/*

 * 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.

 */

#include <emmintrin.h>

#include <immintrin.h>

#include "config/av1_rtcd.h"

#include "aom_dsp/aom_dsp_common.h"

#include "aom_dsp/aom_filter.h"

#include "aom_dsp/x86/convolve_avx2.h"

#include "aom_dsp/x86/convolve_common_intrin.h"

#include "aom_dsp/x86/convolve_sse4_1.h"

#include "aom_dsp/x86/mem_sse2.h"

#include "aom_dsp/x86/synonyms_avx2.h"

#include "av1/common/convolve.h"

static inline __m256i unpack_weights_avx2(ConvolveParams *conv_params) {

  const int w0 = conv_params->fwd_offset;

  const int w1 = conv_params->bck_offset;

  const __m256i wt0 = _mm256_set1_epi16((int16_t)w0);

  const __m256i wt1 = _mm256_set1_epi16((int16_t)w1);

  const __m256i wt = _mm256_unpacklo_epi16(wt0, wt1);

  return wt;

}

static inline __m256i load_line2_avx2(const void *a, const void *b) {

  return _mm256_permute2x128_si256(

      _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)a)),

      _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)b)), 0x20);

}

void av1_dist_wtd_convolve_x_avx2(const uint8_t *src, int src_stride,

                                  uint8_t *dst0, int dst_stride0, int w, int h,

                                  const InterpFilterParams *filter_params_x,

                                  const int subpel_x_qn,

                                  ConvolveParams *conv_params) {

  CONV_BUF_TYPE *dst = conv_params->dst;

  int dst_stride = conv_params->dst_stride;

  const int bd = 8;

  int i, j, is_horiz_4tap = 0;

  const int bits = FILTER_BITS - conv_params->round_1;

  const __m256i wt = unpack_weights_avx2(conv_params);

  const int do_average = conv_params->do_average;

  const int use_dist_wtd_comp_avg = conv_params->use_dist_wtd_comp_avg;

  const int offset_0 =

      bd + 2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

  const int offset = (1 << offset_0) + (1 << (offset_0 - 1));

  const __m256i offset_const = _mm256_set1_epi16(offset);

  const int rounding_shift =

      2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

  const __m256i rounding_const = _mm256_set1_epi16((1 << rounding_shift) >> 1);

  assert(bits >= 0);

  assert(conv_params->round_0 > 0);

  const __m256i round_const =

      _mm256_set1_epi16((1 << (conv_params->round_0 - 1)) >> 1);

  const __m128i round_shift = _mm_cvtsi32_si128(conv_params->round_0 - 1);

  __m256i filt[4], coeffs[4];

  filt[0] = _mm256_load_si256((__m256i const *)filt_global_avx2);

  filt[1] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32));

  prepare_coeffs_lowbd(filter_params_x, subpel_x_qn, coeffs);

  // Condition for checking valid horz_filt taps

  if (!(_mm256_extract_epi32(_mm256_or_si256(coeffs[0], coeffs[3]), 0)))

    is_horiz_4tap = 1;

  // horz_filt as 4 tap

  if (is_horiz_4tap) {

    const int fo_horiz = 1;

    const uint8_t *const src_ptr = src - fo_horiz;

    for (i = 0; i < h; i += 2) {

      const uint8_t *src_data = src_ptr + i * src_stride;

      CONV_BUF_TYPE *dst_data = dst + i * dst_stride;

      for (j = 0; j < w; j += 8) {

        const __m256i data =

            load_line2_avx2(&src_data[j], &src_data[j + src_stride]);

        __m256i res = convolve_lowbd_x_4tap(data, coeffs + 1, filt);

        res = _mm256_sra_epi16(_mm256_add_epi16(res, round_const), round_shift);

        res = _mm256_slli_epi16(res, bits);

        const __m256i res_unsigned = _mm256_add_epi16(res, offset_const);

        // Accumulate values into the destination buffer

        if (do_average) {

          const __m256i data_ref_0 =

              load_line2_avx2(&dst_data[j], &dst_data[j + dst_stride]);

          const __m256i comp_avg_res =

              comp_avg(&data_ref_0, &res_unsigned, &wt, use_dist_wtd_comp_avg);

          const __m256i round_result = convolve_rounding(

              &comp_avg_res, &offset_const, &rounding_const, rounding_shift);

          const __m256i res_8 = _mm256_packus_epi16(round_result, round_result);

          const __m128i res_0 = _mm256_castsi256_si128(res_8);

          const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

          if (w > 4) {

            _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

            _mm_storel_epi64(

                (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1);

          } else {

            *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);

            *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =

                _mm_cvtsi128_si32(res_1);

          }

        } else {

          const __m128i res_0 = _mm256_castsi256_si128(res_unsigned);

          _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_0);

          const __m128i res_1 = _mm256_extracti128_si256(res_unsigned, 1);

          _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                          res_1);

        }

      }

    }

  } else {

    const int fo_horiz = filter_params_x->taps / 2 - 1;

    const uint8_t *const src_ptr = src - fo_horiz;

    filt[2] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 2));

    filt[3] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 3));

    for (i = 0; i < h; i += 2) {

      const uint8_t *src_data = src_ptr + i * src_stride;

      CONV_BUF_TYPE *dst_data = dst + i * dst_stride;

      for (j = 0; j < w; j += 8) {

        const __m256i data =

            load_line2_avx2(&src_data[j], &src_data[j + src_stride]);

        __m256i res = convolve_lowbd_x(data, coeffs, filt);

        res = _mm256_sra_epi16(_mm256_add_epi16(res, round_const), round_shift);

        res = _mm256_slli_epi16(res, bits);

        const __m256i res_unsigned = _mm256_add_epi16(res, offset_const);

