// # Changes: AVX2 vectorization of the ped-ped inner loop (8 floats per __m256, exp still scalar)
// # Predecessor: variant_float_inlining_SoA.cpp

#include "../headers/board_reduced_float.hpp"
#include "../headers/constants_float.hpp"
#include "../headers/pedestrian_reduced_float.hpp"

#include <immintrin.h> // avx2

#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h>
#include <random>
#include <tuple>
#include <vector>

#define SEED 42
#define BOARD_WIDTH 10.0f
#define BOARD_LENGTH 50.0f
#define WALL_EPS 1e-3f
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999f

#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif

#ifndef BENCHMARK
#define BENCHMARK 0
#endif

using namespace std;

// same SoA arrays as the predecessor, but we pad to multiple of 8 so the avx loop is clean
vector<float> pos_x, pos_y;
vector<float> sb_sq;
vector<float> sb_e_x, sb_e_y;
vector<float> e_x, e_y;
vector<float> curr_vel_x, curr_vel_y;
vector<float> w_x, w_y;
vector<float> desired_v0;
vector<float> v_max;
vector<float> destination_x, destination_y;
vector<int> color;

Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
  random_device rd;
  mt19937 gen(rd());
#else
  mt19937 gen(SEED);
#endif

  normal_distribution<float> velocity_gen(v0_mean, v0_std_dev);
  uniform_real_distribution<float> y_gen(0.3, BOARD_WIDTH - 0.3);
  uniform_real_distribution<float> x_gen_left(2.0, BOARD_LENGTH / 2.0);
  uniform_real_distribution<float> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);

  const int n_p_pad = (n_p + 7) & ~7; // round up to a multiple of 8 for avx float lanes

  pos_x.resize(n_p_pad);
  pos_y.resize(n_p_pad);
  sb_sq.resize(n_p_pad);
  sb_e_x.resize(n_p_pad);
  sb_e_y.resize(n_p_pad);
  e_x.resize(n_p_pad);
  e_y.resize(n_p_pad);
  curr_vel_x.resize(n_p_pad);
  curr_vel_y.resize(n_p_pad);
  w_x.resize(n_p_pad);
  w_y.resize(n_p_pad);
  desired_v0.resize(n_p_pad);
  v_max.resize(n_p_pad);
  destination_x.resize(n_p_pad);
  destination_y.resize(n_p_pad);
  color.resize(n_p_pad);

  int n_p_half = n_p / 2;

  for (int i = 0; i < n_p_half; i++) {
    float x = x_gen_left(gen);
    float y = y_gen(gen);

    float dest_x = BOARD_LENGTH + 30.0; // renamed to avoid shadowing destination_x[]
    float dest_y = y;

    float init_e_x = dest_x - x;
    float init_e_y = dest_y - y;
    float init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
    float init_e_unit_x = init_e_x / init_e_norm;
    float init_e_unit_y = init_e_y / init_e_norm;

    float d_v0;
    do {
      d_v0 = velocity_gen(gen);
    } while (d_v0 <= 0.1);

    float v_m = 1.3 * d_v0;

    color[i] = 0;
    pos_x[i] = x;
    pos_y[i] = y;
    e_x[i] = init_e_unit_x;
    e_y[i] = init_e_unit_y;
    v_max[i] = v_m;
    desired_v0[i] = d_v0;
    destination_x[i] = dest_x;
    destination_y[i] = dest_y;

    w_x[i] = 0.0f;
    w_y[i] = 0.0f;
    curr_vel_x[i] = 0.0f;
    curr_vel_y[i] = 0.0f;
    sb_sq[i] = 0.0f;
    sb_e_x[i] = 0.0f;
    sb_e_y[i] = 0.0f;
  }

  for (int i = n_p_half; i < n_p; i++) {
    float x = x_gen_right(gen);
    float y = y_gen(gen);

    float dest_x = -30;
    float dest_y = y;

    float init_e_x = dest_x - x;
    float init_e_y = dest_y - y;
    float init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
    float init_e_unit_x = init_e_x / init_e_norm;
    float init_e_unit_y = init_e_y / init_e_norm;

    float d_v0;
    do {
      d_v0 = velocity_gen(gen);
    } while (d_v0 <= 0.1);

