我正在学习使用 Python 的 Multiprocessing 包来解决令人尴尬的并行问题，因此我编写了串行和并行版本来确定小于或等于自然数n的素数的数量。根据我从博客文章和Stack Overflow 问题中读到的内容，我想出了以下代码：
串行
import math
import time
def is_prime(start, end):
"""determine how many primes within given range"""
numPrime = 0
for n in range(start, end+1):
isPrime = True
for i in range(2, math.floor(math.sqrt(n))+1):
if n % i == 0:
isPrime = False
break
if isPrime:
numPrime += 1
if start == 1:
numPrime -= 1 # since 1 is not prime
return numPrime
if __name__ == "__main__":
natNum = 0
while natNum < 2:
natNum = int(input('Enter a natural number greater than 1: '))
startTime = time.time()
finalResult = is_prime(1, natNum)
print('Elapsed time:', time.time()-startTime, 'seconds')
print('The number of primes <=', natNum, 'is', finalResult)
平行
import math
import multiprocessing as mp
import numpy
import time
def is_prime(vec, output):
"""determine how many primes in vector"""
numPrime = 0
for n in vec:
isPrime = True
for i in range(2, math.floor(math.sqrt(n))+1):
if n % i == 0:
isPrime = False
break
if isPrime:
numPrime += 1
if vec[0] == 1:
numPrime -= 1 # since 1 is not prime
output.put(numPrime)
def chunks(vec, n):
"""evenly divide list into n chunks"""
for i in range(0, len(vec), n):
yield vec[i:i+n]
if __name__ == "__main__":
natNum = 0
while natNum < 2:
natNum = int(input('Enter a natural number greater than 1: '))
numProc = 0
while numProc < 1:
numProc = int(input('Enter the number of desired parallel processes: '))
startTime = time.time()
numSplits = math.ceil(natNum/numProc)
splitList = list(chunks(tuple(range(1, natNum+1)), numSplits))
output = mp.Queue()
processes = [mp.Process(target=is_prime, args=(splitList[jobID], output))
for jobID in range(numProc)]
for p in processes:
p.start()
for p in processes:
p.join()
print('Elapsed time:', time.time()-startTime, 'seconds')
procResults = [output.get() for p in processes]
finalResult = numpy.sum(numpy.array(procResults))
print('Results from each process:\n', procResults)
print('The number of primes <=', natNum, 'is', finalResult)
这是我得到的n = 10000000 （对于并行我请求 8 个进程）：
$ python serial_prime_test.py
Enter a natural number greater than 1: 10000000
Elapsed time: 162.1960825920105 seconds
The number of primes <= 10000000 is 664579
$ python parallel_prime_test.py
Enter a natural number greater than 1: 10000000
Enter the number of desired parallel processes: 8
Elapsed time: 49.41204643249512 seconds
Results from each process:
[96469, 86603, 83645, 80303, 81796, 79445, 78589, 77729]
The number of primes <= 10000000 is 664579
所以看起来我可以获得超过 3 倍的加速。这是我的问题：
- 显然这不是线性加速，所以我能做得更好（或者我应该实际期望什么样的加速）？
- 看起来阿姆达尔定律回答了这个问题，但我不知道如何确定我的程序的哪一部分是严格串行的。
任何帮助表示赞赏。
编辑：有 4 个物理内核，能够进行超线程。