        // Accumulate values into the destination buffer

        if (do_average) {

          const __m256i data_ref_0 =

              load_line2_avx2(&dst_data[j], &dst_data[j + dst_stride]);

          const __m256i comp_avg_res =

              comp_avg(&data_ref_0, &res_unsigned, &wt, use_dist_wtd_comp_avg);

          const __m256i round_result = convolve_rounding(

              &comp_avg_res, &offset_const, &rounding_const, rounding_shift);

          const __m256i res_8 = _mm256_packus_epi16(round_result, round_result);

          const __m128i res_0 = _mm256_castsi256_si128(res_8);

          const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

          if (w > 4) {

            _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

            _mm_storel_epi64(

                (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1);

          } else {

            *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);

            *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =

                _mm_cvtsi128_si32(res_1);

          }

        } else {

          const __m128i res_0 = _mm256_castsi256_si128(res_unsigned);

          _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_0);

          const __m128i res_1 = _mm256_extracti128_si256(res_unsigned, 1);

          _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                          res_1);

        }

      }

    }

  }

}

void av1_dist_wtd_convolve_y_avx2(const uint8_t *src, int src_stride,

                                  uint8_t *dst0, int dst_stride0, int w, int h,

                                  const InterpFilterParams *filter_params_y,

                                  const int subpel_y_qn,

                                  ConvolveParams *conv_params) {

  CONV_BUF_TYPE *dst = conv_params->dst;

  int dst_stride = conv_params->dst_stride;

  const int bd = 8;

  int i, j, is_vert_4tap = 0;

  // +1 to compensate for dividing the filter coeffs by 2

  const int left_shift = FILTER_BITS - conv_params->round_0 + 1;

  const __m256i round_const =

      _mm256_set1_epi32((1 << conv_params->round_1) >> 1);

  const __m128i round_shift = _mm_cvtsi32_si128(conv_params->round_1);

  const __m256i wt = unpack_weights_avx2(conv_params);

  const int do_average = conv_params->do_average;

  const int use_dist_wtd_comp_avg = conv_params->use_dist_wtd_comp_avg;

  const int offset_0 =

      bd + 2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

  const int offset = (1 << offset_0) + (1 << (offset_0 - 1));

  const __m256i offset_const = _mm256_set1_epi16(offset);

  const int offset_1 = (1 << (bd + FILTER_BITS - 2));

  const __m256i offset_const_1 = _mm256_set1_epi16(offset_1);

  const __m256i offset_const_2 = _mm256_set1_epi16((1 << offset_0));

  const int rounding_shift =

      2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

  const __m256i rounding_const = _mm256_set1_epi16((1 << rounding_shift) >> 1);

  const __m256i zero = _mm256_setzero_si256();

  __m256i coeffs[4], s[8];

  assert((FILTER_BITS - conv_params->round_0) >= 0);

  prepare_coeffs_lowbd(filter_params_y, subpel_y_qn, coeffs);

  // Condition for checking valid vert_filt taps

  if (!(_mm256_extract_epi32(_mm256_or_si256(coeffs[0], coeffs[3]), 0)))

    is_vert_4tap = 1;

  if (is_vert_4tap) {

    const int fo_vert = 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride;

    for (j = 0; j < w; j += 16) {

      const uint8_t *data = &src_ptr[j];

      __m256i src4;

      // Load lines a and b. Line a to lower 128, line b to upper 128

      {

        __m256i src_ab[4];

        __m256i src_a[5];

        src_a[0] = _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

        for (int kk = 0; kk < 4; ++kk) {

          data += src_stride;

          src_a[kk + 1] =

              _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

          src_ab[kk] =

              _mm256_permute2x128_si256(src_a[kk], src_a[kk + 1], 0x20);

        }

        src4 = src_a[4];

        s[0] = _mm256_unpacklo_epi8(src_ab[0], src_ab[1]);

        s[1] = _mm256_unpacklo_epi8(src_ab[2], src_ab[3]);

        s[3] = _mm256_unpackhi_epi8(src_ab[0], src_ab[1]);

        s[4] = _mm256_unpackhi_epi8(src_ab[2], src_ab[3]);

      }

      for (i = 0; i < h; i += 2) {

        data = &src_ptr[(i + 5) * src_stride + j];

        const __m256i src5 =

            _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

        const __m256i src_45a = _mm256_permute2x128_si256(src4, src5, 0x20);

        src4 = _mm256_castsi128_si256(

            _mm_loadu_si128((__m128i *)(data + src_stride)));

        const __m256i src_56a = _mm256_permute2x128_si256(src5, src4, 0x20);

        s[2] = _mm256_unpacklo_epi8(src_45a, src_56a);

        s[5] = _mm256_unpackhi_epi8(src_45a, src_56a);

        __m256i res_lo = convolve_lowbd_4tap(s, coeffs + 1);

        res_lo = _mm256_add_epi16(res_lo, offset_const_1);

        const __m256i res_lo_0_32b = _mm256_unpacklo_epi16(res_lo, zero);

        const __m256i res_lo_0_shift =

            _mm256_slli_epi32(res_lo_0_32b, left_shift);

        const __m256i res_lo_0_round = _mm256_sra_epi32(

            _mm256_add_epi32(res_lo_0_shift, round_const), round_shift);

        const __m256i res_lo_1_32b = _mm256_unpackhi_epi16(res_lo, zero);

        const __m256i res_lo_1_shift =

            _mm256_slli_epi32(res_lo_1_32b, left_shift);

        const __m256i res_lo_1_round = _mm256_sra_epi32(

            _mm256_add_epi32(res_lo_1_shift, round_const), round_shift);

        const __m256i res_lo_round =

            _mm256_packs_epi32(res_lo_0_round, res_lo_1_round);

        const __m256i res_lo_unsigned =

            _mm256_add_epi16(res_lo_round, offset_const_2);

        if (w - j < 16) {

          if (do_average) {

            const __m256i data_ref_0 =

                load_line2_avx2(&dst[i * dst_stride + j],

                                &dst[i * dst_stride + j + dst_stride]);

            const __m256i comp_avg_res = comp_avg(&data_ref_0, &res_lo_unsigned,

                                                  &wt, use_dist_wtd_comp_avg);

            const __m256i round_result = convolve_rounding(

                &comp_avg_res, &offset_const, &rounding_const, rounding_shift);

            const __m256i res_8 =

                _mm256_packus_epi16(round_result, round_result);

            const __m128i res_0 = _mm256_castsi256_si128(res_8);

            const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

            if (w - j > 4) {

              _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

              _mm_storel_epi64(

                  (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])),

                  res_1);

