working one

this one works

import numpy as np
import numba
from numba import cuda
import math





@cuda.jit(argtypes=[numba.int32[:]], debug=True)
def kernel(arr):
    def expensive(x):
        return math.pow(x, 1.001)

    def cheap(x):
        return math.sqrt(x)
    def calc(x):
        s1 = expensive(x)
        q = cheap(s1)
        return q + 1

    def threadid():
        return cuda.blockDim.x * cuda.blockIdx.x + cuda.threadIdx.x

    for i in range(1000):
        arr[threadid()] = calc(arr[threadid()])


def main():
    print("SUP")
    z = np.array(range(0, 5000))
    print(z)
    kernel[5000//128+1, 128](z)
    print(z)


if __name__ == '__main__':
    main()