On Tue, 7 Aug 2018, Andi Kleen wrote:
> On Tue, Aug 07, 2018 at 07:48:51PM +0200, Peter Zijlstra wrote:
> > On Tue, Aug 07, 2018 at 10:35:42AM -0700, Dave Hansen wrote:
> > > On 08/07/2018 10:17 AM, kan.li...@linux.intel.com wrote:
> > > > Denverton and Gemini Lake are platform names and should not be used for
> > > > Processor Family stuff. The microarchitecture codename should be used.
> > >
> > > Why?
> > >
> > > Denverton is the platform. "Goldmont" is literally the
> > > microarchitecture, and you are suggesting moving *to* the
> > > microarchitecture name, which contradicts the description.
> >
> > All the other (big core) are uarch names. Atom is weird in that it mixes
> > uarch with platform names.
>
> On most big core the platform/SOC just happens to have the same name as the
> uarch. But the identifiers really have to be per SOC because that
> is how Intel model numbers work.
>
> It should be always the SOC.
Which simply does not work. Look at Goldmont Fam 6 Model 5C. The SoCs
with that Fam/Model combination are:
- Apollo Lake
- Broxton (has two platforms: Morganfield and Willowtrail)
It's even worse with Silvermont.
So no, the interesting information is the UARCH and the variant of that,
e.g. UARCH_CLIENT, UARCH_SERVER, UARCH_WHATEVER. All the magic Code Names
and their platform variants are not interesting at all for the Fam/Model
information.
Thanks,
tglx
