Same patch as the previous on the store side. Before we compiled this:

struct DeclGroup {
  unsigned NumDecls;
};

int foo(DeclGroup D) {
  return D.NumDecls;
}

to:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %tmp = alloca i64                               ; <i64*> [#uses=2]
  store i64 %0, i64* %tmp
  %1 = bitcast i64* %tmp to %struct.DeclGroup*    ; <%struct.DeclGroup*> [#uses=1]
  %2 = load %struct.DeclGroup* %1, align 1        ; <%struct.DeclGroup> [#uses=1]
  store %struct.DeclGroup %2, %struct.DeclGroup* %D
  %tmp1 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp2 = load i32* %tmp1                         ; <i32> [#uses=1]
  ret i32 %tmp2
}

which caused fast isel bailouts due to the FCA load/store of %2.  Now
we generate this just blissful code:

%struct.DeclGroup = type { i32 }

define i32 @_Z3foo9DeclGroup(i64) nounwind ssp noredzone {
entry:
  %D = alloca %struct.DeclGroup, align 4          ; <%struct.DeclGroup*> [#uses=2]
  %tmp = alloca i64                               ; <i64*> [#uses=2]
  %coerce.dive = getelementptr %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  store i64 %0, i64* %tmp
  %1 = bitcast i64* %tmp to i32*                  ; <i32*> [#uses=1]
  %2 = load i32* %1, align 1                      ; <i32> [#uses=1]
  store i32 %2, i32* %coerce.dive
  %tmp1 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i32*> [#uses=1]
  %tmp2 = load i32* %tmp1                         ; <i32> [#uses=1]
  ret i32 %tmp2
}

This avoids fastisel bailing out and is groundwork for future patch.
This reduces bailouts on CGStmt.ll to 911 from 935.

llvm-svn: 106974