 @@ Files in this distribution:
makefile.openbsd => OpenBSD makefile
makefile.sgi => Silicon Graphics IRIX (cc, creates static lib)
makefile.sggcc => Silicon Graphics
- (gcc, creates libpng12.so.0.1.2.18)
+ (gcc, creates libpng12.so.0.1.2.24)
makefile.sunos => Sun makefile
makefile.solaris => Solaris 2.X makefile
- (gcc, creates libpng12.so.0.1.2.18)
+ (gcc, creates libpng12.so.0.1.2.24)
makefile.so9 => Solaris 9 makefile
- (gcc, creates libpng12.so.0.1.2.18)
+ (gcc, creates libpng12.so.0.1.2.24)
makefile.32sunu => Sun Ultra 32-bit makefile
makefile.64sunu => Sun Ultra 64-bit makefile
makefile.sco => For SCO OSr5 ELF and Unixware 7 with Native cc
diff --git a/Build/source/libs/libpng/Y2KINFO b/Build/source/libs/libpng/Y2KINFO
index aa690e4ef46..829b511e45c 100644
--- a/Build/source/libs/libpng/Y2KINFO
+++ b/Build/source/libs/libpng/Y2KINFO
@@ -1,13 +1,13 @@
Y2K compliance in libpng:
=========================
- May 15, 2007
+ December 14, 2007
Since the PNG Development group is an ad-hoc body, we can't make
an official declaration.
This is your unofficial assurance that libpng from version 0.71 and
- upward through 1.2.18 are Y2K compliant. It is my belief that earlier
+ upward through 1.2.24 are Y2K compliant. It is my belief that earlier
versions were also Y2K compliant.
Libpng only has three year fields. One is a 2-byte unsigned integer
diff --git a/Build/source/libs/libpng/libpng-1.2.18.txt b/Build/source/libs/libpng/libpng-1.2.24.txt
index 1b251546ef8..5b8dc53b970 100644
--- a/Build/source/libs/libpng/libpng-1.2.18.txt
+++ b/Build/source/libs/libpng/libpng-1.2.24.txt
@@ -1,6 +1,6 @@
libpng.txt - A description on how to use and modify libpng
- libpng version 1.2.18 - May 15, 2007
+ libpng version 1.2.24 - December 14, 2007
Updated and distributed by Glenn Randers-Pehrson
<glennrp at users.sourceforge.net>
Copyright (c) 1998-2007 Glenn Randers-Pehrson
@@ -86,9 +86,7 @@ Libpng is thread safe, provided the threads are using different
instances of the structures. Each thread should have its own
png_struct and png_info instances, and thus its own image.
Libpng does not protect itself against two threads using the
-same instance of a structure. Note: thread safety may be defeated
-by use of some of the MMX assembler code in pnggccrd.c, which is only
-compiled when the user defines PNG_THREAD_UNSAFE_OK.
+same instance of a structure.
II. Structures
@@ -2355,17 +2353,13 @@ For a more compact example of writing a PNG image, see the file example.c.
V. Modifying/Customizing libpng:
-There are three issues here. The first is changing how libpng does
+There are two issues here. The first is changing how libpng does
standard things like memory allocation, input/output, and error handling.
The second deals with more complicated things like adding new chunks,
adding new transformations, and generally changing how libpng works.
Both of those are compile-time issues; that is, they are generally
determined at the time the code is written, and there is rarely a need
-to provide the user with a means of changing them. The third is a
-run-time issue: choosing between and/or tuning one or more alternate
-versions of computationally intensive routines; specifically, optimized
-assembly-language (and therefore compiler- and platform-dependent)
-versions.
+to provide the user with a means of changing them.
Memory allocation, input/output, and error handling
@@ -2726,125 +2720,6 @@ When PNG_DEBUG = 1, the macros are defined, but only png_debug statements
having level = 0 will be printed. There aren't any such statements in
this version of libpng, but if you insert some they will be printed.
-VI. Runtime optimization
-
-A new feature in libpng 1.2.0 is the ability to dynamically switch between
-standard and optimized versions of some routines. Currently these are
-limited to three computationally intensive tasks when reading PNG files:
-decoding row filters, expanding interlacing, and combining interlaced or
-transparent row data with previous row data. Currently the optimized
-versions are available only for x86 (Intel, AMD, etc.) platforms with
-MMX support, though this may change in future versions. (For example,
-the non-MMX assembler optimizations for zlib might become similarly
-runtime-selectable in future releases, in which case libpng could be
-extended to support them. Alternatively, the compile-time choice of
-floating-point versus integer routines for gamma correction might become
-runtime-selectable.)
-
-Because such optimizations tend to be very platform- and compiler-dependent,
-both in how they are written and in how they perform, the new runtime code
-in libpng has been written to allow programs to query, enable, and disable
-either specific optimizations or all such optimizations. For example, to
-enable all possible optimizations (bearing in mind that some "optimizations"
-may actually run more slowly in rare cases):
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- png_uint_32 mask, flags;
-
- flags = png_get_asm_flags(png_ptr);
- mask = png_get_asm_flagmask(PNG_SELECT_READ | PNG_SELECT_WRITE);
- png_set_asm_flags(png_ptr, flags | mask);
- #endif
-
-To enable only optimizations relevant to reading PNGs, use PNG_SELECT_READ
-by itself when calling png_get_asm_flagmask(); similarly for optimizing
-only writing. To disable all optimizations:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- flags = png_get_asm_flags(png_ptr);
- mask = png_get_asm_flagmask(PNG_SELECT_READ | PNG_SELECT_WRITE);
- png_set_asm_flags(png_ptr, flags & ~mask);
- #endif
-
-To enable or disable only MMX-related features, use png_get_mmx_flagmask()
-in place of png_get_asm_flagmask(). The mmx version takes one additional
-parameter:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- int selection = PNG_SELECT_READ | PNG_SELECT_WRITE;
- int compilerID;
-
- mask = png_get_mmx_flagmask(selection, &compilerID);
- #endif
-
-On return, compilerID will indicate which version of the MMX assembler
-optimizations was compiled. Currently two flavors exist: Microsoft
-Visual C++ (compilerID == 1) and GNU C (a.k.a. gcc/gas, compilerID == 2).
-On non-x86 platforms or on systems compiled without MMX optimizations, a
-value of -1 is used.
-
-Note that both png_get_asm_flagmask() and png_get_mmx_flagmask() return
-all valid, settable optimization bits for the version of the library that's
-currently in use. In the case of shared (dynamically linked) libraries,
-this may include optimizations that did not exist at the time the code was
-written and compiled. It is also possible, of course, to enable only known,
-specific optimizations; for example:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- flags = PNG_ASM_FLAG_MMX_READ_COMBINE_ROW \
- | PNG_ASM_FLAG_MMX_READ_INTERLACE \
- | PNG_ASM_FLAG_MMX_READ_FILTER_SUB \
- | PNG_ASM_FLAG_MMX_READ_FILTER_UP \
- | PNG_ASM_FLAG_MMX_READ_FILTER_AVG \
- | PNG_ASM_FLAG_MMX_READ_FILTER_PAETH ;
- png_set_asm_flags(png_ptr, flags);
- #endif
-
-This method would enable only the MMX read-optimizations available at the
-time of libpng 1.2.0's release, regardless of whether a later version of
-the DLL were actually being used. (Also note that these functions did not
-exist in versions older than 1.2.0, so any attempt to run a dynamically
-linked app on such an older version would fail.)
-
-To determine whether the processor supports MMX instructions at all, use
-the png_mmx_support() function:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- mmxsupport = png_mmx_support();
- #endif
-
-It returns -1 if MMX support is not compiled into libpng, 0 if MMX code
-is compiled but MMX is not supported by the processor, or 1 if MMX support
-is fully available. Note that png_mmx_support(), png_get_mmx_flagmask(),
-and png_get_asm_flagmask() all may be called without allocating and ini-
-tializing any PNG structures (for example, as part of a usage screen or
-"about" box).
-
-The following code can be used to prevent an application from using the
-thread_unsafe features, even if libpng was built with PNG_THREAD_UNSAFE_OK
-defined:
-
-#if defined(PNG_USE_PNGGCCRD) && defined(PNG_ASSEMBLER_CODE_SUPPORTED) \
- && defined(PNG_THREAD_UNSAFE_OK)
- /* Disable thread-unsafe features of pnggccrd */
- if (png_access_version_number() >= 10200)
- {
- png_uint_32 mmx_disable_mask = 0;
- png_uint_32 asm_flags;
-
- mmx_disable_mask |= ( PNG_ASM_FLAG_MMX_READ_COMBINE_ROW \
- | PNG_ASM_FLAG_MMX_READ_FILTER_SUB \
- | PNG_ASM_FLAG_MMX_READ_FILTER_AVG \
- | PNG_ASM_FLAG_MMX_READ_FILTER_PAETH );
- asm_flags = png_get_asm_flags(png_ptr);
- png_set_asm_flags(png_ptr, asm_flags & ~mmx_disable_mask);
- }
-#endif
-
-For more extensive examples of runtime querying, enabling and disabling
-of optimized features, see contrib/gregbook/readpng2.c in the libpng
-source-code distribution.
-
VII. MNG support
The MNG specification (available at http://www.libpng.org/pub/mng) allows
@@ -2921,13 +2796,13 @@ application:
IX. Y2K Compliance in libpng
-May 15, 2007
+December 14, 2007
Since the PNG Development group is an ad-hoc body, we can't make
an official declaration.
This is your unofficial assurance that libpng from version 0.71 and
-upward through 1.2.18 are Y2K compliant. It is my belief that earlier
+upward through 1.2.24 are Y2K compliant. It is my belief that earlier
versions were also Y2K compliant.
Libpng only has three year fields. One is a 2-byte unsigned integer that
diff --git a/Build/source/libs/libpng/libpng.3 b/Build/source/libs/libpng/libpng.3
index a94c616db7f..060cdc1426f 100644
--- a/Build/source/libs/libpng/libpng.3
+++ b/Build/source/libs/libpng/libpng.3
@@ -1,6 +1,6 @@
-.TH LIBPNG 3 "May 15, 2007"
+.TH LIBPNG 3 "December 14, 2007"
.SH NAME
-libpng \- Portable Network Graphics (PNG) Reference Library 1.2.18
+libpng \- Portable Network Graphics (PNG) Reference Library 1.2.24
.SH SYNOPSIS
\fB
#include <png.h>\fP
@@ -410,7 +410,7 @@ Following is a copy of the libpng.txt file that accompanies libpng.
.SH LIBPNG.TXT
libpng.txt - A description on how to use and modify libpng
- libpng version 1.2.18 - May 15, 2007
+ libpng version 1.2.24 - December 14, 2007
Updated and distributed by Glenn Randers-Pehrson
<glennrp at users.sourceforge.net>
Copyright (c) 1998-2007 Glenn Randers-Pehrson
@@ -496,9 +496,7 @@ Libpng is thread safe, provided the threads are using different
instances of the structures. Each thread should have its own
png_struct and png_info instances, and thus its own image.
Libpng does not protect itself against two threads using the
-same instance of a structure. Note: thread safety may be defeated
-by use of some of the MMX assembler code in pnggccrd.c, which is only
-compiled when the user defines PNG_THREAD_UNSAFE_OK.
+same instance of a structure.
.SH II. Structures
@@ -2765,17 +2763,13 @@ For a more compact example of writing a PNG image, see the file example.c.
.SH V. Modifying/Customizing libpng:
-There are three issues here. The first is changing how libpng does
+There are two issues here. The first is changing how libpng does
standard things like memory allocation, input/output, and error handling.
The second deals with more complicated things like adding new chunks,
adding new transformations, and generally changing how libpng works.
Both of those are compile-time issues; that is, they are generally
determined at the time the code is written, and there is rarely a need
-to provide the user with a means of changing them. The third is a
-run-time issue: choosing between and/or tuning one or more alternate
-versions of computationally intensive routines; specifically, optimized
-assembly-language (and therefore compiler- and platform-dependent)
-versions.
+to provide the user with a means of changing them.
Memory allocation, input/output, and error handling
@@ -3136,125 +3130,6 @@ When PNG_DEBUG = 1, the macros are defined, but only png_debug statements
having level = 0 will be printed. There aren't any such statements in
this version of libpng, but if you insert some they will be printed.
-.SH VI. Runtime optimization
-
-A new feature in libpng 1.2.0 is the ability to dynamically switch between
-standard and optimized versions of some routines. Currently these are
-limited to three computationally intensive tasks when reading PNG files:
-decoding row filters, expanding interlacing, and combining interlaced or
-transparent row data with previous row data. Currently the optimized
-versions are available only for x86 (Intel, AMD, etc.) platforms with
-MMX support, though this may change in future versions. (For example,
-the non-MMX assembler optimizations for zlib might become similarly
-runtime-selectable in future releases, in which case libpng could be
-extended to support them. Alternatively, the compile-time choice of
-floating-point versus integer routines for gamma correction might become
-runtime-selectable.)
-
-Because such optimizations tend to be very platform- and compiler-dependent,
-both in how they are written and in how they perform, the new runtime code
-in libpng has been written to allow programs to query, enable, and disable
-either specific optimizations or all such optimizations. For example, to
-enable all possible optimizations (bearing in mind that some "optimizations"
-may actually run more slowly in rare cases):
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- png_uint_32 mask, flags;
-
- flags = png_get_asm_flags(png_ptr);
- mask = png_get_asm_flagmask(PNG_SELECT_READ | PNG_SELECT_WRITE);
- png_set_asm_flags(png_ptr, flags | mask);
- #endif
-
-To enable only optimizations relevant to reading PNGs, use PNG_SELECT_READ
-by itself when calling png_get_asm_flagmask(); similarly for optimizing
-only writing. To disable all optimizations:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- flags = png_get_asm_flags(png_ptr);
- mask = png_get_asm_flagmask(PNG_SELECT_READ | PNG_SELECT_WRITE);
- png_set_asm_flags(png_ptr, flags & ~mask);
- #endif
-
-To enable or disable only MMX-related features, use png_get_mmx_flagmask()
-in place of png_get_asm_flagmask(). The mmx version takes one additional
-parameter:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- int selection = PNG_SELECT_READ | PNG_SELECT_WRITE;
- int compilerID;
-
- mask = png_get_mmx_flagmask(selection, &compilerID);
- #endif
-
-On return, compilerID will indicate which version of the MMX assembler
-optimizations was compiled. Currently two flavors exist: Microsoft
-Visual C++ (compilerID == 1) and GNU C (a.k.a. gcc/gas, compilerID == 2).
-On non-x86 platforms or on systems compiled without MMX optimizations, a
-value of -1 is used.
-
-Note that both png_get_asm_flagmask() and png_get_mmx_flagmask() return
-all valid, settable optimization bits for the version of the library that's
-currently in use. In the case of shared (dynamically linked) libraries,
-this may include optimizations that did not exist at the time the code was
-written and compiled. It is also possible, of course, to enable only known,
-specific optimizations; for example:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- flags = PNG_ASM_FLAG_MMX_READ_COMBINE_ROW \
- | PNG_ASM_FLAG_MMX_READ_INTERLACE \
- | PNG_ASM_FLAG_MMX_READ_FILTER_SUB \
- | PNG_ASM_FLAG_MMX_READ_FILTER_UP \
- | PNG_ASM_FLAG_MMX_READ_FILTER_AVG \
- | PNG_ASM_FLAG_MMX_READ_FILTER_PAETH ;
- png_set_asm_flags(png_ptr, flags);
- #endif
-
-This method would enable only the MMX read-optimizations available at the
-time of libpng 1.2.0's release, regardless of whether a later version of
-the DLL were actually being used. (Also note that these functions did not
-exist in versions older than 1.2.0, so any attempt to run a dynamically
-linked app on such an older version would fail.)
-
-To determine whether the processor supports MMX instructions at all, use
-the png_mmx_support() function:
-
- #if defined(PNG_LIBPNG_VER) && (PNG_LIBPNG_VER >= 10200)
- mmxsupport = png_mmx_support();
- #endif
-
-It returns -1 if MMX support is not compiled into libpng, 0 if MMX code
-is compiled but MMX is not supported by the processor, or 1 if MMX support
-is fully available. Note that png_mmx_support(), png_get_mmx_flagmask(),
-and png_get_asm_flagmask() all may be called without allocating and ini-
-tializing any PNG structures (for example, as part of a usage screen or
-"about" box).
-
-The following code can be used to prevent an application from using the
-thread_unsafe features, even if libpng was built with PNG_THREAD_UNSAFE_OK
-defined:
-
-#if defined(PNG_USE_PNGGCCRD) && defined(PNG_ASSEMBLER_CODE_SUPPORTED) \
- && defined(PNG_THREAD_UNSAFE_OK)
- /* Disable thread-unsafe features of pnggccrd */
- if (png_access_version_number() >= 10200)
- {
- png_uint_32 mmx_disable_mask = 0;
- png_uint_32 asm_flags;
-
- mmx_disable_mask |= ( PNG_ASM_FLAG_MMX_READ_COMBINE_ROW \
- | PNG_ASM_FLAG_MMX_READ_FILTER_SUB \
- | PNG_ASM_FLAG_MMX_READ_FILTER_AVG \
- | PNG_ASM_FLAG_MMX_READ_FILTER_PAETH );
- asm_flags = png_get_asm_flags(png_ptr);
- png_set_asm_flags(png_ptr, asm_flags & ~mmx_disable_mask);
- }
-#endif
-
-For more extensive examples of runtime querying, enabling and disabling
-of optimized features, see contrib/gregbook/readpng2.c in the libpng
-source-code distribution.
-
.SH VII. MNG support
The MNG specification (available at http://www.libpng.org/pub/mng) allows
@@ -3331,13 +3206,13 @@ application:
.SH IX. Y2K Compliance in libpng
-May 15, 2007
+December 14, 2007
Since the PNG Development group is an ad-hoc body, we can't make
an official declaration.
This is your unofficial assurance that libpng from version 0.71 and
-upward through 1.2.18 are Y2K compliant. It is my belief that earlier
+upward through 1.2.24 are Y2K compliant. It is my belief that earlier
versions were also Y2K compliant.
Libpng only has three year fields. One is a 2-byte unsigned integer that
@@ -3526,6 +3401,31 @@ the first widely used release:
1.2.17 13 10217 12.so.0.17[.0]
1.0.26 10 10026 10.so.0.26[.0]
1.2.18 13 10218 12.so.0.18[.0]
+ 1.2.19beta1-31 13 10219 12.so.0.19[.0]
+ 1.0.27rc1-6 10 10027 10.so.0.27[.0]
+ 1.2.19rc1-6 13 10219 12.so.0.19[.0]
+ 1.0.27 10 10027 10.so.0.27[.0]
+ 1.2.19 13 10219 12.so.0.19[.0]
+ 1.2.20beta01-04 13 10220 12.so.0.20[.0]
+ 1.0.28rc1-6 10 10028 10.so.0.28[.0]
+ 1.2.20rc1-6 13 10220 12.so.0.20[.0]
+ 1.0.28 10 10028 10.so.0.28[.0]
+ 1.2.20 13 10220 12.so.0.20[.0]
+ 1.2.21beta1-2 13 10221 12.so.0.21[.0]
+ 1.2.21rc1-3 13 10221 12.so.0.21[.0]
+ 1.0.29 10 10029 10.so.0.29[.0]
+ 1.2.21 13 10221 12.so.0.21[.0]
+ 1.2.22beta1-4 13 10222 12.so.0.22[.0]
+ 1.0.30rc1 13 10030 10.so.0.30[.0]
+ 1.2.22rc1 13 10222 12.so.0.22[.0]
+ 1.0.30 10 10030 10.so.0.30[.0]
+ 1.2.22 13 10222 12.so.0.22[.0]
+ 1.2.23beta01-05 13 10223 12.so.0.23[.0]
+ 1.2.23rc01 13 10223 12.so.0.23[.0]
+ 1.2.23 13 10223 12.so.0.23[.0]
+ 1.2.24beta01-02 13 10224 12.so.0.24[.0]
+ 1.2.24rc01 13 10224 12.so.0.24[.0]
+ 1.2.24 13 10224 12.so.0.24[.0]
Henceforth the source version will match the shared-library minor
and patch numbers; the shared-library major version number will be
@@ -3538,7 +3438,7 @@ version 1.0.6j; from then on they were given the upcoming public
release number plus "betaNN" or "rcN".
.SH "SEE ALSO"
-libpngpf(3), png(5)
+.IR libpngpf(3) ", " png(5)
.LP
.IR libpng :
.IP
@@ -3581,7 +3481,7 @@ possible without all of you.
Thanks to Frank J. T. Wojcik for helping with the documentation.
-Libpng version 1.2.18 - May 15, 2007:
+Libpng version 1.2.24 - December 14, 2007:
Initially created in 1995 by Guy Eric Schalnat, then of Group 42, Inc.
Currently maintained by Glenn Randers-Pehrson (glennrp at users.sourceforge.net).
@@ -3602,7 +3502,7 @@ included in the libpng distribution, the latter shall prevail.)
If you modify libpng you may insert additional notices immediately following
this sentence.
-libpng versions 1.2.6, August 15, 2004, through 1.2.18, May 15, 2007, are
+libpng versions 1.2.6, August 15, 2004, through 1.2.24, December 14, 2007, are
Copyright (c) 2004,2006-2007 Glenn Randers-Pehrson, and are
distributed according to the same disclaimer and license as libpng-1.2.5
with the following individual added to the list of Contributing Authors
@@ -3701,7 +3601,7 @@ certification mark of the Open Source Initiative.
Glenn Randers-Pehrson
glennrp at users.sourceforge.net
-May 15, 2007
+December 14, 2007
.\" end of man page
diff --git a/Build/source/libs/libpng/libpngpf.3 b/Build/source/libs/libpng/libpngpf.3
index f5723cddc72..1e360de1295 100644
--- a/Build/source/libs/libpng/libpngpf.3
+++ b/Build/source/libs/libpng/libpngpf.3
@@ -1,6 +1,6 @@
-.TH LIBPNGPF 3 "May 15, 2007"
+.TH LIBPNGPF 3 "December 14, 2007"
.SH NAME
-libpng \- Portable Network Graphics (PNG) Reference Library 1.2.18
+libpng \- Portable Network Graphics (PNG) Reference Library 1.2.24
(private functions)
.SH SYNOPSIS
\fB#include <png.h>\fP
@@ -269,6 +269,6 @@ are listed alphabetically here as an aid to libpng maintainers.
See png.h for more information on these functions.
.SH SEE ALSO
-libpng(3), png(5)
+.IR libpng(3) ", " png(5)
.SH AUTHOR
Glenn Randers-Pehrson
diff --git a/Build/source/libs/libpng/png.5 b/Build/source/libs/libpng/png.5
index bf6c6fd5b7c..9f33460582c 100644
--- a/Build/source/libs/libpng/png.5
+++ b/Build/source/libs/libpng/png.5
@@ -1,4 +1,4 @@
-.TH PNG 5 "May 15, 2007"
+.TH PNG 5 "December 14, 2007"
.SH NAME
png \- Portable Network Graphics (PNG) format
.SH DESCRIPTION
@@ -18,7 +18,7 @@ gamma and chromaticity data for improved color matching on heterogeneous
platforms.
.SH "SEE ALSO"
-.IR libpng(3), zlib(3), deflate(5), and zlib(5)
+.IR libpng(3) ", " zlib(3) ", " deflate(5) ", and " zlib(5)
.LP
PNG specification (second edition), November 2003:
.IP
diff --git a/Build/source/libs/libpng/png.c b/Build/source/libs/libpng/png.c
index 9665c2c1c3b..4d25559cf1d 100644
--- a/Build/source/libs/libpng/png.c
+++ b/Build/source/libs/libpng/png.c
@@ -1,7 +1,7 @@
/* png.c - location for general purpose libpng functions
*
- * Last changed in libpng 1.2.17 May 15, 2007
+ * Last changed in libpng 1.2.21 October 4, 2007
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -13,20 +13,20 @@
#include "png.h"
/* Generate a compiler error if there is an old png.h in the search path. */
-typedef version_1_2_18 Your_png_h_is_not_version_1_2_18;
+typedef version_1_2_24 Your_png_h_is_not_version_1_2_24;
/* Version information for C files. This had better match the version
* string defined in png.h. */
#ifdef PNG_USE_GLOBAL_ARRAYS
/* png_libpng_ver was changed to a function in version 1.0.5c */
-const char png_libpng_ver[18] = PNG_LIBPNG_VER_STRING;
+PNG_CONST char png_libpng_ver[18] = PNG_LIBPNG_VER_STRING;
#ifdef PNG_READ_SUPPORTED
/* png_sig was changed to a function in version 1.0.5c */
/* Place to hold the signature string for a PNG file. */
-const png_byte FARDATA png_sig[8] = {137, 80, 78, 71, 13, 10, 26, 10};
+PNG_CONST png_byte FARDATA png_sig[8] = {137, 80, 78, 71, 13, 10, 26, 10};
#endif /* PNG_READ_SUPPORTED */
/* Invoke global declarations for constant strings for known chunk types */
@@ -56,32 +56,27 @@ PNG_zTXt;
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
/* start of interlace block */
-const int FARDATA png_pass_start[] = {0, 4, 0, 2, 0, 1, 0};
+PNG_CONST int FARDATA png_pass_start[] = {0, 4, 0, 2, 0, 1, 0};
/* offset to next interlace block */
-const int FARDATA png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
+PNG_CONST int FARDATA png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
/* start of interlace block in the y direction */
-const int FARDATA png_pass_ystart[] = {0, 0, 4, 0, 2, 0, 1};
+PNG_CONST int FARDATA png_pass_ystart[] = {0, 0, 4, 0, 2, 0, 1};
/* offset to next interlace block in the y direction */
-const int FARDATA png_pass_yinc[] = {8, 8, 8, 4, 4, 2, 2};
-
-/* width of interlace block (used in assembler routines only) */
-#ifdef PNG_HAVE_MMX_COMBINE_ROW
-const int FARDATA png_pass_width[] = {8, 4, 4, 2, 2, 1, 1};
-#endif
+PNG_CONST int FARDATA png_pass_yinc[] = {8, 8, 8, 4, 4, 2, 2};
/* Height of interlace block. This is not currently used - if you need
* it, uncomment it here and in png.h
-const int FARDATA png_pass_height[] = {8, 8, 4, 4, 2, 2, 1};
+PNG_CONST int FARDATA png_pass_height[] = {8, 8, 4, 4, 2, 2, 1};
*/
/* Mask to determine which pixels are valid in a pass */
-const int FARDATA png_pass_mask[] = {0x80, 0x08, 0x88, 0x22, 0xaa, 0x55, 0xff};
+PNG_CONST int FARDATA png_pass_mask[] = {0x80, 0x08, 0x88, 0x22, 0xaa, 0x55, 0xff};
/* Mask to determine which pixels to overwrite while displaying */
-const int FARDATA png_pass_dsp_mask[]
+PNG_CONST int FARDATA png_pass_dsp_mask[]
= {0xff, 0x0f, 0xff, 0x33, 0xff, 0x55, 0xff};
#endif /* PNG_READ_SUPPORTED */
@@ -134,7 +129,7 @@ png_sig_cmp(png_bytep sig, png_size_t start, png_size_t num_to_check)
#if defined(PNG_1_0_X) || defined(PNG_1_2_X)
/* (Obsolete) function to check signature bytes. It does not allow one
* to check a partial signature. This function might be removed in the
- * future - use png_sig_cmp(). Returns true (nonzero) if the file is a PNG.
+ * future - use png_sig_cmp(). Returns true (nonzero) if the file is PNG.
*/
int PNGAPI
png_check_sig(png_bytep sig, int num)
@@ -674,7 +669,7 @@ png_convert_to_rfc1123(png_structp png_ptr, png_timep ptime)
#ifdef USE_FAR_KEYWORD
{
char near_time_buf[29];
- sprintf(near_time_buf, "%d %s %d %02d:%02d:%02d +0000",
+ png_snprintf6(near_time_buf,29,"%d %s %d %02d:%02d:%02d +0000",
ptime->day % 32, short_months[(ptime->month - 1) % 12],
ptime->year, ptime->hour % 24, ptime->minute % 60,
ptime->second % 61);
@@ -682,7 +677,7 @@ png_convert_to_rfc1123(png_structp png_ptr, png_timep ptime)
29*png_sizeof(char));
}
#else
- sprintf(png_ptr->time_buffer, "%d %s %d %02d:%02d:%02d +0000",
+ png_snprintf6(png_ptr->time_buffer,29,"%d %s %d %02d:%02d:%02d +0000",
ptime->day % 32, short_months[(ptime->month - 1) % 12],
ptime->year, ptime->hour % 24, ptime->minute % 60,
ptime->second % 61);
@@ -692,25 +687,16 @@ png_convert_to_rfc1123(png_structp png_ptr, png_timep ptime)
}
#endif /* PNG_TIME_RFC1123_SUPPORTED */
-#if 0
-/* Signature string for a PNG file. */
-png_bytep PNGAPI
-png_sig_bytes(void)
-{
- return ((png_bytep)"\211\120\116\107\015\012\032\012");
-}
-#endif
#endif /* defined(PNG_READ_SUPPORTED) || defined(PNG_WRITE_SUPPORTED) */
png_charp PNGAPI
png_get_copyright(png_structp png_ptr)
{
- if (&png_ptr != NULL) /* silence compiler warning about unused png_ptr */
- return ((png_charp) "\n libpng version 1.2.18 - May 15, 2007\n\
+ png_ptr = png_ptr; /* silence compiler warning about unused png_ptr */
+ return ((png_charp) "\n libpng version 1.2.24 - December 14, 2007\n\
Copyright (c) 1998-2007 Glenn Randers-Pehrson\n\
Copyright (c) 1996-1997 Andreas Dilger\n\
Copyright (c) 1995-1996 Guy Eric Schalnat, Group 42, Inc.\n");
- return ((png_charp) "");
}
/* The following return the library version as a short string in the
@@ -725,27 +711,28 @@ png_charp PNGAPI
png_get_libpng_ver(png_structp png_ptr)
{
/* Version of *.c files used when building libpng */
- if (&png_ptr != NULL) /* silence compiler warning about unused png_ptr */
- return ((png_charp) PNG_LIBPNG_VER_STRING);
- return ((png_charp) "");
+ png_ptr = png_ptr; /* silence compiler warning about unused png_ptr */
+ return ((png_charp) PNG_LIBPNG_VER_STRING);
}
png_charp PNGAPI
png_get_header_ver(png_structp png_ptr)
{
/* Version of *.h files used when building libpng */
- if (&png_ptr != NULL) /* silence compiler warning about unused png_ptr */
- return ((png_charp) PNG_LIBPNG_VER_STRING);
- return ((png_charp) "");
+ png_ptr = png_ptr; /* silence compiler warning about unused png_ptr */
+ return ((png_charp) PNG_LIBPNG_VER_STRING);
}
png_charp PNGAPI
png_get_header_version(png_structp png_ptr)
{
/* Returns longer string containing both version and date */
- if (&png_ptr != NULL) /* silence compiler warning about unused png_ptr */
- return ((png_charp) PNG_HEADER_VERSION_STRING);
- return ((png_charp) "");
+ png_ptr = png_ptr; /* silence compiler warning about unused png_ptr */
+ return ((png_charp) PNG_HEADER_VERSION_STRING
+#ifndef PNG_READ_SUPPORTED
+ " (NO READ SUPPORT)"
+#endif
+ "\n");
}
#if defined(PNG_READ_SUPPORTED) || defined(PNG_WRITE_SUPPORTED)
@@ -756,7 +743,7 @@ png_handle_as_unknown(png_structp png_ptr, png_bytep chunk_name)
/* check chunk_name and return "keep" value if it's on the list, else 0 */
int i;
png_bytep p;
- if((png_ptr == NULL && chunk_name == NULL) || png_ptr->num_chunk_list<=0)
+ if(png_ptr == NULL || chunk_name == NULL || png_ptr->num_chunk_list<=0)
return 0;
p=png_ptr->chunk_list+png_ptr->num_chunk_list*5-5;
for (i = png_ptr->num_chunk_list; i; i--, p-=5)
@@ -786,65 +773,15 @@ png_access_version_number(void)
#if defined(PNG_READ_SUPPORTED) && defined(PNG_ASSEMBLER_CODE_SUPPORTED)
#if !defined(PNG_1_0_X)
-#if defined(PNG_MMX_CODE_SUPPORTED)
-/* this INTERNAL function was added to libpng 1.2.0 */
-void /* PRIVATE */
-png_init_mmx_flags (png_structp png_ptr)
-{
- if(png_ptr == NULL) return;
- png_ptr->mmx_rowbytes_threshold = 0;
- png_ptr->mmx_bitdepth_threshold = 0;
-
-# if (defined(PNG_USE_PNGVCRD) || defined(PNG_USE_PNGGCCRD))
-
- png_ptr->asm_flags |= PNG_ASM_FLAG_MMX_SUPPORT_COMPILED;
-
- if (png_mmx_support() > 0) {
- png_ptr->asm_flags |= PNG_ASM_FLAG_MMX_SUPPORT_IN_CPU
-# ifdef PNG_HAVE_MMX_COMBINE_ROW
- | PNG_ASM_FLAG_MMX_READ_COMBINE_ROW
-# endif
-# ifdef PNG_HAVE_MMX_READ_INTERLACE
- | PNG_ASM_FLAG_MMX_READ_INTERLACE
-# endif
-# ifndef PNG_HAVE_MMX_READ_FILTER_ROW
- ;
-# else
- | PNG_ASM_FLAG_MMX_READ_FILTER_SUB
- | PNG_ASM_FLAG_MMX_READ_FILTER_UP
- | PNG_ASM_FLAG_MMX_READ_FILTER_AVG
- | PNG_ASM_FLAG_MMX_READ_FILTER_PAETH ;
-
- png_ptr->mmx_rowbytes_threshold = PNG_MMX_ROWBYTES_THRESHOLD_DEFAULT;
- png_ptr->mmx_bitdepth_threshold = PNG_MMX_BITDEPTH_THRESHOLD_DEFAULT;
-# endif
- } else {
- png_ptr->asm_flags &= ~( PNG_ASM_FLAG_MMX_SUPPORT_IN_CPU
- | PNG_MMX_READ_FLAGS
- | PNG_MMX_WRITE_FLAGS );
- }
-
-# else /* !(PNGVCRD || PNGGCCRD) */
-
- /* clear all MMX flags; no support is compiled in */
- png_ptr->asm_flags &= ~( PNG_MMX_FLAGS );
-
-# endif /* ?(PNGVCRD || PNGGCCRD) */
-}
-
-#endif /* !(PNG_MMX_CODE_SUPPORTED) */
-
/* this function was added to libpng 1.2.0 */
-#if !defined(PNG_USE_PNGGCCRD) && \
- !(defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_USE_PNGVCRD))
int PNGAPI
png_mmx_support(void)
{
+ /* obsolete, to be removed from libpng-1.4.0 */
return -1;
}
-#endif
-#endif /* PNG_1_0_X && PNG_ASSEMBLER_CODE_SUPPORTED */
-#endif /* PNG_READ_SUPPORTED */
+#endif /* PNG_1_0_X */
+#endif /* PNG_READ_SUPPORTED && PNG_ASSEMBLER_CODE_SUPPORTED */
#if defined(PNG_READ_SUPPORTED) || defined(PNG_WRITE_SUPPORTED)
#ifdef PNG_SIZE_T
diff --git a/Build/source/libs/libpng/png.h b/Build/source/libs/libpng/png.h
index 7bb0f301ea8..3ac393ea343 100644
--- a/Build/source/libs/libpng/png.h
+++ b/Build/source/libs/libpng/png.h
@@ -1,7 +1,7 @@
/* png.h - header file for PNG reference library
*
- * libpng version 1.2.18 - May 15, 2007
+ * libpng version 1.2.24 - December 14, 2007
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
* (Version 0.88 Copyright (c) 1995, 1996 Guy Eric Schalnat, Group 42, Inc.)
@@ -9,7 +9,7 @@
* Authors and maintainers:
* libpng versions 0.71, May 1995, through 0.88, January 1996: Guy Schalnat
* libpng versions 0.89c, June 1996, through 0.96, May 1997: Andreas Dilger
- * libpng versions 0.97, January 1998, through 1.2.18 - May 15, 2007: Glenn
+ * libpng versions 0.97, January 1998, through 1.2.24 - December 14, 2007: Glenn
* See also "Contributing Authors", below.
*
* Note about libpng version numbers:
@@ -150,6 +150,31 @@
* 1.2.17 13 10217 12.so.0.17[.0]
* 1.0.26 10 10026 10.so.0.26[.0]
* 1.2.18 13 10218 12.so.0.18[.0]
+ * 1.2.19beta1-31 13 10219 12.so.0.19[.0]
+ * 1.0.27rc1-6 10 10027 10.so.0.27[.0]
+ * 1.2.19rc1-6 13 10219 12.so.0.19[.0]
+ * 1.0.27 10 10027 10.so.0.27[.0]
+ * 1.2.19 13 10219 12.so.0.19[.0]
+ * 1.2.20beta01-04 13 10220 12.so.0.20[.0]
+ * 1.0.28rc1-6 10 10028 10.so.0.28[.0]
+ * 1.2.20rc1-6 13 10220 12.so.0.20[.0]
+ * 1.0.28 10 10028 10.so.0.28[.0]
+ * 1.2.20 13 10220 12.so.0.20[.0]
+ * 1.2.21beta1-2 13 10221 12.so.0.21[.0]
+ * 1.2.21rc1-3 13 10221 12.so.0.21[.0]
+ * 1.0.29 10 10029 10.so.0.29[.0]
+ * 1.2.21 13 10221 12.so.0.21[.0]
+ * 1.2.22beta1-4 13 10222 12.so.0.22[.0]
+ * 1.0.30rc1 10 10030 10.so.0.30[.0]
+ * 1.2.22rc1 13 10222 12.so.0.22[.0]
+ * 1.0.30 10 10030 10.so.0.30[.0]
+ * 1.2.22 13 10222 12.so.0.22[.0]
+ * 1.2.23beta01-05 13 10223 12.so.0.23[.0]
+ * 1.2.23rc01 13 10223 12.so.0.23[.0]
+ * 1.2.23 13 10223 12.so.0.23[.0]
+ * 1.2.24beta01-02 13 10224 12.so.0.24[.0]
+ * 1.2.24rc01 13 10224 12.so.0.24[.0]
+ * 1.2.24 13 10224 12.so.0.24[.0]
*
* Henceforth the source version will match the shared-library major
* and minor numbers; the shared-library major version number will be
@@ -179,7 +204,7 @@
* If you modify libpng you may insert additional notices immediately following
* this sentence.
*
- * libpng versions 1.2.6, August 15, 2004, through 1.2.18, May 15, 2007, are
+ * libpng versions 1.2.6, August 15, 2004, through 1.2.24, December 14, 2007, are
* Copyright (c) 2004, 2006-2007 Glenn Randers-Pehrson, and are
* distributed according to the same disclaimer and license as libpng-1.2.5
* with the following individual added to the list of Contributing Authors:
@@ -291,13 +316,13 @@
* Y2K compliance in libpng:
* =========================
*
- * May 15, 2007
+ * December 14, 2007
*
* Since the PNG Development group is an ad-hoc body, we can't make
* an official declaration.
*
* This is your unofficial assurance that libpng from version 0.71 and
- * upward through 1.2.18 are Y2K compliant. It is my belief that earlier
+ * upward through 1.2.24 are Y2K compliant. It is my belief that earlier
* versions were also Y2K compliant.
*
* Libpng only has three year fields. One is a 2-byte unsigned integer
@@ -353,9 +378,9 @@
*/
/* Version information for png.h - this should match the version in png.c */
-#define PNG_LIBPNG_VER_STRING "1.2.18"
+#define PNG_LIBPNG_VER_STRING "1.2.24"
#define PNG_HEADER_VERSION_STRING \
- " libpng version 1.2.18 - May 15, 2007 (header)\n"
+ " libpng version 1.2.24 - December 14, 2007\n"
#define PNG_LIBPNG_VER_SONUM 0
#define PNG_LIBPNG_VER_DLLNUM 13
@@ -363,7 +388,7 @@
/* These should match the first 3 components of PNG_LIBPNG_VER_STRING: */
#define PNG_LIBPNG_VER_MAJOR 1
#define PNG_LIBPNG_VER_MINOR 2
-#define PNG_LIBPNG_VER_RELEASE 18
+#define PNG_LIBPNG_VER_RELEASE 24
/* This should match the numeric part of the final component of
* PNG_LIBPNG_VER_STRING, omitting any leading zero: */
@@ -391,7 +416,7 @@
* Versions 0.7 through 1.0.0 were in the range 0 to 100 here (only
* version 1.0.0 was mis-numbered 100 instead of 10000). From
* version 1.0.1 it's xxyyzz, where x=major, y=minor, z=release */
-#define PNG_LIBPNG_VER 10218 /* 1.2.18 */
+#define PNG_LIBPNG_VER 10224 /* 1.2.24 */
#ifndef PNG_VERSION_INFO_ONLY
/* include the compression library's header */
@@ -479,7 +504,7 @@ extern "C" {
* the version above.
*/
#ifdef PNG_USE_GLOBAL_ARRAYS
-PNG_EXPORT_VAR (const char) png_libpng_ver[18];
+PNG_EXPORT_VAR (PNG_CONST char) png_libpng_ver[18];
/* need room for 99.99.99beta99z */
#else
#define png_libpng_ver png_get_header_ver(NULL)
@@ -488,17 +513,14 @@ PNG_EXPORT_VAR (const char) png_libpng_ver[18];
#ifdef PNG_USE_GLOBAL_ARRAYS
/* This was removed in version 1.0.5c */
/* Structures to facilitate easy interlacing. See png.c for more details */
-PNG_EXPORT_VAR (const int FARDATA) png_pass_start[7];
-PNG_EXPORT_VAR (const int FARDATA) png_pass_inc[7];
-PNG_EXPORT_VAR (const int FARDATA) png_pass_ystart[7];
-PNG_EXPORT_VAR (const int FARDATA) png_pass_yinc[7];
-PNG_EXPORT_VAR (const int FARDATA) png_pass_mask[7];
-PNG_EXPORT_VAR (const int FARDATA) png_pass_dsp_mask[7];
-#ifdef PNG_USE_PNGGCCRD
-PNG_EXPORT_VAR (const int FARDATA) png_pass_width[7];
-#endif
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_start[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_inc[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_ystart[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_yinc[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_mask[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_dsp_mask[7];
/* This isn't currently used. If you need it, see png.c for more details.
-PNG_EXPORT_VAR (const int FARDATA) png_pass_height[7];
+PNG_EXPORT_VAR (PNG_CONST int FARDATA) png_pass_height[7];
*/
#endif
@@ -635,9 +657,10 @@ typedef png_time FAR * FAR * png_timepp;
* up private chunks for output even though the library doesn't actually
* know about their semantics.
*/
+#define PNG_CHUNK_NAME_LENGTH 5
typedef struct png_unknown_chunk_t
{
- png_byte name[5];
+ png_byte name[PNG_CHUNK_NAME_LENGTH];
png_byte *data;
png_size_t size;
@@ -1164,10 +1187,12 @@ struct png_struct_def
png_uint_32 row_number; /* current row in interlace pass */
png_bytep prev_row; /* buffer to save previous (unfiltered) row */
png_bytep row_buf; /* buffer to save current (unfiltered) row */
+#ifndef PNG_NO_WRITE_FILTERING
png_bytep sub_row; /* buffer to save "sub" row when filtering */
png_bytep up_row; /* buffer to save "up" row when filtering */
png_bytep avg_row; /* buffer to save "avg" row when filtering */
png_bytep paeth_row; /* buffer to save "Paeth" row when filtering */
+#endif
png_row_info row_info; /* used for transformation routines */
png_uint_32 idat_size; /* current IDAT size for read */
@@ -1269,8 +1294,7 @@ struct png_struct_def
png_size_t current_text_left; /* how much text left to read in input */
png_charp current_text; /* current text chunk buffer */
png_charp current_text_ptr; /* current location in current_text */
-# endif /* PNG_PROGRESSIVE_READ_SUPPORTED && PNG_TEXT_SUPPORTED */
-
+# endif /* PNG_TEXT_SUPPORTED */
#endif /* PNG_PROGRESSIVE_READ_SUPPORTED */
#if defined(__TURBOC__) && !defined(_Windows) && !defined(__FLAT__)
@@ -1352,7 +1376,7 @@ struct png_struct_def
png_byte filter_type;
#endif
-#if defined(PNG_1_0_X) || (defined(PNG_DEBUG) && defined(PNG_USE_PNGGCCRD))
+#if defined(PNG_1_0_X)
/* New member added in libpng-1.0.10, ifdef'ed out in 1.2.0 */
png_uint_32 row_buf_size;
#endif
@@ -1406,7 +1430,7 @@ struct png_struct_def
/* This triggers a compiler error in png.c, if png.c and png.h
* do not agree upon the version number.
*/
-typedef png_structp version_1_2_18;
+typedef png_structp version_1_2_24;
typedef png_struct FAR * FAR * png_structpp;
@@ -2054,6 +2078,7 @@ extern void *png_far_to_near PNGARG((png_structp png_ptr,png_voidp ptr,
int check));
#endif /* USE_FAR_KEYWORD */
+#ifndef PNG_NO_ERROR_TEXT
/* Fatal error in PNG image of libpng - can't continue */
extern PNG_EXPORT(void,png_error) PNGARG((png_structp png_ptr,
png_const_charp error_message));
@@ -2061,14 +2086,22 @@ extern PNG_EXPORT(void,png_error) PNGARG((png_structp png_ptr,
/* The same, but the chunk name is prepended to the error string. */
extern PNG_EXPORT(void,png_chunk_error) PNGARG((png_structp png_ptr,
png_const_charp error_message));
+#else
+/* Fatal error in PNG image of libpng - can't continue */
+extern PNG_EXPORT(void,png_err) PNGARG((png_structp png_ptr));
+#endif
+#ifndef PNG_NO_WARNINGS
/* Non-fatal error in libpng. Can continue, but may have a problem. */
extern PNG_EXPORT(void,png_warning) PNGARG((png_structp png_ptr,
png_const_charp warning_message));
+#ifdef PNG_READ_SUPPORTED
/* Non-fatal error in libpng, chunk name is prepended to message. */
extern PNG_EXPORT(void,png_chunk_warning) PNGARG((png_structp png_ptr,
png_const_charp warning_message));
+#endif /* PNG_READ_SUPPORTED */
+#endif /* PNG_NO_WARNINGS */
/* The png_set_<chunk> functions are for storing values in the png_info_struct.
* Similarly, the png_get_<chunk> calls are used to read values from the
@@ -2490,10 +2523,6 @@ extern PNG_EXPORT(void, png_write_png) PNGARG((png_structp png_ptr,
#define png_debug2(l, m, p1, p2)
#endif
-#if 0
-extern PNG_EXPORT(png_bytep,png_sig_bytes) PNGARG((void));
-#endif
-
extern PNG_EXPORT(png_charp,png_get_copyright) PNGARG((png_structp png_ptr));
extern PNG_EXPORT(png_charp,png_get_header_ver) PNGARG((png_structp png_ptr));
extern PNG_EXPORT(png_charp,png_get_header_version) PNGARG((png_structp png_ptr));
@@ -2817,11 +2846,8 @@ extern PNG_EXPORT(void,png_save_uint_16)
#if !defined(PNG_NO_EXTERN) || defined(PNG_ALWAYS_EXTERN)
/* place to hold the signature string for a PNG file. */
#ifdef PNG_USE_GLOBAL_ARRAYS
- PNG_EXPORT_VAR (const png_byte FARDATA) png_sig[8];
+ PNG_EXPORT_VAR (PNG_CONST png_byte FARDATA) png_sig[8];
#else
-#if 0
-#define png_sig png_sig_bytes(NULL)
-#endif
#endif
#endif /* PNG_NO_EXTERN */
@@ -2829,50 +2855,50 @@ extern PNG_EXPORT(void,png_save_uint_16)
* define the name here, and add an invocation of the macro in png.c and
* wherever it's needed.
*/
-#define PNG_IHDR const png_byte png_IHDR[5] = { 73, 72, 68, 82, '\0'}
-#define PNG_IDAT const png_byte png_IDAT[5] = { 73, 68, 65, 84, '\0'}
-#define PNG_IEND const png_byte png_IEND[5] = { 73, 69, 78, 68, '\0'}
-#define PNG_PLTE const png_byte png_PLTE[5] = { 80, 76, 84, 69, '\0'}
-#define PNG_bKGD const png_byte png_bKGD[5] = { 98, 75, 71, 68, '\0'}
-#define PNG_cHRM const png_byte png_cHRM[5] = { 99, 72, 82, 77, '\0'}
-#define PNG_gAMA const png_byte png_gAMA[5] = {103, 65, 77, 65, '\0'}
-#define PNG_hIST const png_byte png_hIST[5] = {104, 73, 83, 84, '\0'}
-#define PNG_iCCP const png_byte png_iCCP[5] = {105, 67, 67, 80, '\0'}
-#define PNG_iTXt const png_byte png_iTXt[5] = {105, 84, 88, 116, '\0'}
-#define PNG_oFFs const png_byte png_oFFs[5] = {111, 70, 70, 115, '\0'}
-#define PNG_pCAL const png_byte png_pCAL[5] = {112, 67, 65, 76, '\0'}
-#define PNG_sCAL const png_byte png_sCAL[5] = {115, 67, 65, 76, '\0'}
-#define PNG_pHYs const png_byte png_pHYs[5] = {112, 72, 89, 115, '\0'}
-#define PNG_sBIT const png_byte png_sBIT[5] = {115, 66, 73, 84, '\0'}
-#define PNG_sPLT const png_byte png_sPLT[5] = {115, 80, 76, 84, '\0'}
-#define PNG_sRGB const png_byte png_sRGB[5] = {115, 82, 71, 66, '\0'}
-#define PNG_tEXt const png_byte png_tEXt[5] = {116, 69, 88, 116, '\0'}
-#define PNG_tIME const png_byte png_tIME[5] = {116, 73, 77, 69, '\0'}
-#define PNG_tRNS const png_byte png_tRNS[5] = {116, 82, 78, 83, '\0'}
-#define PNG_zTXt const png_byte png_zTXt[5] = {122, 84, 88, 116, '\0'}
+#define PNG_IHDR png_byte png_IHDR[5] = { 73, 72, 68, 82, '\0'}
+#define PNG_IDAT png_byte png_IDAT[5] = { 73, 68, 65, 84, '\0'}
+#define PNG_IEND png_byte png_IEND[5] = { 73, 69, 78, 68, '\0'}
+#define PNG_PLTE png_byte png_PLTE[5] = { 80, 76, 84, 69, '\0'}
+#define PNG_bKGD png_byte png_bKGD[5] = { 98, 75, 71, 68, '\0'}
+#define PNG_cHRM png_byte png_cHRM[5] = { 99, 72, 82, 77, '\0'}
+#define PNG_gAMA png_byte png_gAMA[5] = {103, 65, 77, 65, '\0'}
+#define PNG_hIST png_byte png_hIST[5] = {104, 73, 83, 84, '\0'}
+#define PNG_iCCP png_byte png_iCCP[5] = {105, 67, 67, 80, '\0'}
+#define PNG_iTXt png_byte png_iTXt[5] = {105, 84, 88, 116, '\0'}
+#define PNG_oFFs png_byte png_oFFs[5] = {111, 70, 70, 115, '\0'}
+#define PNG_pCAL png_byte png_pCAL[5] = {112, 67, 65, 76, '\0'}
+#define PNG_sCAL png_byte png_sCAL[5] = {115, 67, 65, 76, '\0'}
+#define PNG_pHYs png_byte png_pHYs[5] = {112, 72, 89, 115, '\0'}
+#define PNG_sBIT png_byte png_sBIT[5] = {115, 66, 73, 84, '\0'}
+#define PNG_sPLT png_byte png_sPLT[5] = {115, 80, 76, 84, '\0'}
+#define PNG_sRGB png_byte png_sRGB[5] = {115, 82, 71, 66, '\0'}
+#define PNG_tEXt png_byte png_tEXt[5] = {116, 69, 88, 116, '\0'}
+#define PNG_tIME png_byte png_tIME[5] = {116, 73, 77, 69, '\0'}
+#define PNG_tRNS png_byte png_tRNS[5] = {116, 82, 78, 83, '\0'}
+#define PNG_zTXt png_byte png_zTXt[5] = {122, 84, 88, 116, '\0'}
#ifdef PNG_USE_GLOBAL_ARRAYS
-PNG_EXPORT_VAR (const png_byte FARDATA) png_IHDR[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_IDAT[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_IEND[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_PLTE[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_bKGD[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_cHRM[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_gAMA[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_hIST[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_iCCP[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_iTXt[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_oFFs[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_pCAL[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_sCAL[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_pHYs[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_sBIT[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_sPLT[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_sRGB[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_tEXt[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_tIME[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_tRNS[5];
-PNG_EXPORT_VAR (const png_byte FARDATA) png_zTXt[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_IHDR[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_IDAT[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_IEND[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_PLTE[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_bKGD[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_cHRM[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_gAMA[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_hIST[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_iCCP[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_iTXt[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_oFFs[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_pCAL[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_sCAL[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_pHYs[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_sBIT[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_sPLT[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_sRGB[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_tEXt[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_tIME[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_tRNS[5];
+PNG_EXPORT_VAR (png_byte FARDATA) png_zTXt[5];
#endif /* PNG_USE_GLOBAL_ARRAYS */
#if defined(PNG_1_0_X) || defined (PNG_1_2_X)
diff --git a/Build/source/libs/libpng/pngconf.h b/Build/source/libs/libpng/pngconf.h
index a5047325f77..c40507446fe 100644
--- a/Build/source/libs/libpng/pngconf.h
+++ b/Build/source/libs/libpng/pngconf.h
@@ -1,7 +1,7 @@
/* pngconf.h - machine configurable file for libpng
*
- * libpng version 1.2.18 - May 15, 2007
+ * libpng version 1.2.24 - December 14, 2007
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -75,6 +75,14 @@
/* End of material added to libpng-1.2.8 */
+/* Added at libpng-1.2.19, removed at libpng-1.2.20 because it caused trouble
+ Restored at libpng-1.2.21 */
+#if !defined(PNG_NO_WARN_UNINITIALIZED_ROW) && \
+ !defined(PNG_WARN_UNINITIALIZED_ROW)
+# define PNG_WARN_UNINITIALIZED_ROW 1
+#endif
+/* End of material added at libpng-1.2.19/1.2.21 */
+
/* This is the size of the compression buffer, and thus the size of
* an IDAT chunk. Make this whatever size you feel is best for your
* machine. One of these will be allocated per png_struct. When this
@@ -276,6 +284,7 @@
# define PNGARG(arglist) arglist
#endif /* _NO_PROTO */
+
#endif /* OF */
#endif /* PNGARG */
@@ -314,7 +323,7 @@
/* If you encounter a compiler error here, see the explanation
* near the end of INSTALL.
