Re: RFA: Avoid versioning loop with unaligned step

2018-12-20 Thread Jakub Jelinek
On Fri, Dec 21, 2018 at 12:46:41AM +0100, Jakub Jelinek wrote: > The following patch makes it build again, will commit as obvious if it > passes bootstrap/regtest: > > 2018-12-21 Jakub Jelinek > > * tree-vect-data-refs.c (vect_enhance_data_refs_alignment): Use > DR_TARGET_ALIGNMENT

Re: RFA: Avoid versioning loop with unaligned step

2018-12-20 Thread Jakub Jelinek
On Thu, Dec 20, 2018 at 07:46:31PM +, Richard Sandiford wrote: > > vect_compute_data_ref_alignment uses DR_TARGET_ALIGNMENT > > and DR_STEP_ALIGNMENT () % dr_target-alignment == 0 as check. > > > > I think it's preferable to use the same or similar values for the desired > > alignment. > > Yea

Re: RFA: Avoid versioning loop with unaligned step

2018-12-20 Thread Richard Sandiford
Richard Biener writes: > On Thu, Dec 20, 2018 at 2:43 PM Joern Wolfgang Rennecke > wrote: >> >> eSi-RISC has vector permute functionality, but no unaligned loads. We >> see execution failures on gcc.dg/vect/slp-perm-12.c because loop >> versioning is used to make the tptr aligned for the first l

Re: RFA: Avoid versioning loop with unaligned step

2018-12-20 Thread Richard Biener
On Thu, Dec 20, 2018 at 2:43 PM Joern Wolfgang Rennecke wrote: > > eSi-RISC has vector permute functionality, but no unaligned loads. We > see execution failures on gcc.dg/vect/slp-perm-12.c because loop > versioning is used to make the tptr aligned for the first loop > iteration, and then with a