mewin/libpng
1
0
Fork 0
mirror of https://git.code.sf.net/p/libpng/code.git synced 2025-07-10 18:04:09 +02:00
Code Issues Projects Releases Wiki Activity

[libpng16] Moved SSE2 optimization code into the main libpng source directory.

Browse Source 
Configure libpng with "configure --enable-intel-see" or compile
libpng with "-DPNG_INTEL_SSE" in CPPFLAGS to enable it.
This commit is contained in:
Glenn Randers-Pehrson
2017-01-03 19:15:15 -06:00
parent 24dfd3f2d7
commit edef058e18
10 changed files with 123 additions and 367 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
pngpriv.h
View File

@@ -190,6 +190,42 @@
# endif
#endif
#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
#if PNG_MIPS_MSA_OPT > 0
# define PNG_FILTER_OPTIMIZATIONS png_init_filter_functions_msa
# ifndef PNG_MIPS_MSA_IMPLEMENTATION
@@ -1256,6 +1292,21 @@ PNG_INTERNAL_FUNCTION(void,png_read_filter_row_paeth4_msa,(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);
@@ -1991,6 +2042,11 @@ PNG_INTERNAL_FUNCTION(void, png_init_filter_functions_neon,
PNG_INTERNAL_FUNCTION(void, png_init_filter_functions_msa,
(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,