From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on dcvr.yhbt.net X-Spam-Level: X-Spam-ASN: AS3215 2.6.0.0/16 X-Spam-Status: No, score=-4.1 required=3.0 tests=AWL,BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,MAILING_LIST_MULTI, RCVD_IN_DNSWL_MED,SPF_HELO_PASS,SPF_PASS shortcircuit=no autolearn=ham autolearn_force=no version=3.4.2 Received: from sourceware.org (server2.sourceware.org [IPv6:2620:52:3:1:0:246e:9693:128c]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256) (No client certificate requested) by dcvr.yhbt.net (Postfix) with ESMTPS id 8ED321F8C6 for ; Wed, 15 Sep 2021 08:25:24 +0000 (UTC) Received: from server2.sourceware.org (localhost [IPv6:::1]) by sourceware.org (Postfix) with ESMTP id B2EF93858421 for ; Wed, 15 Sep 2021 08:25:21 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org B2EF93858421 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sourceware.org; s=default; t=1631694321; bh=jTZpupluWG186kW9YP0JFJGRq22VvVL7AqsKMTmLPxE=; h=To:Subject:Date:References:In-Reply-To:List-Id:List-Unsubscribe: List-Archive:List-Post:List-Help:List-Subscribe:From:Reply-To: From; b=SPJIrKUZFxc2I1ckL+6P9x4TYtUvK2pZQfCBMyWqmPuyAvn3irFh9yQuxJlaAAZAE M7CNGu4a5P8CNGgai4qrK9vhQoAfLhmqWguX9gXqnY9GKwD57KcHLc3XndL2+Urx/K IboWmC6HKYZBnEywxAVDXQ6OxBa62yMKkWPjCfeY= Received: from esa2.fujitsucc.c3s2.iphmx.com (esa2.fujitsucc.c3s2.iphmx.com [68.232.152.246]) by sourceware.org (Postfix) with ESMTPS id 806F33858C2C for ; Wed, 15 Sep 2021 08:25:01 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.4.1 sourceware.org 806F33858C2C X-IronPort-AV: E=McAfee;i="6200,9189,10107"; a="47406009" X-IronPort-AV: E=Sophos;i="5.85,294,1624287600"; d="scan'208";a="47406009" Received: from mail-os2jpn01lp2050.outbound.protection.outlook.com (HELO JPN01-OS2-obe.outbound.protection.outlook.com) ([104.47.92.50]) by ob1.fujitsucc.c3s2.iphmx.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 15 Sep 2021 17:24:59 +0900 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=kOCMepl/2HOp4HNY5pGDBG+rNQgXSkLOyaVNvcLT27zchHhK7autZc31VldiWp9YIpfPvwp3gcrhRZkILZTkwvDginIcBOs9n4AYNarbvswPVPp+aw7SBlwVQDrO+hpTdtSIbK+ZrqxR/Mnweaf4WxV5qVn5vAqFfHlWPFUBUI0py5b9cLCyFwoFGa4oL+V3zxUc/w/wqewv/E/Tvz8wSFbW+fMsyEiZauIL8ATB/AzAPgOrcmIMIdneYjL8oOQ0hJIIJnAeE3owVUzCUevHOlYCtftwa95K9VQZrwCIFjE9VWu7Eg5yRniZm03VTf8dreZW/dfqpeXbMBBuVpSIXA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version; bh=jTZpupluWG186kW9YP0JFJGRq22VvVL7AqsKMTmLPxE=; b=RjxNtTluW0FOvKk7yjbq3n3nWXafMXv5ooGVjM6zmi4TRB5X3DEMxxGYVBa2emG5ktJh3apoXp1cAY0ctWQ8/Hr/dC42oJeHTEAA9PO8DTH96QCmLZCAec4aPUMP1fOhWPq9tItad9Tawn5Z9tj2PZH2VB1tevFFVOpIG9+z1TLEg7JjBc663WetRJoM+sL8aa7E/xWdVFY2vlYw5fCTqMFTZowOKGvTGOsjig/4m6IzgqPc0Gru6d1sDq6mbQvkY+ylGHHxB0/3LKWhLMcO3Bp8sG8F6vMtu8eoOZhWLIYrzj8T9E2Q8ynL42zsPclaQwzpjLQuC8rg7frvwHxlfw== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=fujitsu.com; dmarc=pass