/*

 * 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 <assert.h>

#include <math.h>

#include <stdio.h>

#include "config/av1_rtcd.h"

#include "aom_dsp/aom_dsp_common.h"

#include "aom_mem/aom_mem.h"

#include "aom_ports/bitops.h"

#include "aom_ports/mem.h"

#include "av1/common/common.h"

#include "av1/common/entropy.h"

#include "av1/common/entropymode.h"

#include "av1/common/mvref_common.h"

#include "av1/common/pred_common.h"

#include "av1/common/quant_common.h"

#include "av1/common/reconinter.h"

#include "av1/common/reconintra.h"

#include "av1/common/seg_common.h"

#include "av1/encoder/av1_quantize.h"

#include "av1/encoder/cost.h"

#include "av1/encoder/encodemb.h"

#include "av1/encoder/encodemv.h"

#include "av1/encoder/encoder.h"

#include "av1/encoder/encodetxb.h"

#include "av1/encoder/mcomp.h"

#include "av1/encoder/ratectrl.h"

#include "av1/encoder/rd.h"

#include "av1/encoder/tokenize.h"

#define RD_THRESH_POW 1.25

// The baseline rd thresholds for breaking out of the rd loop for

// certain modes are assumed to be based on 8x8 blocks.

// This table is used to correct for block size.

// The factors here are << 2 (2 = x0.5, 32 = x8 etc).

static const uint8_t rd_thresh_block_size_factor[BLOCK_SIZES_ALL] = {

  2, 3, 3, 4, 6, 6, 8, 12, 12, 16, 24, 24, 32, 48, 48, 64, 4, 4, 8, 8, 16, 16

};

static const int use_intra_ext_tx_for_txsize[EXT_TX_SETS_INTRA]

                                            [EXT_TX_SIZES] = {

                                              { 1, 1, 1, 1 },  // unused

                                              { 1, 1, 0, 0 },

                                              { 0, 0, 1, 0 },

                                            };

static const int use_inter_ext_tx_for_txsize[EXT_TX_SETS_INTER]

                                            [EXT_TX_SIZES] = {

                                              { 1, 1, 1, 1 },  // unused

                                              { 1, 1, 0, 0 },

                                              { 0, 0, 1, 0 },

                                              { 0, 1, 1, 1 },

                                            };

static const int av1_ext_tx_set_idx_to_type[2][AOMMAX(EXT_TX_SETS_INTRA,

                                                      EXT_TX_SETS_INTER)] = {

  {

      // Intra

      EXT_TX_SET_DCTONLY,

      EXT_TX_SET_DTT4_IDTX_1DDCT,

      EXT_TX_SET_DTT4_IDTX,

  },

  {

      // Inter

      EXT_TX_SET_DCTONLY,

      EXT_TX_SET_ALL16,

      EXT_TX_SET_DTT9_IDTX_1DDCT,

      EXT_TX_SET_DCT_IDTX,

  },

};

void av1_fill_mode_rates(AV1_COMMON *const cm, ModeCosts *mode_costs,

                         FRAME_CONTEXT *fc) {

  int i, j;

  for (i = 0; i < PARTITION_CONTEXTS; ++i)

    av1_cost_tokens_from_cdf(mode_costs->partition_cost[i],

                             fc->partition_cdf[i], NULL);

  if (cm->current_frame.skip_mode_info.skip_mode_flag) {

    for (i = 0; i < SKIP_MODE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->skip_mode_cost[i],

                               fc->skip_mode_cdfs[i], NULL);

    }

  }

  for (i = 0; i < SKIP_CONTEXTS; ++i) {

    av1_cost_tokens_from_cdf(mode_costs->skip_txfm_cost[i],

                             fc->skip_txfm_cdfs[i], NULL);

  }

  for (i = 0; i < KF_MODE_CONTEXTS; ++i)

    for (j = 0; j < KF_MODE_CONTEXTS; ++j)

      av1_cost_tokens_from_cdf(mode_costs->y_mode_costs[i][j],

                               fc->kf_y_cdf[i][j], NULL);

  for (i = 0; i < BLOCK_SIZE_GROUPS; ++i)

    av1_cost_tokens_from_cdf(mode_costs->mbmode_cost[i], fc->y_mode_cdf[i],

                             NULL);

  for (i = 0; i < CFL_ALLOWED_TYPES; ++i)

    for (j = 0; j < INTRA_MODES; ++j)

      av1_cost_tokens_from_cdf(mode_costs->intra_uv_mode_cost[i][j],

                               fc->uv_mode_cdf[i][j], NULL);

  av1_cost_tokens_from_cdf(mode_costs->filter_intra_mode_cost,

                           fc->filter_intra_mode_cdf, NULL);

  for (i = 0; i < BLOCK_SIZES_ALL; ++i) {

    if (av1_filter_intra_allowed_bsize(cm, i))

      av1_cost_tokens_from_cdf(mode_costs->filter_intra_cost[i],

                               fc->filter_intra_cdfs[i], NULL);

  }

  for (i = 0; i < SWITCHABLE_FILTER_CONTEXTS; ++i)

    av1_cost_tokens_from_cdf(mode_costs->switchable_interp_costs[i],

                             fc->switchable_interp_cdf[i], NULL);

  for (i = 0; i < PALATTE_BSIZE_CTXS; ++i) {

    av1_cost_tokens_from_cdf(mode_costs->palette_y_size_cost[i],

                             fc->palette_y_size_cdf[i], NULL);

    av1_cost_tokens_from_cdf(mode_costs->palette_uv_size_cost[i],

                             fc->palette_uv_size_cdf[i], NULL);

    for (j = 0; j < PALETTE_Y_MODE_CONTEXTS; ++j) {

      av1_cost_tokens_from_cdf(mode_costs->palette_y_mode_cost[i][j],

                               fc->palette_y_mode_cdf[i][j], NULL);

