Use numpy array in shared memory for multiprocessing

Question

I would like to use a numpy array in shared memory for use with the multiprocessing module. The difficulty is using it like a numpy array, and not just as a ctypes array.

from multiprocessing import Process, Array
import scipy

def f(a):
    a[0] = -a[0]

if __name__ == '__main__':
    # Create the array
    N = int(10)
    unshared_arr = scipy.rand(N)
    arr = Array('d', unshared_arr)
    print "Originally, the first two elements of arr = %s"%(arr[:2])

    # Create, start, and finish the child processes
    p = Process(target=f, args=(arr,))
    p.start()
    p.join()

    # Printing out the changed values
    print "Now, the first two elements of arr = %s"%arr[:2]

This produces output such as:

Originally, the first two elements of arr = [0.3518653236697369, 0.517794725524976]
Now, the first two elements of arr = [-0.3518653236697369, 0.517794725524976]

The array can be accessed in a ctypes manner, e.g. arr[i] makes sense. However, it is not a numpy array, and I cannot perform operations such as -1*arr, or arr.sum(). I suppose a solution would be to convert the ctypes array into a numpy array. However (besides not being able to make this work), I don't believe it would be shared anymore.

It seems there would be a standard solution to what has to be a common problem.

Answer 1

To add to @unutbu's (not available anymore) and @Henry Gomersall's answers. You could use shared_arr.get_lock() to synchronize access when needed:

shared_arr = mp.Array(ctypes.c_double, N)
# ...
def f(i): # could be anything numpy accepts as an index such another numpy array
    with shared_arr.get_lock(): # synchronize access
        arr = np.frombuffer(shared_arr.get_obj()) # no data copying
        arr[i] = -arr[i]

Example

import ctypes
import logging
import multiprocessing as mp

from contextlib import closing

import numpy as np

info = mp.get_logger().info

def main():
    logger = mp.log_to_stderr()
    logger.setLevel(logging.INFO)

    # create shared array
    N, M = 100, 11
    shared_arr = mp.Array(ctypes.c_double, N)
    arr = tonumpyarray(shared_arr)

    # fill with random values
    arr[:] = np.random.uniform(size=N)
    arr_orig = arr.copy()

    # write to arr from different processes
    with closing(mp.Pool(initializer=init, initargs=(shared_arr,))) as p:
        # many processes access the same slice
        stop_f = N // 10
        p.map_async(f, [slice(stop_f)]*M)

        # many processes access different slices of the same array
        assert M % 2 # odd
        step = N // 10
        p.map_async(g, [slice(i, i + step) for i in range(stop_f, N, step)])
    p.join()
    assert np.allclose(((-1)**M)*tonumpyarray(shared_arr), arr_orig)

def init(shared_arr_):
    global shared_arr
    shared_arr = shared_arr_ # must be inherited, not passed as an argument

def tonumpyarray(mp_arr):
    return np.frombuffer(mp_arr.get_obj())

def f(i):
    """synchronized."""
    with shared_arr.get_lock(): # synchronize access
        g(i)

def g(i):
    """no synchronization."""
    info("start %s" % (i,))
    arr = tonumpyarray(shared_arr)
    arr[i] = -1 * arr[i]
    info("end   %s" % (i,))

if __name__ == '__main__':
    mp.freeze_support()
    main()

If you don't need synchronized access or you create your own locks then mp.Array() is unnecessary. You could use mp.sharedctypes.RawArray in this case.