Which one is faster in Python – threads or processes?

In Python, threads operate within a single process and are limited by the Global Interpreter Lock (GIL), which means only one Python bytecode thread executes at a time. Therefore, multithreading does not increase the speed of CPU-bound tasks.

Processes (multiprocessing) are launched independently and have their own Python interpreter, allowing code to run in parallel on multiple CPU cores.

Thus, for CPU-intensive tasks, processes usually perform faster than threads. For IO-bound tasks, threads can be more efficient because they are simpler and have lower overhead.

Example of using multiprocessing:

from multiprocessing import Pool

def f(x):
    return x * x

if __name__ == '__main__':
    with Pool(4) as p:
        print(p.map(f, [1, 2, 3, 4]))