On Thu, 14 Nov 2024, Alex Coplan wrote: > On 29/10/2024 13:45, Richard Biener wrote: > > On Tue, 29 Oct 2024, Richard Biener wrote: > > > > > On Mon, 28 Oct 2024, Alex Coplan wrote: > > > > > > > Currently we only cost gconds for the vector loop while we omit costing > > > > them when analyzing the scalar loop; this unfairly penalizes the vector > > > > loop in the case of loops with early exits. > > > > > > > > This (together with the previous patches) enables us to vectorize > > > > std::find with 64-bit element sizes. > > > > > > OK. > > > > Ah, wait - but we're now costing the scalar IV gcond but we're not > > costing the vector (scalar) IV gcond. So you want to exempt the > > main IV gcond here. > > Hmm, don't we already ignore the main IV since it should be > !STMT_VINFO_RELEVANT_P?
Hmm, indeed. Thus OK. Thanks, Richard. > Sorry for the slow reply. > > Alex > > > > > Richard. > > > > > Thanks, > > > Richard. > > > > > > > gcc/ChangeLog: > > > > > > > > * tree-vect-loop.cc (vect_compute_single_scalar_iteration_cost): > > > > Don't skip over gconds. > > > > --- > > > > gcc/tree-vect-loop.cc | 4 +++- > > > > 1 file changed, 3 insertions(+), 1 deletion(-) > > > > > > > > > > > > > > > > > > -- > > Richard Biener <rguent...@suse.de> > > SUSE Software Solutions Germany GmbH, > > Frankenstrasse 146, 90461 Nuernberg, Germany; > > GF: Ivo Totev, Andrew McDonald, Werner Knoblich; (HRB 36809, AG Nuernberg) > -- Richard Biener <rguent...@suse.de> SUSE Software Solutions Germany GmbH, Frankenstrasse 146, 90461 Nuernberg, Germany; GF: Ivo Totev, Andrew McDonald, Werner Knoblich; (HRB 36809, AG Nuernberg)
