admin/263-0007-00L-Advanced-Systems-Lab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Clean up

Browse Source
This commit is contained in:
[Quy Anh] «Elliot» Nguyen
2026-06-18 22:33:37 +02:00
parent 0ff7e829de
commit be263a947a
9 changed files with 2 additions and 3250 deletions
Download Patch File Download Diff File Expand all files Collapse all files
variants/variant_AVX512_1_flopcount.cpp
-568
View File
@@ -1,568 +0,0 @@
// # This file attempts to use AVX-512 intrinsics to speed up computation.
// # Predecessor: variant_inlining_7.cpp
#ifdef __AVX512F__
#include "../headers/board_reduced.hpp"
#include "../headers/constants.hpp"
#include "../headers/pedestrian_reduced.hpp"
#include "immintrin.h"
#include "sleef.h"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <immintrin.h>
#include <iostream>
#include <math.h>
#include <random>
#include <tuple>
#include <vector>
#define SEED 42
#define BOARD_WIDTH 10.0
#define BOARD_LENGTH 50.0
#define BOARD_LENGTH_MINUS_ONE BOARD_LENGTH - 1.0f
#define BOARD_LENGTH_MINUS_ONE_POINT_FIVE BOARD_LENGTH - 1.5f
#define WALL_EPS 1e-3
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999
#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif
#ifndef BENCHMARK
#define BENCHMARK 0
#endif
using namespace std;
Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
random_device rd;
mt19937 gen(rd());
#else
mt19937 gen(SEED);
#endif
normal_distribution<double> velocity_gen(v0_mean, v0_std_dev);
uniform_real_distribution<double> y_gen(0.3, BOARD_WIDTH - 0.3);
uniform_real_distribution<double> x_gen_left(2.0, BOARD_LENGTH / 2.0);
uniform_real_distribution<double> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);
Pedestrian *P = new Pedestrian[n_p];
int n_p_half = n_p / 2;
for (int i = 0; i < n_p_half; i++) {
double x = x_gen_left(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = BOARD_LENGTH + 30.0;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(0, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
for (int i = n_p_half; i < n_p; i++) {
double x = x_gen_right(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = -30;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(1, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
return P;
}
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) {
#if BENCHMARK
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
vector<tuple<int, int, double, double, double, double, 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++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
}
#endif
// # ADDs: n_iter * n_p * 4 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 / (ceil(((double) (n_p - 7)) / 8))) * 7 * 14 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 - 1 / (ceil(((double) (n_p - 7)) / 8))) * 224 +
// # n_iter * n_p * (n_p - floor((double) n_p / 8) * 8) * 14 +
// # n_iter * n_p * board.n_obstacles * 12 +
// # n_iter * n_p * 7
// # MULTs: n_iter * n_p * 4 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 / (ceil(((double) (n_p - 7)) / 8))) * 7 * 24 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 - 1 / (ceil(((double) (n_p - 7)) / 8))) * 352 +
// # n_iter * n_p * (n_p - floor((double) n_p / 8) * 8) * 24 +
// # n_iter * n_p * board.n_obstacles * 19 +
// # n_iter * n_p * 17
// # DIVs: n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 / (ceil(((double) (n_p - 7)) / 8))) * 7 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 - 1 / (ceil(((double) (n_p - 7)) / 8))) * 8 +
// # n_iter * n_p * (n_p - floor((double) n_p / 8) * 8) +
// # n_iter * n_p * board.n_obstacles +
// # n_iter * n_p * 2
// # SQRTs: n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 / (ceil(((double) (n_p - 7)) / 8))) * 7 * 3 +
// # n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 - 1 / (ceil(((double) (n_p - 7)) / 8))) * 24 +
// # n_iter * n_p * (n_p - floor((double) n_p / 8) * 8) * 3 +
// # n_iter * n_p * board.n_obstacles +
// # n_iter * n_p * 3
// # EXPs: n_iter * n_p * ceil(((double) (n_p - 7)) / 8) * (1 / (ceil(((double) (n_p - 7)) / 8))) * 7 +
// # n_iter * n_p * (n_p - floor((double) n_p / 8) * 8) +
// # n_iter * n_p * board.n_obstacles
for (int t = 0; t < n_iter; t++) {
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 MULTs
double desired_velocity_x = p.e_x * p.desired_v0;
double desired_velocity_y = p.e_y * p.desired_v0;
// # 2 ADDs, 2 MULTs
double f_alpha_dt_x = (desired_velocity_x - p.curr_vel_x) * dt_times_tau_alpha_inv;
double f_alpha_dt_y = (desired_velocity_y - p.curr_vel_y) * dt_times_tau_alpha_inv;
__m512d desired_velocity_x_vec = _mm512_set1_pd(desired_velocity_x);
__m512d desired_velocity_y_vec = _mm512_set1_pd(desired_velocity_y);
__m512d f_alpha_dt_x_vec = _mm512_set1_pd(f_alpha_dt_x);
__m512d f_alpha_dt_y_vec = _mm512_set1_pd(f_alpha_dt_y);
__m512d alpha_curr_pos_x_vec = _mm512_set1_pd(p.curr_pos_x);
__m512d alpha_curr_pos_y_vec = _mm512_set1_pd(p.curr_pos_y);
__m512d alpha_e_x_vec = _mm512_set1_pd(p.e_x);
__m512d alpha_e_y_vec = _mm512_set1_pd(p.e_y);
int j;
// # ############################################################################################################################################################################################
for (j = 0; j < n_p - 7; j += 8) {
if (j <= i && i <= j + 7) {
for (int jj = j; jj < j + 8; jj++) {
if (jj == i) {
continue;
}
// # 2 ADDs
double r_ab_x = p.curr_pos_x - pedestrians[jj].curr_pos_x;
double r_ab_y = p.curr_pos_y - pedestrians[jj].curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab_norm = sqrt(r_ab_x * r_ab_x + r_ab_y * r_ab_y);
// # 2 ADDs
double r_ab2_x = r_ab_x - pedestrians[jj].s_b_e_x;
double r_ab2_y = r_ab_y - pedestrians[jj].s_b_e_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
// # 2 ADDs, 1 MULT
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - pedestrians[jj].s_b_sq;
// # 1 SQRT
double two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 DIV, 1 EXP
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 2 MULTs
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 4 MULTs, 2 ADDs
double f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
double f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_beta_neg_x + p.e_y * f_alpha_beta_neg_y) * cos_phi_inv;
// # 2 MULTs, 1 ADD
double b_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs, 2 ADDs
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
} else {
__m512d beta_curr_pos_x_vec = _mm512_setr_pd(pedestrians[j].curr_pos_x, pedestrians[j + 1].curr_pos_x, pedestrians[j + 2].curr_pos_x, pedestrians[j + 3].curr_pos_x, pedestrians[j + 4].curr_pos_x, pedestrians[j + 5].curr_pos_x, pedestrians[j + 6].curr_pos_x, pedestrians[j + 7].curr_pos_x);
__m512d beta_curr_pos_y_vec = _mm512_setr_pd(pedestrians[j].curr_pos_y, pedestrians[j + 1].curr_pos_y, pedestrians[j + 2].curr_pos_y, pedestrians[j + 3].curr_pos_y, pedestrians[j + 4].curr_pos_y, pedestrians[j + 5].curr_pos_y, pedestrians[j + 6].curr_pos_y, pedestrians[j + 7].curr_pos_y);
// # 16 ADDs
__m512d r_ab_x_vec = _mm512_sub_pd(alpha_curr_pos_x_vec, beta_curr_pos_x_vec);
__m512d r_ab_y_vec = _mm512_sub_pd(alpha_curr_pos_y_vec, beta_curr_pos_y_vec);
// # 8 MULTs
__m512d r_ab_y_mul_r_ab_y_vec = _mm512_mul_pd(r_ab_y_vec, r_ab_y_vec);
// # 8 MULTs, 8 ADDs
__m512d r_ab_norm_sq_vec = _mm512_fmadd_pd(r_ab_x_vec, r_ab_x_vec, r_ab_y_mul_r_ab_y_vec);
// # 8 SQRTs
__m512d r_ab_norm_vec = _mm512_sqrt_pd(r_ab_norm_sq_vec);
__m512d beta_s_b_e_x_vec = _mm512_setr_pd(pedestrians[j].s_b_e_x, pedestrians[j + 1].s_b_e_x, pedestrians[j + 2].s_b_e_x, pedestrians[j + 3].s_b_e_x, pedestrians[j + 4].s_b_e_x, pedestrians[j + 5].s_b_e_x, pedestrians[j + 6].s_b_e_x, pedestrians[j + 7].s_b_e_x);
// # 8 ADDs
__m512d r_ab2_x_vec = _mm512_sub_pd(r_ab_x_vec, beta_s_b_e_x_vec);
__m512d beta_s_b_e_y_vec = _mm512_setr_pd(pedestrians[j].s_b_e_y, pedestrians[j + 1].s_b_e_y, pedestrians[j + 2].s_b_e_y, pedestrians[j + 3].s_b_e_y, pedestrians[j + 4].s_b_e_y, pedestrians[j + 5].s_b_e_y, pedestrians[j + 6].s_b_e_y, pedestrians[j + 7].s_b_e_y);
// # 8 ADDs
__m512d r_ab2_y_vec = _mm512_sub_pd(r_ab_y_vec, beta_s_b_e_y_vec);
// # 8 MULTs
__m512d r_ab2_y_mul_r_ab2_y_vec = _mm512_mul_pd(r_ab2_y_vec, r_ab2_y_vec);
// # 8 MULTs, 8 ADDs
__m512d r_ab2_norm_sq_vec = _mm512_fmadd_pd(r_ab2_x_vec, r_ab2_x_vec, r_ab2_y_mul_r_ab2_y_vec);
// # 8 SQRTs
__m512d r_ab2_norm_vec = _mm512_sqrt_pd(r_ab2_norm_sq_vec);
// # 8 ADDs
__m512d r_ab_norm_sum_vec = _mm512_add_pd(r_ab_norm_vec, r_ab2_norm_vec);
__m512d beta_s_b_sq_vec = _mm512_setr_pd(pedestrians[j].s_b_sq, pedestrians[j + 1].s_b_sq, pedestrians[j + 2].s_b_sq, pedestrians[j + 3].s_b_sq, pedestrians[j + 4].s_b_sq, pedestrians[j + 5].s_b_sq, pedestrians[j + 6].s_b_sq, pedestrians[j + 7].s_b_sq);
// # 8 MULTs, 8 ADDs
__m512d two_b_sq_vec = _mm512_fmsub_pd(r_ab_norm_sum_vec, r_ab_norm_sum_vec, beta_s_b_sq_vec);
// # 8 SQRTs