*/
- __png.h__ already includes setjmp.h;
+ __pngconf.h__ already includes setjmp.h;
__dont__ include it again.;
# endif
# endif /* __linux__ */
@@ -324,7 +333,9 @@
# ifdef __linux__
# ifdef PNG_SAVE_BSD_SOURCE
-# define _BSD_SOURCE
+# ifndef _BSD_SOURCE
+# define _BSD_SOURCE
+# endif
# undef PNG_SAVE_BSD_SOURCE
# endif
# endif /* __linux__ */
@@ -594,16 +605,16 @@
#endif /* PNG_READ_TRANSFORMS_SUPPORTED */
#if !defined(PNG_NO_PROGRESSIVE_READ) && \
- !defined(PNG_PROGRESSIVE_READ_NOT_SUPPORTED) /* if you don't do progressive */
-# define PNG_PROGRESSIVE_READ_SUPPORTED /* reading. This is not talking */
-#endif /* about interlacing capability! You'll */
- /* still have interlacing unless you change the following line: */
+ !defined(PNG_PROGRESSIVE_READ_SUPPORTED) /* if you don't do progressive */
+# define PNG_PROGRESSIVE_READ_SUPPORTED /* reading. This is not talking */
+#endif /* about interlacing capability! You'll */
+ /* still have interlacing unless you change the following line: */
-#define PNG_READ_INTERLACING_SUPPORTED /* required for PNG-compliant decoders */
+#define PNG_READ_INTERLACING_SUPPORTED /* required in PNG-compliant decoders */
#ifndef PNG_NO_READ_COMPOSITE_NODIV
# ifndef PNG_NO_READ_COMPOSITED_NODIV /* libpng-1.0.x misspelling */
-# define PNG_READ_COMPOSITE_NODIV_SUPPORTED /* well tested on Intel, SGI */
+# define PNG_READ_COMPOSITE_NODIV_SUPPORTED /* well tested on Intel, SGI */
# endif
#endif
@@ -721,37 +732,46 @@
#endif
/* PNG_ASSEMBLER_CODE was enabled by default in version 1.2.0
- * even when PNG_USE_PNGVCRD or PNG_USE_PNGGCCRD is not defined.
- *
- * PNG_NO_ASSEMBLER_CODE disables use of all assembler code and optimized C,
- * and removes or includes several functions in the API.
- *
- * PNG_NO_MMX_CODE disables the use of MMX code without changing the API.
- * When MMX code is off, then optimized C replacement functions are used.
+ * and removed from version 1.2.20. The following will be removed
+ * from libpng-1.4.0
*/
+
+#if defined(PNG_READ_SUPPORTED) && !defined(PNG_NO_OPTIMIZED_CODE)
+# ifndef PNG_OPTIMIZED_CODE_SUPPORTED
+# define PNG_OPTIMIZED_CODE_SUPPORTED
+# endif
+#endif
+
#if defined(PNG_READ_SUPPORTED) && !defined(PNG_NO_ASSEMBLER_CODE)
# ifndef PNG_ASSEMBLER_CODE_SUPPORTED
# define PNG_ASSEMBLER_CODE_SUPPORTED
# endif
-# if defined(XP_MACOSX) && !defined(PNG_NO_MMX_CODE)
- /* work around Intel-Mac compiler bug */
-# define PNG_NO_MMX_CODE
+
+# if defined(__GNUC__) && defined(__x86_64__) && (__GNUC__ < 4)
+ /* work around 64-bit gcc compiler bugs in gcc-3.x */
+# if !defined(PNG_MMX_CODE_SUPPORTED) && !defined(PNG_NO_MMX_CODE)
+# define PNG_NO_MMX_CODE
+# endif
# endif
-# if !defined(PNG_MMX_CODE_SUPPORTED) && !defined(PNG_NO_MMX_CODE) && \
- defined(__MMX__)
-# define PNG_MMX_CODE_SUPPORTED
+
+# if defined(__APPLE__)
+# if !defined(PNG_MMX_CODE_SUPPORTED) && !defined(PNG_NO_MMX_CODE)
+# define PNG_NO_MMX_CODE
+# endif
# endif
-# if !defined(PNG_USE_PNGGCCRD) && !defined(PNG_NO_MMX_CODE) && \
- !defined(PNG_USE_PNGVCRD) && defined(__MMX__)
-# define PNG_USE_PNGGCCRD
+
+# if (defined(__MWERKS__) && ((__MWERKS__ < 0x0900) || macintosh))
+# if !defined(PNG_MMX_CODE_SUPPORTED) && !defined(PNG_NO_MMX_CODE)
+# define PNG_NO_MMX_CODE
+# endif
# endif
-#endif
-/* If you are sure that you don't need thread safety and you are compiling
- with PNG_USE_PNGCCRD for an MMX application, you can define this for
- faster execution. See pnggccrd.c.
-#define PNG_THREAD_UNSAFE_OK
-*/
+# if !defined(PNG_MMX_CODE_SUPPORTED) && !defined(PNG_NO_MMX_CODE)
+# define PNG_MMX_CODE_SUPPORTED
+# endif
+
+#endif
+/* end of obsolete code to be removed from libpng-1.4.0 */
#if !defined(PNG_1_0_X)
#if !defined(PNG_NO_USER_MEM) && !defined(PNG_USER_MEM_SUPPORTED)
@@ -1273,7 +1293,8 @@ typedef z_stream FAR * png_zstreamp;
* but might be required for some pre-1.0.5c applications.
*/
#if !defined(PNG_USE_LOCAL_ARRAYS) && !defined(PNG_USE_GLOBAL_ARRAYS)
-# if defined(PNG_NO_GLOBAL_ARRAYS) || (defined(__GNUC__) && defined(PNG_DLL))
+# if defined(PNG_NO_GLOBAL_ARRAYS) || \
+ (defined(__GNUC__) && defined(PNG_DLL)) || defined(_MSC_VER)
# define PNG_USE_LOCAL_ARRAYS
# else
# define PNG_USE_GLOBAL_ARRAYS
@@ -1410,8 +1431,7 @@ typedef z_stream FAR * png_zstreamp;
# define NOCHECK 0
# define CVT_PTR(ptr) (png_far_to_near(png_ptr,ptr,CHECK))
# define CVT_PTR_NOCHECK(ptr) (png_far_to_near(png_ptr,ptr,NOCHECK))
-# define png_strcpy _fstrcpy
-# define png_strncpy _fstrncpy /* Added to v 1.2.6 */
+# define png_snprintf _fsnprintf /* Added to v 1.2.19 */
# define png_strlen _fstrlen
# define png_memcmp _fmemcmp /* SJT: added */
# define png_memcpy _fmemcpy
@@ -1419,8 +1439,27 @@ typedef z_stream FAR * png_zstreamp;
#else /* use the usual functions */
# define CVT_PTR(ptr) (ptr)
# define CVT_PTR_NOCHECK(ptr) (ptr)
-# define png_strcpy strcpy
-# define png_strncpy strncpy /* Added to v 1.2.6 */
+# ifndef PNG_NO_SNPRINTF
+# ifdef _MSC_VER
+# define png_snprintf _snprintf /* Added to v 1.2.19 */
+# define png_snprintf2 _snprintf
+# define png_snprintf6 _snprintf
+# else
+# define png_snprintf snprintf /* Added to v 1.2.19 */
+# define png_snprintf2 snprintf
+# define png_snprintf6 snprintf
+# endif
+# else
+ /* You don't have or don't want to use snprintf(). Caution: Using
+ * sprintf instead of snprintf exposes your application to accidental
+ * or malevolent buffer overflows. If you don't have snprintf()
+ * as a general rule you should provide one (you can get one from
+ * Portable OpenSSH). */
+# define png_snprintf(s1,n,fmt,x1) sprintf(s1,fmt,x1)
+# define png_snprintf2(s1,n,fmt,x1,x2) sprintf(s1,fmt,x1,x2)
+# define png_snprintf6(s1,n,fmt,x1,x2,x3,x4,x5,x6) \
+ sprintf(s1,fmt,x1,x2,x3,x4,x5,x6)
+# endif
# define png_strlen strlen
# define png_memcmp memcmp /* SJT: added */
# define png_memcpy memcpy
@@ -1436,47 +1475,6 @@ typedef z_stream FAR * png_zstreamp;
# define PNG_ZBUF_SIZE 65536L
#endif
-#ifdef PNG_READ_SUPPORTED
-/* Prior to libpng-1.0.9, this block was in pngasmrd.h */
-#if defined(PNG_INTERNAL)
-
-/* These are the default thresholds before the MMX code kicks in; if either
- * rowbytes or bitdepth is below the threshold, plain C code is used. These
- * can be overridden at runtime via the png_set_mmx_thresholds() call in
- * libpng 1.2.0 and later. The values below were chosen by Intel.
- */
-
-#ifndef PNG_MMX_ROWBYTES_THRESHOLD_DEFAULT
-# define PNG_MMX_ROWBYTES_THRESHOLD_DEFAULT 128 /* >= */
-#endif
-#ifndef PNG_MMX_BITDEPTH_THRESHOLD_DEFAULT
-# define PNG_MMX_BITDEPTH_THRESHOLD_DEFAULT 9 /* >= */
-#endif
-
-/* Set this in the makefile for VC++ on Pentium, not here. */
-/* Platform must be Pentium. Makefile must assemble and load pngvcrd.c .
- * MMX will be detected at run time and used if present.
- */
-#ifdef PNG_USE_PNGVCRD
-# define PNG_HAVE_MMX_COMBINE_ROW
-# define PNG_HAVE_MMX_READ_INTERLACE
-# define PNG_HAVE_MMX_READ_FILTER_ROW
-#endif
-
-/* Set this in the makefile for gcc/as on Pentium, not here. */
-/* Platform must be Pentium. Makefile must assemble and load pnggccrd.c .
- * MMX will be detected at run time and used if present.
- */
-#ifdef PNG_USE_PNGGCCRD
-# define PNG_HAVE_MMX_COMBINE_ROW
-# define PNG_HAVE_MMX_READ_INTERLACE
-# define PNG_HAVE_MMX_READ_FILTER_ROW
-#endif
-/* - see pnggccrd.c for info about what is currently enabled */
-
-#endif /* PNG_INTERNAL */
-#endif /* PNG_READ_SUPPORTED */
-
/* Added at libpng-1.2.8 */
#endif /* PNG_VERSION_INFO_ONLY */
diff --git a/Build/source/libs/libpng/pngerror.c b/Build/source/libs/libpng/pngerror.c
index f50f6534427..b364fc00af4 100644
--- a/Build/source/libs/libpng/pngerror.c
+++ b/Build/source/libs/libpng/pngerror.c
@@ -1,9 +1,9 @@
/* pngerror.c - stub functions for i/o and memory allocation
*
- * Last changed in libpng 1.2.13 November 13, 2006
+ * Last changed in libpng 1.2.22 [October 13, 2007]
* For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2006 Glenn Randers-Pehrson
+ * Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
* (Version 0.88 Copyright (c) 1995, 1996 Guy Eric Schalnat, Group 42, Inc.)
*
@@ -20,15 +20,18 @@
static void /* PRIVATE */
png_default_error PNGARG((png_structp png_ptr,
png_const_charp error_message));
+#ifndef PNG_NO_WARNINGS
static void /* PRIVATE */
png_default_warning PNGARG((png_structp png_ptr,
png_const_charp warning_message));
+#endif /* PNG_NO_WARNINGS */
/* This function is called whenever there is a fatal error. This function
* should not be changed. If there is a need to handle errors differently,
* you should supply a replacement error function and use png_set_error_fn()
* to replace the error function at run-time.
*/
+#ifndef PNG_NO_ERROR_TEXT
void PNGAPI
png_error(png_structp png_ptr, png_const_charp error_message)
{
@@ -75,7 +78,20 @@ png_error(png_structp png_ptr, png_const_charp error_message)
use the default handler, which will not return. */
png_default_error(png_ptr, error_message);
}
+#else
+void PNGAPI
+png_err(png_structp png_ptr)
+{
+ if (png_ptr != NULL && png_ptr->error_fn != NULL)
+ (*(png_ptr->error_fn))(png_ptr, '\0');
+
+ /* If the custom handler doesn't exist, or if it returns,
+ use the default handler, which will not return. */
+ png_default_error(png_ptr, '\0');
+}
+#endif /* PNG_NO_ERROR_TEXT */
+#ifndef PNG_NO_WARNINGS
/* This function is called whenever there is a non-fatal error. This function
* should not be changed. If there is a need to handle warnings differently,
* you should supply a replacement warning function and use
@@ -105,6 +121,8 @@ png_warning(png_structp png_ptr, png_const_charp warning_message)
else
png_default_warning(png_ptr, warning_message+offset);
}
+#endif /* PNG_NO_WARNINGS */
+
/* These utilities are used internally to build an error message that relates
* to the current chunk. The chunk name comes from png_ptr->chunk_name,
@@ -113,11 +131,14 @@ png_warning(png_structp png_ptr, png_const_charp warning_message)
* if the character is invalid.
*/
#define isnonalpha(c) ((c) < 65 || (c) > 122 || ((c) > 90 && (c) < 97))
-const static PNG_CONST char png_digit[16] = {
+static PNG_CONST char png_digit[16] = {
'0', '1', '2', '3', '4', '5', '6', '7', '8', '9',
'A', 'B', 'C', 'D', 'E', 'F'
};
+#define PNG_MAX_ERROR_TEXT 64
+
+#if !defined(PNG_NO_WARNINGS) || !defined(PNG_NO_ERROR_TEXT)
static void /* PRIVATE */
png_format_buffer(png_structp png_ptr, png_charp buffer, png_const_charp
error_message)
@@ -141,20 +162,21 @@ png_format_buffer(png_structp png_ptr, png_charp buffer, png_const_charp
}
if (error_message == NULL)
- buffer[iout] = 0;
+ buffer[iout] = '\0';
else
{
buffer[iout++] = ':';
buffer[iout++] = ' ';
- png_strncpy(buffer+iout, error_message, 63);
- buffer[iout+63] = 0;
+ png_memcpy(buffer+iout, error_message, PNG_MAX_ERROR_TEXT);
+ buffer[iout+PNG_MAX_ERROR_TEXT-1] = '\0';
}
}
+#ifdef PNG_READ_SUPPORTED
void PNGAPI
png_chunk_error(png_structp png_ptr, png_const_charp error_message)
{
- char msg[18+64];
+ char msg[18+PNG_MAX_ERROR_TEXT];
if (png_ptr == NULL)
png_error(png_ptr, error_message);
else
@@ -163,11 +185,14 @@ png_chunk_error(png_structp png_ptr, png_const_charp error_message)
png_error(png_ptr, msg);
}
}
+#endif /* PNG_READ_SUPPORTED */
+#endif /* !defined(PNG_NO_WARNINGS) || !defined(PNG_NO_ERROR_TEXT) */
+#ifndef PNG_NO_WARNINGS
void PNGAPI
png_chunk_warning(png_structp png_ptr, png_const_charp warning_message)
{
- char msg[18+64];
+ char msg[18+PNG_MAX_ERROR_TEXT];
if (png_ptr == NULL)
png_warning(png_ptr, warning_message);
else
@@ -176,6 +201,8 @@ png_chunk_warning(png_structp png_ptr, png_const_charp warning_message)
png_warning(png_ptr, msg);
}
}
+#endif /* PNG_NO_WARNINGS */
+
/* This is the default error handling function. Note that replacements for
* this function MUST NOT RETURN, or the program will likely crash. This
@@ -217,7 +244,7 @@ png_default_error(png_structp png_ptr, png_const_charp error_message)
# ifdef USE_FAR_KEYWORD
{
jmp_buf jmpbuf;
- png_memcpy(jmpbuf,png_ptr->jmpbuf,png_sizeof(jmp_buf));
+ png_memcpy(jmpbuf, png_ptr->jmpbuf, png_sizeof(jmp_buf));
longjmp(jmpbuf, 1);
}
# else
@@ -228,12 +255,11 @@ png_default_error(png_structp png_ptr, png_const_charp error_message)
PNG_ABORT();
#endif
#ifdef PNG_NO_CONSOLE_IO
- /* make compiler happy */ ;
- if (&error_message != NULL)
- return;
+ error_message = error_message; /* make compiler happy */
#endif
}
+#ifndef PNG_NO_WARNINGS
/* This function is called when there is a warning, but the library thinks
* it can continue anyway. Replacement functions don't have to do anything
* here if you don't want them to. In the default configuration, png_ptr is
@@ -267,14 +293,11 @@ png_default_warning(png_structp png_ptr, png_const_charp warning_message)
# endif
fprintf(stderr, "libpng warning: %s\n", warning_message);
#else
- /* make compiler happy */ ;
- if (warning_message)
- return;
+ warning_message = warning_message; /* make compiler happy */
#endif
- /* make compiler happy */ ;
- if (png_ptr)
- return;
+ png_ptr = png_ptr; /* make compiler happy */
}
+#endif /* PNG_NO_WARNINGS */
/* This function is called when the application wants to use another method
* of handling errors and warnings. Note that the error function MUST NOT
diff --git a/Build/source/libs/libpng/pnggccrd.c b/Build/source/libs/libpng/pnggccrd.c
index fab523c0bdc..a7248d6ca64 100644
--- a/Build/source/libs/libpng/pnggccrd.c
+++ b/Build/source/libs/libpng/pnggccrd.c
@@ -1,5374 +1,51 @@
+/* pnggccrd.c was removed from libpng-1.2.20. */
-/* pnggccrd.c - mixed C/assembler version of utilities to read a PNG file
- *
- * For Intel x86 CPU (Pentium-MMX or later) and GNU C compiler.
- *
- * See http://www.intel.com/drg/pentiumII/appnotes/916/916.htm
- * and http://www.intel.com/drg/pentiumII/appnotes/923/923.htm
- * for Intel's performance analysis of the MMX vs. non-MMX code.
- *
- * Last changed in libpng 1.2.15 January 5, 2007
- * For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2007 Glenn Randers-Pehrson
- * Copyright (c) 1998, Intel Corporation
- *
- * Based on MSVC code contributed by Nirav Chhatrapati, Intel Corp., 1998.
- * Interface to libpng contributed by Gilles Vollant, 1999.
- * GNU C port by Greg Roelofs, 1999-2001.
- *
- * Lines 2350-4300 converted in place with intel2gas 1.3.1:
- *
- * intel2gas -mdI pnggccrd.c.partially-msvc -o pnggccrd.c
- *
- * and then cleaned up by hand. See http://hermes.terminal.at/intel2gas/ .
- *
- * NOTE: A sufficiently recent version of GNU as (or as.exe under DOS/Windows)
- * is required to assemble the newer MMX instructions such as movq.
- * For djgpp, see
- *
- * ftp://ftp.simtel.net/pub/simtelnet/gnu/djgpp/v2gnu/bnu281b.zip
- *
- * (or a later version in the same directory). For Linux, check your
- * distribution's web site(s) or try these links:
- *
- * http://rufus.w3.org/linux/RPM/binutils.html
- * http://www.debian.org/Packages/stable/devel/binutils.html
- * ftp://ftp.slackware.com/pub/linux/slackware/slackware/slakware/d1/
- * binutils.tgz
- *
- * For other platforms, see the main GNU site:
- *
- * ftp://ftp.gnu.org/pub/gnu/binutils/
- *
- * Version 2.5.2l.15 is definitely too old...
- */
+/* This code snippet is for use by configure's compilation test. */
-/*
- * TEMPORARY PORTING NOTES AND CHANGELOG (mostly by Greg Roelofs)
- * =====================================
- *
- * 19991006:
- * - fixed sign error in post-MMX cleanup code (16- & 32-bit cases)
- *
- * 19991007:
- * - additional optimizations (possible or definite):
- * x [DONE] write MMX code for 64-bit case (pixel_bytes == 8) [not tested]
- * - write MMX code for 48-bit case (pixel_bytes == 6)
- * - figure out what's up with 24-bit case (pixel_bytes == 3):
- * why subtract 8 from width_mmx in the pass 4/5 case?
- * (only width_mmx case) (near line 1606)
- * x [DONE] replace pixel_bytes within each block with the true
- * constant value (or are compilers smart enough to do that?)
- * - rewrite all MMX interlacing code so it's aligned with
- * the *beginning* of the row buffer, not the end. This
- * would not only allow one to eliminate half of the memory
- * writes for odd passes (that is, pass == odd), it may also
- * eliminate some unaligned-data-access exceptions (assuming
- * there's a penalty for not aligning 64-bit accesses on
- * 64-bit boundaries). The only catch is that the "leftover"
- * pixel(s) at the end of the row would have to be saved,
- * but there are enough unused MMX registers in every case,
- * so this is not a problem. A further benefit is that the
- * post-MMX cleanup code (C code) in at least some of the
- * cases could be done within the assembler block.
- * x [DONE] the "v3 v2 v1 v0 v7 v6 v5 v4" comments are confusing,
- * inconsistent, and don't match the MMX Programmer's Reference
- * Manual conventions anyway. They should be changed to
- * "b7 b6 b5 b4 b3 b2 b1 b0," where b0 indicates the byte that
- * was lowest in memory (e.g., corresponding to a left pixel)
- * and b7 is the byte that was highest (e.g., a right pixel).
- *
- * 19991016:
- * - Brennan's Guide notwithstanding, gcc under Linux does *not*
- * want globals prefixed by underscores when referencing them--
- * i.e., if the variable is const4, then refer to it as const4,
- * not _const4. This seems to be a djgpp-specific requirement.
- * Also, such variables apparently *must* be declared outside
- * of functions; neither static nor automatic variables work if
- * defined within the scope of a single function, but both
- * static and truly global (multi-module) variables work fine.
- *
- * 19991023:
- * - fixed png_combine_row() non-MMX replication bug (odd passes only?)
- * - switched from string-concatenation-with-macros to cleaner method of
- * renaming global variables for djgpp--i.e., always use prefixes in
- * inlined assembler code (== strings) and conditionally rename the
- * variables, not the other way around. Hence _const4, _mask8_0, etc.
- *
- * 19991024:
- * - fixed mmxsupport()/png_do_read_interlace() first-row bug
- * This one was severely weird: even though mmxsupport() doesn't touch
- * ebx (where "row" pointer was stored), it nevertheless managed to zero
- * the register (even in static/non-fPIC code--see below), which in turn
- * caused png_do_read_interlace() to return prematurely on the first row of
- * interlaced images (i.e., without expanding the interlaced pixels).
- * Inspection of the generated assembly code didn't turn up any clues,
- * although it did point at a minor optimization (i.e., get rid of
- * mmx_supported_local variable and just use eax). Possibly the CPUID
- * instruction is more destructive than it looks? (Not yet checked.)
- * - "info gcc" was next to useless, so compared fPIC and non-fPIC assembly
- * listings... Apparently register spillage has to do with ebx, since
- * it's used to index the global offset table. Commenting it out of the
- * input-reg lists in png_combine_row() eliminated compiler barfage, so
- * ifdef'd with __PIC__ macro: if defined, use a global for unmask
- *
- * 19991107:
- * - verified CPUID clobberage: 12-char string constant ("GenuineIntel",
- * "AuthenticAMD", etc.) placed in ebx:ecx:edx. Still need to polish.
- *
- * 19991120:
- * - made "diff" variable (now "_dif") global to simplify conversion of
- * filtering routines (running out of regs, sigh). "diff" is still used
- * in interlacing routines, however.
- * - fixed up both versions of mmxsupport() (ORIG_THAT_USED_TO_CLOBBER_EBX
- * macro determines which is used); original not yet tested.
- *
- * 20000213:
- * - when compiling with gcc, be sure to use -fomit-frame-pointer
- *
- * 20000319:
- * - fixed a register-name typo in png_do_read_interlace(), default (MMX) case,
- * pass == 4 or 5, that caused visible corruption of interlaced images
- *
- * 20000623:
- * - Various problems were reported with gcc 2.95.2 in the Cygwin environment,
- * many of the form "forbidden register 0 (ax) was spilled for class AREG."
- * This is explained at http://gcc.gnu.org/fom_serv/cache/23.html, and
- * Chuck Wilson supplied a patch involving dummy output registers. See
- * http://sourceforge.net/bugs/?func=detailbug&bug_id=108741&group_id=5624
- * for the original (anonymous) SourceForge bug report.
- *
- * 20000706:
- * - Chuck Wilson passed along these remaining gcc 2.95.2 errors:
- * pnggccrd.c: In function `png_combine_row':
- * pnggccrd.c:525: more than 10 operands in `asm'
- * pnggccrd.c:669: more than 10 operands in `asm'
- * pnggccrd.c:828: more than 10 operands in `asm'
- * pnggccrd.c:994: more than 10 operands in `asm'
- * pnggccrd.c:1177: more than 10 operands in `asm'
- * They are all the same problem and can be worked around by using the
- * global _unmask variable unconditionally, not just in the -fPIC case.
- * Reportedly earlier versions of gcc also have the problem with more than
- * 10 operands; they just don't report it. Much strangeness ensues, etc.
- *
- * 20000729:
- * - enabled png_read_filter_row_mmx_up() (shortest remaining unconverted
- * MMX routine); began converting png_read_filter_row_mmx_sub()
- * - to finish remaining sections:
- * - clean up indentation and comments
- * - preload local variables
- * - add output and input regs (order of former determines numerical
- * mapping of latter)
- * - avoid all usage of ebx (including bx, bh, bl) register [20000823]
- * - remove "$" from addressing of Shift and Mask variables [20000823]
- *
- * 20000731:
- * - global union vars causing segfaults in png_read_filter_row_mmx_sub()?
- *
- * 20000822:
- * - ARGH, stupid png_read_filter_row_mmx_sub() segfault only happens with
- * shared-library (-fPIC) version! Code works just fine as part of static
- * library. Damn damn damn damn damn, should have tested that sooner.
- * ebx is getting clobbered again (explicitly this time); need to save it
- * on stack or rewrite asm code to avoid using it altogether. Blargh!
- *
- * 20000823:
- * - first section was trickiest; all remaining sections have ebx -> edx now.
- * (-fPIC works again.) Also added missing underscores to various Shift*
- * and *Mask* globals and got rid of leading "$" signs.
- *
- * 20000826:
- * - added visual separators to help navigate microscopic printed copies
- * (http://pobox.com/~newt/code/gpr-latest.zip, mode 10); started working
- * on png_read_filter_row_mmx_avg()
- *
- * 20000828:
- * - finished png_read_filter_row_mmx_avg(): only Paeth left! (930 lines...)
- * What the hell, did png_read_filter_row_mmx_paeth(), too. Comments not
- * cleaned up/shortened in either routine, but functionality is complete
- * and seems to be working fine.
- *
- * 20000829:
- * - ahhh, figured out last(?) bit of gcc/gas asm-fu: if register is listed
- * as an input reg (with dummy output variables, etc.), then it *cannot*
- * also appear in the clobber list or gcc 2.95.2 will barf. The solution
- * is simple enough...
- *
- * 20000914:
- * - bug in png_read_filter_row_mmx_avg(): 16-bit grayscale not handled
- * correctly (but 48-bit RGB just fine)
- *
- * 20000916:
- * - fixed bug in png_read_filter_row_mmx_avg(), bpp == 2 case; three errors:
- * - "_ShiftBpp.use = 24;" should have been "_ShiftBpp.use = 16;"
- * - "_ShiftRem.use = 40;" should have been "_ShiftRem.use = 48;"
- * - "psllq _ShiftRem, %%mm2" should have been "psrlq _ShiftRem, %%mm2"
- *
- * 20010101:
- * - added new png_init_mmx_flags() function (here only because it needs to
- * call mmxsupport(), which should probably become global png_mmxsupport());
- * modified other MMX routines to run conditionally (png_ptr->asm_flags)
- *
- * 20010103:
- * - renamed mmxsupport() to png_mmx_support(), with auto-set of mmx_supported,
- * and made it public; moved png_init_mmx_flags() to png.c as internal func
- *
- * 20010104:
- * - removed dependency on png_read_filter_row_c() (C code already duplicated
- * within MMX version of png_read_filter_row()) so no longer necessary to
- * compile it into pngrutil.o
- *
- * 20010310:
- * - fixed buffer-overrun bug in png_combine_row() C code (non-MMX)
- *
- * 20020304:
- * - eliminated incorrect use of width_mmx in pixel_bytes == 8 case
- *
- * 20040724:
- * - more tinkering with clobber list at lines 4529 and 5033, to get
- * it to compile on gcc-3.4.
- *
- * STILL TO DO:
- * - test png_do_read_interlace() 64-bit case (pixel_bytes == 8)
- * - write MMX code for 48-bit case (pixel_bytes == 6)
- * - figure out what's up with 24-bit case (pixel_bytes == 3):
- * why subtract 8 from width_mmx in the pass 4/5 case?
- * (only width_mmx case) (near line 1606)
- * - rewrite all MMX interlacing code so it's aligned with beginning
- * of the row buffer, not the end (see 19991007 for details)
- * x pick one version of mmxsupport() and get rid of the other
- * - add error messages to any remaining bogus default cases
- * - enable pixel_depth == 8 cases in png_read_filter_row()? (test speed)
- * x add support for runtime enable/disable/query of various MMX routines
- */
+#if defined(PNG_ASSEMBLER_CODE_SUPPORTED) && \
+ defined(PNG_MMX_CODE_SUPPORTED)
+int PNGAPI png_dummy_mmx_support(void);
-#define PNG_INTERNAL
-#include "png.h"
+static int _mmx_supported = 2; // 0: no MMX; 1: MMX supported; 2: not tested
-#if defined(PNG_ASSEMBLER_CODE_SUPPORTED) && defined(PNG_USE_PNGGCCRD)
-
-int PNGAPI png_mmx_support(void);
-
-#ifdef PNG_USE_LOCAL_ARRAYS
-const static int FARDATA png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0};
-const static int FARDATA png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
-const static int FARDATA png_pass_width[7] = {8, 4, 4, 2, 2, 1, 1};
-#endif
-
-#if defined(PNG_MMX_CODE_SUPPORTED)
-/* djgpp, Win32, Cygwin, and OS2 add their own underscores to global variables,
- * so define them without: */
-#if defined(__DJGPP__) || defined(WIN32) || defined(__CYGWIN__) || \
- defined(__OS2__)
-# define _mmx_supported mmx_supported
-# define _const4 const4
-# define _const6 const6
-# define _mask8_0 mask8_0
-# define _mask16_1 mask16_1
-# define _mask16_0 mask16_0
-# define _mask24_2 mask24_2
-# define _mask24_1 mask24_1
-# define _mask24_0 mask24_0
-# define _mask32_3 mask32_3
-# define _mask32_2 mask32_2
-# define _mask32_1 mask32_1
-# define _mask32_0 mask32_0
-# define _mask48_5 mask48_5
-# define _mask48_4 mask48_4
-# define _mask48_3 mask48_3
-# define _mask48_2 mask48_2
-# define _mask48_1 mask48_1
-# define _mask48_0 mask48_0
-# define _LBCarryMask LBCarryMask
-# define _HBClearMask HBClearMask
-# define _ActiveMask ActiveMask
-# define _ActiveMask2 ActiveMask2
-# define _ActiveMaskEnd ActiveMaskEnd
-# define _ShiftBpp ShiftBpp
-# define _ShiftRem ShiftRem
-#ifdef PNG_THREAD_UNSAFE_OK
-# define _unmask unmask
-# define _FullLength FullLength
-# define _MMXLength MMXLength
-# define _dif dif
-# define _patemp patemp
-# define _pbtemp pbtemp
-# define _pctemp pctemp
-#endif
-#endif
-
-
-/* These constants are used in the inlined MMX assembly code.
- Ignore gcc's "At top level: defined but not used" warnings. */
-
-/* GRR 20000706: originally _unmask was needed only when compiling with -fPIC,
- * since that case uses the %ebx register for indexing the Global Offset Table
- * and there were no other registers available. But gcc 2.95 and later emit
- * "more than 10 operands in `asm'" errors when %ebx is used to preload unmask
- * in the non-PIC case, so we'll just use the global unconditionally now.
- */
-#ifdef PNG_THREAD_UNSAFE_OK
-static int _unmask;
-#endif
-
-const static unsigned long long _mask8_0 = 0x0102040810204080LL;
-
-const static unsigned long long _mask16_1 = 0x0101020204040808LL;
-const static unsigned long long _mask16_0 = 0x1010202040408080LL;
-
-const static unsigned long long _mask24_2 = 0x0101010202020404LL;
-const static unsigned long long _mask24_1 = 0x0408080810101020LL;
-const static unsigned long long _mask24_0 = 0x2020404040808080LL;
-
-const static unsigned long long _mask32_3 = 0x0101010102020202LL;
-const static unsigned long long _mask32_2 = 0x0404040408080808LL;
-const static unsigned long long _mask32_1 = 0x1010101020202020LL;
-const static unsigned long long _mask32_0 = 0x4040404080808080LL;
-
-const static unsigned long long _mask48_5 = 0x0101010101010202LL;
-const static unsigned long long _mask48_4 = 0x0202020204040404LL;
-const static unsigned long long _mask48_3 = 0x0404080808080808LL;
-const static unsigned long long _mask48_2 = 0x1010101010102020LL;
-const static unsigned long long _mask48_1 = 0x2020202040404040LL;
-const static unsigned long long _mask48_0 = 0x4040808080808080LL;
-
-const static unsigned long long _const4 = 0x0000000000FFFFFFLL;
-//const static unsigned long long _const5 = 0x000000FFFFFF0000LL; // NOT USED
-const static unsigned long long _const6 = 0x00000000000000FFLL;
-
-// These are used in the row-filter routines and should/would be local
-// variables if not for gcc addressing limitations.
-// WARNING: Their presence probably defeats the thread safety of libpng.
-
-#ifdef PNG_THREAD_UNSAFE_OK
-static png_uint_32 _FullLength;
-static png_uint_32 _MMXLength;
-static int _dif;
-static int _patemp; // temp variables for Paeth routine
-static int _pbtemp;
-static int _pctemp;
-#endif
-
-void /* PRIVATE */
-png_squelch_warnings(void)
-{
-#ifdef PNG_THREAD_UNSAFE_OK
- _dif = _dif;
- _patemp = _patemp;
- _pbtemp = _pbtemp;
- _pctemp = _pctemp;
- _MMXLength = _MMXLength;
-#endif
- _const4 = _const4;
- _const6 = _const6;
- _mask8_0 = _mask8_0;
- _mask16_1 = _mask16_1;
- _mask16_0 = _mask16_0;
- _mask24_2 = _mask24_2;
- _mask24_1 = _mask24_1;
- _mask24_0 = _mask24_0;
- _mask32_3 = _mask32_3;
- _mask32_2 = _mask32_2;
- _mask32_1 = _mask32_1;
- _mask32_0 = _mask32_0;
- _mask48_5 = _mask48_5;
- _mask48_4 = _mask48_4;
- _mask48_3 = _mask48_3;
- _mask48_2 = _mask48_2;
- _mask48_1 = _mask48_1;
- _mask48_0 = _mask48_0;
-}
-#endif /* PNG_MMX_CODE_SUPPORTED */
-
-
-static int _mmx_supported = 2;
-
-/*===========================================================================*/
-/* */
-/* P N G _ C O M B I N E _ R O W */
-/* */
-/*===========================================================================*/
-
-#if defined(PNG_HAVE_MMX_COMBINE_ROW)
-
-#define BPP2 2
-#define BPP3 3 /* bytes per pixel (a.k.a. pixel_bytes) */
-#define BPP4 4
-#define BPP6 6 /* (defined only to help avoid cut-and-paste errors) */
-#define BPP8 8
-
-/* Combines the row recently read in with the previous row.
- This routine takes care of alpha and transparency if requested.
- This routine also handles the two methods of progressive display
- of interlaced images, depending on the mask value.
- The mask value describes which pixels are to be combined with
- the row. The pattern always repeats every 8 pixels, so just 8
- bits are needed. A one indicates the pixel is to be combined; a
- zero indicates the pixel is to be skipped. This is in addition
- to any alpha or transparency value associated with the pixel.
- If you want all pixels to be combined, pass 0xff (255) in mask. */
-
-/* Use this routine for the x86 platform - it uses a faster MMX routine
- if the machine supports MMX. */
-
-void /* PRIVATE */
-png_combine_row(png_structp png_ptr, png_bytep row, int mask)
-{
- png_debug(1, "in png_combine_row (pnggccrd.c)\n");
-
-#if defined(PNG_MMX_CODE_SUPPORTED)
- if (_mmx_supported == 2) {
-#if !defined(PNG_1_0_X)
- /* this should have happened in png_init_mmx_flags() already */
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-#endif
-
- if (mask == 0xff)
- {
- png_debug(2,"mask == 0xff: doing single png_memcpy()\n");
- png_memcpy(row, png_ptr->row_buf + 1,
- (png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,png_ptr->width));
- }
- else /* (png_combine_row() is never called with mask == 0) */
- {
- switch (png_ptr->row_info.pixel_depth)
- {
- case 1: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep sp;
- png_bytep dp;
- int s_inc, s_start, s_end;
- int m;
- int shift;
- png_uint_32 i;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 7;
- s_inc = 1;
- }
- else
-#endif
- {
- s_start = 7;
- s_end = 0;
- s_inc = -1;
- }
-
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- int value;
-
- value = (*sp >> shift) & 0x1;
- *dp &= (png_byte)((0x7f7f >> (7 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
-
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 2: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep sp;
- png_bytep dp;
- int s_start, s_end, s_inc;
- int m;
- int shift;
- png_uint_32 i;
- int value;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 6;
- s_inc = 2;
- }
- else
-#endif
- {
- s_start = 6;
- s_end = 0;
- s_inc = -2;
- }
-
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- value = (*sp >> shift) & 0x3;
- *dp &= (png_byte)((0x3f3f >> (6 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 4: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep sp;
- png_bytep dp;
- int s_start, s_end, s_inc;
- int m;
- int shift;
- png_uint_32 i;
- int value;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 4;
- s_inc = 4;
- }
- else
-#endif
- {
- s_start = 4;
- s_end = 0;
- s_inc = -4;
- }
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- value = (*sp >> shift) & 0xf;
- *dp &= (png_byte)((0xf0f >> (4 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 8: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
-
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- png_uint_32 len;
- int diff;
- int dummy_value_a; // fix 'forbidden register spilled' error
- int dummy_value_d;
- int dummy_value_c;
- int dummy_value_S;
- int dummy_value_D;
- _unmask = ~mask; // global variable for -fPIC version
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- len = png_ptr->width &~7; // reduce to multiple of 8
- diff = (int) (png_ptr->width & 7); // amount lost
-
- __asm__ __volatile__ (
- "movd _unmask, %%mm7 \n\t" // load bit pattern
- "psubb %%mm6, %%mm6 \n\t" // zero mm6
- "punpcklbw %%mm7, %%mm7 \n\t"
- "punpcklwd %%mm7, %%mm7 \n\t"
- "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks
-
- "movq _mask8_0, %%mm0 \n\t"
- "pand %%mm7, %%mm0 \n\t" // nonzero if keep byte
- "pcmpeqb %%mm6, %%mm0 \n\t" // zeros->1s, v versa
-
-// preload "movl len, %%ecx \n\t" // load length of line
-// preload "movl srcptr, %%esi \n\t" // load source
-// preload "movl dstptr, %%edi \n\t" // load dest
-
- "cmpl $0, %%ecx \n\t" // len == 0 ?