    float v_m = 1.3 * d_v0;

    color[i] = 1;
    pos_x[i] = x;
    pos_y[i] = y;
    e_x[i] = init_e_unit_x;
    e_y[i] = init_e_unit_y;
    v_max[i] = v_m;
    desired_v0[i] = d_v0;
    destination_x[i] = dest_x;
    destination_y[i] = dest_y;

    w_x[i] = 0.0f;
    w_y[i] = 0.0f;
    curr_vel_x[i] = 0.0f;
    curr_vel_y[i] = 0.0f;
    sb_sq[i] = 0.0f;
    sb_e_x[i] = 0.0f;
    sb_e_y[i] = 0.0f;
  }

  // padding lanes: park them far away, zero everything else.
  // exp(very negative) is roughly 0 and the active mask zeroes their contribution anyway.
  for (int j = n_p; j < n_p_pad; j++) {
    pos_x[j] = 1e9f;
    pos_y[j] = 1e9f;
    sb_sq[j] = 0.0f;
    sb_e_x[j] = 0.0f;
    sb_e_y[j] = 0.0f;
  }
  return nullptr;
}

Board init_board_without_obstacles() { return Board(BOARD_LENGTH, BOARD_WIDTH, 0, nullptr); }

int run_simulation(Pedestrian *pedestrians, Board &board, int n_p, int n_iter, const char *dump_path) {
  (void)pedestrians;
#if BENCHMARK
  (void)dump_path;
#endif

#if !BENCHMARK
  const int dump_interval = 1;

  vector<tuple<int, int, float, float, float, float, int>> samples;

  if (dump_path) {
    samples.reserve(static_cast<size_t>(n_iter / dump_interval + 1) * n_p);

    for (int i = 0; i < n_p; i++) {
      samples.emplace_back(0, i, pos_x[i], pos_y[i], e_x[i], e_y[i], color[i]);
    }
  }
#endif

  const int n_p_pad = (n_p + 7) & ~7;

  // {0,1,2,3,4,5,6,7} so we can build per-iter j indices as (j + lane_off)
  alignas(32) const float lane_offset_arr[8] = {0.0f, 1.0f, 2.0f, 3.0f, 4.0f, 5.0f, 6.0f, 7.0f};
  const __m256 lane_off = _mm256_load_ps(lane_offset_arr);

  // constants broadcast to all 8 lanes once
  const __m256 v_neg_v0_div_2s = _mm256_set1_ps(NEG_V0_AB_div_TWO_SIGMA);
  const __m256 v_neg_2s_inv = _mm256_set1_ps(NEG_TWO_SIGMA_INV);
  const __m256 v_cos_phi_sq = _mm256_set1_ps(cos_phi_sq);
  const __m256 v_dt_neg = _mm256_set1_ps(dt_neg);
  const __m256 v_c_neg_dt = _mm256_set1_ps(c_neg_times_dt);
  const __m256 v_zero = _mm256_setzero_ps();
  const __m256 v_one = _mm256_set1_ps(1.0f);
  const __m256 v_eps = _mm256_set1_ps(EPS);
  const __m256 v_eps_sq = _mm256_set1_ps(EPS_SQ);
  const __m256 v_np = _mm256_set1_ps((float)n_p);

  for (int t = 0; t < n_iter; t++) {

    for (int i = 0; i < n_p; i++) {

      float desired_velocity_x = e_x[i] * desired_v0[i];
      float desired_velocity_y = e_y[i] * desired_v0[i];

      float f_alpha_dt_x = (desired_velocity_x - curr_vel_x[i]) * dt_times_tau_alpha_inv;
      float f_alpha_dt_y = (desired_velocity_y - curr_vel_y[i]) * dt_times_tau_alpha_inv;

      // i is fixed for the inner loops, broadcast its fields once
      const __m256 pix = _mm256_set1_ps(pos_x[i]);
      const __m256 piy = _mm256_set1_ps(pos_y[i]);
      const __m256 eix = _mm256_set1_ps(e_x[i]);
      const __m256 eiy = _mm256_set1_ps(e_y[i]);
      const __m256 v_i = _mm256_set1_ps((float)i);

