aom_subpixel_8t_intrin_ssse3.c | Explore in Territory

/*
 * Copyright (c) 2016, 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.
 */

#include <tmmintrin.h>

#include "config/aom_dsp_rtcd.h"

#include "aom_dsp/aom_filter.h"
#include "aom_dsp/x86/convolve.h"
#include "aom_dsp/x86/convolve_sse2.h"
#include "aom_dsp/x86/convolve_ssse3.h"
#include "aom_dsp/x86/mem_sse2.h"
#include "aom_dsp/x86/transpose_sse2.h"
#include "aom_mem/aom_mem.h"
#include "aom_ports/mem.h"
#include "aom_ports/emmintrin_compat.h"

DECLARE_ALIGNED(32, static const uint8_t, filt_h4[]) = …;

DECLARE_ALIGNED(32, static const uint8_t, filtd4[]) = …;

static void aom_filter_block1d4_h4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pixels_per_line, uint8_t *output_ptr,
    ptrdiff_t output_pitch, uint32_t output_height, const int16_t *filter) { … }

static void aom_filter_block1d4_v4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pitch, uint8_t *output_ptr,
    ptrdiff_t out_pitch, uint32_t output_height, const int16_t *filter) { … }

static void aom_filter_block1d8_h4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pixels_per_line, uint8_t *output_ptr,
    ptrdiff_t output_pitch, uint32_t output_height, const int16_t *filter) { … }

static void aom_filter_block1d8_v4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pitch, uint8_t *output_ptr,
    ptrdiff_t out_pitch, uint32_t output_height, const int16_t *filter) { … }

static void aom_filter_block1d16_h4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pixels_per_line, uint8_t *output_ptr,
    ptrdiff_t output_pitch, uint32_t output_height, const int16_t *filter) { … }

static void aom_filter_block1d16_v4_ssse3(
    const uint8_t *src_ptr, ptrdiff_t src_pitch, uint8_t *output_ptr,
    ptrdiff_t out_pitch, uint32_t output_height, const int16_t *filter) { … }

static inline __m128i shuffle_filter_convolve8_8_ssse3(
    const __m128i *const s, const int16_t *const filter) { … }

static void filter_horiz_w8_ssse3(const uint8_t *const src,
                                  const ptrdiff_t src_stride,
                                  uint8_t *const dst,
                                  const int16_t *const x_filter) { … }

static void transpose8x8_to_dst(const uint8_t *const src,
                                const ptrdiff_t src_stride, uint8_t *const dst,
                                const ptrdiff_t dst_stride) { … }

static void scaledconvolve_horiz_w8(const uint8_t *src,
                                    const ptrdiff_t src_stride, uint8_t *dst,
                                    const ptrdiff_t dst_stride,
                                    const InterpKernel *const x_filters,
                                    const int x0_q4, const int x_step_q4,
                                    const int w, const int h) { … }

static void filter_horiz_w4_ssse3(const uint8_t *const src,
                                  const ptrdiff_t src_stride,
                                  uint8_t *const dst,
                                  const int16_t *const filter) { … }

static void transpose4x4_to_dst(const uint8_t *const src,
                                const ptrdiff_t src_stride, uint8_t *const dst,
                                const ptrdiff_t dst_stride) { … }

static void scaledconvolve_horiz_w4(const uint8_t *src,
                                    const ptrdiff_t src_stride, uint8_t *dst,
                                    const ptrdiff_t dst_stride,
                                    const InterpKernel *const x_filters,
                                    const int x0_q4, const int x_step_q4,
                                    const int w, const int h) { … }

static __m128i filter_vert_kernel(const __m128i *const s,
                                  const int16_t *const filter) { … }

static void filter_vert_w4_ssse3(const uint8_t *const src,
                                 const ptrdiff_t src_stride, uint8_t *const dst,
                                 const int16_t *const filter) { … }

static void scaledconvolve_vert_w4(
    const uint8_t *src, const ptrdiff_t src_stride, uint8_t *const dst,
    const ptrdiff_t dst_stride, const InterpKernel *const y_filters,
    const int y0_q4, const int y_step_q4, const int w, const int h) { … }

static void filter_vert_w8_ssse3(const uint8_t *const src,
                                 const ptrdiff_t src_stride, uint8_t *const dst,
                                 const int16_t *const filter) { … }

static void scaledconvolve_vert_w8(
    const uint8_t *src, const ptrdiff_t src_stride, uint8_t *const dst,
    const ptrdiff_t dst_stride, const InterpKernel *const y_filters,
    const int y0_q4, const int y_step_q4, const int w, const int h) { … }

static void filter_vert_w16_ssse3(const uint8_t *src,
                                  const ptrdiff_t src_stride,
                                  uint8_t *const dst,
                                  const int16_t *const filter, const int w) { … }

static void scaledconvolve_vert_w16(
    const uint8_t *src, const ptrdiff_t src_stride, uint8_t *const dst,
    const ptrdiff_t dst_stride, const InterpKernel *const y_filters,
    const int y0_q4, const int y_step_q4, const int w, const int h) { … }

void aom_scaled_2d_ssse3(const uint8_t *src, ptrdiff_t src_stride, uint8_t *dst,
                         ptrdiff_t dst_stride, const InterpKernel *filter,
                         int x0_q4, int x_step_q4, int y0_q4, int y_step_q4,
                         int w, int h) { … }

filter8_1dfunction aom_filter_block1d16_v8_ssse3;
filter8_1dfunction aom_filter_block1d16_h8_ssse3;
filter8_1dfunction aom_filter_block1d8_v8_ssse3;
filter8_1dfunction aom_filter_block1d8_h8_ssse3;
filter8_1dfunction aom_filter_block1d4_v8_ssse3;
filter8_1dfunction aom_filter_block1d4_h8_ssse3;

filter8_1dfunction aom_filter_block1d16_v2_ssse3;
filter8_1dfunction aom_filter_block1d16_h2_ssse3;
filter8_1dfunction aom_filter_block1d8_v2_ssse3;
filter8_1dfunction aom_filter_block1d8_h2_ssse3;
filter8_1dfunction aom_filter_block1d4_v2_ssse3;
filter8_1dfunction aom_filter_block1d4_h2_ssse3;

// void aom_convolve8_horiz_ssse3(const uint8_t *src, ptrdiff_t src_stride,
//                                uint8_t *dst, ptrdiff_t dst_stride,
//                                const int16_t *filter_x, int x_step_q4,
//                                const int16_t *filter_y, int y_step_q4,
//                                int w, int h);
// void aom_convolve8_vert_ssse3(const uint8_t *src, ptrdiff_t src_stride,
//                               uint8_t *dst, ptrdiff_t dst_stride,
//                               const int16_t *filter_x, int x_step_q4,
//                               const int16_t *filter_y, int y_step_q4,
//                               int w, int h);
FUN_CONV_1D(…)
FUN_CONV_1D(…)
chromium/third_party/libaom/source/libaom/aom_dsp/x86/aom_subpixel_8t_intrin_ssse3.c