- "je mainloop8end \n\t"
-
- "mainloop8: \n\t"
- "movq (%%esi), %%mm4 \n\t" // *srcptr
- "pand %%mm0, %%mm4 \n\t"
- "movq %%mm0, %%mm6 \n\t"
- "pandn (%%edi), %%mm6 \n\t" // *dstptr
- "por %%mm6, %%mm4 \n\t"
- "movq %%mm4, (%%edi) \n\t"
- "addl $8, %%esi \n\t" // inc by 8 bytes processed
- "addl $8, %%edi \n\t"
- "subl $8, %%ecx \n\t" // dec by 8 pixels processed
- "ja mainloop8 \n\t"
-
- "mainloop8end: \n\t"
-// preload "movl diff, %%ecx \n\t" // (diff is in eax)
- "movl %%eax, %%ecx \n\t"
- "cmpl $0, %%ecx \n\t"
- "jz end8 \n\t"
-// preload "movl mask, %%edx \n\t"
- "sall $24, %%edx \n\t" // make low byte, high byte
-
- "secondloop8: \n\t"
- "sall %%edx \n\t" // move high bit to CF
- "jnc skip8 \n\t" // if CF = 0
- "movb (%%esi), %%al \n\t"
- "movb %%al, (%%edi) \n\t"
-
- "skip8: \n\t"
- "incl %%esi \n\t"
- "incl %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz secondloop8 \n\t"
-
- "end8: \n\t"
- "EMMS \n\t" // DONE
-
- : "=a" (dummy_value_a), // output regs (dummy)
- "=d" (dummy_value_d),
- "=c" (dummy_value_c),
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "3" (srcptr), // esi // input regs
- "4" (dstptr), // edi
- "0" (diff), // eax
-// was (unmask) "b" RESERVED // ebx // Global Offset Table idx
- "2" (len), // ecx
- "1" (mask) // edx
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm4", "%mm6", "%mm7" // clobber list
-#endif
- );
- }
- else /* mmx _not supported - Use modified C routine */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- register png_uint_32 i;
- png_uint_32 initial_val = png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff /* *BPP1 */ ;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
-
- } /* end of else (_mmx_supported) */
-
- break;
- } /* end 8 bpp */
-
- case 16: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
-
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- png_uint_32 len;
- int diff;
- int dummy_value_a; // fix 'forbidden register spilled' error
- int dummy_value_d;
- int dummy_value_c;
- int dummy_value_S;
- int dummy_value_D;
- _unmask = ~mask; // global variable for -fPIC version
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- len = png_ptr->width &~7; // reduce to multiple of 8
- diff = (int) (png_ptr->width & 7); // amount lost //
-
- __asm__ __volatile__ (
- "movd _unmask, %%mm7 \n\t" // load bit pattern
- "psubb %%mm6, %%mm6 \n\t" // zero mm6
- "punpcklbw %%mm7, %%mm7 \n\t"
- "punpcklwd %%mm7, %%mm7 \n\t"
- "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks
-
- "movq _mask16_0, %%mm0 \n\t"
- "movq _mask16_1, %%mm1 \n\t"
-
- "pand %%mm7, %%mm0 \n\t"
- "pand %%mm7, %%mm1 \n\t"
-
- "pcmpeqb %%mm6, %%mm0 \n\t"
- "pcmpeqb %%mm6, %%mm1 \n\t"
-
-// preload "movl len, %%ecx \n\t" // load length of line
-// preload "movl srcptr, %%esi \n\t" // load source
-// preload "movl dstptr, %%edi \n\t" // load dest
-
- "cmpl $0, %%ecx \n\t"
- "jz mainloop16end \n\t"
-
- "mainloop16: \n\t"
- "movq (%%esi), %%mm4 \n\t"
- "pand %%mm0, %%mm4 \n\t"
- "movq %%mm0, %%mm6 \n\t"
- "movq (%%edi), %%mm7 \n\t"
- "pandn %%mm7, %%mm6 \n\t"
- "por %%mm6, %%mm4 \n\t"
- "movq %%mm4, (%%edi) \n\t"
-
- "movq 8(%%esi), %%mm5 \n\t"
- "pand %%mm1, %%mm5 \n\t"
- "movq %%mm1, %%mm7 \n\t"
- "movq 8(%%edi), %%mm6 \n\t"
- "pandn %%mm6, %%mm7 \n\t"
- "por %%mm7, %%mm5 \n\t"
- "movq %%mm5, 8(%%edi) \n\t"
-
- "addl $16, %%esi \n\t" // inc by 16 bytes processed
- "addl $16, %%edi \n\t"
- "subl $8, %%ecx \n\t" // dec by 8 pixels processed
- "ja mainloop16 \n\t"
-
- "mainloop16end: \n\t"
-// preload "movl diff, %%ecx \n\t" // (diff is in eax)
- "movl %%eax, %%ecx \n\t"
- "cmpl $0, %%ecx \n\t"
- "jz end16 \n\t"
-// preload "movl mask, %%edx \n\t"
- "sall $24, %%edx \n\t" // make low byte, high byte
-
- "secondloop16: \n\t"
- "sall %%edx \n\t" // move high bit to CF
- "jnc skip16 \n\t" // if CF = 0
- "movw (%%esi), %%ax \n\t"
- "movw %%ax, (%%edi) \n\t"
-
- "skip16: \n\t"
- "addl $2, %%esi \n\t"
- "addl $2, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz secondloop16 \n\t"
-
- "end16: \n\t"
- "EMMS \n\t" // DONE
-
- : "=a" (dummy_value_a), // output regs (dummy)
- "=c" (dummy_value_c),
- "=d" (dummy_value_d),
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (diff), // eax // input regs
-// was (unmask) " " RESERVED // ebx // Global Offset Table idx
- "1" (len), // ecx
- "2" (mask), // edx
- "3" (srcptr), // esi
- "4" (dstptr) // edi
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm4" // clobber list
- , "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- else /* mmx _not supported - Use modified C routine */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- register png_uint_32 i;
- png_uint_32 initial_val = BPP2 * png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = BPP2 * png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = BPP2 * png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = BPP2 * len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff*BPP2;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
- } /* end of else (_mmx_supported) */
-
- break;
- } /* end 16 bpp */
-
- case 24: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
-
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- png_uint_32 len;
- int diff;
- int dummy_value_a; // fix 'forbidden register spilled' error
- int dummy_value_d;
- int dummy_value_c;
- int dummy_value_S;
- int dummy_value_D;
- _unmask = ~mask; // global variable for -fPIC version
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- len = png_ptr->width &~7; // reduce to multiple of 8
- diff = (int) (png_ptr->width & 7); // amount lost //
-
- __asm__ __volatile__ (
- "movd _unmask, %%mm7 \n\t" // load bit pattern
- "psubb %%mm6, %%mm6 \n\t" // zero mm6
- "punpcklbw %%mm7, %%mm7 \n\t"
- "punpcklwd %%mm7, %%mm7 \n\t"
- "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks
-
- "movq _mask24_0, %%mm0 \n\t"
- "movq _mask24_1, %%mm1 \n\t"
- "movq _mask24_2, %%mm2 \n\t"
-
- "pand %%mm7, %%mm0 \n\t"
- "pand %%mm7, %%mm1 \n\t"
- "pand %%mm7, %%mm2 \n\t"
-
- "pcmpeqb %%mm6, %%mm0 \n\t"
- "pcmpeqb %%mm6, %%mm1 \n\t"
- "pcmpeqb %%mm6, %%mm2 \n\t"
-
-// preload "movl len, %%ecx \n\t" // load length of line
-// preload "movl srcptr, %%esi \n\t" // load source
-// preload "movl dstptr, %%edi \n\t" // load dest
-
- "cmpl $0, %%ecx \n\t"
- "jz mainloop24end \n\t"
-
- "mainloop24: \n\t"
- "movq (%%esi), %%mm4 \n\t"
- "pand %%mm0, %%mm4 \n\t"
- "movq %%mm0, %%mm6 \n\t"
- "movq (%%edi), %%mm7 \n\t"
- "pandn %%mm7, %%mm6 \n\t"
- "por %%mm6, %%mm4 \n\t"
- "movq %%mm4, (%%edi) \n\t"
-
- "movq 8(%%esi), %%mm5 \n\t"
- "pand %%mm1, %%mm5 \n\t"
- "movq %%mm1, %%mm7 \n\t"
- "movq 8(%%edi), %%mm6 \n\t"
- "pandn %%mm6, %%mm7 \n\t"
- "por %%mm7, %%mm5 \n\t"
- "movq %%mm5, 8(%%edi) \n\t"
-
- "movq 16(%%esi), %%mm6 \n\t"
- "pand %%mm2, %%mm6 \n\t"
- "movq %%mm2, %%mm4 \n\t"
- "movq 16(%%edi), %%mm7 \n\t"
- "pandn %%mm7, %%mm4 \n\t"
- "por %%mm4, %%mm6 \n\t"
- "movq %%mm6, 16(%%edi) \n\t"
-
- "addl $24, %%esi \n\t" // inc by 24 bytes processed
- "addl $24, %%edi \n\t"
- "subl $8, %%ecx \n\t" // dec by 8 pixels processed
-
- "ja mainloop24 \n\t"
-
- "mainloop24end: \n\t"
-// preload "movl diff, %%ecx \n\t" // (diff is in eax)
- "movl %%eax, %%ecx \n\t"
- "cmpl $0, %%ecx \n\t"
- "jz end24 \n\t"
-// preload "movl mask, %%edx \n\t"
- "sall $24, %%edx \n\t" // make low byte, high byte
-
- "secondloop24: \n\t"
- "sall %%edx \n\t" // move high bit to CF
- "jnc skip24 \n\t" // if CF = 0
- "movw (%%esi), %%ax \n\t"
- "movw %%ax, (%%edi) \n\t"
- "xorl %%eax, %%eax \n\t"
- "movb 2(%%esi), %%al \n\t"
- "movb %%al, 2(%%edi) \n\t"
-
- "skip24: \n\t"
- "addl $3, %%esi \n\t"
- "addl $3, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz secondloop24 \n\t"
-
- "end24: \n\t"
- "EMMS \n\t" // DONE
-
- : "=a" (dummy_value_a), // output regs (dummy)
- "=d" (dummy_value_d),
- "=c" (dummy_value_c),
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "3" (srcptr), // esi // input regs
- "4" (dstptr), // edi
- "0" (diff), // eax
-// was (unmask) "b" RESERVED // ebx // Global Offset Table idx
- "2" (len), // ecx
- "1" (mask) // edx
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2" // clobber list
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- else /* mmx _not supported - Use modified C routine */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- register png_uint_32 i;
- png_uint_32 initial_val = BPP3 * png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = BPP3 * png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = BPP3 * png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = BPP3 * len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff*BPP3;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
- } /* end of else (_mmx_supported) */
-
- break;
- } /* end 24 bpp */
-
- case 32: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
-
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- png_uint_32 len;
- int diff;
- int dummy_value_a; // fix 'forbidden register spilled' error
- int dummy_value_d;
- int dummy_value_c;
- int dummy_value_S;
- int dummy_value_D;
- _unmask = ~mask; // global variable for -fPIC version
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- len = png_ptr->width &~7; // reduce to multiple of 8
- diff = (int) (png_ptr->width & 7); // amount lost //
-
- __asm__ __volatile__ (
- "movd _unmask, %%mm7 \n\t" // load bit pattern
- "psubb %%mm6, %%mm6 \n\t" // zero mm6
- "punpcklbw %%mm7, %%mm7 \n\t"
- "punpcklwd %%mm7, %%mm7 \n\t"
- "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks
-
- "movq _mask32_0, %%mm0 \n\t"
- "movq _mask32_1, %%mm1 \n\t"
- "movq _mask32_2, %%mm2 \n\t"
- "movq _mask32_3, %%mm3 \n\t"
-
- "pand %%mm7, %%mm0 \n\t"
- "pand %%mm7, %%mm1 \n\t"
- "pand %%mm7, %%mm2 \n\t"
- "pand %%mm7, %%mm3 \n\t"
-
- "pcmpeqb %%mm6, %%mm0 \n\t"
- "pcmpeqb %%mm6, %%mm1 \n\t"
- "pcmpeqb %%mm6, %%mm2 \n\t"
- "pcmpeqb %%mm6, %%mm3 \n\t"
-
-// preload "movl len, %%ecx \n\t" // load length of line
-// preload "movl srcptr, %%esi \n\t" // load source
-// preload "movl dstptr, %%edi \n\t" // load dest
-
- "cmpl $0, %%ecx \n\t" // lcr
- "jz mainloop32end \n\t"
-
- "mainloop32: \n\t"
- "movq (%%esi), %%mm4 \n\t"
- "pand %%mm0, %%mm4 \n\t"
- "movq %%mm0, %%mm6 \n\t"
- "movq (%%edi), %%mm7 \n\t"
- "pandn %%mm7, %%mm6 \n\t"
- "por %%mm6, %%mm4 \n\t"
- "movq %%mm4, (%%edi) \n\t"
-
- "movq 8(%%esi), %%mm5 \n\t"
- "pand %%mm1, %%mm5 \n\t"
- "movq %%mm1, %%mm7 \n\t"
- "movq 8(%%edi), %%mm6 \n\t"
- "pandn %%mm6, %%mm7 \n\t"
- "por %%mm7, %%mm5 \n\t"
- "movq %%mm5, 8(%%edi) \n\t"
-
- "movq 16(%%esi), %%mm6 \n\t"
- "pand %%mm2, %%mm6 \n\t"
- "movq %%mm2, %%mm4 \n\t"
- "movq 16(%%edi), %%mm7 \n\t"
- "pandn %%mm7, %%mm4 \n\t"
- "por %%mm4, %%mm6 \n\t"
- "movq %%mm6, 16(%%edi) \n\t"
-
- "movq 24(%%esi), %%mm7 \n\t"
- "pand %%mm3, %%mm7 \n\t"
- "movq %%mm3, %%mm5 \n\t"
- "movq 24(%%edi), %%mm4 \n\t"
- "pandn %%mm4, %%mm5 \n\t"
- "por %%mm5, %%mm7 \n\t"
- "movq %%mm7, 24(%%edi) \n\t"
-
- "addl $32, %%esi \n\t" // inc by 32 bytes processed
- "addl $32, %%edi \n\t"
- "subl $8, %%ecx \n\t" // dec by 8 pixels processed
- "ja mainloop32 \n\t"
-
- "mainloop32end: \n\t"
-// preload "movl diff, %%ecx \n\t" // (diff is in eax)
- "movl %%eax, %%ecx \n\t"
- "cmpl $0, %%ecx \n\t"
- "jz end32 \n\t"
-// preload "movl mask, %%edx \n\t"
- "sall $24, %%edx \n\t" // low byte => high byte
-
- "secondloop32: \n\t"
- "sall %%edx \n\t" // move high bit to CF
- "jnc skip32 \n\t" // if CF = 0
- "movl (%%esi), %%eax \n\t"
- "movl %%eax, (%%edi) \n\t"
-
- "skip32: \n\t"
- "addl $4, %%esi \n\t"
- "addl $4, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz secondloop32 \n\t"
-
- "end32: \n\t"
- "EMMS \n\t" // DONE
-
- : "=a" (dummy_value_a), // output regs (dummy)
- "=d" (dummy_value_d),
- "=c" (dummy_value_c),
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "3" (srcptr), // esi // input regs
- "4" (dstptr), // edi
- "0" (diff), // eax
-// was (unmask) "b" RESERVED // ebx // Global Offset Table idx
- "2" (len), // ecx
- "1" (mask) // edx
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- else /* mmx _not supported - Use modified C routine */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- register png_uint_32 i;
- png_uint_32 initial_val = BPP4 * png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = BPP4 * png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = BPP4 * png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = BPP4 * len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff*BPP4;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
- } /* end of else (_mmx_supported) */
-
- break;
- } /* end 32 bpp */
-
- case 48: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
-
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- png_uint_32 len;
- int diff;
- int dummy_value_a; // fix 'forbidden register spilled' error
- int dummy_value_d;
- int dummy_value_c;
- int dummy_value_S;
- int dummy_value_D;
- _unmask = ~mask; // global variable for -fPIC version
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- len = png_ptr->width &~7; // reduce to multiple of 8
- diff = (int) (png_ptr->width & 7); // amount lost //
-
- __asm__ __volatile__ (
- "movd _unmask, %%mm7 \n\t" // load bit pattern
- "psubb %%mm6, %%mm6 \n\t" // zero mm6
- "punpcklbw %%mm7, %%mm7 \n\t"
- "punpcklwd %%mm7, %%mm7 \n\t"
- "punpckldq %%mm7, %%mm7 \n\t" // fill reg with 8 masks
-
- "movq _mask48_0, %%mm0 \n\t"
- "movq _mask48_1, %%mm1 \n\t"
- "movq _mask48_2, %%mm2 \n\t"
- "movq _mask48_3, %%mm3 \n\t"
- "movq _mask48_4, %%mm4 \n\t"
- "movq _mask48_5, %%mm5 \n\t"
-
- "pand %%mm7, %%mm0 \n\t"
- "pand %%mm7, %%mm1 \n\t"
- "pand %%mm7, %%mm2 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pand %%mm7, %%mm4 \n\t"
- "pand %%mm7, %%mm5 \n\t"
-
- "pcmpeqb %%mm6, %%mm0 \n\t"
- "pcmpeqb %%mm6, %%mm1 \n\t"
- "pcmpeqb %%mm6, %%mm2 \n\t"
- "pcmpeqb %%mm6, %%mm3 \n\t"
- "pcmpeqb %%mm6, %%mm4 \n\t"
- "pcmpeqb %%mm6, %%mm5 \n\t"
-
-// preload "movl len, %%ecx \n\t" // load length of line
-// preload "movl srcptr, %%esi \n\t" // load source
-// preload "movl dstptr, %%edi \n\t" // load dest
-
- "cmpl $0, %%ecx \n\t"
- "jz mainloop48end \n\t"
-
- "mainloop48: \n\t"
- "movq (%%esi), %%mm7 \n\t"
- "pand %%mm0, %%mm7 \n\t"
- "movq %%mm0, %%mm6 \n\t"
- "pandn (%%edi), %%mm6 \n\t"
- "por %%mm6, %%mm7 \n\t"
- "movq %%mm7, (%%edi) \n\t"
-
- "movq 8(%%esi), %%mm6 \n\t"
- "pand %%mm1, %%mm6 \n\t"
- "movq %%mm1, %%mm7 \n\t"
- "pandn 8(%%edi), %%mm7 \n\t"
- "por %%mm7, %%mm6 \n\t"
- "movq %%mm6, 8(%%edi) \n\t"
-
- "movq 16(%%esi), %%mm6 \n\t"
- "pand %%mm2, %%mm6 \n\t"
- "movq %%mm2, %%mm7 \n\t"
- "pandn 16(%%edi), %%mm7 \n\t"
- "por %%mm7, %%mm6 \n\t"
- "movq %%mm6, 16(%%edi) \n\t"
-
- "movq 24(%%esi), %%mm7 \n\t"
- "pand %%mm3, %%mm7 \n\t"
- "movq %%mm3, %%mm6 \n\t"
- "pandn 24(%%edi), %%mm6 \n\t"
- "por %%mm6, %%mm7 \n\t"
- "movq %%mm7, 24(%%edi) \n\t"
-
- "movq 32(%%esi), %%mm6 \n\t"
- "pand %%mm4, %%mm6 \n\t"
- "movq %%mm4, %%mm7 \n\t"
- "pandn 32(%%edi), %%mm7 \n\t"
- "por %%mm7, %%mm6 \n\t"
- "movq %%mm6, 32(%%edi) \n\t"
-
- "movq 40(%%esi), %%mm7 \n\t"
- "pand %%mm5, %%mm7 \n\t"
- "movq %%mm5, %%mm6 \n\t"
- "pandn 40(%%edi), %%mm6 \n\t"
- "por %%mm6, %%mm7 \n\t"
- "movq %%mm7, 40(%%edi) \n\t"
-
- "addl $48, %%esi \n\t" // inc by 48 bytes processed
- "addl $48, %%edi \n\t"
- "subl $8, %%ecx \n\t" // dec by 8 pixels processed
-
- "ja mainloop48 \n\t"
-
- "mainloop48end: \n\t"
-// preload "movl diff, %%ecx \n\t" // (diff is in eax)
- "movl %%eax, %%ecx \n\t"
- "cmpl $0, %%ecx \n\t"
- "jz end48 \n\t"
-// preload "movl mask, %%edx \n\t"
- "sall $24, %%edx \n\t" // make low byte, high byte
-
- "secondloop48: \n\t"
- "sall %%edx \n\t" // move high bit to CF
- "jnc skip48 \n\t" // if CF = 0
- "movl (%%esi), %%eax \n\t"
- "movl %%eax, (%%edi) \n\t"
-
- "skip48: \n\t"
- "addl $4, %%esi \n\t"
- "addl $4, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz secondloop48 \n\t"
-
- "end48: \n\t"
- "EMMS \n\t" // DONE
-
- : "=a" (dummy_value_a), // output regs (dummy)
- "=d" (dummy_value_d),
- "=c" (dummy_value_c),
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "3" (srcptr), // esi // input regs
- "4" (dstptr), // edi
- "0" (diff), // eax
-// was (unmask) "b" RESERVED // ebx // Global Offset Table idx
- "2" (len), // ecx
- "1" (mask) // edx
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2", "%mm3" // clobber list
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- else /* mmx _not supported - Use modified C routine */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- register png_uint_32 i;
- png_uint_32 initial_val = BPP6 * png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = BPP6 * png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = BPP6 * png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = BPP6 * len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff*BPP6;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
- } /* end of else (_mmx_supported) */
-
- break;
- } /* end 48 bpp */
-
- case 64: /* png_ptr->row_info.pixel_depth */
- {
- png_bytep srcptr;
- png_bytep dstptr;
- register png_uint_32 i;
- png_uint_32 initial_val = BPP8 * png_pass_start[png_ptr->pass];
- /* png.c: png_pass_start[] = {0, 4, 0, 2, 0, 1, 0}; */
- register int stride = BPP8 * png_pass_inc[png_ptr->pass];
- /* png.c: png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1}; */
- register int rep_bytes = BPP8 * png_pass_width[png_ptr->pass];
- /* png.c: png_pass_width[] = {8, 4, 4, 2, 2, 1, 1}; */
- png_uint_32 len = png_ptr->width &~7; /* reduce to mult. of 8 */
- int diff = (int) (png_ptr->width & 7); /* amount lost */
- register png_uint_32 final_val = BPP8 * len; /* GRR bugfix */
-
- srcptr = png_ptr->row_buf + 1 + initial_val;
- dstptr = row + initial_val;
-
- for (i = initial_val; i < final_val; i += stride)
- {
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- if (diff) /* number of leftover pixels: 3 for pngtest */
- {
- final_val+=diff*BPP8;
- for (; i < final_val; i += stride)
- {
- if (rep_bytes > (int)(final_val-i))
- rep_bytes = (int)(final_val-i);
- png_memcpy(dstptr, srcptr, rep_bytes);
- srcptr += stride;
- dstptr += stride;
- }
- }
-
- break;
- } /* end 64 bpp */
-
- default: /* png_ptr->row_info.pixel_depth != 1,2,4,8,16,24,32,48,64 */
- {
- /* this should never happen */
- png_warning(png_ptr, "Invalid row_info.pixel_depth in pnggccrd");
- break;
- }
- } /* end switch (png_ptr->row_info.pixel_depth) */
-
- } /* end if (non-trivial mask) */
-
-} /* end png_combine_row() */
-
-#endif /* PNG_HAVE_MMX_COMBINE_ROW */
-
-
-
-
-/*===========================================================================*/
-/* */
-/* P N G _ D O _ R E A D _ I N T E R L A C E */
-/* */
-/*===========================================================================*/
-
-#if defined(PNG_READ_INTERLACING_SUPPORTED)
-#if defined(PNG_HAVE_MMX_READ_INTERLACE)
-
-/* png_do_read_interlace() is called after any 16-bit to 8-bit conversion
- * has taken place. [GRR: what other steps come before and/or after?]
- */
-
-void /* PRIVATE */
-png_do_read_interlace(png_structp png_ptr)
-{
- png_row_infop row_info = &(png_ptr->row_info);
- png_bytep row = png_ptr->row_buf + 1;
- int pass = png_ptr->pass;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- png_uint_32 transformations = png_ptr->transformations;
-#endif
-
- png_debug(1, "in png_do_read_interlace (pnggccrd.c)\n");
-
-#if defined(PNG_MMX_CODE_SUPPORTED)
- if (_mmx_supported == 2) {
-#if !defined(PNG_1_0_X)
- /* this should have happened in png_init_mmx_flags() already */
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-#endif
-
- if (row != NULL && row_info != NULL)
- {
- png_uint_32 final_width;
-
- final_width = row_info->width * png_pass_inc[pass];
-
- switch (row_info->pixel_depth)
- {
- case 1:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_byte v;
- png_uint_32 i;
- int j;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 3);
- dp = row + (png_size_t)((final_width - 1) >> 3);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (int)((row_info->width + 7) & 7);
- dshift = (int)((final_width + 7) & 7);
- s_start = 7;
- s_end = 0;
- s_inc = -1;
- }
- else
-#endif
- {
- sshift = 7 - (int)((row_info->width + 7) & 7);
- dshift = 7 - (int)((final_width + 7) & 7);
- s_start = 0;
- s_end = 7;
- s_inc = 1;
- }
-
- for (i = row_info->width; i; i--)
- {
- v = (png_byte)((*sp >> sshift) & 0x1);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0x7f7f >> (7 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- case 2:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_uint_32 i;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 2);
- dp = row + (png_size_t)((final_width - 1) >> 2);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (png_size_t)(((row_info->width + 3) & 3) << 1);
- dshift = (png_size_t)(((final_width + 3) & 3) << 1);
- s_start = 6;
- s_end = 0;
- s_inc = -2;
- }
- else
-#endif
- {
- sshift = (png_size_t)((3 - ((row_info->width + 3) & 3)) << 1);
- dshift = (png_size_t)((3 - ((final_width + 3) & 3)) << 1);
- s_start = 0;
- s_end = 6;
- s_inc = 2;
- }
-
- for (i = row_info->width; i; i--)
- {
- png_byte v;
- int j;
-
- v = (png_byte)((*sp >> sshift) & 0x3);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0x3f3f >> (6 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- case 4:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_uint_32 i;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 1);
- dp = row + (png_size_t)((final_width - 1) >> 1);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (png_size_t)(((row_info->width + 1) & 1) << 2);
- dshift = (png_size_t)(((final_width + 1) & 1) << 2);
- s_start = 4;
- s_end = 0;
- s_inc = -4;
- }
- else
-#endif
- {
- sshift = (png_size_t)((1 - ((row_info->width + 1) & 1)) << 2);
- dshift = (png_size_t)((1 - ((final_width + 1) & 1)) << 2);
- s_start = 0;
- s_end = 4;
- s_inc = 4;
- }
-
- for (i = row_info->width; i; i--)
- {
- png_byte v;
- int j;
-
- v = (png_byte)((*sp >> sshift) & 0xf);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0xf0f >> (4 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- /*====================================================================*/
-
- default: /* 8-bit or larger (this is where the routine is modified) */
- {
-#if 0
-// static unsigned long long _const4 = 0x0000000000FFFFFFLL; no good
-// static unsigned long long const4 = 0x0000000000FFFFFFLL; no good
-// unsigned long long _const4 = 0x0000000000FFFFFFLL; no good
-// unsigned long long const4 = 0x0000000000FFFFFFLL; no good
-#endif
- png_bytep sptr, dp;
- png_uint_32 i;
- png_size_t pixel_bytes;
- int width = (int)row_info->width;
-
- pixel_bytes = (row_info->pixel_depth >> 3);
-
- /* point sptr at the last pixel in the pre-expanded row: */
- sptr = row + (width - 1) * pixel_bytes;
-
- /* point dp at the last pixel position in the expanded row: */
- dp = row + (final_width - 1) * pixel_bytes;
-
- /* New code by Nirav Chhatrapati - Intel Corporation */
-
-#if defined(PNG_MMX_CODE_SUPPORTED)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_INTERLACE)
- /* && _mmx_supported */ )
-#else
- if (_mmx_supported)
-#endif
- {
- //--------------------------------------------------------------
- if (pixel_bytes == 3)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
- int dummy_value_a;
-
- __asm__ __volatile__ (
- "subl $21, %%edi \n\t"
- // (png_pass_inc[pass] - 1)*pixel_bytes
-
- ".loop3_pass0: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0
- "pand (%3), %%mm0 \n\t" // z z z z z 2 1 0
- "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0
- "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z
- "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z
- "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z
- "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1
- "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z
- "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1
- "movq %%mm0, %%mm3 \n\t" // 2 1 0 2 1 0 2 1
- "psllq $16, %%mm0 \n\t" // 0 2 1 0 2 1 z z
- "movq %%mm3, %%mm4 \n\t" // 2 1 0 2 1 0 2 1
- "punpckhdq %%mm0, %%mm3 \n\t" // 0 2 1 0 2 1 0 2
- "movq %%mm4, 16(%%edi) \n\t"
- "psrlq $32, %%mm0 \n\t" // z z z z 0 2 1 0
- "movq %%mm3, 8(%%edi) \n\t"
- "punpckldq %%mm4, %%mm0 \n\t" // 1 0 2 1 0 2 1 0
- "subl $3, %%esi \n\t"
- "movq %%mm0, (%%edi) \n\t"
- "subl $24, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz .loop3_pass0 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D),
- "=a" (dummy_value_a)
-
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width), // ecx
- "3" (&_const4) // %1(?) (0x0000000000FFFFFFLL)
-
-#if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2" // clobber list
- , "%mm3", "%mm4"
-#endif
- );
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
- int dummy_value_a;
-
- __asm__ __volatile__ (
- "subl $9, %%edi \n\t"
- // (png_pass_inc[pass] - 1)*pixel_bytes
-
- ".loop3_pass2: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x x 2 1 0
- "pand (%3), %%mm0 \n\t" // z z z z z 2 1 0
- "movq %%mm0, %%mm1 \n\t" // z z z z z 2 1 0
- "psllq $16, %%mm0 \n\t" // z z z 2 1 0 z z
- "movq %%mm0, %%mm2 \n\t" // z z z 2 1 0 z z
- "psllq $24, %%mm0 \n\t" // 2 1 0 z z z z z
- "psrlq $8, %%mm1 \n\t" // z z z z z z 2 1
- "por %%mm2, %%mm0 \n\t" // 2 1 0 2 1 0 z z
- "por %%mm1, %%mm0 \n\t" // 2 1 0 2 1 0 2 1
- "movq %%mm0, 4(%%edi) \n\t"
- "psrlq $16, %%mm0 \n\t" // z z 2 1 0 2 1 0
- "subl $3, %%esi \n\t"
- "movd %%mm0, (%%edi) \n\t"
- "subl $12, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz .loop3_pass2 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D),
- "=a" (dummy_value_a)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width), // ecx
- "3" (&_const4) // (0x0000000000FFFFFFLL)
-
-#if 0 /* %mm0, ..., %mm2 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2" // clobber list
-#endif
- );
- }
- else if (width) /* && ((pass == 4) || (pass == 5)) */
- {
- int width_mmx = ((width >> 1) << 1) - 8; // GRR: huh?
- if (width_mmx < 0)
- width_mmx = 0;
- width -= width_mmx; // 8 or 9 pix, 24 or 27 bytes
- if (width_mmx)
- {
- // png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
- // sptr points at last pixel in pre-expanded row
- // dp points at last pixel position in expanded row
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
- int dummy_value_a;
- int dummy_value_d;
-
- __asm__ __volatile__ (
- "subl $3, %%esi \n\t"
- "subl $9, %%edi \n\t"
- // (png_pass_inc[pass] + 1)*pixel_bytes
-
- ".loop3_pass4: \n\t"
- "movq (%%esi), %%mm0 \n\t" // x x 5 4 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // x x 5 4 3 2 1 0
- "movq %%mm0, %%mm2 \n\t" // x x 5 4 3 2 1 0
- "psllq $24, %%mm0 \n\t" // 4 3 2 1 0 z z z
- "pand (%3), %%mm1 \n\t" // z z z z z 2 1 0
- "psrlq $24, %%mm2 \n\t" // z z z x x 5 4 3
- "por %%mm1, %%mm0 \n\t" // 4 3 2 1 0 2 1 0
- "movq %%mm2, %%mm3 \n\t" // z z z x x 5 4 3
- "psllq $8, %%mm2 \n\t" // z z x x 5 4 3 z
- "movq %%mm0, (%%edi) \n\t"
- "psrlq $16, %%mm3 \n\t" // z z z z z x x 5
- "pand (%4), %%mm3 \n\t" // z z z z z z z 5
- "por %%mm3, %%mm2 \n\t" // z z x x 5 4 3 5
- "subl $6, %%esi \n\t"
- "movd %%mm2, 8(%%edi) \n\t"
- "subl $12, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop3_pass4 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D),
- "=a" (dummy_value_a),
- "=d" (dummy_value_d)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx), // ecx
- "3" (&_const4), // 0x0000000000FFFFFFLL
- "4" (&_const6) // 0x00000000000000FFLL
-
-#if 0 /* %mm0, ..., %mm3 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
- , "%mm2", "%mm3"
-#endif
- );
- }
-
- sptr -= width_mmx*3;
- dp -= width_mmx*6;
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
-
- png_memcpy(v, sptr, 3);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 3);
- dp -= 3;
- }
- sptr -= 3;
- }
- }
- } /* end of pixel_bytes == 3 */
-
- //--------------------------------------------------------------
- else if (pixel_bytes == 1)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 2) << 2);
- width -= width_mmx; // 0-3 pixels => 0-3 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $3, %%esi \n\t"
- "subl $31, %%edi \n\t"
-
- ".loop1_pass0: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // x x x x 3 2 1 0
- "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0
- "movq %%mm0, %%mm2 \n\t" // 3 3 2 2 1 1 0 0
- "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0
- "movq %%mm0, %%mm3 \n\t" // 1 1 1 1 0 0 0 0
- "punpckldq %%mm0, %%mm0 \n\t" // 0 0 0 0 0 0 0 0
- "punpckhdq %%mm3, %%mm3 \n\t" // 1 1 1 1 1 1 1 1
- "movq %%mm0, (%%edi) \n\t"
- "punpckhwd %%mm2, %%mm2 \n\t" // 3 3 3 3 2 2 2 2
- "movq %%mm3, 8(%%edi) \n\t"
- "movq %%mm2, %%mm4 \n\t" // 3 3 3 3 2 2 2 2
- "punpckldq %%mm2, %%mm2 \n\t" // 2 2 2 2 2 2 2 2
- "punpckhdq %%mm4, %%mm4 \n\t" // 3 3 3 3 3 3 3 3
- "movq %%mm2, 16(%%edi) \n\t"
- "subl $4, %%esi \n\t"
- "movq %%mm4, 24(%%edi) \n\t"
- "subl $32, %%edi \n\t"
- "subl $4, %%ecx \n\t"
- "jnz .loop1_pass0 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, ..., %mm4 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1", "%mm2" // clobber list
- , "%mm3", "%mm4"
-#endif
- );
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*8;
- for (i = width; i; i--)
- {
- int j;
-
- /* I simplified this part in version 1.0.4e
- * here and in several other instances where
- * pixel_bytes == 1 -- GR-P
- *
- * Original code:
- *
- * png_byte v[8];
- * png_memcpy(v, sptr, pixel_bytes);
- * for (j = 0; j < png_pass_inc[pass]; j++)
- * {
- * png_memcpy(dp, v, pixel_bytes);
- * dp -= pixel_bytes;
- * }
- * sptr -= pixel_bytes;
- *
- * Replacement code is in the next three lines:
- */
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- --sptr;
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 2) << 2);
- width -= width_mmx; // 0-3 pixels => 0-3 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $3, %%esi \n\t"
- "subl $15, %%edi \n\t"
-
- ".loop1_pass2: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0
- "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0
- "movq %%mm0, %%mm1 \n\t" // 3 3 2 2 1 1 0 0
- "punpcklwd %%mm0, %%mm0 \n\t" // 1 1 1 1 0 0 0 0
- "punpckhwd %%mm1, %%mm1 \n\t" // 3 3 3 3 2 2 2 2
- "movq %%mm0, (%%edi) \n\t"
- "subl $4, %%esi \n\t"
- "movq %%mm1, 8(%%edi) \n\t"
- "subl $16, %%edi \n\t"
- "subl $4, %%ecx \n\t"
- "jnz .loop1_pass2 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*4;
- for (i = width; i; i--)
- {
- int j;
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- --sptr;
- }
- }
- else if (width) /* && ((pass == 4) || (pass == 5)) */
- {
- int width_mmx = ((width >> 3) << 3);
- width -= width_mmx; // 0-3 pixels => 0-3 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $7, %%esi \n\t"
- "subl $15, %%edi \n\t"
-
- ".loop1_pass4: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0
- "punpcklbw %%mm0, %%mm0 \n\t" // 3 3 2 2 1 1 0 0
- "punpckhbw %%mm1, %%mm1 \n\t" // 7 7 6 6 5 5 4 4
- "movq %%mm1, 8(%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm0, (%%edi) \n\t"
- "subl $16, %%edi \n\t"
- "subl $8, %%ecx \n\t"
- "jnz .loop1_pass4 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (none)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*2;
- for (i = width; i; i--)
- {
- int j;
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- --sptr;
- }
- }
- } /* end of pixel_bytes == 1 */
-
- //--------------------------------------------------------------
- else if (pixel_bytes == 2)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 1) << 1);
- width -= width_mmx; // 0,1 pixels => 0,2 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $2, %%esi \n\t"
- "subl $30, %%edi \n\t"
-
- ".loop2_pass0: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0
- "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0
- "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0
- "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0
- "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2
- "movq %%mm0, (%%edi) \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "movq %%mm1, 16(%%edi) \n\t"
- "subl $4, %%esi \n\t"
- "movq %%mm1, 24(%%edi) \n\t"
- "subl $32, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop2_pass0 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*16 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx; // 0,1 pixels => 0,2 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $2, %%esi \n\t"
- "subl $14, %%edi \n\t"
-
- ".loop2_pass2: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0
- "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0
- "movq %%mm0, %%mm1 \n\t" // 3 2 3 2 1 0 1 0
- "punpckldq %%mm0, %%mm0 \n\t" // 1 0 1 0 1 0 1 0
- "punpckhdq %%mm1, %%mm1 \n\t" // 3 2 3 2 3 2 3 2
- "movq %%mm0, (%%edi) \n\t"
- "subl $4, %%esi \n\t"
- "movq %%mm1, 8(%%edi) \n\t"
- "subl $16, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop2_pass2 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*8 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- else if (width) // pass == 4 or 5
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx; // 0,1 pixels => 0,2 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $2, %%esi \n\t"
- "subl $6, %%edi \n\t"
-
- ".loop2_pass4: \n\t"
- "movd (%%esi), %%mm0 \n\t" // x x x x 3 2 1 0
- "punpcklwd %%mm0, %%mm0 \n\t" // 3 2 3 2 1 0 1 0
- "subl $4, %%esi \n\t"
- "movq %%mm0, (%%edi) \n\t"
- "subl $8, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop2_pass4 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*4 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- } /* end of pixel_bytes == 2 */
-
- //--------------------------------------------------------------
- else if (pixel_bytes == 4)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 1) << 1);
- width -= width_mmx; // 0,1 pixels => 0,4 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $4, %%esi \n\t"
- "subl $60, %%edi \n\t"
-
- ".loop4_pass0: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0
- "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0
- "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4
- "movq %%mm0, (%%edi) \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "movq %%mm0, 16(%%edi) \n\t"
- "movq %%mm0, 24(%%edi) \n\t"
- "movq %%mm1, 32(%%edi) \n\t"
- "movq %%mm1, 40(%%edi) \n\t"
- "movq %%mm1, 48(%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm1, 56(%%edi) \n\t"
- "subl $64, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop4_pass0 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*32 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 1) << 1);
- width -= width_mmx; // 0,1 pixels => 0,4 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $4, %%esi \n\t"
- "subl $28, %%edi \n\t"
-
- ".loop4_pass2: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0
- "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0
- "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4
- "movq %%mm0, (%%edi) \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "movq %%mm1, 16(%%edi) \n\t"
- "movq %%mm1, 24(%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "subl $32, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop4_pass2 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*16 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
- else if (width) // pass == 4 or 5
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx; // 0,1 pixels => 0,4 bytes
- if (width_mmx)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $4, %%esi \n\t"
- "subl $12, %%edi \n\t"
-
- ".loop4_pass4: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, %%mm1 \n\t" // 7 6 5 4 3 2 1 0
- "punpckldq %%mm0, %%mm0 \n\t" // 3 2 1 0 3 2 1 0
- "punpckhdq %%mm1, %%mm1 \n\t" // 7 6 5 4 7 6 5 4
- "movq %%mm0, (%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm1, 8(%%edi) \n\t"
- "subl $16, %%edi \n\t"
- "subl $2, %%ecx \n\t"
- "jnz .loop4_pass4 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width_mmx) // ecx
-
-#if 0 /* %mm0, %mm1 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0", "%mm1" // clobber list
-#endif
- );
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*8 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
- } /* end of pixel_bytes == 4 */
-
- //--------------------------------------------------------------
- else if (pixel_bytes == 8)
- {
-// GRR TEST: should work, but needs testing (special 64-bit version of rpng2?)
- // GRR NOTE: no need to combine passes here!
- if (((pass == 0) || (pass == 1)) && width)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- // source is 8-byte RRGGBBAA
- // dest is 64-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA ...
- __asm__ __volatile__ (
- "subl $56, %%edi \n\t" // start of last block
-
- ".loop8_pass0: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, (%%edi) \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "movq %%mm0, 16(%%edi) \n\t"
- "movq %%mm0, 24(%%edi) \n\t"
- "movq %%mm0, 32(%%edi) \n\t"
- "movq %%mm0, 40(%%edi) \n\t"
- "movq %%mm0, 48(%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm0, 56(%%edi) \n\t"
- "subl $64, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz .loop8_pass0 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width) // ecx
-
-#if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0" // clobber list
-#endif
- );
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- // source is 8-byte RRGGBBAA
- // dest is 32-byte RRGGBBAA RRGGBBAA RRGGBBAA RRGGBBAA
- // (recall that expansion is _in place_: sptr and dp
- // both point at locations within same row buffer)
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $24, %%edi \n\t" // start of last block
-
- ".loop8_pass2: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, (%%edi) \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "movq %%mm0, 16(%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm0, 24(%%edi) \n\t"
- "subl $32, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz .loop8_pass2 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width) // ecx
-
-#if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0" // clobber list
-#endif
- );
- }
- }
- else if (width) // pass == 4 or 5
- {
- // source is 8-byte RRGGBBAA
- // dest is 16-byte RRGGBBAA RRGGBBAA
- {
- int dummy_value_c; // fix 'forbidden register spilled'
- int dummy_value_S;
- int dummy_value_D;
-
- __asm__ __volatile__ (
- "subl $8, %%edi \n\t" // start of last block
-
- ".loop8_pass4: \n\t"
- "movq (%%esi), %%mm0 \n\t" // 7 6 5 4 3 2 1 0
- "movq %%mm0, (%%edi) \n\t"
- "subl $8, %%esi \n\t"
- "movq %%mm0, 8(%%edi) \n\t"
- "subl $16, %%edi \n\t"
- "decl %%ecx \n\t"
- "jnz .loop8_pass4 \n\t"
- "EMMS \n\t" // DONE
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "1" (sptr), // esi // input regs
- "2" (dp), // edi
- "0" (width) // ecx
-
-#if 0 /* %mm0 not supported by gcc 2.7.2.3 or egcs 1.1 */
- : "%mm0" // clobber list
-#endif
- );
- }
- }
-
- } /* end of pixel_bytes == 8 */
-
- //--------------------------------------------------------------
- else if (pixel_bytes == 6)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 6);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 6);
- dp -= 6;
- }
- sptr -= 6;
- }
- } /* end of pixel_bytes == 6 */
-
- //--------------------------------------------------------------
- else
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr-= pixel_bytes;
- }
- }
- } // end of _mmx_supported ========================================
-
- else /* MMX not supported: use modified C code - takes advantage
- * of inlining of png_memcpy for a constant */
- /* GRR 19991007: does it? or should pixel_bytes in each
- * block be replaced with immediate value (e.g., 1)? */
- /* GRR 19991017: replaced with constants in each case */
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- if (pixel_bytes == 1)
- {
- for (i = width; i; i--)
- {
- int j;
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- --sptr;
- }
- }
- else if (pixel_bytes == 3)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 3);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 3);
- dp -= 3;
- }
- sptr -= 3;
- }
- }
- else if (pixel_bytes == 2)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 2);
- dp -= 2;
- }
- sptr -= 2;
- }
- }
- else if (pixel_bytes == 4)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
-#ifdef PNG_DEBUG
- if (dp < row || dp+3 > row+png_ptr->row_buf_size)
- {
- printf("dp out of bounds: row=%d, dp=%d, rp=%d\n",
- row, dp, row+png_ptr->row_buf_size);
- printf("row_buf=%d\n",png_ptr->row_buf_size);
- }
-#endif
- png_memcpy(dp, v, 4);
- dp -= 4;
- }
- sptr -= 4;
- }
- }
- else if (pixel_bytes == 6)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 6);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 6);
- dp -= 6;
- }
- sptr -= 6;
- }
- }
- else if (pixel_bytes == 8)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 8);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 8);
- dp -= 8;
- }
- sptr -= 8;
- }
- }
- else /* GRR: should never be reached */
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
-
- } /* end if (MMX not supported) */
- break;
- }
- } /* end switch (row_info->pixel_depth) */
-
- row_info->width = final_width;
-
- row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width);
- }
-
-} /* end png_do_read_interlace() */
-
-#endif /* PNG_HAVE_MMX_READ_INTERLACE */
-#endif /* PNG_READ_INTERLACING_SUPPORTED */
-
-
-
-#if defined(PNG_HAVE_MMX_READ_FILTER_ROW)
-#if defined(PNG_MMX_CODE_SUPPORTED)
-
-// These variables are utilized in the functions below. They are declared
-// globally here to ensure alignment on 8-byte boundaries.
-
-union uAll {
- long long use;
- double align;
-} _LBCarryMask = {0x0101010101010101LL},
- _HBClearMask = {0x7f7f7f7f7f7f7f7fLL},
- _ActiveMask, _ActiveMask2, _ActiveMaskEnd, _ShiftBpp, _ShiftRem;
-
-#ifdef PNG_THREAD_UNSAFE_OK
-//===========================================================================//
-// //
-// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ A V G //
-// //
-//===========================================================================//
-
-// Optimized code for PNG Average filter decoder
-
-static void /* PRIVATE */
-png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row,
- png_bytep prev_row)
-{
- int bpp;
- int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error
- int dummy_value_S;
- int dummy_value_D;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // get # bytes per pixel
- _FullLength = row_info->rowbytes; // # of bytes to filter
-
- __asm__ __volatile__ (
- // initialize address pointers and offset
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save index to Global Offset Table
-#endif
-//pre "movl row, %%edi \n\t" // edi: Avg(x)
- "xorl %%ebx, %%ebx \n\t" // ebx: x
- "movl %%edi, %%edx \n\t"
-//pre "movl prev_row, %%esi \n\t" // esi: Prior(x)
-//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx)
- "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp)
-
- "xorl %%eax,%%eax \n\t"
-
- // Compute the Raw value for the first bpp bytes
- // Raw(x) = Avg(x) + (Prior(x)/2)
- "avg_rlp: \n\t"
- "movb (%%esi,%%ebx,),%%al \n\t" // load al with Prior(x)
- "incl %%ebx \n\t"
- "shrb %%al \n\t" // divide by 2
- "addb -1(%%edi,%%ebx,),%%al \n\t" // add Avg(x); -1 to offset inc ebx
-//pre "cmpl bpp, %%ebx \n\t" // (bpp is preloaded into ecx)
- "cmpl %%ecx, %%ebx \n\t"
- "movb %%al,-1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx
- "jb avg_rlp \n\t" // mov does not affect flags
-
- // get # of bytes to alignment
- "movl %%edi, _dif \n\t" // take start of row
- "addl %%ebx, _dif \n\t" // add bpp
- "addl $0xf, _dif \n\t" // add 7+8 to incr past alignment bdry
- "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary
- "subl %%edi, _dif \n\t" // subtract from start => value ebx at
- "jz avg_go \n\t" // alignment
-
- // fix alignment
- // Compute the Raw value for the bytes up to the alignment boundary
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- "xorl %%ecx, %%ecx \n\t"
-
- "avg_lp1: \n\t"
- "xorl %%eax, %%eax \n\t"
- "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x)
- "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp)
- "addw %%cx, %%ax \n\t"
- "incl %%ebx \n\t"
- "shrw %%ax \n\t" // divide by 2
- "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx
- "cmpl _dif, %%ebx \n\t" // check if at alignment boundary
- "movb %%al, -1(%%edi,%%ebx,) \n\t" // write Raw(x); -1 to offset inc ebx
- "jb avg_lp1 \n\t" // repeat until at alignment boundary
-
- "avg_go: \n\t"
- "movl _FullLength, %%eax \n\t"
- "movl %%eax, %%ecx \n\t"
- "subl %%ebx, %%eax \n\t" // subtract alignment fix
- "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8
- "subl %%eax, %%ecx \n\t" // drop over bytes from original length
- "movl %%ecx, _MMXLength \n\t"
-#ifdef __PIC__
- "popl %%ebx \n\t" // restore index to Global Offset Table
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list
-#ifndef __PIC__
- , "%ebx"
-#endif
- // GRR: INCLUDE "memory" as clobbered? (_dif, _MMXLength)
- // (seems to work fine without...)
- );
-
- // now do the math for the rest of the row
- switch (bpp)
- {
- case 3:
- {
- _ActiveMask.use = 0x0000000000ffffffLL;
- _ShiftBpp.use = 24; // == 3 * 8
- _ShiftRem.use = 40; // == 64 - 24
-
- __asm__ __volatile__ (
- // re-init address pointers and offset
- "movq _ActiveMask, %%mm7 \n\t"
- "movl _dif, %%ecx \n\t" // ecx: x = offset to
- "movq _LBCarryMask, %%mm5 \n\t" // alignment boundary
-// preload "movl row, %%edi \n\t" // edi: Avg(x)
- "movq _HBClearMask, %%mm4 \n\t"
-// preload "movl prev_row, %%esi \n\t" // esi: Prior(x)
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes
- // (correct pos. in loop below)
- "avg_3lp: \n\t"
- "movq (%%edi,%%ecx,), %%mm0 \n\t" // load mm0 with Avg(x)
- "movq %%mm5, %%mm3 \n\t"
- "psrlq _ShiftRem, %%mm2 \n\t" // correct position Raw(x-bpp)
- // data
- "movq (%%esi,%%ecx,), %%mm1 \n\t" // load mm1 with Prior(x)
- "movq %%mm7, %%mm6 \n\t"
- "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte
- "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2
- "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for
- // each byte
- // add 1st active group (Raw(x-bpp)/2) to average with LBCarry
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active
- // byte
- // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry
- "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover
- // bytes 3-5
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active
- // byte
-
- // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry
- "psllq _ShiftBpp, %%mm6 \n\t" // shift mm6 mask to cover last
- // two
- // bytes
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- // Data only needs to be shifted once here to
- // get the correct x-bpp offset.
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "addl $8, %%ecx \n\t"
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active
- // byte
- // now ready to write back to memory
- "movq %%mm0, -8(%%edi,%%ecx,) \n\t"
- // move updated Raw(x) to use as Raw(x-bpp) for next loop
- "cmpl _MMXLength, %%ecx \n\t"
- "movq %%mm0, %%mm2 \n\t" // mov updated Raw(x) to mm2
- "jb avg_3lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 3 bpp
-
- case 6:
- case 4:
- //case 7: // who wrote this? PNG doesn't support 5 or 7 bytes/pixel
- //case 5: // GRR BOGUS
- {
- _ActiveMask.use = 0xffffffffffffffffLL; // use shift below to clear
- // appropriate inactive bytes
- _ShiftBpp.use = bpp << 3;
- _ShiftRem.use = 64 - _ShiftBpp.use;
-
- __asm__ __volatile__ (
- "movq _HBClearMask, %%mm4 \n\t"
-
- // re-init address pointers and offset
- "movl _dif, %%ecx \n\t" // ecx: x = offset to
- // alignment boundary
-
- // load _ActiveMask and clear all bytes except for 1st active group
- "movq _ActiveMask, %%mm7 \n\t"
-// preload "movl row, %%edi \n\t" // edi: Avg(x)
- "psrlq _ShiftRem, %%mm7 \n\t"
-// preload "movl prev_row, %%esi \n\t" // esi: Prior(x)
- "movq %%mm7, %%mm6 \n\t"
- "movq _LBCarryMask, %%mm5 \n\t"
- "psllq _ShiftBpp, %%mm6 \n\t" // create mask for 2nd active
- // group
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes
- // (we correct pos. in loop below)
- "avg_4lp: \n\t"
- "movq (%%edi,%%ecx,), %%mm0 \n\t"
- "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly
- "movq (%%esi,%%ecx,), %%mm1 \n\t"
- // add (Prev_row/2) to average
- "movq %%mm5, %%mm3 \n\t"
- "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte
- "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2
- "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for
- // each byte
- // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm7, %%mm2 \n\t" // leave only Active Group 1
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg
- // for each Active
- // byte
- // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- "addl $8, %%ecx \n\t"
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active
- // byte
- "cmpl _MMXLength, %%ecx \n\t"
- // now ready to write back to memory
- "movq %%mm0, -8(%%edi,%%ecx,) \n\t"
- // prep Raw(x-bpp) for next loop
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "jb avg_4lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 4,6 bpp
-
- case 2:
- {
- _ActiveMask.use = 0x000000000000ffffLL;
- _ShiftBpp.use = 16; // == 2 * 8
- _ShiftRem.use = 48; // == 64 - 16
-
- __asm__ __volatile__ (
- // load _ActiveMask
- "movq _ActiveMask, %%mm7 \n\t"
- // re-init address pointers and offset
- "movl _dif, %%ecx \n\t" // ecx: x = offset to alignment
- // boundary
- "movq _LBCarryMask, %%mm5 \n\t"
-// preload "movl row, %%edi \n\t" // edi: Avg(x)
- "movq _HBClearMask, %%mm4 \n\t"
-// preload "movl prev_row, %%esi \n\t" // esi: Prior(x)
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes
- // (we correct pos. in loop below)
- "avg_2lp: \n\t"
- "movq (%%edi,%%ecx,), %%mm0 \n\t"
- "psrlq _ShiftRem, %%mm2 \n\t" // shift data to pos. correctly
- "movq (%%esi,%%ecx,), %%mm1 \n\t" // (GRR BUGFIX: was psllq)
- // add (Prev_row/2) to average
- "movq %%mm5, %%mm3 \n\t"
- "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte
- "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2
- "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each
- // byte
- "movq %%mm7, %%mm6 \n\t"
- "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for
- // each byte
-
- // add 1st active group (Raw(x-bpp)/2) to average with _LBCarry
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid
- // for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 1
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to Avg
- // for each Active byte
-
- // add 2nd active group (Raw(x-bpp)/2) to average with _LBCarry
- "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover
- // bytes 2 & 3
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid
- // for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active byte
-
- // add 3rd active group (Raw(x-bpp)/2) to average with _LBCarry
- "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover
- // bytes 4 & 5
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both lsb's were == 1
- // (only valid for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active byte
-
- // add 4th active group (Raw(x-bpp)/2) to average with _LBCarry
- "psllq _ShiftBpp, %%mm6 \n\t" // shift the mm6 mask to cover
- // bytes 6 & 7
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "psllq _ShiftBpp, %%mm2 \n\t" // shift data to pos. correctly
- "addl $8, %%ecx \n\t"
- "movq %%mm3, %%mm1 \n\t" // now use mm1 for getting
- // LBCarrys
- "pand %%mm2, %%mm1 \n\t" // get LBCarrys for each byte
- // where both
- // lsb's were == 1 (only valid
- // for active group)
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm2 \n\t" // add LBCarrys to (Raw(x-bpp)/2)
- // for each byte
- "pand %%mm6, %%mm2 \n\t" // leave only Active Group 2
- // bytes to add to Avg
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) + LBCarrys to
- // Avg for each Active byte
-
- "cmpl _MMXLength, %%ecx \n\t"
- // now ready to write back to memory
- "movq %%mm0, -8(%%edi,%%ecx,) \n\t"
- // prep Raw(x-bpp) for next loop
- "movq %%mm0, %%mm2 \n\t" // mov updated Raws to mm2
- "jb avg_2lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 2 bpp
-
- case 1:
- {
- __asm__ __volatile__ (
- // re-init address pointers and offset
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save Global Offset Table index
-#endif
- "movl _dif, %%ebx \n\t" // ebx: x = offset to alignment
- // boundary
-// preload "movl row, %%edi \n\t" // edi: Avg(x)
- "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array
- "jnb avg_1end \n\t"
- // do Paeth decode for remaining bytes
-// preload "movl prev_row, %%esi \n\t" // esi: Prior(x)
- "movl %%edi, %%edx \n\t"
-// preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx)
- "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp)
- "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx
- // in loop below
- "avg_1lp: \n\t"
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- "xorl %%eax, %%eax \n\t"
- "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x)
- "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp)
- "addw %%cx, %%ax \n\t"
- "incl %%ebx \n\t"
- "shrw %%ax \n\t" // divide by 2
- "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset
- // inc ebx
- "cmpl _FullLength, %%ebx \n\t" // check if at end of array
- "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x);
- // mov does not affect flags; -1 to offset inc ebx
- "jb avg_1lp \n\t"
-
- "avg_1end: \n\t"
-#ifdef __PIC__
- "popl %%ebx \n\t" // Global Offset Table index
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list
-#ifndef __PIC__
- , "%ebx"
-#endif
- );
- }
- return; // end 1 bpp
-
- case 8:
- {
- __asm__ __volatile__ (
- // re-init address pointers and offset
- "movl _dif, %%ecx \n\t" // ecx: x == offset to alignment
- "movq _LBCarryMask, %%mm5 \n\t" // boundary
-// preload "movl row, %%edi \n\t" // edi: Avg(x)
- "movq _HBClearMask, %%mm4 \n\t"
-// preload "movl prev_row, %%esi \n\t" // esi: Prior(x)
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm2 \n\t" // load previous aligned 8 bytes
- // (NO NEED to correct pos. in loop below)
-
- "avg_8lp: \n\t"
- "movq (%%edi,%%ecx,), %%mm0 \n\t"
- "movq %%mm5, %%mm3 \n\t"
- "movq (%%esi,%%ecx,), %%mm1 \n\t"
- "addl $8, %%ecx \n\t"
- "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte
- "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2
- "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte
- // where both lsb's were == 1
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7, each byte
- "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg, each byte
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7, each byte
- "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg, each
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each
- "cmpl _MMXLength, %%ecx \n\t"
- "movq %%mm0, -8(%%edi,%%ecx,) \n\t"
- "movq %%mm0, %%mm2 \n\t" // reuse as Raw(x-bpp)
- "jb avg_8lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm5 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2"
- , "%mm3", "%mm4", "%mm5"
-#endif
- );
- }
- break; // end 8 bpp
-
- default: // bpp greater than 8 (!= 1,2,3,4,[5],6,[7],8)
- {
-
-#ifdef PNG_DEBUG
- // GRR: PRINT ERROR HERE: SHOULD NEVER BE REACHED
- png_debug(1,
- "Internal logic error in pnggccrd (png_read_filter_row_mmx_avg())\n");
-#endif
-
-#if 0
- __asm__ __volatile__ (
- "movq _LBCarryMask, %%mm5 \n\t"
- // re-init address pointers and offset
- "movl _dif, %%ebx \n\t" // ebx: x = offset to
- // alignment boundary
- "movl row, %%edi \n\t" // edi: Avg(x)
- "movq _HBClearMask, %%mm4 \n\t"
- "movl %%edi, %%edx \n\t"
- "movl prev_row, %%esi \n\t" // esi: Prior(x)
- "subl bpp, %%edx \n\t" // edx: Raw(x-bpp)
- "avg_Alp: \n\t"
- "movq (%%edi,%%ebx,), %%mm0 \n\t"
- "movq %%mm5, %%mm3 \n\t"
- "movq (%%esi,%%ebx,), %%mm1 \n\t"
- "pand %%mm1, %%mm3 \n\t" // get lsb for each prev_row byte
- "movq (%%edx,%%ebx,), %%mm2 \n\t"
- "psrlq $1, %%mm1 \n\t" // divide prev_row bytes by 2
- "pand %%mm2, %%mm3 \n\t" // get LBCarrys for each byte
- // where both lsb's were == 1
- "psrlq $1, %%mm2 \n\t" // divide raw bytes by 2
- "pand %%mm4, %%mm1 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm3, %%mm0 \n\t" // add LBCarrys to Avg for each
- // byte
- "pand %%mm4, %%mm2 \n\t" // clear invalid bit 7 of each
- // byte
- "paddb %%mm1, %%mm0 \n\t" // add (Prev_row/2) to Avg for
- // each byte
- "addl $8, %%ebx \n\t"
- "paddb %%mm2, %%mm0 \n\t" // add (Raw/2) to Avg for each
- // byte
- "cmpl _MMXLength, %%ebx \n\t"
- "movq %%mm0, -8(%%edi,%%ebx,) \n\t"
- "jb avg_Alp \n\t"
-
- : // FIXASM: output regs/vars go here, e.g.: "=m" (memory_var)
-
- : // FIXASM: input regs, e.g.: "c" (count), "S" (src), "D" (dest)
-
- : "%ebx", "%edx", "%edi", "%esi" // CHECKASM: clobber list
- );
-#endif /* 0 - NEVER REACHED */
- }
- break;
-
- } // end switch (bpp)
-
- __asm__ __volatile__ (
- // MMX acceleration complete; now do clean-up
- // check if any remaining bytes left to decode
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save index to Global Offset Table
-#endif
- "movl _MMXLength, %%ebx \n\t" // ebx: x == offset bytes after MMX
-//pre "movl row, %%edi \n\t" // edi: Avg(x)
- "cmpl _FullLength, %%ebx \n\t" // test if offset at end of array
- "jnb avg_end \n\t"
-
- // do Avg decode for remaining bytes
-//pre "movl prev_row, %%esi \n\t" // esi: Prior(x)
- "movl %%edi, %%edx \n\t"
-//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx)
- "subl %%ecx, %%edx \n\t" // edx: Raw(x-bpp)
- "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below
-
- "avg_lp2: \n\t"
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- "xorl %%eax, %%eax \n\t"
- "movb (%%esi,%%ebx,), %%cl \n\t" // load cl with Prior(x)
- "movb (%%edx,%%ebx,), %%al \n\t" // load al with Raw(x-bpp)
- "addw %%cx, %%ax \n\t"
- "incl %%ebx \n\t"
- "shrw %%ax \n\t" // divide by 2
- "addb -1(%%edi,%%ebx,), %%al \n\t" // add Avg(x); -1 to offset inc ebx
- "cmpl _FullLength, %%ebx \n\t" // check if at end of array
- "movb %%al, -1(%%edi,%%ebx,) \n\t" // write back Raw(x) [mov does not
- "jb avg_lp2 \n\t" // affect flags; -1 to offset inc ebx]
-
- "avg_end: \n\t"
- "EMMS \n\t" // end MMX; prep for poss. FP instrs.
