From mboxrd@z Thu Jan  1 00:00:00 1970
X-Msuck: nntp://news.gmane.org/gmane.linux.lib.musl.general/7027
Path: news.gmane.org!not-for-mail
From: Denys Vlasenko <vda.linux@googlemail.com>
Newsgroups: gmane.linux.lib.musl.general
Subject: Re: [PATCH 1/2] x86_64/memset: avoid multiply insn if possible
Date: Fri, 13 Feb 2015 17:38:45 +0100
Message-ID: <CAK1hOcP8D2pbFMrcFWPrbiHXeB5_NBUwJ20Bf75fx1ETNp4ptA@mail.gmail.com>
References: <1423761423-30050-1-git-send-email-vda.linux@googlemail.com>
 <20150212172735.GX23507@brightrain.aerifal.cx> <CAK1hOcPVMiQo=fdRJSSMH6vx22aDbTcxjf_tFVphhNE8Szi6RQ@mail.gmail.com>
 <CAK1hOcOvpmNVO=HPy40N2StZHDt0LNaKxw5_ZjJSZ+_47Av-eg@mail.gmail.com> <20150213072436.GD23507@brightrain.aerifal.cx>
Reply-To: musl@lists.openwall.com
NNTP-Posting-Host: plane.gmane.org
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8
X-Trace: ger.gmane.org 1423845563 15176 80.91.229.3 (13 Feb 2015 16:39:23 GMT)
X-Complaints-To: usenet@ger.gmane.org
NNTP-Posting-Date: Fri, 13 Feb 2015 16:39:23 +0000 (UTC)
To: musl <musl@lists.openwall.com>
Original-X-From: musl-return-7040-gllmg-musl=m.gmane.org@lists.openwall.com Fri Feb 13 17:39:22 2015
Return-path: <musl-return-7040-gllmg-musl=m.gmane.org@lists.openwall.com>
Envelope-to: gllmg-musl@m.gmane.org
Original-Received: from mother.openwall.net ([195.42.179.200])
	by plane.gmane.org with smtp (Exim 4.69)
	(envelope-from <musl-return-7040-gllmg-musl=m.gmane.org@lists.openwall.com>)
	id 1YMJH0-0007Qh-8S
	for gllmg-musl@m.gmane.org; Fri, 13 Feb 2015 17:39:22 +0100
Original-Received: (qmail 26573 invoked by uid 550); 13 Feb 2015 16:39:20 -0000
Mailing-List: contact musl-help@lists.openwall.com; run by ezmlm
Precedence: bulk
List-Post: <mailto:musl@lists.openwall.com>
List-Help: <mailto:musl-help@lists.openwall.com>
List-Unsubscribe: <mailto:musl-unsubscribe@lists.openwall.com>
List-Subscribe: <mailto:musl-subscribe@lists.openwall.com>
Original-Received: (qmail 26520 invoked from network); 13 Feb 2015 16:39:17 -0000
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=googlemail.com; s=20120113;
        h=mime-version:in-reply-to:references:from:date:message-id:subject:to
         :content-type;
        bh=bDq0ZV/Uw/vLKmDh1A91NZnd2tnRY6ILUbH/4uMTpmM=;
        b=UhtzZfjz63trIUXkps1U8dzBXZuYcGr+0Iwtnxlz7hlOAZFaYe3ESvYpz6n9ZwjRNW
         1TcOH/8KDIc1eBer6qzdWoNWuk7AtkJzGn+Wb8Py/R6KEnsyS6SnudhGKFZsSBFjI1jq
         aWlDeNsQJ/nq4B4QRk6smFovjzak/PAf4a4Pt6wiFNjb6pXM55eaY110IsJxM6RxVqGS
         s/fr6Nsg6c7h8gDjmXzUCPDE/qn7PE+onytzWFciMYdf5ZwHwdAkcQWWzx2/mJkCLTD2
         aWuF6rNbY0V5ZlE7nYUWdBlK3hilAQoIT/T27Ryvk6vnHuaQxplC5kTYtDPXBQ+jfQz0
         E4Mw==
X-Received: by 10.140.150.16 with SMTP id 16mr1454280qhw.67.1423845545569;
 Fri, 13 Feb 2015 08:39:05 -0800 (PST)
In-Reply-To: <20150213072436.GD23507@brightrain.aerifal.cx>
Xref: news.gmane.org gmane.linux.lib.musl.general:7027
Archived-At: <http://permalink.gmane.org/gmane.linux.lib.musl.general/7027>

On Fri, Feb 13, 2015 at 8:24 AM, Rich Felker <dalias@libc.org> wrote:
> On Thu, Feb 12, 2015 at 09:36:26PM +0100, Denys Vlasenko wrote:
> In practice it performs quite well. x86's are good at this. The
> generic C code in memset.c does not do any overlapping writes of
> different sizes for the short buffer code path -- all writes there are
> single-byte, and multiple-write only happens for some of the inner
> bytes depending on the value of n.

Measurements agree: I was not able to make it faster by doing it
differently.
I did find it possible to extend your trick to be usable for up to 30
byte blocks.
Sending the patch...