action=none header.from=fujitsu.com; dkim=pass header.d=fujitsu.com; arc=none Received: from TYAPR01MB6025.jpnprd01.prod.outlook.com (2603:1096:402:36::13) by TYAPR01MB5322.jpnprd01.prod.outlook.com (2603:1096:404:803c::16) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.4523.14; Wed, 15 Sep 2021 08:24:56 +0000 Received: from TYAPR01MB6025.jpnprd01.prod.outlook.com ([fe80::cde6:2645:63a1:51b]) by TYAPR01MB6025.jpnprd01.prod.outlook.com ([fe80::cde6:2645:63a1:51b%9]) with mapi id 15.20.4500.019; Wed, 15 Sep 2021 08:24:56 +0000 To: Wilco Dijkstra , "'Lucas A. M. Magalhaes'" , Noah Goldstein , "libc-alpha@sourceware.org" Subject: RE: [PATCH v3 2/5] benchtests: Add memset zero fill benchtest Thread-Topic: [PATCH v3 2/5] benchtests: Add memset zero fill benchtest Thread-Index: AQHXic6jy6USnJyx5kO37MI1gLA1squd9IkAgANfZaCAAOkzAIAArxWggADifACAAMeSUA== Date: Wed, 15 Sep 2021 08:24:56 +0000 Message-ID: References: <20210805074733.433430-1-naohirot@fujitsu.com> <20210805075053.433538-1-naohirot@fujitsu.com> <163130642274.404689.6991051609396665932@localhost.localdomain> <163154191414.705584.12050866556951422556@localhost.localdomain> In-Reply-To: Accept-Language: en-001, ja-JP, en-US Content-Language: aa X-MS-Has-Attach: X-MS-TNEF-Correlator: msip_labels: MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_Enabled=True; MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_SiteId=a19f121d-81e1-4858-a9d8-736e267fd4c7; MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_SetDate=2021-09-15T08:24:55.298Z; MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_Name=FUJITSU-RESTRICTED; MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_ContentBits=0; MSIP_Label_a7295cc1-d279-42ac-ab4d-3b0f4fece050_Method=Standard; x-ms-publictraffictype: Email x-ms-office365-filtering-correlation-id: 8be05f47-1ebd-4f81-5fff-08d978224cd1 x-ms-traffictypediagnostic: TYAPR01MB5322: x-ms-exchange-transport-forked: True x-microsoft-antispam-prvs: x-ms-oob-tlc-oobclassifiers: OLM:10000; x-ms-exchange-senderadcheck: 1 x-ms-exchange-antispam-relay: 0 x-microsoft-antispam: BCL:0; x-microsoft-antispam-message-info: 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 x-forefront-antispam-report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:TYAPR01MB6025.jpnprd01.prod.outlook.com; PTR:; CAT:NONE; SFS:(4636009)(396003)(346002)(366004)(136003)(376002)(39860400002)(86362001)(76116006)(478600001)(64756008)(71200400001)(66476007)(66556008)(316002)(66946007)(6506007)(122000001)(2906002)(38100700002)(52536014)(5660300002)(186003)(38070700005)(26005)(55016002)(8676002)(7696005)(85182001)(8936002)(33656002)(66446008)(110136005)(966005)(9686003); DIR:OUT; SFP:1101; x-ms-exchange-antispam-messagedata-chunkcount: 1 x-ms-exchange-antispam-messagedata-0: =?iso-2022-jp?B?aFdpMzg5clhHU2ZGUTlveXVmRW55OVQ3TkZHSkVPYmZrL21QSFcxYVpO?