From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: Re: [PATCH] xen/arm: minor improvement in
	smp_send_call_function_mask()
Date: Thu, 21 Aug 2014 18:22:03 +0100
Message-ID: <53F62ABB.6080203@citrix.com>
References: <1408423704-15059-1-git-send-email-anup.patel@linaro.org>	<53F3BC41.5040409@linaro.org>	<CALrVBku4D6NVrAQkry0JqN5ongvc6ko77QOdh_238tYU=_Dhbw@mail.gmail.com>	<53F4B9B4.5090303@linaro.org>	<CALrVBkuyo7V_=1GUHvVrcBBKH=q=tDGmZr8uUoX7Do3DT1oj8Q@mail.gmail.com>
	<53F62455.2030906@linaro.org>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
In-Reply-To: <53F62455.2030906@linaro.org>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: Julien Grall <julien.grall@linaro.org>, Anup Patel <anup.patel@linaro.org>
Cc: Ian Campbell <Ian.Campbell@citrix.com>, Stefano Stabellini <stefano.stabellini@eu.citrix.com>, patches <patches@apm.com>, xen-devel <xen-devel@lists.xen.org>, "stefano.stabellini" <stefano.stabellini@citrix.com>, Pranavkumar Sawargaonkar <pranavkumar@linaro.org>
List-Id: xen-devel@lists.xenproject.org

On 21/08/14 17:54, Julien Grall wrote:
> Hi Anup,
>
> On 21/08/14 06:04, Anup Patel wrote:
>>> The best alternative would be cpumask_empty.
>>
>> All three cpumask_empty(), cpumask_first(), and cpumask_weight()
>> are O(N) where N is number of bits in cpumask.
>> It really does not make much difference which of these operation
>> is chosen.

They are all O(N), but O() notation hides lesser factors.

cpumask_empty() is slightly cheaper than cpumask_first(), which are both
substantially cheaper than cpumask_weight().

There is no fastpath for calculating the hamming weight of 0, resulting
in a lot of dependent shift/mask operations.

~Andrew