Re: [vect] PR103997: Fix epilogue mode skipping

On 19/01/2022 11:04, Richard Biener wrote: On Tue, 18 Jan 2022, Andre Vieira (lists) wrote: On 14/01/2022 09:57, Richard Biener wrote: The 'used_vector_modes' is also a heuristic by itself since it registers every vector type we query, not only those that are used in the end ... So it's real

Re: [vect] PR103997: Fix epilogue mode skipping

On Tue, 18 Jan 2022, Andre Vieira (lists) wrote: > > On 14/01/2022 09:57, Richard Biener wrote: > > > > The 'used_vector_modes' is also a heuristic by itself since it registers > > every vector type we query, not only those that are used in the end ... > > > > So it's really all heuristics that c

Re: [vect] PR103997: Fix epilogue mode skipping

On 14/01/2022 09:57, Richard Biener wrote: The 'used_vector_modes' is also a heuristic by itself since it registers every vector type we query, not only those that are used in the end ... So it's really all heuristics that can eventually go bad. IMHO remembering the VF that we ended up with (

Re: [vect] PR103997: Fix epilogue mode skipping

On Fri, 14 Jan 2022, Andre Vieira (lists) wrote: > > On 14/01/2022 07:08, Richard Biener wrote: > > On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > > > >> On 13/01/2022 14:25, Richard Biener wrote: > >>> On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > >>> > On 13/01/2022 12:36, Richard

Re: [vect] PR103997: Fix epilogue mode skipping

On 14/01/2022 07:08, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: On 13/01/2022 14:25, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: On 13/01/2022 12:36, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: This time t

Re: [vect] PR103997: Fix epilogue mode skipping

On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > > On 13/01/2022 14:25, Richard Biener wrote: > > On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > > > >> On 13/01/2022 12:36, Richard Biener wrote: > >>> On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > >>> > This time to the list too (s

Re: [vect] PR103997: Fix epilogue mode skipping

On 13/01/2022 14:25, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: On 13/01/2022 12:36, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: This time to the list too (sorry for double email) Hi, The original patch '[vect] Re-analyze all modes f

Re: [vect] PR103997: Fix epilogue mode skipping

On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > > On 13/01/2022 12:36, Richard Biener wrote: > > On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > > > >> This time to the list too (sorry for double email) > >> > >> Hi, > >> > >> The original patch '[vect] Re-analyze all modes for epilogues',

Re: [vect] PR103997: Fix epilogue mode skipping

On 13/01/2022 12:36, Richard Biener wrote: On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: This time to the list too (sorry for double email) Hi, The original patch '[vect] Re-analyze all modes for epilogues', skipped modes that should not be skipped since it used the vector mode provided

Re: [vect] PR103997: Fix epilogue mode skipping

On Thu, 13 Jan 2022, Andre Vieira (lists) wrote: > This time to the list too (sorry for double email) > > Hi, > > The original patch '[vect] Re-analyze all modes for epilogues', skipped modes > that should not be skipped since it used the vector mode provided by > autovectorize_vector_modes to d

[vect] PR103997: Fix epilogue mode skipping

This time to the list too (sorry for double email) Hi, The original patch '[vect] Re-analyze all modes for epilogues', skipped modes that should not be skipped since it used the vector mode provided by autovectorize_vector_modes to derive the minimum VF required for it. However, those modes s