From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([140.186.70.92]:38284)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <zhur@ispras.ru>) id 1QNlax-0001Au-MO
	for qemu-devel@nongnu.org; Sat, 21 May 2011 08:47:55 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <zhur@ispras.ru>) id 1QNlaw-0001z5-Em
	for qemu-devel@nongnu.org; Sat, 21 May 2011 08:47:51 -0400
Received: from smtp.ispras.ru ([83.149.198.202]:58939)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <zhur@ispras.ru>) id 1QNlaw-0001yk-8J
	for qemu-devel@nongnu.org; Sat, 21 May 2011 08:47:50 -0400
Message-ID: <4DD7B469.1040802@ispras.ru>
Date: Sat, 21 May 2011 16:47:37 +0400
From: Dmitry Zhurikhin <zhur@ispras.ru>
MIME-Version: 1.0
References: <cover.1305889001.git.batuzovk@ispras.ru>
	<20110520193508.GB27170@hall.aurel32.net>
In-Reply-To: <20110520193508.GB27170@hall.aurel32.net>
Content-Type: text/plain; charset=ISO-8859-15
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [PATCH 0/6] Implement constant folding and copy
 propagation in TCG
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Aurelien Jarno <aurelien@aurel32.net>
Cc: mj.mccormack@samsung.com, qemu-devel@nongnu.org, Kirill Batuzov <batuzovk@ispras.ru>

On 05/20/2011 11:35 PM, Aurelien Jarno wrote:
> 
> On Fri, May 20, 2011 at 04:39:27PM +0400, Kirill Batuzov wrote:
>> This series implements some basic machine-independent optimizations.  They
>> simplify code and allow liveness analysis do it's work better.
>>
>> Suppose we have following ARM code:
>>
>>  movw    r12, #0xb6db
>>  movt    r12, #0xdb6d
>>
>> In TCG before optimizations we'll have:
>>
>>  movi_i32 tmp8,$0xb6db
>>  mov_i32 r12,tmp8
>>  mov_i32 tmp8,r12
>>  ext16u_i32 tmp8,tmp8
>>  movi_i32 tmp9,$0xdb6d0000
>>  or_i32 tmp8,tmp8,tmp9
>>  mov_i32 r12,tmp8
>>
>> And after optimizations we'll have this:
>>
>>  movi_i32 r12,$0xdb6db6db
>>
>> Here are performance evaluation results on SPEC CPU2000 integer tests in
>> user-mode emulation on x86_64 host.  There were 5 runs of each test on
>> reference data set.  The tables below show runtime in seconds for all these
>> runs.
> 
> How are the tests done? Are they done with linux-user, or running the
> executables in qemu-system-xxx?
They were run in user mode on a dedicated machine not doing anything
else.  We found system emulation to be too volatile for measuring
anything.  Anyway even with user mode and on a dedicated machine there
are some weird performance jumps we can't explain but overall SPEC seems
stable enough to notice influence of such changes in code generation.

> 
>> ...

	Dmitry