__m512d two_b_vec = _mm512_sqrt_pd(two_b_sq_vec);
// # 8 MULTs
__m512d two_b_mul_r_ab_norm_vec = _mm512_mul_pd(two_b_vec, r_ab_norm_vec);
// # 8 MULTs
__m512d denom_vec = _mm512_mul_pd(two_b_mul_r_ab_norm_vec, r_ab2_norm_vec);
// # 8 DIVs
__m512d scalar_mult_common_left_vec = _mm512_div_pd(r_ab_norm_sum_vec, denom_vec);
// # 8 MULTs
__m512d two_b_mul_NEG_TWO_SIGMA_INV_vec = _mm512_mul_pd(two_b_vec, NEG_TWO_SIGMA_INV_VEC);
// # 160 MULTs, 112 ADDs
// objdump -d --demangle /usr/lib/x86_64-linux-gnu/libsleef.so | grep -A 67 "Sleef_expd8_u10@@Base"
__m512d e_vec = Sleef_expd8_u10(two_b_mul_NEG_TWO_SIGMA_INV_vec);
// # 16 MULTs
__m512d scalar_mult_common_right_vec = _mm512_mul_pd(NEG_V0_AB_DIV_TWO_SIGMA_VEC, e_vec);
__m512d scalar_mult_common_vec = _mm512_mul_pd(scalar_mult_common_left_vec, scalar_mult_common_right_vec);
// # 16 MULTs
__m512d scalar_mult_r_ab_vec = _mm512_mul_pd(scalar_mult_common_vec, r_ab2_norm_vec);
__m512d scalar_mult_r_ab2_vec = _mm512_mul_pd(scalar_mult_common_vec, r_ab_norm_vec);
// # 16 MULTs
__m512d r_ab2_x_mul_scalar_mult_r_ab2_vec = _mm512_mul_pd(r_ab2_x_vec, scalar_mult_r_ab2_vec);
__m512d r_ab2_y_mul_scalar_mult_r_ab2_vec = _mm512_mul_pd(r_ab2_y_vec, scalar_mult_r_ab2_vec);
// # 16 MULTs, 16 ADDs
__m512d f_alpha_beta_neg_x_vec = _mm512_fmadd_pd(r_ab_x_vec, scalar_mult_r_ab_vec, r_ab2_x_mul_scalar_mult_r_ab2_vec);
__m512d f_alpha_beta_neg_y_vec = _mm512_fmadd_pd(r_ab_y_vec, scalar_mult_r_ab_vec, r_ab2_y_mul_scalar_mult_r_ab2_vec);
// # 8 MULTs
__m512d rgt_vec = _mm512_mul_pd(alpha_e_y_vec, f_alpha_beta_neg_y_vec);
// # 8 MULTs, 8 ADDs
__m512d lft_add_rgt_vec = _mm512_fmadd_pd(alpha_e_x_vec, f_alpha_beta_neg_x_vec, rgt_vec);
// # 8 MULTs
__m512d a_vec = _mm512_mul_pd(lft_add_rgt_vec, cos_phi_inv_vec);
// # 8 MULTs
__m512d f_alpha_beta_neg_y_sq_vec = _mm512_mul_pd(f_alpha_beta_neg_y_vec, f_alpha_beta_neg_y_vec);
// # 8 MULTs, 8 ADDs
__m512d b_sq_vec = _mm512_fmadd_pd(f_alpha_beta_neg_x_vec, f_alpha_beta_neg_x_vec, f_alpha_beta_neg_y_sq_vec);
__m512d w_val_vec = dt_neg_vec;
__mmask8 a_ge_zero_mask = _mm512_cmp_pd_mask(a_vec, ZERO_VEC, _CMP_GE_OQ);
// # 8 MULTs
__m512d a_sq_vec = _mm512_mul_pd(a_vec, a_vec);
__mmask8 a_sq_gt_b_sq_mask = _mm512_cmp_pd_mask(a_sq_vec, b_sq_vec, _CMP_GT_OQ);
__mmask8 cond_mask = _kand_mask8(a_ge_zero_mask, a_sq_gt_b_sq_mask);
w_val_vec = _mm512_mask_mov_pd(w_val_vec, cond_mask, c_neg_times_dt_vec);
// # 16 MULTs
__m512d x_term_vec = _mm512_mul_pd(f_alpha_beta_neg_x_vec, w_val_vec);
__m512d y_term_vec = _mm512_mul_pd(f_alpha_beta_neg_y_vec, w_val_vec);
// # 16 ADDs
f_alpha_dt_x += _mm512_reduce_add_pd(x_term_vec);
f_alpha_dt_y += _mm512_reduce_add_pd(y_term_vec);
}
}
// # ############################################################################################################################################################################################
for (; j < n_p; j++) {
if (j == i) {
continue;
}
// # 2 ADDs
double r_ab_x = p.curr_pos_x - pedestrians[j].curr_pos_x;
double r_ab_y = p.curr_pos_y - pedestrians[j].curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab_norm = sqrt(r_ab_x * r_ab_x + r_ab_y * r_ab_y);
// # 2 ADDs
double r_ab2_x = r_ab_x - pedestrians[j].s_b_e_x;
double r_ab2_y = r_ab_y - pedestrians[j].s_b_e_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
// # 1 ADD
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 MULT, 1 ADD
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - pedestrians[j].s_b_sq;
// # 1 SQRT
double two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 DIV, 1 EXP
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 2 MULTs
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 4 MULTs, 2 ADDs
double f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
double f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_beta_neg_x + p.e_y * f_alpha_beta_neg_y) * cos_phi_inv;
// # 2 MULTs, 1 ADD
double b_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs, 2 ADDs
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
// # ############################################################################################################################################################################################
for (int k = 0; k < board.n_obstacles; k++) {
// # 2 ADDs
double v1_x = p.curr_pos_x - board.obstacles[k].start_x;
double v1_y = p.curr_pos_y - board.obstacles[k].start_y;
// # 3 MULTs, 1 ADD
double projection = (v1_x * board.obstacles[k].obstacle_v_x + v1_y * board.obstacles[k].obstacle_v_y) * board.obstacles[k].length_sq_inv;
if (projection < 0.0)
projection = 0.0;
else if (projection > 1.0)
projection = 1.0;
// # 2 MULTs, 4 ADDs
double r_aB_x = p.curr_pos_x - (board.obstacles[k].start_x + board.obstacles[k].obstacle_v_x * projection);
double r_aB_y = p.curr_pos_y - (board.obstacles[k].start_y + board.obstacles[k].obstacle_v_y * projection);
// # 1 SQRT, 2 MULTs, 1 ADD
double r_aB_norm = sqrt(r_aB_x * r_aB_x + r_aB_y * r_aB_y);
// # 2 MULTs, 1 EXP, 1 DIV
double scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
// # 2 MULTs
double f_alpha_B_neg_x = r_aB_x * scalar_mult;
double f_alpha_B_neg_y = r_aB_y * scalar_mult;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_B_neg_x + p.e_y * f_alpha_B_neg_y) * cos_phi_inv;
// # 2 MULTs, 1 ADD
double b_sq = f_alpha_B_neg_x * f_alpha_B_neg_x + f_alpha_B_neg_y * f_alpha_B_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs
double f_alpha_B_dt_x = f_alpha_B_neg_x * w_val;
double f_alpha_B_dt_y = f_alpha_B_neg_y * w_val;
// # 2 ADDs
f_alpha_dt_x += f_alpha_B_dt_x;
f_alpha_dt_y += f_alpha_B_dt_y;
}
// # 2 ADDs
p.w_x += f_alpha_dt_x;
p.w_y += f_alpha_dt_y;
}
// # ############################################################################################################################################################################################
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 SQRT, 2 MULTs, 1 ADD
double w_norm = sqrt(p.w_x * p.w_x + p.w_y * p.w_y);
// # 1 DIV
double correction_factor = min(1.0, p.v_max / w_norm);
// # 2 MULTs
p.curr_vel_x = p.w_x * correction_factor;
p.curr_vel_y = p.w_y * correction_factor;
// # 2 MULTs, 2 ADDs
p.curr_pos_x = p.curr_pos_x + p.curr_vel_x * dt;
p.curr_pos_y = p.curr_pos_y + p.curr_vel_y * dt;
if (p.color == 0 && p.curr_pos_x > BOARD_LENGTH_MINUS_ONE_POINT_FIVE) {
p.curr_pos_x = 1.0;
p.destination_y = p.curr_pos_y;
p.w_x = p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
if (p.color == 1 && p.curr_pos_x < 1.5) {
p.curr_pos_x = BOARD_LENGTH_MINUS_ONE;
p.destination_y = p.curr_pos_y;
p.w_x = -p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
p.curr_pos_y = clamp(p.curr_pos_y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
double e_x = p.destination_x - p.curr_pos_x;
double e_y = p.destination_y - p.curr_pos_y;
// # 1 DIV, 1 SQRT, 2 MULTs, 1 ADD
double e_norm_inv = 1.0 / sqrt(e_x * e_x + e_y * e_y);
// # 2 MULTs
p.e_x = e_x * e_norm_inv;
p.e_y = e_y * e_norm_inv;
// # 2 MULTs, 1 ADD
double velocity_norm_sq = p.curr_vel_x * p.curr_vel_x + p.curr_vel_y * p.curr_vel_y;
// # 1 SQRT
double velocity_norm = sqrt(velocity_norm_sq);
// # 5 MULTs
p.s_b_sq = velocity_norm_sq * delta_t_sq;
p.s_b_e_x = p.e_x * (velocity_norm * delta_t);
p.s_b_e_y = p.e_y * (velocity_norm * delta_t);
#if !BENCHMARK
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
#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;
}
#endif
variants/variant_baseline_flopcount.cpp
-440
View File
@@ -1,440 +0,0 @@
// This file is merged from the forces.cpp and social_forces_baseline.cpp
// The goal is that we from now on only have one file as our baseline
// This should make it more easy in the future to implement optimizations
// Our naming convention from now on is: variant_<variant_name>.cpp (Please make sure to keep that consistent, otherwise our Makefile wont work anymore)
#include "../headers/board.hpp"
#include "../headers/constants.hpp"
#include "../headers/pedestrian.hpp"
#include "../headers/vector2d.hpp"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h> // keep — forces code uses unqualified sqrt/exp
#include <random>
#include <tuple>
#include <vector>
#define SEED 42
#define BOARD_WIDTH 10.0
#define BOARD_LENGTH 50.0
#define WALL_EPS 1e-3
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999
#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif
#ifndef BENCHMARK
#define BENCHMARK 0
#endif
using namespace std;
// forces.cpp
// Flop count: 2 ADDs, 6 MULTs
double w_ped(Vector2d e, Vector2d f) {
double f_norm_sq = f.dot(f);
double rhs = f_norm_sq * cos_phi_sq;
double e_dot_f = e.dot(f);
double e_dot_f_sq = e_dot_f * e_dot_f;
if (e_dot_f >= 0.0 || e_dot_f_sq <= rhs)
return dt_neg;
else
return c_neg_times_dt;
}
double w_obstacle(Vector2d e, Vector2d f) {
double e_dot_f = (f.y == 0) ? 0 : (f.y < 0 ? -e.y : e.y);