            } else {

              *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);

              *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =

                  _mm_cvtsi128_si32(res_1);

            }

          } else {

            const __m128i res_0 = _mm256_castsi256_si128(res_lo_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_0);

            const __m128i res_1 = _mm256_extracti128_si256(res_lo_unsigned, 1);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                            res_1);

          }

        } else {

          __m256i res_hi = convolve_lowbd_4tap(s + 3, coeffs + 1);

          res_hi = _mm256_add_epi16(res_hi, offset_const_1);

          const __m256i res_hi_0_32b = _mm256_unpacklo_epi16(res_hi, zero);

          const __m256i res_hi_0_shift =

              _mm256_slli_epi32(res_hi_0_32b, left_shift);

          const __m256i res_hi_0_round = _mm256_sra_epi32(

              _mm256_add_epi32(res_hi_0_shift, round_const), round_shift);

          const __m256i res_hi_1_32b = _mm256_unpackhi_epi16(res_hi, zero);

          const __m256i res_hi_1_shift =

              _mm256_slli_epi32(res_hi_1_32b, left_shift);

          const __m256i res_hi_1_round = _mm256_sra_epi32(

              _mm256_add_epi32(res_hi_1_shift, round_const), round_shift);

          const __m256i res_hi_round =

              _mm256_packs_epi32(res_hi_0_round, res_hi_1_round);

          const __m256i res_hi_unsigned =

              _mm256_add_epi16(res_hi_round, offset_const_2);

          if (do_average) {

            const __m256i data_ref_0_lo =

                load_line2_avx2(&dst[i * dst_stride + j],

                                &dst[i * dst_stride + j + dst_stride]);

            const __m256i data_ref_0_hi =

                load_line2_avx2(&dst[i * dst_stride + j + 8],

                                &dst[i * dst_stride + j + 8 + dst_stride]);

            const __m256i comp_avg_res_lo = comp_avg(

                &data_ref_0_lo, &res_lo_unsigned, &wt, use_dist_wtd_comp_avg);

            const __m256i comp_avg_res_hi = comp_avg(

                &data_ref_0_hi, &res_hi_unsigned, &wt, use_dist_wtd_comp_avg);

            const __m256i round_result_lo =

                convolve_rounding(&comp_avg_res_lo, &offset_const,

                                  &rounding_const, rounding_shift);

            const __m256i round_result_hi =

                convolve_rounding(&comp_avg_res_hi, &offset_const,

                                  &rounding_const, rounding_shift);

            const __m256i res_8 =

                _mm256_packus_epi16(round_result_lo, round_result_hi);

            const __m128i res_0 = _mm256_castsi256_si128(res_8);

            const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

            _mm_store_si128((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

            _mm_store_si128(

                (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1);

          } else {

            const __m128i res_lo_0 = _mm256_castsi256_si128(res_lo_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_lo_0);

            const __m128i res_lo_1 =

                _mm256_extracti128_si256(res_lo_unsigned, 1);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                            res_lo_1);

            const __m128i res_hi_0 = _mm256_castsi256_si128(res_hi_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + 8]),

                            res_hi_0);

            const __m128i res_hi_1 =

                _mm256_extracti128_si256(res_hi_unsigned, 1);

            _mm_store_si128(

                (__m128i *)(&dst[i * dst_stride + j + 8 + dst_stride]),

                res_hi_1);

          }

        }

        s[0] = s[1];

        s[1] = s[2];

        s[3] = s[4];

        s[4] = s[5];

      }

    }

  } else {

    const int fo_vert = filter_params_y->taps / 2 - 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride;

    for (j = 0; j < w; j += 16) {

      const uint8_t *data = &src_ptr[j];

      __m256i src6;

      // Load lines a and b. Line a to lower 128, line b to upper 128

      {

        __m256i src_ab[7];

        __m256i src_a[7];

        src_a[0] = _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

        for (int kk = 0; kk < 6; ++kk) {

          data += src_stride;

          src_a[kk + 1] =

              _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

          src_ab[kk] =

              _mm256_permute2x128_si256(src_a[kk], src_a[kk + 1], 0x20);

        }

        src6 = src_a[6];

        s[0] = _mm256_unpacklo_epi8(src_ab[0], src_ab[1]);

        s[1] = _mm256_unpacklo_epi8(src_ab[2], src_ab[3]);

        s[2] = _mm256_unpacklo_epi8(src_ab[4], src_ab[5]);

        s[4] = _mm256_unpackhi_epi8(src_ab[0], src_ab[1]);

        s[5] = _mm256_unpackhi_epi8(src_ab[2], src_ab[3]);

        s[6] = _mm256_unpackhi_epi8(src_ab[4], src_ab[5]);

      }

      for (i = 0; i < h; i += 2) {

        data = &src_ptr[(i + 7) * src_stride + j];

        const __m256i src7 =

            _mm256_castsi128_si256(_mm_loadu_si128((__m128i *)data));

        const __m256i src_67a = _mm256_permute2x128_si256(src6, src7, 0x20);

        src6 = _mm256_castsi128_si256(

            _mm_loadu_si128((__m128i *)(data + src_stride)));

        const __m256i src_78a = _mm256_permute2x128_si256(src7, src6, 0x20);

        s[3] = _mm256_unpacklo_epi8(src_67a, src_78a);

        s[7] = _mm256_unpackhi_epi8(src_67a, src_78a);

