/*

 * 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 <limits.h>

#include <math.h>

#include <stdio.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 "aom_ports/aom_once.h"

#include "av1/common/common.h"

#include "av1/common/entropy.h"

#include "av1/common/entropymode.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/cost.h"

#include "av1/encoder/encodemv.h"

#include "av1/encoder/encoder.h"

#include "av1/encoder/nonrd_opt.h"

#include "av1/encoder/ratectrl.h"

#include "av1/encoder/rd.h"

#include "config/aom_config.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);

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

    av1_cost_tokens_from_cdf(mode_costs->spatial_pred_cost[i],

                             fc->seg.spatial_pred_seg_cdf[i], NULL);

  }

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

    av1_cost_tokens_from_cdf(mode_costs->tmp_pred_cost[i], fc->seg.pred_cdf[i],

                             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);

    }

  }

}

#if !CONFIG_REALTIME_ONLY

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);

}

#endif  // !CONFIG_REALTIME_ONLY

// 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);

  }

}

static void 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);

}

void av1_init_me_luts(void) { aom_once(init_me_luts); }

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 + (0.0015 * (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 + (0.0015 * (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 + (0.0015 * (double)qindex);

}

int av1_compute_rd_mult_based_on_qindex(aom_bit_depth_t bit_depth,

                                        FRAME_UPDATE_TYPE update_type,

                                        int qindex, aom_tune_metric tuning) {

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

  int64_t rdmult = q * q;

  if (update_type == KF_UPDATE) {

    double def_rd_q_mult = def_kf_rd_multiplier(q);

    rdmult = (int64_t)((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(q);

    rdmult = (int64_t)((double)rdmult * def_rd_q_mult);

  } else {

    double def_rd_q_mult = def_inter_rd_multiplier(q);

    rdmult = (int64_t)((double)rdmult * def_rd_q_mult);

  }

  if (tuning == AOM_TUNE_IQ) {

    // Further multiply rdmult (by up to 200/128 = 1.5625) to improve image

    // quality. The most noticeable effect is a mild bias towards choosing

    // larger transform sizes (e.g. one 16x16 transform instead of 4 8x8

    // transforms).

    // For very high qindexes, start progressively reducing the weight towards

    // unity (128/128), as transforms are large enough and making them even

    // larger actually harms subjective quality and SSIMULACRA 2 scores.

    // This weight part of the equation was determined by iteratively increasing

    // weight on CID22 and Daala's subset1, and observing its effects on visual

    // quality and SSIMULACRA 2 scores along the usable (0-100) range.

    // The ramp-down part of the equation was determined by choosing a fixed

    // initial qindex point [qindex 159 = (255 - 159) * 3 / 4] where SSIMULACRA

    // 2 scores for encodes with qindexes greater than 159 scored at or above

    // their equivalents with no rdmult adjustment.

    const int weight = clamp(((255 - qindex) * 3) / 4, 0, 72) + 128;

    rdmult = (int64_t)((double)rdmult * weight / 128.0);

  }

  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 ? (int)AOMMIN(rdmult, INT_MAX) : 1;

}

int av1_compute_rd_mult(const int qindex, const aom_bit_depth_t bit_depth,

                        const FRAME_UPDATE_TYPE update_type,

                        const int layer_depth, const int boost_index,

                        const FRAME_TYPE frame_type,

                        const int use_fixed_qp_offsets,

                        const int is_stat_consumption_stage,

                        const aom_tune_metric tuning) {

  int64_t rdmult = av1_compute_rd_mult_based_on_qindex(bit_depth, update_type,

                                                       qindex, tuning);

  if (is_stat_consumption_stage && !use_fixed_qp_offsets &&

      (frame_type != KEY_FRAME)) {

    // Layer depth adjustment

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

    // ARF boost adjustment

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

  }

  return rdmult > 0 ? (int)AOMMIN(rdmult, INT_MAX) : 1;

}

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;

}

#if !CONFIG_REALTIME_ONLY

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

  assert(beta > 0.0);

  const AV1_COMMON *cm = &cpi->common;