    }

  }

  for (i = 0; i < PALETTE_UV_MODE_CONTEXTS; ++i) {

    av1_cost_tokens_from_cdf(mode_costs->palette_uv_mode_cost[i],

                             fc->palette_uv_mode_cdf[i], NULL);

  }

  for (i = 0; i < PALETTE_SIZES; ++i) {

    for (j = 0; j < PALETTE_COLOR_INDEX_CONTEXTS; ++j) {

      av1_cost_tokens_from_cdf(mode_costs->palette_y_color_cost[i][j],

                               fc->palette_y_color_index_cdf[i][j], NULL);

      av1_cost_tokens_from_cdf(mode_costs->palette_uv_color_cost[i][j],

                               fc->palette_uv_color_index_cdf[i][j], NULL);

    }

  }

  int sign_cost[CFL_JOINT_SIGNS];

  av1_cost_tokens_from_cdf(sign_cost, fc->cfl_sign_cdf, NULL);

  for (int joint_sign = 0; joint_sign < CFL_JOINT_SIGNS; joint_sign++) {

    int *cost_u = mode_costs->cfl_cost[joint_sign][CFL_PRED_U];

    int *cost_v = mode_costs->cfl_cost[joint_sign][CFL_PRED_V];

    if (CFL_SIGN_U(joint_sign) == CFL_SIGN_ZERO) {

      memset(cost_u, 0, CFL_ALPHABET_SIZE * sizeof(*cost_u));

    } else {

      const aom_cdf_prob *cdf_u = fc->cfl_alpha_cdf[CFL_CONTEXT_U(joint_sign)];

      av1_cost_tokens_from_cdf(cost_u, cdf_u, NULL);

    }

    if (CFL_SIGN_V(joint_sign) == CFL_SIGN_ZERO) {

      memset(cost_v, 0, CFL_ALPHABET_SIZE * sizeof(*cost_v));

    } else {

      const aom_cdf_prob *cdf_v = fc->cfl_alpha_cdf[CFL_CONTEXT_V(joint_sign)];

      av1_cost_tokens_from_cdf(cost_v, cdf_v, NULL);

    }

    for (int u = 0; u < CFL_ALPHABET_SIZE; u++)

      cost_u[u] += sign_cost[joint_sign];

  }

  for (i = 0; i < MAX_TX_CATS; ++i)

    for (j = 0; j < TX_SIZE_CONTEXTS; ++j)

      av1_cost_tokens_from_cdf(mode_costs->tx_size_cost[i][j],

                               fc->tx_size_cdf[i][j], NULL);

  for (i = 0; i < TXFM_PARTITION_CONTEXTS; ++i) {

    av1_cost_tokens_from_cdf(mode_costs->txfm_partition_cost[i],

                             fc->txfm_partition_cdf[i], NULL);

  }

  for (i = TX_4X4; i < EXT_TX_SIZES; ++i) {

    int s;

    for (s = 1; s < EXT_TX_SETS_INTER; ++s) {

      if (use_inter_ext_tx_for_txsize[s][i]) {

        av1_cost_tokens_from_cdf(

            mode_costs->inter_tx_type_costs[s][i], fc->inter_ext_tx_cdf[s][i],

            av1_ext_tx_inv[av1_ext_tx_set_idx_to_type[1][s]]);

      }

    }

    for (s = 1; s < EXT_TX_SETS_INTRA; ++s) {

      if (use_intra_ext_tx_for_txsize[s][i]) {

        for (j = 0; j < INTRA_MODES; ++j) {

          av1_cost_tokens_from_cdf(

              mode_costs->intra_tx_type_costs[s][i][j],

              fc->intra_ext_tx_cdf[s][i][j],

              av1_ext_tx_inv[av1_ext_tx_set_idx_to_type[0][s]]);

        }

      }

    }

  }

  for (i = 0; i < DIRECTIONAL_MODES; ++i) {

    av1_cost_tokens_from_cdf(mode_costs->angle_delta_cost[i],

                             fc->angle_delta_cdf[i], NULL);

  }

  av1_cost_tokens_from_cdf(mode_costs->intrabc_cost, fc->intrabc_cdf, NULL);

  if (!frame_is_intra_only(cm)) {

    for (i = 0; i < COMP_INTER_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->comp_inter_cost[i],

                               fc->comp_inter_cdf[i], NULL);

    }

    for (i = 0; i < REF_CONTEXTS; ++i) {

      for (j = 0; j < SINGLE_REFS - 1; ++j) {

        av1_cost_tokens_from_cdf(mode_costs->single_ref_cost[i][j],

                                 fc->single_ref_cdf[i][j], NULL);

      }

    }

    for (i = 0; i < COMP_REF_TYPE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->comp_ref_type_cost[i],

                               fc->comp_ref_type_cdf[i], NULL);

    }

    for (i = 0; i < UNI_COMP_REF_CONTEXTS; ++i) {

      for (j = 0; j < UNIDIR_COMP_REFS - 1; ++j) {

        av1_cost_tokens_from_cdf(mode_costs->uni_comp_ref_cost[i][j],

                                 fc->uni_comp_ref_cdf[i][j], NULL);

      }

    }

    for (i = 0; i < REF_CONTEXTS; ++i) {

      for (j = 0; j < FWD_REFS - 1; ++j) {

        av1_cost_tokens_from_cdf(mode_costs->comp_ref_cost[i][j],

                                 fc->comp_ref_cdf[i][j], NULL);

      }

    }

    for (i = 0; i < REF_CONTEXTS; ++i) {

      for (j = 0; j < BWD_REFS - 1; ++j) {

        av1_cost_tokens_from_cdf(mode_costs->comp_bwdref_cost[i][j],

                                 fc->comp_bwdref_cdf[i][j], NULL);

