From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
	id 9A55B3858015; Tue, 20 Sep 2022 14:14:59 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 9A55B3858015
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1663683299;
	bh=TuSBBrtOe1RjDHbdODEngKF2rHWc+HNCyUpV210f6x8=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=Cwfh9KVP9pSkgeGenBIQ2DjpJwI5CWjTTMMIR3xzPIu2GaWvQgVop/LLk2x8MWuAv
	 9U43ZzpF2i8DbE7Tz8hBrKFi8HWB8+1kcm7jzMNEuqMXaK1DitMKaOA6cApEFxZcme
	 /eZBjIqwyUg92fSqikfLQJE630O6Qp+ZvMQUrA4A=
From: "rodgertq at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug libstdc++/106772] atomic<T>::wait shouldn't touch waiter pool
 if used platform wait
Date: Tue, 20 Sep 2022 14:14:58 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: libstdc++
X-Bugzilla-Version: unknown
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: rodgertq at gcc dot gnu.org
X-Bugzilla-Status: RESOLVED
X-Bugzilla-Resolution: INVALID
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: 
Message-ID: <bug-106772-4-cBWpFOrWNE@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-106772-4@http.gcc.gnu.org/bugzilla/>
References: <bug-106772-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
List-Id: <gcc-bugs.sourceware.org>

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D106772

--- Comment #6 from Thomas Rodgers <rodgertq at gcc dot gnu.org> ---
(In reply to Mkkt Bkkt from comment #5)
> Single reason why I want to use atomic::wait/notify is cross platform api
> for futex, wait/wake on address, ulock, etc
> Not because I need YOU decide instead of me how many spins, or other
> optimization I need.
>=20
> boost::atomic already do this.
>=20
> Why do you cannot make same?

(In reply to Mkkt Bkkt from comment #4)
> Nice, thanks for benchmarks without code.
>=20
> Also, why do I need call notify when don't have wait?=20
>=20
> Common usage from my point of view looks like:
>=20
> atomic.wait(value, mo):
>=20
> while (atomic.load(mo) =3D=3D value) {
>   futex_wait();
> }
>=20
> Notify want to looks like:
>=20
> atomic.store(1, mo)
> atomic.notify_one();
>=20
> See:
>=20
> https://github.com/lewissbaker/cppcoro/blob/master/lib/
> lightweight_manual_reset_event.cpp
>=20

I have every confidence that Lewis knows how to bring a paper for a
'lightweight manual reset event' to SG1, I suspect it will be well received
when he does.

> https://github.com/YACLib/YACLib/blob/main/src/util/atomic_event.cpp
>=20
> and others
>=20
> So your optimization is pretty useless.
>=20
> Also if for some reason possible few notification, or notify before wait,
> then possible to have code can looks like:
>=20
> if (atomic.exchange(non_wait_value, mo) =3D=3D wait_value) {
>   atomic.notify_one();
> }

I=