From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.33)
	id 1CgVK5-0001Qo-0X
	for qemu-devel@nongnu.org; Mon, 20 Dec 2004 16:44:09 -0500
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.33)
	id 1CgVK1-0001NR-Mr
	for qemu-devel@nongnu.org; Mon, 20 Dec 2004 16:44:06 -0500
Received: from [199.232.76.173] (helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.33) id 1CgVK1-0001ME-Hb
	for qemu-devel@nongnu.org; Mon, 20 Dec 2004 16:44:05 -0500
Received: from [64.233.184.195] (helo=wproxy.gmail.com)
	by monty-python.gnu.org with esmtp (Exim 4.34) id 1CgV7w-0006T6-Jv
	for qemu-devel@nongnu.org; Mon, 20 Dec 2004 16:31:36 -0500
Received: by wproxy.gmail.com with SMTP id 68so633444wri
	for <qemu-devel@nongnu.org>; Mon, 20 Dec 2004 13:31:34 -0800 (PST)
Message-ID: <da63183704122013313371ce6@mail.gmail.com>
Date: Mon, 20 Dec 2004 22:31:34 +0100
From: Piotras <piotras@gmail.com>
In-Reply-To: <aec7e5c304122009555c1f820f@mail.gmail.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
References: <aec7e5c304122009555c1f820f@mail.gmail.com>
Subject: [Qemu-devel] Re: [PATCH] CONFIG_MMU_MAP powerpc host support
Reply-To: Piotras <piotras@gmail.com>, qemu-devel@nongnu.org
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: Magnus Damm <magnus.damm@gmail.com>, qemu-devel@nongnu.org

Great!

Do you have an estimate of possible performance gain by introducing 
direct pointer to mmu_map for memory read?

I have two ideas for future experimentation.

There is a trick possible without wasting another register for global 
variable: use two copies of CPUState (one for privileged and another 
for user mode), then make mmu_map.add_read first member of the 
struct. This would introduce guest register coping for user/supervisor 
switch, but maybe performance gain would justify this.

Another idea: if we could align add_read/add_write on 64k boundary, 
"addi" could be removed.


Regards,

Piotrek

On Mon, 20 Dec 2004 18:55:21 +0100, Magnus Damm <magnus.damm@gmail.com> wrote:
> Hello,
> 
> This patch adds powerpc host support to the CONFIG_MMU_MAP patch
> written by Piotrek. My patch should be applied on top of
> v1-part[1-3].patch.gz. I have only tested the code with a x86 guest on
> a ppc host running Linux - someone, please test on a host running OSX.
> 
> Performance gain reported by nbench:
> 
> Memory index: 50%
> Integer index: 44%
> Fp index: 4%
> 
> Right now each map-memory access consists of 5-6 powerpc instructions.
> If a direct pointer to mem_map could be kept in a register then we
> would be down to 3-4 instructions per memoy access...
> 
> / magnus