Re: [SVE] PR96463 - Optimise svld1rq from vectors

2022-01-03 Thread Richard Biener via Gcc-patches
On Tue, 14 Dec 2021, Prathamesh Kulkarni wrote: > On Tue, 7 Dec 2021 at 19:08, Richard Sandiford > wrote: > > > > Prathamesh Kulkarni writes: > > > On Thu, 2 Dec 2021 at 23:11, Richard Sandiford > > > wrote: > > >> > > >> Prathamesh Kulkarni writes: > > >> > Hi Richard, > > >> > I have attache

Re: [SVE] PR96463 - Optimise svld1rq from vectors

2021-12-14 Thread Prathamesh Kulkarni via Gcc-patches
On Tue, 7 Dec 2021 at 19:08, Richard Sandiford wrote: > > Prathamesh Kulkarni writes: > > On Thu, 2 Dec 2021 at 23:11, Richard Sandiford > > wrote: > >> > >> Prathamesh Kulkarni writes: > >> > Hi Richard, > >> > I have attached a WIP untested patch for PR96463. > >> > IIUC, the PR suggests to t

Re: [SVE] PR96463 - Optimise svld1rq from vectors

2021-12-07 Thread Richard Sandiford via Gcc-patches
Prathamesh Kulkarni writes: > On Thu, 2 Dec 2021 at 23:11, Richard Sandiford > wrote: >> >> Prathamesh Kulkarni writes: >> > Hi Richard, >> > I have attached a WIP untested patch for PR96463. >> > IIUC, the PR suggests to transform >> > lhs = svld1rq ({-1, -1, ...}, &v[0]) >> > into: >> > lhs =

Re: [SVE] PR96463 - Optimise svld1rq from vectors

2021-12-07 Thread Prathamesh Kulkarni via Gcc-patches
On Thu, 2 Dec 2021 at 23:11, Richard Sandiford wrote: > > Prathamesh Kulkarni writes: > > Hi Richard, > > I have attached a WIP untested patch for PR96463. > > IIUC, the PR suggests to transform > > lhs = svld1rq ({-1, -1, ...}, &v[0]) > > into: > > lhs = vec_perm_expr > > if v is vector of 4 ele

Re: [SVE] PR96463 - Optimise svld1rq from vectors

2021-12-02 Thread Richard Sandiford via Gcc-patches
Prathamesh Kulkarni writes: > Hi Richard, > I have attached a WIP untested patch for PR96463. > IIUC, the PR suggests to transform > lhs = svld1rq ({-1, -1, ...}, &v[0]) > into: > lhs = vec_perm_expr > if v is vector of 4 elements, and each element is 32 bits on little > endian target ? > > I am s

[SVE] PR96463 - Optimise svld1rq from vectors

2021-12-02 Thread Prathamesh Kulkarni via Gcc-patches
Hi Richard, I have attached a WIP untested patch for PR96463. IIUC, the PR suggests to transform lhs = svld1rq ({-1, -1, ...}, &v[0]) into: lhs = vec_perm_expr if v is vector of 4 elements, and each element is 32 bits on little endian target ? I am sorry if this sounds like a silly question, but I