        __m256i res_lo = convolve_lowbd(s, coeffs);

        res_lo = _mm256_add_epi16(res_lo, offset_const_1);

        const __m256i res_lo_0_32b = _mm256_unpacklo_epi16(res_lo, zero);

        const __m256i res_lo_0_shift =

            _mm256_slli_epi32(res_lo_0_32b, left_shift);

        const __m256i res_lo_0_round = _mm256_sra_epi32(

            _mm256_add_epi32(res_lo_0_shift, round_const), round_shift);

        const __m256i res_lo_1_32b = _mm256_unpackhi_epi16(res_lo, zero);

        const __m256i res_lo_1_shift =

            _mm256_slli_epi32(res_lo_1_32b, left_shift);

        const __m256i res_lo_1_round = _mm256_sra_epi32(

            _mm256_add_epi32(res_lo_1_shift, round_const), round_shift);

        const __m256i res_lo_round =

            _mm256_packs_epi32(res_lo_0_round, res_lo_1_round);

        const __m256i res_lo_unsigned =

            _mm256_add_epi16(res_lo_round, offset_const_2);

        if (w - j < 16) {

          if (do_average) {

            const __m256i data_ref_0 =

                load_line2_avx2(&dst[i * dst_stride + j],

                                &dst[i * dst_stride + j + dst_stride]);

            const __m256i comp_avg_res = comp_avg(&data_ref_0, &res_lo_unsigned,

                                                  &wt, use_dist_wtd_comp_avg);

            const __m256i round_result = convolve_rounding(

                &comp_avg_res, &offset_const, &rounding_const, rounding_shift);

            const __m256i res_8 =

                _mm256_packus_epi16(round_result, round_result);

            const __m128i res_0 = _mm256_castsi256_si128(res_8);

            const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

            if (w - j > 4) {

              _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

              _mm_storel_epi64(

                  (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])),

                  res_1);

            } else {

              *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);

              *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =

                  _mm_cvtsi128_si32(res_1);

            }

          } else {

            const __m128i res_0 = _mm256_castsi256_si128(res_lo_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_0);

            const __m128i res_1 = _mm256_extracti128_si256(res_lo_unsigned, 1);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                            res_1);

          }

        } else {

          __m256i res_hi = convolve_lowbd(s + 4, coeffs);

          res_hi = _mm256_add_epi16(res_hi, offset_const_1);

          const __m256i res_hi_0_32b = _mm256_unpacklo_epi16(res_hi, zero);

          const __m256i res_hi_0_shift =

              _mm256_slli_epi32(res_hi_0_32b, left_shift);

          const __m256i res_hi_0_round = _mm256_sra_epi32(

              _mm256_add_epi32(res_hi_0_shift, round_const), round_shift);

          const __m256i res_hi_1_32b = _mm256_unpackhi_epi16(res_hi, zero);

          const __m256i res_hi_1_shift =

              _mm256_slli_epi32(res_hi_1_32b, left_shift);

          const __m256i res_hi_1_round = _mm256_sra_epi32(

              _mm256_add_epi32(res_hi_1_shift, round_const), round_shift);

          const __m256i res_hi_round =

              _mm256_packs_epi32(res_hi_0_round, res_hi_1_round);

          const __m256i res_hi_unsigned =

              _mm256_add_epi16(res_hi_round, offset_const_2);

          if (do_average) {

            const __m256i data_ref_0_lo =

                load_line2_avx2(&dst[i * dst_stride + j],

                                &dst[i * dst_stride + j + dst_stride]);

            const __m256i data_ref_0_hi =

                load_line2_avx2(&dst[i * dst_stride + j + 8],

                                &dst[i * dst_stride + j + 8 + dst_stride]);

            const __m256i comp_avg_res_lo = comp_avg(

                &data_ref_0_lo, &res_lo_unsigned, &wt, use_dist_wtd_comp_avg);

            const __m256i comp_avg_res_hi = comp_avg(

                &data_ref_0_hi, &res_hi_unsigned, &wt, use_dist_wtd_comp_avg);

            const __m256i round_result_lo =

                convolve_rounding(&comp_avg_res_lo, &offset_const,

                                  &rounding_const, rounding_shift);

            const __m256i round_result_hi =

                convolve_rounding(&comp_avg_res_hi, &offset_const,

                                  &rounding_const, rounding_shift);

            const __m256i res_8 =

                _mm256_packus_epi16(round_result_lo, round_result_hi);

            const __m128i res_0 = _mm256_castsi256_si128(res_8);

            const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);

            _mm_store_si128((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);

            _mm_store_si128(

                (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1);

          } else {

            const __m128i res_lo_0 = _mm256_castsi256_si128(res_lo_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_lo_0);

            const __m128i res_lo_1 =

                _mm256_extracti128_si256(res_lo_unsigned, 1);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),

                            res_lo_1);

            const __m128i res_hi_0 = _mm256_castsi256_si128(res_hi_unsigned);

            _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + 8]),

                            res_hi_0);

            const __m128i res_hi_1 =

                _mm256_extracti128_si256(res_hi_unsigned, 1);

            _mm_store_si128(

                (__m128i *)(&dst[i * dst_stride + j + 8 + dst_stride]),

                res_hi_1);

          }

        }

        s[0] = s[1];

        s[1] = s[2];

        s[2] = s[3];

        s[4] = s[5];

        s[5] = s[6];

        s[6] = s[7];