  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);

  const FRAME_TYPE frame_type = cm->current_frame.frame_type;

  const int qindex_rdmult = cm->quant_params.base_qindex;

  return (int)(av1_compute_rd_mult(

                   qindex_rdmult, cm->seq_params->bit_depth,

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

                   layer_depth, boost_index, frame_type,

                   cpi->oxcf.q_cfg.use_fixed_qp_offsets,

                   is_stat_consumption_stage(cpi), cpi->oxcf.tune_cfg.tuning) /

               beta);

}

#endif  // !CONFIG_REALTIME_ONLY

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 use_nonrd_pick_mode) {

  int i, bsize, segment_id;

  THR_MODES mode_indices[RTC_REFS * RTC_MODES] = { 0 };

  int num_modes_count = use_nonrd_pick_mode ? 0 : MAX_MODES;

  if (use_nonrd_pick_mode) {

    for (int r_idx = 0; r_idx < RTC_REFS; r_idx++) {

      const MV_REFERENCE_FRAME ref = real_time_ref_combos[r_idx][0];

      if (ref != INTRA_FRAME) {

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

          mode_indices[num_modes_count++] =

              mode_idx[ref][mode_offset(inter_mode_list[i])];

      } else {

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

          mode_indices[num_modes_count++] =

              mode_idx[ref][mode_offset(intra_mode_list[i])];

      }

    }

  }

  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 < num_modes_count; ++i) {

        const int mode_index = use_nonrd_pick_mode ? mode_indices[i] : i;

        rd->threshes[segment_id][bsize][mode_index] =

            rd->thresh_mult[mode_index] < thresh_max

                ? rd->thresh_mult[mode_index] * 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);

}

// Decide whether we want to update the mode entropy cost for the current frame.

// The logit is currently inherited from selective_disable_cdf_rtc.

static inline int should_force_mode_cost_update(const AV1_COMP *cpi) {

  const REAL_TIME_SPEED_FEATURES *const rt_sf = &cpi->sf.rt_sf;

  if (!rt_sf->frame_level_mode_cost_update) {

    return false;

  }

  if (cpi->oxcf.algo_cfg.cdf_update_mode == 2) {

    return cpi->frames_since_last_update == 1;

  } else if (cpi->oxcf.algo_cfg.cdf_update_mode == 1) {

    if (cpi->svc.number_spatial_layers == 1 &&

        cpi->svc.number_temporal_layers == 1) {

      const AV1_COMMON *const cm = &cpi->common;

      const RATE_CONTROL *const rc = &cpi->rc;

      return frame_is_intra_only(cm) || is_frame_resize_pending(cpi) ||

             rc->high_source_sad || rc->frames_since_key < 10 ||

             cpi->cyclic_refresh->counter_encode_maxq_scene_change < 10 ||

             cm->current_frame.frame_number % 8 == 0;

    } else if (cpi->svc.number_temporal_layers > 1) {

      return cpi->svc.temporal_layer_id != cpi->svc.number_temporal_layers - 1;

    }

  }

  return false;

}

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;

  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);

  const FRAME_TYPE frame_type = cm->current_frame.frame_type;

  const int qindex_rdmult =

      cm->quant_params.base_qindex + cm->quant_params.y_dc_delta_q;

  rd->RDMULT = av1_compute_rd_mult(

      qindex_rdmult, cm->seq_params->bit_depth,

      cpi->ppi->gf_group.update_type[cpi->gf_frame_index], layer_depth,

      boost_index, frame_type, cpi->oxcf.q_cfg.use_fixed_qp_offsets,

      is_stat_consumption_stage(cpi), cpi->oxcf.tune_cfg.tuning);

#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, cpi->sf.rt_sf.use_nonrd_pick_mode);

  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 (should_force_mode_cost_update(cpi) ||

      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 (av1_need_dv_costs(cpi)) {

    if (cpi->td.dv_costs_alloc == NULL) {

      CHECK_MEM_ERROR(

          cm, cpi->td.dv_costs_alloc,

          (IntraBCMVCosts *)aom_malloc(sizeof(*cpi->td.dv_costs_alloc)));

      cpi->td.mb.dv_costs = cpi->td.dv_costs_alloc;

    }

    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