= =?iso-2022-jp?B?S2drSzByMGRhNnpEYkRWRXVYeDJCTmhKbUVZdmlQUFpqakd3bWlDVUZD?= =?iso-2022-jp?B?ZklWeVM0NkZ6MmRuQlJDNk81eG5NRHcydG9NWlFSSEh3R0NyMG9XT1Nh?= =?iso-2022-jp?B?U1FoWUR1ZW92a2xSVkg0QXJqTWY3eEVEcndaL0t4amZ4Q1diUFhMa0xv?= =?iso-2022-jp?B?czR2Z0MwWTlSRUZVK2lmM1lOZ2pwUThqM0REaFo0czhuNHU1R21RZm1R?= =?iso-2022-jp?B?MSt4OEtNK2RGTWphRDBGSUhKWkZoQzdteW1LZlhuTWtNclZGM01GT0ZG?= =?iso-2022-jp?B?VFBxbW1TQVdoMnQwaXk4eFBIaTR4VUI5OHRHOVBLRkl3UjgyVU84NTlO?= =?iso-2022-jp?B?NjVpdmpZbGxNcGh5YkxmMm42MzB5Z25PamZKSTlwaFp0Y1pIL1YzbUZ5?= =?iso-2022-jp?B?OVMyRlVvemZWckMvVVFoS0xVYjJlZjExQnNVbTF3YysrTUppR2NVWjF4?= =?iso-2022-jp?B?bTh4cExnY1J1R1Z6ZzBPUUVoSFRuZ2tVMlR2ZmYzbm9RQlRSVlBGd3NF?= =?iso-2022-jp?B?ZUZvb2FtTlRqZSs0NWw1NUJmblRMVXdBMzF4cFdBQ0tJWWJudHY0ZnVv?= =?iso-2022-jp?B?SSttYkZFb2NPRHZHZVZzU1VxREJLaGM2Yzl4SGREck1FSE9XZ2VyMmJ2?= =?iso-2022-jp?B?eXJJbXZIR016U1FRM1NKYnhtVk0vMzZPRi9HbFpZYlVLNys3c3VJNlBE?= =?iso-2022-jp?B?TmRYQWZjS3pDcHNrQkwrREd5cW14aW5KVGlzbVMwR2tSMDhZTDRzOC9u?= =?iso-2022-jp?B?WEFNbkYzai9KdXJRQmNHbkkxQXpSdHZXS1AvaXdpUFZoZTRiSFdGSFRj?= =?iso-2022-jp?B?Z1hONlpCdGVpeVlnR2I4RldDckNtaHZpQ2kwSlBScUR5R2czQkJGNVI2?= =?iso-2022-jp?B?cGdJUnpvbmRCZTlWbHZVeG1wT2VFYUw0a3VhYnh6L0prT2pkVW9hTEJW?= =?iso-2022-jp?B?OUFJam50aGl2Z3ZuMjlRUVVVeUtZcFNRV3FOVVZlVVRGK3hFdUQrdFlh?= =?iso-2022-jp?B?T0RBdCtqWFdiaDA0dmNiaFlnZGxnVVBKVnZNRkdpQTRMTXlIZnVTTUdm?= =?iso-2022-jp?B?LzR0MlA4Nml1STM3akFtTkVVcXZaMHNkN0RrUFVvL2phR0IxYjQvVStK?= =?iso-2022-jp?B?Sk5EZGhSc3BSanMyRFZFQTYwYVNoY1lJRmc3M0FsejZablN1NWhQR3FP?= =?iso-2022-jp?B?UWVuRm4xZmlMRDFwT0pUQ1NnNlcvZmtQMFZjYnRhaEZxUFZ5ZkV1QTdW?= =?iso-2022-jp?B?UkwydzZnMUJoTXVGeVU4UDNSR1JkaHVPMkNQbFQydWZWTXcwSVBFRlNB?= =?iso-2022-jp?B?UGQxOU05UDYzNEk4QlRBSzk3WnR6TUhtNmVmMzBKMzFoSXFtc1o5dDR5?= =?iso-2022-jp?B?cUdHZms1bFIyaU5BOTluaHBqckFPVFpVTkx3OHlydVVXRUNDMGIvRm14?= =?iso-2022-jp?B?TDJ4aGU2dS8rellOdk9FaXZHc2ZzZC9OSitnK3l0UVYyc2huRkdKVmdy?= =?iso-2022-jp?B?aVhUbTAweXRmVStuWGN5MGUwMG55bmVvRWRrZFYrV3NscHBPV2NCeWZP?= =?iso-2022-jp?B?YTFvMzAvNlp5aUs2ZklyV2wwaFFQd0JjY1NPQ2duQ3dGNEJJRDRlZVBV?= =?iso-2022-jp?B?MzA4Q1ErTTJXZEZNTndRRm9WZDhDQ3JMaVM1NWNmMGlXcWxQTi9rQTQ3?= =?iso-2022-jp?B?SkFrbWtMRnV4RTFDbzNsSDBaWUVCVm5LV0RlNWZuMHR0MDNZTFM3TENN?= =?iso-2022-jp?B?NGJhNzhwWkJrWWpOWG9PTWJTRlA1NzRabzVwUFppN2E4Nm5tVHIvR1kw?= =?iso-2022-jp?B?cXh6d3FPdG1RUWFBNXozV2dNSEtVPQ==?