stack realignment

[Marcus Meissner]

On Sun, Oct 11, 2015 at 04:09:59PM +0900, Alexandre Julliard wrote:
> Marcus Meissner <marcus at jet.franken.de> writes:
> 
> > Hi,
> >
> > (as small heads up)
> > As we have this problem with the Win64 code calling us with non-16 byte aligned stacks,
> > the gcc folks have now commited code to trunk gcc that allows -mincoming-stack-boundary=3
> > on October 7th.
> 
> What we really need is force_align_arg_pointer. The bug says that this
> is fixed too, have you verified it?

While I do not have such a test function here, I used the one from the gcc testcase:


typedef float v4sf __attribute__((vector_size(16)));

__attribute__((force_align_arg_pointer))
v4sf test (v4sf a, v4sf b)
{ 
  volatile v4sf z = a + b;
  return z;
}

without attribute and -O2:

00000000000000c0 <test>:
  c0:   0f 58 c8                addps  %xmm0,%xmm1
  c3:   0f 29 4c 24 e8          movaps %xmm1,-0x18(%rsp)
  c8:   0f 28 44 24 e8          movaps -0x18(%rsp),%xmm0
  cd:   c3                      retq   

with attribute and -O2 :

00000000000000c0 <test>:
  c0:   4c 8d 54 24 08          lea    0x8(%rsp),%r10
  c5:   0f 58 c8                addps  %xmm0,%xmm1
  c8:   48 83 e4 f0             and    $0xfffffffffffffff0,%rsp
  cc:   41 ff 72 f8             pushq  -0x8(%r10)
  d0:   55                      push   %rbp
  d1:   48 89 e5                mov    %rsp,%rbp
  d4:   41 52                   push   %r10
  d6:   0f 29 4d e0             movaps %xmm1,-0x20(%rbp)
  da:   0f 28 45 e0             movaps -0x20(%rbp),%xmm0
  de:   41 5a                   pop    %r10
  e0:   5d                      pop    %rbp
  e1:   49 8d 62 f8             lea    -0x8(%r10),%rsp
  e5:   c3                      retq   

Ciao, Marcus