Python-在共享内存中使用numpy数组进行多处理

Python-在共享内存中使用numpy数组进行多处理

添加到

@unutbu

（不再可用）和

@Henry Gomersall

的答案中。你可以

shared_arr.get_lock()

在需要时使用来同步访问：

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]

例

import ctypesimport loggingimport multiprocessing as mpfrom contextlib import closingimport numpy as npinfo = mp.get_logger().infodef 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 argumentdef 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()

如果不需要同步访问或创建自己的锁，则mp.Array()没有必要。mp.sharedctypes.RawArray在这种情况下，你可以使用。