minor performance improvements for philox

def uint32(x):

    """Converts (N,) np.uint64 array into (2, N) np.unit32 array."""

    return np.moveaxis(x.view(np.uint32).reshape(-1, 2), 0, 1)

    return x.view(np.uint32).reshape(-1, 2).transpose(1, 0)

def philox4_round(counter, key):

def box_muller(x, y):

    """Returns just the first out of two numbers generated by Box–Muller transform algorithm."""

    u = x.astype(np.float32) * two_pow32_inv + two_pow32_inv / 2

    v = y.astype(np.float32) * two_pow32_inv_2pi + two_pow32_inv_2pi / 2

    u = x * two_pow32_inv + two_pow32_inv / 2

    v = y * two_pow32_inv_2pi + two_pow32_inv_2pi / 2

    s = np.sqrt(-2.0 * np.log(u))

        counter[2] = np.arange(n, dtype=np.uint32)  # up to 2^32 numbers can be generated - if you want more you'd need to spill into counter[3]

        self.offset += 1

        key = uint32(np.array([[self.seed] * n], dtype=np.uint64))

        key = np.empty(n, dtype=np.uint64)

        key.fill(self.seed)

        key = uint32(key)

        g = philox4_32(counter, key)