Re: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-05 Thread Richard Sandiford
Richard Biener writes: > On Tue, 4 Jun 2024, Richard Sandiford wrote: > >> Richard Biener writes: >> > The following emulates classical interleaving for SLP load permutes >> > that we are unlikely handling natively. This is to handle cases >> > where interleaving (or load/store-lanes) is the opt

Re: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-05 Thread Richard Biener
On Wed, 5 Jun 2024, Richard Biener wrote: > On Tue, 4 Jun 2024, Richard Sandiford wrote: > > > Richard Biener writes: > > > The following emulates classical interleaving for SLP load permutes > > > that we are unlikely handling natively. This is to handle cases > > > where interleaving (or load

RE: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-05 Thread Richard Biener
On Wed, 5 Jun 2024, Tamar Christina wrote: > > -Original Message- > > From: Richard Biener > > Sent: Tuesday, June 4, 2024 3:33 PM > > To: gcc-patches@gcc.gnu.org > > Cc: Richard Sandiford ; Tamar Christina > > > > Subject: [PATCH] [RFC]

Re: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-05 Thread Richard Biener
On Tue, 4 Jun 2024, Richard Sandiford wrote: > Richard Biener writes: > > The following emulates classical interleaving for SLP load permutes > > that we are unlikely handling natively. This is to handle cases > > where interleaving (or load/store-lanes) is the optimal choice for > > vectorizing

RE: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-05 Thread Tamar Christina
> -Original Message- > From: Richard Biener > Sent: Tuesday, June 4, 2024 3:33 PM > To: gcc-patches@gcc.gnu.org > Cc: Richard Sandiford ; Tamar Christina > > Subject: [PATCH] [RFC] lower SLP load permutation to interleaving > > The following emulates classica

Re: [PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-04 Thread Richard Sandiford
Richard Biener writes: > The following emulates classical interleaving for SLP load permutes > that we are unlikely handling natively. This is to handle cases > where interleaving (or load/store-lanes) is the optimal choice for > vectorizing even when we are doing that within SLP. An example > w

[PATCH] [RFC] lower SLP load permutation to interleaving

2024-06-04 Thread Richard Biener
The following emulates classical interleaving for SLP load permutes that we are unlikely handling natively. This is to handle cases where interleaving (or load/store-lanes) is the optimal choice for vectorizing even when we are doing that within SLP. An example would be void foo (int * __restric