      }

    }

    for (i = 0; i < INTRA_INTER_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->intra_inter_cost[i],

                               fc->intra_inter_cdf[i], NULL);

    }

    for (i = 0; i < NEWMV_MODE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->newmv_mode_cost[i], fc->newmv_cdf[i],

                               NULL);

    }

    for (i = 0; i < GLOBALMV_MODE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->zeromv_mode_cost[i],

                               fc->zeromv_cdf[i], NULL);

    }

    for (i = 0; i < REFMV_MODE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->refmv_mode_cost[i], fc->refmv_cdf[i],

                               NULL);

    }

    for (i = 0; i < DRL_MODE_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->drl_mode_cost0[i], fc->drl_cdf[i],

                               NULL);

    }

    for (i = 0; i < INTER_MODE_CONTEXTS; ++i)

      av1_cost_tokens_from_cdf(mode_costs->inter_compound_mode_cost[i],

                               fc->inter_compound_mode_cdf[i], NULL);

    for (i = 0; i < BLOCK_SIZES_ALL; ++i)

      av1_cost_tokens_from_cdf(mode_costs->compound_type_cost[i],

                               fc->compound_type_cdf[i], NULL);

    for (i = 0; i < BLOCK_SIZES_ALL; ++i) {

      if (av1_is_wedge_used(i)) {

        av1_cost_tokens_from_cdf(mode_costs->wedge_idx_cost[i],

                                 fc->wedge_idx_cdf[i], NULL);

      }

    }

    for (i = 0; i < BLOCK_SIZE_GROUPS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->interintra_cost[i],

                               fc->interintra_cdf[i], NULL);

      av1_cost_tokens_from_cdf(mode_costs->interintra_mode_cost[i],

                               fc->interintra_mode_cdf[i], NULL);

    }

    for (i = 0; i < BLOCK_SIZES_ALL; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->wedge_interintra_cost[i],

                               fc->wedge_interintra_cdf[i], NULL);

    }

    for (i = BLOCK_8X8; i < BLOCK_SIZES_ALL; i++) {

      av1_cost_tokens_from_cdf(mode_costs->motion_mode_cost[i],

                               fc->motion_mode_cdf[i], NULL);

    }

    for (i = BLOCK_8X8; i < BLOCK_SIZES_ALL; i++) {

      av1_cost_tokens_from_cdf(mode_costs->motion_mode_cost1[i],

                               fc->obmc_cdf[i], NULL);

    }

    for (i = 0; i < COMP_INDEX_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->comp_idx_cost[i],

                               fc->compound_index_cdf[i], NULL);

    }

    for (i = 0; i < COMP_GROUP_IDX_CONTEXTS; ++i) {

      av1_cost_tokens_from_cdf(mode_costs->comp_group_idx_cost[i],

                               fc->comp_group_idx_cdf[i], NULL);

    }

  }

}

void av1_fill_lr_rates(ModeCosts *mode_costs, FRAME_CONTEXT *fc) {

  av1_cost_tokens_from_cdf(mode_costs->switchable_restore_cost,

                           fc->switchable_restore_cdf, NULL);

  av1_cost_tokens_from_cdf(mode_costs->wiener_restore_cost,

                           fc->wiener_restore_cdf, NULL);

  av1_cost_tokens_from_cdf(mode_costs->sgrproj_restore_cost,

                           fc->sgrproj_restore_cdf, NULL);

}

// Values are now correlated to quantizer.

static int sad_per_bit_lut_8[QINDEX_RANGE];

static int sad_per_bit_lut_10[QINDEX_RANGE];

static int sad_per_bit_lut_12[QINDEX_RANGE];

static void init_me_luts_bd(int *bit16lut, int range,

                            aom_bit_depth_t bit_depth) {

  int i;

  // Initialize the sad lut tables using a formulaic calculation for now.

  // This is to make it easier to resolve the impact of experimental changes

  // to the quantizer tables.

  for (i = 0; i < range; i++) {

    const double q = av1_convert_qindex_to_q(i, bit_depth);

    bit16lut[i] = (int)(0.0418 * q + 2.4107);

  }

}

void av1_init_me_luts(void) {

  init_me_luts_bd(sad_per_bit_lut_8, QINDEX_RANGE, AOM_BITS_8);

  init_me_luts_bd(sad_per_bit_lut_10, QINDEX_RANGE, AOM_BITS_10);

  init_me_luts_bd(sad_per_bit_lut_12, QINDEX_RANGE, AOM_BITS_12);

}

static const int rd_boost_factor[16] = { 64, 32, 32, 32, 24, 16, 12, 12,

                                         8,  8,  4,  4,  2,  2,  1,  0 };

static const int rd_layer_depth_factor[7] = {

  160, 160, 160, 160, 192, 208, 224

};

// Returns the default rd multiplier for inter frames for a given qindex.

// The function here is a first pass estimate based on data from

// a previous Vizer run

static double def_inter_rd_multiplier(int qindex) {

  return 3.2 + (0.0035 * (double)qindex);

}

// Returns the default rd multiplier for ARF/Golden Frames for a given qindex.

// The function here is a first pass estimate based on data from

// a previous Vizer run

static double def_arf_rd_multiplier(int qindex) {

  return 3.25 + (0.0035 * (double)qindex);

}

// Returns the default rd multiplier for key frames for a given qindex.

