This is the mail archive of the gcc-bugs@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[Bug target/52492] [4.6/4.7/4.8 Regression] -ftree-vectorize optimization bug


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=52492

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Target|                            |x86_64-*-*
             Status|UNCONFIRMED                 |NEW
      Known to work|                            |4.5.3
           Keywords|                            |wrong-code
   Last reconfirmed|                            |2012-03-05
          Component|c++                         |target
     Ever Confirmed|0                           |1
            Summary|-ftree-vectorize            |[4.6/4.7/4.8 Regression]
                   |optimization bug            |-ftree-vectorize
                   |                            |optimization bug
   Target Milestone|---                         |4.6.4
      Known to fail|                            |4.6.3, 4.7.0

--- Comment #1 from Richard Guenther <rguenth at gcc dot gnu.org> 2012-03-05 14:33:05 UTC ---
Confirmed.

   0x0000000000400bc3 <+188>:   mov    $0x0,%esi
=> 0x0000000000400bc8 <+193>:   psubusw (%rcx),%xmm0

and rcx is 0x603051, thus this is an unaligned access.  We're expanding
MAX_EXPR, so I suspect a target bug for now.

4.5.x works.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]