[rfc] improving 32bit user performance/experience...

[John Moser]

Daniel J Blueman wrote:
> All older VIA processors, AMD Geode procs and so on support the full
> i586 instruction set, which including MMX instructions and registers,
> which itself can provide a good win.
> 

Geodes have partial implementation, particularly they only handle a few 
PREFETCH instructions IIRC.

  >>> (does any of this apply to x86-64, eg -mtune=core2 or k8?)
>> Yes but this becomes a mess.  Leave it as is.  gcc is good at tuning
>> to general-purpose in an instruction set.
> 
> -mtune is instruction-set invariant. gcc will tune for for i386
> scheduling, ie fewer pipeline stages. It's later processors that have
> had to optimise for short-pipeline-scheduled code, not the converse.
> IA64 would have been crippled if the instruction scheduling wasn't
> right from the outset.
> 

Why the hell would you tune 64-bit instructions for a 32-bit processor? 
  x86-64 has as much to do with IA-32 (i386, x86, i686, etc) as PPC has 
to do with SPARC.