// The function here is a first pass estimate based on data from

// a previous Vizer run

static double def_kf_rd_multiplier(int qindex) {

  return 3.3 + (0.0035 * (double)qindex);

}

int av1_compute_rd_mult_based_on_qindex(aom_bit_depth_t bit_depth,

                                        FRAME_UPDATE_TYPE update_type,

                                        int qindex) {

  const int q = av1_dc_quant_QTX(qindex, 0, bit_depth);

  int rdmult = q * q;

  if (update_type == KF_UPDATE) {

    double def_rd_q_mult = def_kf_rd_multiplier(qindex);

    rdmult = (int)((double)rdmult * def_rd_q_mult);

  } else if ((update_type == GF_UPDATE) || (update_type == ARF_UPDATE)) {

    double def_rd_q_mult = def_arf_rd_multiplier(qindex);

    rdmult = (int)((double)rdmult * def_rd_q_mult);

  } else {

    double def_rd_q_mult = def_inter_rd_multiplier(qindex);

    rdmult = (int)((double)rdmult * def_rd_q_mult);

  }

  switch (bit_depth) {

    case AOM_BITS_8: break;

    case AOM_BITS_10: rdmult = ROUND_POWER_OF_TWO(rdmult, 4); break;

    case AOM_BITS_12: rdmult = ROUND_POWER_OF_TWO(rdmult, 8); break;

    default:

      assert(0 && "bit_depth should be AOM_BITS_8, AOM_BITS_10 or AOM_BITS_12");

      return -1;

  }

  return rdmult > 0 ? rdmult : 1;

}

int av1_compute_rd_mult(const AV1_COMP *cpi, int qindex) {

  const aom_bit_depth_t bit_depth = cpi->common.seq_params->bit_depth;

  const FRAME_UPDATE_TYPE update_type =

      cpi->ppi->gf_group.update_type[cpi->gf_frame_index];

  int64_t rdmult =

      av1_compute_rd_mult_based_on_qindex(bit_depth, update_type, qindex);

  if (is_stat_consumption_stage(cpi) && !cpi->oxcf.q_cfg.use_fixed_qp_offsets &&

      (cpi->common.current_frame.frame_type != KEY_FRAME)) {

    const GF_GROUP *const gf_group = &cpi->ppi->gf_group;

    const int boost_index = AOMMIN(15, (cpi->ppi->p_rc.gfu_boost / 100));

    const int layer_depth =

        AOMMIN(gf_group->layer_depth[cpi->gf_frame_index], 6);

    // Layer depth adjustment

    rdmult = (rdmult * rd_layer_depth_factor[layer_depth]) >> 7;

    // ARF boost adjustment

    rdmult += ((rdmult * rd_boost_factor[boost_index]) >> 7);

  }

  return (int)rdmult;

}

int av1_get_deltaq_offset(aom_bit_depth_t bit_depth, int qindex, double beta) {

  assert(beta > 0.0);

  int q = av1_dc_quant_QTX(qindex, 0, bit_depth);

  int newq = (int)rint(q / sqrt(beta));

  int orig_qindex = qindex;

  if (newq == q) {

    return 0;

  }

  if (newq < q) {

    while (qindex > 0) {

      qindex--;

      q = av1_dc_quant_QTX(qindex, 0, bit_depth);

      if (newq >= q) {

        break;

      }

    }

  } else {

    while (qindex < MAXQ) {

      qindex++;

      q = av1_dc_quant_QTX(qindex, 0, bit_depth);

      if (newq <= q) {

        break;

      }

    }

  }

  return qindex - orig_qindex;

}

int av1_adjust_q_from_delta_q_res(int delta_q_res, int prev_qindex,

                                  int curr_qindex) {

  curr_qindex = clamp(curr_qindex, delta_q_res, 256 - delta_q_res);

  const int sign_deltaq_index = curr_qindex - prev_qindex >= 0 ? 1 : -1;

  const int deltaq_deadzone = delta_q_res / 4;

  const int qmask = ~(delta_q_res - 1);

  int abs_deltaq_index = abs(curr_qindex - prev_qindex);

  abs_deltaq_index = (abs_deltaq_index + deltaq_deadzone) & qmask;

  int adjust_qindex = prev_qindex + sign_deltaq_index * abs_deltaq_index;

  adjust_qindex = AOMMAX(adjust_qindex, MINQ + 1);

  return adjust_qindex;

}

int av1_get_adaptive_rdmult(const AV1_COMP *cpi, double beta) {

  assert(beta > 0.0);

  const AV1_COMMON *cm = &cpi->common;

  int q = av1_dc_quant_QTX(cm->quant_params.base_qindex, 0,

                           cm->seq_params->bit_depth);

  return (int)(av1_compute_rd_mult(cpi, q) / beta);

}

static int compute_rd_thresh_factor(int qindex, aom_bit_depth_t bit_depth) {

  double q;

  switch (bit_depth) {

    case AOM_BITS_8: q = av1_dc_quant_QTX(qindex, 0, AOM_BITS_8) / 4.0; break;

    case AOM_BITS_10:

      q = av1_dc_quant_QTX(qindex, 0, AOM_BITS_10) / 16.0;

      break;

    case AOM_BITS_12:

      q = av1_dc_quant_QTX(qindex, 0, AOM_BITS_12) / 64.0;

      break;

    default:

      assert(0 && "bit_depth should be AOM_BITS_8, AOM_BITS_10 or AOM_BITS_12");

      return -1;

  }

  // TODO(debargha): Adjust the function below.

  return AOMMAX((int)(pow(q, RD_THRESH_POW) * 5.12), 8);

}

void av1_set_sad_per_bit(const AV1_COMP *cpi, int *sadperbit, int qindex) {

  switch (cpi->common.seq_params->bit_depth) {

    case AOM_BITS_8: *sadperbit = sad_per_bit_lut_8[qindex]; break;

    case AOM_BITS_10: *sadperbit = sad_per_bit_lut_10[qindex]; break;

    case AOM_BITS_12: *sadperbit = sad_per_bit_lut_12[qindex]; break;

    default:

      assert(0 && "bit_depth should be AOM_BITS_8, AOM_BITS_10 or AOM_BITS_12");

