From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1NMrMp-0004UW-7l
	for qemu-devel@nongnu.org; Mon, 21 Dec 2009 18:08:43 -0500
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1NMrMi-0004Ts-R9
	for qemu-devel@nongnu.org; Mon, 21 Dec 2009 18:08:41 -0500
Received: from [199.232.76.173] (port=57049 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1NMrMi-0004Tp-Lt
	for qemu-devel@nongnu.org; Mon, 21 Dec 2009 18:08:36 -0500
Received: from mail-pz0-f188.google.com ([209.85.222.188]:50180)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <laurent.desnogues@gmail.com>) id 1NMrMi-0008Nx-D4
	for qemu-devel@nongnu.org; Mon, 21 Dec 2009 18:08:36 -0500
Received: by pzk26 with SMTP id 26so3337446pzk.4
	for <qemu-devel@nongnu.org>; Mon, 21 Dec 2009 15:08:35 -0800 (PST)
MIME-Version: 1.0
In-Reply-To: <4B2FFBA3.4060601@twiddle.net>
References: <cover.1261248772.git.rth@twiddle.net>
	<200912202257.22503.paul@codesourcery.com>
	<4B2ED6D0.1010900@twiddle.net>
	<761ea48b0912210113p42608776q7677f79eec83f5a6@mail.gmail.com>
	<4B2FDA53.6040605@twiddle.net>
	<761ea48b0912211421y2e213dc0gfed24835f3b7f658@mail.gmail.com>
	<4B2FFBA3.4060601@twiddle.net>
Date: Tue, 22 Dec 2009 00:08:35 +0100
Message-ID: <761ea48b0912211508i481286b8gcb78c34afb4e26ea@mail.gmail.com>
Subject: Re: [Qemu-devel] [PATCH 0/5] tcg conditional set, round 4
From: Laurent Desnogues <laurent.desnogues@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.gnu.org/pipermail/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Richard Henderson <rth@twiddle.net>
Cc: Paul Brook <paul@codesourcery.com>, aurelien@aurel32.net, qemu-devel@nongnu.org

On Mon, Dec 21, 2009 at 11:50 PM, Richard Henderson <rth@twiddle.net> wrote=
:
[...]
>> Even if movcond was quick to generate
>> host code, for instance for ARM, you'd have to explicitly detect
>> conditional moves
>
> One of us is confused. =A0Why would I have to explicitly detect condition=
al
> moves?

Most ARM instructions are conditional, with condition code being the
top 4 bits of the instruction.  So the front-end does it the simplest
way possible:

    if (cond !=3D 0xe) {
        /* if not always execute, we generate a conditional jump to
           next instruction */
        s->condlabel =3D gen_new_label();
        gen_test_cc(cond ^ 1, s->condlabel);
        s->condjmp =3D 1;
    }

and then generates the code for the instruction as if it wasn't
conditional.  If you wanted to use movcond, you'd have to make
cond + move a special case, which would add some cost to
all conditional instructions.  OTOH that cost could be amortized
by generating less TCG ops for that instruction, and by a
potentially faster generated code.  But if this isn't measured I
won't bet which one is faster, I have been wrong too often.


Laurent