From mboxrd@z Thu Jan  1 00:00:00 1970
From: Thomas Monjalon <thomas.monjalon@6wind.com>
Subject: Re: [PATCH 2/5] i40e: implement vector PMD for ARM
	architecture
Date: Fri, 26 Aug 2016 16:20:18 +0200
Message-ID: <5549852.k8GMpo7ItU@xps13>
References: <1472032425-16136-1-git-send-email-jianbo.liu@linaro.org>
 <1472032425-16136-3-git-send-email-jianbo.liu@linaro.org>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7Bit
Cc: dev@dpdk.org, helin.zhang@intel.com, jingjing.wu@intel.com,
 jerin.jacob@caviumnetworks.com
To: Jianbo Liu <jianbo.liu@linaro.org>
Return-path: <dev-bounces@dpdk.org>
Received: from mail-wm0-f45.google.com (mail-wm0-f45.google.com [74.125.82.45])
 by dpdk.org (Postfix) with ESMTP id A87A45A6C
 for <dev@dpdk.org>; Fri, 26 Aug 2016 16:20:20 +0200 (CEST)
Received: by mail-wm0-f45.google.com with SMTP id q128so281414070wma.1
 for <dev@dpdk.org>; Fri, 26 Aug 2016 07:20:20 -0700 (PDT)
In-Reply-To: <1472032425-16136-3-git-send-email-jianbo.liu@linaro.org>
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>

Hi Jianbo (and other developers of vectorized PMDs),

2016-08-24 15:23, Jianbo Liu:
> Use ARM NEON intrinsic to implement i40e vPMD

Have you tried to use the generic SIMD intrinsics?
We could maintain only one vectorized implementation by using
	__attribute__ ((vector_size (n)))
as described in https://gcc.gnu.org/onlinedocs/gcc/Vector-Extensions.html

I don't know the limitations of the vector builtins (support, performance,
endianness, etc) but it is worth making a try.
Currently we target to support each PMD for SSE/AVX, Altivec and NEON.
Is there any volunteers working on Intel, POWER and ARM to try converting
the existing codebase?

Thanks