  }

}

static void set_block_thresholds(const AV1_COMMON *cm, RD_OPT *rd) {

  int i, bsize, segment_id;

  for (segment_id = 0; segment_id < MAX_SEGMENTS; ++segment_id) {

    const int qindex = clamp(

        av1_get_qindex(&cm->seg, segment_id, cm->quant_params.base_qindex) +

            cm->quant_params.y_dc_delta_q,

        0, MAXQ);

    const int q = compute_rd_thresh_factor(qindex, cm->seq_params->bit_depth);

    for (bsize = 0; bsize < BLOCK_SIZES_ALL; ++bsize) {

      // Threshold here seems unnecessarily harsh but fine given actual

      // range of values used for cpi->sf.thresh_mult[].

      const int t = q * rd_thresh_block_size_factor[bsize];

      const int thresh_max = INT_MAX / t;

      for (i = 0; i < MAX_MODES; ++i)

        rd->threshes[segment_id][bsize][i] = rd->thresh_mult[i] < thresh_max

                                                 ? rd->thresh_mult[i] * t / 4

                                                 : INT_MAX;

    }

  }

}

void av1_fill_coeff_costs(CoeffCosts *coeff_costs, FRAME_CONTEXT *fc,

                          const int num_planes) {

  const int nplanes = AOMMIN(num_planes, PLANE_TYPES);

  for (int eob_multi_size = 0; eob_multi_size < 7; ++eob_multi_size) {

    for (int plane = 0; plane < nplanes; ++plane) {

      LV_MAP_EOB_COST *pcost = &coeff_costs->eob_costs[eob_multi_size][plane];

      for (int ctx = 0; ctx < 2; ++ctx) {

        aom_cdf_prob *pcdf;

        switch (eob_multi_size) {

          case 0: pcdf = fc->eob_flag_cdf16[plane][ctx]; break;

          case 1: pcdf = fc->eob_flag_cdf32[plane][ctx]; break;

          case 2: pcdf = fc->eob_flag_cdf64[plane][ctx]; break;

          case 3: pcdf = fc->eob_flag_cdf128[plane][ctx]; break;

          case 4: pcdf = fc->eob_flag_cdf256[plane][ctx]; break;

          case 5: pcdf = fc->eob_flag_cdf512[plane][ctx]; break;

          case 6:

          default: pcdf = fc->eob_flag_cdf1024[plane][ctx]; break;

        }

        av1_cost_tokens_from_cdf(pcost->eob_cost[ctx], pcdf, NULL);

      }

    }

  }

  for (int tx_size = 0; tx_size < TX_SIZES; ++tx_size) {

    for (int plane = 0; plane < nplanes; ++plane) {

      LV_MAP_COEFF_COST *pcost = &coeff_costs->coeff_costs[tx_size][plane];

      for (int ctx = 0; ctx < TXB_SKIP_CONTEXTS; ++ctx)

        av1_cost_tokens_from_cdf(pcost->txb_skip_cost[ctx],

                                 fc->txb_skip_cdf[tx_size][ctx], NULL);

      for (int ctx = 0; ctx < SIG_COEF_CONTEXTS_EOB; ++ctx)

        av1_cost_tokens_from_cdf(pcost->base_eob_cost[ctx],

                                 fc->coeff_base_eob_cdf[tx_size][plane][ctx],

                                 NULL);

      for (int ctx = 0; ctx < SIG_COEF_CONTEXTS; ++ctx)

        av1_cost_tokens_from_cdf(pcost->base_cost[ctx],

                                 fc->coeff_base_cdf[tx_size][plane][ctx], NULL);

      for (int ctx = 0; ctx < SIG_COEF_CONTEXTS; ++ctx) {

        pcost->base_cost[ctx][4] = 0;

        pcost->base_cost[ctx][5] = pcost->base_cost[ctx][1] +

                                   av1_cost_literal(1) -

                                   pcost->base_cost[ctx][0];

        pcost->base_cost[ctx][6] =

            pcost->base_cost[ctx][2] - pcost->base_cost[ctx][1];

        pcost->base_cost[ctx][7] =

            pcost->base_cost[ctx][3] - pcost->base_cost[ctx][2];

      }

      for (int ctx = 0; ctx < EOB_COEF_CONTEXTS; ++ctx)

        av1_cost_tokens_from_cdf(pcost->eob_extra_cost[ctx],

                                 fc->eob_extra_cdf[tx_size][plane][ctx], NULL);

      for (int ctx = 0; ctx < DC_SIGN_CONTEXTS; ++ctx)

        av1_cost_tokens_from_cdf(pcost->dc_sign_cost[ctx],

                                 fc->dc_sign_cdf[plane][ctx], NULL);

      for (int ctx = 0; ctx < LEVEL_CONTEXTS; ++ctx) {

        int br_rate[BR_CDF_SIZE];

        int prev_cost = 0;

        int i, j;

        av1_cost_tokens_from_cdf(

            br_rate, fc->coeff_br_cdf[AOMMIN(tx_size, TX_32X32)][plane][ctx],

            NULL);

        // printf("br_rate: ");

        // for(j = 0; j < BR_CDF_SIZE; j++)

        //  printf("%4d ", br_rate[j]);

        // printf("\n");

        for (i = 0; i < COEFF_BASE_RANGE; i += BR_CDF_SIZE - 1) {

          for (j = 0; j < BR_CDF_SIZE - 1; j++) {

            pcost->lps_cost[ctx][i + j] = prev_cost + br_rate[j];

          }

          prev_cost += br_rate[j];

        }

        pcost->lps_cost[ctx][i] = prev_cost;

        // printf("lps_cost: %d %d %2d : ", tx_size, plane, ctx);

        // for (i = 0; i <= COEFF_BASE_RANGE; i++)

        //  printf("%5d ", pcost->lps_cost[ctx][i]);

        // printf("\n");