-#ifdef __PIC__
- "popl %%ebx \n\t" // restore index to Global Offset Table
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list
-#ifndef __PIC__
- , "%ebx"
-#endif
- );
-
-} /* end png_read_filter_row_mmx_avg() */
-#endif
-
-
-
-#ifdef PNG_THREAD_UNSAFE_OK
-//===========================================================================//
-// //
-// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ P A E T H //
-// //
-//===========================================================================//
-
-// Optimized code for PNG Paeth filter decoder
-
-static void /* PRIVATE */
-png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row,
- png_bytep prev_row)
-{
- int bpp;
- int dummy_value_c; // fix 'forbidden register 2 (cx) was spilled' error
- int dummy_value_S;
- int dummy_value_D;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel
- _FullLength = row_info->rowbytes; // # of bytes to filter
-
- __asm__ __volatile__ (
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save index to Global Offset Table
-#endif
- "xorl %%ebx, %%ebx \n\t" // ebx: x offset
-//pre "movl row, %%edi \n\t"
- "xorl %%edx, %%edx \n\t" // edx: x-bpp offset
-//pre "movl prev_row, %%esi \n\t"
- "xorl %%eax, %%eax \n\t"
-
- // Compute the Raw value for the first bpp bytes
- // Note: the formula works out to be always
- // Paeth(x) = Raw(x) + Prior(x) where x < bpp
- "paeth_rlp: \n\t"
- "movb (%%edi,%%ebx,), %%al \n\t"
- "addb (%%esi,%%ebx,), %%al \n\t"
- "incl %%ebx \n\t"
-//pre "cmpl bpp, %%ebx \n\t" (bpp is preloaded into ecx)
- "cmpl %%ecx, %%ebx \n\t"
- "movb %%al, -1(%%edi,%%ebx,) \n\t"
- "jb paeth_rlp \n\t"
- // get # of bytes to alignment
- "movl %%edi, _dif \n\t" // take start of row
- "addl %%ebx, _dif \n\t" // add bpp
- "xorl %%ecx, %%ecx \n\t"
- "addl $0xf, _dif \n\t" // add 7 + 8 to incr past alignment
- // boundary
- "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary
- "subl %%edi, _dif \n\t" // subtract from start ==> value ebx
- // at alignment
- "jz paeth_go \n\t"
- // fix alignment
-
- "paeth_lp1: \n\t"
- "xorl %%eax, %%eax \n\t"
- // pav = p - a = (a + b - c) - a = b - c
- "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, _patemp \n\t" // Save pav for later use
- "xorl %%eax, %%eax \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, %%ecx \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "addl _patemp, %%eax \n\t" // pcv = pav + pbv
- // pc = abs(pcv)
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_pca \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_pca: \n\t"
- "movl %%eax, _pctemp \n\t" // save pc for later use
- // pb = abs(pbv)
- "testl $0x80000000, %%ecx \n\t"
- "jz paeth_pba \n\t"
- "negl %%ecx \n\t" // reverse sign of neg values
-
- "paeth_pba: \n\t"
- "movl %%ecx, _pbtemp \n\t" // save pb for later use
- // pa = abs(pav)
- "movl _patemp, %%eax \n\t"
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_paa \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_paa: \n\t"
- "movl %%eax, _patemp \n\t" // save pa for later use
- // test if pa <= pb
- "cmpl %%ecx, %%eax \n\t"
- "jna paeth_abb \n\t"
- // pa > pb; now test if pb <= pc
- "cmpl _pctemp, %%ecx \n\t"
- "jna paeth_bbc \n\t"
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_paeth \n\t"
-
- "paeth_bbc: \n\t"
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl
- "jmp paeth_paeth \n\t"
-
- "paeth_abb: \n\t"
- // pa <= pb; now test if pa <= pc
- "cmpl _pctemp, %%eax \n\t"
- "jna paeth_abc \n\t"
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_paeth \n\t"
-
- "paeth_abc: \n\t"
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl
-
- "paeth_paeth: \n\t"
- "incl %%ebx \n\t"
- "incl %%edx \n\t"
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- "addb %%cl, -1(%%edi,%%ebx,) \n\t"
- "cmpl _dif, %%ebx \n\t"
- "jb paeth_lp1 \n\t"
-
- "paeth_go: \n\t"
- "movl _FullLength, %%ecx \n\t"
- "movl %%ecx, %%eax \n\t"
- "subl %%ebx, %%eax \n\t" // subtract alignment fix
- "andl $0x00000007, %%eax \n\t" // calc bytes over mult of 8
- "subl %%eax, %%ecx \n\t" // drop over bytes from original length
- "movl %%ecx, _MMXLength \n\t"
-#ifdef __PIC__
- "popl %%ebx \n\t" // restore index to Global Offset Table
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list
-#ifndef __PIC__
- , "%ebx"
-#endif
- );
-
- // now do the math for the rest of the row
- switch (bpp)
- {
- case 3:
- {
- _ActiveMask.use = 0x0000000000ffffffLL;
- _ActiveMaskEnd.use = 0xffff000000000000LL;
- _ShiftBpp.use = 24; // == bpp(3) * 8
- _ShiftRem.use = 40; // == 64 - 24
-
- __asm__ __volatile__ (
- "movl _dif, %%ecx \n\t"
-// preload "movl row, %%edi \n\t"
-// preload "movl prev_row, %%esi \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t"
- "paeth_3lp: \n\t"
- "psrlq _ShiftRem, %%mm1 \n\t" // shift last 3 bytes to 1st
- // 3 bytes
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // prep c=Prior(x-bpp) bytes
- "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- "psrlq _ShiftRem, %%mm3 \n\t" // shift last 3 bytes to 1st
- // 3 bytes
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "packuswb %%mm1, %%mm7 \n\t"
- "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp)
- "pand _ActiveMask, %%mm7 \n\t"
- "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1
- "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x)
- "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value
- "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as
- // Raw(x-bpp)
- // now do Paeth for 2nd set of bytes (3-5)
- "psrlq _ShiftBpp, %%mm2 \n\t" // load b=Prior(x) step 2
- "punpcklbw %%mm0, %%mm1 \n\t" // unpack High bytes of a
- "pxor %%mm7, %%mm7 \n\t"
- "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) =
- // pav + pbv = pbv + pav
- "movq %%mm5, %%mm6 \n\t"
- "paddw %%mm4, %%mm6 \n\t"
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm5, %%mm0 \n\t" // create mask pbv bytes < 0
- "pcmpgtw %%mm4, %%mm7 \n\t" // create mask pav bytes < 0
- "pand %%mm5, %%mm0 \n\t" // only pbv bytes < 0 in mm0
- "pand %%mm4, %%mm7 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm0, %%mm5 \n\t"
- "psubw %%mm7, %%mm4 \n\t"
- "psubw %%mm0, %%mm5 \n\t"
- "psubw %%mm7, %%mm4 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "pxor %%mm1, %%mm1 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "packuswb %%mm1, %%mm7 \n\t"
- "movq %%mm2, %%mm3 \n\t" // load c=Prior(x-bpp) step 1
- "pand _ActiveMask, %%mm7 \n\t"
- "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- "psllq _ShiftBpp, %%mm7 \n\t" // shift bytes to 2nd group of
- // 3 bytes
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x)
- "psllq _ShiftBpp, %%mm3 \n\t" // load c=Prior(x-bpp) step 2
- "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value
- "movq %%mm7, %%mm1 \n\t"
- "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- "psllq _ShiftBpp, %%mm1 \n\t" // shift bytes
- // now mm1 will be used as Raw(x-bpp)
- // now do Paeth for 3rd, and final, set of bytes (6-7)
- "pxor %%mm7, %%mm7 \n\t"
- "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a
- "psubw %%mm3, %%mm4 \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "paddw %%mm5, %%mm6 \n\t"
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm1, %%mm1 \n\t"
- "packuswb %%mm7, %%mm1 \n\t"
- // step ecx to next set of 8 bytes and repeat loop til done
- "addl $8, %%ecx \n\t"
- "pand _ActiveMaskEnd, %%mm1 \n\t"
- "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with
- // Raw(x)
-
- "cmpl _MMXLength, %%ecx \n\t"
- "pxor %%mm0, %%mm0 \n\t" // pxor does not affect flags
- "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- // mm3 ready to be used as Prior(x-bpp) next loop
- "jb paeth_3lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 3 bpp
-
- case 6:
- //case 7: // GRR BOGUS
- //case 5: // GRR BOGUS
- {
- _ActiveMask.use = 0x00000000ffffffffLL;
- _ActiveMask2.use = 0xffffffff00000000LL;
- _ShiftBpp.use = bpp << 3; // == bpp * 8
- _ShiftRem.use = 64 - _ShiftBpp.use;
-
- __asm__ __volatile__ (
- "movl _dif, %%ecx \n\t"
-// preload "movl row, %%edi \n\t"
-// preload "movl prev_row, %%esi \n\t"
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
-
- "paeth_6lp: \n\t"
- // must shift to position Raw(x-bpp) data
- "psrlq _ShiftRem, %%mm1 \n\t"
- // do first set of 4 bytes
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes
- "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b
- // must shift to position Prior(x-bpp) data
- "psrlq _ShiftRem, %%mm3 \n\t"
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "packuswb %%mm1, %%mm7 \n\t"
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp)
- "pand _ActiveMask, %%mm7 \n\t"
- "psrlq _ShiftRem, %%mm3 \n\t"
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x) step 1
- "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor and Raw(x)
- "movq %%mm2, %%mm6 \n\t"
- "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t"
- "psllq _ShiftBpp, %%mm6 \n\t"
- "movq %%mm7, %%mm5 \n\t"
- "psrlq _ShiftRem, %%mm1 \n\t"
- "por %%mm6, %%mm3 \n\t"
- "psllq _ShiftBpp, %%mm5 \n\t"
- "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- "por %%mm5, %%mm1 \n\t"
- // do second set of 4 bytes
- "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "pxor %%mm1, %%mm1 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // step ecx to next set of 8 bytes and repeat loop til done
- "addl $8, %%ecx \n\t"
- "packuswb %%mm7, %%mm1 \n\t"
- "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x)
- "cmpl _MMXLength, %%ecx \n\t"
- "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- "jb paeth_6lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 6 bpp
-
- case 4:
- {
- _ActiveMask.use = 0x00000000ffffffffLL;
-
- __asm__ __volatile__ (
- "movl _dif, %%ecx \n\t"
-// preload "movl row, %%edi \n\t"
-// preload "movl prev_row, %%esi \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read
- // a=Raw(x-bpp) bytes
- "paeth_4lp: \n\t"
- // do first set of 4 bytes
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes
- "punpckhbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "punpcklbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "packuswb %%mm1, %%mm7 \n\t"
- "movq (%%esi,%%ecx,), %%mm3 \n\t" // load c=Prior(x-bpp)
- "pand _ActiveMask, %%mm7 \n\t"
- "movq %%mm3, %%mm2 \n\t" // load b=Prior(x) step 1
- "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x)
- "punpcklbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value
- "movq %%mm7, %%mm1 \n\t" // now mm1 will be used as Raw(x-bpp)
- // do second set of 4 bytes
- "punpckhbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b
- "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "pxor %%mm1, %%mm1 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // step ecx to next set of 8 bytes and repeat loop til done
- "addl $8, %%ecx \n\t"
- "packuswb %%mm7, %%mm1 \n\t"
- "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add predictor with Raw(x)
- "cmpl _MMXLength, %%ecx \n\t"
- "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- "jb paeth_4lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 4 bpp
-
- case 8: // bpp == 8
- {
- _ActiveMask.use = 0x00000000ffffffffLL;
-
- __asm__ __volatile__ (
- "movl _dif, %%ecx \n\t"
-// preload "movl row, %%edi \n\t"
-// preload "movl prev_row, %%esi \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // only time should need to read
- // a=Raw(x-bpp) bytes
- "paeth_8lp: \n\t"
- // do first set of 4 bytes
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes
- "punpcklbw %%mm0, %%mm1 \n\t" // unpack Low bytes of a
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "punpcklbw %%mm0, %%mm2 \n\t" // unpack Low bytes of b
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- "punpcklbw %%mm0, %%mm3 \n\t" // unpack Low bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "packuswb %%mm1, %%mm7 \n\t"
- "movq -8(%%esi,%%ecx,), %%mm3 \n\t" // read c=Prior(x-bpp) bytes
- "pand _ActiveMask, %%mm7 \n\t"
- "movq (%%esi,%%ecx,), %%mm2 \n\t" // load b=Prior(x)
- "paddb (%%edi,%%ecx,), %%mm7 \n\t" // add Paeth predictor with Raw(x)
- "punpckhbw %%mm0, %%mm3 \n\t" // unpack High bytes of c
- "movq %%mm7, (%%edi,%%ecx,) \n\t" // write back updated value
- "movq -8(%%edi,%%ecx,), %%mm1 \n\t" // read a=Raw(x-bpp) bytes
-
- // do second set of 4 bytes
- "punpckhbw %%mm0, %%mm2 \n\t" // unpack High bytes of b
- "punpckhbw %%mm0, %%mm1 \n\t" // unpack High bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- "movq %%mm2, %%mm4 \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movq %%mm1, %%mm5 \n\t"
- "psubw %%mm3, %%mm4 \n\t"
- "pxor %%mm7, %%mm7 \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "movq %%mm4, %%mm6 \n\t"
- "psubw %%mm3, %%mm5 \n\t"
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- "pcmpgtw %%mm4, %%mm0 \n\t" // create mask pav bytes < 0
- "paddw %%mm5, %%mm6 \n\t"
- "pand %%mm4, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "pcmpgtw %%mm5, %%mm7 \n\t" // create mask pbv bytes < 0
- "psubw %%mm0, %%mm4 \n\t"
- "pand %%mm5, %%mm7 \n\t" // only pbv bytes < 0 in mm0
- "psubw %%mm0, %%mm4 \n\t"
- "psubw %%mm7, %%mm5 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- "pcmpgtw %%mm6, %%mm0 \n\t" // create mask pcv bytes < 0
- "pand %%mm6, %%mm0 \n\t" // only pav bytes < 0 in mm7
- "psubw %%mm7, %%mm5 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- // test pa <= pb
- "movq %%mm4, %%mm7 \n\t"
- "psubw %%mm0, %%mm6 \n\t"
- "pcmpgtw %%mm5, %%mm7 \n\t" // pa > pb?
- "movq %%mm7, %%mm0 \n\t"
- // use mm7 mask to merge pa & pb
- "pand %%mm7, %%mm5 \n\t"
- // use mm0 mask copy to merge a & b
- "pand %%mm0, %%mm2 \n\t"
- "pandn %%mm4, %%mm7 \n\t"
- "pandn %%mm1, %%mm0 \n\t"
- "paddw %%mm5, %%mm7 \n\t"
- "paddw %%mm2, %%mm0 \n\t"
- // test ((pa <= pb)? pa:pb) <= pc
- "pcmpgtw %%mm6, %%mm7 \n\t" // pab > pc?
- "pxor %%mm1, %%mm1 \n\t"
- "pand %%mm7, %%mm3 \n\t"
- "pandn %%mm0, %%mm7 \n\t"
- "pxor %%mm1, %%mm1 \n\t"
- "paddw %%mm3, %%mm7 \n\t"
- "pxor %%mm0, %%mm0 \n\t"
- // step ecx to next set of 8 bytes and repeat loop til done
- "addl $8, %%ecx \n\t"
- "packuswb %%mm7, %%mm1 \n\t"
- "paddb -8(%%edi,%%ecx,), %%mm1 \n\t" // add Paeth predictor with Raw(x)
- "cmpl _MMXLength, %%ecx \n\t"
- "movq %%mm1, -8(%%edi,%%ecx,) \n\t" // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- "jb paeth_8lp \n\t"
-
- : "=S" (dummy_value_S), // output regs (dummy)
- "=D" (dummy_value_D)
-
- : "0" (prev_row), // esi // input regs
- "1" (row) // edi
-
- : "%ecx" // clobber list
-#if 0 /* %mm0, ..., %mm7 not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break; // end 8 bpp
-
- case 1: // bpp = 1
- case 2: // bpp = 2
- default: // bpp > 8
- {
- __asm__ __volatile__ (
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save Global Offset Table index
-#endif
- "movl _dif, %%ebx \n\t"
- "cmpl _FullLength, %%ebx \n\t"
- "jnb paeth_dend \n\t"
-
-// preload "movl row, %%edi \n\t"
-// preload "movl prev_row, %%esi \n\t"
- // do Paeth decode for remaining bytes
- "movl %%ebx, %%edx \n\t"
-// preload "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx)
- "subl %%ecx, %%edx \n\t" // edx = ebx - bpp
- "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx
-
- "paeth_dlp: \n\t"
- "xorl %%eax, %%eax \n\t"
- // pav = p - a = (a + b - c) - a = b - c
- "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, _patemp \n\t" // Save pav for later use
- "xorl %%eax, %%eax \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, %%ecx \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "addl _patemp, %%eax \n\t" // pcv = pav + pbv
- // pc = abs(pcv)
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_dpca \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_dpca: \n\t"
- "movl %%eax, _pctemp \n\t" // save pc for later use
- // pb = abs(pbv)
- "testl $0x80000000, %%ecx \n\t"
- "jz paeth_dpba \n\t"
- "negl %%ecx \n\t" // reverse sign of neg values
-
- "paeth_dpba: \n\t"
- "movl %%ecx, _pbtemp \n\t" // save pb for later use
- // pa = abs(pav)
- "movl _patemp, %%eax \n\t"
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_dpaa \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_dpaa: \n\t"
- "movl %%eax, _patemp \n\t" // save pa for later use
- // test if pa <= pb
- "cmpl %%ecx, %%eax \n\t"
- "jna paeth_dabb \n\t"
- // pa > pb; now test if pb <= pc
- "cmpl _pctemp, %%ecx \n\t"
- "jna paeth_dbbc \n\t"
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_dpaeth \n\t"
-
- "paeth_dbbc: \n\t"
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl
- "jmp paeth_dpaeth \n\t"
-
- "paeth_dabb: \n\t"
- // pa <= pb; now test if pa <= pc
- "cmpl _pctemp, %%eax \n\t"
- "jna paeth_dabc \n\t"
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_dpaeth \n\t"
-
- "paeth_dabc: \n\t"
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl
-
- "paeth_dpaeth: \n\t"
- "incl %%ebx \n\t"
- "incl %%edx \n\t"
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- "addb %%cl, -1(%%edi,%%ebx,) \n\t"
- "cmpl _FullLength, %%ebx \n\t"
- "jb paeth_dlp \n\t"
-
- "paeth_dend: \n\t"
-#ifdef __PIC__
- "popl %%ebx \n\t" // index to Global Offset Table
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list
-#ifndef __PIC__
- , "%ebx"
-#endif
- );
- }
- return; // No need to go further with this one
-
- } // end switch (bpp)
-
- __asm__ __volatile__ (
- // MMX acceleration complete; now do clean-up
- // check if any remaining bytes left to decode
-#ifdef __PIC__
- "pushl %%ebx \n\t" // save index to Global Offset Table
-#endif
- "movl _MMXLength, %%ebx \n\t"
- "cmpl _FullLength, %%ebx \n\t"
- "jnb paeth_end \n\t"
-//pre "movl row, %%edi \n\t"
-//pre "movl prev_row, %%esi \n\t"
- // do Paeth decode for remaining bytes
- "movl %%ebx, %%edx \n\t"
-//pre "subl bpp, %%edx \n\t" // (bpp is preloaded into ecx)
- "subl %%ecx, %%edx \n\t" // edx = ebx - bpp
- "xorl %%ecx, %%ecx \n\t" // zero ecx before using cl & cx below
-
- "paeth_lp2: \n\t"
- "xorl %%eax, %%eax \n\t"
- // pav = p - a = (a + b - c) - a = b - c
- "movb (%%esi,%%ebx,), %%al \n\t" // load Prior(x) into al
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, _patemp \n\t" // Save pav for later use
- "xorl %%eax, %%eax \n\t"
- // pbv = p - b = (a + b - c) - b = a - c
- "movb (%%edi,%%edx,), %%al \n\t" // load Raw(x-bpp) into al
- "subl %%ecx, %%eax \n\t" // subtract Prior(x-bpp)
- "movl %%eax, %%ecx \n\t"
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- "addl _patemp, %%eax \n\t" // pcv = pav + pbv
- // pc = abs(pcv)
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_pca2 \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_pca2: \n\t"
- "movl %%eax, _pctemp \n\t" // save pc for later use
- // pb = abs(pbv)
- "testl $0x80000000, %%ecx \n\t"
- "jz paeth_pba2 \n\t"
- "negl %%ecx \n\t" // reverse sign of neg values
-
- "paeth_pba2: \n\t"
- "movl %%ecx, _pbtemp \n\t" // save pb for later use
- // pa = abs(pav)
- "movl _patemp, %%eax \n\t"
- "testl $0x80000000, %%eax \n\t"
- "jz paeth_paa2 \n\t"
- "negl %%eax \n\t" // reverse sign of neg values
-
- "paeth_paa2: \n\t"
- "movl %%eax, _patemp \n\t" // save pa for later use
- // test if pa <= pb
- "cmpl %%ecx, %%eax \n\t"
- "jna paeth_abb2 \n\t"
- // pa > pb; now test if pb <= pc
- "cmpl _pctemp, %%ecx \n\t"
- "jna paeth_bbc2 \n\t"
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_paeth2 \n\t"
-
- "paeth_bbc2: \n\t"
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- "movb (%%esi,%%ebx,), %%cl \n\t" // load Prior(x) into cl
- "jmp paeth_paeth2 \n\t"
-
- "paeth_abb2: \n\t"
- // pa <= pb; now test if pa <= pc
- "cmpl _pctemp, %%eax \n\t"
- "jna paeth_abc2 \n\t"
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- "movb (%%esi,%%edx,), %%cl \n\t" // load Prior(x-bpp) into cl
- "jmp paeth_paeth2 \n\t"
-
- "paeth_abc2: \n\t"
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- "movb (%%edi,%%edx,), %%cl \n\t" // load Raw(x-bpp) into cl
-
- "paeth_paeth2: \n\t"
- "incl %%ebx \n\t"
- "incl %%edx \n\t"
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- "addb %%cl, -1(%%edi,%%ebx,) \n\t"
- "cmpl _FullLength, %%ebx \n\t"
- "jb paeth_lp2 \n\t"
-
- "paeth_end: \n\t"
- "EMMS \n\t" // end MMX; prep for poss. FP instrs.
-#ifdef __PIC__
- "popl %%ebx \n\t" // restore index to Global Offset Table
-#endif
-
- : "=c" (dummy_value_c), // output regs (dummy)
- "=S" (dummy_value_S),
- "=D" (dummy_value_D)
-
- : "0" (bpp), // ecx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%edx" // clobber list (no input regs!)
-#ifndef __PIC__
- , "%ebx"
-#endif
- );
-
-} /* end png_read_filter_row_mmx_paeth() */
-#endif
-
-
-
-
-#ifdef PNG_THREAD_UNSAFE_OK
-//===========================================================================//
-// //
-// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ S U B //
-// //
-//===========================================================================//
-
-// Optimized code for PNG Sub filter decoder
-
-static void /* PRIVATE */
-png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row)
-{
- int bpp;
- int dummy_value_a;
- int dummy_value_D;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // calc number of bytes per pixel
- _FullLength = row_info->rowbytes - bpp; // number of bytes to filter
-
- __asm__ __volatile__ (
-//pre "movl row, %%edi \n\t"
- "movl %%edi, %%esi \n\t" // lp = row
-//pre "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
-//irr "xorl %%eax, %%eax \n\t"
- // get # of bytes to alignment
- "movl %%edi, _dif \n\t" // take start of row
- "addl $0xf, _dif \n\t" // add 7 + 8 to incr past
- // alignment boundary
- "xorl %%ecx, %%ecx \n\t"
- "andl $0xfffffff8, _dif \n\t" // mask to alignment boundary
- "subl %%edi, _dif \n\t" // subtract from start ==> value
- "jz sub_go \n\t" // ecx at alignment
-
- "sub_lp1: \n\t" // fix alignment
- "movb (%%esi,%%ecx,), %%al \n\t"
- "addb %%al, (%%edi,%%ecx,) \n\t"
- "incl %%ecx \n\t"
- "cmpl _dif, %%ecx \n\t"
- "jb sub_lp1 \n\t"
-
- "sub_go: \n\t"
- "movl _FullLength, %%eax \n\t"
- "movl %%eax, %%edx \n\t"
- "subl %%ecx, %%edx \n\t" // subtract alignment fix
- "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8
- "subl %%edx, %%eax \n\t" // drop over bytes from length
- "movl %%eax, _MMXLength \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%esi", "%ecx", "%edx" // clobber list
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
-
- // now do the math for the rest of the row
- switch (bpp)
- {
- case 3:
- {
- _ActiveMask.use = 0x0000ffffff000000LL;
- _ShiftBpp.use = 24; // == 3 * 8
- _ShiftRem.use = 40; // == 64 - 24
-
- __asm__ __volatile__ (
-// preload "movl row, %%edi \n\t"
- "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd
- // active byte group
- "movl %%edi, %%esi \n\t" // lp = row
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
- "movq %%mm7, %%mm6 \n\t"
- "movl _dif, %%edx \n\t"
- "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover
- // 3rd active byte group
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%edx,), %%mm1 \n\t"
-
- "sub_3lp: \n\t" // shift data for adding first
- "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask;
- // shift clears inactive bytes)
- // add 1st active group
- "movq (%%edi,%%edx,), %%mm0 \n\t"
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 2nd active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 3rd active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group
- "addl $8, %%edx \n\t"
- "paddb %%mm1, %%mm0 \n\t"
-
- "cmpl _MMXLength, %%edx \n\t"
- "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array
- "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop
- "jb sub_3lp \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm6", "%mm7"
-#endif
- );
- }
- break;
-
- case 1:
- {
- __asm__ __volatile__ (
- "movl _dif, %%edx \n\t"
-// preload "movl row, %%edi \n\t"
- "cmpl _FullLength, %%edx \n\t"
- "jnb sub_1end \n\t"
- "movl %%edi, %%esi \n\t" // lp = row
- "xorl %%eax, %%eax \n\t"
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
-
- "sub_1lp: \n\t"
- "movb (%%esi,%%edx,), %%al \n\t"
- "addb %%al, (%%edi,%%edx,) \n\t"
- "incl %%edx \n\t"
- "cmpl _FullLength, %%edx \n\t"
- "jb sub_1lp \n\t"
-
- "sub_1end: \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
- );
- }
- return;
-
- case 6:
- case 4:
- //case 7: // GRR BOGUS
- //case 5: // GRR BOGUS
- {
- _ShiftBpp.use = bpp << 3;
- _ShiftRem.use = 64 - _ShiftBpp.use;
-
- __asm__ __volatile__ (
-// preload "movl row, %%edi \n\t"
- "movl _dif, %%edx \n\t"
- "movl %%edi, %%esi \n\t" // lp = row
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%edx,), %%mm1 \n\t"
-
- "sub_4lp: \n\t" // shift data for adding first
- "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask;
- // shift clears inactive bytes)
- "movq (%%edi,%%edx,), %%mm0 \n\t"
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 2nd active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "addl $8, %%edx \n\t"
- "paddb %%mm1, %%mm0 \n\t"
-
- "cmpl _MMXLength, %%edx \n\t"
- "movq %%mm0, -8(%%edi,%%edx,) \n\t"
- "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop
- "jb sub_4lp \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1"
-#endif
- );
- }
- break;
-
- case 2:
- {
- _ActiveMask.use = 0x00000000ffff0000LL;
- _ShiftBpp.use = 16; // == 2 * 8
- _ShiftRem.use = 48; // == 64 - 16
-
- __asm__ __volatile__ (
- "movq _ActiveMask, %%mm7 \n\t" // load _ActiveMask for 2nd
- // active byte group
- "movl _dif, %%edx \n\t"
- "movq %%mm7, %%mm6 \n\t"
-// preload "movl row, %%edi \n\t"
- "psllq _ShiftBpp, %%mm6 \n\t" // move mask in mm6 to cover
- // 3rd active byte group
- "movl %%edi, %%esi \n\t" // lp = row
- "movq %%mm6, %%mm5 \n\t"
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
- "psllq _ShiftBpp, %%mm5 \n\t" // move mask in mm5 to cover
- // 4th active byte group
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%edx,), %%mm1 \n\t"
-
- "sub_2lp: \n\t" // shift data for adding first
- "psrlq _ShiftRem, %%mm1 \n\t" // bpp bytes (no need for mask;
- // shift clears inactive bytes)
- // add 1st active group
- "movq (%%edi,%%edx,), %%mm0 \n\t"
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 2nd active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "pand %%mm7, %%mm1 \n\t" // mask to use 2nd active group
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 3rd active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "pand %%mm6, %%mm1 \n\t" // mask to use 3rd active group
- "paddb %%mm1, %%mm0 \n\t"
-
- // add 4th active group
- "movq %%mm0, %%mm1 \n\t" // mov updated Raws to mm1
- "psllq _ShiftBpp, %%mm1 \n\t" // shift data to pos. correctly
- "pand %%mm5, %%mm1 \n\t" // mask to use 4th active group
- "addl $8, %%edx \n\t"
- "paddb %%mm1, %%mm0 \n\t"
- "cmpl _MMXLength, %%edx \n\t"
- "movq %%mm0, -8(%%edi,%%edx,) \n\t" // write updated Raws to array
- "movq %%mm0, %%mm1 \n\t" // prep 1st add at top of loop
- "jb sub_2lp \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break;
-
- case 8:
- {
- __asm__ __volatile__ (
-// preload "movl row, %%edi \n\t"
- "movl _dif, %%edx \n\t"
- "movl %%edi, %%esi \n\t" // lp = row
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
- "movl _MMXLength, %%ecx \n\t"
-
- // prime the pump: load the first Raw(x-bpp) data set
- "movq -8(%%edi,%%edx,), %%mm7 \n\t"
- "andl $0x0000003f, %%ecx \n\t" // calc bytes over mult of 64
-
- "sub_8lp: \n\t"
- "movq (%%edi,%%edx,), %%mm0 \n\t" // load Sub(x) for 1st 8 bytes
- "paddb %%mm7, %%mm0 \n\t"
- "movq 8(%%edi,%%edx,), %%mm1 \n\t" // load Sub(x) for 2nd 8 bytes
- "movq %%mm0, (%%edi,%%edx,) \n\t" // write Raw(x) for 1st 8 bytes
-
- // Now mm0 will be used as Raw(x-bpp) for the 2nd group of 8 bytes.
- // This will be repeated for each group of 8 bytes with the 8th
- // group being used as the Raw(x-bpp) for the 1st group of the
- // next loop.
-
- "paddb %%mm0, %%mm1 \n\t"
- "movq 16(%%edi,%%edx,), %%mm2 \n\t" // load Sub(x) for 3rd 8 bytes
- "movq %%mm1, 8(%%edi,%%edx,) \n\t" // write Raw(x) for 2nd 8 bytes
- "paddb %%mm1, %%mm2 \n\t"
- "movq 24(%%edi,%%edx,), %%mm3 \n\t" // load Sub(x) for 4th 8 bytes
- "movq %%mm2, 16(%%edi,%%edx,) \n\t" // write Raw(x) for 3rd 8 bytes
- "paddb %%mm2, %%mm3 \n\t"
- "movq 32(%%edi,%%edx,), %%mm4 \n\t" // load Sub(x) for 5th 8 bytes
- "movq %%mm3, 24(%%edi,%%edx,) \n\t" // write Raw(x) for 4th 8 bytes
- "paddb %%mm3, %%mm4 \n\t"
- "movq 40(%%edi,%%edx,), %%mm5 \n\t" // load Sub(x) for 6th 8 bytes
- "movq %%mm4, 32(%%edi,%%edx,) \n\t" // write Raw(x) for 5th 8 bytes
- "paddb %%mm4, %%mm5 \n\t"
- "movq 48(%%edi,%%edx,), %%mm6 \n\t" // load Sub(x) for 7th 8 bytes
- "movq %%mm5, 40(%%edi,%%edx,) \n\t" // write Raw(x) for 6th 8 bytes
- "paddb %%mm5, %%mm6 \n\t"
- "movq 56(%%edi,%%edx,), %%mm7 \n\t" // load Sub(x) for 8th 8 bytes
- "movq %%mm6, 48(%%edi,%%edx,) \n\t" // write Raw(x) for 7th 8 bytes
- "addl $64, %%edx \n\t"
- "paddb %%mm6, %%mm7 \n\t"
- "cmpl %%ecx, %%edx \n\t"
- "movq %%mm7, -8(%%edi,%%edx,) \n\t" // write Raw(x) for 8th 8 bytes
- "jb sub_8lp \n\t"
-
- "cmpl _MMXLength, %%edx \n\t"
- "jnb sub_8lt8 \n\t"
-
- "sub_8lpA: \n\t"
- "movq (%%edi,%%edx,), %%mm0 \n\t"
- "addl $8, %%edx \n\t"
- "paddb %%mm7, %%mm0 \n\t"
- "cmpl _MMXLength, %%edx \n\t"
- "movq %%mm0, -8(%%edi,%%edx,) \n\t" // -8 to offset early addl edx
- "movq %%mm0, %%mm7 \n\t" // move calculated Raw(x) data
- // to mm1 to be new Raw(x-bpp)
- // for next loop
- "jb sub_8lpA \n\t"
-
- "sub_8lt8: \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%ecx", "%edx", "%esi" // clobber list
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3", "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
- }
- break;
-
- default: // bpp greater than 8 bytes GRR BOGUS
- {
- __asm__ __volatile__ (
- "movl _dif, %%edx \n\t"
-// preload "movl row, %%edi \n\t"
- "movl %%edi, %%esi \n\t" // lp = row
-// preload "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
-
- "sub_Alp: \n\t"
- "movq (%%edi,%%edx,), %%mm0 \n\t"
- "movq (%%esi,%%edx,), %%mm1 \n\t"
- "addl $8, %%edx \n\t"
- "paddb %%mm1, %%mm0 \n\t"
- "cmpl _MMXLength, %%edx \n\t"
- "movq %%mm0, -8(%%edi,%%edx,) \n\t" // mov does not affect flags;
- // -8 to offset addl edx
- "jb sub_Alp \n\t"
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1"
-#endif
- );
- }
- break;
-
- } // end switch (bpp)
-
- __asm__ __volatile__ (
- "movl _MMXLength, %%edx \n\t"
-//pre "movl row, %%edi \n\t"
- "cmpl _FullLength, %%edx \n\t"
- "jnb sub_end \n\t"
-
- "movl %%edi, %%esi \n\t" // lp = row
-//pre "movl bpp, %%eax \n\t"
- "addl %%eax, %%edi \n\t" // rp = row + bpp
- "xorl %%eax, %%eax \n\t"
-
- "sub_lp2: \n\t"
- "movb (%%esi,%%edx,), %%al \n\t"
- "addb %%al, (%%edi,%%edx,) \n\t"
- "incl %%edx \n\t"
- "cmpl _FullLength, %%edx \n\t"
- "jb sub_lp2 \n\t"
-
- "sub_end: \n\t"
- "EMMS \n\t" // end MMX instructions
-
- : "=a" (dummy_value_a), // 0 // output regs (dummy)
- "=D" (dummy_value_D) // 1
-
- : "0" (bpp), // eax // input regs
- "1" (row) // edi
-
- : "%edx", "%esi" // clobber list
- );
-
-} // end of png_read_filter_row_mmx_sub()
-#endif
-
-
-
-
-//===========================================================================//
-// //
-// P N G _ R E A D _ F I L T E R _ R O W _ M M X _ U P //
-// //
-//===========================================================================//
-
-// Optimized code for PNG Up filter decoder
-
-static void /* PRIVATE */
-png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row,
- png_bytep prev_row)
-{
- png_uint_32 len;
- int dummy_value_d; // fix 'forbidden register 3 (dx) was spilled' error
- int dummy_value_S;
- int dummy_value_D;
-
- len = row_info->rowbytes; // number of bytes to filter
-
- __asm__ __volatile__ (
-//pre "movl row, %%edi \n\t"
- // get # of bytes to alignment
-#ifdef __PIC__
- "pushl %%ebx \n\t"
-#endif
- "movl %%edi, %%ecx \n\t"
- "xorl %%ebx, %%ebx \n\t"
- "addl $0x7, %%ecx \n\t"
- "xorl %%eax, %%eax \n\t"
- "andl $0xfffffff8, %%ecx \n\t"
-//pre "movl prev_row, %%esi \n\t"
- "subl %%edi, %%ecx \n\t"
- "jz up_go \n\t"
-
- "up_lp1: \n\t" // fix alignment
- "movb (%%edi,%%ebx,), %%al \n\t"
- "addb (%%esi,%%ebx,), %%al \n\t"
- "incl %%ebx \n\t"
- "cmpl %%ecx, %%ebx \n\t"
- "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to
- "jb up_lp1 \n\t" // offset incl ebx
-
- "up_go: \n\t"
-//pre "movl len, %%edx \n\t"
- "movl %%edx, %%ecx \n\t"
- "subl %%ebx, %%edx \n\t" // subtract alignment fix
- "andl $0x0000003f, %%edx \n\t" // calc bytes over mult of 64
- "subl %%edx, %%ecx \n\t" // drop over bytes from length
-
- // unrolled loop - use all MMX registers and interleave to reduce
- // number of branch instructions (loops) and reduce partial stalls
- "up_loop: \n\t"
- "movq (%%esi,%%ebx,), %%mm1 \n\t"
- "movq (%%edi,%%ebx,), %%mm0 \n\t"
- "movq 8(%%esi,%%ebx,), %%mm3 \n\t"
- "paddb %%mm1, %%mm0 \n\t"
- "movq 8(%%edi,%%ebx,), %%mm2 \n\t"
- "movq %%mm0, (%%edi,%%ebx,) \n\t"
- "paddb %%mm3, %%mm2 \n\t"
- "movq 16(%%esi,%%ebx,), %%mm5 \n\t"
- "movq %%mm2, 8(%%edi,%%ebx,) \n\t"
- "movq 16(%%edi,%%ebx,), %%mm4 \n\t"
- "movq 24(%%esi,%%ebx,), %%mm7 \n\t"
- "paddb %%mm5, %%mm4 \n\t"
- "movq 24(%%edi,%%ebx,), %%mm6 \n\t"
- "movq %%mm4, 16(%%edi,%%ebx,) \n\t"
- "paddb %%mm7, %%mm6 \n\t"
- "movq 32(%%esi,%%ebx,), %%mm1 \n\t"
- "movq %%mm6, 24(%%edi,%%ebx,) \n\t"
- "movq 32(%%edi,%%ebx,), %%mm0 \n\t"
- "movq 40(%%esi,%%ebx,), %%mm3 \n\t"
- "paddb %%mm1, %%mm0 \n\t"
- "movq 40(%%edi,%%ebx,), %%mm2 \n\t"
- "movq %%mm0, 32(%%edi,%%ebx,) \n\t"
- "paddb %%mm3, %%mm2 \n\t"
- "movq 48(%%esi,%%ebx,), %%mm5 \n\t"
- "movq %%mm2, 40(%%edi,%%ebx,) \n\t"
- "movq 48(%%edi,%%ebx,), %%mm4 \n\t"
- "movq 56(%%esi,%%ebx,), %%mm7 \n\t"
- "paddb %%mm5, %%mm4 \n\t"
- "movq 56(%%edi,%%ebx,), %%mm6 \n\t"
- "movq %%mm4, 48(%%edi,%%ebx,) \n\t"
- "addl $64, %%ebx \n\t"
- "paddb %%mm7, %%mm6 \n\t"
- "cmpl %%ecx, %%ebx \n\t"
- "movq %%mm6, -8(%%edi,%%ebx,) \n\t" // (+56)movq does not affect flags;
- "jb up_loop \n\t" // -8 to offset addl ebx
-
- "cmpl $0, %%edx \n\t" // test for bytes over mult of 64
- "jz up_end \n\t"
-
- "cmpl $8, %%edx \n\t" // test for less than 8 bytes
- "jb up_lt8 \n\t" // [added by lcreeve at netins.net]
-
- "addl %%edx, %%ecx \n\t"
- "andl $0x00000007, %%edx \n\t" // calc bytes over mult of 8
- "subl %%edx, %%ecx \n\t" // drop over bytes from length
- "jz up_lt8 \n\t"
-
- "up_lpA: \n\t" // use MMX regs to update 8 bytes sim.
- "movq (%%esi,%%ebx,), %%mm1 \n\t"
- "movq (%%edi,%%ebx,), %%mm0 \n\t"
- "addl $8, %%ebx \n\t"
- "paddb %%mm1, %%mm0 \n\t"
- "cmpl %%ecx, %%ebx \n\t"
- "movq %%mm0, -8(%%edi,%%ebx,) \n\t" // movq does not affect flags; -8 to
- "jb up_lpA \n\t" // offset add ebx
- "cmpl $0, %%edx \n\t" // test for bytes over mult of 8
- "jz up_end \n\t"
-
- "up_lt8: \n\t"
- "xorl %%eax, %%eax \n\t"
- "addl %%edx, %%ecx \n\t" // move over byte count into counter
-
- "up_lp2: \n\t" // use x86 regs for remaining bytes
- "movb (%%edi,%%ebx,), %%al \n\t"
- "addb (%%esi,%%ebx,), %%al \n\t"
- "incl %%ebx \n\t"
- "cmpl %%ecx, %%ebx \n\t"
- "movb %%al, -1(%%edi,%%ebx,) \n\t" // mov does not affect flags; -1 to
- "jb up_lp2 \n\t" // offset inc ebx
-
- "up_end: \n\t"
- "EMMS \n\t" // conversion of filtered row complete
-#ifdef __PIC__
- "popl %%ebx \n\t"
-#endif
-
- : "=d" (dummy_value_d), // 0 // output regs (dummy)
- "=S" (dummy_value_S), // 1
- "=D" (dummy_value_D) // 2
-
- : "0" (len), // edx // input regs
- "1" (prev_row), // esi
- "2" (row) // edi
-
- : "%eax", "%ecx" // clobber list (no input regs!)
-#ifndef __PIC__
- , "%ebx"
-#endif
-
-#if 0 /* MMX regs (%mm0, etc.) not supported by gcc 2.7.2.3 or egcs 1.1 */
- , "%mm0", "%mm1", "%mm2", "%mm3"
- , "%mm4", "%mm5", "%mm6", "%mm7"
-#endif
- );
-
-} // end of png_read_filter_row_mmx_up()
-
-#endif /* PNG_MMX_CODE_SUPPORTED */
-
-
-
-
-/*===========================================================================*/
-/* */
-/* P N G _ R E A D _ F I L T E R _ R O W */
-/* */
-/*===========================================================================*/
-
-
-/* Optimized png_read_filter_row routines */
-
-void /* PRIVATE */
-png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep
- row, png_bytep prev_row, int filter)
-{
-#ifdef PNG_DEBUG
- char filnm[10];
-#endif
-
-#if defined(PNG_MMX_CODE_SUPPORTED)
-/* GRR: these are superseded by png_ptr->asm_flags: */
-#define UseMMX_sub 1 // GRR: converted 20000730
-#define UseMMX_up 1 // GRR: converted 20000729
-#define UseMMX_avg 1 // GRR: converted 20000828 (+ 16-bit bugfix 20000916)
-#define UseMMX_paeth 1 // GRR: converted 20000828
-
- if (_mmx_supported == 2) {
- /* this should have happened in png_init_mmx_flags() already */
-#if !defined(PNG_1_0_X)
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-#endif /* PNG_MMX_CODE_SUPPORTED */
-
-#ifdef PNG_DEBUG
- png_debug(1, "in png_read_filter_row (pnggccrd.c)\n");
- switch (filter)
- {
- case 0: sprintf(filnm, "none");
- break;
- case 1: sprintf(filnm, "sub-%s",
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB)? "MMX" :
-#endif
-#endif
-"x86");
- break;
- case 2: sprintf(filnm, "up-%s",
-#ifdef PNG_MMX_CODE_SUPPORTED
-#if !defined(PNG_1_0_X)
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP)? "MMX" :
-#endif
-#endif
- "x86");
- break;
- case 3: sprintf(filnm, "avg-%s",
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG)? "MMX" :
-#endif
-#endif
- "x86");
- break;
- case 4: sprintf(filnm, "Paeth-%s",
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH)? "MMX":
-#endif
-#endif
-"x86");
- break;
- default: sprintf(filnm, "unknw");
- break;
- }
- png_debug2(0, "row_number=%5ld, %5s, ", png_ptr->row_number, filnm);
- png_debug1(0, "row=0x%08lx, ", (unsigned long)row);
- png_debug2(0, "pixdepth=%2d, bytes=%d, ", (int)row_info->pixel_depth,
- (int)((row_info->pixel_depth + 7) >> 3));
- png_debug1(0,"rowbytes=%8ld\n", row_info->rowbytes);
-#endif /* PNG_DEBUG */
-
- switch (filter)
- {
- case PNG_FILTER_VALUE_NONE:
- break;
-
- case PNG_FILTER_VALUE_SUB:
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (_mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_sub(row_info, row);
- }
- else
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- png_uint_32 i;
- png_uint_32 istop = row_info->rowbytes;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_bytep rp = row + bpp;
- png_bytep lp = row;
-
- for (i = bpp; i < istop; i++)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*lp++)) & 0xff);
- rp++;
- }
- } /* end !UseMMX_sub */
- break;
-
- case PNG_FILTER_VALUE_UP:
-#if defined(PNG_MMX_CODE_SUPPORTED)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (_mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_up(row_info, row, prev_row);
- }
- else
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- png_uint_32 i;
- png_uint_32 istop = row_info->rowbytes;
- png_bytep rp = row;
- png_bytep pp = prev_row;
-
- for (i = 0; i < istop; ++i)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff);
- rp++;
- }
- } /* end !UseMMX_up */
- break;
-
- case PNG_FILTER_VALUE_AVG:
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (_mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_avg(row_info, row, prev_row);
- }
- else
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- png_uint_32 i;
- png_bytep rp = row;
- png_bytep pp = prev_row;
- png_bytep lp = row;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_uint_32 istop = row_info->rowbytes - bpp;
-
- for (i = 0; i < bpp; i++)
- {
- *rp = (png_byte)(((int)(*rp) +
- ((int)(*pp++) >> 1)) & 0xff);
- rp++;
- }
-
- for (i = 0; i < istop; i++)
- {
- *rp = (png_byte)(((int)(*rp) +
- ((int)(*pp++ + *lp++) >> 1)) & 0xff);
- rp++;
- }
- } /* end !UseMMX_avg */
- break;
-
- case PNG_FILTER_VALUE_PAETH:
-#if defined(PNG_MMX_CODE_SUPPORTED) && defined(PNG_THREAD_UNSAFE_OK)
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (_mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_paeth(row_info, row, prev_row);
- }
- else
-#endif /* PNG_MMX_CODE_SUPPORTED */
- {
- png_uint_32 i;
- png_bytep rp = row;
- png_bytep pp = prev_row;
- png_bytep lp = row;
- png_bytep cp = prev_row;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_uint_32 istop = row_info->rowbytes - bpp;
-
- for (i = 0; i < bpp; i++)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff);
- rp++;
- }
-
- for (i = 0; i < istop; i++) /* use leftover rp,pp */
- {
- int a, b, c, pa, pb, pc, p;
-
- a = *lp++;
- b = *pp++;
- c = *cp++;
-
- p = b - c;
- pc = a - c;
-
-#ifdef PNG_USE_ABS
- pa = abs(p);
- pb = abs(pc);
- pc = abs(p + pc);
-#else
- pa = p < 0 ? -p : p;
- pb = pc < 0 ? -pc : pc;
- pc = (p + pc) < 0 ? -(p + pc) : p + pc;
-#endif
-
- /*
- if (pa <= pb && pa <= pc)
- p = a;
- else if (pb <= pc)
- p = b;
- else
- p = c;
- */
-
- p = (pa <= pb && pa <= pc) ? a : (pb <= pc) ? b : c;
-
- *rp = (png_byte)(((int)(*rp) + p) & 0xff);
- rp++;
- }
- } /* end !UseMMX_paeth */
- break;
-
- default:
- png_warning(png_ptr, "Ignoring bad row-filter type");
- *row=0;
- break;
- }
-}
-
-#endif /* PNG_HAVE_MMX_READ_FILTER_ROW */
-
-
-/*===========================================================================*/
-/* */
-/* P N G _ M M X _ S U P P O R T */
-/* */
-/*===========================================================================*/
-
-/* GRR NOTES: (1) the following code assumes 386 or better (pushfl/popfl)
- * (2) all instructions compile with gcc 2.7.2.3 and later
- * (3) the function is moved down here to prevent gcc from
- * inlining it in multiple places and then barfing be-
- * cause the ".NOT_SUPPORTED" label is multiply defined
- * [is there a way to signal that a *single* function should
- * not be inlined? is there a way to modify the label for
- * each inlined instance, e.g., by appending _1, _2, etc.?
