# import sys
# import numpy as np
# from timeit import Timer
# print(np.__version__, sys.version)
# # results sensitive to hardware cache size
# n = 5
# sizes = [2**20, 2**21, 2**22, 2**23]
# stmts = [
#     'np.zeros(({},))',
#     'np.random.rand({})',
#     'np.linspace(0,1,{})',
#     'np.exp(np.zeros(({},)))',
# ]
# for stmt in stmts:
#     for size in sizes:
#         s = stmt.format(size)
#         print(s+':')
#         t = Timer(s, globals=globals()).timeit(n)
#         print(f'\t{size/n/t} elements/second')
#!/usr/bin/env python3



import sys
import time
import concurrent.futures
import numpy as np

SIZE = 16 * 1024 * 1024
PASSES = 100
THREADS = 64

print(np.__version__, sys.version)
with open('/sys/kernel/mm/transparent_hugepage/enabled') as f:
    print(f.read())

def work(thread_id):
    arrs = []
    for i in range(PASSES):
        arrs.append(np.ones(SIZE, np.uint8))
    np.stack(arrs)

with concurrent.futures.ThreadPoolExecutor(THREADS) as pool:
    start = time.monotonic()
    list(pool.map(work, range(THREADS)))
    stop = time.monotonic()
    print(stop - start)


# import time
# import numpy as np
# start = time.monotonic()
# N_GB = 10
# a = np.ones(N_GB * 1024 * 1024 * 1024, 'ubyte')
# stop = time.monotonic()
# print(stop - start)