aom_subpixel_8t_intrin_avx2.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 <immintrin.h>

#include "config/aom_dsp_rtcd.h"

#include "aom_dsp/x86/convolve.h"
#include "aom_dsp/x86/convolve_avx2.h"
#include "aom_dsp/x86/synonyms_avx2.h"
#include "aom_ports/mem.h"

#if defined(__clang__)
#if (__clang_major__ > 0 && __clang_major__ < 3) ||            \
    (__clang_major__ == 3 && __clang_minor__ <= 3) ||          \
    (defined(__APPLE__) && defined(__apple_build_version__) && \
     ((__clang_major__ == 4 && __clang_minor__ <= 2) ||        \
      (__clang_major__ == 5 && __clang_minor__ == 0)))
#define MM256_BROADCASTSI128_SI256 …
#else  // clang > 3.3, and not 5.0 on macosx.
#define MM256_BROADCASTSI128_SI256(x) …
#endif  // clang <= 3.3
#elif defined(__GNUC__)
#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ <= 6)
#define MM256_BROADCASTSI128_SI256 …
#elif __GNUC__ == 4 && __GNUC_MINOR__ == 7
#define MM256_BROADCASTSI128_SI256 …
#else  // gcc > 4.7
#define MM256_BROADCASTSI128_SI256 …
#endif  // gcc <= 4.6
#else   // !(gcc || clang)
#define MM256_BROADCASTSI128_SI256 …
#endif  // __clang__

static inline void xx_storeu2_epi32(const uint8_t *output_ptr,
                                    const ptrdiff_t stride, const __m256i *a) { … }

static inline __m256i xx_loadu2_epi64(const void *hi, const void *lo) { … }

static inline void xx_storeu2_epi64(const uint8_t *output_ptr,
                                    const ptrdiff_t stride, const __m256i *a) { … }

static inline void xx_store2_mi128(const uint8_t *output_ptr,
                                   const ptrdiff_t stride, const __m256i *a) { … }

static void aom_filter_block1d4_h4_avx2(
    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_h8_avx2(
    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_h4_avx2(
    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_h8_avx2(
    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_h4_avx2(
    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_h8_avx2(
    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_avx2(
    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_v8_avx2(
    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_v4_avx2(
    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_v8_avx2(
    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_block1d4_v4_avx2(
    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) { … }

#if HAVE_AVX2 && HAVE_SSSE3
filter8_1dfunction aom_filter_block1d4_v8_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;
#define aom_filter_block1d4_v8_avx2 …
#define aom_filter_block1d16_v2_avx2 …
#define aom_filter_block1d16_h2_avx2 …
#define aom_filter_block1d8_v2_avx2 …
#define aom_filter_block1d8_h2_avx2 …
#define aom_filter_block1d4_v2_avx2 …
#define aom_filter_block1d4_h2_avx2 …
// void aom_convolve8_horiz_avx2(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_avx2(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(…)

#endif  // HAVE_AX2 && HAVE_SSSE3
chromium/third_party/libaom/source/libaom/aom_dsp/x86/aom_subpixel_8t_intrin_avx2.c
