// Y1H LXVD2X (R18)(P1ptr), Y1 // Y1L XXPERMDI Y0, Y0, $2, Y0 XXPERMDI Y1, Y1, $2, Y1 CALL p256MulInternal<>(SB) // SUB(T<T3-T) Y3:=T // Y3 = T3-T4 T3 T4 (T3 = Y3) p256SubInternal(Y3H,Y3L,T3H,T3L,T1,T0) // if (sel == 0) { // copy(P3.x[:], X1) // copy(P3.y[:], Y1) // copy(P3.z[:], Z1) // } LXVD2X (R0)(P1ptr), X1L LXVD2X (R16)(P1ptr), X1H XXPERMDI X1H, X1H, $2, X1H XXPERMDI X1L, X1L, $2, X1L // Y1 already loaded, left over from addition LXVD2X (R19)(P1ptr), Z1L LXVD2X (R20)(P1ptr), Z1H XXPERMDI Z1H,...