On Fri, 4 Jul 2025, Richard Sandiford wrote:
> Richard Biener <rguent...@suse.de> writes:
> > @@ -1738,8 +1738,13 @@ protected:
> > unsigned int m_suggested_unroll_factor;
> >
> > /* The suggested mode to be used for a vectorized epilogue or VOIDmode,
> > - determined at finish_cost. */
> > + determined at finish_cost. m_masked_epilogue is epilogue should use
> > + masked vectorization, regardless of the --param
> > vect-partial-vector-usage
>
> Does this mean "m_masked_epilogue is 1 if the epilogue should use..."?
m_masked_epilogue specifies whether the epilogue should use...
sorry for the bad english, fixed as indicated.
> Is 0 valid, and if so, does it override the --param? Or is the override
> only in one direction (to 1)?
Yes, 0 is valid and overrides the --param.
Richard.
>
> Otherwise LGTM too FWIW.
>
> Thanks,
> Richard
>
> > + default. If -1 then the --param setting takes precedence. If the
> > + user explicitly specified --param vect-partial-vector-usage then that
> > + takes precedence. */
> > machine_mode m_suggested_epilogue_mode;
> > + int m_masked_epilogue;
> >
> > /* True if finish_cost has been called. */
> > bool m_finished;
> > @@ -1755,6 +1760,7 @@ vector_costs::vector_costs (vec_info *vinfo, bool
> > costing_for_scalar)
> > m_costs (),
> > m_suggested_unroll_factor(1),
> > m_suggested_epilogue_mode(VOIDmode),
> > + m_masked_epilogue (-1),
> > m_finished (false)
> > {
> > }
> > @@ -1815,9 +1821,10 @@ vector_costs::suggested_unroll_factor () const
> > /* Return the suggested epilogue mode. */
> >
> > inline machine_mode
> > -vector_costs::suggested_epilogue_mode () const
> > +vector_costs::suggested_epilogue_mode (int &masked_p) const
> > {
> > gcc_checking_assert (m_finished);
> > + masked_p = m_masked_epilogue;
> > return m_suggested_epilogue_mode;
> > }
>
--
Richard Biener <rguent...@suse.de>
SUSE Software Solutions Germany GmbH,
Frankenstrasse 146, 90461 Nuernberg, Germany;
GF: Ivo Totev, Andrew McDonald, Werner Knoblich; (HRB 36809, AG Nuernberg)
