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] Eliminate PNG_NO_INTEL_SSE_3BPP from intel INSTALL

Browse Source
This commit is contained in:
Glenn Randers-Pehrson
2016-04-05 12:33:17 -05:00
parent f47e1d4995
commit 5765a22249
2 changed files with 7 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
contrib/intel/INSTALL
View File

@@ -1,7 +1,9 @@
Enabling SSE support Enabling SSE support
Copyright (c) 2016 Google, Inc. Copyright (c) 2016 Google, Inc.
Written by Mike Klein and Matt Sarett Written by Mike Klein, Matt Sarett
This INSTALL file written by Glenn Randers-Pehrson, 2016.
If you have moved intel_init.c and filter_sse2_intrinsics.c to a different If you have moved intel_init.c and filter_sse2_intrinsics.c to a different
directory, be sure to update the '#include "../../pngpriv.h"' line in both directory, be sure to update the '#include "../../pngpriv.h"' line in both
@@ -24,26 +26,24 @@ distribution, remove any existing pre-built configure scripts:
make maintainer-clean make maintainer-clean
./autogen.sh --maintainer --clean ./autogen.sh --maintainer --clean
Finally, configure libpng with -DPNG_INTEL_SSE in CPPFLAGS. If you only Finally, configure libpng with -DPNG_INTEL_SSE in CPPFLAGS:
want to optimize reading 4bpp images, also use -DPNG_NO_INTEL_SSE_3BPP:
./autogen.sh --maintainer ./autogen.sh --maintainer
CPPFLAGS="-DPNG_INTEL_SSE -DPNG_NO_INTEL_SSE_3BPP" ./configure [options] CPPFLAGS="-DPNG_INTEL_SSE" ./configure [options]
make make
II. Using a custom makefile: II. Using a custom makefile:
If you are using a custom makefile makefile, you will have to update it If you are using a custom makefile makefile, you will have to update it
manually to include contrib/intel/*.o in the dependencies, and to define manually to include contrib/intel/*.o in the dependencies, and to define
PNG_INTEL_SSE and possibly PNG_NO_INTEL_SSE_3BPP. PNG_INTEL_SSE.
III. Using manually updated "configure" scripts: III. Using manually updated "configure" scripts:
If you prefer, manually edit configure.ac and Makefile.am, following the If you prefer, manually edit configure.ac and Makefile.am, following the
instructions below, then follow the instructions in section II of INSTALL instructions below, then follow the instructions in section II of INSTALL
in the main libpng directory, then configure libpng with -DPNG_INTEL_SSE in the main libpng directory, then configure libpng with -DPNG_INTEL_SSE
in CPPFLAGS. If you only want to optimize reading 4bpp images, also use in CPPFLAGS.
-DPNG_NO_INTEL_SSE_3BPP.
1. Insert the following lines above the copyright line near the top of 1. Insert the following lines above the copyright line near the top of
configure.ac: configure.ac:

8
contrib/intel/filter_sse2_intrinsics.c
View File

@@ -37,7 +37,6 @@ static void store4(void* p, __m128i v) {
*(int*)p = _mm_cvtsi128_si32(v); *(int*)p = _mm_cvtsi128_si32(v);
} }
#ifndef PNG_NO_INTEL_SSE_3BPP
static __m128i load3(const void* p) { static __m128i load3(const void* p) {
/* We'll load 2 bytes, then 1 byte, /* We'll load 2 bytes, then 1 byte,
* then mask them together, and finally load into SSE. * then mask them together, and finally load into SSE.
@@ -62,9 +61,7 @@ static void store3(void* p, __m128i v) {
*p01 = v012; *p01 = v012;
*p2 = v012 >> 16; *p2 = v012 >> 16;
} }
#endif
#ifndef PNG_NO_INTEL_SSE_3BPP
void png_read_filter_row_sub3_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_sub3_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)
{ {
@@ -93,7 +90,6 @@ void png_read_filter_row_sub3_sse2(png_row_infop row_info, png_bytep row,
rb -= 3; rb -= 3;
} }
} }
#endif
void png_read_filter_row_sub4_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_sub4_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)
@@ -116,7 +112,6 @@ void png_read_filter_row_sub4_sse2(png_row_infop row_info, png_bytep row,
} }
} }
#ifndef PNG_NO_INTEL_SSE_3BPP
void png_read_filter_row_avg3_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_avg3_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)
{ {
@@ -165,7 +160,6 @@ void png_read_filter_row_avg3_sse2(png_row_infop row_info, png_bytep row,
rb -= 3; rb -= 3;
} }
} }
#endif
void png_read_filter_row_avg4_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_avg4_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)
@@ -228,7 +222,6 @@ static __m128i if_then_else(__m128i c, __m128i t, __m128i e) {
#endif #endif
} }
#ifndef PNG_NO_INTEL_SSE_3BPP
void png_read_filter_row_paeth3_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_paeth3_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)
{ {
@@ -322,7 +315,6 @@ void png_read_filter_row_paeth3_sse2(png_row_infop row_info, png_bytep row,
rb -= 3; rb -= 3;
} }
} }
#endif
void png_read_filter_row_paeth4_sse2(png_row_infop row_info, png_bytep row, void png_read_filter_row_paeth4_sse2(png_row_infop row_info, png_bytep row,
png_const_bytep prev) png_const_bytep prev)