- * maybe if don't use leading "." in label name? (nope...sigh)]
- */
+int PNGAPI
+png_dummy_mmx_support(void) __attribute__((noinline));
int PNGAPI
-png_mmx_support(void)
+png_dummy_mmx_support(void)
{
-#if defined(PNG_MMX_CODE_SUPPORTED)
- int result;
+ int result;
+#if defined(PNG_MMX_CODE_SUPPORTED) // superfluous, but what the heck
__asm__ __volatile__ (
+#if defined(__x86_64__)
+ "pushq %%rbx \n\t" // rbx gets clobbered by CPUID instruction
+ "pushq %%rcx \n\t" // so does rcx...
+ "pushq %%rdx \n\t" // ...and rdx (but rcx & rdx safe on Linux)
+ "pushfq \n\t" // save Eflag to stack
+ "popq %%rax \n\t" // get Eflag from stack into rax
+ "movq %%rax, %%rcx \n\t" // make another copy of Eflag in rcx
+ "xorl $0x200000, %%eax \n\t" // toggle ID bit in Eflag (i.e., bit 21)
+ "pushq %%rax \n\t" // save modified Eflag back to stack
+ "popfq \n\t" // restore modified value to Eflag reg
+ "pushfq \n\t" // save Eflag to stack
+ "popq %%rax \n\t" // get Eflag from stack
+ "pushq %%rcx \n\t" // save original Eflag to stack
+ "popfq \n\t" // restore original Eflag
+#else
"pushl %%ebx \n\t" // ebx gets clobbered by CPUID instruction
"pushl %%ecx \n\t" // so does ecx...
"pushl %%edx \n\t" // ...and edx (but ecx & edx safe on Linux)
-// ".byte 0x66 \n\t" // convert 16-bit pushf to 32-bit pushfd
-// "pushf \n\t" // 16-bit pushf
"pushfl \n\t" // save Eflag to stack
"popl %%eax \n\t" // get Eflag from stack into eax
"movl %%eax, %%ecx \n\t" // make another copy of Eflag in ecx
"xorl $0x200000, %%eax \n\t" // toggle ID bit in Eflag (i.e., bit 21)
"pushl %%eax \n\t" // save modified Eflag back to stack
-// ".byte 0x66 \n\t" // convert 16-bit popf to 32-bit popfd
-// "popf \n\t" // 16-bit popf
"popfl \n\t" // restore modified value to Eflag reg
"pushfl \n\t" // save Eflag to stack
"popl %%eax \n\t" // get Eflag from stack
"pushl %%ecx \n\t" // save original Eflag to stack
"popfl \n\t" // restore original Eflag
+#endif
"xorl %%ecx, %%eax \n\t" // compare new Eflag with original Eflag
"jz 0f \n\t" // if same, CPUID instr. is not supported
@@ -5392,9 +69,15 @@ png_mmx_support(void)
"0: \n\t" // .NOT_SUPPORTED: target label for jump instructions
"movl $0, %%eax \n\t" // set return value to 0
"1: \n\t" // .RETURN: target label for jump instructions
+#if defined(__x86_64__)
+ "popq %%rdx \n\t" // restore rdx
+ "popq %%rcx \n\t" // restore rcx
+ "popq %%rbx \n\t" // restore rbx
+#else
"popl %%edx \n\t" // restore edx
"popl %%ecx \n\t" // restore ecx
"popl %%ebx \n\t" // restore ebx
+#endif
// "ret \n\t" // DONE: no MMX support
// (fall through to standard C "ret")
@@ -5415,6 +98,4 @@ png_mmx_support(void)
return _mmx_supported;
}
-
-
-#endif /* PNG_USE_PNGGCCRD */
+#endif
diff --git a/Build/source/libs/libpng/pngget.c b/Build/source/libs/libpng/pngget.c
index 036e9af6ed7..a0e90bb6a4f 100644
--- a/Build/source/libs/libpng/pngget.c
+++ b/Build/source/libs/libpng/pngget.c
@@ -512,8 +512,11 @@ png_get_sPLT(png_structp png_ptr, png_infop info_ptr,
png_sPLT_tpp spalettes)
{
if (png_ptr != NULL && info_ptr != NULL && spalettes != NULL)
+ {
*spalettes = info_ptr->splt_palettes;
- return ((png_uint_32)info_ptr->splt_palettes_num);
+ return ((png_uint_32)info_ptr->splt_palettes_num);
+ }
+ return (0);
}
#endif
@@ -800,8 +803,11 @@ png_get_unknown_chunks(png_structp png_ptr, png_infop info_ptr,
png_unknown_chunkpp unknowns)
{
if (png_ptr != NULL && info_ptr != NULL && unknowns != NULL)
+ {
*unknowns = info_ptr->unknown_chunks;
- return ((png_uint_32)info_ptr->unknown_chunks_num);
+ return ((png_uint_32)info_ptr->unknown_chunks_num);
+ }
+ return (0);
}
#endif
@@ -835,105 +841,44 @@ png_get_compression_buffer_size(png_structp png_ptr)
png_uint_32 PNGAPI
png_get_asm_flags (png_structp png_ptr)
{
-#ifdef PNG_MMX_CODE_SUPPORTED
- return (png_uint_32)(png_ptr? png_ptr->asm_flags : 0L);
-#else
+ /* obsolete, to be removed from libpng-1.4.0 */
return (png_ptr? 0L: 0L);
-#endif
}
/* this function was added to libpng 1.2.0 and should exist by default */
png_uint_32 PNGAPI
png_get_asm_flagmask (int flag_select)
{
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_uint_32 settable_asm_flags = 0;
-
- if (flag_select & PNG_SELECT_READ)
- settable_asm_flags |=
- PNG_ASM_FLAG_MMX_READ_COMBINE_ROW |
- PNG_ASM_FLAG_MMX_READ_INTERLACE |
- PNG_ASM_FLAG_MMX_READ_FILTER_SUB |
- PNG_ASM_FLAG_MMX_READ_FILTER_UP |
- PNG_ASM_FLAG_MMX_READ_FILTER_AVG |
- PNG_ASM_FLAG_MMX_READ_FILTER_PAETH ;
- /* no non-MMX flags yet */
-
-#if 0
- /* GRR: no write-flags yet, either, but someday... */
- if (flag_select & PNG_SELECT_WRITE)
- settable_asm_flags |=
- PNG_ASM_FLAG_MMX_WRITE_ [whatever] ;
-#endif /* 0 */
-
- return settable_asm_flags; /* _theoretically_ settable capabilities only */
-#else
- return (0L);
-#endif /* PNG_MMX_CODE_SUPPORTED */
+ /* obsolete, to be removed from libpng-1.4.0 */
+ flag_select=flag_select;
+ return 0L;
}
-
/* GRR: could add this: && defined(PNG_MMX_CODE_SUPPORTED) */
/* this function was added to libpng 1.2.0 */
png_uint_32 PNGAPI
png_get_mmx_flagmask (int flag_select, int *compilerID)
{
-#if defined(PNG_MMX_CODE_SUPPORTED)
- png_uint_32 settable_mmx_flags = 0;
-
- if (flag_select & PNG_SELECT_READ)
- settable_mmx_flags |=
- PNG_ASM_FLAG_MMX_READ_COMBINE_ROW |
- PNG_ASM_FLAG_MMX_READ_INTERLACE |
- PNG_ASM_FLAG_MMX_READ_FILTER_SUB |
- PNG_ASM_FLAG_MMX_READ_FILTER_UP |
- PNG_ASM_FLAG_MMX_READ_FILTER_AVG |
- PNG_ASM_FLAG_MMX_READ_FILTER_PAETH ;
-#if 0
- /* GRR: no MMX write support yet, but someday... */
- if (flag_select & PNG_SELECT_WRITE)
- settable_mmx_flags |=
- PNG_ASM_FLAG_MMX_WRITE_ [whatever] ;
-#endif /* 0 */
-
- if (compilerID != NULL) {
-#ifdef PNG_USE_PNGVCRD
- *compilerID = 1; /* MSVC */
-#else
-#ifdef PNG_USE_PNGGCCRD
- *compilerID = 2; /* gcc/gas */
-#else
- *compilerID = -1; /* unknown (i.e., no asm/MMX code compiled) */
-#endif
-#endif
- }
-
- return settable_mmx_flags; /* _theoretically_ settable capabilities only */
-#else
- return (0L);
-#endif /* ?PNG_MMX_CODE_SUPPORTED */
+ /* obsolete, to be removed from libpng-1.4.0 */
+ flag_select=flag_select;
+ *compilerID = -1; /* unknown (i.e., no asm/MMX code compiled) */
+ return 0L;
}
/* this function was added to libpng 1.2.0 */
png_byte PNGAPI
png_get_mmx_bitdepth_threshold (png_structp png_ptr)
{
-#if defined(PNG_MMX_CODE_SUPPORTED)
- return (png_byte)(png_ptr? png_ptr->mmx_bitdepth_threshold : 0);
-#else
+ /* obsolete, to be removed from libpng-1.4.0 */
return (png_ptr? 0: 0);
-#endif /* ?PNG_MMX_CODE_SUPPORTED */
}
/* this function was added to libpng 1.2.0 */
png_uint_32 PNGAPI
png_get_mmx_rowbytes_threshold (png_structp png_ptr)
{
-#if defined(PNG_MMX_CODE_SUPPORTED)
- return (png_uint_32)(png_ptr? png_ptr->mmx_rowbytes_threshold : 0L);
-#else
+ /* obsolete, to be removed from libpng-1.4.0 */
return (png_ptr? 0L: 0L);
-#endif /* ?PNG_MMX_CODE_SUPPORTED */
}
#endif /* ?PNG_1_0_X */
#endif /* ?PNG_ASSEMBLER_CODE_SUPPORTED */
@@ -951,5 +896,6 @@ png_get_user_height_max (png_structp png_ptr)
return (png_ptr? png_ptr->user_height_max : 0);
}
#endif /* ?PNG_SET_USER_LIMITS_SUPPORTED */
+
#endif /* PNG_READ_SUPPORTED || PNG_WRITE_SUPPORTED */
diff --git a/Build/source/libs/libpng/pngpread.c b/Build/source/libs/libpng/pngpread.c
index 1470b0fe0f6..8f4b7d1795c 100644
--- a/Build/source/libs/libpng/pngpread.c
+++ b/Build/source/libs/libpng/pngpread.c
@@ -1,7 +1,7 @@
/* pngpread.c - read a png file in push mode
*
- * Last changed in libpng 1.2.17 May 15, 2007
+ * Last changed in libpng 1.2.23 [November 6, 2007]
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -137,60 +137,60 @@ void /* PRIVATE */
png_push_read_chunk(png_structp png_ptr, png_infop info_ptr)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IHDR;
- PNG_IDAT;
- PNG_IEND;
- PNG_PLTE;
+ PNG_CONST PNG_IHDR;
+ PNG_CONST PNG_IDAT;
+ PNG_CONST PNG_IEND;
+ PNG_CONST PNG_PLTE;
#if defined(PNG_READ_bKGD_SUPPORTED)
- PNG_bKGD;
+ PNG_CONST PNG_bKGD;
#endif
#if defined(PNG_READ_cHRM_SUPPORTED)
- PNG_cHRM;
+ PNG_CONST PNG_cHRM;
#endif
#if defined(PNG_READ_gAMA_SUPPORTED)
- PNG_gAMA;
+ PNG_CONST PNG_gAMA;
#endif
#if defined(PNG_READ_hIST_SUPPORTED)
- PNG_hIST;
+ PNG_CONST PNG_hIST;
#endif
#if defined(PNG_READ_iCCP_SUPPORTED)
- PNG_iCCP;
+ PNG_CONST PNG_iCCP;
#endif
#if defined(PNG_READ_iTXt_SUPPORTED)
- PNG_iTXt;
+ PNG_CONST PNG_iTXt;
#endif
#if defined(PNG_READ_oFFs_SUPPORTED)
- PNG_oFFs;
+ PNG_CONST PNG_oFFs;
#endif
#if defined(PNG_READ_pCAL_SUPPORTED)
- PNG_pCAL;
+ PNG_CONST PNG_pCAL;
#endif
#if defined(PNG_READ_pHYs_SUPPORTED)
- PNG_pHYs;
+ PNG_CONST PNG_pHYs;
#endif
#if defined(PNG_READ_sBIT_SUPPORTED)
- PNG_sBIT;
+ PNG_CONST PNG_sBIT;
#endif
#if defined(PNG_READ_sCAL_SUPPORTED)
- PNG_sCAL;
+ PNG_CONST PNG_sCAL;
#endif
#if defined(PNG_READ_sRGB_SUPPORTED)
- PNG_sRGB;
+ PNG_CONST PNG_sRGB;
#endif
#if defined(PNG_READ_sPLT_SUPPORTED)
- PNG_sPLT;
+ PNG_CONST PNG_sPLT;
#endif
#if defined(PNG_READ_tEXt_SUPPORTED)
- PNG_tEXt;
+ PNG_CONST PNG_tEXt;
#endif
#if defined(PNG_READ_tIME_SUPPORTED)
- PNG_tIME;
+ PNG_CONST PNG_tIME;
#endif
#if defined(PNG_READ_tRNS_SUPPORTED)
- PNG_tRNS;
+ PNG_CONST PNG_tRNS;
#endif
#if defined(PNG_READ_zTXt_SUPPORTED)
- PNG_zTXt;
+ PNG_CONST PNG_zTXt;
#endif
#endif /* PNG_USE_LOCAL_ARRAYS */
/* First we make sure we have enough data for the 4 byte chunk name
@@ -216,7 +216,7 @@ png_push_read_chunk(png_structp png_ptr, png_infop info_ptr)
png_ptr->mode |= PNG_HAVE_CHUNK_HEADER;
}
- if (!png_memcmp(png_ptr->chunk_name, (png_bytep)png_IDAT, 4))
+ if (!png_memcmp(png_ptr->chunk_name, png_IDAT, 4))
if(png_ptr->mode & PNG_AFTER_IDAT)
png_ptr->mode |= PNG_HAVE_CHUNK_AFTER_IDAT;
@@ -273,7 +273,7 @@ png_push_read_chunk(png_structp png_ptr, png_infop info_ptr)
}
png_handle_PLTE(png_ptr, info_ptr, png_ptr->push_length);
}
- else if (!png_memcmp(png_ptr->chunk_name, (png_bytep)png_IDAT, 4))
+ else if (!png_memcmp(png_ptr->chunk_name, png_IDAT, 4))
{
/* If we reach an IDAT chunk, this means we have read all of the
* header chunks, and we can start reading the image (or if this
@@ -660,7 +660,7 @@ void /* PRIVATE */
png_push_read_IDAT(png_structp png_ptr)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IDAT;
+ PNG_CONST PNG_IDAT;
#endif
if (!(png_ptr->mode & PNG_HAVE_CHUNK_HEADER))
{
@@ -678,7 +678,7 @@ png_push_read_IDAT(png_structp png_ptr)
png_crc_read(png_ptr, png_ptr->chunk_name, 4);
png_ptr->mode |= PNG_HAVE_CHUNK_HEADER;
- if (png_memcmp(png_ptr->chunk_name, (png_bytep)png_IDAT, 4))
+ if (png_memcmp(png_ptr->chunk_name, png_IDAT, 4))
{
png_ptr->process_mode = PNG_READ_CHUNK_MODE;
if (!(png_ptr->flags & PNG_FLAG_ZLIB_FINISHED))
@@ -990,25 +990,20 @@ png_read_push_finish_row(png_structp png_ptr)
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
/* start of interlace block */
- const int FARDATA png_pass_start[] = {0, 4, 0, 2, 0, 1, 0};
+ PNG_CONST int FARDATA png_pass_start[] = {0, 4, 0, 2, 0, 1, 0};
/* offset to next interlace block */
- const int FARDATA png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
+ PNG_CONST int FARDATA png_pass_inc[] = {8, 8, 4, 4, 2, 2, 1};
/* start of interlace block in the y direction */
- const int FARDATA png_pass_ystart[] = {0, 0, 4, 0, 2, 0, 1};
+ PNG_CONST int FARDATA png_pass_ystart[] = {0, 0, 4, 0, 2, 0, 1};
/* offset to next interlace block in the y direction */
- const int FARDATA png_pass_yinc[] = {8, 8, 8, 4, 4, 2, 2};
-
- /* Width of interlace block. This is not currently used - if you need
- * it, uncomment it here and in png.h
- const int FARDATA png_pass_width[] = {8, 4, 4, 2, 2, 1, 1};
- */
+ PNG_CONST int FARDATA png_pass_yinc[] = {8, 8, 8, 4, 4, 2, 2};
/* Height of interlace block. This is not currently used - if you need
* it, uncomment it here and in png.h
- const int FARDATA png_pass_height[] = {8, 8, 4, 4, 2, 2, 1};
+ PNG_CONST int FARDATA png_pass_height[] = {8, 8, 4, 4, 2, 2, 1};
*/
#endif
@@ -1062,8 +1057,7 @@ png_push_handle_tEXt(png_structp png_ptr, png_infop info_ptr, png_uint_32
if (!(png_ptr->mode & PNG_HAVE_IHDR) || (png_ptr->mode & PNG_HAVE_IEND))
{
png_error(png_ptr, "Out of place tEXt");
- /* to quiet some compiler warnings */
- if(info_ptr == NULL) return;
+ info_ptr = info_ptr; /* to quiet some compiler warnings */
}
#ifdef PNG_MAX_MALLOC_64K
@@ -1126,7 +1120,7 @@ png_push_read_tEXt(png_structp png_ptr, png_infop info_ptr)
for (text = key; *text; text++)
/* empty loop */ ;
- if (text != key + png_ptr->current_text_size)
+ if (text < key + png_ptr->current_text_size)
text++;
text_ptr = (png_textp)png_malloc(png_ptr,
@@ -1159,8 +1153,7 @@ png_push_handle_zTXt(png_structp png_ptr, png_infop info_ptr, png_uint_32
if (!(png_ptr->mode & PNG_HAVE_IHDR) || (png_ptr->mode & PNG_HAVE_IEND))
{
png_error(png_ptr, "Out of place zTXt");
- /* to quiet some compiler warnings */
- if(info_ptr == NULL) return;
+ info_ptr = info_ptr; /* to quiet some compiler warnings */
}
#ifdef PNG_MAX_MALLOC_64K
@@ -1222,7 +1215,7 @@ png_push_read_zTXt(png_structp png_ptr, png_infop info_ptr)
/* empty loop */ ;
/* zTXt can't have zero text */
- if (text == key + png_ptr->current_text_size)
+ if (text >= key + png_ptr->current_text_size)
{
png_ptr->current_text = NULL;
png_free(png_ptr, key);
@@ -1352,8 +1345,7 @@ png_push_handle_iTXt(png_structp png_ptr, png_infop info_ptr, png_uint_32
if (!(png_ptr->mode & PNG_HAVE_IHDR) || (png_ptr->mode & PNG_HAVE_IEND))
{
png_error(png_ptr, "Out of place iTXt");
- /* to quiet some compiler warnings */
- if(info_ptr == NULL) return;
+ info_ptr = info_ptr; /* to quiet some compiler warnings */
}
#ifdef PNG_MAX_MALLOC_64K
@@ -1420,7 +1412,7 @@ png_push_read_iTXt(png_structp png_ptr, png_infop info_ptr)
for (lang = key; *lang; lang++)
/* empty loop */ ;
- if (lang != key + png_ptr->current_text_size)
+ if (lang < key + png_ptr->current_text_size - 3)
lang++;
comp_flag = *lang++;
@@ -1430,10 +1422,14 @@ png_push_read_iTXt(png_structp png_ptr, png_infop info_ptr)
/* empty loop */ ;
lang_key++; /* skip NUL separator */
- for (text = lang_key; *text; text++)
- /* empty loop */ ;
+ text=lang_key;
+ if (lang_key < key + png_ptr->current_text_size - 1)
+ {
+ for (; *text; text++)
+ /* empty loop */ ;
+ }
- if (text != key + png_ptr->current_text_size)
+ if (text < key + png_ptr->current_text_size)
text++;
text_ptr = (png_textp)png_malloc(png_ptr,
@@ -1471,60 +1467,61 @@ png_push_handle_unknown(png_structp png_ptr, png_infop info_ptr, png_uint_32
if (!(png_ptr->chunk_name[0] & 0x20))
{
#if defined(PNG_READ_UNKNOWN_CHUNKS_SUPPORTED)
- if(png_handle_as_unknown(png_ptr, png_ptr->chunk_name) !=
- PNG_HANDLE_CHUNK_ALWAYS
+ if(png_handle_as_unknown(png_ptr, png_ptr->chunk_name) !=
+ PNG_HANDLE_CHUNK_ALWAYS
#if defined(PNG_READ_USER_CHUNKS_SUPPORTED)
- && png_ptr->read_user_chunk_fn == NULL
+ && png_ptr->read_user_chunk_fn == NULL
#endif
- )
+ )
#endif
- png_chunk_error(png_ptr, "unknown critical chunk");
+ png_chunk_error(png_ptr, "unknown critical chunk");
- /* to quiet compiler warnings about unused info_ptr */
- if (info_ptr == NULL)
- return;
+ info_ptr = info_ptr; /* to quiet some compiler warnings */
}
#if defined(PNG_READ_UNKNOWN_CHUNKS_SUPPORTED)
if (png_ptr->flags & PNG_FLAG_KEEP_UNKNOWN_CHUNKS)
{
#ifdef PNG_MAX_MALLOC_64K
- if (length > (png_uint_32)65535L)
- {
- png_warning(png_ptr, "unknown chunk too large to fit in memory");
- skip = length - (png_uint_32)65535L;
- length = (png_uint_32)65535L;
- }
+ if (length > (png_uint_32)65535L)
+ {
+ png_warning(png_ptr, "unknown chunk too large to fit in memory");
+ skip = length - (png_uint_32)65535L;
+ length = (png_uint_32)65535L;
+ }
#endif
- png_strcpy((png_charp)png_ptr->unknown_chunk.name,
- (png_charp)png_ptr->chunk_name);
- png_ptr->unknown_chunk.data = (png_bytep)png_malloc(png_ptr, length);
- png_ptr->unknown_chunk.size = (png_size_t)length;
- png_crc_read(png_ptr, (png_bytep)png_ptr->unknown_chunk.data, length);
+ png_memcpy((png_charp)png_ptr->unknown_chunk.name,
+ (png_charp)png_ptr->chunk_name,
+ png_sizeof(png_ptr->unknown_chunk.name));
+ png_ptr->unknown_chunk.name[png_sizeof(png_ptr->unknown_chunk.name)-1]='\0';
+
+ png_ptr->unknown_chunk.data = (png_bytep)png_malloc(png_ptr, length);
+ png_ptr->unknown_chunk.size = (png_size_t)length;
+ png_crc_read(png_ptr, (png_bytep)png_ptr->unknown_chunk.data, length);
#if defined(PNG_READ_USER_CHUNKS_SUPPORTED)
- if(png_ptr->read_user_chunk_fn != NULL)
- {
- /* callback to user unknown chunk handler */
- int ret;
- ret = (*(png_ptr->read_user_chunk_fn))
- (png_ptr, &png_ptr->unknown_chunk);
- if (ret < 0)
- png_chunk_error(png_ptr, "error in user chunk");
- if (ret == 0)
- {
- if (!(png_ptr->chunk_name[0] & 0x20))
- if(png_handle_as_unknown(png_ptr, png_ptr->chunk_name) !=
- PNG_HANDLE_CHUNK_ALWAYS)
- png_chunk_error(png_ptr, "unknown critical chunk");
- png_set_unknown_chunks(png_ptr, info_ptr,
- &png_ptr->unknown_chunk, 1);
- }
- }
+ if(png_ptr->read_user_chunk_fn != NULL)
+ {
+ /* callback to user unknown chunk handler */
+ int ret;
+ ret = (*(png_ptr->read_user_chunk_fn))
+ (png_ptr, &png_ptr->unknown_chunk);
+ if (ret < 0)
+ png_chunk_error(png_ptr, "error in user chunk");
+ if (ret == 0)
+ {
+ if (!(png_ptr->chunk_name[0] & 0x20))
+ if(png_handle_as_unknown(png_ptr, png_ptr->chunk_name) !=
+ PNG_HANDLE_CHUNK_ALWAYS)
+ png_chunk_error(png_ptr, "unknown critical chunk");
+ png_set_unknown_chunks(png_ptr, info_ptr,
+ &png_ptr->unknown_chunk, 1);
+ }
+ }
#else
- png_set_unknown_chunks(png_ptr, info_ptr, &png_ptr->unknown_chunk, 1);
+ png_set_unknown_chunks(png_ptr, info_ptr, &png_ptr->unknown_chunk, 1);
#endif
- png_free(png_ptr, png_ptr->unknown_chunk.data);
- png_ptr->unknown_chunk.data = NULL;
+ png_free(png_ptr, png_ptr->unknown_chunk.data);
+ png_ptr->unknown_chunk.data = NULL;
}
else
#endif
@@ -1559,7 +1556,7 @@ png_progressive_combine_row (png_structp png_ptr,
png_bytep old_row, png_bytep new_row)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- const int FARDATA png_pass_dsp_mask[7] =
+ PNG_CONST int FARDATA png_pass_dsp_mask[7] =
{0xff, 0x0f, 0xff, 0x33, 0xff, 0x55, 0xff};
#endif
if(png_ptr == NULL) return;
diff --git a/Build/source/libs/libpng/pngread.c b/Build/source/libs/libpng/pngread.c
index 56dac8a80af..5de5e563550 100644
--- a/Build/source/libs/libpng/pngread.c
+++ b/Build/source/libs/libpng/pngread.c
@@ -1,7 +1,7 @@
/* pngread.c - read a PNG file
*
- * Last changed in libpng 1.2.15 January 5, 2007
+ * Last changed in libpng 1.2.24 December 14, 2007
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -55,12 +55,6 @@ png_create_read_struct_2(png_const_charp user_png_ver, png_voidp error_ptr,
if (png_ptr == NULL)
return (NULL);
-#if !defined(PNG_1_0_X)
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_init_mmx_flags(png_ptr); /* 1.2.0 addition */
-#endif
-#endif /* PNG_1_0_X */
-
/* added at libpng-1.2.6 */
#ifdef PNG_SET_USER_LIMITS_SUPPORTED
png_ptr->user_width_max=PNG_USER_WIDTH_MAX;
@@ -117,11 +111,13 @@ png_create_read_struct_2(png_const_charp user_png_ver, png_voidp error_ptr,
char msg[80];
if (user_png_ver)
{
- sprintf(msg, "Application was compiled with png.h from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application was compiled with png.h from libpng-%.20s",
user_png_ver);
png_warning(png_ptr, msg);
}
- sprintf(msg, "Application is running with png.c from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application is running with png.c from libpng-%.20s",
png_libpng_ver);
png_warning(png_ptr, msg);
#endif
@@ -197,11 +193,13 @@ png_read_init_2(png_structp png_ptr, png_const_charp user_png_ver,
png_ptr->warning_fn=NULL;
if (user_png_ver)
{
- sprintf(msg, "Application was compiled with png.h from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application was compiled with png.h from libpng-%.20s",
user_png_ver);
png_warning(png_ptr, msg);
}
- sprintf(msg, "Application is running with png.c from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application is running with png.c from libpng-%.20s",
png_libpng_ver);
png_warning(png_ptr, msg);
}
@@ -346,60 +344,60 @@ png_read_info(png_structp png_ptr, png_infop info_ptr)
for(;;)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IHDR;
- PNG_IDAT;
- PNG_IEND;
- PNG_PLTE;
+ PNG_CONST PNG_IHDR;
+ PNG_CONST PNG_IDAT;
+ PNG_CONST PNG_IEND;
+ PNG_CONST PNG_PLTE;
#if defined(PNG_READ_bKGD_SUPPORTED)
- PNG_bKGD;
+ PNG_CONST PNG_bKGD;
#endif
#if defined(PNG_READ_cHRM_SUPPORTED)
- PNG_cHRM;
+ PNG_CONST PNG_cHRM;
#endif
#if defined(PNG_READ_gAMA_SUPPORTED)
- PNG_gAMA;
+ PNG_CONST PNG_gAMA;
#endif
#if defined(PNG_READ_hIST_SUPPORTED)
- PNG_hIST;
+ PNG_CONST PNG_hIST;
#endif
#if defined(PNG_READ_iCCP_SUPPORTED)
- PNG_iCCP;
+ PNG_CONST PNG_iCCP;
#endif
#if defined(PNG_READ_iTXt_SUPPORTED)
- PNG_iTXt;
+ PNG_CONST PNG_iTXt;
#endif
#if defined(PNG_READ_oFFs_SUPPORTED)
- PNG_oFFs;
+ PNG_CONST PNG_oFFs;
#endif
#if defined(PNG_READ_pCAL_SUPPORTED)
- PNG_pCAL;
+ PNG_CONST PNG_pCAL;
#endif
#if defined(PNG_READ_pHYs_SUPPORTED)
- PNG_pHYs;
+ PNG_CONST PNG_pHYs;
#endif
#if defined(PNG_READ_sBIT_SUPPORTED)
- PNG_sBIT;
+ PNG_CONST PNG_sBIT;
#endif
#if defined(PNG_READ_sCAL_SUPPORTED)
- PNG_sCAL;
+ PNG_CONST PNG_sCAL;
#endif
#if defined(PNG_READ_sPLT_SUPPORTED)
- PNG_sPLT;
+ PNG_CONST PNG_sPLT;
#endif
#if defined(PNG_READ_sRGB_SUPPORTED)
- PNG_sRGB;
+ PNG_CONST PNG_sRGB;
#endif
#if defined(PNG_READ_tEXt_SUPPORTED)
- PNG_tEXt;
+ PNG_CONST PNG_tEXt;
#endif
#if defined(PNG_READ_tIME_SUPPORTED)
- PNG_tIME;
+ PNG_CONST PNG_tIME;
#endif
#if defined(PNG_READ_tRNS_SUPPORTED)
- PNG_tRNS;
+ PNG_CONST PNG_tRNS;
#endif
#if defined(PNG_READ_zTXt_SUPPORTED)
- PNG_zTXt;
+ PNG_CONST PNG_zTXt;
#endif
#endif /* PNG_USE_LOCAL_ARRAYS */
png_byte chunk_length[4];
@@ -417,7 +415,7 @@ png_read_info(png_structp png_ptr, png_infop info_ptr)
/* This should be a binary subdivision search or a hash for
* matching the chunk name rather than a linear search.
*/
- if (!png_memcmp(png_ptr->chunk_name, (png_bytep)png_IDAT, 4))
+ if (!png_memcmp(png_ptr->chunk_name, png_IDAT, 4))
if(png_ptr->mode & PNG_AFTER_IDAT)
png_ptr->mode |= PNG_HAVE_CHUNK_AFTER_IDAT;
@@ -567,9 +565,10 @@ void PNGAPI
png_read_row(png_structp png_ptr, png_bytep row, png_bytep dsp_row)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IDAT;
- const int png_pass_dsp_mask[7] = {0xff, 0x0f, 0xff, 0x33, 0xff, 0x55, 0xff};
- const int png_pass_mask[7] = {0x80, 0x08, 0x88, 0x22, 0xaa, 0x55, 0xff};
+ PNG_CONST PNG_IDAT;
+ PNG_CONST int png_pass_dsp_mask[7] = {0xff, 0x0f, 0xff, 0x33, 0xff, 0x55,
+ 0xff};
+ PNG_CONST int png_pass_mask[7] = {0x80, 0x08, 0x88, 0x22, 0xaa, 0x55, 0xff};
#endif
int ret;
if(png_ptr == NULL) return;
@@ -925,60 +924,60 @@ png_read_end(png_structp png_ptr, png_infop info_ptr)
do
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IHDR;
- PNG_IDAT;
- PNG_IEND;
- PNG_PLTE;
+ PNG_CONST PNG_IHDR;
+ PNG_CONST PNG_IDAT;
+ PNG_CONST PNG_IEND;
+ PNG_CONST PNG_PLTE;
#if defined(PNG_READ_bKGD_SUPPORTED)
- PNG_bKGD;
+ PNG_CONST PNG_bKGD;
#endif
#if defined(PNG_READ_cHRM_SUPPORTED)
- PNG_cHRM;
+ PNG_CONST PNG_cHRM;
#endif
#if defined(PNG_READ_gAMA_SUPPORTED)
- PNG_gAMA;
+ PNG_CONST PNG_gAMA;
#endif
#if defined(PNG_READ_hIST_SUPPORTED)
- PNG_hIST;
+ PNG_CONST PNG_hIST;
#endif
#if defined(PNG_READ_iCCP_SUPPORTED)
- PNG_iCCP;
+ PNG_CONST PNG_iCCP;
#endif
#if defined(PNG_READ_iTXt_SUPPORTED)
- PNG_iTXt;
+ PNG_CONST PNG_iTXt;
#endif
#if defined(PNG_READ_oFFs_SUPPORTED)
- PNG_oFFs;
+ PNG_CONST PNG_oFFs;
#endif
#if defined(PNG_READ_pCAL_SUPPORTED)
- PNG_pCAL;
+ PNG_CONST PNG_pCAL;
#endif
#if defined(PNG_READ_pHYs_SUPPORTED)
- PNG_pHYs;
+ PNG_CONST PNG_pHYs;
#endif
#if defined(PNG_READ_sBIT_SUPPORTED)
- PNG_sBIT;
+ PNG_CONST PNG_sBIT;
#endif
#if defined(PNG_READ_sCAL_SUPPORTED)
- PNG_sCAL;
+ PNG_CONST PNG_sCAL;
#endif
#if defined(PNG_READ_sPLT_SUPPORTED)
- PNG_sPLT;
+ PNG_CONST PNG_sPLT;
#endif
#if defined(PNG_READ_sRGB_SUPPORTED)
- PNG_sRGB;
+ PNG_CONST PNG_sRGB;
#endif
#if defined(PNG_READ_tEXt_SUPPORTED)
- PNG_tEXt;
+ PNG_CONST PNG_tEXt;
#endif
#if defined(PNG_READ_tIME_SUPPORTED)
- PNG_tIME;
+ PNG_CONST PNG_tIME;
#endif
#if defined(PNG_READ_tRNS_SUPPORTED)
- PNG_tRNS;
+ PNG_CONST PNG_tRNS;
#endif
#if defined(PNG_READ_zTXt_SUPPORTED)
- PNG_zTXt;
+ PNG_CONST PNG_zTXt;
#endif
#endif /* PNG_USE_LOCAL_ARRAYS */
@@ -1100,13 +1099,19 @@ png_destroy_read_struct(png_structpp png_ptr_ptr, png_infopp info_ptr_ptr,
png_structp png_ptr = NULL;
png_infop info_ptr = NULL, end_info_ptr = NULL;
#ifdef PNG_USER_MEM_SUPPORTED
- png_free_ptr free_fn;
- png_voidp mem_ptr;
+ png_free_ptr free_fn = NULL;
+ png_voidp mem_ptr = NULL;
#endif
png_debug(1, "in png_destroy_read_struct\n");
if (png_ptr_ptr != NULL)
+ {
png_ptr = *png_ptr_ptr;
+#ifdef PNG_USER_MEM_SUPPORTED
+ free_fn = png_ptr->free_fn;
+ mem_ptr = png_ptr->mem_ptr;
+#endif
+ }
if (info_ptr_ptr != NULL)
info_ptr = *info_ptr_ptr;
@@ -1114,11 +1119,6 @@ png_destroy_read_struct(png_structpp png_ptr_ptr, png_infopp info_ptr_ptr,
if (end_info_ptr_ptr != NULL)
end_info_ptr = *end_info_ptr_ptr;
-#ifdef PNG_USER_MEM_SUPPORTED
- free_fn = png_ptr->free_fn;
- mem_ptr = png_ptr->mem_ptr;
-#endif
-
png_read_destroy(png_ptr, info_ptr, end_info_ptr);
if (info_ptr != NULL)
@@ -1464,8 +1464,8 @@ png_read_png(png_structp png_ptr, png_infop info_ptr,
/* read rest of file, and get additional chunks in info_ptr - REQUIRED */
png_read_end(png_ptr, info_ptr);
- if(transforms == 0 || params == NULL)
- /* quiet compiler warnings */ return;
+ transforms = transforms; /* quiet compiler warnings */
+ params = params;
}
#endif /* PNG_INFO_IMAGE_SUPPORTED */
diff --git a/Build/source/libs/libpng/pngrtran.c b/Build/source/libs/libpng/pngrtran.c
index 6ef0a1c0730..cda392154e5 100644
--- a/Build/source/libs/libpng/pngrtran.c
+++ b/Build/source/libs/libpng/pngrtran.c
@@ -1,7 +1,7 @@
/* pngrtran.c - transforms the data in a row for PNG readers
*
- * Last changed in libpng 1.2.15 January 5, 2007
+ * Last changed in libpng 1.2.22 [October 13, 2007]
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -548,6 +548,9 @@ png_set_expand(png_structp png_ptr)
png_debug(1, "in png_set_expand\n");
if(png_ptr == NULL) return;
png_ptr->transformations |= (PNG_EXPAND | PNG_EXPAND_tRNS);
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ png_ptr->flags &= ~PNG_FLAG_ROW_INIT;
+#endif
}
/* GRR 19990627: the following three functions currently are identical
@@ -574,6 +577,9 @@ png_set_palette_to_rgb(png_structp png_ptr)
png_debug(1, "in png_set_palette_to_rgb\n");
if(png_ptr == NULL) return;
png_ptr->transformations |= (PNG_EXPAND | PNG_EXPAND_tRNS);
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ png_ptr->flags &= ~PNG_FLAG_ROW_INIT;
+#endif
}
#if !defined(PNG_1_0_X)
@@ -584,6 +590,9 @@ png_set_expand_gray_1_2_4_to_8(png_structp png_ptr)
png_debug(1, "in png_set_expand_gray_1_2_4_to_8\n");
if(png_ptr == NULL) return;
png_ptr->transformations |= PNG_EXPAND;
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ png_ptr->flags &= ~PNG_FLAG_ROW_INIT;
+#endif
}
#endif
@@ -604,8 +613,11 @@ png_set_gray_1_2_4_to_8(png_structp png_ptr)
void PNGAPI
png_set_tRNS_to_alpha(png_structp png_ptr)
{
- png_debug(1, "in png_set_expand\n");
+ png_debug(1, "in png_set_tRNS_to_alpha\n");
png_ptr->transformations |= (PNG_EXPAND | PNG_EXPAND_tRNS);
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ png_ptr->flags &= ~PNG_FLAG_ROW_INIT;
+#endif
}
#endif /* defined(PNG_READ_EXPAND_SUPPORTED) */
@@ -615,6 +627,9 @@ png_set_gray_to_rgb(png_structp png_ptr)
{
png_debug(1, "in png_set_gray_to_rgb\n");
png_ptr->transformations |= PNG_GRAY_TO_RGB;
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ png_ptr->flags &= ~PNG_FLAG_ROW_INIT;
+#endif
}
#endif
@@ -842,7 +857,7 @@ png_init_read_transformations(png_structp png_ptr)
k=1; /* partial transparency is present */
}
if (k == 0)
- png_ptr->transformations &= (~PNG_GAMMA);
+ png_ptr->transformations &= ~PNG_GAMMA;
}
if ((png_ptr->transformations & (PNG_GAMMA | PNG_RGB_TO_GRAY)) &&
@@ -1244,19 +1259,29 @@ void /* PRIVATE */
png_do_read_transformations(png_structp png_ptr)
{
png_debug(1, "in png_do_read_transformations\n");
-#if !defined(PNG_USELESS_TESTS_SUPPORTED)
if (png_ptr->row_buf == NULL)
{
#if !defined(PNG_NO_STDIO) && !defined(_WIN32_WCE)
char msg[50];
- sprintf(msg, "NULL row buffer for row %ld, pass %d", png_ptr->row_number,
+ png_snprintf2(msg, 50,
+ "NULL row buffer for row %ld, pass %d", png_ptr->row_number,
png_ptr->pass);
png_error(png_ptr, msg);
#else
png_error(png_ptr, "NULL row buffer");
#endif
}
+#ifdef PNG_WARN_UNINITIALIZED_ROW
+ if (!(png_ptr->flags & PNG_FLAG_ROW_INIT))
+ /* Application has failed to call either png_read_start_image()
+ * or png_read_update_info() after setting transforms that expand
+ * pixels. This check added to libpng-1.2.19 */
+#if (PNG_WARN_UNINITIALIZED_ROW==1)
+ png_error(png_ptr, "Uninitialized row");
+#else
+ png_warning(png_ptr, "Uninitialized row");
+#endif
#endif
#if defined(PNG_READ_EXPAND_SUPPORTED)
@@ -1269,7 +1294,8 @@ png_do_read_transformations(png_structp png_ptr)
}
else
{
- if (png_ptr->num_trans && (png_ptr->transformations & PNG_EXPAND_tRNS))
+ if (png_ptr->num_trans &&
+ (png_ptr->transformations & PNG_EXPAND_tRNS))
png_do_expand(&(png_ptr->row_info), png_ptr->row_buf + 1,
&(png_ptr->trans_values));
else
@@ -1293,9 +1319,11 @@ png_do_read_transformations(png_structp png_ptr)
if(rgb_error)
{
png_ptr->rgb_to_gray_status=1;
- if(png_ptr->transformations & PNG_RGB_TO_GRAY_WARN)
+ if((png_ptr->transformations & PNG_RGB_TO_GRAY) ==
+ PNG_RGB_TO_GRAY_WARN)
png_warning(png_ptr, "png_do_rgb_to_gray found nongray pixel");
- if(png_ptr->transformations & PNG_RGB_TO_GRAY_ERR)
+ if((png_ptr->transformations & PNG_RGB_TO_GRAY) ==
+ PNG_RGB_TO_GRAY_ERR)
png_error(png_ptr, "png_do_rgb_to_gray found nongray pixel");
}
}
@@ -3699,7 +3727,7 @@ png_do_expand(png_row_infop row_info, png_bytep row,
{
case 1:
{
- gray = (png_uint_16)(gray*0xff);
+ gray = (png_uint_16)((gray&0x01)*0xff);
sp = row + (png_size_t)((row_width - 1) >> 3);
dp = row + (png_size_t)row_width - 1;
shift = 7 - (int)((row_width + 7) & 0x07);
@@ -3723,7 +3751,7 @@ png_do_expand(png_row_infop row_info, png_bytep row,
}
case 2:
{
- gray = (png_uint_16)(gray*0x55);
+ gray = (png_uint_16)((gray&0x03)*0x55);
sp = row + (png_size_t)((row_width - 1) >> 2);
dp = row + (png_size_t)row_width - 1;
shift = (int)((3 - ((row_width + 3) & 0x03)) << 1);
@@ -3746,7 +3774,7 @@ png_do_expand(png_row_infop row_info, png_bytep row,
}
case 4:
{
- gray = (png_uint_16)(gray*0x11);
+ gray = (png_uint_16)((gray&0x0f)*0x11);
sp = row + (png_size_t)((row_width - 1) >> 1);
dp = row + (png_size_t)row_width - 1;
shift = (int)((1 - ((row_width + 1) & 0x01)) << 2);
@@ -3776,6 +3804,7 @@ png_do_expand(png_row_infop row_info, png_bytep row,
{
if (row_info->bit_depth == 8)
{
+ gray = gray & 0xff;
sp = row + (png_size_t)row_width - 1;
dp = row + (png_size_t)(row_width << 1) - 1;
for (i = 0; i < row_width; i++)
@@ -3789,12 +3818,13 @@ png_do_expand(png_row_infop row_info, png_bytep row,
}
else if (row_info->bit_depth == 16)
{
+ png_byte gray_high = (gray >> 8) & 0xff;
+ png_byte gray_low = gray & 0xff;
sp = row + row_info->rowbytes - 1;
dp = row + (row_info->rowbytes << 1) - 1;
for (i = 0; i < row_width; i++)
{
- if (((png_uint_16)*(sp) |
- ((png_uint_16)*(sp - 1) << 8)) == gray)
+ if (*(sp-1) == gray_high && *(sp) == gray_low)
{
*dp-- = 0;
*dp-- = 0;
@@ -3819,13 +3849,14 @@ png_do_expand(png_row_infop row_info, png_bytep row,
{
if (row_info->bit_depth == 8)
{
+ png_byte red = trans_value->red & 0xff;
+ png_byte green = trans_value->green & 0xff;
+ png_byte blue = trans_value->blue & 0xff;
sp = row + (png_size_t)row_info->rowbytes - 1;
dp = row + (png_size_t)(row_width << 2) - 1;
for (i = 0; i < row_width; i++)
{
- if (*(sp - 2) == trans_value->red &&
- *(sp - 1) == trans_value->green &&
- *(sp - 0) == trans_value->blue)
+ if (*(sp - 2) == red && *(sp - 1) == green && *(sp) == blue)
*dp-- = 0;
else
*dp-- = 0xff;
@@ -3836,16 +3867,22 @@ png_do_expand(png_row_infop row_info, png_bytep row,
}
else if (row_info->bit_depth == 16)
{
+ png_byte red_high = (trans_value->red >> 8) & 0xff;
+ png_byte green_high = (trans_value->green >> 8) & 0xff;
+ png_byte blue_high = (trans_value->blue >> 8) & 0xff;
+ png_byte red_low = trans_value->red & 0xff;
+ png_byte green_low = trans_value->green & 0xff;
+ png_byte blue_low = trans_value->blue & 0xff;
sp = row + row_info->rowbytes - 1;
dp = row + (png_size_t)(row_width << 3) - 1;
for (i = 0; i < row_width; i++)
{
- if ((((png_uint_16)*(sp - 4) |
- ((png_uint_16)*(sp - 5) << 8)) == trans_value->red) &&
- (((png_uint_16)*(sp - 2) |
- ((png_uint_16)*(sp - 3) << 8)) == trans_value->green) &&
- (((png_uint_16)*(sp - 0) |
- ((png_uint_16)*(sp - 1) << 8)) == trans_value->blue))
+ if (*(sp - 5) == red_high &&
+ *(sp - 4) == red_low &&
+ *(sp - 3) == green_high &&
+ *(sp - 2) == green_low &&
+ *(sp - 1) == blue_high &&
+ *(sp ) == blue_low)
{
*dp-- = 0;
*dp-- = 0;
@@ -3965,7 +4002,7 @@ png_do_dither(png_row_infop row_info, png_bytep row,
#ifdef PNG_FLOATING_POINT_SUPPORTED
#if defined(PNG_READ_GAMMA_SUPPORTED)
-const static int png_gamma_shift[] =
+static PNG_CONST int png_gamma_shift[] =
{0x10, 0x21, 0x42, 0x84, 0x110, 0x248, 0x550, 0xff0, 0x00};
/* We build the 8- or 16-bit gamma tables here. Note that for 16-bit
diff --git a/Build/source/libs/libpng/pngrutil.c b/Build/source/libs/libpng/pngrutil.c
index 2abca7cc54b..5e40aca481e 100644
--- a/Build/source/libs/libpng/pngrutil.c
+++ b/Build/source/libs/libpng/pngrutil.c
@@ -1,7 +1,7 @@
/* pngrutil.c - utilities to read a PNG file
*
- * Last changed in libpng 1.2.17 May 15, 2007
+ * Last changed in libpng 1.2.23 [November 6, 2007]
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -16,10 +16,14 @@
#if defined(PNG_READ_SUPPORTED)
+#if defined(_WIN32_WCE) && (_WIN32_WCE<0x500)
+# define WIN32_WCE_OLD
+#endif
+
#ifdef PNG_FLOATING_POINT_SUPPORTED
-# if defined(_WIN32_WCE)
+# if defined(WIN32_WCE_OLD)
/* strtod() function is not supported on WindowsCE */
-__inline double png_strtod(png_structp png_ptr, const char *nptr, char **endptr)
+__inline double png_strtod(png_structp png_ptr, PNG_CONST char *nptr, char **endptr)
{
double result = 0;
int len;
@@ -33,7 +37,7 @@ __inline double png_strtod(png_structp png_ptr, const char *nptr, char **endptr)
result = wcstod(str, &end);
len = WideCharToMultiByte(CP_ACP, 0, end, -1, NULL, 0, NULL, NULL);
*endptr = (char *)nptr + (png_strlen(nptr) - len + 1);
- png_free(str);
+ png_free(png_ptr, str);
}
return result;
}
@@ -181,7 +185,7 @@ png_decompress_chunk(png_structp png_ptr, int comp_type,
png_charp chunkdata, png_size_t chunklength,
png_size_t prefix_size, png_size_t *newlength)
{
- const static char msg[] = "Error decoding compressed text";
+ static PNG_CONST char msg[] = "Error decoding compressed text";
png_charp text;
png_size_t text_size;
@@ -282,13 +286,16 @@ png_decompress_chunk(png_structp png_ptr, int comp_type,
char umsg[52];
if (ret == Z_BUF_ERROR)
- sprintf(umsg,"Buffer error in compressed datastream in %s chunk",
+ png_snprintf(umsg, 52,
+ "Buffer error in compressed datastream in %s chunk",
png_ptr->chunk_name);
else if (ret == Z_DATA_ERROR)
- sprintf(umsg,"Data error in compressed datastream in %s chunk",
+ png_snprintf(umsg, 52,
+ "Data error in compressed datastream in %s chunk",
png_ptr->chunk_name);
else
- sprintf(umsg,"Incomplete compressed datastream in %s chunk",
+ png_snprintf(umsg, 52,
+ "Incomplete compressed datastream in %s chunk",
png_ptr->chunk_name);
png_warning(png_ptr, umsg);
#else
@@ -321,7 +328,8 @@ png_decompress_chunk(png_structp png_ptr, int comp_type,
#if !defined(PNG_NO_STDIO) && !defined(_WIN32_WCE)
char umsg[50];
- sprintf(umsg, "Unknown zTXt compression type %d", comp_type);
+ png_snprintf(umsg, 50,
+ "Unknown zTXt compression type %d", comp_type);
png_warning(png_ptr, umsg);
#else
png_warning(png_ptr, "Unknown zTXt compression type");
@@ -563,8 +571,7 @@ png_handle_IEND(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
}
png_crc_finish(png_ptr, length);
- if (&info_ptr == NULL) /* quiet compiler warnings about unused info_ptr */
- return;
+ info_ptr =info_ptr; /* quiet compiler warnings about unused info_ptr */
}
#if defined(PNG_READ_gAMA_SUPPORTED)
@@ -1037,7 +1044,7 @@ png_handle_iCCP(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
/* there should be at least one zero (the compression type byte)
following the separator, and we should be on it */
- if ( profile >= chunkdata + slength)
+ if ( profile >= chunkdata + slength - 1)
{
png_free(png_ptr, chunkdata);
png_warning(png_ptr, "Malformed iCCP chunk");
@@ -1141,7 +1148,7 @@ png_handle_sPLT(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
++entry_start;
/* a sample depth should follow the separator, and we should be on it */
- if (entry_start > chunkdata + slength)
+ if (entry_start > chunkdata + slength - 2)
{
png_free(png_ptr, chunkdata);
png_warning(png_ptr, "malformed sPLT chunk");
@@ -1234,9 +1241,15 @@ void /* PRIVATE */
png_handle_tRNS(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
{
png_byte readbuf[PNG_MAX_PALETTE_LENGTH];
+ int bit_mask;
png_debug(1, "in png_handle_tRNS\n");
+ /* For non-indexed color, mask off any bits in the tRNS value that
+ * exceed the bit depth. Some creators were writing extra bits there.
