谿瑚: https://blog.dominodatalab.com/simple-parallelization/
from joblib import Parallel, delayed
import multiprocessing
     
# what are your inputs, and what operation do you want to 
# perform on each input. For example...
L1 = [1,2,3,4]
L2 = [5,6,7,8]
def processInput(i, j):
    return i * i + j
 
num_cores = multiprocessing.cpu_count()
results = Parallel(n_jobs=num_cores)(delayed(processInput)(i,j) for i,j in tuple(zip(L1, L2)))