      }

    }

  }

}

#define JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(last_4, mode)                     \

  do {                                                                         \

    __m256i s0_reg =                                                           \

        _mm256_loadu_si256((__m256i *)(im_block + 0 * im_stride));             \

    __m256i s2_reg =                                                           \

        _mm256_loadu_si256((__m256i *)(im_block + 2 * im_stride));             \

    __m256i s4_init =                                                          \

        _mm256_loadu_si256((__m256i *)(im_block + 4 * im_stride));             \

    __m256i s1_reg = _mm256_permute2x128_si256(s0_reg, s2_reg, 0x21);          \

    __m256i s3_reg = _mm256_permute2x128_si256(s2_reg, s4_init, 0x21);         \

    __m256i s0 = _mm256_unpacklo_epi16(s0_reg, s1_reg);                        \

    __m256i s1 = _mm256_unpacklo_epi16(s2_reg, s3_reg);                        \

    __m256i s3 = _mm256_setzero_si256();                                       \

    __m256i s4 = _mm256_setzero_si256();                                       \

    if (!(last_4)) {                                                           \

      s3 = _mm256_unpackhi_epi16(s0_reg, s1_reg);                              \

      s4 = _mm256_unpackhi_epi16(s2_reg, s3_reg);                              \

    }                                                                          \

    for (i = 0; i < h; i += 2) {                                               \

      const int16_t *data = &im_block[i * im_stride];                          \

                                                                               \

      const __m256i s4_reg =                                                   \

          _mm256_loadu_si256((__m256i *)(data + 4 * im_stride));               \

      const __m256i s5_reg =                                                   \

          _mm256_loadu_si256((__m256i *)(data + 5 * im_stride));               \

                                                                               \

      __m256i s2 = _mm256_unpacklo_epi16(s4_reg, s5_reg);                      \

                                                                               \

      const __m256i res_a_1 = _mm256_madd_epi16(s0, coeffs_y[1]);              \

      const __m256i res_a_2 = _mm256_madd_epi16(s1, coeffs_y[2]);              \

      const __m256i res_a = _mm256_add_epi32(res_a_1, res_a_2);                \

      const __m256i res_a_round =                                              \

          _mm256_srai_epi32(_mm256_add_epi32(res_a, round_offset_const_v), 7); \

                                                                               \

      __m256i res_unsigned;                                                    \

      if (last_4) {                                                            \

        res_unsigned = _mm256_packus_epi32(res_a_round, res_a_round);          \

      } else {                                                                 \

        __m256i s5 = _mm256_unpackhi_epi16(s4_reg, s5_reg);                    \

        const __m256i res_b_1 = _mm256_madd_epi16(s3, coeffs_y[1]);            \

        const __m256i res_b_2 = _mm256_madd_epi16(s4, coeffs_y[2]);            \

        const __m256i res_b = _mm256_add_epi32(res_b_1, res_b_2);              \

        const __m256i res_b_round = _mm256_srai_epi32(                         \

            _mm256_add_epi32(res_b, round_offset_const_v), 7);                 \

        res_unsigned = _mm256_packus_epi32(res_a_round, res_b_round);          \

        s3 = s4;                                                               \

        s4 = s5;                                                               \

      }                                                                        \

      s0 = s1;                                                                 \

      s1 = s2;                                                                 \

                                                                               \

      if (mode == 0) {                                                         \

        const __m256i comp_const = _mm256_set1_epi32(-16 * offset + 128);      \

        const __m256i wt = unpack_weights_avx2(conv_params);                   \

        __m256i round_result;                                                  \

        const __m256i data_ref_0 = load_line2_avx2(                            \

            &dst[i * dst_stride + j], &dst[i * dst_stride + j + dst_stride]);  \

        const __m256i data_lo =                                                \

            _mm256_unpacklo_epi16(data_ref_0, res_unsigned);                   \

        const __m256i wt_res_lo = _mm256_madd_epi16(data_lo, wt);              \

        const __m256i fused_lo =                                               \

            _mm256_srai_epi32(_mm256_add_epi32(wt_res_lo, comp_const), 8);     \

        if (last_4) {                                                          \

          round_result = _mm256_packs_epi32(fused_lo, fused_lo);               \

        } else {                                                               \

          const __m256i data_hi =                                              \

              _mm256_unpackhi_epi16(data_ref_0, res_unsigned);                 \

          const __m256i wt_res_hi = _mm256_madd_epi16(data_hi, wt);            \

          const __m256i fused_hi =                                             \

              _mm256_srai_epi32(_mm256_add_epi32(wt_res_hi, comp_const), 8);   \

          round_result = _mm256_packs_epi32(fused_lo, fused_hi);               \

        }                                                                      \

        const __m256i res_8 = _mm256_packus_epi16(round_result, round_result); \

        const __m128i res_0 = _mm256_castsi256_si128(res_8);                   \

        const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);              \

        if (last_4) {                                                          \

          *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);     \

          *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =                 \

              _mm_cvtsi128_si32(res_1);                                        \

        } else {                                                               \

          _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);    \

          _mm_storel_epi64(                                                    \

              (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1); \

        }                                                                      \

      } else if (mode == 1) {                                                  \

        const int rounding_shift =                                             \

            2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;     \

        const __m256i offset_const = _mm256_set1_epi16(offset);                \

