Numba

from numba import njit, prange
import numpy as np

@njit(parallel=True)
def test(x):
    n = x.shape[0]
    a = np.sin(x)
    b = np.cos(a * a)
    acc = 0
    for i in prange(n - 2):
        for j in prange(n - 1):
            acc += b[i] + b[j + 1]
    return acc

test(np.arange(10))

test.parallel_diagnostics(level=4)

#!/usr/bin/env python
from __future__ import print_function, division, absolute_import

import math
import threading
from timeit import repeat

import numpy as np
from numba import jit

nthreads = 4
size = 10**6

def func_np(a, b):
    """
    Control function using Numpy.
    """
    return np.exp(2.1 * a + 3.2 * b)

@jit('void(double[:], double[:], double[:])', nopython=True, nogil=True)
def inner_func_nb(result, a, b):
    """
    Function under test.
    """
    for i in range(len(result)):
        result[i] = math.exp(2.1 * a[i] + 3.2 * b[i])

def timefunc(correct, s, func, *args, **kwargs):
    """
    Benchmark *func* and print out its runtime.
    """
    print(s.ljust(20), end=" ")
    # Make sure the function is compiled before we start the benchmark
    res = func(*args, **kwargs)
    if correct is not None:
        assert np.allclose(res, correct), (res, correct)
    # time it
    print('{:>5.0f} ms'.format(min(repeat(lambda: func(*args, **kwargs),
                                          number=5, repeat=2)) * 1000))
    return res

def make_singlethread(inner_func):
    """
    Run the given function inside a single thread.
    """
    def func(*args):
        length = len(args[0])
        result = np.empty(length, dtype=np.float64)
        inner_func(result, *args)
        return result
    return func

def make_multithread(inner_func, numthreads):
    """
    Run the given function inside *numthreads* threads, splitting its
    arguments into equal-sized chunks.
    """
    def func_mt(*args):
        length = len(args[0])
        result = np.empty(length, dtype=np.float64)
        args = (result,) + args
        chunklen = (length + numthreads - 1) // numthreads
        # Create argument tuples for each input chunk
        chunks = [[arg[i * chunklen:(i + 1) * chunklen] for arg in args]
                  for i in range(numthreads)]
        # Spawn one thread per chunk
        threads = [threading.Thread(target=inner_func, args=chunk)
                   for chunk in chunks]
        for thread in threads:
            thread.start()
        for thread in threads:
            thread.join()
        return result
    return func_mt


func_nb = make_singlethread(inner_func_nb)
func_nb_mt = make_multithread(inner_func_nb, nthreads)

a = np.random.rand(size)
b = np.random.rand(size)

correct = timefunc(None, "numpy (1 thread)", func_np, a, b)
timefunc(correct, "numba (1 thread)", func_nb, a, b)
timefunc(correct, "numba (%d threads)" % nthreads, func_nb_mt, a, b)

from numba import cuda

# 현재 사용 중인 디바이스 해제
cuda.select_device(0)
cuda.close()

with the_ipc_array_handle as ipc_array:
    # use ipc_array here as a normal gpu array object
    some_code(ipc_array)

# ipc_array is dead at this point

import numpy as np
from numba import cuda
from time import sleep
from pickle import dumps

# CUDA 장치에서 배열을 생성합니다.
data = np.arange(10, dtype=np.float32)
d_data = cuda.to_device(data)

# IPC 핸들을 생성합니다.
ipc_handle = d_data.get_ipc_handle()

# IPC 핸들을 직렬화하여 다른 프로세스에 전달할 수 있습니다.
serialized_handle = dumps(ipc_handle)

# serialized_handle을 파일이나 다른 방법으로 다른 프로세스에 전달합니다.
with open('ipc_handle.bin', 'wb') as f:
    f.write(serialized_handle)


while True:
    sleep(1)
    print(".", end="", flush=True)

from numba import cuda
from pickle import loads

# serialized_handle을 파일이나 다른 방법으로 수신합니다.
with open('ipc_handle.bin', 'rb') as f:
    serialized_handle = f.read()

# IPC 핸들을 역직렬화합니다.
ipc_handle = loads(serialized_handle)

# 핸들을 통해 배열에 접근합니다.
d_data = ipc_handle.open()
data = d_data.copy_to_host()

print(data)