[Bug tree-optimization/91094] BB vectorization is too quick to disable itself because of possible unrolling needed

[rguenth at gcc dot gnu.org via Gcc-bugs]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=91094

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|ASSIGNED                    |RESOLVED
         Resolution|---                         |FIXED

--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
With SSE4.2 we generate

        movq    b(%rip), %xmm0
        movq    b+8(%rip), %xmm1
        paddd   %xmm1, %xmm0
        pmovsxdq        %xmm0, %xmm0
        movaps  %xmm0, a(%rip)

now, thus fixed.  The x264_pixel_satd_8x4 issue is PR98138.