[Bug target/91818] SSE optimization flaw with float vs. double

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91818

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |RESOLVED
         Resolution|---                         |INVALID

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
It's a feature, using vrsqrtps plus newton raphson is supposed to be faster
than vsqrtps.