      }

      for (int ctx = 0; ctx < LEVEL_CONTEXTS; ++ctx) {

        pcost->lps_cost[ctx][0 + COEFF_BASE_RANGE + 1] =

            pcost->lps_cost[ctx][0];

        for (int i = 1; i <= COEFF_BASE_RANGE; ++i) {

          pcost->lps_cost[ctx][i + COEFF_BASE_RANGE + 1] =

              pcost->lps_cost[ctx][i] - pcost->lps_cost[ctx][i - 1];

        }

      }

    }

  }

}

void av1_fill_mv_costs(const nmv_context *nmvc, int integer_mv, int usehp,

                       MvCosts *mv_costs) {

  // Avoid accessing 'mv_costs' when it is not allocated.

  if (mv_costs == NULL) return;

  mv_costs->nmv_cost[0] = &mv_costs->nmv_cost_alloc[0][MV_MAX];

  mv_costs->nmv_cost[1] = &mv_costs->nmv_cost_alloc[1][MV_MAX];

  mv_costs->nmv_cost_hp[0] = &mv_costs->nmv_cost_hp_alloc[0][MV_MAX];

  mv_costs->nmv_cost_hp[1] = &mv_costs->nmv_cost_hp_alloc[1][MV_MAX];

  if (integer_mv) {

    mv_costs->mv_cost_stack = (int **)&mv_costs->nmv_cost;

    av1_build_nmv_cost_table(mv_costs->nmv_joint_cost, mv_costs->mv_cost_stack,

                             nmvc, MV_SUBPEL_NONE);

  } else {

    mv_costs->mv_cost_stack =

        usehp ? mv_costs->nmv_cost_hp : mv_costs->nmv_cost;

    av1_build_nmv_cost_table(mv_costs->nmv_joint_cost, mv_costs->mv_cost_stack,

                             nmvc, usehp);

  }

}

void av1_fill_dv_costs(const nmv_context *ndvc, IntraBCMVCosts *dv_costs) {

  dv_costs->dv_costs[0] = &dv_costs->dv_costs_alloc[0][MV_MAX];

  dv_costs->dv_costs[1] = &dv_costs->dv_costs_alloc[1][MV_MAX];

  av1_build_nmv_cost_table(dv_costs->joint_mv, dv_costs->dv_costs, ndvc,

                           MV_SUBPEL_NONE);

}

// Populates speed features based on codec control settings (of type

// COST_UPDATE_TYPE) and expected speed feature settings (of type

// INTERNAL_COST_UPDATE_TYPE) by considering the least frequent cost update.

// The populated/updated speed features are used for cost updates in the

// encoder.

// WARNING: Population of unified cost update frequency needs to be taken care

// accordingly, in case of any modifications/additions to the enum

// COST_UPDATE_TYPE/INTERNAL_COST_UPDATE_TYPE.

static INLINE void populate_unified_cost_update_freq(

    const CostUpdateFreq cost_upd_freq, SPEED_FEATURES *const sf) {

  INTER_MODE_SPEED_FEATURES *const inter_sf = &sf->inter_sf;

  // Mapping of entropy cost update frequency from the encoder's codec control

  // settings of type COST_UPDATE_TYPE to speed features of type

  // INTERNAL_COST_UPDATE_TYPE.

  static const INTERNAL_COST_UPDATE_TYPE

      map_cost_upd_to_internal_cost_upd[NUM_COST_UPDATE_TYPES] = {

        INTERNAL_COST_UPD_SB, INTERNAL_COST_UPD_SBROW, INTERNAL_COST_UPD_TILE,

        INTERNAL_COST_UPD_OFF

      };

  inter_sf->mv_cost_upd_level =

      AOMMIN(inter_sf->mv_cost_upd_level,

             map_cost_upd_to_internal_cost_upd[cost_upd_freq.mv]);

  inter_sf->coeff_cost_upd_level =

      AOMMIN(inter_sf->coeff_cost_upd_level,

             map_cost_upd_to_internal_cost_upd[cost_upd_freq.coeff]);

  inter_sf->mode_cost_upd_level =

      AOMMIN(inter_sf->mode_cost_upd_level,

             map_cost_upd_to_internal_cost_upd[cost_upd_freq.mode]);

  sf->intra_sf.dv_cost_upd_level =

      AOMMIN(sf->intra_sf.dv_cost_upd_level,

             map_cost_upd_to_internal_cost_upd[cost_upd_freq.dv]);

}

// Checks if entropy costs should be initialized/updated at frame level or not.

static INLINE int is_frame_level_cost_upd_freq_set(

    const AV1_COMMON *const cm, const INTERNAL_COST_UPDATE_TYPE cost_upd_level,

    const int use_nonrd_pick_mode, const int frames_since_key) {

  const int fill_costs =

      frame_is_intra_only(cm) ||

      (use_nonrd_pick_mode ? frames_since_key < 2

                           : (cm->current_frame.frame_number & 0x07) == 1);

  return ((!use_nonrd_pick_mode && cost_upd_level != INTERNAL_COST_UPD_OFF) ||

          cost_upd_level == INTERNAL_COST_UPD_TILE || fill_costs);

}

void av1_initialize_rd_consts(AV1_COMP *cpi) {

  AV1_COMMON *const cm = &cpi->common;

  MACROBLOCK *const x = &cpi->td.mb;

  SPEED_FEATURES *const sf = &cpi->sf;

  RD_OPT *const rd = &cpi->rd;

  int use_nonrd_pick_mode = cpi->sf.rt_sf.use_nonrd_pick_mode;

  int frames_since_key = cpi->rc.frames_since_key;

  rd->RDMULT = av1_compute_rd_mult(

      cpi, cm->quant_params.base_qindex + cm->quant_params.y_dc_delta_q);