= Content-Type: text/plain; charset="iso-2022-jp" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: fujitsu.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-AuthSource: TYAPR01MB6025.jpnprd01.prod.outlook.com X-MS-Exchange-CrossTenant-Network-Message-Id: 8be05f47-1ebd-4f81-5fff-08d978224cd1 X-MS-Exchange-CrossTenant-originalarrivaltime: 15 Sep 2021 08:24:56.1492 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: a19f121d-81e1-4858-a9d8-736e267fd4c7 X-MS-Exchange-CrossTenant-mailboxtype: HOSTED X-MS-Exchange-CrossTenant-userprincipalname: MC+foR7XYBKbkIRZGp/QNPzOHDclRZgdWsRFU/UqHUT+QxaEVSVi/oH9x8JCtz+Xupws0C9nL9/wiM8ZXYeVBQ== X-MS-Exchange-Transport-CrossTenantHeadersStamped: TYAPR01MB5322 X-BeenThere: libc-alpha@sourceware.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Libc-alpha mailing list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , From: naohirot--- via Libc-alpha Reply-To: "naohirot@fujitsu.com" Errors-To: libc-alpha-bounces+e=80x24.org@sourceware.org Sender: "Libc-alpha" Hi Wilco,=0A= =0A= Thank you for the comment.=0A= I understood your concerns about the start size and the end size.=0A= =0A= > From: Wilco Dijkstra =0A= > Sent: Tuesday, September 14, 2021 11:03 PM=0A= >=0A= > I had a quick go at running the new benchmark. The main problem is that i= t doesn't=0A= > give repeatable results - there are huge variations from run to run of ab= out 50% for=0A= > the smaller sizes. This is a fundamental problem due to the timing loop, = and the only=0A= > way to reduce it is to increase the time taken by memset, ie. start at a = much larger=0A= > size (say at 16KB).=0A= =0A= In terms of the start size, 256B is chosen because __memset_generic=0A= (sysdeps/aarch64/memset.S) calls DC ZVA for zero fill from 256B, which=0A= code you committed [1].=0A= And I reported an interesting insight in the mail [2] that DC ZVA is=0A= slower than store instruction from 256B to 16KB on A64FX [3].=0A= So it seems valuable to measure the range from 256B to 16KB to see=0A= each CPU's behavior.=0A= What do you think?=0A= =0A= [1] https://sourceware.org/git/?p=3Dglibc.git&h=3Da8c5a2a9521e105da6e96eaf4= 029b8e4d595e4f5=0A= [2] https://sourceware.org/pipermail/libc-alpha/2021-August/129805.html=0A= [3] https://drive.google.com/file/d/1fonjDDlF4LPLfZY9-z22DGn-yaSpGN4g/view= =0A= =0A= > It also takes a long time to run - generally it's best to ensure a benchm= ark takes less=0A= > than 10 seconds on a typical modern system (remember there will be many t= hat are=0A= > slower!). It should be feasible to reduce the iteration count for large s= izes, but you=0A= > could go up to 16MB rather than 64MB.=0A= =0A= OK, I'll change the end size to 16MB.=0A= =0A= Thanks.=0A= Naohiro=0A=