      __m256 acc_x = _mm256_setzero_ps();
      __m256 acc_y = _mm256_setzero_ps();

      for (int j = 0; j < n_p_pad; j += 8) {
        // 8 lanes at once, lane k maps to pedestrian j+k
        __m256 j_idx = _mm256_add_ps(_mm256_set1_ps((float)j), lane_off);

        // active = (j+k != i) AND (j+k < n_p), zero in lanes we wanna skip
        __m256 m_neq_i = _mm256_cmp_ps(j_idx, v_i, _CMP_NEQ_OQ);
        __m256 m_in_range = _mm256_cmp_ps(j_idx, v_np, _CMP_LT_OQ);
        __m256 active = _mm256_and_ps(m_neq_i, m_in_range);

        // j-side loads, SoA is contiguous. loadu because std::vector only guarantees 16B align
        __m256 pjx = _mm256_loadu_ps(&pos_x[j]);
        __m256 pjy = _mm256_loadu_ps(&pos_y[j]);
        __m256 sbe_jx = _mm256_loadu_ps(&sb_e_x[j]);
        __m256 sbe_jy = _mm256_loadu_ps(&sb_e_y[j]);
        __m256 sb_jsq = _mm256_loadu_ps(&sb_sq[j]);

        // r_ab = pos_i - pos_j ; |r_ab| with the EPS clamp the scalar version does
        __m256 r_ab_x = _mm256_sub_ps(pix, pjx);
        __m256 r_ab_y = _mm256_sub_ps(piy, pjy);
        __m256 r_ab_n2 = _mm256_fmadd_ps(r_ab_x, r_ab_x, _mm256_mul_ps(r_ab_y, r_ab_y));
        __m256 r_ab_n = _mm256_sqrt_ps(r_ab_n2);
        r_ab_n = _mm256_max_ps(r_ab_n, v_eps);

        // r_ab2 = r_ab - sb_e_j ; |r_ab2| also clamped
        __m256 r_ab2_x = _mm256_sub_ps(r_ab_x, sbe_jx);
        __m256 r_ab2_y = _mm256_sub_ps(r_ab_y, sbe_jy);
        __m256 r_ab2_n2 = _mm256_fmadd_ps(r_ab2_x, r_ab2_x, _mm256_mul_ps(r_ab2_y, r_ab2_y));
        __m256 r_ab2_n = _mm256_sqrt_ps(r_ab2_n2);
        r_ab2_n = _mm256_max_ps(r_ab2_n, v_eps);

        // 2b = sqrt((|r_ab| + |r_ab2|)^2 - sb_sq_j) ; clamp the inside with EPS_SQ
        __m256 r_sum = _mm256_add_ps(r_ab_n, r_ab2_n);
        __m256 two_b_sq = _mm256_fmsub_ps(r_sum, r_sum, sb_jsq);
        two_b_sq = _mm256_max_ps(two_b_sq, v_eps_sq);
        __m256 two_b = _mm256_sqrt_ps(two_b_sq);

        // exp scalar fallback. manually unrolled, otherwise gcc keeps it as a loop with
        // one expf call and serialises all 8 (the double avx2 with 4 iters does get unrolled, the 8 here doesn't).
        __m256 e_arg = _mm256_mul_ps(two_b, v_neg_2s_inv);
        alignas(32) float tmp_arg[8], tmp_val[8];
        _mm256_store_ps(tmp_arg, e_arg);
        tmp_val[0] = expf(tmp_arg[0]);
        tmp_val[1] = expf(tmp_arg[1]);
        tmp_val[2] = expf(tmp_arg[2]);
        tmp_val[3] = expf(tmp_arg[3]);
        tmp_val[4] = expf(tmp_arg[4]);
        tmp_val[5] = expf(tmp_arg[5]);
        tmp_val[6] = expf(tmp_arg[6]);
        tmp_val[7] = expf(tmp_arg[7]);
        __m256 e_val = _mm256_load_ps(tmp_val);

