[Bug middle-end/79665] gcc's signed (x*x)/200 is slower than clang's

[tulipawn at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79665

--- Comment #13 from PeteVine <tulipawn at gmail dot com> ---
Still, the 5% regression must have happened very recently. The fast gcc was
built on 20170220 and the slow one yesterday, using the original patch. Once
again, switching away from Cortex-A53 codegen restores the expected
performance.