contrib/intel/intel_sse.patch

diff --git a/configure.ac b/configure.ac
--- a/configure.ac	2016-05-25 18:59:10.000000000 -0400
+++ b/configure.ac	2016-05-25 19:48:10.631751170 -0400
@@ -341,16 +341,50 @@ AC_ARG_ENABLE([arm-neon],
 
 AM_CONDITIONAL([PNG_ARM_NEON],
    [test "$enable_arm_neon" != 'no' &&
     case "$host_cpu" in
       arm*|aarch64*) :;;
       *)    test "$enable_arm_neon" != '';;
     esac])
 
+# INTEL
+# =====
+#
+# INTEL SSE (SIMD) support.
+
+AC_ARG_ENABLE([intel-sse],
+   AS_HELP_STRING([[[--enable-intel-sse]]],
+      [Enable Intel SSE optimizations: =no/off, yes/on:]
+      [no/off: disable the optimizations;]
+      [yes/on: enable the optimizations.]
+      [If not specified: determined by the compiler.]),
+   [case "$enableval" in
+      no|off)
+         # disable the default enabling:
+         AC_DEFINE([PNG_INTEL_SSE_OPT], [0],
+                   [Disable Intel SSE optimizations])
+         # Prevent inclusion of the assembler files below:
+         enable_intel_sse=no;;
+      yes|on)
+         AC_DEFINE([PNG_INTEL_SSE_OPT], [1],
+                   [Enable Intel SSE optimizations]);;
+      *)
+         AC_MSG_ERROR([--enable-intel-sse=${enable_intel_sse}: invalid value])
+   esac])
+
+# Add Intel specific files to all builds where the host_cpu is Intel ('x86*')
+# or where Intel optimizations were explicitly requested (this allows a
+# fallback if a future host CPU does not match 'x86*')
+AM_CONDITIONAL([PNG_INTEL_SSE],
+   [test "$enable_intel_sse" != 'no' &&
+    case "$host_cpu" in
+      i?86|x86_64) :;;
+      *)    test "$enable_intel_sse" != '';;
+    esac])
 AC_MSG_NOTICE([[Extra options for compiler: $PNG_COPTS]])
 
 # Config files, substituting as above
 AC_CONFIG_FILES([Makefile libpng.pc:libpng.pc.in])
 AC_CONFIG_FILES([libpng-config:libpng-config.in],
    [chmod +x libpng-config])
 
 AC_OUTPUT
diff --git a/Makefile.am b/Makefile.am
--- a/Makefile.am	2016-05-17 18:15:12.000000000 -0400
+++ b/Makefile.am	2016-05-25 19:48:10.631751170 -0400
@@ -92,16 +92,20 @@ libpng@PNGLIB_MAJOR@@PNGLIB_MINOR@_la_SO
 	pngset.c pngtrans.c pngwio.c pngwrite.c pngwtran.c pngwutil.c\
 	png.h pngconf.h pngdebug.h pnginfo.h pngpriv.h pngstruct.h pngusr.dfa
 
 if PNG_ARM_NEON
 libpng@PNGLIB_MAJOR@@PNGLIB_MINOR@_la_SOURCES += arm/arm_init.c\
 	arm/filter_neon.S arm/filter_neon_intrinsics.c
 endif
 
+if PNG_INTEL_SSE
+libpng@PNGLIB_MAJOR@@PNGLIB_MINOR@_la_SOURCES += contrib/intel/intel_init.c\
+    contrib/intel/filter_sse2_intrinsics.c
+endif
 nodist_libpng@PNGLIB_MAJOR@@PNGLIB_MINOR@_la_SOURCES = pnglibconf.h
 
 libpng@PNGLIB_MAJOR@@PNGLIB_MINOR@_la_LDFLAGS = -no-undefined -export-dynamic \
 	-version-number @PNGLIB_MAJOR@@PNGLIB_MINOR@:@PNGLIB_RELEASE@:0
 
 if HAVE_LD_VERSION_SCRIPT
 #   Versioned symbols and restricted exports
 if HAVE_SOLARIS_LD
diff --git a/pngpriv.h b/pngpriv.h
--- a/pngpriv.h	2016-08-01 18:13:38.770128810 -0500
+++ b/pngpriv.h	2016-08-01 18:50:19.130179017 -0500
@@ -177,16 +177,52 @@
 #  endif /* !PNG_ARM_NEON_IMPLEMENTATION */
 
 #  ifndef PNG_ARM_NEON_IMPLEMENTATION
       /* Use the intrinsics code by default. */
 #     define PNG_ARM_NEON_IMPLEMENTATION 1
 #  endif
 #endif /* PNG_ARM_NEON_OPT > 0 */
 