if (e_dot_f >= cos_phi)
return dt_neg;
else
return c_neg_times_dt;
}
// Flop count: 2 ADDs, 4 MULTs
Vector2d acceleration_term_dt(const Pedestrian &alpha) {
// # 2 MULTs
Vector2d desired_velocity = alpha.e * alpha.desired_v0;
Vector2d actual_velocity = alpha.curr_vel;
// # 2 ADDs, 2 MULTs
Vector2d f_alpha_0_dt = (desired_velocity - actual_velocity) * dt_times_tau_alpha_inv;
return f_alpha_0_dt;
}
// Flop count: 12 ADDs, 24 MULTs, 1 DIV, 3 SQRTs, 1 EXP
Vector2d pedestrian_repulsion_dt(const Pedestrian &alpha, const Pedestrian &beta) {
// # 2 ADDs
// $\vec{r}_{\alpha\beta}$
Vector2d r_ab = alpha.curr_pos - beta.curr_pos;
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert$
double r_ab_norm = r_ab.norm();
r_ab_norm = r_ab_norm > EPS ? r_ab_norm : EPS; // Avoid division by zero
// $v_\beta \Delta t \vec{e}_\beta$
Vector2d s_b_e = beta.s_b_e;
// # 2 ADDs
// $\vec{r}_{\alpha\beta} - \vec{v}_{\beta}\varDelta_{t}\vec{e}_{\beta}$
Vector2d r_ab2 = r_ab - s_b_e;
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert$
double r_ab2_norm = r_ab2.norm();
r_ab2_norm = r_ab2_norm > EPS ? r_ab2_norm : EPS; // Avoid division by zero
// # 1 ADD
// $\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert$
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 ADD, 1 MULTs, 1 SQRT
//
// $2b = \sqrt{(\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert)^2 - (v_\beta \Delta t)^2}$
//
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - beta.s_b_sq;
two_b_sq = two_b_sq > EPS_SQ ? two_b_sq : EPS_SQ; // Avoid sqrt of negative and avoid division by zero
double two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 DIV, 1 EXP
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}$
//
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 1 MULT
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}$
//
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
// # 1 MULT
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}$
//
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 2 ADDs, 4 MULTs
//
// $\vec{-f}_{\alpha \beta}(\vec{r}_{\alpha \beta}) = \frac{-V^0_{\alpha \beta}}{2\sigma}e^{-b / \sigma} 2\grad_{\vec{r}_{\alpha \beta}}b $
//
//
// $= \frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}\,\vec{r}_{\alpha \beta} + \frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} -
// v_\beta \Delta t \vec{e}_\beta \Arrowvert}\,(\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta)$
//
//
//
// $2\grad_{\vec{r}_{\alpha \beta}}b = \frac{(\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert)(\frac{\vec{r}_{\alpha \beta}}{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert} + \frac{\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta}{\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert})}{2b}$
//
//
// $= \frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}\,\vec{r}_{\alpha \beta} + \frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}\,(\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta)$
//
//
Vector2d f_alpha_beta_neg = r_ab * scalar_mult_r_ab + r_ab2 * scalar_mult_r_ab2;
// # 2 ADDs, 8 MULTs
//
// $\vec{F}_{\alpha\beta}(\vec{e}_{\alpha}, \vec{r}_{\alpha \beta}).dt = w(\vec{e}_{\alpha}, -\vec{f}_{\alpha\beta}(\vec{r}_{\alpha \beta})).\vec{f}_{\alpha\beta}(\vec{r}_{\alpha \beta}).dt$
//
Vector2d f_alpha_beta_dt = f_alpha_beta_neg * w_ped(alpha.e, f_alpha_beta_neg);
return f_alpha_beta_dt;
}
// Flop count: 8 ADDs, 13 MULTs, 1 DIV, 1 SQRT, 1 EXP
Vector2d obstacle_repulsion_dt(const Pedestrian &alpha, const Obstacle &B) {
// # 7 ADDs, 5 MULTs
// $\vec{r}_{\alpha B}$
Vector2d r_aB = alpha.curr_pos - B.find_nearest_obstacle_point(alpha.curr_pos);
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha B} \Arrowvert$
double r_aB_norm = r_aB.norm();
r_aB_norm = r_aB_norm > EPS ? r_aB_norm : EPS; // Avoid division by zero
// # 2 MULTs, 1 DIV, 1 EXP
//
// $\frac{-U^0_{\alpha B}}{R} e^{- \Arrowvert \vec{r}_{\alpha B} \Arrowvert / R}$
//
double scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
// # 2 MULTs
//
// $-\vec{F}_{\alpha B}(\vec{r}_{\alpha B}) = \frac{-U^0_{\alpha B}}{R} e^{- \Arrowvert \vec{r}_{\alpha B} \Arrowvert / R} \frac{\vec{r}_{\alpha B}}{\Arrowvert \vec{r}_{\alpha B} \Arrowvert}$
//
Vector2d f_alpha_B_neg = r_aB * scalar_mult;
// # 2 MULTs
//
// $\vec{F}_{\alpha B}(\vec{e}_{\alpha}, \vec{r}_{\alpha B}).dt = w(\vec{e}_{\alpha}, -\vec{F}_{\alpha B}(\vec{r}_{\alpha B})).\vec{F}_{\alpha B}(\vec{r}_{\alpha B}).dt$
//
Vector2d f_alpha_B_dt = f_alpha_B_neg * w_obstacle(alpha.e, f_alpha_B_neg);
return f_alpha_B_dt;
}
// social_force_baseline.cpp
Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
random_device rd; // Platform-provided random seed source.
mt19937 gen(rd()); // Non-reproducible initialization.
#else
mt19937 gen(SEED); // Reproducible initialization.
#endif
normal_distribution<double> velocity_gen(v0_mean, v0_std_dev);
uniform_real_distribution<double> y_gen(0.3, BOARD_WIDTH - 0.3);
uniform_real_distribution<double> x_gen_left(2.0, BOARD_LENGTH / 2.0);
uniform_real_distribution<double> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);
Pedestrian *P = new Pedestrian[n_p];
int n_p_half = n_p / 2;
// Group of pedestrians walking from left to right.
for (int i = 0; i < n_p_half; i++) {
double x = x_gen_left(gen);
double y = y_gen(gen);
Vector2d start_pos = Vector2d(x, y);
Vector2d destination = Vector2d(BOARD_LENGTH + 30.0, y);
Vector2d init_e = destination - start_pos;
double init_e_norm = init_e.norm();
Vector2d init_e_unit = init_e / init_e_norm;
// Reject near-zero desired speeds to avoid pedestrians that barely move,
// and reject negative speeds because they would reverse the intended
// walking direction.
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(WHITE, Vector2d(), start_pos, init_e_unit, v_max, desired_v0, destination);
}
// Group of pedestrians walking from right to left.
for (int i = n_p_half; i < n_p; i++) {
double x = x_gen_right(gen);
double y = y_gen(gen);
Vector2d start_pos = Vector2d(x, y);
Vector2d destination = Vector2d(-30.0, y);
Vector2d init_e = destination - start_pos;
double init_e_norm = init_e.norm();
Vector2d init_e_unit = init_e / init_e_norm;
// Reject near-zero desired speeds to avoid pedestrians that barely move,
// and reject negative speeds because they would reverse the intended
// walking direction.
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(BLACK, Vector2d(), start_pos, init_e_unit, v_max, desired_v0, destination);
}
return P;
}
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) {
#if BENCHMARK
// Avoid compiler unused parameter warning
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
// Each sample stores: time step, pedestrian id, x, y, e.x, e.y, color.
vector<tuple<int, int, double, double, double, double, int>> samples;
if (dump_path) {
samples.reserve(static_cast<size_t>(n_iter / dump_interval + 1) * n_p);
// Store the initial state before the first simulation step.
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos.x, p.curr_pos.y, p.e.x, p.e.y, p.color);
}
}
#endif
// # ADDs: n_iter * (
// # n_p * 4 +
// # n_p * (n_p - 1) * 14 +
// # n_p * board.n_obstacles * 10 +
// # n_p * 7
// # )
// # MULTs: n_iter * (
// # n_p * 4
// # n_p * (n_p - 1) * 24 +
// # n_p * board.n_obstacles * 13 +
// # n_p * 16
// # )
// # DIVs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles +
// # n_p * 2
// # )
// # SQRTs: n_iter * (
// # n_p * (n_p - 1) * 3 +
// # n_p * board.n_obstacles +
// # n_p * 3
// # )
// # EXPs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles
// # )
for (int t = 0; t < n_iter; t++) {
// Pass 1: Compute all forces from the current state.
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 ADDs, 4 MULTs
//
// $\vec{F}_\alpha(\vec{v}_\alpha, v^0_\alpha \vec{e}_\alpha) = \frac{1}{\tau_\alpha}(v^0_\alpha \vec{e}_\alpha - \vec{v}_\alpha)$
//
Vector2d f_alpha_dt = acceleration_term_dt(p);
// # (N-1) * (14 ADDs, 24 MULTs, 1 DIV, 3 SQRTs, 1 EXP)
//
// $\sum_{\beta} \vec{F}_{\alpha\beta}(\vec{e}_{\alpha},\vec{r}_{\alpha} - \vec{r}_{\beta})$
//
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
f_alpha_dt += pedestrian_repulsion_dt(p, pedestrians[j]);
}
// # board.n_obstacles * (10 ADDs, 13 MULTs, 1 DIV, 1 SQRT, 1 EXP)
//
// $\sum_{B} \vec{F}_{\alpha B}(\vec{e}_{\alpha}, \vec{r}_{\alpha} - \vec{r}_{B})$
//
for (int k = 0; k < board.n_obstacles; k++) {
f_alpha_dt += obstacle_repulsion_dt(p, board.obstacles[k]);
}
// # 2 ADDs
//
//
// $\frac{d\vec{w}_\alpha}{dt} = \vec{F}_{\alpha}(t)$
//
p.w += f_alpha_dt;
}
// Pass 2: Update pedestrian states after all forces have been computed.
// # (7 ADDs, 16 MULTs, 2 DIVs, 3 SQRTs) * n_p
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 ADD, 2 MULTs, 1 SQRT
double w_norm = p.w.norm();
double w_norm2 = w_norm > EPS ? w_norm : EPS; // Avoid division by zero.
