[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190820154011.GY2332@hirez.programming.kicks-ass.net>
Date: Tue, 20 Aug 2019 17:40:11 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: "Luck, Tony" <tony.luck@...el.com>, Borislav Petkov <bp@...en8.de>,
Dave Hansen <dave.hansen@...el.com>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] MAINTAINERS, x86/CPU: Tony Luck will maintain
asm/intel-family.h
On Thu, Aug 15, 2019 at 10:22:07PM +0200, Thomas Gleixner wrote:
> We have the following existing _SHORT variants:
> _G
> _GT3E
Those two are special SOCs due to 'extra graphics bits on', and I
suppose we could collate them. That said; I'm not sure NHM_G ever
shipped, I'm looking at a wikipedia page that says both Auburndale and
Havendale got scrapped.
> _EP
> _EX
Both are historical, intel is no longer making that distinction and
current chips will have _X.
> _CORE
> _DESKTOP
These two and no _SHORT should/could be collated, I think.
> _ULT
> _MOBILE
I suspect these two are the same.
> _XEON_D
Bit unfortunate that; we use _XEON_D for big microservers and ATOM_*_X
for small microservers. So there's room for improvement here by unifying
this.
> _MID
That one lived for 4 atom generations, but afaict it's no longer alive.
> _NNPI
> _TABLET
These are so far one offs, not sure about the future.
> _PLUS
Like said in the other email, that one is not actually a _SHORT at all,
but rather the uarch is 'Goldmont Plus'
Powered by blists - more mailing lists