        // smc = (r_sum * NEG_V0_AB_div_TWO_SIGMA * e_val) / (two_b * r_ab_n * r_ab2_n)
        // i==j and padding lanes collapse the denom, so we swap in 1.0 there to keep smc finite.
        // the AND with active below zeroes those lanes anyway.
        __m256 numer = _mm256_mul_ps(_mm256_mul_ps(r_sum, v_neg_v0_div_2s), e_val);
        __m256 denom = _mm256_mul_ps(_mm256_mul_ps(two_b, r_ab_n), r_ab2_n);
        __m256 denom_safe = _mm256_blendv_ps(v_one, denom, active);
        __m256 smc = _mm256_div_ps(numer, denom_safe);

        __m256 sm_r_ab = _mm256_mul_ps(smc, r_ab2_n);
        __m256 sm_r_ab2 = _mm256_mul_ps(smc, r_ab_n);

        // scalar: f_x = r_ab_x * sm_r_ab + r_ab2_x * sm_r_ab2
        __m256 f_x = _mm256_fmadd_ps(r_ab2_x, sm_r_ab2, _mm256_mul_ps(r_ab_x, sm_r_ab));
        __m256 f_y = _mm256_fmadd_ps(r_ab2_y, sm_r_ab2, _mm256_mul_ps(r_ab_y, sm_r_ab));

        // float w_val: default dt_neg, switch to c_neg_times_dt when
        //(e_dot_f < 0 AND e_dot_f_sq > f_norm_sq * cos_phi_sq).
        // this is the DeMorgan of the scalar's if (e_dot_f >= 0 || e_dot_f_sq <= rhs)
        __m256 f_norm_sq = _mm256_fmadd_ps(f_x, f_x, _mm256_mul_ps(f_y, f_y));
        __m256 rhs = _mm256_mul_ps(f_norm_sq, v_cos_phi_sq);
        __m256 e_dot_f = _mm256_fmadd_ps(eix, f_x, _mm256_mul_ps(eiy, f_y));
        __m256 e_dot_f_sq = _mm256_mul_ps(e_dot_f, e_dot_f);

        __m256 c1 = _mm256_cmp_ps(e_dot_f, v_zero, _CMP_LT_OQ);
        __m256 c2 = _mm256_cmp_ps(e_dot_f_sq, rhs, _CMP_GT_OQ);
        __m256 cond = _mm256_and_ps(c1, c2);
        __m256 w_val = _mm256_blendv_ps(v_dt_neg, v_c_neg_dt, cond);

        // mask out i==j lane and padding before accumulating.
        // AND with all-zeros = 0, AND with all-ones passes through, cheaper than blendv here.
        __m256 f_x_safe = _mm256_and_ps(f_x, active);
        __m256 f_y_safe = _mm256_and_ps(f_y, active);
        acc_x = _mm256_fmadd_ps(f_x_safe, w_val, acc_x);
        acc_y = _mm256_fmadd_ps(f_y_safe, w_val, acc_y);
      }

      // horizontal sum of acc_x and acc_y at the same time
      __m256 hsum = _mm256_hadd_ps(acc_x, acc_y);
      __m128 hsum_lo = _mm256_castps256_ps128(hsum);
      __m128 hsum_hi = _mm256_extractf128_ps(hsum, 1);
      __m128 sum4 = _mm_add_ps(hsum_lo, hsum_hi);
      sum4 = _mm_hadd_ps(sum4, sum4);
      alignas(16) float sum_out[4];
      _mm_store_ps(sum_out, sum4);
      f_alpha_dt_x += sum_out[0];
      f_alpha_dt_y += sum_out[1];

      // obstacle loop kept scalar, board.n_obstacles is 0 in this setup anyway
      for (int k = 0; k < board.n_obstacles; k++) {

        float v1_x = pos_x[i] - board.obstacles[k].start_x;
        float v1_y = pos_y[i] - board.obstacles[k].start_y;
        float v2_x = board.obstacles[k].obstacle_v_x;
        float v2_y = board.obstacles[k].obstacle_v_y;

        float projection = (v1_x * v2_x + v1_y * v2_y) * board.obstacles[k].length_sq_inv;

        if (projection < 0.0)
          projection = 0.0;
        else if (projection > 1.0)
          projection = 1.0;

