foo.py

from numba import cuda
import numpy as np
import cupy

def gather_from_detector():
    return cupy.random.random((1000, 1000), dtype="float32")


@cuda.jit
def smooth_gpu(x, out):
    i, j = cuda.grid(2)
    n, m = x.shape
    if 1 <= i < n - 1 and 1 <= j < m - 1:
        out[i, j] = (x[i - 1, j - 1] + x[i - 1, j] + x[i - 1, j + 1] +
                     x[i    , j - 1] + x[i    , j] + x[i    , j + 1] +
                     x[i + 1, j - 1] + x[i + 1, j] + x[i + 1, j + 1]) // 9


def smooth(x):
    out = cupy.empty_like(x)
    smooth_gpu[2, 32](x, out)
    return out


def save(x, filename):
    pass