From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
	id S1753240AbcHRD7k (ORCPT <rfc822;w@1wt.eu>);
	Wed, 17 Aug 2016 23:59:40 -0400
Received: from terminus.zytor.com ([198.137.202.10]:49638 "EHLO mail.zytor.com"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1753000AbcHRD7j (ORCPT <rfc822;linux-kernel@vger.kernel.org>);
	Wed, 17 Aug 2016 23:59:39 -0400
User-Agent: K-9 Mail for Android
In-Reply-To: <20160818034513.GA21415@nazgul.tnic>
References: <20160816142642.GA24206@yexl-desktop> <9FF32F53-5EF8-40D4-B696-A30FDF7201E1@zytor.com> <20160816171635.GA10542@nazgul.tnic> <796A2A72-06B7-4B3D-AA38-DF558FC75857@zytor.com> <20160817054605.GA6728@nazgul.tnic> <87r39n58sv.fsf@yhuang-mobile.sh.intel.com> <20160818034513.GA21415@nazgul.tnic>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain;
 charset=UTF-8
Subject: Re: [LKP] [lkp] [x86/hweight] 65ea11ec6a: will-it-scale.per_process_ops 9.3% improvement
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Wed, 17 Aug 2016 20:57:12 -0700
To: Borislav Petkov <bp@suse.de>, "Huang, Ying" <ying.huang@intel.com>
CC: Denys Vlasenko <dvlasenk@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>, Brian Gerst <brgerst@gmail.com>,
        LKML <linux-kernel@vger.kernel.org>,
        Andy Lutomirski <luto@amacapital.net>, lkp@01.org,
        Thomas Gleixner <tglx@linutronix.de>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Ingo Molnar <mingo@kernel.org>,
        =?ISO-8859-1?Q?Ville_Syrj=E4l=E4?= <ville.syrjala@linux.intel.com>
Message-ID: <ABE9E34B-8A07-4A82-B7A0-BA340FE2C6B2@zytor.com>
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On August 17, 2016 8:45:13 PM PDT, Borislav Petkov <bp@suse.de> wrote:
>On Wed, Aug 17, 2016 at 03:29:04PM -0700, Huang, Ying wrote:
>> branch-miss-rate decreased from ~0.30% to ~0.043%.
>> 
>> So I guess there are some code alignment change, which caused
>decreased
>> branch miss rate.
>
>Hrrm, I still can't imagine how that would happen if the machine
>supports POPCNT and we never call the __sw_hweight* variants. Or does
>it?
>
>Can you paste /proc/cpuinfo from that Sandy Bridge-EP box?
>
>Thanks.

popcnt was introduced in Nehalem AFAIK, two generations before Sandy Bridge.
-- 
Sent from my Android device with K-9 Mail. Please excuse brevity and formatting.