[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20180807195945.GK2494@hirez.programming.kicks-ass.net>
Date: Tue, 7 Aug 2018 21:59:45 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Andi Kleen <ak@...ux.intel.com>
Cc: Dave Hansen <dave.hansen@...ux.intel.com>,
kan.liang@...ux.intel.com, tglx@...utronix.de, mingo@...hat.com,
len.brown@...el.com, linux-kernel@...r.kernel.org, x86@...nel.org
Subject: Re: [PATCH] x86/cpu: Rename Denverton and Gemini Lake
On Tue, Aug 07, 2018 at 11:37:36AM -0700, 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.liang@...ux.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.
I'm sure that is how we ended up with two SKX parts with identical model
numbers but different crystal frequencies :-(
Let's just keep consistency and use MICROARCH_TYPE things for
everything.
Powered by blists - more mailing lists