Re: [PATCH] Maintain (mis-)alignment info in the first element of a group

2021-09-15 Thread Richard Sandiford via Gcc-patches
Richard Biener via Gcc-patches writes: > On Wed, 15 Sep 2021, Richard Sandiford wrote: >> Richard Biener writes: >> > On Tue, 14 Sep 2021, Richard Sandiford wrote: >> > >> >> Richard Biener via Gcc-patches writes: >> >> > This changes us to maintain and compute (mis-)alignment info for >> >> > t

Re: [PATCH] Maintain (mis-)alignment info in the first element of a group

2021-09-15 Thread Richard Biener via Gcc-patches
On Wed, 15 Sep 2021, Richard Sandiford wrote: > Richard Biener writes: > > On Tue, 14 Sep 2021, Richard Sandiford wrote: > > > >> Richard Biener via Gcc-patches writes: > >> > This changes us to maintain and compute (mis-)alignment info for > >> > the first element of a group only rather than fo

Re: [PATCH] Maintain (mis-)alignment info in the first element of a group

2021-09-15 Thread Richard Sandiford via Gcc-patches
Richard Biener writes: > On Tue, 14 Sep 2021, Richard Sandiford wrote: > >> Richard Biener via Gcc-patches writes: >> > This changes us to maintain and compute (mis-)alignment info for >> > the first element of a group only rather than for each DR when >> > doing interleaving and for the earliest

Re: [PATCH] Maintain (mis-)alignment info in the first element of a group

2021-09-14 Thread Richard Biener via Gcc-patches
On Tue, 14 Sep 2021, Richard Sandiford wrote: > Richard Biener via Gcc-patches writes: > > This changes us to maintain and compute (mis-)alignment info for > > the first element of a group only rather than for each DR when > > doing interleaving and for the earliest, first, or first in the SLP >

Re: [PATCH] Maintain (mis-)alignment info in the first element of a group

2021-09-14 Thread Richard Sandiford via Gcc-patches
Richard Biener via Gcc-patches writes: > This changes us to maintain and compute (mis-)alignment info for > the first element of a group only rather than for each DR when > doing interleaving and for the earliest, first, or first in the SLP > node (or any pair or all three of those) when SLP vecto