From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <bruce.richardson@intel.com>
Received: from mga11.intel.com (mga11.intel.com [192.55.52.93])
 by dpdk.org (Postfix) with ESMTP id ED46A8DAD
 for <dev@dpdk.org>; Wed, 13 Jan 2016 12:34:36 +0100 (CET)
Received: from fmsmga002.fm.intel.com ([10.253.24.26])
 by fmsmga102.fm.intel.com with ESMTP; 13 Jan 2016 03:34:37 -0800
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.22,288,1449561600"; d="scan'208";a="892278304"
Received: from bricha3-mobl3.ger.corp.intel.com ([10.237.208.64])
 by fmsmga002.fm.intel.com with SMTP; 13 Jan 2016 03:34:34 -0800
Received: by  (sSMTP sendmail emulation); Wed, 13 Jan 2016 11:34:33 +0025
Date: Wed, 13 Jan 2016 11:34:33 +0000
From: Bruce Richardson <bruce.richardson@intel.com>
To: Moon-Sang Lee <sang0627@gmail.com>
Message-ID: <20160113113432.GA7216@bricha3-MOBL3>
References: <CAACK=Xe4HtqjmOkuscbpWGs2NzPQjEmsUxvhhLih5cX1d5MXSQ@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAACK=Xe4HtqjmOkuscbpWGs2NzPQjEmsUxvhhLih5cX1d5MXSQ@mail.gmail.com>
Organization: Intel Shannon Ltd.
User-Agent: Mutt/1.5.23 (2014-03-12)
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] rte_prefetch0() is effective?
X-BeenThere: dev@dpdk.org
X-Mailman-Version: 2.1.15
Precedence: list
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>
X-List-Received-Date: Wed, 13 Jan 2016 11:34:37 -0000

On Thu, Dec 24, 2015 at 03:35:14PM +0900, Moon-Sang Lee wrote:
> I see codes as below in example directory, and I wonder it is effective.
> Coherent IO is adopted to modern architectures,
> so I think that DMA initiation by rte_eth_rx_burst() might already fulfills
> cache lines of RX buffers.
> Do I really need to call rte_prefetchX()?
> 
>             nb_rx = rte_eth_rx_burst(portid, queueid, pkts_burst,
> MAX_PKT_BURST);
>             ...
>             /* Prefetch and forward already prefetched packets */
>             for (j = 0; j < (nb_rx - PREFETCH_OFFSET); j++) {
>                 rte_prefetch0(rte_pktmbuf_mtod(pkts_burst[
>                         j + PREFETCH_OFFSET], void *));
>                 l3fwd_simple_forward(pkts_burst[j], portid,
>                     qconf);
>             }
> 

Good question.
When the first example apps using this style of prefetch were originally written,
yes, there was a noticable performance increase achieved by using the prefetch.
Thereafter, I'm not sure that anyone has checked with each generation of
platforms whether the prefetches are still necessary and how much they help, but
I suspect that they still help a bit, and don't hurt performance.
It would be an interesting exercise to check whether the prefetch offsets used
in code like above can be adjusted to give better performance on our latest
supported platforms.

/Bruce