        float r_aB_x = pos_x[i] - (board.obstacles[k].start_x + board.obstacles[k].obstacle_v_x * projection);
        float r_aB_y = pos_y[i] - (board.obstacles[k].start_y + board.obstacles[k].obstacle_v_y * projection);

        float r_aB_norm = sqrt(r_aB_x * r_aB_x + r_aB_y * r_aB_y);
        r_aB_norm = r_aB_norm > EPS ? r_aB_norm : EPS;

        float scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
        float f_alpha_B_neg_x = r_aB_x * scalar_mult;
        float f_alpha_B_neg_y = r_aB_y * scalar_mult;

        float w_val;

        float e_dot_f = (f_alpha_B_neg_y == 0) ? 0 : (f_alpha_B_neg_y < 0 ? -e_y[i] : e_y[i]);

        if (e_dot_f >= cos_phi)
          w_val = dt_neg;
        else
          w_val = c_neg_times_dt;

        float f_alpha_B_dt_x = f_alpha_B_neg_x * w_val;
        float f_alpha_B_dt_y = f_alpha_B_neg_y * w_val;

        f_alpha_dt_x += f_alpha_B_dt_x;
        f_alpha_dt_y += f_alpha_B_dt_y;
      }

      w_x[i] += f_alpha_dt_x;
      w_y[i] += f_alpha_dt_y;
    }

    // position update loop stays scalar, same as the double AVX2 variant does
    for (int i = 0; i < n_p; i++) {

      float w_norm = sqrt(w_x[i] * w_x[i] + w_y[i] * w_y[i]);
      float w_norm2 = w_norm > EPS ? w_norm : EPS;
      float correction_factor = min(1.0f, v_max[i] / w_norm2);

      curr_vel_x[i] = w_x[i] * correction_factor;
      curr_vel_y[i] = w_y[i] * correction_factor;

      pos_x[i] = pos_x[i] + curr_vel_x[i] * dt;
      pos_y[i] = pos_y[i] + curr_vel_y[i] * dt;

      if (color[i] == 0 && pos_x[i] > (BOARD_LENGTH - 1.5)) {
        pos_x[i] = 1.0;
        destination_y[i] = pos_y[i];
        w_x[i] = desired_v0[i];
        w_y[i] = 0.0;
        curr_vel_x[i] = w_x[i];
        curr_vel_y[i] = w_y[i];
      }
      if (color[i] == 1 && pos_x[i] < 1.5) {
        pos_x[i] = BOARD_LENGTH - 1.0;
        destination_y[i] = pos_y[i];
        w_x[i] = -desired_v0[i];
        w_y[i] = 0.0;
        curr_vel_x[i] = w_x[i];
        curr_vel_y[i] = w_y[i];
      }

      pos_y[i] = clamp(pos_y[i], WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);

      float ex = destination_x[i] - pos_x[i];
      float ey = destination_y[i] - pos_y[i];

      float e_norm = sqrt(ex * ex + ey * ey);
      float e_norm2 = e_norm > EPS ? e_norm : EPS;
      float e_norm_inv = 1.0 / e_norm2;

      e_x[i] = ex * e_norm_inv;
      e_y[i] = ey * e_norm_inv;

      float velocity_norm_sq = curr_vel_x[i] * curr_vel_x[i] + curr_vel_y[i] * curr_vel_y[i];
      float velocity_norm = sqrt(velocity_norm_sq);

      sb_sq[i] = velocity_norm_sq * delta_t_sq;
      sb_e_x[i] = e_x[i] * (velocity_norm * delta_t);
      sb_e_y[i] = e_y[i] * (velocity_norm * delta_t);

#if !BENCHMARK
      if (dump_path && (t % dump_interval == 0)) {
        samples.emplace_back(t + 1, i, pos_x[i], pos_y[i], e_x[i], e_y[i], color[i]);
      }
#endif
    }
  }

#if !BENCHMARK
  if (dump_path) {
    ofstream out(dump_path);
    out << "time,id,x,y,p.e.x,p.e.y,color\n";

    for (auto &[t, id, x, y, e_x, e_y, c] : samples) {
      out << t << ',' << id << ',' << x << ',' << y << ',' << e_x << ',' << e_y << ',' << c << '\n';
    }
  }
#endif

  return 0;
}