p256MulInternal<>(SB) // s2 = y2 * z1藛3 STy(s2) LDx(y1in) CALL p256SubInternal<>(SB) // r = s2 - s1 STx(r) CALL p256SqrInternal<>(SB) // rsqr = r藛2 STy (rsqr) LDx(h) CALL p256SqrInternal<>(SB) // hsqr = h藛2 STy(hsqr) CALL p256MulInternal<>(SB) // hcub = h藛3 STy(hcub) LDx(y1in) CALL p256MulInternal<>(SB) // y1 * h藛3 STy(s2) LDP hsqr(0*8), (x0, x1) LDP hsqr(2*8), (x2, x3) LDP 0*16(a_ptr), (y0, y1) LDP 1*16(a_ptr), (y2, y3) CALL p256MulInternal<>(SB) // u1 * h藛2 STP (y0, y1), h(0*8) STP (y2, y3), h(2*8) p256MulBy2Inline...

p256MulInternal<>(SB) // s2 = y2 * z1藛3 STy(s2) LDx(y1in) CALL p256SubInternal<>(SB) // r = s2 - s1 STx(r) CALL p256SqrInternal<>(SB) // rsqr = r藛2 STy (rsqr) LDx(h) CALL p256SqrInternal<>(SB) // hsqr = h藛2 STy(hsqr) CALL p256MulInternal<>(SB) // hcub = h藛3 STy(hcub) LDx(y1in) CALL p256MulInternal<>(SB) // y1 * h藛3 STy(s2) LDP hsqr(0*8), (x0, x1) LDP hsqr(2*8), (x2, x3) LDP 0*16(a_ptr), (y0, y1) LDP 1*16(a_ptr), (y2, y3) CALL p256MulInternal<>(SB) // u1 * h藛2 STP (y0, y1), h(0*8) STP (y2, y3), h(2*8) p256MulBy2Inline...

        and
        [`@dataclasses.dataclass`](https://docs.python.org/3/library/dataclasses.html#dataclasses.dataclass)
        from the standard Python library.
    *   Extension types are supported by Keras, tf.data, TF-hub, SavedModel,
        tf.function, control flow ops, py_function, and distribution strategy.
    *   Add "dispatch decorators" that can be used to override the default