// # 1 DIV
double correction_factor = std::min(1.0, p.v_max / w_norm2);
// # 2 MULTs
p.curr_vel = p.w * correction_factor;
// # 2 ADDs, 2 MULTs
//
// $\vec{r}_i^{t+1} = \vec{r}_i^t + \vec{v}_i^t dt$
//
p.curr_pos = p.curr_pos + p.curr_vel * dt;
// When a pedestrian reaches the end of the corridor, teleport them back
// to the opposite entrance while keeping the same y-coordinate. This
// maintains a constant pedestrian flow and makes lane formation easier to
// observe.
if (p.color == WHITE && p.curr_pos.x > (BOARD_LENGTH - 1.5)) {
p.curr_pos.x = 1.0;
p.destination.y = p.curr_pos.y;
p.w = Vector2d(p.desired_v0, 0.0);
p.curr_vel = p.w;
}
if (p.color == BLACK && p.curr_pos.x < 1.5) {
p.curr_pos.x = BOARD_LENGTH - 1.0;
p.destination.y = p.curr_pos.y;
p.w = Vector2d(-p.desired_v0, 0.0);
p.curr_vel = p.w;
}
// Keep pedestrians inside the board boundaries.
p.curr_pos.y = clamp(p.curr_pos.y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
Vector2d e = p.destination - p.curr_pos;
// # 1 ADD, 2 MULTs, 1 DIV, 1 SQRT
double e_norm = e.norm();
double e_norm2 = e_norm > EPS ? e_norm : EPS; // Avoid division by zero.
double e_norm_inv = 1.0 / e_norm2;
// # 2 MULTs
p.e = e * e_norm_inv;
// # 1 ADD, 2 MULTs
double velocity_norm_sq = p.curr_vel.dot(p.curr_vel);
// # 1 SQRT
double velocity_norm = std::sqrt(velocity_norm_sq);
// # 1 MULT
p.s_b_sq = velocity_norm_sq * delta_t_sq;
// # 3 MULTs
p.s_b_e = p.e * (velocity_norm * delta_t);
#if !BENCHMARK
// Store the current pedestrian state for visualization.
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos.x, p.curr_pos.y, p.e.x, p.e.y, p.color);
}
#endif
}
}
#if !BENCHMARK
// Export recorded simulation states to CSV.
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;
}
variants/variant_float_baseline_flopcount.cpp
-438
View File
@@ -1,438 +0,0 @@
// # Changes: Added per-instruction flop count
// # Predecessor: variant_float_baseline.cpp
#include "../headers/board_float.hpp"
#include "../headers/constants_float.hpp"
#include "../headers/pedestrian_float.hpp"
#include "../headers/vector2d_float.hpp"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h> // keep — forces code uses unqualified sqrt/exp
#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;
// forces.cpp
// Flop count: 2 ADDs, 6 MULTs
float w_ped(Vector2d e, Vector2d f) {
float f_norm_sq = f.dot(f);
float rhs = f_norm_sq * cos_phi_sq;
float e_dot_f = e.dot(f);
float e_dot_f_sq = e_dot_f * e_dot_f;
if (e_dot_f >= 0.0 || e_dot_f_sq <= rhs)
return dt_neg;
else
return c_neg_times_dt;
}
float w_obstacle(Vector2d e, Vector2d f) {
float e_dot_f = (f.y == 0) ? 0 : (f.y < 0 ? -e.y : e.y);
if (e_dot_f >= cos_phi)
return dt_neg;
else
return c_neg_times_dt;
}
// Flop count: 2 ADDs, 4 MULTs
Vector2d acceleration_term_dt(const Pedestrian &alpha) {
// # 2 MULTs
Vector2d desired_velocity = alpha.e * alpha.desired_v0;
Vector2d actual_velocity = alpha.curr_vel;
// # 2 ADDs, 2 MULTs
Vector2d f_alpha_0_dt = (desired_velocity - actual_velocity) * dt_times_tau_alpha_inv;
return f_alpha_0_dt;
}
// Flop count: 12 ADDs, 24 MULTs, 1 DIV, 3 SQRTs, 1 EXP
Vector2d pedestrian_repulsion_dt(const Pedestrian &alpha, const Pedestrian &beta) {
// # 2 ADDs
// $\vec{r}_{\alpha\beta}$
Vector2d r_ab = alpha.curr_pos - beta.curr_pos;
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert$
float r_ab_norm = r_ab.norm();
r_ab_norm = r_ab_norm > EPS ? r_ab_norm : EPS; // Avoid division by zero
// $v_\beta \Delta t \vec{e}_\beta$
Vector2d s_b_e = beta.s_b_e;
// # 2 ADDs
// $\vec{r}_{\alpha\beta} - \vec{v}_{\beta}\varDelta_{t}\vec{e}_{\beta}$
Vector2d r_ab2 = r_ab - s_b_e;
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert$
float r_ab2_norm = r_ab2.norm();
r_ab2_norm = r_ab2_norm > EPS ? r_ab2_norm : EPS; // Avoid division by zero
// # 1 ADD
// $\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert$
float r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 ADD, 1 MULTs, 1 SQRT
//
// $2b = \sqrt{(\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert)^2 - (v_\beta \Delta t)^2}$
//
float two_b_sq = r_ab_norm_sum * r_ab_norm_sum - beta.s_b_sq;
two_b_sq = two_b_sq > EPS_SQ ? two_b_sq : EPS_SQ; // Avoid sqrt of negative and avoid division by zero
float two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 DIV, 1 EXP
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}$
//
float scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 1 MULT
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}$
//
float scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
// # 1 MULT
//
// $\frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}$
//
float scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 2 ADDs, 4 MULTs
//
// $\vec{-f}_{\alpha \beta}(\vec{r}_{\alpha \beta}) = \frac{-V^0_{\alpha \beta}}{2\sigma}e^{-b / \sigma} 2\grad_{\vec{r}_{\alpha \beta}}b $
//
//
// $= \frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}\,\vec{r}_{\alpha \beta} + \frac{-V^0_{\alpha\beta}}{2\sigma}\,e^{-b/\sigma}\,\frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} -
// v_\beta \Delta t \vec{e}_\beta \Arrowvert}\,(\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta)$
//
//
//
// $2\grad_{\vec{r}_{\alpha \beta}}b = \frac{(\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert)(\frac{\vec{r}_{\alpha \beta}}{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert} + \frac{\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta}{\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert})}{2b}$
//
//
// $= \frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert}\,\vec{r}_{\alpha \beta} + \frac{\Arrowvert \vec{r}_{\alpha \beta} \Arrowvert + \Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}{2b\,\Arrowvert \vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta \Arrowvert}\,(\vec{r}_{\alpha \beta} - v_\beta \Delta t \vec{e}_\beta)$
//
//
Vector2d f_alpha_beta_neg = r_ab * scalar_mult_r_ab + r_ab2 * scalar_mult_r_ab2;
// # 2 ADDs, 8 MULTs
//
// $\vec{F}_{\alpha\beta}(\vec{e}_{\alpha}, \vec{r}_{\alpha \beta}).dt = w(\vec{e}_{\alpha}, -\vec{f}_{\alpha\beta}(\vec{r}_{\alpha \beta})).\vec{f}_{\alpha\beta}(\vec{r}_{\alpha \beta}).dt$
//
Vector2d f_alpha_beta_dt = f_alpha_beta_neg * w_ped(alpha.e, f_alpha_beta_neg);
return f_alpha_beta_dt;
}
// Flop count: 8 ADDs, 13 MULTs, 1 DIV, 1 SQRT, 1 EXP
Vector2d obstacle_repulsion_dt(const Pedestrian &alpha, const Obstacle &B) {
// # 7 ADDs, 5 MULTs
// $\vec{r}_{\alpha B}$
Vector2d r_aB = alpha.curr_pos - B.find_nearest_obstacle_point(alpha.curr_pos);
// # 1 ADD, 2 MULTs, 1 SQRT
// $\Arrowvert \vec{r}_{\alpha B} \Arrowvert$
float r_aB_norm = r_aB.norm();
r_aB_norm = r_aB_norm > EPS ? r_aB_norm : EPS; // Avoid division by zero
// # 2 MULTs, 1 DIV, 1 EXP
//
// $\frac{-U^0_{\alpha B}}{R} e^{- \Arrowvert \vec{r}_{\alpha B} \Arrowvert / R}$
//
float scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
// # 2 MULTs
//
// $-\vec{F}_{\alpha B}(\vec{r}_{\alpha B}) = \frac{-U^0_{\alpha B}}{R} e^{- \Arrowvert \vec{r}_{\alpha B} \Arrowvert / R} \frac{\vec{r}_{\alpha B}}{\Arrowvert \vec{r}_{\alpha B} \Arrowvert}$
//
Vector2d f_alpha_B_neg = r_aB * scalar_mult;
// # 2 MULTs
//
// $\vec{F}_{\alpha B}(\vec{e}_{\alpha}, \vec{r}_{\alpha B}).dt = w(\vec{e}_{\alpha}, -\vec{F}_{\alpha B}(\vec{r}_{\alpha B})).\vec{F}_{\alpha B}(\vec{r}_{\alpha B}).dt$
//
Vector2d f_alpha_B_dt = f_alpha_B_neg * w_obstacle(alpha.e, f_alpha_B_neg);
return f_alpha_B_dt;
}
// social_force_baseline.cpp
Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
random_device rd; // Platform-provided random seed source.
mt19937 gen(rd()); // Non-reproducible initialization.
#else
mt19937 gen(SEED); // Reproducible initialization.
#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);
Pedestrian *P = new Pedestrian[n_p];
int n_p_half = n_p / 2;
// Group of pedestrians walking from left to right.
for (int i = 0; i < n_p_half; i++) {
float x = x_gen_left(gen);
float y = y_gen(gen);
Vector2d start_pos = Vector2d(x, y);
Vector2d destination = Vector2d(BOARD_LENGTH + 30.0, y);
Vector2d init_e = destination - start_pos;
float init_e_norm = init_e.norm();
Vector2d init_e_unit = init_e / init_e_norm;
// Reject near-zero desired speeds to avoid pedestrians that barely move,
// and reject negative speeds because they would reverse the intended
// walking direction.
float desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
float v_max = 1.3 * desired_v0;
P[i] = Pedestrian(WHITE, Vector2d(), start_pos, init_e_unit, v_max, desired_v0, destination);
}
// Group of pedestrians walking from right to left.
for (int i = n_p_half; i < n_p; i++) {
float x = x_gen_right(gen);
float y = y_gen(gen);
Vector2d start_pos = Vector2d(x, y);
Vector2d destination = Vector2d(-30.0, y);
Vector2d init_e = destination - start_pos;
float init_e_norm = init_e.norm();
Vector2d init_e_unit = init_e / init_e_norm;
// Reject near-zero desired speeds to avoid pedestrians that barely move,
// and reject negative speeds because they would reverse the intended
// walking direction.
float desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
float v_max = 1.3 * desired_v0;
P[i] = Pedestrian(BLACK, Vector2d(), start_pos, init_e_unit, v_max, desired_v0, destination);
}
return P;
}
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) {
#if BENCHMARK
// Avoid compiler unused parameter warning
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
// Each sample stores: time step, pedestrian id, x, y, e.x, e.y, color.