+ * This is not needed for indexed color. */
+ bit_mask = (1 << png_ptr->bit_depth) - 1;
+
if (!(png_ptr->mode & PNG_HAVE_IHDR))
png_error(png_ptr, "Missing IHDR before tRNS");
else if (png_ptr->mode & PNG_HAVE_IDAT)
@@ -1265,7 +1278,7 @@ png_handle_tRNS(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
png_crc_read(png_ptr, buf, 2);
png_ptr->num_trans = 1;
- png_ptr->trans_values.gray = png_get_uint_16(buf);
+ png_ptr->trans_values.gray = png_get_uint_16(buf) & bit_mask;
}
else if (png_ptr->color_type == PNG_COLOR_TYPE_RGB)
{
@@ -1279,9 +1292,9 @@ png_handle_tRNS(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
}
png_crc_read(png_ptr, buf, (png_size_t)length);
png_ptr->num_trans = 1;
- png_ptr->trans_values.red = png_get_uint_16(buf);
- png_ptr->trans_values.green = png_get_uint_16(buf + 2);
- png_ptr->trans_values.blue = png_get_uint_16(buf + 4);
+ png_ptr->trans_values.red = png_get_uint_16(buf) & bit_mask;
+ png_ptr->trans_values.green = png_get_uint_16(buf + 2) & bit_mask;
+ png_ptr->trans_values.blue = png_get_uint_16(buf + 4) & bit_mask;
}
else if (png_ptr->color_type == PNG_COLOR_TYPE_PALETTE)
{
@@ -1660,7 +1673,7 @@ png_handle_pCAL(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
buf++; /* Skip the null string terminator from previous parameter. */
png_debug1(3, "Reading pCAL parameter %d\n", i);
- for (params[i] = buf; *buf != 0x00 && buf <= endptr; buf++)
+ for (params[i] = buf; buf <= endptr && *buf != 0x00; buf++)
/* Empty loop to move past each parameter string */ ;
/* Make sure we haven't run out of data yet */
@@ -1758,6 +1771,17 @@ png_handle_sCAL(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
/* empty loop */ ;
ep++;
+ if (buffer + slength < ep)
+ {
+ png_warning(png_ptr, "Truncated sCAL chunk");
+#if defined(PNG_FIXED_POINT_SUPPORTED) && \
+ !defined(PNG_FLOATING_POINT_SUPPORTED)
+ png_free(png_ptr, swidth);
+#endif
+ png_free(png_ptr, buffer);
+ return;
+ }
+
#ifdef PNG_FLOATING_POINT_SUPPORTED
height = png_strtod(png_ptr, ep, &vp);
if (*vp)
@@ -1981,10 +2005,11 @@ png_handle_zTXt(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
/* empty loop */ ;
/* zTXt must have some text after the chunkdataword */
- if (text == chunkdata + slength)
+ if (text >= chunkdata + slength - 2)
{
- comp_type = PNG_TEXT_COMPRESSION_NONE;
- png_warning(png_ptr, "Zero length zTXt chunk");
+ png_warning(png_ptr, "Truncated zTXt chunk");
+ png_free(png_ptr, chunkdata);
+ return;
}
else
{
@@ -2084,10 +2109,11 @@ png_handle_iTXt(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
translated keyword (possibly empty), and possibly some text after the
keyword */
- if (lang >= chunkdata + slength)
+ if (lang >= chunkdata + slength - 3)
{
- comp_flag = PNG_TEXT_COMPRESSION_NONE;
- png_warning(png_ptr, "Zero length iTXt chunk");
+ png_warning(png_ptr, "Truncated iTXt chunk");
+ png_free(png_ptr, chunkdata);
+ return;
}
else
{
@@ -2099,9 +2125,22 @@ png_handle_iTXt(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
/* empty loop */ ;
lang_key++; /* skip NUL separator */
+ if (lang_key >= chunkdata + slength)
+ {
+ png_warning(png_ptr, "Truncated iTXt chunk");
+ png_free(png_ptr, chunkdata);
+ return;
+ }
+
for (text = lang_key; *text; text++)
/* empty loop */ ;
text++; /* skip NUL separator */
+ if (text >= chunkdata + slength)
+ {
+ png_warning(png_ptr, "Malformed iTXt chunk");
+ png_free(png_ptr, chunkdata);
+ return;
+ }
prefix_len = text - chunkdata;
@@ -2151,7 +2190,7 @@ png_handle_unknown(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
if (png_ptr->mode & PNG_HAVE_IDAT)
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IDAT;
+ PNG_CONST PNG_IDAT;
#endif
if (png_memcmp(png_ptr->chunk_name, png_IDAT, 4)) /* not an IDAT */
png_ptr->mode |= PNG_AFTER_IDAT;
@@ -2184,8 +2223,10 @@ png_handle_unknown(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
length = (png_uint_32)65535L;
}
#endif
- png_strcpy((png_charp)png_ptr->unknown_chunk.name,
- (png_charp)png_ptr->chunk_name);
+ png_memcpy((png_charp)png_ptr->unknown_chunk.name,
+ (png_charp)png_ptr->chunk_name,
+ png_sizeof(png_ptr->unknown_chunk.name));
+ png_ptr->unknown_chunk.name[png_sizeof(png_ptr->unknown_chunk.name)-1] = '\0';
png_ptr->unknown_chunk.data = (png_bytep)png_malloc(png_ptr, length);
png_ptr->unknown_chunk.size = (png_size_t)length;
png_crc_read(png_ptr, (png_bytep)png_ptr->unknown_chunk.data, length);
@@ -2221,8 +2262,7 @@ png_handle_unknown(png_structp png_ptr, png_infop info_ptr, png_uint_32 length)
png_crc_finish(png_ptr, skip);
#if !defined(PNG_READ_USER_CHUNKS_SUPPORTED)
- if (&info_ptr == NULL) /* quiet compiler warnings about unused info_ptr */
- return;
+ info_ptr = info_ptr; /* quiet compiler warnings about unused info_ptr */
#endif
}
@@ -2255,7 +2295,7 @@ png_check_chunk_name(png_structp png_ptr, png_bytep chunk_name)
a zero indicates the pixel is to be skipped. This is in addition
to any alpha or transparency value associated with the pixel. If
you want all pixels to be combined, pass 0xff (255) in mask. */
-#ifndef PNG_HAVE_MMX_COMBINE_ROW
+
void /* PRIVATE */
png_combine_row(png_structp png_ptr, png_bytep row, int mask)
{
@@ -2456,10 +2496,8 @@ png_combine_row(png_structp png_ptr, png_bytep row, int mask)
}
}
}
-#endif /* !PNG_HAVE_MMX_COMBINE_ROW */
#ifdef PNG_READ_INTERLACING_SUPPORTED
-#ifndef PNG_HAVE_MMX_READ_INTERLACE /* else in pngvcrd.c, pnggccrd.c */
/* OLD pre-1.0.9 interface:
void png_do_read_interlace(png_row_infop row_info, png_bytep row, int pass,
png_uint_32 transformations)
@@ -2474,10 +2512,10 @@ png_do_read_interlace(png_structp png_ptr)
#ifdef PNG_USE_LOCAL_ARRAYS
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
/* offset to next interlace block */
- const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
+ PNG_CONST int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
#endif
- png_debug(1,"in png_do_read_interlace (stock C version)\n");
+ png_debug(1,"in png_do_read_interlace\n");
if (row != NULL && row_info != NULL)
{
png_uint_32 final_width;
@@ -2681,14 +2719,11 @@ png_do_read_interlace(png_structp png_ptr)
row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width);
}
#if !defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (&transformations == NULL) /* silence compiler warning */
- return;
+ transformations = transformations; /* silence compiler warning */
#endif
}
-#endif /* !PNG_HAVE_MMX_READ_INTERLACE */
#endif /* PNG_READ_INTERLACING_SUPPORTED */
-#ifndef PNG_HAVE_MMX_READ_FILTER_ROW
void /* PRIVATE */
png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep row,
png_bytep prev_row, int filter)
@@ -2811,7 +2846,6 @@ png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep row,
break;
}
}
-#endif /* !PNG_HAVE_MMX_READ_FILTER_ROW */
void /* PRIVATE */
png_read_finish_row(png_structp png_ptr)
@@ -2820,16 +2854,16 @@ png_read_finish_row(png_structp png_ptr)
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
/* start of interlace block */
- const int png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0};
+ PNG_CONST int png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0};
/* offset to next interlace block */
- const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
+ PNG_CONST int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
/* start of interlace block in the y direction */
- const int png_pass_ystart[7] = {0, 0, 4, 0, 2, 0, 1};
+ PNG_CONST int png_pass_ystart[7] = {0, 0, 4, 0, 2, 0, 1};
/* offset to next interlace block in the y direction */
- const int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
+ PNG_CONST int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
#endif
png_debug(1, "in png_read_finish_row\n");
@@ -2840,7 +2874,8 @@ png_read_finish_row(png_structp png_ptr)
if (png_ptr->interlaced)
{
png_ptr->row_number = 0;
- png_memset_check(png_ptr, png_ptr->prev_row, 0, png_ptr->rowbytes + 1);
+ png_memset_check(png_ptr, png_ptr->prev_row, 0,
+ png_ptr->rowbytes + 1);
do
{
png_ptr->pass++;
@@ -2874,7 +2909,7 @@ png_read_finish_row(png_structp png_ptr)
if (!(png_ptr->flags & PNG_FLAG_ZLIB_FINISHED))
{
#ifdef PNG_USE_LOCAL_ARRAYS
- PNG_IDAT;
+ PNG_CONST PNG_IDAT;
#endif
char extra;
int ret;
@@ -2895,7 +2930,7 @@ png_read_finish_row(png_structp png_ptr)
png_ptr->idat_size = png_get_uint_31(png_ptr, chunk_length);
png_reset_crc(png_ptr);
png_crc_read(png_ptr, png_ptr->chunk_name, 4);
- if (png_memcmp(png_ptr->chunk_name, (png_bytep)png_IDAT, 4))
+ if (png_memcmp(png_ptr->chunk_name, png_IDAT, 4))
png_error(png_ptr, "Not enough image data");
}
@@ -2947,16 +2982,16 @@ png_read_start_row(png_structp png_ptr)
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
/* start of interlace block */
- const int png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0};
+ PNG_CONST int png_pass_start[7] = {0, 4, 0, 2, 0, 1, 0};
/* offset to next interlace block */
- const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
+ PNG_CONST int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
/* start of interlace block in the y direction */
- const int png_pass_ystart[7] = {0, 0, 4, 0, 2, 0, 1};
+ PNG_CONST int png_pass_ystart[7] = {0, 0, 4, 0, 2, 0, 1};
/* offset to next interlace block in the y direction */
- const int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
+ PNG_CONST int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
#endif
int max_pixel_depth;
@@ -3105,9 +3140,6 @@ defined(PNG_USER_TRANSFORM_PTR_SUPPORTED)
#endif
png_ptr->big_row_buf = (png_bytep)png_malloc(png_ptr, row_bytes+64);
png_ptr->row_buf = png_ptr->big_row_buf+32;
-#if defined(PNG_DEBUG) && defined(PNG_USE_PNGGCCRD)
- png_ptr->row_buf_size = row_bytes;
-#endif
#ifdef PNG_MAX_MALLOC_64K
if ((png_uint_32)png_ptr->rowbytes + 1 > (png_uint_32)65536L)
diff --git a/Build/source/libs/libpng/pngset.c b/Build/source/libs/libpng/pngset.c
index f1a1ef6100f..f8f9b7e3b3e 100644
--- a/Build/source/libs/libpng/pngset.c
+++ b/Build/source/libs/libpng/pngset.c
@@ -1,7 +1,7 @@
/* pngset.c - storage of image information into info struct
*
- * Last changed in libpng 1.2.17 May 15, 2007
+ * Last changed in libpng 1.2.24 [December 14, 2007]
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -41,7 +41,13 @@ png_set_cHRM(png_structp png_ptr, png_infop info_ptr,
png_debug1(1, "in %s storage function\n", "cHRM");
if (png_ptr == NULL || info_ptr == NULL)
return;
-
+ if (!(white_x || white_y || red_x || red_y || green_x || green_y ||
+ blue_x || blue_y))
+ {
+ png_warning(png_ptr,
+ "Ignoring attempt to set all-zero chromaticity values");
+ return;
+ }
if (white_x < 0.0 || white_y < 0.0 ||
red_x < 0.0 || red_y < 0.0 ||
green_x < 0.0 || green_y < 0.0 ||
@@ -93,6 +99,13 @@ png_set_cHRM_fixed(png_structp png_ptr, png_infop info_ptr,
if (png_ptr == NULL || info_ptr == NULL)
return;
+ if (!(white_x || white_y || red_x || red_y || green_x || green_y ||
+ blue_x || blue_y))
+ {
+ png_warning(png_ptr,
+ "Ignoring attempt to set all-zero chromaticity values");
+ return;
+ }
if (white_x < 0 || white_y < 0 ||
red_x < 0 || red_y < 0 ||
green_x < 0 || green_y < 0 ||
@@ -102,25 +115,14 @@ png_set_cHRM_fixed(png_structp png_ptr, png_infop info_ptr,
"Ignoring attempt to set negative chromaticity value");
return;
}
-#ifdef PNG_FLOATING_POINT_SUPPORTED
- if (white_x > (double) PNG_UINT_31_MAX ||
- white_y > (double) PNG_UINT_31_MAX ||
- red_x > (double) PNG_UINT_31_MAX ||
- red_y > (double) PNG_UINT_31_MAX ||
- green_x > (double) PNG_UINT_31_MAX ||
- green_y > (double) PNG_UINT_31_MAX ||
- blue_x > (double) PNG_UINT_31_MAX ||
- blue_y > (double) PNG_UINT_31_MAX)
-#else
- if (white_x > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- white_y > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- red_x > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- red_y > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- green_x > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- green_y > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- blue_x > (png_fixed_point) PNG_UINT_31_MAX/100000L ||
- blue_y > (png_fixed_point) PNG_UINT_31_MAX/100000L)
-#endif
+ if (white_x > (png_fixed_point) PNG_UINT_31_MAX ||
+ white_y > (png_fixed_point) PNG_UINT_31_MAX ||
+ red_x > (png_fixed_point) PNG_UINT_31_MAX ||
+ red_y > (png_fixed_point) PNG_UINT_31_MAX ||
+ green_x > (png_fixed_point) PNG_UINT_31_MAX ||
+ green_y > (png_fixed_point) PNG_UINT_31_MAX ||
+ blue_x > (png_fixed_point) PNG_UINT_31_MAX ||
+ blue_y > (png_fixed_point) PNG_UINT_31_MAX )
{
png_warning(png_ptr,
"Ignoring attempt to set chromaticity value exceeding 21474.83");
@@ -222,7 +224,7 @@ png_set_hIST(png_structp png_ptr, png_infop info_ptr, png_uint_16p hist)
png_debug1(1, "in %s storage function\n", "hIST");
if (png_ptr == NULL || info_ptr == NULL)
return;
- if (info_ptr->num_palette <= 0 || info_ptr->num_palette
+ if (info_ptr->num_palette == 0 || info_ptr->num_palette
> PNG_MAX_PALETTE_LENGTH)
{
png_warning(png_ptr,
@@ -353,7 +355,7 @@ png_set_IHDR(png_structp png_ptr, png_infop info_ptr,
info_ptr->pixel_depth = (png_byte)(info_ptr->channels * info_ptr->bit_depth);
/* check for potential overflow */
- if ( width > (PNG_UINT_32_MAX
+ if (width > (PNG_UINT_32_MAX
>> 3) /* 8-byte RGBA pixels */
- 64 /* bigrowbuf hack */
- 1 /* filter byte */
@@ -484,7 +486,8 @@ png_set_sCAL_s(png_structp png_ptr, png_infop info_ptr,
info_ptr->scal_s_width = (png_charp)png_malloc_warn(png_ptr, length);
if (info_ptr->scal_s_width == NULL)
{
- png_warning(png_ptr, "Memory allocation failed while processing sCAL.");
+ png_warning(png_ptr,
+ "Memory allocation failed while processing sCAL.");
}
png_memcpy(info_ptr->scal_s_width, swidth, (png_size_t)length);
@@ -494,7 +497,8 @@ png_set_sCAL_s(png_structp png_ptr, png_infop info_ptr,
if (info_ptr->scal_s_height == NULL)
{
png_free (png_ptr, info_ptr->scal_s_width);
- png_warning(png_ptr, "Memory allocation failed while processing sCAL.");
+ png_warning(png_ptr,
+ "Memory allocation failed while processing sCAL.");
}
png_memcpy(info_ptr->scal_s_height, sheight, (png_size_t)length);
@@ -677,18 +681,20 @@ png_set_iCCP(png_structp png_ptr, png_infop info_ptr,
{
png_charp new_iccp_name;
png_charp new_iccp_profile;
+ png_uint_32 length;
png_debug1(1, "in %s storage function\n", "iCCP");
if (png_ptr == NULL || info_ptr == NULL || name == NULL || profile == NULL)
return;
- new_iccp_name = (png_charp)png_malloc_warn(png_ptr, png_strlen(name)+1);
+ length = png_strlen(name)+1;
+ new_iccp_name = (png_charp)png_malloc_warn(png_ptr, length);
if (new_iccp_name == NULL)
{
png_warning(png_ptr, "Insufficient memory to process iCCP chunk.");
return;
}
- png_strcpy(new_iccp_name, name);
+ png_memcpy(new_iccp_name, name, length);
new_iccp_profile = (png_charp)png_malloc_warn(png_ptr, proflen);
if (new_iccp_profile == NULL)
{
@@ -877,9 +883,6 @@ png_set_text_2(png_structp png_ptr, png_infop info_ptr, png_textp text_ptr,
textp->itxt_length = 0;
#endif
}
-#if 0 /* appears to be redundant; */
- info_ptr->text[info_ptr->num_text]= *textp;
-#endif
info_ptr->num_text++;
png_debug1(3, "transferred text chunk %d\n", info_ptr->num_text);
}
@@ -972,14 +975,25 @@ png_set_sPLT(png_structp png_ptr,
{
png_sPLT_tp to = np + info_ptr->splt_palettes_num + i;
png_sPLT_tp from = entries + i;
+ png_uint_32 length;
- to->name = (png_charp)png_malloc(png_ptr,
- png_strlen(from->name) + 1);
- /* TODO: use png_malloc_warn */
- png_strcpy(to->name, from->name);
- to->entries = (png_sPLT_entryp)png_malloc(png_ptr,
+ length = png_strlen(from->name) + 1;
+ to->name = (png_charp)png_malloc_warn(png_ptr, length);
+ if (to->name == NULL)
+ {
+ png_warning(png_ptr,
+ "Out of memory while processing sPLT chunk");
+ }
+ png_memcpy(to->name, from->name, length);
+ to->entries = (png_sPLT_entryp)png_malloc_warn(png_ptr,
from->nentries * png_sizeof(png_sPLT_entry));
- /* TODO: use png_malloc_warn */
+ if (to->entries == NULL)
+ {
+ png_warning(png_ptr,
+ "Out of memory while processing sPLT chunk");
+ png_free(png_ptr,to->name);
+ to->name = NULL;
+ }
png_memcpy(to->entries, from->entries,
from->nentries * png_sizeof(png_sPLT_entry));
to->nentries = from->nentries;
@@ -1011,7 +1025,8 @@ png_set_unknown_chunks(png_structp png_ptr,
png_sizeof(png_unknown_chunk));
if (np == NULL)
{
- png_warning(png_ptr, "Out of memory while processing unknown chunk.");
+ png_warning(png_ptr,
+ "Out of memory while processing unknown chunk.");
return;
}
@@ -1025,11 +1040,16 @@ png_set_unknown_chunks(png_structp png_ptr,
png_unknown_chunkp to = np + info_ptr->unknown_chunks_num + i;
png_unknown_chunkp from = unknowns + i;
- png_strncpy((png_charp)to->name, (png_charp)from->name, 5);
+ png_memcpy((png_charp)to->name,
+ (png_charp)from->name,
+ png_sizeof(from->name));
+ to->name[png_sizeof(to->name)-1] = '\0';
+
to->data = (png_bytep)png_malloc_warn(png_ptr, from->size);
if (to->data == NULL)
{
- png_warning(png_ptr, "Out of memory processing unknown chunk.");
+ png_warning(png_ptr,
+ "Out of memory while processing unknown chunk.");
}
else
{
@@ -1069,7 +1089,7 @@ png_permit_empty_plte (png_structp png_ptr, int empty_plte_permitted)
if (png_ptr == NULL)
return;
png_ptr->mng_features_permitted = (png_byte)
- ((png_ptr->mng_features_permitted & (~(PNG_FLAG_MNG_EMPTY_PLTE))) |
+ ((png_ptr->mng_features_permitted & (~PNG_FLAG_MNG_EMPTY_PLTE)) |
((empty_plte_permitted & PNG_FLAG_MNG_EMPTY_PLTE)));
}
#endif
@@ -1183,57 +1203,19 @@ void PNGAPI
png_set_invalid(png_structp png_ptr, png_infop info_ptr, int mask)
{
if (png_ptr && info_ptr)
- info_ptr->valid &= ~(mask);
+ info_ptr->valid &= ~mask;
}
#ifndef PNG_1_0_X
#ifdef PNG_ASSEMBLER_CODE_SUPPORTED
-/* this function was added to libpng 1.2.0 and should always exist by default */
+/* function was added to libpng 1.2.0 and should always exist by default */
void PNGAPI
png_set_asm_flags (png_structp png_ptr, png_uint_32 asm_flags)
{
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_uint_32 settable_asm_flags;
- png_uint_32 settable_mmx_flags;
-#endif
- if (png_ptr == NULL)
- return;
-#ifdef PNG_MMX_CODE_SUPPORTED
-
- settable_mmx_flags =
-#ifdef PNG_HAVE_MMX_COMBINE_ROW
- PNG_ASM_FLAG_MMX_READ_COMBINE_ROW |
-#endif
-#ifdef PNG_HAVE_MMX_READ_INTERLACE
- PNG_ASM_FLAG_MMX_READ_INTERLACE |
-#endif
-#ifdef PNG_HAVE_MMX_READ_FILTER_ROW
- PNG_ASM_FLAG_MMX_READ_FILTER_SUB |
- PNG_ASM_FLAG_MMX_READ_FILTER_UP |
- PNG_ASM_FLAG_MMX_READ_FILTER_AVG |
- PNG_ASM_FLAG_MMX_READ_FILTER_PAETH |
-#endif
- 0;
-
- /* could be some non-MMX ones in the future, but not currently: */
- settable_asm_flags = settable_mmx_flags;
-
- if (!(png_ptr->asm_flags & PNG_ASM_FLAG_MMX_SUPPORT_COMPILED) ||
- !(png_ptr->asm_flags & PNG_ASM_FLAG_MMX_SUPPORT_IN_CPU))
- {
- /* clear all MMX flags if MMX isn't supported */
- settable_asm_flags &= ~settable_mmx_flags;
- png_ptr->asm_flags &= ~settable_mmx_flags;
- }
-
- /* we're replacing the settable bits with those passed in by the user,
- * so first zero them out of the master copy, then bitwise-OR in the
- * allowed subset that was requested */
-
- png_ptr->asm_flags &= ~settable_asm_flags; /* zero them */
- png_ptr->asm_flags |= (asm_flags & settable_asm_flags); /* set them */
-#endif /* ?PNG_MMX_CODE_SUPPORTED */
+/* Obsolete as of libpng-1.2.20 and will be removed from libpng-1.4.0 */
+ if (png_ptr != NULL)
+ png_ptr->asm_flags = 0;
}
/* this function was added to libpng 1.2.0 */
@@ -1242,12 +1224,9 @@ png_set_mmx_thresholds (png_structp png_ptr,
png_byte mmx_bitdepth_threshold,
png_uint_32 mmx_rowbytes_threshold)
{
+/* Obsolete as of libpng-1.2.20 and will be removed from libpng-1.4.0 */
if (png_ptr == NULL)
return;
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_ptr->mmx_bitdepth_threshold = mmx_bitdepth_threshold;
- png_ptr->mmx_rowbytes_threshold = mmx_rowbytes_threshold;
-#endif /* ?PNG_MMX_CODE_SUPPORTED */
}
#endif /* ?PNG_ASSEMBLER_CODE_SUPPORTED */
diff --git a/Build/source/libs/libpng/pngtest.c b/Build/source/libs/libpng/pngtest.c
index 299e2947de2..dd2946bf46f 100644
--- a/Build/source/libs/libpng/pngtest.c
+++ b/Build/source/libs/libpng/pngtest.c
@@ -1,9 +1,9 @@
/* pngtest.c - a simple test program to test libpng
*
- * Last changed in libpng 1.2.6 - August 15, 2004
+ * Last changed in libpng 1.2.23 - [November 6, 2007]
* For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2004 Glenn Randers-Pehrson
+ * Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
* (Version 0.88 Copyright (c) 1995, 1996 Guy Eric Schalnat, Group 42, Inc.)
*
@@ -82,8 +82,9 @@ static float t_start, t_stop, t_decode, t_encode, t_misc;
#endif
#if defined(PNG_TIME_RFC1123_SUPPORTED)
+#define PNG_tIME_STRING_LENGTH 30
static int tIME_chunk_present=0;
-static char tIME_string[30] = "no tIME chunk present in file";
+static char tIME_string[PNG_tIME_STRING_LENGTH] = "no tIME chunk present in file";
#endif
static int verbose = 0;
@@ -434,8 +435,9 @@ pngtest_write_data(png_structp png_ptr, png_bytep data, png_size_t length)
png_error(png_ptr, "Write Error");
}
}
-
#endif /* USE_FAR_KEYWORD */
+#endif /* PNG_NO_STDIO */
+/* END of code to validate stdio-free compilation */
/* This function is called when there is a warning, but the library thinks
* it can continue anyway. Replacement functions don't have to do anything
@@ -463,8 +465,6 @@ pngtest_error(png_structp png_ptr, png_const_charp message)
/* We can return because png_error calls the default handler, which is
* actually OK in this case. */
}
-#endif /* PNG_NO_STDIO */
-/* END of code to validate stdio-free compilation */
/* START of code to validate memory allocation and deallocation */
#if defined(PNG_USER_MEM_SUPPORTED) && PNG_DEBUG
@@ -658,10 +658,8 @@ test_one_file(PNG_CONST char *inname, PNG_CONST char *outname)
read_ptr = png_create_read_struct(PNG_LIBPNG_VER_STRING, png_voidp_NULL,
png_error_ptr_NULL, png_error_ptr_NULL);
#endif
-#if defined(PNG_NO_STDIO)
png_set_error_fn(read_ptr, (png_voidp)inname, pngtest_error,
pngtest_warning);
-#endif
#ifdef PNG_WRITE_SUPPORTED
#if defined(PNG_USER_MEM_SUPPORTED) && PNG_DEBUG
write_ptr = png_create_write_struct_2(PNG_LIBPNG_VER_STRING, png_voidp_NULL,
@@ -671,11 +669,9 @@ test_one_file(PNG_CONST char *inname, PNG_CONST char *outname)
write_ptr = png_create_write_struct(PNG_LIBPNG_VER_STRING, png_voidp_NULL,
png_error_ptr_NULL, png_error_ptr_NULL);
#endif
-#if defined(PNG_NO_STDIO)
png_set_error_fn(write_ptr, (png_voidp)inname, pngtest_error,
pngtest_warning);
#endif
-#endif
png_debug(0, "Allocating read_info, write_info and end_info structures\n");
read_info_ptr = png_create_info_struct(read_ptr);
end_info_ptr = png_create_info_struct(read_ptr);
@@ -1007,10 +1003,13 @@ test_one_file(PNG_CONST char *inname, PNG_CONST char *outname)
{
png_set_tIME(write_ptr, write_info_ptr, mod_time);
#if defined(PNG_TIME_RFC1123_SUPPORTED)
- /* we have to use png_strcpy instead of "=" because the string
+ /* we have to use png_memcpy instead of "=" because the string
pointed to by png_convert_to_rfc1123() gets free'ed before
we use it */
- png_strcpy(tIME_string,png_convert_to_rfc1123(read_ptr, mod_time));
+ png_memcpy(tIME_string,
+ png_convert_to_rfc1123(read_ptr, mod_time),
+ png_sizeof(tIME_string));
+ tIME_string[png_sizeof(tIME_string)-1] = '\0';
tIME_chunk_present++;
#endif /* PNG_TIME_RFC1123_SUPPORTED */
}
@@ -1147,10 +1146,13 @@ test_one_file(PNG_CONST char *inname, PNG_CONST char *outname)
{
png_set_tIME(write_ptr, write_end_info_ptr, mod_time);
#if defined(PNG_TIME_RFC1123_SUPPORTED)
- /* we have to use png_strcpy instead of "=" because the string
+ /* we have to use png_memcpy instead of "=" because the string
pointed to by png_convert_to_rfc1123() gets free'ed before
we use it */
- png_strcpy(tIME_string,png_convert_to_rfc1123(read_ptr, mod_time));
+ png_memcpy(tIME_string,
+ png_convert_to_rfc1123(read_ptr, mod_time),
+ png_sizeof(tIME_string));
+ tIME_string[png_sizeof(tIME_string)-1] = '\0';
tIME_chunk_present++;
#endif /* PNG_TIME_RFC1123_SUPPORTED */
}
@@ -1551,4 +1553,4 @@ main(int argc, char *argv[])
}
/* Generate a compiler error if there is an old png.h in the search path. */
-typedef version_1_2_18 your_png_h_is_not_version_1_2_18;
+typedef version_1_2_24 your_png_h_is_not_version_1_2_24;
diff --git a/Build/source/libs/libpng/pngtrans.c b/Build/source/libs/libpng/pngtrans.c
index 8cb4b886165..1640095020c 100644
--- a/Build/source/libs/libpng/pngtrans.c
+++ b/Build/source/libs/libpng/pngtrans.c
@@ -1,9 +1,9 @@
/* pngtrans.c - transforms the data in a row (used by both readers and writers)
*
- * Last changed in libpng 1.2.13 November 13, 2006
+ * Last changed in libpng 1.2.17 May 15, 2007
* For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2006 Glenn Randers-Pehrson
+ * Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
* (Version 0.88 Copyright (c) 1995, 1996 Guy Eric Schalnat, Group 42, Inc.)
*/
@@ -252,7 +252,7 @@ png_do_swap(png_row_infop row_info, png_bytep row)
#endif
#if defined(PNG_READ_PACKSWAP_SUPPORTED)||defined(PNG_WRITE_PACKSWAP_SUPPORTED)
-const static PNG_CONST png_byte onebppswaptable[256] = {
+static PNG_CONST png_byte onebppswaptable[256] = {
0x00, 0x80, 0x40, 0xC0, 0x20, 0xA0, 0x60, 0xE0,
0x10, 0x90, 0x50, 0xD0, 0x30, 0xB0, 0x70, 0xF0,
0x08, 0x88, 0x48, 0xC8, 0x28, 0xA8, 0x68, 0xE8,
@@ -287,7 +287,7 @@ const static PNG_CONST png_byte onebppswaptable[256] = {
0x1F, 0x9F, 0x5F, 0xDF, 0x3F, 0xBF, 0x7F, 0xFF
};
-const static PNG_CONST png_byte twobppswaptable[256] = {
+static PNG_CONST png_byte twobppswaptable[256] = {
0x00, 0x40, 0x80, 0xC0, 0x10, 0x50, 0x90, 0xD0,
0x20, 0x60, 0xA0, 0xE0, 0x30, 0x70, 0xB0, 0xF0,
0x04, 0x44, 0x84, 0xC4, 0x14, 0x54, 0x94, 0xD4,
@@ -322,7 +322,7 @@ const static PNG_CONST png_byte twobppswaptable[256] = {
0x2F, 0x6F, 0xAF, 0xEF, 0x3F, 0x7F, 0xBF, 0xFF
};
-const static PNG_CONST png_byte fourbppswaptable[256] = {
+static PNG_CONST png_byte fourbppswaptable[256] = {
0x00, 0x10, 0x20, 0x30, 0x40, 0x50, 0x60, 0x70,
0x80, 0x90, 0xA0, 0xB0, 0xC0, 0xD0, 0xE0, 0xF0,
0x01, 0x11, 0x21, 0x31, 0x41, 0x51, 0x61, 0x71,
diff --git a/Build/source/libs/libpng/pngvcrd.c b/Build/source/libs/libpng/pngvcrd.c
index d1c6405e5fe..ce4233efe7e 100644
--- a/Build/source/libs/libpng/pngvcrd.c
+++ b/Build/source/libs/libpng/pngvcrd.c
@@ -1,3904 +1 @@
-
-/* pngvcrd.c - mixed C/assembler version of utilities to read a PNG file
- *
- * For Intel x86 CPU and Microsoft Visual C++ compiler
- *
- * Last changed in libpng 1.2.6 - August 15, 2004
- * For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2004 Glenn Randers-Pehrson
- * Copyright (c) 1998, Intel Corporation
- *
- * Contributed by Nirav Chhatrapati, Intel Corporation, 1998
- * Interface to libpng contributed by Gilles Vollant, 1999
- *
- *
- * In png_do_read_interlace() in libpng versions 1.0.3a through 1.0.4d,
- * a sign error in the post-MMX cleanup code for each pixel_depth resulted
- * in bad pixels at the beginning of some rows of some images, and also
- * (due to out-of-range memory reads and writes) caused heap corruption
- * when compiled with MSVC 6.0. The error was fixed in version 1.0.4e.
- *
- * [png_read_filter_row_mmx_avg() bpp == 2 bugfix, GRR 20000916]
- *
- * [runtime MMX configuration, GRR 20010102]
- *
- */
-
-#define PNG_INTERNAL
-#include "png.h"
-
-#if defined(PNG_ASSEMBLER_CODE_SUPPORTED) && defined(PNG_USE_PNGVCRD)
-
-static int mmx_supported=2;
-
-
-int PNGAPI
-png_mmx_support(void)
-{
- int mmx_supported_local = 0;
- _asm {
- push ebx //CPUID will trash these
- push ecx
- push edx
-
- pushfd //Save Eflag to stack
- pop eax //Get Eflag from stack into eax
- mov ecx, eax //Make another copy of Eflag in ecx
- xor eax, 0x200000 //Toggle ID bit in Eflag [i.e. bit(21)]
- push eax //Save modified Eflag back to stack
-
- popfd //Restored modified value back to Eflag reg
- pushfd //Save Eflag to stack
- pop eax //Get Eflag from stack
- push ecx // save original Eflag to stack
- popfd // restore original Eflag
- xor eax, ecx //Compare the new Eflag with the original Eflag
- jz NOT_SUPPORTED //If the same, CPUID instruction is not supported,
- //skip following instructions and jump to
- //NOT_SUPPORTED label
-
- xor eax, eax //Set eax to zero
-
- _asm _emit 0x0f //CPUID instruction (two bytes opcode)
- _asm _emit 0xa2
-
- cmp eax, 1 //make sure eax return non-zero value
- jl NOT_SUPPORTED //If eax is zero, mmx not supported
-
- xor eax, eax //set eax to zero
- inc eax //Now increment eax to 1. This instruction is
- //faster than the instruction "mov eax, 1"
-
- _asm _emit 0x0f //CPUID instruction
- _asm _emit 0xa2
-
- and edx, 0x00800000 //mask out all bits but mmx bit(24)
- cmp edx, 0 // 0 = mmx not supported
- jz NOT_SUPPORTED // non-zero = Yes, mmx IS supported
-
- mov mmx_supported_local, 1 //set return value to 1
-
-NOT_SUPPORTED:
- mov eax, mmx_supported_local //move return value to eax
- pop edx //CPUID trashed these
- pop ecx
- pop ebx
- }
-
- //mmx_supported_local=0; // test code for force don't support MMX
- //printf("MMX : %u (1=MMX supported)\n",mmx_supported_local);
-
- mmx_supported = mmx_supported_local;
- return mmx_supported_local;
-}
-
-/* Combines the row recently read in with the previous row.
- This routine takes care of alpha and transparency if requested.
- This routine also handles the two methods of progressive display
- of interlaced images, depending on the mask value.
- The mask value describes which pixels are to be combined with
- the row. The pattern always repeats every 8 pixels, so just 8
- bits are needed. A one indicates the pixel is to be combined; a
- zero indicates the pixel is to be skipped. This is in addition
- to any alpha or transparency value associated with the pixel. If
- you want all pixels to be combined, pass 0xff (255) in mask. */
-
-/* Use this routine for x86 platform - uses faster MMX routine if machine
- supports MMX */
-
-void /* PRIVATE */
-png_combine_row(png_structp png_ptr, png_bytep row, int mask)
-{
-#ifdef PNG_USE_LOCAL_ARRAYS
- const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
-#endif
-
- png_debug(1,"in png_combine_row_asm\n");
-
- if (mmx_supported == 2) {
-#if !defined(PNG_1_0_X)
- /* this should have happened in png_init_mmx_flags() already */
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-
- if (mask == 0xff)
- {
- png_memcpy(row, png_ptr->row_buf + 1,
- (png_size_t)PNG_ROWBYTES(png_ptr->row_info.pixel_depth,
- png_ptr->width));
- }
- /* GRR: add "else if (mask == 0)" case?
- * or does png_combine_row() not even get called in that case? */
- else
- {
- switch (png_ptr->row_info.pixel_depth)
- {
- case 1:
- {
- png_bytep sp;
- png_bytep dp;
- int s_inc, s_start, s_end;
- int m;
- int shift;
- png_uint_32 i;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 7;
- s_inc = 1;
- }
- else
-#endif
- {
- s_start = 7;
- s_end = 0;
- s_inc = -1;
- }
-
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- int value;
-
- value = (*sp >> shift) & 0x1;
- *dp &= (png_byte)((0x7f7f >> (7 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
-
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 2:
- {
- png_bytep sp;
- png_bytep dp;
- int s_start, s_end, s_inc;
- int m;
- int shift;
- png_uint_32 i;
- int value;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 6;
- s_inc = 2;
- }
- else
-#endif
- {
- s_start = 6;
- s_end = 0;
- s_inc = -2;
- }
-
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- value = (*sp >> shift) & 0x3;
- *dp &= (png_byte)((0x3f3f >> (6 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 4:
- {
- png_bytep sp;
- png_bytep dp;
- int s_start, s_end, s_inc;
- int m;
- int shift;
- png_uint_32 i;
- int value;
-
- sp = png_ptr->row_buf + 1;
- dp = row;
- m = 0x80;
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (png_ptr->transformations & PNG_PACKSWAP)
- {
- s_start = 0;
- s_end = 4;
- s_inc = 4;
- }
- else
-#endif
- {
- s_start = 4;
- s_end = 0;
- s_inc = -4;
- }
- shift = s_start;
-
- for (i = 0; i < png_ptr->width; i++)
- {
- if (m & mask)
- {
- value = (*sp >> shift) & 0xf;
- *dp &= (png_byte)((0xf0f >> (4 - shift)) & 0xff);
- *dp |= (png_byte)(value << shift);
- }
-
- if (shift == s_end)
- {
- shift = s_start;
- sp++;
- dp++;
- }
- else
- shift += s_inc;
- if (m == 1)
- m = 0x80;
- else
- m >>= 1;
- }
- break;
- }
-
- case 8:
- {
- png_bytep srcptr;
- png_bytep dstptr;
- png_uint_32 len;
- int m;
- int diff, unmask;
-
- __int64 mask0=0x0102040810204080;
-
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
- m = 0x80;
- unmask = ~mask;
- len = png_ptr->width &~7; //reduce to multiple of 8
- diff = png_ptr->width & 7; //amount lost
-
- _asm
- {
- movd mm7, unmask //load bit pattern
- psubb mm6,mm6 //zero mm6
- punpcklbw mm7,mm7
- punpcklwd mm7,mm7
- punpckldq mm7,mm7 //fill register with 8 masks
-
- movq mm0,mask0
-
- pand mm0,mm7 //nonzero if keep byte
- pcmpeqb mm0,mm6 //zeros->1s, v versa
-
- mov ecx,len //load length of line (pixels)
- mov esi,srcptr //load source
- mov ebx,dstptr //load dest
- cmp ecx,0 //lcr
- je mainloop8end
-
-mainloop8:
- movq mm4,[esi]
- pand mm4,mm0
- movq mm6,mm0
- pandn mm6,[ebx]
- por mm4,mm6
- movq [ebx],mm4
-
- add esi,8 //inc by 8 bytes processed
- add ebx,8
- sub ecx,8 //dec by 8 pixels processed
-
- ja mainloop8
-mainloop8end:
-
- mov ecx,diff
- cmp ecx,0
- jz end8
-
- mov edx,mask
- sal edx,24 //make low byte the high byte
-
-secondloop8:
- sal edx,1 //move high bit to CF
- jnc skip8 //if CF = 0
- mov al,[esi]
- mov [ebx],al
-skip8:
- inc esi
- inc ebx
-
- dec ecx
- jnz secondloop8
-end8:
- emms
- }
- }
- else /* mmx not supported - use modified C routine */
- {
- register unsigned int incr1, initial_val, final_val;
- png_size_t pixel_bytes;
- png_uint_32 i;
- register int disp = png_pass_inc[png_ptr->pass];
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dstptr, srcptr, pixel_bytes);
- srcptr += incr1;
- dstptr += incr1;
- }
- } /* end of else */
-
- break;
- } // end 8 bpp
-
- case 16:
- {
- png_bytep srcptr;
- png_bytep dstptr;
- png_uint_32 len;
- int unmask, diff;
- __int64 mask1=0x0101020204040808,
- mask0=0x1010202040408080;
-
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
-
- unmask = ~mask;
- len = (png_ptr->width)&~7;
- diff = (png_ptr->width)&7;
- _asm
- {
- movd mm7, unmask //load bit pattern
- psubb mm6,mm6 //zero mm6
- punpcklbw mm7,mm7
- punpcklwd mm7,mm7
- punpckldq mm7,mm7 //fill register with 8 masks
-
- movq mm0,mask0
- movq mm1,mask1
-
- pand mm0,mm7
- pand mm1,mm7
-
- pcmpeqb mm0,mm6
- pcmpeqb mm1,mm6
-
- mov ecx,len //load length of line
- mov esi,srcptr //load source
- mov ebx,dstptr //load dest
- cmp ecx,0 //lcr
- jz mainloop16end
-
-mainloop16:
- movq mm4,[esi]
- pand mm4,mm0
- movq mm6,mm0
- movq mm7,[ebx]
- pandn mm6,mm7
- por mm4,mm6
- movq [ebx],mm4
-
- movq mm5,[esi+8]
- pand mm5,mm1
- movq mm7,mm1
- movq mm6,[ebx+8]
- pandn mm7,mm6
- por mm5,mm7
- movq [ebx+8],mm5
-
- add esi,16 //inc by 16 bytes processed
- add ebx,16
- sub ecx,8 //dec by 8 pixels processed
-
- ja mainloop16
-
-mainloop16end:
- mov ecx,diff
- cmp ecx,0
- jz end16
-
- mov edx,mask
- sal edx,24 //make low byte the high byte
-secondloop16:
- sal edx,1 //move high bit to CF
- jnc skip16 //if CF = 0
- mov ax,[esi]
- mov [ebx],ax
-skip16:
- add esi,2
- add ebx,2
-
- dec ecx
- jnz secondloop16
-end16:
- emms
- }
- }
- else /* mmx not supported - use modified C routine */
- {
- register unsigned int incr1, initial_val, final_val;
- png_size_t pixel_bytes;
- png_uint_32 i;
- register int disp = png_pass_inc[png_ptr->pass];
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dstptr, srcptr, pixel_bytes);
- srcptr += incr1;
- dstptr += incr1;
- }
- } /* end of else */
-
- break;
- } // end 16 bpp
-
- case 24:
- {
- png_bytep srcptr;
- png_bytep dstptr;
- png_uint_32 len;
- int unmask, diff;
-
- __int64 mask2=0x0101010202020404, //24bpp
- mask1=0x0408080810101020,
- mask0=0x2020404040808080;
-
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
-
- unmask = ~mask;
- len = (png_ptr->width)&~7;
- diff = (png_ptr->width)&7;
-
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- _asm
- {
- movd mm7, unmask //load bit pattern
- psubb mm6,mm6 //zero mm6
- punpcklbw mm7,mm7
- punpcklwd mm7,mm7
- punpckldq mm7,mm7 //fill register with 8 masks
-
- movq mm0,mask0
- movq mm1,mask1
- movq mm2,mask2
-
- pand mm0,mm7
- pand mm1,mm7
- pand mm2,mm7
-
- pcmpeqb mm0,mm6
- pcmpeqb mm1,mm6
- pcmpeqb mm2,mm6
-
- mov ecx,len //load length of line
- mov esi,srcptr //load source
- mov ebx,dstptr //load dest
- cmp ecx,0
- jz mainloop24end
-
-mainloop24:
- movq mm4,[esi]
- pand mm4,mm0
- movq mm6,mm0
- movq mm7,[ebx]
- pandn mm6,mm7
- por mm4,mm6
- movq [ebx],mm4
-
-
- movq mm5,[esi+8]
- pand mm5,mm1
- movq mm7,mm1
- movq mm6,[ebx+8]
- pandn mm7,mm6
- por mm5,mm7
- movq [ebx+8],mm5
-
- movq mm6,[esi+16]
- pand mm6,mm2
- movq mm4,mm2
- movq mm7,[ebx+16]
- pandn mm4,mm7
- por mm6,mm4
- movq [ebx+16],mm6
-
- add esi,24 //inc by 24 bytes processed
- add ebx,24
- sub ecx,8 //dec by 8 pixels processed
-
- ja mainloop24
-
-mainloop24end:
- mov ecx,diff
- cmp ecx,0
- jz end24
-
- mov edx,mask
- sal edx,24 //make low byte the high byte
-secondloop24:
- sal edx,1 //move high bit to CF
- jnc skip24 //if CF = 0
- mov ax,[esi]
- mov [ebx],ax
- xor eax,eax
- mov al,[esi+2]
- mov [ebx+2],al
-skip24:
- add esi,3
- add ebx,3
-
- dec ecx
- jnz secondloop24
-
-end24:
- emms
- }
- }
- else /* mmx not supported - use modified C routine */
- {
- register unsigned int incr1, initial_val, final_val;
- png_size_t pixel_bytes;
- png_uint_32 i;
- register int disp = png_pass_inc[png_ptr->pass];
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dstptr, srcptr, pixel_bytes);
- srcptr += incr1;
- dstptr += incr1;
- }
- } /* end of else */
-
- break;
- } // end 24 bpp
-
- case 32:
- {
- png_bytep srcptr;
- png_bytep dstptr;
- png_uint_32 len;
- int unmask, diff;
-
- __int64 mask3=0x0101010102020202, //32bpp
- mask2=0x0404040408080808,
- mask1=0x1010101020202020,
- mask0=0x4040404080808080;
-
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
-
- unmask = ~mask;
- len = (png_ptr->width)&~7;
- diff = (png_ptr->width)&7;
-
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- _asm
- {
- movd mm7, unmask //load bit pattern
- psubb mm6,mm6 //zero mm6
- punpcklbw mm7,mm7
- punpcklwd mm7,mm7
- punpckldq mm7,mm7 //fill register with 8 masks
-
- movq mm0,mask0
- movq mm1,mask1
- movq mm2,mask2
- movq mm3,mask3
-
- pand mm0,mm7
- pand mm1,mm7
- pand mm2,mm7
- pand mm3,mm7
-
- pcmpeqb mm0,mm6
- pcmpeqb mm1,mm6
- pcmpeqb mm2,mm6
- pcmpeqb mm3,mm6
-
- mov ecx,len //load length of line
- mov esi,srcptr //load source
- mov ebx,dstptr //load dest
-
- cmp ecx,0 //lcr
- jz mainloop32end
-
-mainloop32:
- movq mm4,[esi]
- pand mm4,mm0
- movq mm6,mm0
- movq mm7,[ebx]
- pandn mm6,mm7
- por mm4,mm6
- movq [ebx],mm4
-
- movq mm5,[esi+8]
- pand mm5,mm1
- movq mm7,mm1
- movq mm6,[ebx+8]
- pandn mm7,mm6
- por mm5,mm7
- movq [ebx+8],mm5
-
- movq mm6,[esi+16]
- pand mm6,mm2
- movq mm4,mm2
- movq mm7,[ebx+16]
- pandn mm4,mm7
- por mm6,mm4
- movq [ebx+16],mm6
-
- movq mm7,[esi+24]
- pand mm7,mm3
- movq mm5,mm3
- movq mm4,[ebx+24]
- pandn mm5,mm4
- por mm7,mm5
- movq [ebx+24],mm7
-
- add esi,32 //inc by 32 bytes processed
- add ebx,32
- sub ecx,8 //dec by 8 pixels processed
-
- ja mainloop32
-
-mainloop32end:
- mov ecx,diff
- cmp ecx,0
- jz end32
-
- mov edx,mask
- sal edx,24 //make low byte the high byte
-secondloop32:
- sal edx,1 //move high bit to CF
- jnc skip32 //if CF = 0
- mov eax,[esi]
- mov [ebx],eax
-skip32:
- add esi,4
- add ebx,4
-
- dec ecx
- jnz secondloop32
-
-end32:
- emms
- }
- }
- else /* mmx _not supported - Use modified C routine */
- {
- register unsigned int incr1, initial_val, final_val;
- png_size_t pixel_bytes;
- png_uint_32 i;
- register int disp = png_pass_inc[png_ptr->pass];
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dstptr, srcptr, pixel_bytes);
- srcptr += incr1;
- dstptr += incr1;
- }
- } /* end of else */
-
- break;
- } // end 32 bpp
-
- case 48:
- {
- png_bytep srcptr;
- png_bytep dstptr;
- png_uint_32 len;
- int unmask, diff;
-
- __int64 mask5=0x0101010101010202,
- mask4=0x0202020204040404,
- mask3=0x0404080808080808,
- mask2=0x1010101010102020,
- mask1=0x2020202040404040,
- mask0=0x4040808080808080;
-
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_COMBINE_ROW)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- srcptr = png_ptr->row_buf + 1;
- dstptr = row;
-
- unmask = ~mask;
- len = (png_ptr->width)&~7;
- diff = (png_ptr->width)&7;
- _asm
- {
- movd mm7, unmask //load bit pattern
- psubb mm6,mm6 //zero mm6
- punpcklbw mm7,mm7
- punpcklwd mm7,mm7
- punpckldq mm7,mm7 //fill register with 8 masks
-
- movq mm0,mask0
- movq mm1,mask1
- movq mm2,mask2
- movq mm3,mask3
- movq mm4,mask4
- movq mm5,mask5
-
- pand mm0,mm7
- pand mm1,mm7
- pand mm2,mm7
- pand mm3,mm7
- pand mm4,mm7
- pand mm5,mm7
-
- pcmpeqb mm0,mm6
- pcmpeqb mm1,mm6
- pcmpeqb mm2,mm6
- pcmpeqb mm3,mm6
- pcmpeqb mm4,mm6
- pcmpeqb mm5,mm6
-
- mov ecx,len //load length of line
- mov esi,srcptr //load source
- mov ebx,dstptr //load dest
-
- cmp ecx,0
- jz mainloop48end
-
-mainloop48:
- movq mm7,[esi]
- pand mm7,mm0
- movq mm6,mm0
- pandn mm6,[ebx]
- por mm7,mm6
- movq [ebx],mm7
-
- movq mm6,[esi+8]
- pand mm6,mm1
- movq mm7,mm1
- pandn mm7,[ebx+8]
- por mm6,mm7
- movq [ebx+8],mm6
-
- movq mm6,[esi+16]
- pand mm6,mm2
- movq mm7,mm2
- pandn mm7,[ebx+16]
- por mm6,mm7
- movq [ebx+16],mm6
-
- movq mm7,[esi+24]
- pand mm7,mm3
- movq mm6,mm3
- pandn mm6,[ebx+24]
- por mm7,mm6
- movq [ebx+24],mm7
-
- movq mm6,[esi+32]
- pand mm6,mm4
- movq mm7,mm4
- pandn mm7,[ebx+32]
- por mm6,mm7
- movq [ebx+32],mm6
-
- movq mm7,[esi+40]
- pand mm7,mm5
- movq mm6,mm5
- pandn mm6,[ebx+40]
- por mm7,mm6
- movq [ebx+40],mm7
-
- add esi,48 //inc by 32 bytes processed
- add ebx,48
- sub ecx,8 //dec by 8 pixels processed
-
- ja mainloop48
-mainloop48end:
-
- mov ecx,diff
- cmp ecx,0
- jz end48
-
- mov edx,mask
- sal edx,24 //make low byte the high byte
-
-secondloop48:
- sal edx,1 //move high bit to CF
- jnc skip48 //if CF = 0
- mov eax,[esi]
- mov [ebx],eax
-skip48:
- add esi,4
- add ebx,4
-
- dec ecx
- jnz secondloop48
-
-end48:
- emms
- }
- }
- else /* mmx _not supported - Use modified C routine */
- {
- register unsigned int incr1, initial_val, final_val;
- png_size_t pixel_bytes;
- png_uint_32 i;
- register int disp = png_pass_inc[png_ptr->pass];
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- srcptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dstptr = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dstptr, srcptr, pixel_bytes);
- srcptr += incr1;
- dstptr += incr1;
- }
- } /* end of else */
-
- break;
- } // end 48 bpp
-
- default:
- {
- png_bytep sptr;
- png_bytep dp;
- png_size_t pixel_bytes;
- int offset_table[7] = {0, 4, 0, 2, 0, 1, 0};
- unsigned int i;
- register int disp = png_pass_inc[png_ptr->pass]; // get the offset
- register unsigned int incr1, initial_val, final_val;
-
- pixel_bytes = (png_ptr->row_info.pixel_depth >> 3);
- sptr = png_ptr->row_buf + 1 + offset_table[png_ptr->pass]*
- pixel_bytes;
- dp = row + offset_table[png_ptr->pass]*pixel_bytes;
- initial_val = offset_table[png_ptr->pass]*pixel_bytes;
- final_val = png_ptr->width*pixel_bytes;
- incr1 = (disp)*pixel_bytes;
- for (i = initial_val; i < final_val; i += incr1)
- {
- png_memcpy(dp, sptr, pixel_bytes);
- sptr += incr1;
- dp += incr1;
- }
- break;
- }
- } /* end switch (png_ptr->row_info.pixel_depth) */
- } /* end if (non-trivial mask) */
-
-} /* end png_combine_row() */
-
-
-#if defined(PNG_READ_INTERLACING_SUPPORTED)
-
-void /* PRIVATE */
-png_do_read_interlace(png_structp png_ptr)
-{
- png_row_infop row_info = &(png_ptr->row_info);
- png_bytep row = png_ptr->row_buf + 1;
- int pass = png_ptr->pass;
- png_uint_32 transformations = png_ptr->transformations;
-#ifdef PNG_USE_LOCAL_ARRAYS
- const int png_pass_inc[7] = {8, 8, 4, 4, 2, 2, 1};
-#endif
-
- png_debug(1,"in png_do_read_interlace\n");
-
- if (mmx_supported == 2) {
-#if !defined(PNG_1_0_X)
- /* this should have happened in png_init_mmx_flags() already */
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-
- if (row != NULL && row_info != NULL)
- {
- png_uint_32 final_width;
-
- final_width = row_info->width * png_pass_inc[pass];
-
- switch (row_info->pixel_depth)
- {
- case 1:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_byte v;
- png_uint_32 i;
- int j;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 3);
- dp = row + (png_size_t)((final_width - 1) >> 3);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (int)((row_info->width + 7) & 7);
- dshift = (int)((final_width + 7) & 7);
- s_start = 7;
- s_end = 0;
- s_inc = -1;
- }
- else
-#endif
- {
- sshift = 7 - (int)((row_info->width + 7) & 7);
- dshift = 7 - (int)((final_width + 7) & 7);
- s_start = 0;
- s_end = 7;
- s_inc = 1;
- }
-
- for (i = row_info->width; i; i--)
- {
- v = (png_byte)((*sp >> sshift) & 0x1);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0x7f7f >> (7 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- case 2:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_uint_32 i;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 2);
- dp = row + (png_size_t)((final_width - 1) >> 2);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (png_size_t)(((row_info->width + 3) & 3) << 1);
- dshift = (png_size_t)(((final_width + 3) & 3) << 1);
- s_start = 6;
- s_end = 0;
- s_inc = -2;
- }
- else
-#endif
- {
- sshift = (png_size_t)((3 - ((row_info->width + 3) & 3)) << 1);
- dshift = (png_size_t)((3 - ((final_width + 3) & 3)) << 1);
- s_start = 0;
- s_end = 6;
- s_inc = 2;
- }
-
- for (i = row_info->width; i; i--)
- {
- png_byte v;
- int j;
-
- v = (png_byte)((*sp >> sshift) & 0x3);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0x3f3f >> (6 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- case 4:
- {
- png_bytep sp, dp;
- int sshift, dshift;
- int s_start, s_end, s_inc;
- png_uint_32 i;
-
- sp = row + (png_size_t)((row_info->width - 1) >> 1);
- dp = row + (png_size_t)((final_width - 1) >> 1);
-#if defined(PNG_READ_PACKSWAP_SUPPORTED)
- if (transformations & PNG_PACKSWAP)
- {
- sshift = (png_size_t)(((row_info->width + 1) & 1) << 2);
- dshift = (png_size_t)(((final_width + 1) & 1) << 2);
- s_start = 4;
- s_end = 0;
- s_inc = -4;
- }
- else
-#endif
- {
- sshift = (png_size_t)((1 - ((row_info->width + 1) & 1)) << 2);
- dshift = (png_size_t)((1 - ((final_width + 1) & 1)) << 2);
- s_start = 0;
- s_end = 4;
- s_inc = 4;
- }
-
- for (i = row_info->width; i; i--)
- {
- png_byte v;
- int j;
-
- v = (png_byte)((*sp >> sshift) & 0xf);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp &= (png_byte)((0xf0f >> (4 - dshift)) & 0xff);
- *dp |= (png_byte)(v << dshift);
- if (dshift == s_end)
- {
- dshift = s_start;
- dp--;
- }
- else
- dshift += s_inc;
- }
- if (sshift == s_end)
- {
- sshift = s_start;
- sp--;
- }
- else
- sshift += s_inc;
- }
- break;
- }
-
- default: // This is the place where the routine is modified
- {
- __int64 const4 = 0x0000000000FFFFFF;
- // __int64 const5 = 0x000000FFFFFF0000; // unused...
