chromium/third_party/libaom/source/libaom/aom_dsp/x86/blend_mask_sse4.h

/*
 * Copyright (c) 2018, Alliance for Open Media. All rights reserved.
 *
 * This source code is subject to the terms of the BSD 2 Clause License and
 * the Alliance for Open Media Patent License 1.0. If the BSD 2 Clause License
 * was not distributed with this source code in the LICENSE file, you can
 * obtain it at www.aomedia.org/license/software. If the Alliance for Open
 * Media Patent License 1.0 was not distributed with this source code in the
 * PATENTS file, you can obtain it at www.aomedia.org/license/patent.
 */

#ifndef AOM_AOM_DSP_X86_BLEND_MASK_SSE4_H_
#define AOM_AOM_DSP_X86_BLEND_MASK_SSE4_H_
#include <smmintrin.h>  // SSE4.1

#include <assert.h>

#include "aom/aom_integer.h"
#include "aom_ports/mem.h"
#include "aom_dsp/aom_dsp_common.h"
#include "aom_dsp/blend.h"

#include "aom_dsp/x86/synonyms.h"

#include "config/aom_dsp_rtcd.h"

static inline void blend_a64_d16_mask_w4_sse41(
    uint8_t *dst, const CONV_BUF_TYPE *src0, const CONV_BUF_TYPE *src1,
    const __m128i *m, const __m128i *v_round_offset, const __m128i *v_maxval,
    int shift) { … }

static inline void blend_a64_d16_mask_w8_sse41(
    uint8_t *dst, const CONV_BUF_TYPE *src0, const CONV_BUF_TYPE *src1,
    const __m128i *m, const __m128i *v_round_offset, const __m128i *v_maxval,
    int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw0_subh0_w4_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw0_subh0_w8_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw1_subh1_w4_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw1_subh1_w8_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw1_subh0_w4_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw1_subh0_w8_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }
static inline void aom_lowbd_blend_a64_d16_mask_subw0_subh1_w4_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }

static inline void aom_lowbd_blend_a64_d16_mask_subw0_subh1_w8_sse4_1(
    uint8_t *dst, uint32_t dst_stride, const CONV_BUF_TYPE *src0,
    uint32_t src0_stride, const CONV_BUF_TYPE *src1, uint32_t src1_stride,
    const uint8_t *mask, uint32_t mask_stride, int h,
    const __m128i *round_offset, int shift) { … }
#endif  // AOM_AOM_DSP_X86_BLEND_MASK_SSE4_H_