On Tue, 9 Nov 2021, Tamar Christina wrote:
> > > + bitmap_set_bit (exit_bbs, single_exit (loop)->dest->index);
> > > + bitmap_set_bit (exit_bbs, loop->latch->index);
> >
> > treating the latch as exit is probably premature optimization (yes, it's
> > empty).
> >
> > > +
> > > +
> > + bitmap_set_bit (exit_bbs, single_exit (loop)->dest->index);
> > + bitmap_set_bit (exit_bbs, loop->latch->index);
>
> treating the latch as exit is probably premature optimization (yes, it's
> empty).
>
> > +
> > + do_rpo_vn (cfun, loop_preheader_edge (loop), exit_bbs);
> >
> >
> > > >> > -Original Message-
> > > >> > From: Richard Biener
> > > >> > Sent: Tuesday, November 2, 2021 2:24 PM
> > > >> > To: Tamar Christina
> > > >> > Cc: gcc-patches@gcc.gnu.org; nd
> -Original Message-
> From: Richard Biener
> Sent: Tuesday, November 2, 2021 6:22 PM
> To: Richard Sandiford
> Cc: Richard Biener via Gcc-patches ; Tamar
> Christina ; nd
> Subject: Re: [PATCH]middle-end Add an RPO pass after successful
> vectorization
2:24 PM
> >> > To: Tamar Christina
> >> > Cc: gcc-patches@gcc.gnu.org; nd
> >> > Subject: Re: [PATCH]middle-end Add an RPO pass after successful
> >> > vectorization
> >> >
> >> > On Tue, 2 Nov 2021, Tamar Christina wrote:
> &g
Richard Biener via Gcc-patches writes:
> On Tue, 2 Nov 2021, Tamar Christina wrote:
>
>> > -Original Message-
>> > From: Richard Biener
>> > Sent: Tuesday, November 2, 2021 2:24 PM
>> > To: Tamar Christina
>> > Cc: gcc-patches@gcc.g
On Tue, 2 Nov 2021, Tamar Christina wrote:
> > -Original Message-
> > From: Richard Biener
> > Sent: Tuesday, November 2, 2021 2:24 PM
> > To: Tamar Christina
> > Cc: gcc-patches@gcc.gnu.org; nd
> > Subject: Re: [PATCH]middle-end Add an RPO pas
> -Original Message-
> From: Richard Biener
> Sent: Tuesday, November 2, 2021 2:24 PM
> To: Tamar Christina
> Cc: gcc-patches@gcc.gnu.org; nd
> Subject: Re: [PATCH]middle-end Add an RPO pass after successful
> vectorization
>
> On Tue, 2 Nov 2021, Tamar Chr
On Tue, 2 Nov 2021, Tamar Christina wrote:
> Hi All,
>
> Following my current SVE predicate optimization series a problem has presented
> itself in that the way vector masks are generated for masked operations relies
> on CSE to share masks efficiently.
>
> The issue however is that masking is