#if CONFIG_RD_COMMAND

  if (cpi->oxcf.pass == 2) {

    const RD_COMMAND *rd_command = &cpi->rd_command;

    if (rd_command->option_ls[rd_command->frame_index] ==

        RD_OPTION_SET_Q_RDMULT) {

      rd->RDMULT = rd_command->rdmult_ls[rd_command->frame_index];

    }

  }

#endif  // CONFIG_RD_COMMAND

  av1_set_error_per_bit(&x->errorperbit, rd->RDMULT);

  set_block_thresholds(cm, rd);

  populate_unified_cost_update_freq(cpi->oxcf.cost_upd_freq, sf);

  const INTER_MODE_SPEED_FEATURES *const inter_sf = &cpi->sf.inter_sf;

  // Frame level mv cost update

  if (is_frame_level_cost_upd_freq_set(cm, inter_sf->mv_cost_upd_level,

                                       use_nonrd_pick_mode, frames_since_key))

    av1_fill_mv_costs(&cm->fc->nmvc, cm->features.cur_frame_force_integer_mv,

                      cm->features.allow_high_precision_mv, x->mv_costs);

  // Frame level coefficient cost update

  if (is_frame_level_cost_upd_freq_set(cm, inter_sf->coeff_cost_upd_level,

                                       use_nonrd_pick_mode, frames_since_key))

    av1_fill_coeff_costs(&x->coeff_costs, cm->fc, av1_num_planes(cm));

  // Frame level mode cost update

  if (is_frame_level_cost_upd_freq_set(cm, inter_sf->mode_cost_upd_level,

                                       use_nonrd_pick_mode, frames_since_key))

    av1_fill_mode_rates(cm, &x->mode_costs, cm->fc);

  // Frame level dv cost update

  if (!use_nonrd_pick_mode && av1_allow_intrabc(cm) &&

      !is_stat_generation_stage(cpi)) {

    av1_fill_dv_costs(&cm->fc->ndvc, x->dv_costs);

  }

}

static void model_rd_norm(int xsq_q10, int *r_q10, int *d_q10) {

  // NOTE: The tables below must be of the same size.

  // The functions described below are sampled at the four most significant

  // bits of x^2 + 8 / 256.

  // Normalized rate:

  // This table models the rate for a Laplacian source with given variance

  // when quantized with a uniform quantizer with given stepsize. The

  // closed form expression is:

  // Rn(x) = H(sqrt(r)) + sqrt(r)*[1 + H(r)/(1 - r)],

  // where r = exp(-sqrt(2) * x) and x = qpstep / sqrt(variance),

  // and H(x) is the binary entropy function.

  static const int rate_tab_q10[] = {

    65536, 6086, 5574, 5275, 5063, 4899, 4764, 4651, 4553, 4389, 4255, 4142,

    4044,  3958, 3881, 3811, 3748, 3635, 3538, 3453, 3376, 3307, 3244, 3186,

    3133,  3037, 2952, 2877, 2809, 2747, 2690, 2638, 2589, 2501, 2423, 2353,

    2290,  2232, 2179, 2130, 2084, 2001, 1928, 1862, 1802, 1748, 1698, 1651,

    1608,  1530, 1460, 1398, 1342, 1290, 1243, 1199, 1159, 1086, 1021, 963,

    911,   864,  821,  781,  745,  680,  623,  574,  530,  490,  455,  424,

    395,   345,  304,  269,  239,  213,  190,  171,  154,  126,  104,  87,

    73,    61,   52,   44,   38,   28,   21,   16,   12,   10,   8,    6,

    5,     3,    2,    1,    1,    1,    0,    0,

  };

  // Normalized distortion:

  // This table models the normalized distortion for a Laplacian source

  // with given variance when quantized with a uniform quantizer

  // with given stepsize. The closed form expression is:

  // Dn(x) = 1 - 1/sqrt(2) * x / sinh(x/sqrt(2))

  // where x = qpstep / sqrt(variance).

  // Note the actual distortion is Dn * variance.

  static const int dist_tab_q10[] = {

    0,    0,    1,    1,    1,    2,    2,    2,    3,    3,    4,    5,

    5,    6,    7,    7,    8,    9,    11,   12,   13,   15,   16,   17,

    18,   21,   24,   26,   29,   31,   34,   36,   39,   44,   49,   54,

    59,   64,   69,   73,   78,   88,   97,   106,  115,  124,  133,  142,

    151,  167,  184,  200,  215,  231,  245,  260,  274,  301,  327,  351,

    375,  397,  418,  439,  458,  495,  528,  559,  587,  613,  637,  659,

    680,  717,  749,  777,  801,  823,  842,  859,  874,  899,  919,  936,

    949,  960,  969,  977,  983,  994,  1001, 1006, 1010, 1013, 1015, 1017,

    1018, 1020, 1022, 1022, 1023, 1023, 1023, 1024,

  };

  static const int xsq_iq_q10[] = {

    0,      4,      8,      12,     16,     20,     24,     28,     32,

    40,     48,     56,     64,     72,     80,     88,     96,     112,

    128,    144,    160,    176,    192,    208,    224,    256,    288,

    320,    352,    384,    416,    448,    480,    544,    608,    672,

    736,    800,    864,    928,    992,    1120,   1248,   1376,   1504,

    1632,   1760,   1888,   2016,   2272,   2528,   2784,   3040,   3296,

    3552,   3808,   4064,   4576,   5088,   5600,   6112,   6624,   7136,

    7648,   8160,   9184,   10208,  11232,  12256,  13280,  14304,  15328,

    16352,  18400,  20448,  22496,  24544,  26592,  28640,  30688,  32736,

    36832,  40928,  45024,  49120,  53216,  57312,  61408,  65504,  73696,

    81888,  90080,  98272,  106464, 114656, 122848, 131040, 147424, 163808,

    180192, 196576, 212960, 229344, 245728,

  };

  const int tmp = (xsq_q10 >> 2) + 8;

  const int k = get_msb(tmp) - 3;

  const int xq = (k << 3) + ((tmp >> k) & 0x7);

  const int one_q10 = 1 << 10;

  const int a_q10 = ((xsq_q10 - xsq_iq_q10[xq]) << 10) >> (2 + k);

  const int b_q10 = one_q10 - a_q10;