- __int64 const6 = 0x00000000000000FF;
- png_bytep sptr, dp;
- png_uint_32 i;
- png_size_t pixel_bytes;
- int width = row_info->width;
-
- pixel_bytes = (row_info->pixel_depth >> 3);
-
- sptr = row + (width - 1) * pixel_bytes;
- dp = row + (final_width - 1) * pixel_bytes;
- // New code by Nirav Chhatrapati - Intel Corporation
- // sign fix by GRR
- // NOTE: there is NO MMX code for 48-bit and 64-bit images
-
- // use MMX routine if machine supports it
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_INTERLACE)
- /* && mmx_supported */ )
-#else
- if (mmx_supported)
-#endif
- {
- if (pixel_bytes == 3)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width
- sub edi, 21 // (png_pass_inc[pass] - 1)*pixel_bytes
-loop_pass0:
- movd mm0, [esi] ; X X X X X v2 v1 v0
- pand mm0, const4 ; 0 0 0 0 0 v2 v1 v0
- movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
- psllq mm0, 16 ; 0 0 0 v2 v1 v0 0 0
- movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
- psllq mm0, 24 ; v2 v1 v0 0 0 0 0 0
- psrlq mm1, 8 ; 0 0 0 0 0 0 v2 v1
- por mm0, mm2 ; v2 v1 v0 v2 v1 v0 0 0
- por mm0, mm1 ; v2 v1 v0 v2 v1 v0 v2 v1
- movq mm3, mm0 ; v2 v1 v0 v2 v1 v0 v2 v1
- psllq mm0, 16 ; v0 v2 v1 v0 v2 v1 0 0
- movq mm4, mm3 ; v2 v1 v0 v2 v1 v0 v2 v1
- punpckhdq mm3, mm0 ; v0 v2 v1 v0 v2 v1 v0 v2
- movq [edi+16] , mm4
- psrlq mm0, 32 ; 0 0 0 0 v0 v2 v1 v0
- movq [edi+8] , mm3
- punpckldq mm0, mm4 ; v1 v0 v2 v1 v0 v2 v1 v0
- sub esi, 3
- movq [edi], mm0
- sub edi, 24
- //sub esi, 3
- dec ecx
- jnz loop_pass0
- EMMS
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width
- sub edi, 9 // (png_pass_inc[pass] - 1)*pixel_bytes
-loop_pass2:
- movd mm0, [esi] ; X X X X X v2 v1 v0
- pand mm0, const4 ; 0 0 0 0 0 v2 v1 v0
- movq mm1, mm0 ; 0 0 0 0 0 v2 v1 v0
- psllq mm0, 16 ; 0 0 0 v2 v1 v0 0 0
- movq mm2, mm0 ; 0 0 0 v2 v1 v0 0 0
- psllq mm0, 24 ; v2 v1 v0 0 0 0 0 0
- psrlq mm1, 8 ; 0 0 0 0 0 0 v2 v1
- por mm0, mm2 ; v2 v1 v0 v2 v1 v0 0 0
- por mm0, mm1 ; v2 v1 v0 v2 v1 v0 v2 v1
- movq [edi+4], mm0 ; move to memory
- psrlq mm0, 16 ; 0 0 v2 v1 v0 v2 v1 v0
- movd [edi], mm0 ; move to memory
- sub esi, 3
- sub edi, 12
- dec ecx
- jnz loop_pass2
- EMMS
- }
- }
- else if (width) /* && ((pass == 4) || (pass == 5)) */
- {
- int width_mmx = ((width >> 1) << 1) - 8;
- if (width_mmx < 0)
- width_mmx = 0;
- width -= width_mmx; // 8 or 9 pix, 24 or 27 bytes
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 3
- sub edi, 9
-loop_pass4:
- movq mm0, [esi] ; X X v2 v1 v0 v5 v4 v3
- movq mm7, mm0 ; X X v2 v1 v0 v5 v4 v3
- movq mm6, mm0 ; X X v2 v1 v0 v5 v4 v3
- psllq mm0, 24 ; v1 v0 v5 v4 v3 0 0 0
- pand mm7, const4 ; 0 0 0 0 0 v5 v4 v3
- psrlq mm6, 24 ; 0 0 0 X X v2 v1 v0
- por mm0, mm7 ; v1 v0 v5 v4 v3 v5 v4 v3
- movq mm5, mm6 ; 0 0 0 X X v2 v1 v0
- psllq mm6, 8 ; 0 0 X X v2 v1 v0 0
- movq [edi], mm0 ; move quad to memory
- psrlq mm5, 16 ; 0 0 0 0 0 X X v2
- pand mm5, const6 ; 0 0 0 0 0 0 0 v2
- por mm6, mm5 ; 0 0 X X v2 v1 v0 v2
- movd [edi+8], mm6 ; move double to memory
- sub esi, 6
- sub edi, 12
- sub ecx, 2
- jnz loop_pass4
- EMMS
- }
- }
-
- sptr -= width_mmx*3;
- dp -= width_mmx*6;
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
-
- png_memcpy(v, sptr, 3);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 3);
- dp -= 3;
- }
- sptr -= 3;
- }
- }
- } /* end of pixel_bytes == 3 */
-
- else if (pixel_bytes == 1)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 2) << 2);
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub edi, 31
- sub esi, 3
-loop1_pass0:
- movd mm0, [esi] ; X X X X v0 v1 v2 v3
- movq mm1, mm0 ; X X X X v0 v1 v2 v3
- punpcklbw mm0, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
- movq mm2, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
- punpcklwd mm0, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
- movq mm3, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
- punpckldq mm0, mm0 ; v3 v3 v3 v3 v3 v3 v3 v3
- punpckhdq mm3, mm3 ; v2 v2 v2 v2 v2 v2 v2 v2
- movq [edi], mm0 ; move to memory v3
- punpckhwd mm2, mm2 ; v0 v0 v0 v0 v1 v1 v1 v1
- movq [edi+8], mm3 ; move to memory v2
- movq mm4, mm2 ; v0 v0 v0 v0 v1 v1 v1 v1
- punpckldq mm2, mm2 ; v1 v1 v1 v1 v1 v1 v1 v1
- punpckhdq mm4, mm4 ; v0 v0 v0 v0 v0 v0 v0 v0
- movq [edi+16], mm2 ; move to memory v1
- movq [edi+24], mm4 ; move to memory v0
- sub esi, 4
- sub edi, 32
- sub ecx, 4
- jnz loop1_pass0
- EMMS
- }
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*8;
- for (i = width; i; i--)
- {
- int j;
-
- /* I simplified this part in version 1.0.4e
- * here and in several other instances where
- * pixel_bytes == 1 -- GR-P
- *
- * Original code:
- *
- * png_byte v[8];
- * png_memcpy(v, sptr, pixel_bytes);
- * for (j = 0; j < png_pass_inc[pass]; j++)
- * {
- * png_memcpy(dp, v, pixel_bytes);
- * dp -= pixel_bytes;
- * }
- * sptr -= pixel_bytes;
- *
- * Replacement code is in the next three lines:
- */
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- *dp-- = *sptr;
- sptr--;
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 2) << 2);
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub edi, 15
- sub esi, 3
-loop1_pass2:
- movd mm0, [esi] ; X X X X v0 v1 v2 v3
- punpcklbw mm0, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
- movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
- punpcklwd mm0, mm0 ; v2 v2 v2 v2 v3 v3 v3 v3
- punpckhwd mm1, mm1 ; v0 v0 v0 v0 v1 v1 v1 v1
- movq [edi], mm0 ; move to memory v2 and v3
- sub esi, 4
- movq [edi+8], mm1 ; move to memory v1 and v0
- sub edi, 16
- sub ecx, 4
- jnz loop1_pass2
- EMMS
- }
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*4;
- for (i = width; i; i--)
- {
- int j;
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- sptr --;
- }
- }
- else if (width) /* && ((pass == 4) || (pass == 5))) */
- {
- int width_mmx = ((width >> 3) << 3);
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub edi, 15
- sub esi, 7
-loop1_pass4:
- movq mm0, [esi] ; v0 v1 v2 v3 v4 v5 v6 v7
- movq mm1, mm0 ; v0 v1 v2 v3 v4 v5 v6 v7
- punpcklbw mm0, mm0 ; v4 v4 v5 v5 v6 v6 v7 v7
- //movq mm1, mm0 ; v0 v0 v1 v1 v2 v2 v3 v3
- punpckhbw mm1, mm1 ;v0 v0 v1 v1 v2 v2 v3 v3
- movq [edi+8], mm1 ; move to memory v0 v1 v2 and v3
- sub esi, 8
- movq [edi], mm0 ; move to memory v4 v5 v6 and v7
- //sub esi, 4
- sub edi, 16
- sub ecx, 8
- jnz loop1_pass4
- EMMS
- }
- }
-
- sptr -= width_mmx;
- dp -= width_mmx*2;
- for (i = width; i; i--)
- {
- int j;
-
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- *dp-- = *sptr;
- }
- sptr --;
- }
- }
- } /* end of pixel_bytes == 1 */
-
- else if (pixel_bytes == 2)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 1) << 1);
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 2
- sub edi, 30
-loop2_pass0:
- movd mm0, [esi] ; X X X X v1 v0 v3 v2
- punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
- movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
- punpckldq mm0, mm0 ; v3 v2 v3 v2 v3 v2 v3 v2
- punpckhdq mm1, mm1 ; v1 v0 v1 v0 v1 v0 v1 v0
- movq [edi], mm0
- movq [edi + 8], mm0
- movq [edi + 16], mm1
- movq [edi + 24], mm1
- sub esi, 4
- sub edi, 32
- sub ecx, 2
- jnz loop2_pass0
- EMMS
- }
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*16 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 2
- sub edi, 14
-loop2_pass2:
- movd mm0, [esi] ; X X X X v1 v0 v3 v2
- punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
- movq mm1, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
- punpckldq mm0, mm0 ; v3 v2 v3 v2 v3 v2 v3 v2
- punpckhdq mm1, mm1 ; v1 v0 v1 v0 v1 v0 v1 v0
- movq [edi], mm0
- sub esi, 4
- movq [edi + 8], mm1
- //sub esi, 4
- sub edi, 16
- sub ecx, 2
- jnz loop2_pass2
- EMMS
- }
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*8 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- else if (width) // pass == 4 or 5
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 2
- sub edi, 6
-loop2_pass4:
- movd mm0, [esi] ; X X X X v1 v0 v3 v2
- punpcklwd mm0, mm0 ; v1 v0 v1 v0 v3 v2 v3 v2
- sub esi, 4
- movq [edi], mm0
- sub edi, 8
- sub ecx, 2
- jnz loop2_pass4
- EMMS
- }
- }
-
- sptr -= (width_mmx*2 - 2); // sign fixed
- dp -= (width_mmx*4 - 2); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 2;
- png_memcpy(v, sptr, 2);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 2;
- png_memcpy(dp, v, 2);
- }
- }
- }
- } /* end of pixel_bytes == 2 */
-
- else if (pixel_bytes == 4)
- {
- if (((pass == 0) || (pass == 1)) && width)
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 4
- sub edi, 60
-loop4_pass0:
- movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
- movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
- punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
- punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
- movq [edi], mm0
- movq [edi + 8], mm0
- movq [edi + 16], mm0
- movq [edi + 24], mm0
- movq [edi+32], mm1
- movq [edi + 40], mm1
- movq [edi+ 48], mm1
- sub esi, 8
- movq [edi + 56], mm1
- sub edi, 64
- sub ecx, 2
- jnz loop4_pass0
- EMMS
- }
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*32 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
- else if (((pass == 2) || (pass == 3)) && width)
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 4
- sub edi, 28
-loop4_pass2:
- movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
- movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
- punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
- punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
- movq [edi], mm0
- movq [edi + 8], mm0
- movq [edi+16], mm1
- movq [edi + 24], mm1
- sub esi, 8
- sub edi, 32
- sub ecx, 2
- jnz loop4_pass2
- EMMS
- }
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*16 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
- else if (width) // pass == 4 or 5
- {
- int width_mmx = ((width >> 1) << 1) ;
- width -= width_mmx;
- if (width_mmx)
- {
- _asm
- {
- mov esi, sptr
- mov edi, dp
- mov ecx, width_mmx
- sub esi, 4
- sub edi, 12
-loop4_pass4:
- movq mm0, [esi] ; v3 v2 v1 v0 v7 v6 v5 v4
- movq mm1, mm0 ; v3 v2 v1 v0 v7 v6 v5 v4
- punpckldq mm0, mm0 ; v7 v6 v5 v4 v7 v6 v5 v4
- punpckhdq mm1, mm1 ; v3 v2 v1 v0 v3 v2 v1 v0
- movq [edi], mm0
- sub esi, 8
- movq [edi + 8], mm1
- sub edi, 16
- sub ecx, 2
- jnz loop4_pass4
- EMMS
- }
- }
-
- sptr -= (width_mmx*4 - 4); // sign fixed
- dp -= (width_mmx*8 - 4); // sign fixed
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- sptr -= 4;
- png_memcpy(v, sptr, 4);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- dp -= 4;
- png_memcpy(dp, v, 4);
- }
- }
- }
-
- } /* end of pixel_bytes == 4 */
-
- else if (pixel_bytes == 6)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, 6);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, 6);
- dp -= 6;
- }
- sptr -= 6;
- }
- } /* end of pixel_bytes == 6 */
-
- else
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr-= pixel_bytes;
- }
- }
- } /* end of mmx_supported */
-
- else /* MMX not supported: use modified C code - takes advantage
- * of inlining of memcpy for a constant */
- {
- if (pixel_bytes == 1)
- {
- for (i = width; i; i--)
- {
- int j;
- for (j = 0; j < png_pass_inc[pass]; j++)
- *dp-- = *sptr;
- sptr--;
- }
- }
- else if (pixel_bytes == 3)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
- else if (pixel_bytes == 2)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
- else if (pixel_bytes == 4)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
- else if (pixel_bytes == 6)
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
- else
- {
- for (i = width; i; i--)
- {
- png_byte v[8];
- int j;
- png_memcpy(v, sptr, pixel_bytes);
- for (j = 0; j < png_pass_inc[pass]; j++)
- {
- png_memcpy(dp, v, pixel_bytes);
- dp -= pixel_bytes;
- }
- sptr -= pixel_bytes;
- }
- }
-
- } /* end of MMX not supported */
- break;
- }
- } /* end switch (row_info->pixel_depth) */
-
- row_info->width = final_width;
-
- row_info->rowbytes = PNG_ROWBYTES(row_info->pixel_depth,final_width);
- }
-
-}
-
-#endif /* PNG_READ_INTERLACING_SUPPORTED */
-
-
-// These variables are utilized in the functions below. They are declared
-// globally here to ensure alignment on 8-byte boundaries.
-
-union uAll {
- __int64 use;
- double align;
-} LBCarryMask = {0x0101010101010101},
- HBClearMask = {0x7f7f7f7f7f7f7f7f},
- ActiveMask, ActiveMask2, ActiveMaskEnd, ShiftBpp, ShiftRem;
-
-
-// Optimized code for PNG Average filter decoder
-void /* PRIVATE */
-png_read_filter_row_mmx_avg(png_row_infop row_info, png_bytep row
- , png_bytep prev_row)
-{
- int bpp;
- png_uint_32 FullLength;
- png_uint_32 MMXLength;
- //png_uint_32 len;
- int diff;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel
- FullLength = row_info->rowbytes; // # of bytes to filter
- _asm {
- // Init address pointers and offset
- mov edi, row // edi ==> Avg(x)
- xor ebx, ebx // ebx ==> x
- mov edx, edi
- mov esi, prev_row // esi ==> Prior(x)
- sub edx, bpp // edx ==> Raw(x-bpp)
-
- xor eax, eax
- // Compute the Raw value for the first bpp bytes
- // Raw(x) = Avg(x) + (Prior(x)/2)
-davgrlp:
- mov al, [esi + ebx] // Load al with Prior(x)
- inc ebx
- shr al, 1 // divide by 2
- add al, [edi+ebx-1] // Add Avg(x); -1 to offset inc ebx
- cmp ebx, bpp
- mov [edi+ebx-1], al // Write back Raw(x);
- // mov does not affect flags; -1 to offset inc ebx
- jb davgrlp
- // get # of bytes to alignment
- mov diff, edi // take start of row
- add diff, ebx // add bpp
- add diff, 0xf // add 7 + 8 to incr past alignment boundary
- and diff, 0xfffffff8 // mask to alignment boundary
- sub diff, edi // subtract from start ==> value ebx at alignment
- jz davggo
- // fix alignment
- // Compute the Raw value for the bytes upto the alignment boundary
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- xor ecx, ecx
-davglp1:
- xor eax, eax
- mov cl, [esi + ebx] // load cl with Prior(x)
- mov al, [edx + ebx] // load al with Raw(x-bpp)
- add ax, cx
- inc ebx
- shr ax, 1 // divide by 2
- add al, [edi+ebx-1] // Add Avg(x); -1 to offset inc ebx
- cmp ebx, diff // Check if at alignment boundary
- mov [edi+ebx-1], al // Write back Raw(x);
- // mov does not affect flags; -1 to offset inc ebx
- jb davglp1 // Repeat until at alignment boundary
-davggo:
- mov eax, FullLength
- mov ecx, eax
- sub eax, ebx // subtract alignment fix
- and eax, 0x00000007 // calc bytes over mult of 8
- sub ecx, eax // drop over bytes from original length
- mov MMXLength, ecx
- } // end _asm block
- // Now do the math for the rest of the row
- switch ( bpp )
- {
- case 3:
- {
- ActiveMask.use = 0x0000000000ffffff;
- ShiftBpp.use = 24; // == 3 * 8
- ShiftRem.use = 40; // == 64 - 24
- _asm {
- // Re-init address pointers and offset
- movq mm7, ActiveMask
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- movq mm5, LBCarryMask
- mov edi, row // edi ==> Avg(x)
- movq mm4, HBClearMask
- mov esi, prev_row // esi ==> Prior(x)
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
- // (we correct position in loop below)
-davg3lp:
- movq mm0, [edi + ebx] // Load mm0 with Avg(x)
- // Add (Prev_row/2) to Average
- movq mm3, mm5
- psrlq mm2, ShiftRem // Correct position Raw(x-bpp) data
- movq mm1, [esi + ebx] // Load mm1 with Prior(x)
- movq mm6, mm7
- pand mm3, mm1 // get lsb for each prev_row byte
- psrlq mm1, 1 // divide prev_row bytes by 2
- pand mm1, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm1 // add (Prev_row/2) to Avg for each byte
- // Add 1st active group (Raw(x-bpp)/2) to Average with LBCarry
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 1 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active
- // byte
- // Add 2nd active group (Raw(x-bpp)/2) to Average with LBCarry
- psllq mm6, ShiftBpp // shift the mm6 mask to cover bytes 3-5
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active
- // byte
-
- // Add 3rd active group (Raw(x-bpp)/2) to Average with LBCarry
- psllq mm6, ShiftBpp // shift the mm6 mask to cover the last two
- // bytes
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- // Data only needs to be shifted once here to
- // get the correct x-bpp offset.
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- add ebx, 8
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active
- // byte
-
- // Now ready to write back to memory
- movq [edi + ebx - 8], mm0
- // Move updated Raw(x) to use as Raw(x-bpp) for next loop
- cmp ebx, MMXLength
- movq mm2, mm0 // mov updated Raw(x) to mm2
- jb davg3lp
- } // end _asm block
- }
- break;
-
- case 6:
- case 4:
- case 7:
- case 5:
- {
- ActiveMask.use = 0xffffffffffffffff; // use shift below to clear
- // appropriate inactive bytes
- ShiftBpp.use = bpp << 3;
- ShiftRem.use = 64 - ShiftBpp.use;
- _asm {
- movq mm4, HBClearMask
- // Re-init address pointers and offset
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- // Load ActiveMask and clear all bytes except for 1st active group
- movq mm7, ActiveMask
- mov edi, row // edi ==> Avg(x)
- psrlq mm7, ShiftRem
- mov esi, prev_row // esi ==> Prior(x)
- movq mm6, mm7
- movq mm5, LBCarryMask
- psllq mm6, ShiftBpp // Create mask for 2nd active group
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
- // (we correct position in loop below)
-davg4lp:
- movq mm0, [edi + ebx]
- psrlq mm2, ShiftRem // shift data to position correctly
- movq mm1, [esi + ebx]
- // Add (Prev_row/2) to Average
- movq mm3, mm5
- pand mm3, mm1 // get lsb for each prev_row byte
- psrlq mm1, 1 // divide prev_row bytes by 2
- pand mm1, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm1 // add (Prev_row/2) to Avg for each byte
- // Add 1st active group (Raw(x-bpp)/2) to Average with LBCarry
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm7 // Leave only Active Group 1 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active
- // byte
- // Add 2nd active group (Raw(x-bpp)/2) to Average with LBCarry
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- add ebx, 8
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active
- // byte
- cmp ebx, MMXLength
- // Now ready to write back to memory
- movq [edi + ebx - 8], mm0
- // Prep Raw(x-bpp) for next loop
- movq mm2, mm0 // mov updated Raws to mm2
- jb davg4lp
- } // end _asm block
- }
- break;
- case 2:
- {
- ActiveMask.use = 0x000000000000ffff;
- ShiftBpp.use = 16; // == 2 * 8 [BUGFIX]
- ShiftRem.use = 48; // == 64 - 16 [BUGFIX]
- _asm {
- // Load ActiveMask
- movq mm7, ActiveMask
- // Re-init address pointers and offset
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- movq mm5, LBCarryMask
- mov edi, row // edi ==> Avg(x)
- movq mm4, HBClearMask
- mov esi, prev_row // esi ==> Prior(x)
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
- // (we correct position in loop below)
-davg2lp:
- movq mm0, [edi + ebx]
- psrlq mm2, ShiftRem // shift data to position correctly [BUGFIX]
- movq mm1, [esi + ebx]
- // Add (Prev_row/2) to Average
- movq mm3, mm5
- pand mm3, mm1 // get lsb for each prev_row byte
- psrlq mm1, 1 // divide prev_row bytes by 2
- pand mm1, mm4 // clear invalid bit 7 of each byte
- movq mm6, mm7
- paddb mm0, mm1 // add (Prev_row/2) to Avg for each byte
- // Add 1st active group (Raw(x-bpp)/2) to Average with LBCarry
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 1 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active byte
- // Add 2nd active group (Raw(x-bpp)/2) to Average with LBCarry
- psllq mm6, ShiftBpp // shift the mm6 mask to cover bytes 2 & 3
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active byte
-
- // Add rdd active group (Raw(x-bpp)/2) to Average with LBCarry
- psllq mm6, ShiftBpp // shift the mm6 mask to cover bytes 4 & 5
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- // Data only needs to be shifted once here to
- // get the correct x-bpp offset.
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active byte
-
- // Add 4th active group (Raw(x-bpp)/2) to Average with LBCarry
- psllq mm6, ShiftBpp // shift the mm6 mask to cover bytes 6 & 7
- movq mm2, mm0 // mov updated Raws to mm2
- psllq mm2, ShiftBpp // shift data to position correctly
- // Data only needs to be shifted once here to
- // get the correct x-bpp offset.
- add ebx, 8
- movq mm1, mm3 // now use mm1 for getting LBCarrys
- pand mm1, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1 (Only valid for active group)
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm2, mm1 // add LBCarrys to (Raw(x-bpp)/2) for each byte
- pand mm2, mm6 // Leave only Active Group 2 bytes to add to Avg
- paddb mm0, mm2 // add (Raw/2) + LBCarrys to Avg for each Active byte
-
- cmp ebx, MMXLength
- // Now ready to write back to memory
- movq [edi + ebx - 8], mm0
- // Prep Raw(x-bpp) for next loop
- movq mm2, mm0 // mov updated Raws to mm2
- jb davg2lp
- } // end _asm block
- }
- break;
-
- case 1: // bpp == 1
- {
- _asm {
- // Re-init address pointers and offset
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- mov edi, row // edi ==> Avg(x)
- cmp ebx, FullLength // Test if offset at end of array
- jnb davg1end
- // Do Paeth decode for remaining bytes
- mov esi, prev_row // esi ==> Prior(x)
- mov edx, edi
- xor ecx, ecx // zero ecx before using cl & cx in loop below
- sub edx, bpp // edx ==> Raw(x-bpp)
-davg1lp:
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- xor eax, eax
- mov cl, [esi + ebx] // load cl with Prior(x)
- mov al, [edx + ebx] // load al with Raw(x-bpp)
- add ax, cx
- inc ebx
- shr ax, 1 // divide by 2
- add al, [edi+ebx-1] // Add Avg(x); -1 to offset inc ebx
- cmp ebx, FullLength // Check if at end of array
- mov [edi+ebx-1], al // Write back Raw(x);
- // mov does not affect flags; -1 to offset inc ebx
- jb davg1lp
-davg1end:
- } // end _asm block
- }
- return;
-
- case 8: // bpp == 8
- {
- _asm {
- // Re-init address pointers and offset
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- movq mm5, LBCarryMask
- mov edi, row // edi ==> Avg(x)
- movq mm4, HBClearMask
- mov esi, prev_row // esi ==> Prior(x)
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm2, [edi + ebx - 8] // Load previous aligned 8 bytes
- // (NO NEED to correct position in loop below)
-davg8lp:
- movq mm0, [edi + ebx]
- movq mm3, mm5
- movq mm1, [esi + ebx]
- add ebx, 8
- pand mm3, mm1 // get lsb for each prev_row byte
- psrlq mm1, 1 // divide prev_row bytes by 2
- pand mm3, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm1, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm3 // add LBCarrys to Avg for each byte
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm1 // add (Prev_row/2) to Avg for each byte
- paddb mm0, mm2 // add (Raw/2) to Avg for each byte
- cmp ebx, MMXLength
- movq [edi + ebx - 8], mm0
- movq mm2, mm0 // reuse as Raw(x-bpp)
- jb davg8lp
- } // end _asm block
- }
- break;
- default: // bpp greater than 8
- {
- _asm {
- movq mm5, LBCarryMask
- // Re-init address pointers and offset
- mov ebx, diff // ebx ==> x = offset to alignment boundary
- mov edi, row // edi ==> Avg(x)
- movq mm4, HBClearMask
- mov edx, edi
- mov esi, prev_row // esi ==> Prior(x)
- sub edx, bpp // edx ==> Raw(x-bpp)
-davgAlp:
- movq mm0, [edi + ebx]
- movq mm3, mm5
- movq mm1, [esi + ebx]
- pand mm3, mm1 // get lsb for each prev_row byte
- movq mm2, [edx + ebx]
- psrlq mm1, 1 // divide prev_row bytes by 2
- pand mm3, mm2 // get LBCarrys for each byte where both
- // lsb's were == 1
- psrlq mm2, 1 // divide raw bytes by 2
- pand mm1, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm3 // add LBCarrys to Avg for each byte
- pand mm2, mm4 // clear invalid bit 7 of each byte
- paddb mm0, mm1 // add (Prev_row/2) to Avg for each byte
- add ebx, 8
- paddb mm0, mm2 // add (Raw/2) to Avg for each byte
- cmp ebx, MMXLength
- movq [edi + ebx - 8], mm0
- jb davgAlp
- } // end _asm block
- }
- break;
- } // end switch ( bpp )
-
- _asm {
- // MMX acceleration complete now do clean-up
- // Check if any remaining bytes left to decode
- mov ebx, MMXLength // ebx ==> x = offset bytes remaining after MMX
- mov edi, row // edi ==> Avg(x)
- cmp ebx, FullLength // Test if offset at end of array
- jnb davgend
- // Do Paeth decode for remaining bytes
- mov esi, prev_row // esi ==> Prior(x)
- mov edx, edi
- xor ecx, ecx // zero ecx before using cl & cx in loop below
- sub edx, bpp // edx ==> Raw(x-bpp)
-davglp2:
- // Raw(x) = Avg(x) + ((Raw(x-bpp) + Prior(x))/2)
- xor eax, eax
- mov cl, [esi + ebx] // load cl with Prior(x)
- mov al, [edx + ebx] // load al with Raw(x-bpp)
- add ax, cx
- inc ebx
- shr ax, 1 // divide by 2
- add al, [edi+ebx-1] // Add Avg(x); -1 to offset inc ebx
- cmp ebx, FullLength // Check if at end of array
- mov [edi+ebx-1], al // Write back Raw(x);
- // mov does not affect flags; -1 to offset inc ebx
- jb davglp2
-davgend:
- emms // End MMX instructions; prep for possible FP instrs.
- } // end _asm block
-}
-
-// Optimized code for PNG Paeth filter decoder
-void /* PRIVATE */
-png_read_filter_row_mmx_paeth(png_row_infop row_info, png_bytep row,
- png_bytep prev_row)
-{
- png_uint_32 FullLength;
- png_uint_32 MMXLength;
- //png_uint_32 len;
- int bpp;
- int diff;
- //int ptemp;
- int patemp, pbtemp, pctemp;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel
- FullLength = row_info->rowbytes; // # of bytes to filter
- _asm
- {
- xor ebx, ebx // ebx ==> x offset
- mov edi, row
- xor edx, edx // edx ==> x-bpp offset
- mov esi, prev_row
- xor eax, eax
-
- // Compute the Raw value for the first bpp bytes
- // Note: the formula works out to be always
- // Paeth(x) = Raw(x) + Prior(x) where x < bpp
-dpthrlp:
- mov al, [edi + ebx]
- add al, [esi + ebx]
- inc ebx
- cmp ebx, bpp
- mov [edi + ebx - 1], al
- jb dpthrlp
- // get # of bytes to alignment
- mov diff, edi // take start of row
- add diff, ebx // add bpp
- xor ecx, ecx
- add diff, 0xf // add 7 + 8 to incr past alignment boundary
- and diff, 0xfffffff8 // mask to alignment boundary
- sub diff, edi // subtract from start ==> value ebx at alignment
- jz dpthgo
- // fix alignment
-dpthlp1:
- xor eax, eax
- // pav = p - a = (a + b - c) - a = b - c
- mov al, [esi + ebx] // load Prior(x) into al
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- sub eax, ecx // subtract Prior(x-bpp)
- mov patemp, eax // Save pav for later use
- xor eax, eax
- // pbv = p - b = (a + b - c) - b = a - c
- mov al, [edi + edx] // load Raw(x-bpp) into al
- sub eax, ecx // subtract Prior(x-bpp)
- mov ecx, eax
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- add eax, patemp // pcv = pav + pbv
- // pc = abs(pcv)
- test eax, 0x80000000
- jz dpthpca
- neg eax // reverse sign of neg values
-dpthpca:
- mov pctemp, eax // save pc for later use
- // pb = abs(pbv)
- test ecx, 0x80000000
- jz dpthpba
- neg ecx // reverse sign of neg values
-dpthpba:
- mov pbtemp, ecx // save pb for later use
- // pa = abs(pav)
- mov eax, patemp
- test eax, 0x80000000
- jz dpthpaa
- neg eax // reverse sign of neg values
-dpthpaa:
- mov patemp, eax // save pa for later use
- // test if pa <= pb
- cmp eax, ecx
- jna dpthabb
- // pa > pb; now test if pb <= pc
- cmp ecx, pctemp
- jna dpthbbc
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthpaeth
-dpthbbc:
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- mov cl, [esi + ebx] // load Prior(x) into cl
- jmp dpthpaeth
-dpthabb:
- // pa <= pb; now test if pa <= pc
- cmp eax, pctemp
- jna dpthabc
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthpaeth
-dpthabc:
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- mov cl, [edi + edx] // load Raw(x-bpp) into cl
-dpthpaeth:
- inc ebx
- inc edx
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- add [edi + ebx - 1], cl
- cmp ebx, diff
- jb dpthlp1
-dpthgo:
- mov ecx, FullLength
- mov eax, ecx
- sub eax, ebx // subtract alignment fix
- and eax, 0x00000007 // calc bytes over mult of 8
- sub ecx, eax // drop over bytes from original length
- mov MMXLength, ecx
- } // end _asm block
- // Now do the math for the rest of the row
- switch ( bpp )
- {
- case 3:
- {
- ActiveMask.use = 0x0000000000ffffff;
- ActiveMaskEnd.use = 0xffff000000000000;
- ShiftBpp.use = 24; // == bpp(3) * 8
- ShiftRem.use = 40; // == 64 - 24
- _asm
- {
- mov ebx, diff
- mov edi, row
- mov esi, prev_row
- pxor mm0, mm0
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8]
-dpth3lp:
- psrlq mm1, ShiftRem // shift last 3 bytes to 1st 3 bytes
- movq mm2, [esi + ebx] // load b=Prior(x)
- punpcklbw mm1, mm0 // Unpack High bytes of a
- movq mm3, [esi+ebx-8] // Prep c=Prior(x-bpp) bytes
- punpcklbw mm2, mm0 // Unpack High bytes of b
- psrlq mm3, ShiftRem // shift last 3 bytes to 1st 3 bytes
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- punpcklbw mm3, mm0 // Unpack High bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- paddw mm7, mm3
- pxor mm0, mm0
- packuswb mm7, mm1
- movq mm3, [esi + ebx] // load c=Prior(x-bpp)
- pand mm7, ActiveMask
- movq mm2, mm3 // load b=Prior(x) step 1
- paddb mm7, [edi + ebx] // add Paeth predictor with Raw(x)
- punpcklbw mm3, mm0 // Unpack High bytes of c
- movq [edi + ebx], mm7 // write back updated value
- movq mm1, mm7 // Now mm1 will be used as Raw(x-bpp)
- // Now do Paeth for 2nd set of bytes (3-5)
- psrlq mm2, ShiftBpp // load b=Prior(x) step 2
- punpcklbw mm1, mm0 // Unpack High bytes of a
- pxor mm7, mm7
- punpcklbw mm2, mm0 // Unpack High bytes of b
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- psubw mm5, mm3
- psubw mm4, mm3
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) =
- // pav + pbv = pbv + pav
- movq mm6, mm5
- paddw mm6, mm4
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm5 // Create mask pbv bytes < 0
- pcmpgtw mm7, mm4 // Create mask pav bytes < 0
- pand mm0, mm5 // Only pbv bytes < 0 in mm0
- pand mm7, mm4 // Only pav bytes < 0 in mm7
- psubw mm5, mm0
- psubw mm4, mm7
- psubw mm5, mm0
- psubw mm4, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- movq mm2, [esi + ebx] // load b=Prior(x)
- pand mm3, mm7
- pandn mm7, mm0
- pxor mm1, mm1
- paddw mm7, mm3
- pxor mm0, mm0
- packuswb mm7, mm1
- movq mm3, mm2 // load c=Prior(x-bpp) step 1
- pand mm7, ActiveMask
- punpckhbw mm2, mm0 // Unpack High bytes of b
- psllq mm7, ShiftBpp // Shift bytes to 2nd group of 3 bytes
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- paddb mm7, [edi + ebx] // add Paeth predictor with Raw(x)
- psllq mm3, ShiftBpp // load c=Prior(x-bpp) step 2
- movq [edi + ebx], mm7 // write back updated value
- movq mm1, mm7
- punpckhbw mm3, mm0 // Unpack High bytes of c
- psllq mm1, ShiftBpp // Shift bytes
- // Now mm1 will be used as Raw(x-bpp)
- // Now do Paeth for 3rd, and final, set of bytes (6-7)
- pxor mm7, mm7
- punpckhbw mm1, mm0 // Unpack High bytes of a
- psubw mm4, mm3
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- pxor mm0, mm0
- paddw mm6, mm5
-
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- pandn mm0, mm1
- pandn mm7, mm4
- paddw mm0, mm2
- paddw mm7, mm5
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pand mm3, mm7
- pandn mm7, mm0
- paddw mm7, mm3
- pxor mm1, mm1
- packuswb mm1, mm7
- // Step ebx to next set of 8 bytes and repeat loop til done
- add ebx, 8
- pand mm1, ActiveMaskEnd
- paddb mm1, [edi + ebx - 8] // add Paeth predictor with Raw(x)
-
- cmp ebx, MMXLength
- pxor mm0, mm0 // pxor does not affect flags
- movq [edi + ebx - 8], mm1 // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- // mm3 ready to be used as Prior(x-bpp) next loop
- jb dpth3lp
- } // end _asm block
- }
- break;
-
- case 6:
- case 7:
- case 5:
- {
- ActiveMask.use = 0x00000000ffffffff;
- ActiveMask2.use = 0xffffffff00000000;
- ShiftBpp.use = bpp << 3; // == bpp * 8
- ShiftRem.use = 64 - ShiftBpp.use;
- _asm
- {
- mov ebx, diff
- mov edi, row
- mov esi, prev_row
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8]
- pxor mm0, mm0
-dpth6lp:
- // Must shift to position Raw(x-bpp) data
- psrlq mm1, ShiftRem
- // Do first set of 4 bytes
- movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
- punpcklbw mm1, mm0 // Unpack Low bytes of a
- movq mm2, [esi + ebx] // load b=Prior(x)
- punpcklbw mm2, mm0 // Unpack Low bytes of b
- // Must shift to position Prior(x-bpp) data
- psrlq mm3, ShiftRem
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- punpcklbw mm3, mm0 // Unpack Low bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- paddw mm7, mm3
- pxor mm0, mm0
- packuswb mm7, mm1
- movq mm3, [esi + ebx - 8] // load c=Prior(x-bpp)
- pand mm7, ActiveMask
- psrlq mm3, ShiftRem
- movq mm2, [esi + ebx] // load b=Prior(x) step 1
- paddb mm7, [edi + ebx] // add Paeth predictor with Raw(x)
- movq mm6, mm2
- movq [edi + ebx], mm7 // write back updated value
- movq mm1, [edi+ebx-8]
- psllq mm6, ShiftBpp
- movq mm5, mm7
- psrlq mm1, ShiftRem
- por mm3, mm6
- psllq mm5, ShiftBpp
- punpckhbw mm3, mm0 // Unpack High bytes of c
- por mm1, mm5
- // Do second set of 4 bytes
- punpckhbw mm2, mm0 // Unpack High bytes of b
- punpckhbw mm1, mm0 // Unpack High bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- pxor mm1, mm1
- paddw mm7, mm3
- pxor mm0, mm0
- // Step ex to next set of 8 bytes and repeat loop til done
- add ebx, 8
- packuswb mm1, mm7
- paddb mm1, [edi + ebx - 8] // add Paeth predictor with Raw(x)
- cmp ebx, MMXLength
- movq [edi + ebx - 8], mm1 // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- jb dpth6lp
- } // end _asm block
- }
- break;
-
- case 4:
- {
- ActiveMask.use = 0x00000000ffffffff;
- _asm {
- mov ebx, diff
- mov edi, row
- mov esi, prev_row
- pxor mm0, mm0
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8] // Only time should need to read
- // a=Raw(x-bpp) bytes
-dpth4lp:
- // Do first set of 4 bytes
- movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
- punpckhbw mm1, mm0 // Unpack Low bytes of a
- movq mm2, [esi + ebx] // load b=Prior(x)
- punpcklbw mm2, mm0 // Unpack High bytes of b
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- punpckhbw mm3, mm0 // Unpack High bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- paddw mm7, mm3
- pxor mm0, mm0
- packuswb mm7, mm1
- movq mm3, [esi + ebx] // load c=Prior(x-bpp)
- pand mm7, ActiveMask
- movq mm2, mm3 // load b=Prior(x) step 1
- paddb mm7, [edi + ebx] // add Paeth predictor with Raw(x)
- punpcklbw mm3, mm0 // Unpack High bytes of c
- movq [edi + ebx], mm7 // write back updated value
- movq mm1, mm7 // Now mm1 will be used as Raw(x-bpp)
- // Do second set of 4 bytes
- punpckhbw mm2, mm0 // Unpack Low bytes of b
- punpcklbw mm1, mm0 // Unpack Low bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- pxor mm1, mm1
- paddw mm7, mm3
- pxor mm0, mm0
- // Step ex to next set of 8 bytes and repeat loop til done
- add ebx, 8
- packuswb mm1, mm7
- paddb mm1, [edi + ebx - 8] // add Paeth predictor with Raw(x)
- cmp ebx, MMXLength
- movq [edi + ebx - 8], mm1 // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- jb dpth4lp
- } // end _asm block
- }
- break;
- case 8: // bpp == 8
- {
- ActiveMask.use = 0x00000000ffffffff;
- _asm {
- mov ebx, diff
- mov edi, row
- mov esi, prev_row
- pxor mm0, mm0
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8] // Only time should need to read
- // a=Raw(x-bpp) bytes
-dpth8lp:
- // Do first set of 4 bytes
- movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
- punpcklbw mm1, mm0 // Unpack Low bytes of a
- movq mm2, [esi + ebx] // load b=Prior(x)
- punpcklbw mm2, mm0 // Unpack Low bytes of b
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- punpcklbw mm3, mm0 // Unpack Low bytes of c
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- paddw mm7, mm3
- pxor mm0, mm0
- packuswb mm7, mm1
- movq mm3, [esi+ebx-8] // read c=Prior(x-bpp) bytes
- pand mm7, ActiveMask
- movq mm2, [esi + ebx] // load b=Prior(x)
- paddb mm7, [edi + ebx] // add Paeth predictor with Raw(x)
- punpckhbw mm3, mm0 // Unpack High bytes of c
- movq [edi + ebx], mm7 // write back updated value
- movq mm1, [edi+ebx-8] // read a=Raw(x-bpp) bytes
-
- // Do second set of 4 bytes
- punpckhbw mm2, mm0 // Unpack High bytes of b
- punpckhbw mm1, mm0 // Unpack High bytes of a
- // pav = p - a = (a + b - c) - a = b - c
- movq mm4, mm2
- // pbv = p - b = (a + b - c) - b = a - c
- movq mm5, mm1
- psubw mm4, mm3
- pxor mm7, mm7
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- movq mm6, mm4
- psubw mm5, mm3
- // pa = abs(p-a) = abs(pav)
- // pb = abs(p-b) = abs(pbv)
- // pc = abs(p-c) = abs(pcv)
- pcmpgtw mm0, mm4 // Create mask pav bytes < 0
- paddw mm6, mm5
- pand mm0, mm4 // Only pav bytes < 0 in mm7
- pcmpgtw mm7, mm5 // Create mask pbv bytes < 0
- psubw mm4, mm0
- pand mm7, mm5 // Only pbv bytes < 0 in mm0
- psubw mm4, mm0
- psubw mm5, mm7
- pxor mm0, mm0
- pcmpgtw mm0, mm6 // Create mask pcv bytes < 0
- pand mm0, mm6 // Only pav bytes < 0 in mm7
- psubw mm5, mm7
- psubw mm6, mm0
- // test pa <= pb
- movq mm7, mm4
- psubw mm6, mm0
- pcmpgtw mm7, mm5 // pa > pb?
- movq mm0, mm7
- // use mm7 mask to merge pa & pb
- pand mm5, mm7
- // use mm0 mask copy to merge a & b
- pand mm2, mm0
- pandn mm7, mm4
- pandn mm0, mm1
- paddw mm7, mm5
- paddw mm0, mm2
- // test ((pa <= pb)? pa:pb) <= pc
- pcmpgtw mm7, mm6 // pab > pc?
