godot/thirdparty/libpng/intel/filter_sse2_intrinsics.c

/* filter_sse2_intrinsics.c - SSE2 optimized filter functions
 *
 * Copyright (c) 2018 Cosmin Truta
 * Copyright (c) 2016-2017 Glenn Randers-Pehrson
 * Written by Mike Klein and Matt Sarett
 * Derived from arm/filter_neon_intrinsics.c
 *
 * This code is released under the libpng license.
 * For conditions of distribution and use, see the disclaimer
 * and license in png.h
 */

#include "../pngpriv.h"

#ifdef PNG_READ_SUPPORTED

#if PNG_INTEL_SSE_IMPLEMENTATION > 0

#include <immintrin.h>

/* Functions in this file look at most 3 pixels (a,b,c) to predict the 4th (d).
 * They're positioned like this:
 *    prev:  c b
 *    row:   a d
 * The Sub filter predicts d=a, Avg d=(a+b)/2, and Paeth predicts d to be
 * whichever of a, b, or c is closest to p=a+b-c.
 */

static __m128i load4(const void* p) { … }

static void store4(void* p, __m128i v) { … }

static __m128i load3(const void* p) { … }

static void store3(void* p, __m128i v) { … }

void png_read_filter_row_sub3_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

void png_read_filter_row_sub4_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

void png_read_filter_row_avg3_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

void png_read_filter_row_avg4_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

/* Returns |x| for 16-bit lanes. */
static __m128i abs_i16(__m128i x) { … }

/* Bytewise c ? t : e. */
static __m128i if_then_else(__m128i c, __m128i t, __m128i e) { … }

void png_read_filter_row_paeth3_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

void png_read_filter_row_paeth4_sse2(png_row_infop row_info, png_bytep row,
   png_const_bytep prev)
{ … }

#endif /* PNG_INTEL_SSE_IMPLEMENTATION > 0 */
#endif /* READ */