X86-64:

X86-64:
pass/return structs of float/int as float/i32 instead of double/i64
to make the code generated for ABI cleaner.  Passing in the low part
of a double is the same as passing in a float.

For example, we now compile:

struct DeclGroup { float NumDecls; };
float foo(DeclGroup D);
void bar(DeclGroup *D) {
 foo(*D);
}

into:

%struct.DeclGroup = type { float }

define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) nounwind {
entry:
  %D.addr = alloca %struct.DeclGroup*, align 8    ; <%struct.DeclGroup**> [#uses=2]
  %agg.tmp = alloca %struct.DeclGroup, align 4    ; <%struct.DeclGroup*> [#uses=2]
  store %struct.DeclGroup* %D, %struct.DeclGroup** %D.addr
  %tmp = load %struct.DeclGroup** %D.addr         ; <%struct.DeclGroup*> [#uses=1]
  %tmp1 = bitcast %struct.DeclGroup* %agg.tmp to i8* ; <i8*> [#uses=1]
  %tmp2 = bitcast %struct.DeclGroup* %tmp to i8*  ; <i8*> [#uses=1]
  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 4, i32 4, i1 false)
  %coerce.dive = getelementptr %struct.DeclGroup* %agg.tmp, i32 0, i32 0 ; <float*> [#uses=1]
  %0 = load float* %coerce.dive, align 1          ; <float> [#uses=1]
  %call = call float @_Z3foo9DeclGroup(float %0)  ; <float> [#uses=0]
  ret void
}

instead of:

%struct.DeclGroup = type { float }

define void @_Z3barP9DeclGroup(%struct.DeclGroup* %D) nounwind {
entry:
  %D.addr = alloca %struct.DeclGroup*, align 8    ; <%struct.DeclGroup**> [#uses=2]
  %agg.tmp = alloca %struct.DeclGroup, align 4    ; <%struct.DeclGroup*> [#uses=2]
  %tmp3 = alloca double                           ; <double*> [#uses=2]
  store %struct.DeclGroup* %D, %struct.DeclGroup** %D.addr
  %tmp = load %struct.DeclGroup** %D.addr         ; <%struct.DeclGroup*> [#uses=1]
  %tmp1 = bitcast %struct.DeclGroup* %agg.tmp to i8* ; <i8*> [#uses=1]
  %tmp2 = bitcast %struct.DeclGroup* %tmp to i8*  ; <i8*> [#uses=1]
  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %tmp1, i8* %tmp2, i64 4, i32 4, i1 false)
  %coerce.dive = getelementptr %struct.DeclGroup* %agg.tmp, i32 0, i32 0 ; <float*> [#uses=1]
  %0 = bitcast double* %tmp3 to float*            ; <float*> [#uses=1]
  %1 = load float* %coerce.dive                   ; <float> [#uses=1]
  store float %1, float* %0, align 1
  %2 = load double* %tmp3                         ; <double> [#uses=1]
  %call = call float @_Z3foo9DeclGroup(double %2) ; <float> [#uses=0]
  ret void
}

which is this machine code (at -O0):

__Z3barP9DeclGroup:
	subq	$24, %rsp
	movq	%rdi, 16(%rsp)
	movq	16(%rsp), %rdi
	leaq	8(%rsp), %rax
	movl	(%rdi), %ecx
	movl	%ecx, (%rax)
	movss	8(%rsp), %xmm0
	callq	__Z3foo9DeclGroup
	addq	$24, %rsp
	ret

vs this:

__Z3barP9DeclGroup:
	subq	$24, %rsp
	movq	%rdi, 16(%rsp)
	movq	16(%rsp), %rdi
	leaq	8(%rsp), %rax
	movl	(%rdi), %ecx
	movl	%ecx, (%rax)
	movss	8(%rsp), %xmm0
	movss	%xmm0, (%rsp)
	movsd	(%rsp), %xmm0
	callq	__Z3foo9DeclGroup
	addq	$24, %rsp
	ret

At -O3, it is the difference between this now:

__Z3barP9DeclGroup:
	movss	(%rdi), %xmm0
	jmp	__Z3foo9DeclGroup  # TAILCALL

vs this before:

__Z3barP9DeclGroup:
	movl	(%rdi), %eax
	movd	%rax, %xmm0
	jmp	__Z3foo9DeclGroup  # TAILCALL

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@107048 91177308-0d34-0410-b5e6-96231b3b80d8