Rod-Persky

#include <map>
#include <set>
#include <list>
#include <cmath>
#include <ctime>
#include <deque>
#include <queue>
#include <stack>
#include <string>
#include <bitset>

Rod-Persky

# _______  __   __  _______  ______   _______  _______  _______  ______  #
#|       ||  | |  ||       ||      | |   _   ||       ||       ||      | #
#|   _   ||  | |  ||_     _||  _    ||  |_|  ||_     _||    ___||  _    |#
#|  | |  ||  |_|  |  |   |  | | |   ||       |  |   |  |   |___ | | |   |#
#|  |_|  ||       |  |   |  | |_|   ||       |  |   |  |    ___|| |_|   |#
#|       ||       |  |   |  |       ||   _   |  |   |  |   |___ |       |#
#|_______||_______|  |___|  |______| |__| |__|  |___|  |_______||______| #
#                                                                        #
#  Modern CMake practices and importing the QT scripts by adding it to   #
#    your module path makes things a lot better than it used to be       #

Rod-Persky

int step_8 = size / 8;     int step_8_r = size % 8;
int step_4 = step_8_r / 4; int step_4_r = step_8_r % 4;
int step_2 = step_4_r / 2; int step_2_r = step_4_r % 2;
double value = inital_value;

for (int step_n = 0; step_n < step_8; step_n++){
  int offset = 8 * step_n;
  __m256d a = _mm256_set_pd(values[offset], values[offset + 1], values[offset + 2], values[offset + 3]);
  __m256d b = _mm256_set_pd(values[offset + 4], values[offset + 5], values[offset + 6], values[offset + 7]);
  __m256d sum = _mm256_hadd_pd(a, b);

Rod-Persky

#!/bin/bash -l
#PBS -S /bin/bash
####### RESOURCES SETUP #######
#These commands set up the Grid Environment for your job:
# -N [Job Name]
# -l nodes=[number of cores]
# -l ncpus=[number of cpus required]
# -l mem=[amount of memory required]
# -l walltime=[how long the job can run for]
# -m ae = mail on (a)bort and (e)rror