From 9f8b4518761b3701b1eb2607fe4ebea14f6ea1f4 Mon Sep 17 00:00:00 2001
From: Chris Lattner <sabre@nondot.org>
Date: Wed, 25 Aug 2010 23:39:14 +0000
Subject: Finally pass "two floats in a 64-bit unit" as a <2 x float> instead
 of as a double in the x86-64 ABI.  This allows us to generate much better
 code for certain things, e.g.:

_Complex float f32(_Complex float A, _Complex float B) {
  return A+B;
}

Used to compile into (look at the integer silliness!):

_f32:                                   ## @f32
## BB#0:                                ## %entry
	movd	%xmm1, %rax
	movd	%eax, %xmm1
	movd	%xmm0, %rcx
	movd	%ecx, %xmm0
	addss	%xmm1, %xmm0
	movd	%xmm0, %edx
	shrq	$32, %rax
	movd	%eax, %xmm0
	shrq	$32, %rcx
	movd	%ecx, %xmm1
	addss	%xmm0, %xmm1
	movd	%xmm1, %eax
	shlq	$32, %rax
	addq	%rdx, %rax
	movd	%rax, %xmm0
	ret

Now we get:

_f32:                                   ## @f32
	movdqa	%xmm0, %xmm2
	addss	%xmm1, %xmm2
	pshufd	$16, %xmm2, %xmm2
	pshufd	$1, %xmm1, %xmm1
	pshufd	$1, %xmm0, %xmm0
	addss	%xmm1, %xmm0
	pshufd	$16, %xmm0, %xmm1
	movdqa	%xmm2, %xmm0
	unpcklps	%xmm1, %xmm0
	ret

and compile stuff like:

extern float _Complex ccoshf( float _Complex ) ;
float _Complex ccosf ( float _Complex z ) {
 float _Complex iz;
 (__real__ iz) = -(__imag__ z);
 (__imag__ iz) = (__real__ z);
 return ccoshf(iz);
}

into:

_ccosf:                                 ## @ccosf
## BB#0:                                ## %entry
	pshufd	$1, %xmm0, %xmm1
	xorps	LCPI4_0(%rip), %xmm1
	unpcklps	%xmm0, %xmm1
	movaps	%xmm1, %xmm0
	jmp	_ccoshf                 ## TAILCALL

instead of:

_ccosf:                                 ## @ccosf
## BB#0:                                ## %entry
	movd	%xmm0, %rax
	movq	%rax, %rcx
	shlq	$32, %rcx
	shrq	$32, %rax
	xorl	$-2147483648, %eax      ## imm = 0xFFFFFFFF80000000
	addq	%rcx, %rax
	movd	%rax, %xmm0
	jmp	_ccoshf                 ## TAILCALL


There is still "stuff to be done" here for the struct case,
but this resolves rdar://6379669 - [x86-64 ABI] Pass and return
_Complex float / double efficiently

llvm-svn: 112111
---
 clang/test/CodeGen/x86_64-arguments.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

(limited to 'clang/test/CodeGen')

diff --git a/clang/test/CodeGen/x86_64-arguments.c b/clang/test/CodeGen/x86_64-arguments.c
index 9fd08dd4a8b..039dd27869b 100644
--- a/clang/test/CodeGen/x86_64-arguments.c
+++ b/clang/test/CodeGen/x86_64-arguments.c
@@ -1,5 +1,4 @@
-// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o %t %s
-// RUN: FileCheck < %t %s
+// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s| FileCheck %s
 
 // CHECK: %0 = type { i64, double }
 
@@ -215,8 +214,14 @@ void f30(struct S0 p_4) {
 // rdar://8251384
 struct f31foo { float a, b, c; };
 float f31(struct f31foo X) {
-  // CHECK: define float @f31(double %X.coerce0, float %X.coerce1)
+  // CHECK: define float @f31(<2 x float> %X.coerce0, float %X.coerce1)
   return X.c;
 }
 
+_Complex float f32(_Complex float A, _Complex float B) {
+  // rdar://6379669
+  // CHECK: define <2 x float> @f32(<2 x float> %A.coerce, <2 x float> %B.coerce)
+  return A+B;
+}
+
 
-- 
cgit v1.2.3