        const __m256i rounding_const =                                         \

            _mm256_set1_epi16((1 << rounding_shift) >> 1);                     \

        const __m256i data_ref_0 = load_line2_avx2(                            \

            &dst[i * dst_stride + j], &dst[i * dst_stride + j + dst_stride]);  \

        const __m256i wt_res = _mm256_add_epi16(data_ref_0, res_unsigned);     \

        const __m256i comp_avg_res = _mm256_srai_epi16(wt_res, 1);             \

        const __m256i res_signed =                                             \

            _mm256_sub_epi16(comp_avg_res, offset_const);                      \

        const __m256i round_result = _mm256_srai_epi16(                        \

            _mm256_add_epi16(res_signed, rounding_const), 4);                  \

        const __m256i res_8 = _mm256_packus_epi16(round_result, round_result); \

        const __m128i res_0 = _mm256_castsi256_si128(res_8);                   \

        const __m128i res_1 = _mm256_extracti128_si256(res_8, 1);              \

        if (last_4) {                                                          \

          *(int *)(&dst0[i * dst_stride0 + j]) = _mm_cvtsi128_si32(res_0);     \

          *(int *)(&dst0[i * dst_stride0 + j + dst_stride0]) =                 \

              _mm_cvtsi128_si32(res_1);                                        \

        } else {                                                               \

          _mm_storel_epi64((__m128i *)(&dst0[i * dst_stride0 + j]), res_0);    \

          _mm_storel_epi64(                                                    \

              (__m128i *)((&dst0[i * dst_stride0 + j + dst_stride0])), res_1); \

        }                                                                      \

      } else {                                                                 \

        const __m128i res_0 = _mm256_castsi256_si128(res_unsigned);            \

        _mm_store_si128((__m128i *)(&dst[i * dst_stride + j]), res_0);         \

        const __m128i res_1 = _mm256_extracti128_si256(res_unsigned, 1);       \

        _mm_store_si128((__m128i *)(&dst[i * dst_stride + j + dst_stride]),    \

                        res_1);                                                \

      }                                                                        \

    }                                                                          \

  } while (0)

void av1_dist_wtd_convolve_2d_avx2(const uint8_t *src, int src_stride,

                                   uint8_t *dst0, int dst_stride0, int w, int h,

                                   const InterpFilterParams *filter_params_x,

                                   const InterpFilterParams *filter_params_y,

                                   const int subpel_x_qn, const int subpel_y_qn,

                                   ConvolveParams *conv_params) {

  CONV_BUF_TYPE *dst = conv_params->dst;

  int dst_stride = conv_params->dst_stride;

  const int bd = 8;

  DECLARE_ALIGNED(32, int16_t, im_block[(MAX_SB_SIZE + MAX_FILTER_TAP) * 8]);

  int im_stride = 8;

  int i, is_horiz_4tap = 0, is_vert_4tap = 0;

  const int do_average = conv_params->do_average;

  const int use_dist_wtd_comp_avg = conv_params->use_dist_wtd_comp_avg;

  const int offset_0 =

      bd + 2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

  const int offset = (1 << offset_0) + (1 << (offset_0 - 1));

  assert(conv_params->round_0 > 0);

  const __m256i round_const_h = _mm256_set1_epi16(

      ((1 << (conv_params->round_0 - 1)) >> 1) + (1 << (bd + FILTER_BITS - 2)));

  const int round_const_v_val =

      ((1 << conv_params->round_1) >> 1) -

      (1 << (bd + 2 * FILTER_BITS - conv_params->round_0 - 1));

  const __m256i round_const_v = _mm256_set1_epi32(round_const_v_val);

  const __m256i round_offset_const_v =

      _mm256_set1_epi32(round_const_v_val + (offset << 7));

  DECLARE_ALIGNED(32, __m256i, filt[4]);

  DECLARE_ALIGNED(32, __m256i, coeffs_x[4]);

  DECLARE_ALIGNED(32, __m256i, coeffs_y[4]);

  filt[0] = _mm256_load_si256((__m256i const *)filt_global_avx2);

  filt[1] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32));

  prepare_coeffs_lowbd(filter_params_x, subpel_x_qn, coeffs_x);

  prepare_coeffs(filter_params_y, subpel_y_qn, coeffs_y);

  // Condition for checking valid horz_filt taps

  if (!(_mm256_extract_epi32(_mm256_or_si256(coeffs_x[0], coeffs_x[3]), 0)))

    is_horiz_4tap = 1;

  // Condition for checking valid vert_filt taps

  if (!(_mm256_extract_epi32(_mm256_or_si256(coeffs_y[0], coeffs_y[3]), 0)))

    is_vert_4tap = 1;

  if (is_horiz_4tap && is_vert_4tap) {

    int im_h = h + 4;

    const int fo_vert = 1;

    const int fo_horiz = 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride - fo_horiz;

    if (w > 4) {

      for (int j = 0; j < w; j += 8) {

        JNT_CONVOLVE_HORIZONTAL_FILTER(src_ptr + j, convolve_lowbd_x_4tap,

                                       coeffs_x + 1);

        if (do_average) {

          if (use_dist_wtd_comp_avg) {

            JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(0, 0);

          } else {

            JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(0, 1);

          }

        } else {

          JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(0, 2);

        }

      }

    } else {

      const int j = 0;

      JNT_CONVOLVE_HORIZONTAL_FILTER(src_ptr, convolve_lowbd_x_4tap,

                                     coeffs_x + 1);

      if (do_average) {

        if (use_dist_wtd_comp_avg) {

          JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(1, 0);

        } else {

          JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(1, 1);

        }

      } else {

        JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP(1, 2);

      }

    }

  } else if (is_horiz_4tap) {

    int im_h = h + 8;

    const int fo_vert = filter_params_y->taps / 2 - 1;

    const int fo_horiz = 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride - fo_horiz;

    const __m256i wt = unpack_weights_avx2(conv_params);

    const __m256i offset_const = _mm256_set1_epi16(offset);

    const int rounding_shift =

        2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

    const __m256i rounding_const =

        _mm256_set1_epi16((1 << rounding_shift) >> 1);

    for (int j = 0; j < w; j += 8) {

      JNT_CONVOLVE_HORIZONTAL_FILTER(src_ptr + j, convolve_lowbd_x_4tap,

                                     coeffs_x + 1);

      JNT_CONVOLVE_VERTICAL_FILTER_8TAP;

    }

  } else if (is_vert_4tap) {

    int im_h = h + 4;

    const int fo_vert = 1;

    const int fo_horiz = filter_params_x->taps / 2 - 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride - fo_horiz;

    filt[2] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 2));

    filt[3] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 3));

    for (int j = 0; j < w; j += 8) {

      JNT_CONVOLVE_HORIZONTAL_FILTER(src_ptr + j, convolve_lowbd_x, coeffs_x);

      if (do_average) {

        if (use_dist_wtd_comp_avg) {

          JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP((w - j <= 4), 0);

