From mboxrd@z Thu Jan  1 00:00:00 1970
From: Thomas Monjalon <thomas.monjalon@6wind.com>
Subject: Re: [PATCH v3 4/4] eal/arm: introduce
	CONFIG_RTE_ARCH_ARM_NEON_MEMCPY
Date: Sun, 20 Mar 2016 11:33:37 +0100
Message-ID: <3300542.bjkaoNcO2a@xps13>
References: <1458417485-29436-1-git-send-email-viktorin@rehivetech.com>
 <20160320104110.3c05f405@jvn> <20160320104655.45a5c863@jvn>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7Bit
Cc: dev@dpdk.org, jerin.jacob@caviumnetworks.com, tomaszx.kulasek@intel.com,
 jianbo.liu@linaro.org
To: Jan Viktorin <viktorin@rehivetech.com>
Return-path: <dev-bounces@dpdk.org>
Received: from mail-wm0-f52.google.com (mail-wm0-f52.google.com [74.125.82.52])
 by dpdk.org (Postfix) with ESMTP id F0D1D2BD6
 for <dev@dpdk.org>; Sun, 20 Mar 2016 11:35:12 +0100 (CET)
Received: by mail-wm0-f52.google.com with SMTP id p65so89564172wmp.0
 for <dev@dpdk.org>; Sun, 20 Mar 2016 03:35:12 -0700 (PDT)
In-Reply-To: <20160320104655.45a5c863@jvn>
List-Id: patches and discussions about DPDK <dev.dpdk.org>
List-Unsubscribe: <http://dpdk.org/ml/options/dev>,
 <mailto:dev-request@dpdk.org?subject=unsubscribe>
List-Archive: <http://dpdk.org/ml/archives/dev/>
List-Post: <mailto:dev@dpdk.org>
List-Help: <mailto:dev-request@dpdk.org?subject=help>
List-Subscribe: <http://dpdk.org/ml/listinfo/dev>,
 <mailto:dev-request@dpdk.org?subject=subscribe>
Errors-To: dev-bounces@dpdk.org
Sender: "dev" <dev-bounces@dpdk.org>

2016-03-20 10:46, Jan Viktorin:
> On Sun, 20 Mar 2016 10:41:10 +0100
> Jan Viktorin <viktorin@rehivetech.com> wrote:
> 
> > On Sat, 19 Mar 2016 21:14:57 +0100
> > Thomas Monjalon <thomas.monjalon@6wind.com> wrote:
> > 
> > > 2016-03-19 20:58, Jan Viktorin:  
> > > > The flag is used to enable memcpy optimizations in EAL. As it is not always
> > > > the performance benefit, the flag allows to disable it.    
> > > 
> > > Ideally the default should be to choose the best optimization.
> > > If it is not possible, it would help to have some comments explaining
> > > how to choose wether enabling NEON memcpy or not.
> 
> The related statistics are mentioned here:
> 
> commit 04a2fde35daf5e9a271e72331a70b48b951d7568
> Author: Vlastimil Kosar <kosar@rehivetech.com>
> Date:   Tue Nov 3 00:47:20 2015 +0100
> 
>     eal/arm: add vector memcpy for ARMv7
> 
> It's quite difficult to easily summarize it, especially for so many
> CPUs...

If it is difficult for you, it will be  impossible for the users of
this config option.
When someone will ask what is the best value for his CPU, what will
you answer?
At least, we can add a comment explaining that the performance is not
always better, depending of the buffer size and the CPU.