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);
// Store the initial state before the first simulation step.
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos.x, p.curr_pos.y, p.e.x, p.e.y, p.color);
}
}
#endif
// # ADDs: n_iter * (
// # n_p * 4 +
// # n_p * (n_p - 1) * 14 +
// # n_p * board.n_obstacles * 10 +
// # n_p * 7
// # )
// # MULTs: n_iter * (
// # n_p * 4
// # n_p * (n_p - 1) * 24 +
// # n_p * board.n_obstacles * 13 +
// # n_p * 16
// # )
// # DIVs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles +
// # n_p * 2
// # )
// # SQRTs: n_iter * (
// # n_p * (n_p - 1) * 3 +
// # n_p * board.n_obstacles +
// # n_p * 3
// # )
// # EXPs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles
// # )
for (int t = 0; t < n_iter; t++) {
// Pass 1: Compute all forces from the current state.
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 ADDs, 4 MULTs
//
// $\vec{F}_\alpha(\vec{v}_\alpha, v^0_\alpha \vec{e}_\alpha) = \frac{1}{\tau_\alpha}(v^0_\alpha \vec{e}_\alpha - \vec{v}_\alpha)$
//
Vector2d f_alpha_dt = acceleration_term_dt(p);
// # (N-1) * (14 ADDs, 24 MULTs, 1 DIV, 3 SQRTs, 1 EXP)
//
// $\sum_{\beta} \vec{F}_{\alpha\beta}(\vec{e}_{\alpha},\vec{r}_{\alpha} - \vec{r}_{\beta})$
//
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
f_alpha_dt += pedestrian_repulsion_dt(p, pedestrians[j]);
}
// # board.n_obstacles * (10 ADDs, 13 MULTs, 1 DIV, 1 SQRT, 1 EXP)
//
// $\sum_{B} \vec{F}_{\alpha B}(\vec{e}_{\alpha}, \vec{r}_{\alpha} - \vec{r}_{B})$
//
for (int k = 0; k < board.n_obstacles; k++) {
f_alpha_dt += obstacle_repulsion_dt(p, board.obstacles[k]);
}
// # 2 ADDs
//
//
// $\frac{d\vec{w}_\alpha}{dt} = \vec{F}_{\alpha}(t)$
//
p.w += f_alpha_dt;
}
// Pass 2: Update pedestrian states after all forces have been computed.
// # (7 ADDs, 16 MULTs, 2 DIVs, 3 SQRTs) * n_p
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 ADD, 2 MULTs, 1 SQRT
float w_norm = p.w.norm();
float w_norm2 = w_norm > EPS ? w_norm : EPS; // Avoid division by zero.
// # 1 DIV
float correction_factor = std::min(1.0f, p.v_max / w_norm2);
// # 2 MULTs
p.curr_vel = p.w * correction_factor;
// # 2 ADDs, 2 MULTs
//
// $\vec{r}_i^{t+1} = \vec{r}_i^t + \vec{v}_i^t dt$
//
p.curr_pos = p.curr_pos + p.curr_vel * dt;
// When a pedestrian reaches the end of the corridor, teleport them back
// to the opposite entrance while keeping the same y-coordinate. This
// maintains a constant pedestrian flow and makes lane formation easier to
// observe.
if (p.color == WHITE && p.curr_pos.x > (BOARD_LENGTH - 1.5)) {
p.curr_pos.x = 1.0;
p.destination.y = p.curr_pos.y;
p.w = Vector2d(p.desired_v0, 0.0);
p.curr_vel = p.w;
}
if (p.color == BLACK && p.curr_pos.x < 1.5) {
p.curr_pos.x = BOARD_LENGTH - 1.0;
p.destination.y = p.curr_pos.y;
p.w = Vector2d(-p.desired_v0, 0.0);
p.curr_vel = p.w;
}
// Keep pedestrians inside the board boundaries.
p.curr_pos.y = clamp(p.curr_pos.y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
Vector2d e = p.destination - p.curr_pos;
// # 1 ADD, 2 MULTs, 1 DIV, 1 SQRT
float e_norm = e.norm();
float e_norm2 = e_norm > EPS ? e_norm : EPS; // Avoid division by zero.
float e_norm_inv = 1.0 / e_norm2;
// # 2 MULTs
p.e = e * e_norm_inv;
// # 1 ADD, 2 MULTs
float velocity_norm_sq = p.curr_vel.dot(p.curr_vel);
// # 1 SQRT
float velocity_norm = std::sqrt(velocity_norm_sq);
// # 1 MULT
p.s_b_sq = velocity_norm_sq * delta_t_sq;
// # 3 MULTs
p.s_b_e = p.e * (velocity_norm * delta_t);
#if !BENCHMARK
// Store the current pedestrian state for visualization.
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos.x, p.curr_pos.y, p.e.x, p.e.y, p.color);
}
#endif
}
}
#if !BENCHMARK
// Export recorded simulation states to CSV.
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;
}
variants/variant_float_inlining_SoA_NEON_polyexp_morevect_ilp_2_rsqrt_morersqrt.cpp
+2 -1
View File
@@ -187,6 +187,7 @@ static inline float32x4_t _neon_exp_ps(float32x4_t x) {
// # 4 MULTs, 4 ADDs
float32x4_t r = vfmsq_f32(x, nf, ln2); // r = x - nf*ln2
const float32x4_t c13 = vdupq_n_f32(c13_scalar);
const float32x4_t c12 = vdupq_n_f32(c12_scalar);
const float32x4_t c11 = vdupq_n_f32(c11_scalar);
const float32x4_t c10 = vdupq_n_f32(c10_scalar);
@@ -201,7 +202,7 @@ static inline float32x4_t _neon_exp_ps(float32x4_t x) {
const float32x4_t c1 = vdupq_n_f32(c1_scalar);
const float32x4_t c0 = vdupq_n_f32(c0_scalar);
float32x4_t p = c12;
float32x4_t p = c13;
// # 13 * (4 MULTs, 4 ADDs)
// # = 52 MULTs, 52 ADDs
variants/variant_float_inlining_SoA_flopcount.cpp
-380
View File
@@ -1,380 +0,0 @@
// # Changes: SoA layout for pedestrians (file-scope arrays instead of struct fields)
// # Predecessor: variant_float_inlining.cpp
#include "../headers/board_reduced_float.hpp"
#include "../headers/constants_float.hpp"
#include "../headers/pedestrian_reduced_float.hpp"
#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;
// we wanna use arrays so we can implement SoA, one array per pedestrian field
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);
// resize all arrays for this run
pos_x.resize(n_p);
pos_y.resize(n_p);
sb_sq.resize(n_p);
sb_e_x.resize(n_p);
sb_e_y.resize(n_p);
e_x.resize(n_p);
e_y.resize(n_p);
curr_vel_x.resize(n_p);
curr_vel_y.resize(n_p);
w_x.resize(n_p);
w_y.resize(n_p);
desired_v0.resize(n_p);
v_max.resize(n_p);
destination_x.resize(n_p);
destination_y.resize(n_p);
color.resize(n_p);
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;
// Fields the Pedestrian constructor would have zero-initialized (c_v_x=c_v_y=0):
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;
}
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
// # ADDs: n_iter * (
// # n_p * 4 +
// # n_p * (n_p - 1) * 14 +
// # n_p * board.n_obstacles * 10 +
// # n_p * 7
// # )
// # MULTs: n_iter * (
// # n_p * 4
// # n_p * (n_p - 1) * 24 +
// # n_p * board.n_obstacles * 13 +
// # n_p * 17
// # )
// # DIVs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles +
// # n_p * 2
// # )
// # SQRTs: n_iter * (
// # n_p * (n_p - 1) * 3 +
// # n_p * board.n_obstacles +
// # n_p * 3
// # )
// # EXPs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles
// # )
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;
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
float r_ab_x = pos_x[i] - pos_x[j];
float r_ab_y = pos_y[i] - pos_y[j];
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 r_ab2_x = r_ab_x - sb_e_x[j];
float r_ab2_y = r_ab_y - sb_e_y[j];
float r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
r_ab2_norm = r_ab2_norm > EPS ? r_ab2_norm : EPS;
float r_ab_norm_sum = r_ab_norm + r_ab2_norm;
float two_b_sq = r_ab_norm_sum * r_ab_norm_sum - sb_sq[j];
two_b_sq = two_b_sq > EPS_SQ ? two_b_sq : EPS_SQ;
float two_b = sqrt(two_b_sq);
float scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
float scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
float scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
float f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
float f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
float w_val;
float f_norm_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
float rhs = f_norm_sq * cos_phi_sq;
float e_dot_f = e_x[i] * f_alpha_beta_neg_x + e_y[i] * f_alpha_beta_neg_y;
float e_dot_f_sq = e_dot_f * e_dot_f;
if (e_dot_f >= 0.0 || e_dot_f_sq <= rhs)
w_val = dt_neg;
else
w_val = c_neg_times_dt;
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
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;
}
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;
}
variants/variant_float_inlining_flopcount.cpp
-366
View File
@@ -1,366 +0,0 @@
// # Changes: Replaced «double» with «float» in variable declarations
// # Predecessor: variant_float_baseline.cpp
#include "../headers/board_reduced_float.hpp"
#include "../headers/constants_float.hpp"
#include "../headers/pedestrian_reduced_float.hpp"
#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;
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);
Pedestrian *P = new Pedestrian[n_p];
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 start_pos_x = x;
float start_pos_y = y;
float destination_x = BOARD_LENGTH + 30.0;
float destination_y = y;
float init_e_x = destination_x - start_pos_x;
float init_e_y = destination_y - start_pos_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 desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
float v_max = 1.3 * desired_v0;
P[i] = Pedestrian(0, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
for (int i = n_p_half; i < n_p; i++) {
float x = x_gen_right(gen);
float y = y_gen(gen);
float start_pos_x = x;
float start_pos_y = y;
float destination_x = -30;
float destination_y = y;
float init_e_x = destination_x - start_pos_x;
float init_e_y = destination_y - start_pos_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 desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
float v_max = 1.3 * desired_v0;
P[i] = Pedestrian(1, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
return P;
}
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) {
#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++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
}
#endif
// # ADDs: n_iter * (
// # n_p * 4 +
// # n_p * (n_p - 1) * 14 +
// # n_p * board.n_obstacles * 10 +
// # n_p * 7
// # )
// # MULTs: n_iter * (
// # n_p * 4
// # n_p * (n_p - 1) * 24 +
// # n_p * board.n_obstacles * 13 +
// # n_p * 17
// # )
// # DIVs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles +
// # n_p * 2
// # )
// # SQRTs: n_iter * (
// # n_p * (n_p - 1) * 3 +
// # n_p * board.n_obstacles +
// # n_p * 3
// # )
// # EXPs: n_iter * (
// # n_p * (n_p - 1) +
// # n_p * board.n_obstacles
// # )
for (int t = 0; t < n_iter; t++) {
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 MULTs
float desired_velocity_x = p.e_x * p.desired_v0;
float desired_velocity_y = p.e_y * p.desired_v0;
// # 2 MULTs, 2 ADDs
float f_alpha_dt_x = (desired_velocity_x - p.curr_vel_x) * dt_times_tau_alpha_inv;
float f_alpha_dt_y = (desired_velocity_y - p.curr_vel_y) * dt_times_tau_alpha_inv;
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
// # 2 ADDs
float r_ab_x = p.curr_pos_x - pedestrians[j].curr_pos_x;
float r_ab_y = p.curr_pos_y - pedestrians[j].curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
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;
// # 2 ADDs
float r_ab2_x = r_ab_x - pedestrians[j].s_b_e_x;
float r_ab2_y = r_ab_y - pedestrians[j].s_b_e_y;
// # 1 SQRT, 2 MULTs, 1 ADD
float r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
r_ab2_norm = r_ab2_norm > EPS ? r_ab2_norm : EPS;
// # 1 ADD
float r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 MULT 1 ADD
