https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120428
--- Comment #9 from Shawn Xu <shawn at shawnxu dot org> --- (In reply to Jonathan Wakely from comment #8) > (In reply to Shawn Xu from comment #0) > > On x86-64 with avx512, PR115444 caused the following code to vectorize > > sub-optimally: > > What made you blame PR115444 for this? Did you actually bisect it? Yes, but I did the bisection on the original example, which has correct codegen on both 14.2 and 14.3. It seems that the simplified version is slightly different here, which I had overlooked.
