Change CGCall to handle the "coerce" case where the coerce-to type

is a FCA to pass each of the elements as individual scalars.  This
produces code fast isel is less likely to reject and is easier on
the optimizers.

For example, before we would compile:
struct DeclGroup { long NumDecls; char * Y; };
char * foo(DeclGroup D) {
  return D.NumDecls+D.Y;
}

to:
%struct.DeclGroup = type { i64, i64 }

define i64 @_Z3foo9DeclGroup(%struct.DeclGroup) nounwind {
entry:
  %D = alloca %struct.DeclGroup, align 8          ; <%struct.DeclGroup*> [#uses=3]
  store %struct.DeclGroup %0, %struct.DeclGroup* %D, align 1
  %tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
  %tmp1 = load i64* %tmp                          ; <i64> [#uses=1]
  %tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i64*> [#uses=1]
  %tmp3 = load i64* %tmp2                         ; <i64> [#uses=1]
  %add = add nsw i64 %tmp1, %tmp3                 ; <i64> [#uses=1]
  ret i64 %add
}

Now we get:

%0 = type { i64, i64 }
%struct.DeclGroup = type { i64, i8* }

define i8* @_Z3foo9DeclGroup(i64, i64) nounwind {
entry:
  %D = alloca %struct.DeclGroup, align 8          ; <%struct.DeclGroup*> [#uses=3]
  %2 = insertvalue %0 undef, i64 %0, 0            ; <%0> [#uses=1]
  %3 = insertvalue %0 %2, i64 %1, 1               ; <%0> [#uses=1]
  %4 = bitcast %struct.DeclGroup* %D to %0*       ; <%0*> [#uses=1]
  store %0 %3, %0* %4, align 1
  %tmp = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 0 ; <i64*> [#uses=1]
  %tmp1 = load i64* %tmp                          ; <i64> [#uses=1]
  %tmp2 = getelementptr inbounds %struct.DeclGroup* %D, i32 0, i32 1 ; <i8**> [#uses=1]
  %tmp3 = load i8** %tmp2                         ; <i8*> [#uses=1]
  %add.ptr = getelementptr inbounds i8* %tmp3, i64 %tmp1 ; <i8*> [#uses=1]
  ret i8* %add.ptr
}

Elimination of the FCA inside the function is still-to-come.

llvm-svn: 107099

1 files changed, 1 insertions, 1 deletions

diff --git a/clang/test/CodeGen/x86_64-arguments.c b/clang/test/CodeGen/x86_64-arguments.c
index 24223901088..2a96f22e1dc 100644
--- a/clang/test/CodeGen/x86_64-arguments.c
+++ b/clang/test/CodeGen/x86_64-arguments.c
@@ -45,7 +45,7 @@ void f7(e7 a0) {
 // Test merging/passing of upper eightbyte with X87 class.
 //
 // CHECK: define %0 @f8_1()
-// CHECK: define void @f8_2(%0)
+// CHECK: define void @f8_2(i64, double)
 union u8 {
   long double a;
   int b;