from fastcore.test import *
from nbdev.showdoc import *
from fastcore.nb_imports import *

threaded[source]

threaded(f)

Run f in a thread, and returns the thread

@threaded
def _1():
    time.sleep(0.05)
    print("second")

@threaded
def _2():
    time.sleep(0.01)
    print("first")

_1()
_2()
time.sleep(0.1)

first
second

startthread[source]

startthread(f)

Like threaded, but start thread immediately

@startthread
def _():
    time.sleep(0.05)
    print("second")

@startthread
def _():
    time.sleep(0.01)
    print("first")

time.sleep(0.1)

first
second

set_num_threads[source]

set_num_threads(nt)

Get numpy (and others) to use nt threads

This sets the number of threads consistently for many tools, by:

1. Set the following environment variables equal to nt: OPENBLAS_NUM_THREADS,NUMEXPR_NUM_THREADS,OMP_NUM_THREADS,MKL_NUM_THREADS
2. Sets nt threads for numpy and pytorch.

parallelable[source]

parallelable(param_name, num_workers, f=None)

class ThreadPoolExecutor[source]

ThreadPoolExecutor(max_workers=2, on_exc=print, pause=0, **kwargs) :: ThreadPoolExecutor

Same as Python's ThreadPoolExecutor, except can pass max_workers==0 for serial execution

class ProcessPoolExecutor[source]

ProcessPoolExecutor(max_workers=2, on_exc=print, pause=0, **kwargs) :: ProcessPoolExecutor

Same as Python's ProcessPoolExecutor, except can pass max_workers==0 for serial execution

parallel[source]

parallel(f, items, *args, n_workers=2, total=None, progress=None, pause=0, threadpool=False, timeout=None, chunksize=1, **kwargs)

Applies func in parallel to items, using n_workers

add_one[source]

add_one(x, a=1)

inp,exp = range(50),range(1,51)

test_eq(parallel(add_one, inp, n_workers=2, progress=False), exp)
test_eq(parallel(add_one, inp, threadpool=True, n_workers=2, progress=False), exp)
test_eq(parallel(add_one, inp, n_workers=1, a=2), range(2,52))
test_eq(parallel(add_one, inp, n_workers=0), exp)
test_eq(parallel(add_one, inp, n_workers=0, a=2), range(2,52))

Use the pause parameter to ensure a pause of pause seconds between processes starting. This is in case there are race conditions in starting some process, or to stagger the time each process starts, for example when making many requests to a webserver. Set threadpool=True to use ThreadPoolExecutor instead of ProcessPoolExecutor.

from datetime import datetime

def print_time(i): 
    time.sleep(random.random()/1000)
    print(i, datetime.now())

parallel(print_time, range(5), n_workers=2, pause=0.25);

0 2022-04-03 01:25:58.938402
1 2022-04-03 01:25:59.189256
2 2022-04-03 01:25:59.439853
3 2022-04-03 01:25:59.691909
4 2022-04-03 01:25:59.943055

def die_sometimes(x):
#     if 3<x<6: raise Exception(f"exc: {x}")
    return x*2

parallel(die_sometimes, range(8))

(#8) [0,2,4,6,8,10,12,14]

run_procs[source]

run_procs(f, f_done, args)

Call f for each item in args in parallel, yielding f_done

parallel_gen[source]

parallel_gen(items, n_workers=2, **kwargs)

Instantiate cls in n_workers procs & call each on a subset of items in parallel.

class _C:
    def __call__(self, o): return ((i+1) for i in o)

items = range(5)

res = L(parallel_gen(_C, items, n_workers=0))
idxs,dat1 = zip(*res.sorted(itemgetter(0)))
test_eq(dat1, range(1,6))

res = L(parallel_gen(_C, items, n_workers=3))
idxs,dat2 = zip(*res.sorted(itemgetter(0)))
test_eq(dat2, dat1)

cls is any class with __call__. It will be passed args and kwargs when initialized. Note that n_workers instances of cls are created, one in each process. items are then split in n_workers batches and one is sent to each cls. The function then returns a generator of tuples of item indices and results.

class TestSleepyBatchFunc:
    "For testing parallel processes that run at different speeds"
    def __init__(self): self.a=1
    def __call__(self, batch):
        for k in batch:
            time.sleep(random.random()/4)
            yield k+self.a

x = np.linspace(0,0.99,20)

res = L(parallel_gen(TestSleepyBatchFunc, x, n_workers=2))
test_eq(res.sorted().itemgot(1), x+1)