+#ifndef PNG_INTEL_SSE_OPT
+#   ifdef PNG_INTEL_SSE
+      /* Only check for SSE if the build configuration has been modified to
+       * enable SSE optimizations.  This means that these optimizations will
+       * be off by default.  See contrib/intel for more details.
+       */
+#     if defined(__SSE4_1__) || defined(__AVX__) || defined(__SSSE3__) || \
+       defined(__SSE2__) || defined(_M_X64) || defined(_M_AMD64) || \
+       (defined(_M_IX86_FP) && _M_IX86_FP >= 2)
+#         define PNG_INTEL_SSE_OPT 1
+#      endif
+#   endif
+#endif
+
+#if PNG_INTEL_SSE_OPT > 0
+#   ifndef PNG_INTEL_SSE_IMPLEMENTATION
+#      if defined(__SSE4_1__) || defined(__AVX__)
+          /* We are not actually using AVX, but checking for AVX is the best
+             way we can detect SSE4.1 and SSSE3 on MSVC.
+          */
+#         define PNG_INTEL_SSE_IMPLEMENTATION 3
+#      elif defined(__SSSE3__)
+#         define PNG_INTEL_SSE_IMPLEMENTATION 2
+#      elif defined(__SSE2__) || defined(_M_X64) || defined(_M_AMD64) || \
+       (defined(_M_IX86_FP) && _M_IX86_FP >= 2)
+#         define PNG_INTEL_SSE_IMPLEMENTATION 1
+#      else
+#         define PNG_INTEL_SSE_IMPLEMENTATION 0
+#      endif
+#   endif
+
+#   if PNG_INTEL_SSE_IMPLEMENTATION > 0
+#      define PNG_FILTER_OPTIMIZATIONS png_init_filter_functions_sse2
+#   endif
+#endif
+
 /* Is this a build of a DLL where compilation of the object modules requires
  * different preprocessor settings to those required for a simple library?  If
  * so PNG_BUILD_DLL must be set.
  *
  * If libpng is used inside a DLL but that DLL does not export the libpng APIs
  * PNG_BUILD_DLL must not be set.  To avoid the code below kicking in build a
  * static library of libpng then link the DLL against that.
  */
@@ -1185,16 +1221,31 @@ PNG_INTERNAL_FUNCTION(void,png_read_filt
     row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
 PNG_INTERNAL_FUNCTION(void,png_read_filter_row_avg4_neon,(png_row_infop
     row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
 PNG_INTERNAL_FUNCTION(void,png_read_filter_row_paeth3_neon,(png_row_infop
     row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
 PNG_INTERNAL_FUNCTION(void,png_read_filter_row_paeth4_neon,(png_row_infop
     row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
 #endif
+ 
+#if PNG_INTEL_SSE_IMPLEMENTATION > 0
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_sub3_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_sub4_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_avg3_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_avg4_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_paeth3_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+PNG_INTERNAL_FUNCTION(void,png_read_filter_row_paeth4_sse2,(png_row_infop
+    row_info, png_bytep row, png_const_bytep prev_row),PNG_EMPTY);
+#endif
 
 /* Choose the best filter to use and filter the row data */
 PNG_INTERNAL_FUNCTION(void,png_write_find_filter,(png_structrp png_ptr,
     png_row_infop row_info),PNG_EMPTY);
 
 #ifdef PNG_SEQUENTIAL_READ_SUPPORTED
 PNG_INTERNAL_FUNCTION(void,png_read_IDAT_data,(png_structrp png_ptr,
    png_bytep output, png_alloc_size_t avail_out),PNG_EMPTY);
@@ -1914,16 +1965,20 @@ PNG_INTERNAL_FUNCTION(void, PNG_FILTER_O
    /* List *all* the possible optimizations here - this branch is required if
     * the builder of libpng passes the definition of PNG_FILTER_OPTIMIZATIONS in
     * CFLAGS in place of CPPFLAGS *and* uses symbol prefixing.
     */
 #  if PNG_ARM_NEON_OPT > 0
 PNG_INTERNAL_FUNCTION(void, png_init_filter_functions_neon,
    (png_structp png_ptr, unsigned int bpp), PNG_EMPTY);
 #  endif
+#  if PNG_INTEL_SSE_IMPLEMENTATION > 0
+PNG_INTERNAL_FUNCTION(void, png_init_filter_functions_sse2,
+   (png_structp png_ptr, unsigned int bpp), PNG_EMPTY);
+#  endif
 #endif
 
 PNG_INTERNAL_FUNCTION(png_uint_32, png_check_keyword, (png_structrp png_ptr,
    png_const_charp key, png_bytep new_key), PNG_EMPTY);
 
 /* Maintainer: Put new private prototypes here ^ */
 
 #include "pngdebug.h"