From: Alan Stern <stern@rowland.harvard.edu>
To: "Paul E. McKenney" <paulmck@kernel.org>
Cc: linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
kernel-team@fb.com, mingo@kernel.org, parri.andrea@gmail.com,
will@kernel.org, peterz@infradead.org, boqun.feng@gmail.com,
npiggin@gmail.com, dhowells@redhat.com, j.alglave@ucl.ac.uk,
luc.maranget@inria.fr, akiyks@gmail.com
Subject: Re: [PATCH memory-model 5/8] tools/memory-model: Add a glossary of LKMM terms
Date: Fri, 6 Nov 2020 21:32:14 -0500 [thread overview]
Message-ID: <20201107023214.GA64998@rowland.harvard.edu> (raw)
In-Reply-To: <20201106210413.GB3249@paulmck-ThinkPad-P72>
On Fri, Nov 06, 2020 at 01:04:13PM -0800, Paul E. McKenney wrote:
> On Fri, Nov 06, 2020 at 03:40:08PM -0500, Alan Stern wrote:
> > Is it really true that data dependencies are so easily destroyed? I
> > would expect that a true "semantic" dependency (i.e., one where the
> > value written really does vary according to the value read) would be
> > rather hard to second guess.
>
> The usual optimizations apply, for but one example:
>
> r1 = READ_ONCE(x);
> WRITE_ONCE(y, (r1 + 1) % MAX_ELEMENTS);
>
> If MAX_ELEMENTS is 1, so long, data dependency!
Sure, but if MAX_ELEMENTS is 1 then the value written will always be 0
no matter what value r1 has, so it isn't a semantic dependency.
Presumably a semantic data dependency would be much more robust.
I wonder if it's worth pointing out this distinction to the reader.
> With pointers, the compiler has fewer optimization opportunities,
> but there are still cases where it can break the dependency.
> Or transform it to a control dependency.
Transforming a data dependency into a control dependency wouldn't make
any important difference; the hardware would still provide the desired
ordering.
Alan
next prev parent reply other threads:[~2020-11-07 2:37 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-05 21:59 [PATCH memory-model 0/8] LKMM updates for v5.11 Paul E. McKenney
2020-11-05 22:00 ` [PATCH memory-model 1/8] tools: memory-model: Document that the LKMM can easily miss control dependencies paulmck
2020-11-05 22:00 ` [PATCH memory-model 2/8] tools/memory-model: Move Documentation description to Documentation/README paulmck
2020-11-05 22:00 ` [PATCH memory-model 3/8] tools/memory-model: Document categories of ordering primitives paulmck
2020-11-06 16:56 ` Alan Stern
2020-11-06 19:11 ` Paul E. McKenney
2020-11-05 22:00 ` [PATCH memory-model 4/8] docs/memory-barriers.txt: Fix a typo in CPU MEMORY BARRIERS section paulmck
2020-11-05 22:00 ` [PATCH memory-model 5/8] tools/memory-model: Add a glossary of LKMM terms paulmck
2020-11-06 1:47 ` Boqun Feng
2020-11-06 18:01 ` Paul E. McKenney
2020-11-07 3:07 ` Boqun Feng
2020-11-06 16:59 ` Alan Stern
2020-11-06 18:04 ` Paul E. McKenney
2020-11-06 19:23 ` Alan Stern
2020-11-06 19:59 ` Paul E. McKenney
2020-11-06 20:40 ` Alan Stern
2020-11-06 21:04 ` Paul E. McKenney
2020-11-07 2:32 ` Alan Stern [this message]
2020-11-05 22:00 ` [PATCH memory-model 6/8] tools/memory-model: Add types to litmus tests paulmck
2020-11-05 22:41 ` Akira Yokosawa
2020-11-05 22:56 ` Paul E. McKenney
2020-11-25 11:34 ` Akira Yokosawa
2020-11-27 15:46 ` Paul E. McKenney
2020-11-28 5:56 ` Akira Yokosawa
2020-11-28 6:00 ` [PATCH 1/2] tools/memory-model: Remove redundant initialization in " Akira Yokosawa
2020-11-28 6:01 ` [PATCH 2/2] tools/memory-model: Fix typo in klitmus7 compatibility table Akira Yokosawa
2020-11-29 3:33 ` Paul E. McKenney
2020-11-05 22:00 ` [PATCH memory-model 7/8] tools/memory-model: Use "buf" and "flag" for message-passing tests paulmck
2020-11-05 22:00 ` [PATCH memory-model 8/8] tools/memory-model: Label MP tests' producers and consumers paulmck
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=20201107023214.GA64998@rowland.harvard.edu \
--to=stern@rowland.harvard.edu \
--cc=akiyks@gmail.com \
--cc=boqun.feng@gmail.com \
--cc=dhowells@redhat.com \
--cc=j.alglave@ucl.ac.uk \
--cc=kernel-team@fb.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luc.maranget@inria.fr \
--cc=mingo@kernel.org \
--cc=npiggin@gmail.com \
--cc=parri.andrea@gmail.com \
--cc=paulmck@kernel.org \
--cc=peterz@infradead.org \
--cc=will@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).