https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121536
--- Comment #2 from Tamar Christina <tnfchris at gcc dot gnu.org> --- (In reply to Jennifer Schmitz from comment #0) > > Comparing the 185t.vect dumps shows that scalar_stmt previously cost 2, > while it now costs 1, making vectorization less profitable. > Yeah it looks like we were abusing the vectype during scalar costing. because it's now NULL we interpret the scalar instructions as GPR rather than FPR. The throughput costing doesn't have this bug, which is why the vector costing I pasted above didn't change. Testing a patch.