- pxor mm1, mm1
- pand mm3, mm7
- pandn mm7, mm0
- pxor mm1, mm1
- paddw mm7, mm3
- pxor mm0, mm0
- // Step ex to next set of 8 bytes and repeat loop til done
- add ebx, 8
- packuswb mm1, mm7
- paddb mm1, [edi + ebx - 8] // add Paeth predictor with Raw(x)
- cmp ebx, MMXLength
- movq [edi + ebx - 8], mm1 // write back updated value
- // mm1 will be used as Raw(x-bpp) next loop
- jb dpth8lp
- } // end _asm block
- }
- break;
-
- case 1: // bpp = 1
- case 2: // bpp = 2
- default: // bpp > 8
- {
- _asm {
- mov ebx, diff
- cmp ebx, FullLength
- jnb dpthdend
- mov edi, row
- mov esi, prev_row
- // Do Paeth decode for remaining bytes
- mov edx, ebx
- xor ecx, ecx // zero ecx before using cl & cx in loop below
- sub edx, bpp // Set edx = ebx - bpp
-dpthdlp:
- xor eax, eax
- // pav = p - a = (a + b - c) - a = b - c
- mov al, [esi + ebx] // load Prior(x) into al
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- sub eax, ecx // subtract Prior(x-bpp)
- mov patemp, eax // Save pav for later use
- xor eax, eax
- // pbv = p - b = (a + b - c) - b = a - c
- mov al, [edi + edx] // load Raw(x-bpp) into al
- sub eax, ecx // subtract Prior(x-bpp)
- mov ecx, eax
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- add eax, patemp // pcv = pav + pbv
- // pc = abs(pcv)
- test eax, 0x80000000
- jz dpthdpca
- neg eax // reverse sign of neg values
-dpthdpca:
- mov pctemp, eax // save pc for later use
- // pb = abs(pbv)
- test ecx, 0x80000000
- jz dpthdpba
- neg ecx // reverse sign of neg values
-dpthdpba:
- mov pbtemp, ecx // save pb for later use
- // pa = abs(pav)
- mov eax, patemp
- test eax, 0x80000000
- jz dpthdpaa
- neg eax // reverse sign of neg values
-dpthdpaa:
- mov patemp, eax // save pa for later use
- // test if pa <= pb
- cmp eax, ecx
- jna dpthdabb
- // pa > pb; now test if pb <= pc
- cmp ecx, pctemp
- jna dpthdbbc
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthdpaeth
-dpthdbbc:
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- mov cl, [esi + ebx] // load Prior(x) into cl
- jmp dpthdpaeth
-dpthdabb:
- // pa <= pb; now test if pa <= pc
- cmp eax, pctemp
- jna dpthdabc
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthdpaeth
-dpthdabc:
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- mov cl, [edi + edx] // load Raw(x-bpp) into cl
-dpthdpaeth:
- inc ebx
- inc edx
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- add [edi + ebx - 1], cl
- cmp ebx, FullLength
- jb dpthdlp
-dpthdend:
- } // end _asm block
- }
- return; // No need to go further with this one
- } // end switch ( bpp )
- _asm
- {
- // MMX acceleration complete now do clean-up
- // Check if any remaining bytes left to decode
- mov ebx, MMXLength
- cmp ebx, FullLength
- jnb dpthend
- mov edi, row
- mov esi, prev_row
- // Do Paeth decode for remaining bytes
- mov edx, ebx
- xor ecx, ecx // zero ecx before using cl & cx in loop below
- sub edx, bpp // Set edx = ebx - bpp
-dpthlp2:
- xor eax, eax
- // pav = p - a = (a + b - c) - a = b - c
- mov al, [esi + ebx] // load Prior(x) into al
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- sub eax, ecx // subtract Prior(x-bpp)
- mov patemp, eax // Save pav for later use
- xor eax, eax
- // pbv = p - b = (a + b - c) - b = a - c
- mov al, [edi + edx] // load Raw(x-bpp) into al
- sub eax, ecx // subtract Prior(x-bpp)
- mov ecx, eax
- // pcv = p - c = (a + b - c) -c = (a - c) + (b - c) = pav + pbv
- add eax, patemp // pcv = pav + pbv
- // pc = abs(pcv)
- test eax, 0x80000000
- jz dpthpca2
- neg eax // reverse sign of neg values
-dpthpca2:
- mov pctemp, eax // save pc for later use
- // pb = abs(pbv)
- test ecx, 0x80000000
- jz dpthpba2
- neg ecx // reverse sign of neg values
-dpthpba2:
- mov pbtemp, ecx // save pb for later use
- // pa = abs(pav)
- mov eax, patemp
- test eax, 0x80000000
- jz dpthpaa2
- neg eax // reverse sign of neg values
-dpthpaa2:
- mov patemp, eax // save pa for later use
- // test if pa <= pb
- cmp eax, ecx
- jna dpthabb2
- // pa > pb; now test if pb <= pc
- cmp ecx, pctemp
- jna dpthbbc2
- // pb > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthpaeth2
-dpthbbc2:
- // pb <= pc; Raw(x) = Paeth(x) + Prior(x)
- mov cl, [esi + ebx] // load Prior(x) into cl
- jmp dpthpaeth2
-dpthabb2:
- // pa <= pb; now test if pa <= pc
- cmp eax, pctemp
- jna dpthabc2
- // pa > pc; Raw(x) = Paeth(x) + Prior(x-bpp)
- mov cl, [esi + edx] // load Prior(x-bpp) into cl
- jmp dpthpaeth2
-dpthabc2:
- // pa <= pc; Raw(x) = Paeth(x) + Raw(x-bpp)
- mov cl, [edi + edx] // load Raw(x-bpp) into cl
-dpthpaeth2:
- inc ebx
- inc edx
- // Raw(x) = (Paeth(x) + Paeth_Predictor( a, b, c )) mod 256
- add [edi + ebx - 1], cl
- cmp ebx, FullLength
- jb dpthlp2
-dpthend:
- emms // End MMX instructions; prep for possible FP instrs.
- } // end _asm block
-}
-
-// Optimized code for PNG Sub filter decoder
-void /* PRIVATE */
-png_read_filter_row_mmx_sub(png_row_infop row_info, png_bytep row)
-{
- //int test;
- int bpp;
- png_uint_32 FullLength;
- png_uint_32 MMXLength;
- int diff;
-
- bpp = (row_info->pixel_depth + 7) >> 3; // Get # bytes per pixel
- FullLength = row_info->rowbytes - bpp; // # of bytes to filter
- _asm {
- mov edi, row
- mov esi, edi // lp = row
- add edi, bpp // rp = row + bpp
- xor eax, eax
- // get # of bytes to alignment
- mov diff, edi // take start of row
- add diff, 0xf // add 7 + 8 to incr past
- // alignment boundary
- xor ebx, ebx
- and diff, 0xfffffff8 // mask to alignment boundary
- sub diff, edi // subtract from start ==> value
- // ebx at alignment
- jz dsubgo
- // fix alignment
-dsublp1:
- mov al, [esi+ebx]
- add [edi+ebx], al
- inc ebx
- cmp ebx, diff
- jb dsublp1
-dsubgo:
- mov ecx, FullLength
- mov edx, ecx
- sub edx, ebx // subtract alignment fix
- and edx, 0x00000007 // calc bytes over mult of 8
- sub ecx, edx // drop over bytes from length
- mov MMXLength, ecx
- } // end _asm block
-
- // Now do the math for the rest of the row
- switch ( bpp )
- {
- case 3:
- {
- ActiveMask.use = 0x0000ffffff000000;
- ShiftBpp.use = 24; // == 3 * 8
- ShiftRem.use = 40; // == 64 - 24
- _asm {
- mov edi, row
- movq mm7, ActiveMask // Load ActiveMask for 2nd active byte group
- mov esi, edi // lp = row
- add edi, bpp // rp = row + bpp
- movq mm6, mm7
- mov ebx, diff
- psllq mm6, ShiftBpp // Move mask in mm6 to cover 3rd active
- // byte group
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8]
-dsub3lp:
- psrlq mm1, ShiftRem // Shift data for adding 1st bpp bytes
- // no need for mask; shift clears inactive bytes
- // Add 1st active group
- movq mm0, [edi+ebx]
- paddb mm0, mm1
- // Add 2nd active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- pand mm1, mm7 // mask to use only 2nd active group
- paddb mm0, mm1
- // Add 3rd active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- pand mm1, mm6 // mask to use only 3rd active group
- add ebx, 8
- paddb mm0, mm1
- cmp ebx, MMXLength
- movq [edi+ebx-8], mm0 // Write updated Raws back to array
- // Prep for doing 1st add at top of loop
- movq mm1, mm0
- jb dsub3lp
- } // end _asm block
- }
- break;
-
- case 1:
- {
- // Placed here just in case this is a duplicate of the
- // non-MMX code for the SUB filter in png_read_filter_row below
- //
- // png_bytep rp;
- // png_bytep lp;
- // png_uint_32 i;
- // bpp = (row_info->pixel_depth + 7) >> 3;
- // for (i = (png_uint_32)bpp, rp = row + bpp, lp = row;
- // i < row_info->rowbytes; i++, rp++, lp++)
- // {
- // *rp = (png_byte)(((int)(*rp) + (int)(*lp)) & 0xff);
- // }
- _asm {
- mov ebx, diff
- mov edi, row
- cmp ebx, FullLength
- jnb dsub1end
- mov esi, edi // lp = row
- xor eax, eax
- add edi, bpp // rp = row + bpp
-dsub1lp:
- mov al, [esi+ebx]
- add [edi+ebx], al
- inc ebx
- cmp ebx, FullLength
- jb dsub1lp
-dsub1end:
- } // end _asm block
- }
- return;
-
- case 6:
- case 7:
- case 4:
- case 5:
- {
- ShiftBpp.use = bpp << 3;
- ShiftRem.use = 64 - ShiftBpp.use;
- _asm {
- mov edi, row
- mov ebx, diff
- mov esi, edi // lp = row
- add edi, bpp // rp = row + bpp
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8]
-dsub4lp:
- psrlq mm1, ShiftRem // Shift data for adding 1st bpp bytes
- // no need for mask; shift clears inactive bytes
- movq mm0, [edi+ebx]
- paddb mm0, mm1
- // Add 2nd active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- // there is no need for any mask
- // since shift clears inactive bits/bytes
- add ebx, 8
- paddb mm0, mm1
- cmp ebx, MMXLength
- movq [edi+ebx-8], mm0
- movq mm1, mm0 // Prep for doing 1st add at top of loop
- jb dsub4lp
- } // end _asm block
- }
- break;
-
- case 2:
- {
- ActiveMask.use = 0x00000000ffff0000;
- ShiftBpp.use = 16; // == 2 * 8
- ShiftRem.use = 48; // == 64 - 16
- _asm {
- movq mm7, ActiveMask // Load ActiveMask for 2nd active byte group
- mov ebx, diff
- movq mm6, mm7
- mov edi, row
- psllq mm6, ShiftBpp // Move mask in mm6 to cover 3rd active
- // byte group
- mov esi, edi // lp = row
- movq mm5, mm6
- add edi, bpp // rp = row + bpp
- psllq mm5, ShiftBpp // Move mask in mm5 to cover 4th active
- // byte group
- // PRIME the pump (load the first Raw(x-bpp) data set
- movq mm1, [edi+ebx-8]
-dsub2lp:
- // Add 1st active group
- psrlq mm1, ShiftRem // Shift data for adding 1st bpp bytes
- // no need for mask; shift clears inactive
- // bytes
- movq mm0, [edi+ebx]
- paddb mm0, mm1
- // Add 2nd active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- pand mm1, mm7 // mask to use only 2nd active group
- paddb mm0, mm1
- // Add 3rd active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- pand mm1, mm6 // mask to use only 3rd active group
- paddb mm0, mm1
- // Add 4th active group
- movq mm1, mm0 // mov updated Raws to mm1
- psllq mm1, ShiftBpp // shift data to position correctly
- pand mm1, mm5 // mask to use only 4th active group
- add ebx, 8
- paddb mm0, mm1
- cmp ebx, MMXLength
- movq [edi+ebx-8], mm0 // Write updated Raws back to array
- movq mm1, mm0 // Prep for doing 1st add at top of loop
- jb dsub2lp
- } // end _asm block
- }
- break;
- case 8:
- {
- _asm {
- mov edi, row
- mov ebx, diff
- mov esi, edi // lp = row
- add edi, bpp // rp = row + bpp
- mov ecx, MMXLength
- movq mm7, [edi+ebx-8] // PRIME the pump (load the first
- // Raw(x-bpp) data set
- and ecx, 0x0000003f // calc bytes over mult of 64
-dsub8lp:
- movq mm0, [edi+ebx] // Load Sub(x) for 1st 8 bytes
- paddb mm0, mm7
- movq mm1, [edi+ebx+8] // Load Sub(x) for 2nd 8 bytes
- movq [edi+ebx], mm0 // Write Raw(x) for 1st 8 bytes
- // Now mm0 will be used as Raw(x-bpp) for
- // the 2nd group of 8 bytes. This will be
- // repeated for each group of 8 bytes with
- // the 8th group being used as the Raw(x-bpp)
- // for the 1st group of the next loop.
- paddb mm1, mm0
- movq mm2, [edi+ebx+16] // Load Sub(x) for 3rd 8 bytes
- movq [edi+ebx+8], mm1 // Write Raw(x) for 2nd 8 bytes
- paddb mm2, mm1
- movq mm3, [edi+ebx+24] // Load Sub(x) for 4th 8 bytes
- movq [edi+ebx+16], mm2 // Write Raw(x) for 3rd 8 bytes
- paddb mm3, mm2
- movq mm4, [edi+ebx+32] // Load Sub(x) for 5th 8 bytes
- movq [edi+ebx+24], mm3 // Write Raw(x) for 4th 8 bytes
- paddb mm4, mm3
- movq mm5, [edi+ebx+40] // Load Sub(x) for 6th 8 bytes
- movq [edi+ebx+32], mm4 // Write Raw(x) for 5th 8 bytes
- paddb mm5, mm4
- movq mm6, [edi+ebx+48] // Load Sub(x) for 7th 8 bytes
- movq [edi+ebx+40], mm5 // Write Raw(x) for 6th 8 bytes
- paddb mm6, mm5
- movq mm7, [edi+ebx+56] // Load Sub(x) for 8th 8 bytes
- movq [edi+ebx+48], mm6 // Write Raw(x) for 7th 8 bytes
- add ebx, 64
- paddb mm7, mm6
- cmp ebx, ecx
- movq [edi+ebx-8], mm7 // Write Raw(x) for 8th 8 bytes
- jb dsub8lp
- cmp ebx, MMXLength
- jnb dsub8lt8
-dsub8lpA:
- movq mm0, [edi+ebx]
- add ebx, 8
- paddb mm0, mm7
- cmp ebx, MMXLength
- movq [edi+ebx-8], mm0 // use -8 to offset early add to ebx
- movq mm7, mm0 // Move calculated Raw(x) data to mm1 to
- // be the new Raw(x-bpp) for the next loop
- jb dsub8lpA
-dsub8lt8:
- } // end _asm block
- }
- break;
-
- default: // bpp greater than 8 bytes
- {
- _asm {
- mov ebx, diff
- mov edi, row
- mov esi, edi // lp = row
- add edi, bpp // rp = row + bpp
-dsubAlp:
- movq mm0, [edi+ebx]
- movq mm1, [esi+ebx]
- add ebx, 8
- paddb mm0, mm1
- cmp ebx, MMXLength
- movq [edi+ebx-8], mm0 // mov does not affect flags; -8 to offset
- // add ebx
- jb dsubAlp
- } // end _asm block
- }
- break;
-
- } // end switch ( bpp )
-
- _asm {
- mov ebx, MMXLength
- mov edi, row
- cmp ebx, FullLength
- jnb dsubend
- mov esi, edi // lp = row
- xor eax, eax
- add edi, bpp // rp = row + bpp
-dsublp2:
- mov al, [esi+ebx]
- add [edi+ebx], al
- inc ebx
- cmp ebx, FullLength
- jb dsublp2
-dsubend:
- emms // End MMX instructions; prep for possible FP instrs.
- } // end _asm block
-}
-
-// Optimized code for PNG Up filter decoder
-void /* PRIVATE */
-png_read_filter_row_mmx_up(png_row_infop row_info, png_bytep row,
- png_bytep prev_row)
-{
- png_uint_32 len;
- len = row_info->rowbytes; // # of bytes to filter
- _asm {
- mov edi, row
- // get # of bytes to alignment
- mov ecx, edi
- xor ebx, ebx
- add ecx, 0x7
- xor eax, eax
- and ecx, 0xfffffff8
- mov esi, prev_row
- sub ecx, edi
- jz dupgo
- // fix alignment
-duplp1:
- mov al, [edi+ebx]
- add al, [esi+ebx]
- inc ebx
- cmp ebx, ecx
- mov [edi + ebx-1], al // mov does not affect flags; -1 to offset inc ebx
- jb duplp1
-dupgo:
- mov ecx, len
- mov edx, ecx
- sub edx, ebx // subtract alignment fix
- and edx, 0x0000003f // calc bytes over mult of 64
- sub ecx, edx // drop over bytes from length
- // Unrolled loop - use all MMX registers and interleave to reduce
- // number of branch instructions (loops) and reduce partial stalls
-duploop:
- movq mm1, [esi+ebx]
- movq mm0, [edi+ebx]
- movq mm3, [esi+ebx+8]
- paddb mm0, mm1
- movq mm2, [edi+ebx+8]
- movq [edi+ebx], mm0
- paddb mm2, mm3
- movq mm5, [esi+ebx+16]
- movq [edi+ebx+8], mm2
- movq mm4, [edi+ebx+16]
- movq mm7, [esi+ebx+24]
- paddb mm4, mm5
- movq mm6, [edi+ebx+24]
- movq [edi+ebx+16], mm4
- paddb mm6, mm7
- movq mm1, [esi+ebx+32]
- movq [edi+ebx+24], mm6
- movq mm0, [edi+ebx+32]
- movq mm3, [esi+ebx+40]
- paddb mm0, mm1
- movq mm2, [edi+ebx+40]
- movq [edi+ebx+32], mm0
- paddb mm2, mm3
- movq mm5, [esi+ebx+48]
- movq [edi+ebx+40], mm2
- movq mm4, [edi+ebx+48]
- movq mm7, [esi+ebx+56]
- paddb mm4, mm5
- movq mm6, [edi+ebx+56]
- movq [edi+ebx+48], mm4
- add ebx, 64
- paddb mm6, mm7
- cmp ebx, ecx
- movq [edi+ebx-8], mm6 // (+56)movq does not affect flags;
- // -8 to offset add ebx
- jb duploop
-
- cmp edx, 0 // Test for bytes over mult of 64
- jz dupend
-
-
- // 2 lines added by lcreeve at netins.net
- // (mail 11 Jul 98 in png-implement list)
- cmp edx, 8 //test for less than 8 bytes
- jb duplt8
-
-
- add ecx, edx
- and edx, 0x00000007 // calc bytes over mult of 8
- sub ecx, edx // drop over bytes from length
- jz duplt8
- // Loop using MMX registers mm0 & mm1 to update 8 bytes simultaneously
-duplpA:
- movq mm1, [esi+ebx]
- movq mm0, [edi+ebx]
- add ebx, 8
- paddb mm0, mm1
- cmp ebx, ecx
- movq [edi+ebx-8], mm0 // movq does not affect flags; -8 to offset add ebx
- jb duplpA
- cmp edx, 0 // Test for bytes over mult of 8
- jz dupend
-duplt8:
- xor eax, eax
- add ecx, edx // move over byte count into counter
- // Loop using x86 registers to update remaining bytes
-duplp2:
- mov al, [edi + ebx]
- add al, [esi + ebx]
- inc ebx
- cmp ebx, ecx
- mov [edi + ebx-1], al // mov does not affect flags; -1 to offset inc ebx
- jb duplp2
-dupend:
- // Conversion of filtered row completed
- emms // End MMX instructions; prep for possible FP instrs.
- } // end _asm block
-}
-
-
-// Optimized png_read_filter_row routines
-void /* PRIVATE */
-png_read_filter_row(png_structp png_ptr, png_row_infop row_info, png_bytep
- row, png_bytep prev_row, int filter)
-{
-#ifdef PNG_DEBUG
- char filnm[10];
-#endif
-
- if (mmx_supported == 2) {
-#if !defined(PNG_1_0_X)
- /* this should have happened in png_init_mmx_flags() already */
- png_warning(png_ptr, "asm_flags may not have been initialized");
-#endif
- png_mmx_support();
- }
-
-#ifdef PNG_DEBUG
- png_debug(1, "in png_read_filter_row\n");
- switch (filter)
- {
- case 0: sprintf(filnm, "none");
- break;
-#if !defined(PNG_1_0_X)
- case 1: sprintf(filnm, "sub-%s",
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB)? "MMX" : "x86");
- break;
- case 2: sprintf(filnm, "up-%s",
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP)? "MMX" : "x86");
- break;
- case 3: sprintf(filnm, "avg-%s",
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG)? "MMX" : "x86");
- break;
- case 4: sprintf(filnm, "Paeth-%s",
- (png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH)? "MMX":"x86");
- break;
-#else
- case 1: sprintf(filnm, "sub");
- break;
- case 2: sprintf(filnm, "up");
- break;
- case 3: sprintf(filnm, "avg");
- break;
- case 4: sprintf(filnm, "Paeth");
- break;
-#endif
- default: sprintf(filnm, "unknw");
- break;
- }
- png_debug2(0,"row=%5d, %s, ", png_ptr->row_number, filnm);
- png_debug2(0, "pd=%2d, b=%d, ", (int)row_info->pixel_depth,
- (int)((row_info->pixel_depth + 7) >> 3));
- png_debug1(0,"len=%8d, ", row_info->rowbytes);
-#endif /* PNG_DEBUG */
-
- switch (filter)
- {
- case PNG_FILTER_VALUE_NONE:
- break;
-
- case PNG_FILTER_VALUE_SUB:
- {
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_SUB) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_sub(row_info, row);
- }
- else
- {
- png_uint_32 i;
- png_uint_32 istop = row_info->rowbytes;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_bytep rp = row + bpp;
- png_bytep lp = row;
-
- for (i = bpp; i < istop; i++)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*lp++)) & 0xff);
- rp++;
- }
- }
- break;
- }
-
- case PNG_FILTER_VALUE_UP:
- {
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_UP) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_up(row_info, row, prev_row);
- }
- else
- {
- png_uint_32 i;
- png_uint_32 istop = row_info->rowbytes;
- png_bytep rp = row;
- png_bytep pp = prev_row;
-
- for (i = 0; i < istop; ++i)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff);
- rp++;
- }
- }
- break;
- }
-
- case PNG_FILTER_VALUE_AVG:
- {
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_AVG) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_avg(row_info, row, prev_row);
- }
- else
- {
- png_uint_32 i;
- png_bytep rp = row;
- png_bytep pp = prev_row;
- png_bytep lp = row;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_uint_32 istop = row_info->rowbytes - bpp;
-
- for (i = 0; i < bpp; i++)
- {
- *rp = (png_byte)(((int)(*rp) +
- ((int)(*pp++) >> 1)) & 0xff);
- rp++;
- }
-
- for (i = 0; i < istop; i++)
- {
- *rp = (png_byte)(((int)(*rp) +
- ((int)(*pp++ + *lp++) >> 1)) & 0xff);
- rp++;
- }
- }
- break;
- }
-
- case PNG_FILTER_VALUE_PAETH:
- {
-#if !defined(PNG_1_0_X)
- if ((png_ptr->asm_flags & PNG_ASM_FLAG_MMX_READ_FILTER_PAETH) &&
- (row_info->pixel_depth >= png_ptr->mmx_bitdepth_threshold) &&
- (row_info->rowbytes >= png_ptr->mmx_rowbytes_threshold))
-#else
- if (mmx_supported)
-#endif
- {
- png_read_filter_row_mmx_paeth(row_info, row, prev_row);
- }
- else
- {
- png_uint_32 i;
- png_bytep rp = row;
- png_bytep pp = prev_row;
- png_bytep lp = row;
- png_bytep cp = prev_row;
- png_uint_32 bpp = (row_info->pixel_depth + 7) >> 3;
- png_uint_32 istop=row_info->rowbytes - bpp;
-
- for (i = 0; i < bpp; i++)
- {
- *rp = (png_byte)(((int)(*rp) + (int)(*pp++)) & 0xff);
- rp++;
- }
-
- for (i = 0; i < istop; i++) // use leftover rp,pp
- {
- int a, b, c, pa, pb, pc, p;
-
- a = *lp++;
- b = *pp++;
- c = *cp++;
-
- p = b - c;
- pc = a - c;
-
-#ifdef PNG_USE_ABS
- pa = abs(p);
- pb = abs(pc);
- pc = abs(p + pc);
-#else
- pa = p < 0 ? -p : p;
- pb = pc < 0 ? -pc : pc;
- pc = (p + pc) < 0 ? -(p + pc) : p + pc;
-#endif
-
- /*
- if (pa <= pb && pa <= pc)
- p = a;
- else if (pb <= pc)
- p = b;
- else
- p = c;
- */
-
- p = (pa <= pb && pa <=pc) ? a : (pb <= pc) ? b : c;
-
- *rp = (png_byte)(((int)(*rp) + p) & 0xff);
- rp++;
- }
- }
- break;
- }
-
- default:
- png_warning(png_ptr, "Ignoring bad row filter type");
- *row=0;
- break;
- }
-}
-
-#endif /* PNG_ASSEMBLER_CODE_SUPPORTED && PNG_USE_PNGVCRD */
+/* pnggvrd.c was removed from libpng-1.2.20. */
diff --git a/Build/source/libs/libpng/pngwio.c b/Build/source/libs/libpng/pngwio.c
index 4d9d57e36a7..371a4fad624 100644
--- a/Build/source/libs/libpng/pngwio.c
+++ b/Build/source/libs/libpng/pngwio.c
@@ -3,7 +3,7 @@
*
* Last changed in libpng 1.2.13 November 13, 2006
* For conditions of distribution and use, see copyright notice in png.h
- * Copyright (c) 1998-2002 Glenn Randers-Pehrson
+ * Copyright (c) 1998-2006 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
* (Version 0.88 Copyright (c) 1995, 1996 Guy Eric Schalnat, Group 42, Inc.)
*
diff --git a/Build/source/libs/libpng/pngwrite.c b/Build/source/libs/libpng/pngwrite.c
index df7ade3349a..b1f6a593aae 100644
--- a/Build/source/libs/libpng/pngwrite.c
+++ b/Build/source/libs/libpng/pngwrite.c
@@ -1,7 +1,7 @@
/* pngwrite.c - general routines to write a PNG file
*
- * Last changed in libpng 1.2.15 January 5, 2007
+ * Last changed in libpng 1.2.24 December 14, 2007
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -391,11 +391,6 @@ png_write_end(png_structp png_ptr, png_infop info_ptr)
/* write end of PNG file */
png_write_IEND(png_ptr);
-#if 0
-/* This flush, added in libpng-1.0.8, causes some applications to crash
- because they do not set png_ptr->output_flush_fn */
- png_flush(png_ptr);
-#endif
}
#if defined(PNG_WRITE_tIME_SUPPORTED)
@@ -459,14 +454,6 @@ png_create_write_struct_2(png_const_charp user_png_ver, png_voidp error_ptr,
if (png_ptr == NULL)
return (NULL);
-#if !defined(PNG_1_0_X)
-#ifdef PNG_ASSEMBLER_CODE_SUPPORTED
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_init_mmx_flags(png_ptr); /* 1.2.0 addition */
-#endif
-#endif
-#endif /* PNG_1_0_X */
-
/* added at libpng-1.2.6 */
#ifdef PNG_SET_USER_LIMITS_SUPPORTED
png_ptr->user_width_max=PNG_USER_WIDTH_MAX;
@@ -517,11 +504,13 @@ png_create_write_struct_2(png_const_charp user_png_ver, png_voidp error_ptr,
char msg[80];
if (user_png_ver)
{
- sprintf(msg, "Application was compiled with png.h from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application was compiled with png.h from libpng-%.20s",
user_png_ver);
png_warning(png_ptr, msg);
}
- sprintf(msg, "Application is running with png.c from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application is running with png.c from libpng-%.20s",
png_libpng_ver);
png_warning(png_ptr, msg);
#endif
@@ -587,11 +576,13 @@ png_write_init_2(png_structp png_ptr, png_const_charp user_png_ver,
png_ptr->warning_fn=NULL;
if (user_png_ver)
{
- sprintf(msg, "Application was compiled with png.h from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application was compiled with png.h from libpng-%.20s",
user_png_ver);
png_warning(png_ptr, msg);
}
- sprintf(msg, "Application is running with png.c from libpng-%.20s",
+ png_snprintf(msg, 80,
+ "Application is running with png.c from libpng-%.20s",
png_libpng_ver);
png_warning(png_ptr, msg);
}
@@ -671,14 +662,6 @@ png_write_init_3(png_structpp ptr_ptr, png_const_charp user_png_ver,
png_ptr->user_height_max=PNG_USER_HEIGHT_MAX;
#endif
-#if !defined(PNG_1_0_X)
-#ifdef PNG_ASSEMBLER_CODE_SUPPORTED
-#ifdef PNG_MMX_CODE_SUPPORTED
- png_init_mmx_flags(png_ptr); /* 1.2.0 addition */
-#endif
-#endif
-#endif /* PNG_1_0_X */
-
#ifdef PNG_SETJMP_SUPPORTED
/* restore jump buffer */
png_memcpy(png_ptr->jmpbuf, tmp_jmp, png_sizeof (jmp_buf));
@@ -1077,11 +1060,13 @@ png_write_destroy(png_structp png_ptr)
/* free our memory. png_free checks NULL for us. */
png_free(png_ptr, png_ptr->zbuf);
png_free(png_ptr, png_ptr->row_buf);
+#ifndef PNG_NO_WRITE_FILTERING
png_free(png_ptr, png_ptr->prev_row);
png_free(png_ptr, png_ptr->sub_row);
png_free(png_ptr, png_ptr->up_row);
png_free(png_ptr, png_ptr->avg_row);
png_free(png_ptr, png_ptr->paeth_row);
+#endif
#if defined(PNG_TIME_RFC1123_SUPPORTED)
png_free(png_ptr, png_ptr->time_buffer);
@@ -1137,15 +1122,26 @@ png_set_filter(png_structp png_ptr, int method, int filters)
{
switch (filters & (PNG_ALL_FILTERS | 0x07))
{
+#ifndef PNG_NO_WRITE_FILTER
case 5:
case 6:
case 7: png_warning(png_ptr, "Unknown row filter for method 0");
- case PNG_FILTER_VALUE_NONE: png_ptr->do_filter=PNG_FILTER_NONE; break;
- case PNG_FILTER_VALUE_SUB: png_ptr->do_filter=PNG_FILTER_SUB; break;
- case PNG_FILTER_VALUE_UP: png_ptr->do_filter=PNG_FILTER_UP; break;
- case PNG_FILTER_VALUE_AVG: png_ptr->do_filter=PNG_FILTER_AVG; break;
- case PNG_FILTER_VALUE_PAETH: png_ptr->do_filter=PNG_FILTER_PAETH;break;
+#endif /* PNG_NO_WRITE_FILTER */
+ case PNG_FILTER_VALUE_NONE:
+ png_ptr->do_filter=PNG_FILTER_NONE; break;
+#ifndef PNG_NO_WRITE_FILTER
+ case PNG_FILTER_VALUE_SUB:
+ png_ptr->do_filter=PNG_FILTER_SUB; break;
+ case PNG_FILTER_VALUE_UP:
+ png_ptr->do_filter=PNG_FILTER_UP; break;
+ case PNG_FILTER_VALUE_AVG:
+ png_ptr->do_filter=PNG_FILTER_AVG; break;
+ case PNG_FILTER_VALUE_PAETH:
+ png_ptr->do_filter=PNG_FILTER_PAETH; break;
default: png_ptr->do_filter = (png_byte)filters; break;
+#else
+ default: png_warning(png_ptr, "Unknown row filter for method 0");
+#endif /* PNG_NO_WRITE_FILTER */
}
/* If we have allocated the row_buf, this means we have already started
@@ -1159,6 +1155,7 @@ png_set_filter(png_structp png_ptr, int method, int filters)
*/
if (png_ptr->row_buf != NULL)
{
+#ifndef PNG_NO_WRITE_FILTER
if ((png_ptr->do_filter & PNG_FILTER_SUB) && png_ptr->sub_row == NULL)
{
png_ptr->sub_row = (png_bytep)png_malloc(png_ptr,
@@ -1213,6 +1210,7 @@ png_set_filter(png_structp png_ptr, int method, int filters)
}
if (png_ptr->do_filter == PNG_NO_FILTERS)
+#endif /* PNG_NO_WRITE_FILTER */
png_ptr->do_filter = PNG_FILTER_NONE;
}
}
@@ -1511,8 +1509,8 @@ png_write_png(png_structp png_ptr, png_infop info_ptr,
/* It is REQUIRED to call this to finish writing the rest of the file */
png_write_end(png_ptr, info_ptr);
- if(transforms == 0 || params == NULL)
- /* quiet compiler warnings */ return;
+ transforms = transforms; /* quiet compiler warnings */
+ params = params;
}
#endif
#endif /* PNG_WRITE_SUPPORTED */
diff --git a/Build/source/libs/libpng/pngwutil.c b/Build/source/libs/libpng/pngwutil.c
index 314bea20d1c..fef38aef9dd 100644
--- a/Build/source/libs/libpng/pngwutil.c
+++ b/Build/source/libs/libpng/pngwutil.c
@@ -1,7 +1,7 @@
/* pngwutil.c - utilities to write a PNG file
*
- * Last changed in libpng 1.2.15 January 5, 2007
+ * Last changed in libpng 1.2.20 Septhember 3, 2007
* For conditions of distribution and use, see copyright notice in png.h
* Copyright (c) 1998-2007 Glenn Randers-Pehrson
* (Version 0.96 Copyright (c) 1996, 1997 Andreas Dilger)
@@ -182,7 +182,7 @@ png_text_compress(png_structp png_ptr,
{
#if !defined(PNG_NO_STDIO) && !defined(_WIN32_WCE)
char msg[50];
- sprintf(msg, "Unknown compression type %d", compression);
+ png_snprintf(msg, 50, "Unknown compression type %d", compression);
png_warning(png_ptr, msg);
#else
png_warning(png_ptr, "Unknown compression type");
@@ -494,7 +494,7 @@ png_write_IHDR(png_structp png_ptr, png_uint_32 width, png_uint_32 height,
buf[12] = (png_byte)interlace_type;
/* write the chunk */
- png_write_chunk(png_ptr, (png_bytep)png_IHDR, buf, (png_size_t)13);
+ png_write_chunk(png_ptr, png_IHDR, buf, (png_size_t)13);
/* initialize zlib with PNG info */
png_ptr->zstream.zalloc = png_zalloc;
@@ -578,7 +578,7 @@ png_write_PLTE(png_structp png_ptr, png_colorp palette, png_uint_32 num_pal)
png_ptr->num_palette = (png_uint_16)num_pal;
png_debug1(3, "num_palette = %d\n", png_ptr->num_palette);
- png_write_chunk_start(png_ptr, (png_bytep)png_PLTE, num_pal * 3);
+ png_write_chunk_start(png_ptr, png_PLTE, num_pal * 3);
#ifndef PNG_NO_POINTER_INDEXING
for (i = 0, pal_ptr = palette; i < num_pal; i++, pal_ptr++)
{
@@ -650,7 +650,7 @@ png_write_IDAT(png_structp png_ptr, png_bytep data, png_size_t length)
"Invalid zlib compression method or flags in IDAT");
}
- png_write_chunk(png_ptr, (png_bytep)png_IDAT, data, length);
+ png_write_chunk(png_ptr, png_IDAT, data, length);
png_ptr->mode |= PNG_HAVE_IDAT;
}
@@ -662,7 +662,7 @@ png_write_IEND(png_structp png_ptr)
PNG_IEND;
#endif
png_debug(1, "in png_write_IEND\n");
- png_write_chunk(png_ptr, (png_bytep)png_IEND, png_bytep_NULL,
+ png_write_chunk(png_ptr, png_IEND, png_bytep_NULL,
(png_size_t)0);
png_ptr->mode |= PNG_HAVE_IEND;
}
@@ -683,7 +683,7 @@ png_write_gAMA(png_structp png_ptr, double file_gamma)
/* file_gamma is saved in 1/100,000ths */
igamma = (png_uint_32)(file_gamma * 100000.0 + 0.5);
png_save_uint_32(buf, igamma);
- png_write_chunk(png_ptr, (png_bytep)png_gAMA, buf, (png_size_t)4);
+ png_write_chunk(png_ptr, png_gAMA, buf, (png_size_t)4);
}
#endif
#ifdef PNG_FIXED_POINT_SUPPORTED
@@ -698,7 +698,7 @@ png_write_gAMA_fixed(png_structp png_ptr, png_fixed_point file_gamma)
png_debug(1, "in png_write_gAMA\n");
/* file_gamma is saved in 1/100,000ths */
png_save_uint_32(buf, (png_uint_32)file_gamma);
- png_write_chunk(png_ptr, (png_bytep)png_gAMA, buf, (png_size_t)4);
+ png_write_chunk(png_ptr, png_gAMA, buf, (png_size_t)4);
}
#endif
#endif
@@ -718,7 +718,7 @@ png_write_sRGB(png_structp png_ptr, int srgb_intent)
png_warning(png_ptr,
"Invalid sRGB rendering intent specified");
buf[0]=(png_byte)srgb_intent;
- png_write_chunk(png_ptr, (png_bytep)png_sRGB, buf, (png_size_t)1);
+ png_write_chunk(png_ptr, png_sRGB, buf, (png_size_t)1);
}
#endif
@@ -783,7 +783,7 @@ png_write_iCCP(png_structp png_ptr, png_charp name, int compression_type,
PNG_COMPRESSION_TYPE_BASE, &comp);
/* make sure we include the NULL after the name and the compression type */
- png_write_chunk_start(png_ptr, (png_bytep)png_iCCP,
+ png_write_chunk_start(png_ptr, png_iCCP,
(png_uint_32)name_len+profile_len+2);
new_name[name_len+1]=0x00;
png_write_chunk_data(png_ptr, (png_bytep)new_name, name_len + 2);
@@ -823,7 +823,7 @@ png_write_sPLT(png_structp png_ptr, png_sPLT_tp spalette)
}
/* make sure we include the NULL after the name */
- png_write_chunk_start(png_ptr, (png_bytep)png_sPLT,
+ png_write_chunk_start(png_ptr, png_sPLT,
(png_uint_32)(name_len + 2 + palette_size));
png_write_chunk_data(png_ptr, (png_bytep)new_name, name_len + 1);
png_write_chunk_data(png_ptr, (png_bytep)&spalette->depth, 1);
@@ -931,7 +931,7 @@ png_write_sBIT(png_structp png_ptr, png_color_8p sbit, int color_type)
buf[size++] = sbit->alpha;
}
- png_write_chunk(png_ptr, (png_bytep)png_sBIT, buf, size);
+ png_write_chunk(png_ptr, png_sBIT, buf, size);
}
#endif
@@ -995,7 +995,7 @@ png_write_cHRM(png_structp png_ptr, double white_x, double white_y,
itemp = (png_uint_32)(blue_y * 100000.0 + 0.5);
png_save_uint_32(buf + 28, itemp);
- png_write_chunk(png_ptr, (png_bytep)png_cHRM, buf, (png_size_t)32);
+ png_write_chunk(png_ptr, png_cHRM, buf, (png_size_t)32);
}
#endif
#ifdef PNG_FIXED_POINT_SUPPORTED
@@ -1047,7 +1047,7 @@ png_write_cHRM_fixed(png_structp png_ptr, png_fixed_point white_x,
png_save_uint_32(buf + 24, (png_uint_32)blue_x);
png_save_uint_32(buf + 28, (png_uint_32)blue_y);
- png_write_chunk(png_ptr, (png_bytep)png_cHRM, buf, (png_size_t)32);
+ png_write_chunk(png_ptr, png_cHRM, buf, (png_size_t)32);
}
#endif
#endif
@@ -1072,7 +1072,7 @@ png_write_tRNS(png_structp png_ptr, png_bytep trans, png_color_16p tran,
return;
}
/* write the chunk out as it is */
- png_write_chunk(png_ptr, (png_bytep)png_tRNS, trans, (png_size_t)num_trans);
+ png_write_chunk(png_ptr, png_tRNS, trans, (png_size_t)num_trans);
}
else if (color_type == PNG_COLOR_TYPE_GRAY)
{
@@ -1084,7 +1084,7 @@ png_write_tRNS(png_structp png_ptr, png_bytep trans, png_color_16p tran,
return;
}
png_save_uint_16(buf, tran->gray);
- png_write_chunk(png_ptr, (png_bytep)png_tRNS, buf, (png_size_t)2);
+ png_write_chunk(png_ptr, png_tRNS, buf, (png_size_t)2);
}
else if (color_type == PNG_COLOR_TYPE_RGB)
{
@@ -1098,7 +1098,7 @@ png_write_tRNS(png_structp png_ptr, png_bytep trans, png_color_16p tran,
"Ignoring attempt to write 16-bit tRNS chunk when bit_depth is 8");
return;
}
- png_write_chunk(png_ptr, (png_bytep)png_tRNS, buf, (png_size_t)6);
+ png_write_chunk(png_ptr, png_tRNS, buf, (png_size_t)6);
}
else
{
@@ -1131,7 +1131,7 @@ png_write_bKGD(png_structp png_ptr, png_color_16p back, int color_type)
return;
}
buf[0] = back->index;
- png_write_chunk(png_ptr, (png_bytep)png_bKGD, buf, (png_size_t)1);
+ png_write_chunk(png_ptr, png_bKGD, buf, (png_size_t)1);
}
else if (color_type & PNG_COLOR_MASK_COLOR)
{
@@ -1144,7 +1144,7 @@ png_write_bKGD(png_structp png_ptr, png_color_16p back, int color_type)
"Ignoring attempt to write 16-bit bKGD chunk when bit_depth is 8");
return;
}
- png_write_chunk(png_ptr, (png_bytep)png_bKGD, buf, (png_size_t)6);
+ png_write_chunk(png_ptr, png_bKGD, buf, (png_size_t)6);
}
else
{
@@ -1155,7 +1155,7 @@ png_write_bKGD(png_structp png_ptr, png_color_16p back, int color_type)
return;
}
png_save_uint_16(buf, back->gray);
- png_write_chunk(png_ptr, (png_bytep)png_bKGD, buf, (png_size_t)2);
+ png_write_chunk(png_ptr, png_bKGD, buf, (png_size_t)2);
}
}
#endif
@@ -1180,7 +1180,7 @@ png_write_hIST(png_structp png_ptr, png_uint_16p hist, int num_hist)
return;
}
- png_write_chunk_start(png_ptr, (png_bytep)png_hIST, (png_uint_32)(num_hist * 2));
+ png_write_chunk_start(png_ptr, png_hIST, (png_uint_32)(num_hist * 2));
for (i = 0; i < num_hist; i++)
{
png_save_uint_16(buf, hist[i]);
@@ -1231,12 +1231,14 @@ png_check_keyword(png_structp png_ptr, png_charp key, png_charpp new_key)
/* Replace non-printing characters with a blank and print a warning */
for (kp = key, dp = *new_key; *kp != '\0'; kp++, dp++)
{
- if (*kp < 0x20 || (*kp > 0x7E && (png_byte)*kp < 0xA1))
+ if ((png_byte)*kp < 0x20 ||
+ ((png_byte)*kp > 0x7E && (png_byte)*kp < 0xA1))
{
#if !defined(PNG_NO_STDIO) && !defined(_WIN32_WCE)
char msg[40];
- sprintf(msg, "invalid keyword character 0x%02X", *kp);
+ png_snprintf(msg, 40,
+ "invalid keyword character 0x%02X", (png_byte)*kp);
png_warning(png_ptr, msg);
#else
png_warning(png_ptr, "invalid character in keyword");
@@ -1344,7 +1346,7 @@ png_write_tEXt(png_structp png_ptr, png_charp key, png_charp text,
text_len = png_strlen(text);
/* make sure we include the 0 after the key */
- png_write_chunk_start(png_ptr, (png_bytep)png_tEXt, (png_uint_32)key_len+text_len+1);
+ png_write_chunk_start(png_ptr, png_tEXt, (png_uint_32)key_len+text_len+1);
/*
* We leave it to the application to meet PNG-1.0 requirements on the
* contents of the text. PNG-1.0 through PNG-1.2 discourage the use of
@@ -1397,17 +1399,17 @@ png_write_zTXt(png_structp png_ptr, png_charp key, png_charp text,
text_len = png_strlen(text);
- png_free(png_ptr, new_key);
-
/* compute the compressed data; do it now for the length */
text_len = png_text_compress(png_ptr, text, text_len, compression,
&comp);
/* write start of chunk */
- png_write_chunk_start(png_ptr, (png_bytep)png_zTXt, (png_uint_32)
+ png_write_chunk_start(png_ptr, png_zTXt, (png_uint_32)
(key_len+text_len+2));
/* write key */
- png_write_chunk_data(png_ptr, (png_bytep)key, key_len + 1);
+ png_write_chunk_data(png_ptr, (png_bytep)new_key, key_len + 1);
+ png_free(png_ptr, new_key);
+
buf[0] = (png_byte)compression;
/* write compression */
png_write_chunk_data(png_ptr, (png_bytep)buf, (png_size_t)1);
@@ -1470,7 +1472,7 @@ png_write_iTXt(png_structp png_ptr, int compression, png_charp key,
/* make sure we include the compression flag, the compression byte,
* and the NULs after the key, lang, and lang_key parts */
- png_write_chunk_start(png_ptr, (png_bytep)png_iTXt,
+ png_write_chunk_start(png_ptr, png_iTXt,
(png_uint_32)(
5 /* comp byte, comp flag, terminators for key, lang and lang_key */
+ key_len
@@ -1527,10 +1529,9 @@ png_write_oFFs(png_structp png_ptr, png_int_32 x_offset, png_int_32 y_offset,
png_save_int_32(buf + 4, y_offset);
buf[8] = (png_byte)unit_type;
- png_write_chunk(png_ptr, (png_bytep)png_oFFs, buf, (png_size_t)9);
+ png_write_chunk(png_ptr, png_oFFs, buf, (png_size_t)9);
}
#endif
-
#if defined(PNG_WRITE_pCAL_SUPPORTED)
/* write the pCAL chunk (described in the PNG extensions document) */
void /* PRIVATE */
@@ -1569,7 +1570,7 @@ png_write_pCAL(png_structp png_ptr, png_charp purpose, png_int_32 X0,
}
png_debug1(3, "pCAL total length = %d\n", (int)total_len);
- png_write_chunk_start(png_ptr, (png_bytep)png_pCAL, (png_uint_32)total_len);
+ png_write_chunk_start(png_ptr, png_pCAL, (png_uint_32)total_len);
png_write_chunk_data(png_ptr, (png_bytep)new_purpose, purpose_len);
png_save_int_32(buf, X0);
png_save_int_32(buf + 4, X1);
@@ -1622,14 +1623,14 @@ png_write_sCAL(png_structp png_ptr, int unit, double width, double height)
total_len += wc_len;
}
#else
- sprintf(buf + 1, "%12.12e", width);
+ png_snprintf(buf + 1, 63, "%12.12e", width);
total_len = 1 + png_strlen(buf + 1) + 1;
- sprintf(buf + total_len, "%12.12e", height);
+ png_snprintf(buf + total_len, 64-total_len, "%12.12e", height);
total_len += png_strlen(buf + total_len);
#endif
png_debug1(3, "sCAL total length = %u\n", (unsigned int)total_len);
- png_write_chunk(png_ptr, (png_bytep)png_sCAL, (png_bytep)buf, total_len);
+ png_write_chunk(png_ptr, png_sCAL, (png_bytep)buf, total_len);
}
#else
#ifdef PNG_FIXED_POINT_SUPPORTED
@@ -1659,7 +1660,7 @@ png_write_sCAL_s(png_structp png_ptr, int unit, png_charp width,
png_memcpy(buf + wlen + 2, height, hlen); /* do NOT append the '\0' here */
png_debug1(3, "sCAL total length = %u\n", (unsigned int)total_len);
- png_write_chunk(png_ptr, (png_bytep)png_sCAL, buf, total_len);
+ png_write_chunk(png_ptr, png_sCAL, buf, total_len);
}
#endif
#endif
@@ -1685,7 +1686,7 @@ png_write_pHYs(png_structp png_ptr, png_uint_32 x_pixels_per_unit,
png_save_uint_32(buf + 4, y_pixels_per_unit);
buf[8] = (png_byte)unit_type;
- png_write_chunk(png_ptr, (png_bytep)png_pHYs, buf, (png_size_t)9);
+ png_write_chunk(png_ptr, png_pHYs, buf, (png_size_t)9);
}
#endif
@@ -1717,7 +1718,7 @@ png_write_tIME(png_structp png_ptr, png_timep mod_time)
buf[5] = mod_time->minute;
buf[6] = mod_time->second;
- png_write_chunk(png_ptr, (png_bytep)png_tIME, buf, (png_size_t)7);
+ png_write_chunk(png_ptr, png_tIME, buf, (png_size_t)7);
}
#endif
@@ -1725,6 +1726,7 @@ png_write_tIME(png_structp png_ptr, png_timep mod_time)
void /* PRIVATE */
png_write_start_row(png_structp png_ptr)
{
+#ifdef PNG_WRITE_INTERLACING_SUPPORTED
#ifdef PNG_USE_LOCAL_ARRAYS
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
@@ -1740,6 +1742,7 @@ png_write_start_row(png_structp png_ptr)
/* offset to next interlace block in the y direction */
int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
#endif
+#endif
png_size_t buf_size;
@@ -1751,6 +1754,7 @@ png_write_start_row(png_structp png_ptr)
png_ptr->row_buf = (png_bytep)png_malloc(png_ptr, (png_uint_32)buf_size);
png_ptr->row_buf[0] = PNG_FILTER_VALUE_NONE;
+#ifndef PNG_NO_WRITE_FILTERING
/* set up filtering buffer, if using this filter */
if (png_ptr->do_filter & PNG_FILTER_SUB)
{
@@ -1768,7 +1772,7 @@ png_write_start_row(png_structp png_ptr)
if (png_ptr->do_filter & PNG_FILTER_UP)
{
- png_ptr->up_row = (png_bytep )png_malloc(png_ptr,
+ png_ptr->up_row = (png_bytep)png_malloc(png_ptr,
(png_ptr->rowbytes + 1));
png_ptr->up_row[0] = PNG_FILTER_VALUE_UP;
}
@@ -1782,10 +1786,11 @@ png_write_start_row(png_structp png_ptr)
if (png_ptr->do_filter & PNG_FILTER_PAETH)
{
- png_ptr->paeth_row = (png_bytep )png_malloc(png_ptr,
+ png_ptr->paeth_row = (png_bytep)png_malloc(png_ptr,
(png_ptr->rowbytes + 1));
png_ptr->paeth_row[0] = PNG_FILTER_VALUE_PAETH;
}
+#endif /* PNG_NO_WRITE_FILTERING */
}
#ifdef PNG_WRITE_INTERLACING_SUPPORTED
@@ -1819,6 +1824,7 @@ png_write_start_row(png_structp png_ptr)
void /* PRIVATE */
png_write_finish_row(png_structp png_ptr)
{
+#ifdef PNG_WRITE_INTERLACING_SUPPORTED
#ifdef PNG_USE_LOCAL_ARRAYS
/* arrays to facilitate easy interlacing - use pass (0 - 6) as index */
@@ -1834,6 +1840,7 @@ png_write_finish_row(png_structp png_ptr)
/* offset to next interlace block in the y direction */
int png_pass_yinc[7] = {8, 8, 8, 4, 4, 2, 2};
#endif
+#endif
int ret;
@@ -2107,7 +2114,9 @@ png_do_write_interlace(png_row_infop row_info, png_bytep row, int pass)
void /* PRIVATE */
png_write_find_filter(png_structp png_ptr, png_row_infop row_info)
{
- png_bytep prev_row, best_row, row_buf;
+ png_bytep best_row;
+#ifndef PNG_NO_WRITE_FILTER
+ png_bytep prev_row, row_buf;
png_uint_32 mins, bpp;
png_byte filter_to_do = png_ptr->do_filter;
png_uint_32 row_bytes = row_info->rowbytes;
@@ -2120,7 +2129,10 @@ png_write_find_filter(png_structp png_ptr, png_row_infop row_info)
bpp = (row_info->pixel_depth + 7) >> 3;
prev_row = png_ptr->prev_row;
- best_row = row_buf = png_ptr->row_buf;
+#endif
+ best_row = png_ptr->row_buf;
+#ifndef PNG_NO_WRITE_FILTER
+ row_buf = best_row;
mins = PNG_MAXSUM;
/* The prediction method we use is to find which method provides the
@@ -2695,11 +2707,12 @@ png_write_find_filter(png_structp png_ptr, png_row_infop row_info)
best_row = png_ptr->paeth_row;
}
}
-
+#endif /* PNG_NO_WRITE_FILTER */
/* Do the actual writing of the filtered row data from the chosen filter. */
png_write_filtered_row(png_ptr, best_row);
+#ifndef PNG_NO_WRITE_FILTER
#if defined(PNG_WRITE_WEIGHTED_FILTER_SUPPORTED)
/* Save the type of filter we picked this time for future calculations */
if (png_ptr->num_prev_filters > 0)
@@ -2712,6 +2725,7 @@ png_write_find_filter(png_structp png_ptr, png_row_infop row_info)
png_ptr->prev_filters[j] = best_row[0];
}
#endif
+#endif /* PNG_NO_WRITE_FILTER */
}