        } else {

          JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP((w - j <= 4), 1);

        }

      } else {

        JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP((w - j <= 4), 2);

      }

    }

  } else {

    int im_h = h + 8;

    const int fo_vert = filter_params_y->taps / 2 - 1;

    const int fo_horiz = filter_params_x->taps / 2 - 1;

    const uint8_t *const src_ptr = src - fo_vert * src_stride - fo_horiz;

    const __m256i wt = unpack_weights_avx2(conv_params);

    const __m256i offset_const = _mm256_set1_epi16(offset);

    const int rounding_shift =

        2 * FILTER_BITS - conv_params->round_0 - conv_params->round_1;

    const __m256i rounding_const =

        _mm256_set1_epi16((1 << rounding_shift) >> 1);

    filt[2] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 2));

    filt[3] = _mm256_load_si256((__m256i const *)(filt_global_avx2 + 32 * 3));

    for (int j = 0; j < w; j += 8) {

      JNT_CONVOLVE_HORIZONTAL_FILTER(src_ptr + j, convolve_lowbd_x, coeffs_x);

      JNT_CONVOLVE_VERTICAL_FILTER_8TAP;

    }

  }

}

#undef JNT_CONVOLVE_2D_VERTICAL_FILTER_4TAP

#define DO_NO_AVG_2D_COPY_4X16(r0, c0, r1, c1, r2, c2, r3, c3)          \

  do {                                                                  \

    src_0 = _mm256_cvtepu8_epi16(                                       \

        _mm_loadu_si128((__m128i *)(&src[r0 * src_stride + c0])));      \

    src_1 = _mm256_cvtepu8_epi16(                                       \

        _mm_loadu_si128((__m128i *)(&src[r1 * src_stride + c1])));      \

    src_2 = _mm256_cvtepu8_epi16(                                       \

        _mm_loadu_si128((__m128i *)(&src[r2 * src_stride + c2])));      \

    src_3 = _mm256_cvtepu8_epi16(                                       \

        _mm_loadu_si128((__m128i *)(&src[r3 * src_stride + c3])));      \

                                                                        \

    src_0 = _mm256_slli_epi16(src_0, LEFT_SHIFT);                       \

    src_1 = _mm256_slli_epi16(src_1, LEFT_SHIFT);                       \

    src_2 = _mm256_slli_epi16(src_2, LEFT_SHIFT);                       \

    src_3 = _mm256_slli_epi16(src_3, LEFT_SHIFT);                       \

                                                                        \

    src_0 = _mm256_add_epi16(src_0, offset_const);                      \

    src_1 = _mm256_add_epi16(src_1, offset_const);                      \

    src_2 = _mm256_add_epi16(src_2, offset_const);                      \

    src_3 = _mm256_add_epi16(src_3, offset_const);                      \

                                                                        \

    _mm256_store_si256((__m256i *)(&dst[r0 * dst_stride + c0]), src_0); \

    _mm256_store_si256((__m256i *)(&dst[r1 * dst_stride + c1]), src_1); \

    _mm256_store_si256((__m256i *)(&dst[r2 * dst_stride + c2]), src_2); \

    _mm256_store_si256((__m256i *)(&dst[r3 * dst_stride + c3]), src_3); \

  } while (0)

#define LEFT_SHIFT (2 * FILTER_BITS - 3 - 7)

static inline void av1_dist_wtd_convolve_2d_no_avg_copy_avx2(

    const uint8_t *src, int src_stride, CONV_BUF_TYPE *dst, int dst_stride,

    int w, int h, const __m256i offset_const) {

  int i = h;

  if (w >= 16) {

    __m256i src_0, src_1, src_2, src_3;

    if (w == 128) {

      do {

        DO_NO_AVG_2D_COPY_4X16(0, 0, 0, 16, 0, 32, 0, 48);

        DO_NO_AVG_2D_COPY_4X16(0, 64, 0, 80, 0, 96, 0, 112);

        src += 1 * src_stride;

        dst += 1 * dst_stride;

        i -= 1;

      } while (i);

    } else if (w == 64) {

      do {

        DO_NO_AVG_2D_COPY_4X16(0, 0, 0, 16, 0, 32, 0, 48);

        src += 1 * src_stride;

        dst += 1 * dst_stride;

        i -= 1;

      } while (i);

    } else if (w == 32) {

      do {

        DO_NO_AVG_2D_COPY_4X16(0, 0, 1, 0, 0, 16, 1, 16);

        src += 2 * src_stride;

        dst += 2 * dst_stride;

        i -= 2;

      } while (i);

    } else if (w == 16) {

      do {

        DO_NO_AVG_2D_COPY_4X16(0, 0, 1, 0, 2, 0, 3, 0);

        src += 4 * src_stride;

        dst += 4 * dst_stride;

        i -= 4;

      } while (i);

    }

  } else {

    const __m256i zero = _mm256_setzero_si256();

    do {

      const __m128i src_row_0 =

          _mm_loadl_epi64((__m128i *)(&src[0 * src_stride]));

      const __m128i src_row_1 =

          _mm_loadl_epi64((__m128i *)(&src[1 * src_stride]));

      const __m128i src_row_2 =

          _mm_loadl_epi64((__m128i *)(&src[2 * src_stride]));

      const __m128i src_row_3 =

          _mm_loadl_epi64((__m128i *)(&src[3 * src_stride]));

      __m256i src_10 = _mm256_insertf128_si256(

          _mm256_castsi128_si256(src_row_0), src_row_1, 1);

