[Bug rtl-optimization/57534] Performance regression versus 4.7.3, 4.8.1 is ~15% slower

[ncahill_alt at yahoo dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=57534

--- Comment #1 from ncahill_alt at yahoo dot com ---
Here is the 4.7.3 output for comparison:

 8048702:       83 ef 08                sub    $0x8,%edi
 8048705:       d9 ee                   fldz   
 8048707:       d9 c0                   fld    %st(0)
 8048709:       8d b4 26 00 00 00 00    lea    0x0(%esi,%eiz,1),%esi
 8048710:       dd 04 de                fldl   (%esi,%ebx,8)
 8048713:       8d 43 08                lea    0x8(%ebx),%eax
 8048716:       dc 44 de 08             faddl  0x8(%esi,%ebx,8)
 804871a:       39 c7                   cmp    %eax,%edi
 804871c:       dc 44 de 10             faddl  0x10(%esi,%ebx,8)
 8048720:       dc 44 de 18             faddl  0x18(%esi,%ebx,8)
 8048724:       de c2                   faddp  %st,%st(2)
 8048726:       dd 44 de 20             fldl   0x20(%esi,%ebx,8)
 804872a:       dc 44 de 28             faddl  0x28(%esi,%ebx,8)
 804872e:       dc 44 de 30             faddl  0x30(%esi,%ebx,8)
 8048732:       dc 44 de 38             faddl  0x38(%esi,%ebx,8)
 8048736:       de c1                   faddp  %st,%st(1)
 8048738:       7f 0e                   jg     8048748 
 804873a:       a1 34 91 04 08          mov    0x8049134,%eax
 804873f:       85 c0                   test   %eax,%eax
 8048741:       74 0d                   je     8048750 
 8048743:       83 c5 01                add    $0x1,%ebp
 8048746:       31 c0                   xor    %eax,%eax
 8048748:       89 c3                   mov    %eax,%ebx
 804874a:       eb c4                   jmp    8048710 
 804874c:       8d 74 26 00             lea    0x0(%esi,%eiz,1),%esi
 8048750:       dd 5c 24 10             fstpl  0x10(%esp)
 8048754:       83 c3 10                add    $0x10,%ebx
 8048757:       dd 5c 24 20             fstpl  0x20(%esp)