From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1MdRKV-0003Lt-7Q
	for qemu-devel@nongnu.org; Tue, 18 Aug 2009 12:14:35 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1MdRKQ-0003Jy-DY
	for qemu-devel@nongnu.org; Tue, 18 Aug 2009 12:14:34 -0400
Received: from [199.232.76.173] (port=42501 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1MdRKQ-0003Jq-28
	for qemu-devel@nongnu.org; Tue, 18 Aug 2009 12:14:30 -0400
Received: from mail2.shareable.org ([80.68.89.115]:58262)
	by monty-python.gnu.org with esmtps (TLS-1.0:RSA_AES_256_CBC_SHA1:32)
	(Exim 4.60) (envelope-from <jamie@shareable.org>) id 1MdRKP-0004an-OG
	for qemu-devel@nongnu.org; Tue, 18 Aug 2009 12:14:29 -0400
Date: Tue, 18 Aug 2009 17:14:24 +0100
From: Jamie Lokier <jamie@shareable.org>
Subject: Re: [Qemu-devel] Arm emulation tweak
Message-ID: <20090818161424.GA1435@shareable.org>
References: <4A8ACF77.3090801@bandsman.co.uk>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <4A8ACF77.3090801@bandsman.co.uk>
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: Nigel Horne <njh@bandsman.co.uk>
Cc: qemu-devel@nongnu.org

Nigel Horne wrote:
> This small patch reduces (on my machine) the call to new_tmp by 16 
> bytes, which may not sound much, but it's called so often that it makes 
> a nice speed up of Arm emulation:

>      if (GET_TCGV_I32(temps[num_temps]))
>        return temps[num_temps++];
> 
> !     tmp = tcg_temp_new_i32();
> !     temps[num_temps++] = tmp;
> !     return tmp;
>  }

becomes

>      if (GET_TCGV_I32(temps[num_temps]))
>        return temps[num_temps++];
> 
> !     return temps[num_temps++] = tcg_temp_new_i32();
>  }

That's pretty tragic if GCC fails to compile them to identical code,
assuming you had optimisation turned on.

Have you tried building with -Os, -O2 etc. to see if that makes a
difference?

Which GCC version are you using?

-- Jamie