#pragma once
#include <cmath>
#include <new>

#ifdef __x86_64__
#include "immintrin.h"
#endif

//
// $\frac{1}{\tau_{\alpha}}$; $\tau_{\alpha} = 0.5s$
//
const double tau_alpha_inv = 2.0;

// $V^0_{\alpha \beta}$
const double V0_AB = 2.1;

// $\sigma$
const double SIGMA = 0.3;

//
// $\frac{-1}{2\sigma}$
//
const double NEG_TWO_SIGMA_INV = -1.0 / (2 * SIGMA);

//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}$
//
const double NEG_V0_AB_div_TWO_SIGMA = V0_AB * NEG_TWO_SIGMA_INV;

// $U^0_{\alpha B}$
const double U0_AB = 10.0;

// $R$
const double R = 0.2;

//
// $\frac{-1}{R}$
//
const double NEG_R_INV = -1.0 / R;

//
// $\frac{-U^0_{\alpha B}}{R}$
//
const double NEG_U0_AB_div_R = -U0_AB / R;

// $-c$
const double c_neg = -0.5;

// $\varphi$
const double phi = 100.0 / 180.0 * M_PI;

// $cos(\varphi)$
const double cos_phi = cos(phi);

//
// $\frac{1}{cos(\varphi)}$
//
const double cos_phi_inv = 1 / cos(phi);

// $<v^0>$
const double v0_mean = 1.34;

// $\sqrt{\theta}$
const double v0_std_dev = 0.26;

// $\varDelta_{t}$
const double delta_t = 2;

// $\varDelta_{t}^2$
const double delta_t_sq = delta_t * delta_t;

// $dt$
const double dt = 0.02;

// $-dt$
const double dt_neg = -dt;

// $-c \cdot dt$
const double c_neg_times_dt = c_neg * dt;

//
// $\frac{1}{\tau_{\alpha}} \cdot dt$
//
const double dt_times_tau_alpha_inv = dt * tau_alpha_inv;

const double cost_add = 1;
const double cost_mult = 1;
const double cost_div = 1;

// https://acl.inf.ethz.ch/teaching/fastcode/knowledgebase/#:~:text=How%20do%20exp(x)%2C%20sin(x)%2C%20etc.%20count%20in%20the%20flopcount%20of%20an%20algorithm%3F
const double cost_exp = 30;

// -O3 maps each sqrt() call to an instruction
const double cost_sqrt = 1;

// Numerical tolerance used to avoid division by zero and unstable operations
// when distances or norms are extremely small.
const double EPS = 1e-9;

// Squared numerical tolerance
const double EPS_SQ = EPS * EPS;

#ifdef __AVX512F__
const __m512d LN2_VEC = _mm512_set1_pd(log(2));
const __m512d ZERO_VEC = _mm512_setzero_pd();
const __m512d NEG_TWO_SIGMA_INV_VEC = _mm512_set1_pd(NEG_TWO_SIGMA_INV);
const __m512d NEG_V0_AB_DIV_TWO_SIGMA_VEC = _mm512_set1_pd(NEG_V0_AB_div_TWO_SIGMA);
const __m512d c_neg_times_dt_vec = _mm512_set1_pd(c_neg_times_dt);
const __m512d cos_phi_inv_vec = _mm512_set1_pd(cos_phi_inv);
const __m512d dt_neg_vec = _mm512_set1_pd(dt_neg);
#endif

// Cutoff for pedestrian-pedestrian repulsion
const double CUTOFF = 12.0;
const double CUTOFF_SQ = CUTOFF * CUTOFF;

const double cos_phi_sq = cos_phi * cos_phi;

const size_t CACHE_BLOCK_SIZE = std::hardware_destructive_interference_size;

const double c0_scalar = 1.0 / 1;
const double c1_scalar = 1.0 / 1;
const double c2_scalar = 1.0 / 2;
const double c3_scalar = 1.0 / 6;
const double c4_scalar = 1.0 / 24;
const double c5_scalar = 1.0 / 120;
const double c6_scalar = 1.0 / 720;
const double c7_scalar = 1.0 / 5040;
const double c8_scalar = 1.0 / 40320;
const double c9_scalar = 1.0 / 362880;
const double c10_scalar = 1.0 / 3628800;
const double c11_scalar = 1.0 / 39916800;
const double c12_scalar = 1.0 / 479001600;
const double c13_scalar = 1.0 / 6227020800;