From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from gate.crashing.org (gate.crashing.org [63.228.1.57])
	by smtp.subspace.kernel.org (Postfix) with ESMTP id D19823019A0
	for <linux-toolchains@vger.kernel.org>; Mon, 15 Sep 2025 15:00:43 +0000 (UTC)
Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=63.228.1.57
ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116;
	t=1757948446; cv=none; b=JcQ1tgQ/CkDIc8r1njbjDyZeMHhfz2qFIH/EZEEnNTrbTzfDiASMYr1TRFPfadEI5Z7fLYIUXtSokfnXi12RFhq2hG0qTzAciUP6xAfCA63cO1GzNE0bJIotD17BAtrmRIyVxYrwXQhnZ5DrVxPinVdM53ogb6+AKIAZQCsvlOM=
ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org;
	s=arc-20240116; t=1757948446; c=relaxed/simple;
	bh=aWr4UhRURD+gGRLmja8WvWBMsk4/mFWxq6A1ayLjpDY=;
	h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version:
	 Content-Type:Content-Disposition:In-Reply-To; b=VwbzHWLI7jFGqlsWwfBmnLqw6RTKCSQvlxTJJlZ9c4saxsgJRQUX/ebk+3sVNlPD3hXW0KYZ19MT5KJxwp3KXN3kcW9YzZC4R6RgIfWXNQZO0mtNKS4BfBv/zlrD7lbHl5f3g9lrjFBsMNYZke0I3SDXepmKF/UnpTC3IcuCt3c=
ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.crashing.org; spf=pass smtp.mailfrom=kernel.crashing.org; arc=none smtp.client-ip=63.228.1.57
Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=kernel.crashing.org
Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernel.crashing.org
Received: from gate.crashing.org (localhost [127.0.0.1])
	by gate.crashing.org (8.18.1/8.18.1/Debian-2) with ESMTP id 58FF03FH202747;
	Mon, 15 Sep 2025 10:00:03 -0500
Received: (from segher@localhost)
	by gate.crashing.org (8.18.1/8.18.1/Submit) id 58F98YGH184903;
	Mon, 15 Sep 2025 04:08:34 -0500
X-Authentication-Warning: gate.crashing.org: segher set sender to segher@kernel.crashing.org using -f
Date: Mon, 15 Sep 2025 04:08:29 -0500
From: Segher Boessenkool <segher@kernel.crashing.org>
To: Jan Beulich <jbeulich@suse.com>
Cc: Rainer Orth <ro@cebitec.uni-bielefeld.de>,
        Indu Bhagat <indu.bhagat@oracle.com>,
        "linux-toolchains@vger.kernel.org" <linux-toolchains@vger.kernel.org>,
        Jens Remus <jremus@linux.ibm.com>
Subject: Re: Unaligned access trade-offs for SFrame FRE layout
Message-ID: <aMfXjVw2ijr7u-Al@gate>
References: <b7b139c6-1963-4ffc-a872-518010a50563@oracle.com>
 <9d104c46-855c-4b36-8226-1f59b59e455c@suse.com>
 <yddbjndm72n.fsf@CeBiTec.Uni-Bielefeld.DE>
 <26895e7a-5d54-4c89-aeb4-bcd094ba081d@suse.com>
Precedence: bulk
X-Mailing-List: linux-toolchains@vger.kernel.org
List-Id: <linux-toolchains.vger.kernel.org>
List-Subscribe: <mailto:linux-toolchains+subscribe@vger.kernel.org>
List-Unsubscribe: <mailto:linux-toolchains+unsubscribe@vger.kernel.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <26895e7a-5d54-4c89-aeb4-bcd094ba081d@suse.com>

On 14.09.2025 16:39, Rainer Orth wrote:
>> On 12.09.2025 19:34, Indu Bhagat via Binutils wrote:
> look for STRICT_ALIGNMENT in the GCC sources in gcc/config.  While
> several are embedded targets, there's also sparc in that list.
>
> But is this setting a good reference for the purpose here.

It is not a setting usually, also not for you, it is a command-line
option.  Often it is good (for performance) to only do naturally aligned
accesses.  For some (sub-)archs it simply is impossible to even try to
do misaligned accesses OTOH.

> It's okay for gcc to make assumptions (assuming they're properly
> documented),

Only some implementation decisions have to be documented.  And
assumptions are almost never okay.  Typically we depend on the user
promising they do not do X (via a -mno-X flag, say) before we assume
they do not do X.


Segher