[Bug rtl-optimization/51041] g++ strange optimisation behaviour

[pinskia at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=51041

Andrew Pinski <pinskia at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |missed-optimization, ra
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2011-11-08
          Component|other                       |rtl-optimization
     Ever Confirmed|0                           |1

--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> 2011-11-08 22:31:08 UTC ---
.L10:
    movsd    (%rbx,%rdx,8), %xmm0
    mulsd    0(%rbp,%rdx,8), %xmm0
    addq    $1, %rdx
    cmpq    $10000, %rdx
    addsd    %xmm0, %xmm2
    jne    .L10

vs:
.L10:
    movsd    (%rbx,%rdx,8), %xmm0
    mulsd    0(%rbp,%rdx,8), %xmm0
    addq    $1, %rdx
    cmpq    $10000, %rdx
    addsd    (%rsp), %xmm0
    movsd    %xmm0, (%rsp)
    jne    .L10

With -fno-exceptions I get the RA to act better again.