fix rdar://8251384, another case where we could access beyond the

end of a struct.  This improves the case when the struct being passed
contains 3 floats, either due to a struct or array of 3 things.  Before
we'd generate this IR for the testcase:

define float @bar(double %X.coerce0, double %X.coerce1) nounwind {
entry:
  %X = alloca %struct.foof, align 8               ; <%struct.foof*> [#uses=2]
  %0 = bitcast %struct.foof* %X to %1*            ; <%1*> [#uses=2]
  %1 = getelementptr %1* %0, i32 0, i32 0         ; <double*> [#uses=1]
  store double %X.coerce0, double* %1
  %2 = getelementptr %1* %0, i32 0, i32 1         ; <double*> [#uses=1]
  store double %X.coerce1, double* %2
  %tmp = getelementptr inbounds %struct.foof* %X, i32 0, i32 2 ; <float*> [#uses=1]
  %tmp1 = load float* %tmp                        ; <float> [#uses=1]
  ret float %tmp1
}

which compiled (with optimization) to:

_bar:                                   ## @bar
## BB#0:                                ## %entry
	movd	%xmm1, %rax
	movd	%eax, %xmm0
	ret

Now we produce:

define float @bar(double %X.coerce0, float %X.coerce1) nounwind {
entry:
  %X = alloca %struct.foof, align 8               ; <%struct.foof*> [#uses=2]
  %0 = bitcast %struct.foof* %X to %0*            ; <%0*> [#uses=2]
  %1 = getelementptr %0* %0, i32 0, i32 0         ; <double*> [#uses=1]
  store double %X.coerce0, double* %1
  %2 = getelementptr %0* %0, i32 0, i32 1         ; <float*> [#uses=1]
  store float %X.coerce1, float* %2
  %tmp = getelementptr inbounds %struct.foof* %X, i32 0, i32 2 ; <float*> [#uses=1]
  %tmp1 = load float* %tmp                        ; <float> [#uses=1]
  ret float %tmp1
}

and:

_bar:                                   ## @bar
## BB#0:                                ## %entry
	movaps	%xmm1, %xmm0
	ret

llvm-svn: 109776