#define half_ctype_add(a, b, outp) *(outp) =
npy_float_to_half(npy_half_to_float(a) + npy_half_to_float(b))
#define half_ctype_subtract(a, b, outp) *(outp) =
npy_float_to_half(npy_half_to_float(a) - npy_half_to_float(b))
#define half_ctype_multiply(a, b, outp) *(outp) =
npy_float_to_half(npy_half_to_float(a) * npy_half_to_float(b))
#define half_ctype_divide(a, b, outp) *(outp) =
npy_float_to_half(npy_half_to_float(a) / npy_half_to_float(b))