From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by dpdk.org (Postfix) with ESMTP id DC14129D2 for ; Thu, 23 Nov 2017 17:56:56 +0100 (CET) Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga104.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 23 Nov 2017 08:56:55 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.44,441,1505804400"; d="scan'208";a="5064823" Received: from bricha3-mobl3.ger.corp.intel.com ([10.237.221.35]) by FMSMGA003.fm.intel.com with SMTP; 23 Nov 2017 08:56:53 -0800 Received: by (sSMTP sendmail emulation); Thu, 23 Nov 2017 16:56:52 +0000 Date: Thu, 23 Nov 2017 16:56:52 +0000 From: Bruce Richardson To: jingjing.wu@intel.com, beilei.xing@intel.com Cc: dev@dpdk.org Message-ID: <20171123165652.GA13188@bricha3-MOBL3.ger.corp.intel.com> References: <20171123165314.168786-1-bruce.richardson@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20171123165314.168786-1-bruce.richardson@intel.com> Organization: Intel Research and Development Ireland Ltd. User-Agent: Mutt/1.9.1 (2017-09-22) Subject: Re: [dpdk-dev] [PATCH 0/2] AVX2 Vectorized Rx/Tx functions for i40e X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 23 Nov 2017 16:56:57 -0000 On Thu, Nov 23, 2017 at 04:53:12PM +0000, Bruce Richardson wrote: > This patch adds an AVX2 vectorized path to the i40e driver, based on the > existing SSE4.2 version. Using AVX2 instructions gives better performance > than the SSE version, though the percentage increase depends on the exact > settings used. For example: > > * Using 16B rather than 32B descriptors gives the biggest benefit since > 2 descriptors at a time can be read, rather than just 1 when 32B ones > are used. > * Bigger burst sizes for RX gives improved performance - while we see an > improvement with testpmd with the default burst size of 32, burst sizes > of up to 128 give further improvements > * In my testing, most of the improvement comes from faster processing on > the RX path, though the improved TX also gives benefit. > > This has been tested on a system with CPU: "Intel(R) Xeon(R) Gold 6154 CPU > @ 3.00GHz", and I've focused on testing with Rx ring sizes of approx 1k - > generally --rxd=1024 and --txd=512, rather than the defaults which tend to > give poorer zero-loss performance due to the smaller amount of buffering. > > Bruce Richardson (2): > net/i40e: add AVX2 Tx function > net/i40e: add AVX2 Rx function > Just also to note that this set has quite a number of checkpatch warnings about long lines. These were deliberately left in, as the lines are not significantly over 80 characters, and I felt that splitting them would have hurt readability. /Bruce