[PATCH, PowerPC] ABI fixes / improvements for powerpc64-linux

[Hal Finkel]

----- Original Message -----
> From: "Ulrich Weigand" <Ulrich.Weigand at de.ibm.com>
> To: "Hal Finkel" <hfinkel at anl.gov>
> Cc: "cfe commits" <cfe-commits at cs.uiuc.edu>
> Sent: Wednesday, July 9, 2014 3:06:27 PM
> Subject: Re: [PATCH, PowerPC] ABI fixes / improvements for powerpc64-linux
> 
> Ulrich Weigand/Germany/IBM wrote on 09.07.2014 21:54:20:
> 
> > Yes, the ABI doc is wrong here.  We'll fix this in the new version
> > we're currently working on.  What was intended (and what is
> > implemented in GCC today) is somewhat of a mixture of 2 and 3
> > above: if the type's alignment requirement is >= 16 byte,  it
> > will be passed in the save area at 16 byte alignment.
> >
> > The rationale is the this: alignment in the parameter save area
> > matters for two reasons:
> > - if you take the address of the parameter, it has to be properly
> >  aligned, since code is allowed to assume that property;
> > - when you access a member of the parameter in place in the save
> >   area, the ISA may have alignment requirements; on PowerPC, the
> >   only such requirement is 16 byte for VMX loads/stores.
> >
> > The reason why an argument in the save area is 16-byte aligned
> > is that this will suffice for the second reason above, i.e. it
> > is possible to access the argument using VMX instructions.
> >
> > If the argument type actually requires > 16 byte alignment,
> > and code indeed takes the address of the argument, then the
> > compiler will have to copy the incoming argument to another
> > place, properly aligned, on the stack.
> 
> Oh, and I forgot another reason: the parameter area is at a fixed
> place relative to the stack frame, and the stack frame itself is
> only guaranteed to be 16 bytes aligned, so we *cannot* guarantee
> more than 16 byte alignment for any component of the save area.
> 
> The only way to do that is by run-time pointer arithmetic within
> a larger block allocated on the stack dynamically, which is how
> larger alignments are guaranteed for local variables (and copies
> of parameters if necessary).

Right. And if you realign the stack frame (which you need to do anyway when you have locals with enhanced alignment requirements), then there is no problem.

 -Hal

> 
> Bye,
> Ulrich
> 
> 

-- 
Hal Finkel
Assistant Computational Scientist
Leadership Computing Facility
Argonne National Laboratory