      __m256i src_32 = _mm256_insertf128_si256(

          _mm256_castsi128_si256(src_row_2), src_row_3, 1);

      src_10 = _mm256_unpacklo_epi8(src_10, zero);

      src_32 = _mm256_unpacklo_epi8(src_32, zero);

      src_10 = _mm256_slli_epi16(src_10, LEFT_SHIFT);

      src_32 = _mm256_slli_epi16(src_32, LEFT_SHIFT);

      src_10 = _mm256_add_epi16(src_10, offset_const);

      src_32 = _mm256_add_epi16(src_32, offset_const);

      // Accumulate values into the destination buffer

      _mm_store_si128((__m128i *)(&dst[0 * dst_stride]),

                      _mm256_castsi256_si128(src_10));

      _mm_store_si128((__m128i *)(&dst[1 * dst_stride]),

                      _mm256_extracti128_si256(src_10, 1));

      _mm_store_si128((__m128i *)(&dst[2 * dst_stride]),

                      _mm256_castsi256_si128(src_32));

      _mm_store_si128((__m128i *)(&dst[3 * dst_stride]),

                      _mm256_extracti128_si256(src_32, 1));

      src += 4 * src_stride;

      dst += 4 * dst_stride;

      i -= 4;

    } while (i);

  }

}

#define DO_AVG_2D_COPY_4X16(USE_DIST_WEIGHTED, r0, c0, r1, c1, r2, c2, r3, c3) \

  do {                                                                         \

    src_0 = _mm256_cvtepu8_epi16(                                              \

        _mm_loadu_si128((__m128i *)(&src[r0 * src_stride + c0])));             \

    src_1 = _mm256_cvtepu8_epi16(                                              \

        _mm_loadu_si128((__m128i *)(&src[r1 * src_stride + c1])));             \

    src_2 = _mm256_cvtepu8_epi16(                                              \

        _mm_loadu_si128((__m128i *)(&src[r2 * src_stride + c2])));             \

    src_3 = _mm256_cvtepu8_epi16(                                              \

        _mm_loadu_si128((__m128i *)(&src[r3 * src_stride + c3])));             \

                                                                               \

    src_0 = _mm256_slli_epi16(src_0, LEFT_SHIFT);                              \

    src_1 = _mm256_slli_epi16(src_1, LEFT_SHIFT);                              \

    src_2 = _mm256_slli_epi16(src_2, LEFT_SHIFT);                              \

    src_3 = _mm256_slli_epi16(src_3, LEFT_SHIFT);                              \

    src_0 = _mm256_add_epi16(src_0, offset_const);                             \

    src_1 = _mm256_add_epi16(src_1, offset_const);                             \

    src_2 = _mm256_add_epi16(src_2, offset_const);                             \

    src_3 = _mm256_add_epi16(src_3, offset_const);                             \

                                                                               \

    ref_0 = _mm256_loadu_si256((__m256i *)(&dst[r0 * dst_stride + c0]));       \

    ref_1 = _mm256_loadu_si256((__m256i *)(&dst[r1 * dst_stride + c1]));       \

    ref_2 = _mm256_loadu_si256((__m256i *)(&dst[r2 * dst_stride + c2]));       \

    ref_3 = _mm256_loadu_si256((__m256i *)(&dst[r3 * dst_stride + c3]));       \

                                                                               \

    res_0 = comp_avg(&ref_0, &src_0, &wt, USE_DIST_WEIGHTED);                  \

    res_1 = comp_avg(&ref_1, &src_1, &wt, USE_DIST_WEIGHTED);                  \

    res_2 = comp_avg(&ref_2, &src_2, &wt, USE_DIST_WEIGHTED);                  \

    res_3 = comp_avg(&ref_3, &src_3, &wt, USE_DIST_WEIGHTED);                  \

                                                                               \

    res_0 = convolve_rounding(&res_0, &offset_const, &rounding_const,          \

                              rounding_shift);                                 \

    res_1 = convolve_rounding(&res_1, &offset_const, &rounding_const,          \

                              rounding_shift);                                 \

    res_2 = convolve_rounding(&res_2, &offset_const, &rounding_const,          \

                              rounding_shift);                                 \

    res_3 = convolve_rounding(&res_3, &offset_const, &rounding_const,          \

                              rounding_shift);                                 \

                                                                               \

    res_10 = _mm256_packus_epi16(res_0, res_1);                                \

    res_32 = _mm256_packus_epi16(res_2, res_3);                                \

    res_10 = _mm256_permute4x64_epi64(res_10, 0xD8);                           \

    res_32 = _mm256_permute4x64_epi64(res_32, 0xD8);                           \

                                                                               \

    _mm_store_si128((__m128i *)(&dst0[r0 * dst_stride0 + c0]),                 \

                    _mm256_castsi256_si128(res_10));                           \

    _mm_store_si128((__m128i *)(&dst0[r1 * dst_stride0 + c1]),                 \

                    _mm256_extracti128_si256(res_10, 1));                      \

    _mm_store_si128((__m128i *)(&dst0[r2 * dst_stride0 + c2]),                 \

                    _mm256_castsi256_si128(res_32));                           \

    _mm_store_si128((__m128i *)(&dst0[r3 * dst_stride0 + c3]),                 \

                    _mm256_extracti128_si256(res_32, 1));                      \

  } while (0)

#define DO_AVG_2D_COPY(USE_DIST_WEIGHTED)                                     \

  int i = h;                                                                  \

  if (w >= 16) {                                                              \

    __m256i src_0, src_1, src_2, src_3;                                       \

    __m256i ref_0, ref_1, ref_2, ref_3;                                       \

    __m256i res_0, res_1, res_2, res_3;                                       \

    __m256i res_10, res_32;                                                   \

    if (w == 128) {                                                           \

      do {                                                                    \

        DO_AVG_2D_COPY_4X16(USE_DIST_WEIGHTED, 0, 0, 0, 16, 0, 32, 0, 48);    \

        DO_AVG_2D_COPY_4X16(USE_DIST_WEIGHTED, 0, 64, 0, 80, 0, 96, 0, 112);  \