RE: [PATCH]middle-end: rejects loops with nonlinear inductions and early breaks [PR113163]

2024-01-08 Thread Tamar Christina
> -Original Message- > From: Richard Biener > Sent: Monday, January 8, 2024 12:07 PM > To: Tamar Christina > Cc: gcc-patches@gcc.gnu.org; nd ; j...@ventanamicro.com > Subject: Re: [PATCH]middle-end: rejects loops with nonlinear inductions and > early > breaks [P

Re: [PATCH]middle-end: rejects loops with nonlinear inductions and early breaks [PR113163]

2024-01-08 Thread Richard Biener
On Fri, 29 Dec 2023, Tamar Christina wrote: > Hi All, > > We can't support nonlinear inductions other than neg when vectorizing > early breaks and iteration count is known. > > For early break we currently require a peeled epilog but in these cases > we can't compute the remaining values. > >

[PATCH]middle-end: rejects loops with nonlinear inductions and early breaks [PR113163]

2023-12-29 Thread Tamar Christina
Hi All, We can't support nonlinear inductions other than neg when vectorizing early breaks and iteration count is known. For early break we currently require a peeled epilog but in these cases we can't compute the remaining values. Bootstrapped Regtested on aarch64-none-linux-gnu and no issues.