[LLVMdev] Stack alignment on X86 AVX seems incorrect

[Cameron McInally]

Two responses inline...

My current thinking is that an emergency spill slot could be set aside to
> hold the original, ABI conforming, frame pointer. Not an ideal solution,
> but in my situation where I must cover any code a user throws at me,
> breaking the ABI and playing with the stack is preferred.
>
>
Ah, this is not a good idea. I examined this a while back. The issue is
that spilling the base pointer causes two levels of indirection to access
arguments.



> > > Figure 3.3 on page 16 of www.x86-64.org/documentation/abi.pdf is not
> > > normative.  See foot note 7 in the same page.  Figure 3.4 on page 21
> > > confirms that the use of a frame-pointer is optional.
> > >
> > > So, if one doesn't use ENTER in the prologue and uses RSP to access
> local
> > > variables, RBP may be used as a calee-saved GPR.
> >
> > I am not sure if I am completely following. The issue that required
> > aligning the frame to 32 bytes is when there are variable sized objects
> on
> > the stack (e.g. alloca). In that case, the RBP frame pointer is required
> to
> > access the spill slots. If I'm not mistaken, calculating the address of
> > spill slots off of RSP would be costly in this case.
>
> No, stack realignment needs to happen if there are auto variables on the
> stack of types that need a larger alignment than the default. This
> currently means AVX vectors for x86-64 and SSE/AVX vectors for x86-32
> folloing the original sysv ABI. In that case %rbp/%ebp is used to
> reference the original arguments on the stack and %rsp/%esp is used to
> reference the auto variables.
>

That sounds about right; my mistake. When I realign the frame in the
presence of variable sized objects and AVX spills, I have three pointers
sitting around: the real, unaligned frame pointer (let's say RBX and used
as the 'base pointer'); the aligned frame pointer (RBP); and the stack
pointer (RSP). The arguments are based off of the unaligned frame pointer.
Besides the change to make RBX the base pointer in the
Emit[Prologue|Epilogue] routines, everything else stayed the same.

 -Cameron
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20120302/026967af/attachment.html>