Bug 56160

the attached code which does complex float multiplication using sse3 produces 4 unnecessary integer additions if the NaN fallback function comp_mult is inlined

the assembly for the loop generated with -msse3 -O3 -std=c99 in gcc 4.4, 4.6, 4.7 and 4.8 svn 195604 looks like this:
  28:	0f 28 0e             	movaps (%esi),%xmm1
  2b:	f3 0f 12 c1          	movsldup %xmm1,%xmm0
  2f:	8b 55 08             	mov    0x8(%ebp),%edx
  32:	0f 28 13             	movaps (%ebx),%xmm2
  35:	f3 0f 16 c9          	movshdup %xmm1,%xmm1
  39:	0f 59 c2             	mulps  %xmm2,%xmm0
  3c:	0f c6 d2 b1          	shufps $0xb1,%xmm2,%xmm2
  40:	0f 59 ca             	mulps  %xmm2,%xmm1
  43:	f2 0f d0 c1          	addsubps %xmm1,%xmm0
  47:	0f 29 04 fa          	movaps %xmm0,(%edx,%edi,8)
  4b:	0f c2 c0 04          	cmpneqps %xmm0,%xmm0
  4f:	0f 50 c0             	movmskps %xmm0,%eax
  52:	85 c0                	test   %eax,%eax
  54:	75 1d                	jne    73 <sse3_mult+0x73> // inlined comp_mult
  56:	83 c7 02             	add    $0x2,%edi
  59:	83 c6 10             	add    $0x10,%esi
  5c:	83 c3 10             	add    $0x10,%ebx
  5f:	83 c1 10             	add    $0x10,%ecx
  62:	83 45 e4 10          	addl   $0x10,-0x1c(%ebp)
  66:	39 7d 14             	cmp    %edi,0x14(%ebp)
  69:	7f bd                	jg     28 <sse3_mult+0x28>
...

the 4 adds for esi ebx ecx and ebp are completely unnecessary and reduce performance by about 20% on my core2duo.
on amd64 it also creates to seemingly unnecessary additions but I did not test the performance.

a way to coax gcc to emit proper code is to not allow it to inline the fallback
it then generates following good assembly with only one integer add:

  a8:	0f 28 0c df          	movaps (%edi,%ebx,8),%xmm1
  ac:	f3 0f 12 c1          	movsldup %xmm1,%xmm0
  b0:	8b 45 08             	mov    0x8(%ebp),%eax
  b3:	0f 28 14 de          	movaps (%esi,%ebx,8),%xmm2
  b7:	f3 0f 16 c9          	movshdup %xmm1,%xmm1
  bb:	0f 59 c2             	mulps  %xmm2,%xmm0
  be:	0f c6 d2 b1          	shufps $0xb1,%xmm2,%xmm2
  c2:	0f 59 ca             	mulps  %xmm2,%xmm1
  c5:	f2 0f d0 c1          	addsubps %xmm1,%xmm0
  c9:	0f 29 04 d8          	movaps %xmm0,(%eax,%ebx,8)
  cd:	0f c2 c0 04          	cmpneqps %xmm0,%xmm0
  d1:	0f 50 c0             	movmskps %xmm0,%eax
  d4:	85 c0                	test   %eax,%eax
  d6:	75 10                	jne    e8 <sse3_mult+0x58> // non-inlined comp_mult
  d8:	83 c3 02             	add    $0x2,%ebx
  db:	39 5d 14             	cmp    %ebx,0x14(%ebp)
  de:	7f c8                	jg     a8 <sse3_mult+0x18>
...