Which solution in Python is preferable for parallel execution of resource-intensive tasks: using threads or processes?

For resource-intensive tasks in Python, it is preferable to use multiprocessing (the multiprocessing module) rather than threads (threading).

This is because the standard implementation of Python (CPython) has a GIL (Global Interpreter Lock), which prevents multiple threads from executing Python bytecode simultaneously. As a result, threads do not provide a performance boost for CPU-intensive tasks.

Example of using multiprocessing:

from multiprocessing import Pool

def heavy_task(x):
    # some resource-intensive operation
    return x * x

if __name__ == '__main__':
    with Pool(4) as p:
        results = p.map(heavy_task, range(10))
    print(results)

Thus, for CPU-intensive tasks, it is better to use processes, and for I/O-intensive tasks, threads.