Try numba

run.py

#!/usr/bin/env python3
from numba import jit
from numpy import arange
import cProfile


##@jit
def sum2d(arr):
    M, N = arr.shape
    result = 0.0
    for i in range(M):
        for j in range(N):
            result += arr[i,j]
    return result

a = arange(3000*3000).reshape(3000, 3000)

cProfile.run('sum2d(a)')

"""
without @jit

$ ./run.py
         4 function calls in 2.482 seconds

   Ordered by: standard name

   ncalls  tottime  percall  cumtime  percall filename:lineno(function)
        1    0.000    0.000    2.482    2.482 <string>:1(<module>)
        1    2.482    2.482    2.482    2.482 run.py:8(sum2d)
        1    0.000    0.000    2.482    2.482 {built-in method exec}
        1    0.000    0.000    0.000    0.000 {method 'disable' of '_lsprof.Profiler' objects}
"""

"""
with jit

$ ./run.py
         76244 function calls (69807 primitive calls) in 0.105 seconds

   Ordered by: standard name

   ncalls  tottime  percall  cumtime  percall filename:lineno(function)
        2    0.000    0.000    0.000    0.000 <frozen importlib._bootstrap>:2264(_handle_fromlist)
        1    0.017    0.017    0.105    0.105 <string>:1(<module>)
        1    0.000    0.000    0.000    0.000 <string>:12(__new__)
        1    0.000    0.000    0.000    0.000 __init__.py:41(__init__)
        2    0.000    0.000    0.000    0.000 __init__.py:47(create_string_buffer)
        4    0.000    0.000    0.000    0.000 __init__.py:487(cast)
        ......
"""