Re: Proper use of x86/x86_64 CPUID instruction with extended assembler

[Avi Kivity <avi at cloudius-systems dot com>]

On 08/19/2015 12:56 PM, Jeffrey Walton wrote:
> > > > > (I also looked at
> > > > > https://gcc.gnu.org/ml/gcc-patches/2007-09/msg00324.html, which is a
> > > > > GCC patch for cpuid.h. But its not clear to me if the above is correct
> > > > > because the operands are 32-bit in size. Naively, if I use "a" and "b"
> > > > > with a 32-bit operand, then I would expect code for EAX and EBX; and
> > > > > not RAX and RBX).
> > > > It is correct.
> > > Thanks Avi. Regarding the GCC patch... if the output register and the
> > > ABI tells GCC that EBX needs to be preserved, then why does the patch
> > > take special steps to preserve it?
> >
> > Well I just tried it, and gcc is indeed not clever enough to do this on its
> > own.  So it is needed.
> And one more related question... The Intel folks state to minimize the
> use of the the XCHG instruction because it has lock overhead
> (https://software.intel.com/en-us/forums/topic/393587). Should the GCC
> patch example be using a simple push/pop instead of an XCHG?

reg/reg xchg has no lock overhead.