allow num of cpus as max_workers as in windows equivalent

import subprocess

import pathlib

import sys

import os

import concurrent.futures

from threading import Lock

    result_dict = dict()

    # run first part in parallel

    with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor:

    with concurrent.futures.ThreadPoolExecutor(max_workers=os.cpu_count()) as executor:

        executor.map(

            run_file, README_FILES_PARALLEL, BIN_PATHS, [result_dict] * len(README_FILES_PARALLEL)

        )