From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id 6291F282 for ; Mon, 9 Jan 2017 10:48:47 +0100 (CET) Received: from orsmga002.jf.intel.com ([10.7.209.21]) by orsmga103.jf.intel.com with ESMTP; 09 Jan 2017 01:48:46 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.33,339,1477983600"; d="scan'208";a="27933679" Received: from fmsmsx107.amr.corp.intel.com ([10.18.124.205]) by orsmga002.jf.intel.com with ESMTP; 09 Jan 2017 01:48:46 -0800 Received: from bgsmsx106.gar.corp.intel.com (10.223.43.196) by fmsmsx107.amr.corp.intel.com (10.18.124.205) with Microsoft SMTP Server (TLS) id 14.3.248.2; Mon, 9 Jan 2017 01:48:45 -0800 Received: from bgsmsx101.gar.corp.intel.com ([169.254.1.215]) by BGSMSX106.gar.corp.intel.com ([169.254.1.137]) with mapi id 14.03.0248.002; Mon, 9 Jan 2017 15:18:42 +0530 From: "Yang, Zhiyong" To: "thomas.monjalon@6wind.com" , "Richardson, Bruce" , "Ananyev, Konstantin" CC: "yuanhan.liu@linux.intel.com" , "De Lara Guarch, Pablo" , "dev@dpdk.org" Thread-Topic: [dpdk-dev] [PATCH v2 0/4] eal/common: introduce rte_memset and related test Thread-Index: AQHSYCjiz1LitX27AUaZEesePw46VKEv+QAg Date: Mon, 9 Jan 2017 09:48:41 +0000 Message-ID: References: <1480926387-63838-2-git-send-email-zhiyong.yang@intel.com> <1482833098-38096-1-git-send-email-zhiyong.yang@intel.com> In-Reply-To: <1482833098-38096-1-git-send-email-zhiyong.yang@intel.com> Accept-Language: en-US Content-Language: en-US X-MS-Has-Attach: X-MS-TNEF-Correlator: x-titus-metadata-40: eyJDYXRlZ29yeUxhYmVscyI6IiIsIk1ldGFkYXRhIjp7Im5zIjoiaHR0cDpcL1wvd3d3LnRpdHVzLmNvbVwvbnNcL0ludGVsMyIsImlkIjoiOTlmNzFkMzYtODA1NS00MWJjLTlkNzktNTM3M2EwMDgwMzk5IiwicHJvcHMiOlt7Im4iOiJDVFBDbGFzc2lmaWNhdGlvbiIsInZhbHMiOlt7InZhbHVlIjoiQ1RQX0lDIn1dfV19LCJTdWJqZWN0TGFiZWxzIjpbXSwiVE1DVmVyc2lvbiI6IjE1LjkuNi42IiwiVHJ1c3RlZExhYmVsSGFzaCI6Im02OVArd0xEaEJGV0dUbjl1aXVwQWh0ZDhJY202dVo5c3ZpY1NjcmRBbmM9In0= x-ctpclassification: CTP_IC x-originating-ip: [10.223.10.10] Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Subject: Re: [dpdk-dev] [PATCH v2 0/4] eal/common: introduce rte_memset and related test 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: Mon, 09 Jan 2017 09:48:47 -0000 Hi, Thomas, Bruce, Konstantin: Any comments about the patchset? Do I need to modify anything? Thanks Zhiyong=20 > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Zhiyong Yang > Sent: Tuesday, December 27, 2016 6:05 PM > To: dev@dpdk.org > Cc: yuanhan.liu@linux.intel.com; thomas.monjalon@6wind.com; Richardson, > Bruce ; Ananyev, Konstantin > ; De Lara Guarch, Pablo > > Subject: [dpdk-dev] [PATCH v2 0/4] eal/common: introduce rte_memset and > related test >=20 > DPDK code has met performance drop badly in some case when calling glibc > function memset. Reference to discussions about memset in > http://dpdk.org/ml/archives/dev/2016-October/048628.html > It is necessary to introduce more high efficient function to fix it. > One important thing about rte_memset is that we can get clear control on > what instruction flow is used. >=20 > This patchset introduces rte_memset to bring more high efficient > implementation, and will bring obvious perf improvement, especially for > small N bytes in the most application scenarios. >=20 > Patch 1 implements rte_memset in the file rte_memset.h on IA platform The > file supports three types of instruction sets including sse & avx (128bit= s), > avx2(256bits) and avx512(512bits). rte_memset makes use of vectorization > and inline function to improve the perf on IA. In addition, cache line an= d > memory alignment are fully taken into consideration. >=20 > Patch 2 implements functional autotest to validates the function whether = to > work in a right way. >=20 > Patch 3 implements performance autotest separately in cache and memory. > We can see the perf of rte_memset is obviously better than glibc memset > especially for small N bytes. >=20 > Patch 4 Using rte_memset instead of copy_virtio_net_hdr can bring 3%~4% > performance improvements on IA platform from virtio/vhost non-mergeable > loopback testing. >=20 > Changes in V2: >=20 > Patch 1: > Rename rte_memset.h -> rte_memset_64.h and create a file rte_memset.h > for each arch. >=20 > Patch 3: > add the perf comparation data between rte_memset and memset on > haswell. >=20 > Patch 4: > Modify release_17_02.rst description. >=20 > Zhiyong Yang (4): > eal/common: introduce rte_memset on IA platform > app/test: add functional autotest for rte_memset > app/test: add performance autotest for rte_memset > lib/librte_vhost: improve vhost perf using rte_memset >=20 > app/test/Makefile | 3 + > app/test/test_memset.c | 158 +++++++++ > app/test/test_memset_perf.c | 348 +++++++++++++++= ++++ > doc/guides/rel_notes/release_17_02.rst | 7 + > .../common/include/arch/arm/rte_memset.h | 36 ++ > .../common/include/arch/ppc_64/rte_memset.h | 36 ++ > .../common/include/arch/tile/rte_memset.h | 36 ++ > .../common/include/arch/x86/rte_memset.h | 51 +++ > .../common/include/arch/x86/rte_memset_64.h | 378 > +++++++++++++++++++++ > lib/librte_eal/common/include/generic/rte_memset.h | 52 +++ > lib/librte_vhost/virtio_net.c | 18 +- > 11 files changed, 1116 insertions(+), 7 deletions(-) create mode 100644 > app/test/test_memset.c create mode 100644 app/test/test_memset_perf.c > create mode 100644 > lib/librte_eal/common/include/arch/arm/rte_memset.h > create mode 100644 > lib/librte_eal/common/include/arch/ppc_64/rte_memset.h > create mode 100644 lib/librte_eal/common/include/arch/tile/rte_memset.h > create mode 100644 > lib/librte_eal/common/include/arch/x86/rte_memset.h > create mode 100644 > lib/librte_eal/common/include/arch/x86/rte_memset_64.h > create mode 100644 lib/librte_eal/common/include/generic/rte_memset.h >=20 > -- > 2.7.4