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 3DDEE385828C; Sun, 10 Dec 2023 10:32:44 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 3DDEE385828C
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org;
	s=default; t=1702204364;
	bh=5OaTaUNVKH8dk72i1CN0p1kOhyERE1PzklhDZU6/8hQ=;
	h=From:To:Subject:Date:In-Reply-To:References:From;
	b=cYwy5LCHltr9x/+lnH7bvIRw4JE9XTvxoOzlcOJdfy+q0o+fAYjglUMMHbxFuFRml
	 VchxLa7V6CNxagy5LFTFrIFG3odtFCvFmJZSauY5/i3jGL1wfW2SnblShvu4dv1Ide
	 I9hbV/81LtS9ImT3eofIwGdQvnKTVGKGGpT0fxao=
From: "admin_public at liblfds dot org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug target/80878] -mcx16 (enable 128 bit CAS) on x86_64 seems not
 to work on 7.1.0
Date: Sun, 10 Dec 2023 10:32:43 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: changed
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: target
X-Bugzilla-Version: 7.1.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: admin_public at liblfds dot org
X-Bugzilla-Status: NEW
X-Bugzilla-Resolution: 
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-80878-4-KDTireLRV7@http.gcc.gnu.org/bugzilla/>
In-Reply-To: <bug-80878-4@http.gcc.gnu.org/bugzilla/>
References: <bug-80878-4@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=3D80878

--- Comment #43 from admin_public at liblfds dot org ---
> I tested CMPXCHG16B with inline assembly on an i7-1165G7 (Dell XPS 13 930=
5) and it turned out to be much slower than CMPXCHG, even slower than a pai=
r of calls to `pthread_mutex_lock()` and unlock.

Mutexes are faster when single threaded and there's no contention to the
locking object.  Compare-exchange (8 or 16) is much faster (orders of magni=
tude
faster) as contention rises.

Sometimes you need CAS 16, rather than CAS 8, due to the implementation
requirements of lock free data structures.=