return value aliasing ?

[Joachim Schöberl <joachim.schoeberl@xxxxxxxxxxxx>]

Hello,

I am experimenting with AVX optimization of a complex code, and discovered 
this simplified test-case already for scalar code:

I compiled this code

class MyDouble
{
  double data;
public:
  MyDouble (const MyDouble & v2) : data(v2.data) { ; }
  MyDouble (double d) : data(d) { ; }

  MyDouble & operator+= (MyDouble d)
  { data += d.data; return *this; }
};

MyDouble MyFuncBad (int m, MyDouble x)
{
  MyDouble sum = 0.0;
  for (int i = 0; i < m; i++) sum += x;
  return sum;
}

MyDouble MyFuncGood (int m, MyDouble x)
{
  MyDouble sum = 0.0;
  for (int i = 0; i < m; i++) sum += x;
  return MyDouble(sum);
}

with 'gcc-4.8 -O3 -S testdouble.cpp' and got the assembly code below.
I would expect that both functions are equivalent.

In MyFuncBad, the intermediate sum is written to memory in every
iteration, while in MyFuncGood just the final result is brought to
memory. Is this necessary for correctness ?
Can the return-value alias the call-by-value argument ?

In the AVX-code the performance difference was about 30 percent.

If I use the default copy-constructor, I also get the faster code.
Is there something wrong with my (of course here unnecessary) copy-constructor 
?

Thanks a lot for an explanation
Joachim




The generated code is:

	.file	"testdouble.cpp"
	.text
	.p2align 4,,15
	.globl	_Z9MyFuncBadi8MyDouble
	.type	_Z9MyFuncBadi8MyDouble, @function
_Z9MyFuncBadi8MyDouble:
.LFB7:
	.cfi_startproc
	xorpd	%xmm0, %xmm0
	xorl	%ecx, %ecx
	testl	%esi, %esi
	movq	%rdi, %rax
	movsd	%xmm0, (%rdi)
	jle	.L1
	.p2align 4,,10
	.p2align 3
.L5:
	addsd	(%rdx), %xmm0         <-- WHY RELOAD ???
	addl	$1, %ecx
	cmpl	%esi, %ecx
	movsd	%xmm0, (%rax)         <-- WHY THE WRITE IN THE LOOP ????
	jne	.L5
.L1:
	rep; ret
	.cfi_endproc
.LFE7:
	.size	_Z9MyFuncBadi8MyDouble, .-_Z9MyFuncBadi8MyDouble
	.p2align 4,,15
	.globl	_Z10MyFuncGoodi8MyDouble
	.type	_Z10MyFuncGoodi8MyDouble, @function
_Z10MyFuncGoodi8MyDouble:
.LFB8:
	.cfi_startproc
	testl	%esi, %esi
	movq	%rdi, %rax
	xorpd	%xmm0, %xmm0
	jle	.L8
	xorpd	%xmm0, %xmm0
	movsd	(%rdx), %xmm1
	xorl	%edx, %edx
	.p2align 4,,10
	.p2align 3
.L9:
	addl	$1, %edx
	addsd	%xmm1, %xmm0
	cmpl	%esi, %edx
	jne	.L9
.L8:
	movsd	%xmm0, (%rax)               <---- AFTER THE LOOP
	ret
	.cfi_endproc
.LFE8:
	.size	_Z10MyFuncGoodi8MyDouble, .-_Z10MyFuncGoodi8MyDouble
	.ident	"GCC: (Ubuntu 4.8.1-2ubuntu1~12.04) 4.8.1"
	.section	.note.GNU-stack,"",@progbits