From: Dave Martin <Dave.Martin@arm.com>
To: Joseph Myers <joseph@codesourcery.com>
Cc: Florian Weimer <fweimer@redhat.com>,
libc-alpha@sourceware.org,
Ard Biesheuvel <ard.biesheuvel@linaro.org>,
Marc Zyngier <Marc.Zyngier@arm.com>,
gdb@sourceware.org, Yao Qi <qiyaoltc@gmail.com>,
linux-arm-kernel@lists.infradead.org,
Alan Hayward <alan.hayward@arm.com>,
Torvald Riegel <triegel@redhat.com>,
Christoffer Dall <christoffer.dall@linaro.org>
Subject: Re: [RFC PATCH 00/29] arm64: Scalable Vector Extension core support
Date: Fri, 02 Dec 2016 18:21:00 -0000 [thread overview]
Message-ID: <20161202182126.GS1574@e103592.cambridge.arm.com> (raw)
In-Reply-To: <alpine.DEB.2.20.1612021648580.16956@digraph.polyomino.org.uk>
On Fri, Dec 02, 2016 at 04:59:27PM +0000, Joseph Myers wrote:
> On Fri, 2 Dec 2016, Florian Weimer wrote:
>
> > > However, it would be necessary to prevent GCC from moving any code
> > > across these statements -- in particular, SVE code that access VL-
> > > dependent data spilled on the stack is liable to go wrong if reordered
> > > with the above. So the sequence would need to go in an external
> > > function (or a single asm...)
> >
> > I would talk to GCC folksâwe have similar issues with changing the FPU
> > rounding mode, I assume.
>
> In general, GCC doesn't track the implicit uses of thread-local state
> involved in floating-point exceptions and rounding modes, and so doesn't
> avoid moving code across manipulations of such state; there are various
> open bugs in this area (though many of the open bugs are for local rather
> than global issues with code generation or local optimizations not
> respecting exceptions and rounding modes, which are easier to fix). Hence
> glibc using various macros such as math_opt_barrier and math_force_eval
> which use asms to prevent such motion.
Presumably the C language specs specify that fenv manipulations cannot
be reordered with respect to evaluation or floating-point expressions?
Sanity would seem to require this, though I've not dug into the specs
myself yet.
This doesn't get us off the hook for prctl() -- the C specs can only
define constraints on reordering for things that appear in the C spec.
prctl() is just an external function call in this context, and doesn't
enjoy the same guarantees.
> I'm not familiar enough with the optimizers to judge the right way to
> address such issues with implicit use of thread-local state. And I
> haven't thought much yet about how to implement TS 18661-1 constant
> rounding modes, which would involve the compiler implicitly inserting
> rounding modes changes, though I think it would be fairly straightforward
> given underlying support for avoiding inappropriate code motion.
My concern is that the compiler has no clue about what code motions are
appropriate or not with respect to a system call, beyond what applies
to a system call in general (i.e., asm volatile ( ::: "memory" ) for
GCC).
?
Cheers
---Dave
next prev parent reply other threads:[~2016-12-02 18:21 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-25 19:39 Dave Martin
2016-11-25 19:39 ` [RFC PATCH 03/29] arm64: signal: factor out signal frame record allocation Dave Martin
2016-11-25 19:39 ` [RFC PATCH 02/29] arm64: signal: factor frame layout and population into separate passes Dave Martin
2016-11-25 19:39 ` [RFC PATCH 01/29] arm64: signal: Refactor sigcontext parsing in rt_sigreturn Dave Martin
2016-11-25 19:40 ` [RFC PATCH 04/29] arm64: signal: Allocate extra sigcontext space as needed Dave Martin
2016-11-25 19:40 ` [RFC PATCH 05/29] arm64: signal: Parse extra_context during sigreturn Dave Martin
2016-11-25 19:41 ` [RFC PATCH 16/29] arm64/sve: signal: Add SVE state record to sigcontext Dave Martin
2016-11-25 19:41 ` [RFC PATCH 18/29] arm64/sve: signal: Restore FPSIMD/SVE state in rt_sigreturn Dave Martin
2016-11-25 19:41 ` [RFC PATCH 24/29] arm64/sve: Discard SVE state on system call Dave Martin
2016-11-25 19:41 ` [RFC PATCH 17/29] arm64/sve: signal: Dump Scalable Vector Extension registers to user stack Dave Martin
2016-11-30 9:56 ` [RFC PATCH 00/29] arm64: Scalable Vector Extension core support Yao Qi
2016-11-30 12:07 ` Dave Martin
2016-11-30 12:22 ` Szabolcs Nagy
2016-11-30 14:10 ` Dave Martin
2016-11-30 12:38 ` Florian Weimer
2016-11-30 13:56 ` Dave Martin
2016-12-01 9:21 ` Florian Weimer
2016-12-01 10:30 ` Dave Martin
2016-12-01 12:19 ` Dave Martin
2016-12-05 10:44 ` Florian Weimer
2016-12-05 11:07 ` Szabolcs Nagy
2016-12-05 15:05 ` Dave Martin
2016-12-02 11:49 ` Dave Martin
2016-12-02 16:34 ` Florian Weimer
2016-12-02 16:59 ` Joseph Myers
2016-12-02 18:21 ` Dave Martin [this message]
2016-12-02 21:57 ` Joseph Myers
2016-12-02 21:56 ` Yao Qi
2016-12-05 15:12 ` Dave Martin
2016-12-05 22:42 ` Torvald Riegel
2016-12-06 14:46 ` Dave Martin
2016-11-30 10:08 ` Florian Weimer
2016-11-30 11:06 ` Szabolcs Nagy
2016-11-30 14:06 ` Dave Martin
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=20161202182126.GS1574@e103592.cambridge.arm.com \
--to=dave.martin@arm.com \
--cc=Marc.Zyngier@arm.com \
--cc=alan.hayward@arm.com \
--cc=ard.biesheuvel@linaro.org \
--cc=christoffer.dall@linaro.org \
--cc=fweimer@redhat.com \
--cc=gdb@sourceware.org \
--cc=joseph@codesourcery.com \
--cc=libc-alpha@sourceware.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=qiyaoltc@gmail.com \
--cc=triegel@redhat.com \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).