From: Linus Torvalds <torvalds@linux-foundation.org>
To: "Michael S. Zick" <lkml@morethan.org>
Cc: Duane Griffin <duaneg@dghda.com>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
Harald Welte <HaraldWelte@viatech.com>
Subject: Re: Linux 2.6.30-rc8 [also: VIA Support]
Date: Thu, 4 Jun 2009 10:03:21 -0700 (PDT) [thread overview]
Message-ID: <alpine.LFD.2.01.0906040948480.4880@localhost.localdomain> (raw)
In-Reply-To: <200906041121.30845.lkml@morethan.org>
On Thu, 4 Jun 2009, Michael S. Zick wrote:
>
> The C7-M processor uses "in-order retirement" not "out-of-order" - -
> I think the MCR's **should not** be set for "weak ordered writes" -
In-order retirement does not really imply anything at all about how write
ordering works out. In most CPU parlance, you'd say that you've "retired"
a write instruction when it has completed in the write queue - but it
would not mean anything in particular for memory ordering.
Of course, I don't think the C7 is just in-order retirement, I think it's
pretty much in-order everything. Usually you only specify that
"retirement" part when there is some out-of-order execution in other parts
of the pipeline, but I think the C7 is entirely in-order pipeline,
although I suspect the FPU side is likely somewhat separated.
But still, with a write buffer (and _no_ sane x86 does not have a write
buffer), that doesn't actually mean that the cache and memory accesses are
necessarily entirely in-order.
That said, how all the internal CPU registers are set is all black magic.
Linus
next prev parent reply other threads:[~2009-06-04 17:03 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-03 4:06 Linux 2.6.30-rc8 Linus Torvalds
2009-06-04 13:56 ` Linux 2.6.30-rc8 [also: VIA Support] Michael S. Zick
2009-06-04 14:58 ` Michael S. Zick
2009-06-04 15:18 ` Linus Torvalds
2009-06-04 15:37 ` Michael S. Zick
2009-06-04 17:45 ` Harald Welte
2009-06-08 5:48 ` Pavel Machek
2009-06-04 16:00 ` Duane Griffin
2009-06-04 16:08 ` Michael S. Zick
2009-06-04 16:13 ` Linus Torvalds
2009-06-04 16:21 ` Michael S. Zick
2009-06-04 17:03 ` Linus Torvalds [this message]
2009-06-04 17:07 ` Linus Torvalds
2009-06-04 17:27 ` Michael S. Zick
2009-06-04 17:46 ` Linus Torvalds
2009-06-05 11:06 ` VIA PowerSaver (Re: Linux 2.6.30-rc8 [also: VIA Support]) Harald Welte
2009-06-05 13:41 ` Michael S. Zick
2009-06-06 12:17 ` Linux 2.6.30-rc8 [also: VIA Support] Michael S. Zick
2009-06-06 13:28 ` e_powersaver / underclocking (was Re: Linux 2.6.30-rc8 [also: VIA Support]) Harald Welte
2009-06-06 13:46 ` Michael S. Zick
2009-06-06 13:56 ` Michael S. Zick
2009-06-08 7:53 ` e_powersaver driver considered DANGEROUS " Harald Welte
2009-06-08 6:12 ` Pavel Machek
2009-06-08 10:27 ` [PATCH 1/2] CPUFREQ: Enable acpi-cpufreq driver for VIA/Centaur CPUs Harald Welte
2009-06-08 13:16 ` Matthew Garrett
2009-06-08 18:01 ` Harald Welte
2009-06-08 14:25 ` Michael S. Zick
2009-06-08 14:58 ` Matthew Garrett
2009-06-08 15:08 ` Michael S. Zick
2009-06-08 18:35 ` Linus Torvalds
2009-06-08 18:41 ` Michael S. Zick
2009-06-08 21:32 ` Michael S. Zick
2009-06-09 2:15 ` Harald Welte
2009-06-09 12:26 ` Michael S. Zick
2009-06-09 16:22 ` Chuck Ebbert
2009-06-09 16:45 ` Michael S. Zick
2009-06-15 13:10 ` TSC features, was: " Michael S. Zick
2009-06-15 14:25 ` [PATCH, RFC] Re: TSC features, Michael S. Zick
2009-06-08 20:03 ` [PATCH 1/2] CPUFREQ: Enable acpi-cpufreq driver for VIA/Centaur CPUs Michael S. Zick
2009-06-08 21:15 ` Michael S. Zick
2009-06-08 23:48 ` Matthew Garrett
2009-06-09 12:36 ` Michael S. Zick
2009-06-09 16:00 ` Michael S. Zick
2009-06-09 17:51 ` Michael S. Zick
2009-06-09 8:14 ` Linux 2.6.30-rc8 [also: VIA Support] Harald Welte
2009-06-04 17:55 ` Dave Jones
2009-06-05 7:27 ` Harald Welte
2009-06-05 7:41 ` Michael S. Zick
2009-06-05 7:19 ` Harald Welte
2009-06-05 7:27 ` Michael S. Zick
2009-06-05 10:39 ` Harald Welte
2009-06-05 13:18 ` Michael S. Zick
2009-06-08 5:56 ` Pavel Machek
2009-06-04 17:13 ` Michael S. Zick
2009-06-04 17:40 ` Harald Welte
2009-06-04 18:12 ` Michael S. Zick
2009-06-04 19:23 ` Michael S. Zick
2009-06-04 20:32 ` Michael S. Zick
2009-06-05 4:37 ` Michael S. Zick
2009-06-05 9:00 ` Michael S. Zick
2009-06-04 20:33 ` Dave Jones
2009-06-04 21:01 ` Michael S. Zick
2009-06-04 21:24 ` Dave Jones
2009-06-04 21:38 ` Michael S. Zick
2009-06-04 21:43 ` Dave Jones
2009-06-04 22:00 ` Michael S. Zick
2009-06-04 23:26 ` Michael S. Zick
2009-06-05 0:15 ` Dave Jones
2009-06-05 0:27 ` Michael S. Zick
2009-06-05 11:08 ` VIA CPU PCI cache line size (Re: Linux 2.6.30-rc8 [also: VIA Support]) Harald Welte
2009-06-05 13:43 ` Michael S. Zick
2009-06-04 20:16 ` Linux 2.6.30-rc8 [also: VIA Support] Andi Kleen
2009-06-04 20:29 ` Michael S. Zick
2009-06-05 0:33 ` Robert Hancock
2009-06-05 0:52 ` Michael S. Zick
2009-06-05 0:54 ` Robert Hancock
2009-06-05 7:30 ` Harald Welte
2009-06-04 17:08 ` Harald Welte
2009-06-04 17:18 ` Michael S. Zick
2009-06-05 7:24 ` Harald Welte
2009-06-05 7:44 ` Michael S. Zick
2009-06-05 7:52 ` Michael S. Zick
2009-06-04 20:39 ` Gerd Hoffmann
2009-06-05 18:47 ` Linux 2.6.30-rc8 Michael S. Zick
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=alpine.LFD.2.01.0906040948480.4880@localhost.localdomain \
--to=torvalds@linux-foundation.org \
--cc=HaraldWelte@viatech.com \
--cc=duaneg@dghda.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkml@morethan.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.