  *r_q10 = (rate_tab_q10[xq] * b_q10 + rate_tab_q10[xq + 1] * a_q10) >> 10;

  *d_q10 = (dist_tab_q10[xq] * b_q10 + dist_tab_q10[xq + 1] * a_q10) >> 10;

}

void av1_model_rd_from_var_lapndz(int64_t var, unsigned int n_log2,

                                  unsigned int qstep, int *rate,

                                  int64_t *dist) {

  // This function models the rate and distortion for a Laplacian

  // source with given variance when quantized with a uniform quantizer

  // with given stepsize. The closed form expressions are in:

  // Hang and Chen, "Source Model for transform video coder and its

  // application - Part I: Fundamental Theory", IEEE Trans. Circ.

  // Sys. for Video Tech., April 1997.

  if (var == 0) {

    *rate = 0;

    *dist = 0;

  } else {

    int d_q10, r_q10;

    static const uint32_t MAX_XSQ_Q10 = 245727;

    const uint64_t xsq_q10_64 =

        (((uint64_t)qstep * qstep << (n_log2 + 10)) + (var >> 1)) / var;

    const int xsq_q10 = (int)AOMMIN(xsq_q10_64, MAX_XSQ_Q10);

    model_rd_norm(xsq_q10, &r_q10, &d_q10);

    *rate = ROUND_POWER_OF_TWO(r_q10 << n_log2, 10 - AV1_PROB_COST_SHIFT);

    *dist = (var * (int64_t)d_q10 + 512) >> 10;

  }

}

static double interp_cubic(const double *p, double x) {

  return p[1] + 0.5 * x *

                    (p[2] - p[0] +

                     x * (2.0 * p[0] - 5.0 * p[1] + 4.0 * p[2] - p[3] +

                          x * (3.0 * (p[1] - p[2]) + p[3] - p[0])));

}

/*

static double interp_bicubic(const double *p, int p_stride, double x,

                             double y) {

  double q[4];

  q[0] = interp_cubic(p, x);

  q[1] = interp_cubic(p + p_stride, x);

  q[2] = interp_cubic(p + 2 * p_stride, x);

  q[3] = interp_cubic(p + 3 * p_stride, x);

  return interp_cubic(q, y);

}

*/

static const uint8_t bsize_curvfit_model_cat_lookup[BLOCK_SIZES_ALL] = {

  0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 1, 1, 2, 2, 3, 3

};

static int sse_norm_curvfit_model_cat_lookup(double sse_norm) {

  return (sse_norm > 16.0);

}

// Models distortion by sse using a logistic function on

// l = log2(sse / q^2) as:

// dbysse = 16 / (1 + k exp(l + c))

static double get_dbysse_logistic(double l, double c, double k) {

  const double A = 16.0;

  const double dbysse = A / (1 + k * exp(l + c));

  return dbysse;

}

// Models rate using a clamped linear function on

// l = log2(sse / q^2) as:

// rate = max(0, a + b * l)

static double get_rate_clamplinear(double l, double a, double b) {

  const double rate = a + b * l;

  return (rate < 0 ? 0 : rate);

}

static const uint8_t bsize_surffit_model_cat_lookup[BLOCK_SIZES_ALL] = {

  0, 0, 0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 0, 0, 2, 2, 4, 4

};

static const double surffit_rate_params[9][4] = {

  {

      638.390212,

      2.253108,

      166.585650,

      -3.939401,

  },

  {

      5.256905,

      81.997240,

      -1.321771,

      17.694216,

  },

  {

      -74.193045,

      72.431868,

      -19.033152,

      15.407276,

  },

  {

      416.770113,

      14.794188,

      167.686830,

      -6.997756,

  },

  {

      378.511276,

      9.558376,

      154.658843,

      -6.635663,

  },

  {

      277.818787,

      4.413180,

      150.317637,

      -9.893038,

  },

  {

      142.212132,

      11.542038,

      94.393964,

      -5.518517,

  },

  {

      219.100256,

      4.007421,

      108.932852,

      -6.981310,

  },

  {

      222.261971,

      3.251049,

      95.972916,

      -5.609789,

  },

};

static const double surffit_dist_params[7] = { 1.475844,  4.328362, -5.680233,

                                               -0.500994, 0.554585, 4.839478,

                                               -0.695837 };

static void rate_surffit_model_params_lookup(BLOCK_SIZE bsize, double xm,

                                             double *rpar) {

  const int cat = bsize_surffit_model_cat_lookup[bsize];

  rpar[0] = surffit_rate_params[cat][0] + surffit_rate_params[cat][1] * xm;

  rpar[1] = surffit_rate_params[cat][2] + surffit_rate_params[cat][3] * xm;

}

static void dist_surffit_model_params_lookup(BLOCK_SIZE bsize, double xm,

                                             double *dpar) {

  (void)bsize;

  const double *params = surffit_dist_params;

  dpar[0] = params[0] + params[1] / (1 + exp((xm + params[2]) * params[3]));

  dpar[1] = params[4] + params[5] * exp(params[6] * xm);

}

void av1_model_rd_surffit(BLOCK_SIZE bsize, double sse_norm, double xm,

                          double yl, double *rate_f, double *distbysse_f) {

  (void)sse_norm;

  double rpar[2], dpar[2];

  rate_surffit_model_params_lookup(bsize, xm, rpar);

  dist_surffit_model_params_lookup(bsize, xm, dpar);