Hi Kyrill,

> vect_recog_sat_trunc_pattern only forms .SAT_TRUNC when the target has the
> sstrunc or ustrunc optab for the mode pair, and the backend had neither, even
> though aarch64_<su>qmovn<mode> already matches exactly the RTL those optabs
> describe.  A saturating narrowing loop was therefore vectorised as a pair of
> lamps and a permute:

> Bootstrapped and tested on aarch64-none-linux-gnu.
> Ok for trunk?

OK

Cheers,
Wilco

Reply via email to