float two_b_sq = r_ab_norm_sum * r_ab_norm_sum - pedestrians[j].s_b_sq;
two_b_sq = two_b_sq > EPS_SQ ? two_b_sq : EPS_SQ;
// # 1 SQRT
float two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 DIV, 1 EXP
float scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 2 MULTs
float scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
float scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 4 MULTs, 2 ADDs
float f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
float f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
float w_val;
// # 6 MULTs, 2 ADDs
float f_norm_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
float rhs = f_norm_sq * cos_phi_sq;
float e_dot_f = p.e_x * f_alpha_beta_neg_x + p.e_y * f_alpha_beta_neg_y;
float e_dot_f_sq = e_dot_f * e_dot_f;
if (e_dot_f >= 0.0 || e_dot_f_sq <= rhs)
w_val = dt_neg;
else
w_val = c_neg_times_dt;
// # 2 MULTs, 2 ADDs
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
for (int k = 0; k < board.n_obstacles; k++) {
// # 2 ADDs
float v1_x = p.curr_pos_x - board.obstacles[k].start_x;
float v1_y = p.curr_pos_y - board.obstacles[k].start_y;
float v2_x = board.obstacles[k].obstacle_v_x;
float v2_y = board.obstacles[k].obstacle_v_y;
// # 3 MULTs, 1 ADD
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;
// # 4 ADDs, 2 MULTs
float r_aB_x = p.curr_pos_x - (board.obstacles[k].start_x + board.obstacles[k].obstacle_v_x * projection);
float r_aB_y = p.curr_pos_y - (board.obstacles[k].start_y + board.obstacles[k].obstacle_v_y * projection);
// # 1 SQRT, 2 MULTs, 1 ADD
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;
// # 4 MULTs, 1 EXP, 1 DIV
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 ? -p.e_y : p.e_y);
if (e_dot_f >= cos_phi)
w_val = dt_neg;
else
w_val = c_neg_times_dt;
// # 2 MULTS
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;
// # 2 ADDs
f_alpha_dt_x += f_alpha_B_dt_x;
f_alpha_dt_y += f_alpha_B_dt_y;
}
// # 2 ADDs
p.w_x += f_alpha_dt_x;
p.w_y += f_alpha_dt_y;
}
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 SQRT, 2 MULTs, 1 ADD
float w_norm = sqrt(p.w_x * p.w_x + p.w_y * p.w_y);
float w_norm2 = w_norm > EPS ? w_norm : EPS;
// # 1 DIV
float correction_factor = min(1.0f, p.v_max / w_norm2);
// # 2 MULTs
p.curr_vel_x = p.w_x * correction_factor;
p.curr_vel_y = p.w_y * correction_factor;
// # 2 MULTs, 2 ADDs
p.curr_pos_x = p.curr_pos_x + p.curr_vel_x * dt;
p.curr_pos_y = p.curr_pos_y + p.curr_vel_y * dt;
if (p.color == 0 && p.curr_pos_x > (BOARD_LENGTH - 1.5)) {
p.curr_pos_x = 1.0;
p.destination_y = p.curr_pos_y;
p.w_x = p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
if (p.color == 1 && p.curr_pos_x < 1.5) {
p.curr_pos_x = BOARD_LENGTH - 1.0;
p.destination_y = p.curr_pos_y;
p.w_x = -p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
p.curr_pos_y = clamp(p.curr_pos_y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
float e_x = p.destination_x - p.curr_pos_x;
float e_y = p.destination_y - p.curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
float e_norm = sqrt(e_x * e_x + e_y * e_y);
float e_norm2 = e_norm > EPS ? e_norm : EPS;
// # 1 DIV
float e_norm_inv = 1.0 / e_norm2;
// # 2 MULTs
p.e_x = e_x * e_norm_inv;
p.e_y = e_y * e_norm_inv;
// # 2 MULTs, 1 ADD
float velocity_norm_sq = p.curr_vel_x * p.curr_vel_x + p.curr_vel_y * p.curr_vel_y;
// # 1 SQRT
float velocity_norm = sqrt(velocity_norm_sq);
// # 5 MULTs
p.s_b_sq = velocity_norm_sq * delta_t_sq;
p.s_b_e_x = p.e_x * (velocity_norm * delta_t);
p.s_b_e_y = p.e_y * (velocity_norm * delta_t);
#if !BENCHMARK
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
#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;
}
variants/variant_inlining_7_SoA_flopcount.cpp
-362
View File
@@ -1,362 +0,0 @@
// # This file uses avx2
// # This is the first variant and should serve as a base for further avx2 optimizations
// Okay our first step is to use a SoA instead of an AoS
// We only do SoA for the pedestrian struct, there we wanna optimize such that we access for the ped-ped forces adjacent pedestrians (in the arrays)
#include "../headers/board.hpp"
#include "../headers/constants.hpp"
#include "../headers/pedestrian_reduced.hpp"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h>
#include <random>
#include <tuple>
#include <vector>
#define SEED 42
#define BOARD_WIDTH 10.0
#define BOARD_LENGTH 50.0
#define WALL_EPS 1e-3
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999
#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif
#ifndef BENCHMARK
#define BENCHMARK 0
#endif
using namespace std;
// we wanna use arrays so we can implement SOA, we create arrays for all the data we need and access
vector<double> pos_x, pos_y;
vector<double> sb_sq;
vector<double> sb_e_x, sb_e_y;
vector<double> e_x, e_y;
vector<double> curr_vel_x, curr_vel_y;
vector<double> w_x, w_y;
vector<double> desired_v0;
vector<double> v_max;
vector<double> 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<double> velocity_gen(v0_mean, v0_std_dev);
uniform_real_distribution<double> y_gen(0.3, BOARD_WIDTH - 0.3);
uniform_real_distribution<double> x_gen_left(2.0, BOARD_LENGTH / 2.0);
uniform_real_distribution<double> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);
// resize all our arrays for this run
pos_x.resize(n_p);
pos_y.resize(n_p);
sb_sq.resize(n_p);
sb_e_x.resize(n_p);
sb_e_y.resize(n_p);
e_x.resize(n_p);
e_y.resize(n_p);
curr_vel_x.resize(n_p);
curr_vel_y.resize(n_p);
w_x.resize(n_p);
w_y.resize(n_p);
desired_v0.resize(n_p);
v_max.resize(n_p);
destination_x.resize(n_p);
destination_y.resize(n_p);
color.resize(n_p);
int n_p_half = n_p / 2;
for (int i = 0; i < n_p_half; i++) {
double x = x_gen_left(gen);
double y = y_gen(gen);
double dest_x = BOARD_LENGTH + 30.0; // renamed to avoid shadowing destination_x[]
double dest_y = y; // same idea for destination_y[]
double init_e_x = dest_x - x;
double init_e_y = dest_y - y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double d_v0;
do {
d_v0 = velocity_gen(gen);
} while (d_v0 <= 0.1);
double 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;
// Fields the Pedestrian constructor would have zero-initialized:
w_x[i] = 0.0;
w_y[i] = 0.0;
curr_vel_x[i] = 0.0;
curr_vel_y[i] = 0.0;
sb_sq[i] = 0.0;
sb_e_x[i] = 0.0;
sb_e_y[i] = 0.0;
}
for (int i = n_p_half; i < n_p; i++) {
double x = x_gen_right(gen);
double y = y_gen(gen);
double dest_x = -30;
double dest_y = y;
double init_e_x = dest_x - x;
double init_e_y = dest_y - y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double d_v0;
do {
d_v0 = velocity_gen(gen);
} while (d_v0 <= 0.1);
double 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;
// Fields the Pedestrian constructor would have zero-initialized:
w_x[i] = 0.0;
w_y[i] = 0.0;
curr_vel_x[i] = 0.0;
curr_vel_y[i] = 0.0;
sb_sq[i] = 0.0;
sb_e_x[i] = 0.0;
sb_e_y[i] = 0.0;
}
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) {
#if BENCHMARK
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
vector<tuple<int, int, double, double, double, double, 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++) {
// Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, pos_x[i], pos_y[i], e_x[i], e_y[i], color[i]);
}
}
#endif
// # ADDs: n_iter * n_p * 11 +
// # n_iter * n_p * (n_p - 1) * 14 +
// # n_iter * n_p * board.n_obstacles * 12
// # MULTs: n_iter * n_p * 21 +
// # n_iter * n_p * (n_p - 1) * 24 +
// # n_iter * n_p * board.n_obstacles * 19
// # DIVs: n_iter * n_p * 2 +
// # n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
// # SQRTs: n_iter * n_p * 3 +
// # n_iter * n_p * (n_p - 1) * 3 +
// # n_iter * n_p * board.n_obstacles
// # EXPs: n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
for (int t = 0; t < n_iter; t++) {
for (int i = 0; i < n_p; i++) {
double desired_velocity_x = e_x[i] * desired_v0[i];
double desired_velocity_y = e_y[i] * desired_v0[i];
double f_alpha_dt_x = (desired_velocity_x - curr_vel_x[i]) * dt_times_tau_alpha_inv;
double f_alpha_dt_y = (desired_velocity_y - curr_vel_y[i]) * dt_times_tau_alpha_inv;
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
double r_ab_x = pos_x[i] - pos_x[j];
double r_ab_y = pos_y[i] - pos_y[j];
double r_ab_norm = sqrt(r_ab_x * r_ab_x + r_ab_y * r_ab_y);
double r_ab2_x = r_ab_x - sb_e_x[j];
double r_ab2_y = r_ab_y - sb_e_y[j];
double r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - sb_sq[j];
double two_b = sqrt(two_b_sq);
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
double f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
double f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
double w_val;
double a = (e_x[i] * f_alpha_beta_neg_x + e_y[i] * f_alpha_beta_neg_y) * cos_phi_inv;
double b_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
w_val = dt_neg;
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
for (int k = 0; k < board.n_obstacles; k++) {
double v1_x = pos_x[i] - board.obstacles[k].start.x;
double v1_y = pos_y[i] - board.obstacles[k].start.y;
double projection = (v1_x * board.obstacles[k].obstacle_v.x + v1_y * board.obstacles[k].obstacle_v.y) * board.obstacles[k].length_sq_inv;
if (projection < 0.0)
projection = 0.0;
else if (projection > 1.0)
projection = 1.0;
double r_aB_x = pos_x[i] - (board.obstacles[k].start.x + board.obstacles[k].obstacle_v.x * projection);
double r_aB_y = pos_y[i] - (board.obstacles[k].start.y + board.obstacles[k].obstacle_v.y * projection);
double r_aB_norm = sqrt(r_aB_x * r_aB_x + r_aB_y * r_aB_y);
double scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
double f_alpha_B_neg_x = r_aB_x * scalar_mult;
double f_alpha_B_neg_y = r_aB_y * scalar_mult;
double w_val;
double a = (e_x[i] * f_alpha_B_neg_x + e_y[i] * f_alpha_B_neg_y) * cos_phi_inv;
double b_sq = f_alpha_B_neg_x * f_alpha_B_neg_x + f_alpha_B_neg_y * f_alpha_B_neg_y;
w_val = dt_neg;
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
double f_alpha_B_dt_x = f_alpha_B_neg_x * w_val;
double 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;
}
for (int i = 0; i < n_p; i++) {
double w_norm = sqrt(w_x[i] * w_x[i] + w_y[i] * w_y[i]);
double correction_factor = min(1.0, v_max[i] / w_norm);
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);
double ex = destination_x[i] - pos_x[i];
double ey = destination_y[i] - pos_y[i];
double e_norm_inv = 1.0 / sqrt(ex * ex + ey * ey);
e_x[i] = ex * e_norm_inv;
e_y[i] = ey * e_norm_inv;
double velocity_norm_sq = curr_vel_x[i] * curr_vel_x[i] + curr_vel_y[i] * curr_vel_y[i];
double 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;
}
variants/variant_inlining_7_flopcount.cpp
-352
View File
@@ -1,352 +0,0 @@
// # This file performs in-lining for run_simulation.
