[Bug middle-end/45379] [4.6 Regression] ~10% slowdown on test_fpu at revision 163278

["dominiq at lps dot ens dot fr" <gcc-bugzilla at gcc dot gnu dot org>]

------- Comment #11 from dominiq at lps dot ens dot fr  2010-08-24 14:33 -------
Assembly for the inner loop

      do i = 1, n
         b(i,j) = b(i,j)-temp(i)*c
      end do

with -Ofast


r163277

L38:
        movsd   (%rsi,%rax), %xmm0
        addl    $1, %ecx
        movhpd  8(%rsi,%rax), %xmm0
        movapd  %xmm0, %xmm1
        movapd  (%rdi,%rax), %xmm0
        mulpd   %xmm3, %xmm1
        subpd   %xmm1, %xmm0
        movapd  %xmm0, (%rdi,%rax)
        addq    $16, %rax
        cmpl    $249, %ecx
        jbe     L38

r163519

L38:
        movsd   (%rdi,%rax), %xmm5
        addl    $1, %esi
        movhpd  8(%rdi,%rax), %xmm5
        movapd  %xmm5, %xmm1
        movsd   (%rcx,%rax), %xmm5
        mulpd   %xmm3, %xmm1
        movhpd  8(%rcx,%rax), %xmm5
        movapd  %xmm5, %xmm0
        subpd   %xmm1, %xmm0
        movlpd  %xmm0, (%rcx,%rax)
        movhpd  %xmm0, 8(%rcx,%rax)
        addq    $16, %rax
        cmpl    $249, %esi
        jbe     L38


-- 


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=45379