X1H p256SubInternal(X1,X0,X1H,X1L,T1,T0) // ADD(Y<X1+T) // T1 = X1+T1 p256AddInternal(Y1,Y0,X1H,X1L,T1,T0) // X- ; Y- ; MUL; T- // T2 = T2*T1 CALL p256MulInternal<>(SB) // ADD(T2<T+T); ADD(T2<T2+T) // T2 = 3*T2 p256AddInternal(T2H,T2L,T1,T0,T1,T0) p256AddInternal(T2H,T2L,T2H,T2L,T1,T0) // ADD(X<Y1+Y1) // Y3 = 2*Y1 LXVD2X (R17)(P1ptr), Y1L LXVD2X (R18)(P1ptr), Y1H XXPERMDI Y1L, Y1L, $2, Y1L XXPERMDI Y1H, Y1H, $2, Y1H p256AddInternal(X1,X0,Y1H,Y1L,Y1H,Y1L) // X- ; Y=Z1; MUL; Z3:=T // Z3 = Y3*Z1 LXVD2X...