// # Changes: Removed 2 sqrt() calls from the loop bodies
// # Predecessor: variant_inlining_6.cpp
#include "../headers/board.hpp"
#include "../headers/constants.hpp"
#include "../headers/pedestrian_reduced.hpp"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h>
#include <random>
#include <tuple>
#include <vector>
#define SEED 42
#define BOARD_WIDTH 10.0
#define BOARD_LENGTH 50.0
#define BOARD_LENGTH_MINUS_ONE BOARD_LENGTH - 1.0
#define BOARD_LENGTH_MINUS_ONE_POINT_FIVE BOARD_LENGTH - 1.5
#define WALL_EPS 1e-3
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999
#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif
#ifndef BENCHMARK
#define BENCHMARK 0
#endif
using namespace std;
Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
random_device rd;
mt19937 gen(rd());
#else
mt19937 gen(SEED);
#endif
normal_distribution<double> velocity_gen(v0_mean, v0_std_dev);
uniform_real_distribution<double> y_gen(0.3, BOARD_WIDTH - 0.3);
uniform_real_distribution<double> x_gen_left(2.0, BOARD_LENGTH / 2.0);
uniform_real_distribution<double> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);
Pedestrian *P = new Pedestrian[n_p];
int n_p_half = n_p / 2;
for (int i = 0; i < n_p_half; i++) {
double x = x_gen_left(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = BOARD_LENGTH + 30.0;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(0, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
for (int i = n_p_half; i < n_p; i++) {
double x = x_gen_right(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = -30;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(1, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
return P;
}
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) {
#if BENCHMARK
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
vector<tuple<int, int, double, double, double, double, 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++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
}
#endif
// # ADDs: n_iter * n_p * 11 +
// # n_iter * n_p * (n_p - 1) * 14 +
// # n_iter * n_p * board.n_obstacles * 12
// # MULTs: n_iter * n_p * 21 +
// # n_iter * n_p * (n_p - 1) * 24 +
// # n_iter * n_p * board.n_obstacles * 19
// # DIVs: n_iter * n_p * 2 +
// # n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
// # SQRTs: n_iter * n_p * 3 +
// # n_iter * n_p * (n_p - 1) * 3 +
// # n_iter * n_p * board.n_obstacles
// # EXPs: n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
for (int t = 0; t < n_iter; t++) {
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 MULTs
double desired_velocity_x = p.e_x * p.desired_v0;
double desired_velocity_y = p.e_y * p.desired_v0;
// # 2 MULTs, 2 ADDs
double f_alpha_dt_x = (desired_velocity_x - p.curr_vel_x) * dt_times_tau_alpha_inv;
double f_alpha_dt_y = (desired_velocity_y - p.curr_vel_y) * dt_times_tau_alpha_inv;
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
// # 2 ADDs
double r_ab_x = p.curr_pos_x - pedestrians[j].curr_pos_x;
double r_ab_y = p.curr_pos_y - pedestrians[j].curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab_norm = sqrt(r_ab_x * r_ab_x + r_ab_y * r_ab_y);
// # 2 ADDs
double r_ab2_x = r_ab_x - pedestrians[j].s_b_e_x;
double r_ab2_y = r_ab_y - pedestrians[j].s_b_e_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
// # 1ADD
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 MULT, 1 ADD
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - pedestrians[j].s_b_sq;
// # 1 SQRT
double two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 EXP, 1 DIV
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 2 MULTs
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 4 MULTs, 2 ADDs
double f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
double f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_beta_neg_x + p.e_y * f_alpha_beta_neg_y) * cos_phi_inv;
// # 2 MULTs, 1 ADD
double b_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs, 2 ADDs
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
for (int k = 0; k < board.n_obstacles; k++) {
// # 2 ADDs
double v1_x = p.curr_pos_x - board.obstacles[k].start.x;
double v1_y = p.curr_pos_y - board.obstacles[k].start.y;
// # 3 MULTs, 1 ADD
double projection = (v1_x * board.obstacles[k].obstacle_v.x + v1_y * board.obstacles[k].obstacle_v.y) * board.obstacles[k].length_sq_inv;
if (projection < 0.0)
projection = 0.0;
else if (projection > 1.0)
projection = 1.0;
// # 4 ADDs, 2 MULTs
double r_aB_x = p.curr_pos_x - (board.obstacles[k].start.x + board.obstacles[k].obstacle_v.x * projection);
double r_aB_y = p.curr_pos_y - (board.obstacles[k].start.y + board.obstacles[k].obstacle_v.y * projection);
// # 1 SQRT, 2 MULTs, 1 ADD
double r_aB_norm = sqrt(r_aB_x * r_aB_x + r_aB_y * r_aB_y);
// # 4 MULTs, 1 EXP, 1 DIV
double scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
double f_alpha_B_neg_x = r_aB_x * scalar_mult;
double f_alpha_B_neg_y = r_aB_y * scalar_mult;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_B_neg_x + p.e_y * f_alpha_B_neg_y) * cos_phi_inv;
// # 2 MULTS, 1 ADD
double b_sq = f_alpha_B_neg_x * f_alpha_B_neg_x + f_alpha_B_neg_y * f_alpha_B_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs
double f_alpha_B_dt_x = f_alpha_B_neg_x * w_val;
double f_alpha_B_dt_y = f_alpha_B_neg_y * w_val;
// # 2 ADDs
f_alpha_dt_x += f_alpha_B_dt_x;
f_alpha_dt_y += f_alpha_B_dt_y;
}
// # 2 ADDs
p.w_x += f_alpha_dt_x;
p.w_y += f_alpha_dt_y;
}
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 SQRT, 2 MULTs, 1 ADD
double w_norm = sqrt(p.w_x * p.w_x + p.w_y * p.w_y);
// # 1 DIV
double correction_factor = min(1.0, p.v_max / w_norm);
// # 2 MULTs
p.curr_vel_x = p.w_x * correction_factor;
p.curr_vel_y = p.w_y * correction_factor;
// # 2 MULTs, 2 ADDs
p.curr_pos_x = p.curr_pos_x + p.curr_vel_x * dt;
p.curr_pos_y = p.curr_pos_y + p.curr_vel_y * dt;
if (p.color == 0 && p.curr_pos_x > BOARD_LENGTH_MINUS_ONE_POINT_FIVE) {
p.curr_pos_x = 1.0;
p.destination_y = p.curr_pos_y;
p.w_x = p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
if (p.color == 1 && p.curr_pos_x < 1.5) {
p.curr_pos_x = BOARD_LENGTH_MINUS_ONE;
p.destination_y = p.curr_pos_y;
p.w_x = -p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
p.curr_pos_y = clamp(p.curr_pos_y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
double e_x = p.destination_x - p.curr_pos_x;
double e_y = p.destination_y - p.curr_pos_y;
// # 1 DIV, 1 SQRT, 2 MULTs, 1 ADD
double e_norm_inv = 1.0 / sqrt(e_x * e_x + e_y * e_y);
// # 2 MULTs
p.e_x = e_x * e_norm_inv;
p.e_y = e_y * e_norm_inv;
// # 2 MULTs, 1 ADD
double velocity_norm_sq = p.curr_vel_x * p.curr_vel_x + p.curr_vel_y * p.curr_vel_y;
// # 1 SQRT
double velocity_norm = sqrt(velocity_norm_sq);
// # 5 MULTs
p.s_b_sq = velocity_norm_sq * delta_t_sq;
p.s_b_e_x = p.e_x * (velocity_norm * delta_t);
p.s_b_e_y = p.e_y * (velocity_norm * delta_t);
#if !BENCHMARK
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
#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;
}
variants/variant_inlining_8_flopcount.cpp
-343
View File
@@ -1,343 +0,0 @@
// # This file performs in-lining for run_simulation.
// # Changes: Replaced references to Vector2d structs inside each Obstacle of Board.obstacles with references to doubles
// # Predecessor: variant_inlining_7.cpp
#include "../headers/board_reduced.hpp"
#include "../headers/constants.hpp"
#include "../headers/pedestrian_reduced.hpp"
#include <algorithm>
#include <cmath>
#include <fstream>
#include <iostream>
#include <math.h>
#include <random>
#include <tuple>
#include <vector>
#define SEED 42
#define BOARD_WIDTH 10.0
#define BOARD_LENGTH 50.0
#define BOARD_LENGTH_MINUS_ONE BOARD_LENGTH - 1.0
#define BOARD_LENGTH_MINUS_ONE_POINT_FIVE BOARD_LENGTH - 1.5
#define WALL_EPS 1e-3
#define BOARD_WIDTH_MINUS_WALL_EPS 9.999
#ifndef RANDOM_SEED
#define RANDOM_SEED 0
#endif
#ifndef BENCHMARK
#define BENCHMARK 0
#endif
using namespace std;
Pedestrian *init_pedestrians(int n_p) {
#if RANDOM_SEED
random_device rd;
mt19937 gen(rd());
#else
mt19937 gen(SEED);
#endif
normal_distribution<double> velocity_gen(v0_mean, v0_std_dev);
uniform_real_distribution<double> y_gen(0.3, BOARD_WIDTH - 0.3);
uniform_real_distribution<double> x_gen_left(2.0, BOARD_LENGTH / 2.0);
uniform_real_distribution<double> x_gen_right(BOARD_LENGTH / 2.0, BOARD_LENGTH - 2.0);
Pedestrian *P = new Pedestrian[n_p];
int n_p_half = n_p / 2;
for (int i = 0; i < n_p_half; i++) {
double x = x_gen_left(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = BOARD_LENGTH + 30.0;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(0, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
for (int i = n_p_half; i < n_p; i++) {
double x = x_gen_right(gen);
double y = y_gen(gen);
double start_pos_x = x;
double start_pos_y = y;
double destination_x = -30;
double destination_y = y;
double init_e_x = destination_x - start_pos_x;
double init_e_y = destination_y - start_pos_y;
double init_e_norm = sqrt(init_e_x * init_e_x + init_e_y * init_e_y);
double init_e_unit_x = init_e_x / init_e_norm;
double init_e_unit_y = init_e_y / init_e_norm;
double desired_v0;
do {
desired_v0 = velocity_gen(gen);
} while (desired_v0 <= 0.1);
double v_max = 1.3 * desired_v0;
P[i] = Pedestrian(1, 0, 0, start_pos_x, start_pos_y, init_e_unit_x, init_e_unit_y, v_max, desired_v0, destination_x, destination_y);
}
return P;
}
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) {
#if BENCHMARK
(void)dump_path;
#endif
#if !BENCHMARK
const int dump_interval = 1;
vector<tuple<int, int, double, double, double, double, 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++) {
Pedestrian &p = pedestrians[i];
samples.emplace_back(0, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
}
#endif
// # ADDs: n_iter * n_p * 11 +
// # n_iter * n_p * (n_p - 1) * 14 +
// # n_iter * n_p * board.n_obstacles * 10
// # MULTs: n_iter * n_p * 21 +
// # n_iter * n_p * (n_p - 1) * 24 +
// # n_iter * n_p * board.n_obstacles * 13
// # DIVs: n_iter * n_p * 2 +
// # n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
// # SQRTs: n_iter * n_p * 3 +
// # n_iter * n_p * (n_p - 1) * 3 +
// # n_iter * n_p * board.n_obstacles
// # EXPs: n_iter * n_p * (n_p - 1) +
// # n_iter * n_p * board.n_obstacles
for (int t = 0; t < n_iter; t++) {
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 2 MULTs
double desired_velocity_x = p.e_x * p.desired_v0;
double desired_velocity_y = p.e_y * p.desired_v0;
// # 2 MULTs, 2 ADDs
double f_alpha_dt_x = (desired_velocity_x - p.curr_vel_x) * dt_times_tau_alpha_inv;
double f_alpha_dt_y = (desired_velocity_y - p.curr_vel_y) * dt_times_tau_alpha_inv;
for (int j = 0; j < n_p; j++) {
if (i == j)
continue;
// # 2 ADDs
double r_ab_x = p.curr_pos_x - pedestrians[j].curr_pos_x;
double r_ab_y = p.curr_pos_y - pedestrians[j].curr_pos_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab_norm = sqrt(r_ab_x * r_ab_x + r_ab_y * r_ab_y);
// # 2 ADDs
double r_ab2_x = r_ab_x - pedestrians[j].s_b_e_x;
double r_ab2_y = r_ab_y - pedestrians[j].s_b_e_y;
// # 1 SQRT, 2 MULTs, 1 ADD
double r_ab2_norm = sqrt(r_ab2_x * r_ab2_x + r_ab2_y * r_ab2_y);
// # 1ADD
double r_ab_norm_sum = r_ab_norm + r_ab2_norm;
// # 1 MULT, 1 ADD
double two_b_sq = r_ab_norm_sum * r_ab_norm_sum - pedestrians[j].s_b_sq;
// # 1 SQRT
double two_b = sqrt(two_b_sq);
// # 5 MULTs, 1 EXP, 1 DIV
double scalar_mult_common = (r_ab_norm_sum / (two_b * r_ab_norm * r_ab2_norm)) * (NEG_V0_AB_div_TWO_SIGMA * exp(two_b * NEG_TWO_SIGMA_INV));
// # 2 MULTs
double scalar_mult_r_ab = scalar_mult_common * r_ab2_norm;
double scalar_mult_r_ab2 = scalar_mult_common * r_ab_norm;
// # 4 MULTs, 2 ADDs
double f_alpha_beta_neg_x = r_ab_x * scalar_mult_r_ab + r_ab2_x * scalar_mult_r_ab2;
double f_alpha_beta_neg_y = r_ab_y * scalar_mult_r_ab + r_ab2_y * scalar_mult_r_ab2;
double w_val;
// # 3 MULTs, 1 ADD
double a = (p.e_x * f_alpha_beta_neg_x + p.e_y * f_alpha_beta_neg_y) * cos_phi_inv;
// # 2 MULTs, 1 ADD
double b_sq = f_alpha_beta_neg_x * f_alpha_beta_neg_x + f_alpha_beta_neg_y * f_alpha_beta_neg_y;
w_val = dt_neg;
// # 1 MULT
if (a >= 0 && (a * a > b_sq)) {
w_val = c_neg_times_dt;
}
// # 2 MULTs, 2 ADDs
f_alpha_dt_x = f_alpha_dt_x + f_alpha_beta_neg_x * w_val;
f_alpha_dt_y = f_alpha_dt_y + f_alpha_beta_neg_y * w_val;
}
for (int k = 0; k < board.n_obstacles; k++) {
// # 2 ADDs
double v1_x = p.curr_pos_x - board.obstacles[k].start_x;
double v1_y = p.curr_pos_y - board.obstacles[k].start_y;
// # 3 MULTs, 1 ADD
double projection = (v1_x * board.obstacles[k].obstacle_v_x + v1_y * board.obstacles[k].obstacle_v_y) * board.obstacles[k].length_sq_inv;
if (projection < 0.0)
projection = 0.0;
else if (projection > 1.0)
projection = 1.0;
// # 4 ADDs, 2 MULTs
double r_aB_x = p.curr_pos_x - (board.obstacles[k].start_x + board.obstacles[k].obstacle_v_x * projection);
double r_aB_y = p.curr_pos_y - (board.obstacles[k].start_y + board.obstacles[k].obstacle_v_y * projection);
// # 1 SQRT, 2 MULTs, 1 ADD
double r_aB_norm = sqrt(r_aB_x * r_aB_x + r_aB_y * r_aB_y);
// # 4 MULTs, 1 EXP, 1 DIV
double scalar_mult = (NEG_U0_AB_div_R * exp(r_aB_norm * NEG_R_INV)) / r_aB_norm;
double f_alpha_B_neg_x = r_aB_x * scalar_mult;
double f_alpha_B_neg_y = r_aB_y * scalar_mult;
double w_val;
double e_dot_f = (f_alpha_B_neg_y == 0) ? 0 : (f_alpha_B_neg_y < 0 ? -p.e_y : p.e_y);
if (e_dot_f >= cos_phi)
w_val = dt_neg;
else
w_val = c_neg_times_dt;
// # 2 MULTs
double f_alpha_B_dt_x = f_alpha_B_neg_x * w_val;
double f_alpha_B_dt_y = f_alpha_B_neg_y * w_val;
// # 2 ADDs
f_alpha_dt_x += f_alpha_B_dt_x;
f_alpha_dt_y += f_alpha_B_dt_y;
}
// # 2 ADDs
p.w_x += f_alpha_dt_x;
p.w_y += f_alpha_dt_y;
}
for (int i = 0; i < n_p; i++) {
Pedestrian &p = pedestrians[i];
// # 1 SQRT, 2 MULTs, 1 ADD
double w_norm = sqrt(p.w_x * p.w_x + p.w_y * p.w_y);
// # 1 DIV
double correction_factor = min(1.0, p.v_max / w_norm);
// # 2 MULTs
p.curr_vel_x = p.w_x * correction_factor;
p.curr_vel_y = p.w_y * correction_factor;
// # 2 MULTs, 2 ADDs
p.curr_pos_x = p.curr_pos_x + p.curr_vel_x * dt;
p.curr_pos_y = p.curr_pos_y + p.curr_vel_y * dt;
if (p.color == 0 && p.curr_pos_x > BOARD_LENGTH_MINUS_ONE_POINT_FIVE) {
p.curr_pos_x = 1.0;
p.destination_y = p.curr_pos_y;
p.w_x = p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
if (p.color == 1 && p.curr_pos_x < 1.5) {
p.curr_pos_x = BOARD_LENGTH_MINUS_ONE;
p.destination_y = p.curr_pos_y;
p.w_x = -p.desired_v0;
p.w_y = 0.0;
p.curr_vel_x = p.w_x;
p.curr_vel_y = p.w_y;
}
p.curr_pos_y = clamp(p.curr_pos_y, WALL_EPS, BOARD_WIDTH_MINUS_WALL_EPS);
// # 2 ADDs
double e_x = p.destination_x - p.curr_pos_x;
double e_y = p.destination_y - p.curr_pos_y;
// # 1 DIV, 1 SQRT, 2 MULTs, 1 ADD
double e_norm_inv = 1.0 / sqrt(e_x * e_x + e_y * e_y);
// # 2 MULTs
p.e_x = e_x * e_norm_inv;
p.e_y = e_y * e_norm_inv;
// # 2 MULTs, 1 ADD
double velocity_norm_sq = p.curr_vel_x * p.curr_vel_x + p.curr_vel_y * p.curr_vel_y;
// # 1 SQRT
double velocity_norm = sqrt(velocity_norm_sq);
// # 5 MULTs
p.s_b_sq = velocity_norm_sq * delta_t_sq;
p.s_b_e_x = p.e_x * (velocity_norm * delta_t);
p.s_b_e_y = p.e_y * (velocity_norm * delta_t);
#if !BENCHMARK
if (dump_path && (t % dump_interval == 0)) {
samples.emplace_back(t + 1, i, p.curr_pos_x, p.curr_pos_y, p.e_x, p.e_y, p.color);
}
#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;
}