From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 84841 invoked by alias); 12 Mar 2018 17:31:23 -0000 Mailing-List: contact libc-alpha-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: libc-alpha-owner@sourceware.org Received: (qmail 84827 invoked by uid 89); 12 Mar 2018 17:31:22 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-2.8 required=5.0 tests=AWL,BAYES_00,RCVD_IN_DNSWL_NONE,SPF_HELO_PASS,SPF_PASS autolearn=ham version=3.3.2 spammy= X-HELO: EUR01-VE1-obe.outbound.protection.outlook.com From: Wilco Dijkstra To: Siddhesh Poyarekar , "libc-alpha@sourceware.org" CC: nd Subject: Re: [PATCH 6/6] Remove slow paths from sin/cos Date: Mon, 12 Mar 2018 17:31:00 -0000 Message-ID: References: ,<37a3d699-e7aa-a411-f9bf-54aa1491a154@gotplt.org> In-Reply-To: <37a3d699-e7aa-a411-f9bf-54aa1491a154@gotplt.org> authentication-results: spf=none (sender IP is ) smtp.mailfrom=Wilco.Dijkstra@arm.com; x-ms-publictraffictype: Email x-microsoft-exchange-diagnostics: 1;DB6PR0801MB2008;7:aOEWYPcsT96NVs5XMQEnPfY4PHGgcNLtGcJmIzWrM147zqZ2X/Bukxw5166V6hrb+YMIFt3g6ByMv7lHPte7+8i1wVixIKBnmDAomigJzJMzeXArZTOZ/+Uj8oJoc1RrKtxK5hGqR05U9ITmWAhnZS0SMV4Z38w+7fXyvwGiN/Ldqw7NnVZJgwJZCPJ2qsrXyqdP7rzod+oJICrKxGXNGcSvQ+zXlrdaoDCKOOpfB7byuci6/8SmK/fpoxp/vnE2 x-ms-exchange-antispam-srfa-diagnostics: SSOS; x-ms-office365-filtering-ht: Tenant x-ms-office365-filtering-correlation-id: 58622db1-6cc0-4151-6aa1-08d5883f1069 x-microsoft-antispam: UriScan:;BCL:0;PCL:0;RULEID:(7020095)(4652020)(48565401081)(5600026)(4604075)(3008032)(2017052603328)(7153060)(7193020);SRVR:DB6PR0801MB2008; x-ms-traffictypediagnostic: DB6PR0801MB2008: nodisclaimer: True x-microsoft-antispam-prvs: x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:(8211001083)(6040522)(2401047)(8121501046)(5005006)(3002001)(93006095)(93001095)(10201501046)(3231220)(944501244)(52105095)(6055026)(6041310)(20161123564045)(201703131423095)(201702281528075)(20161123555045)(201703061421075)(201703061406153)(20161123562045)(20161123560045)(20161123558120)(6072148)(201708071742011);SRVR:DB6PR0801MB2008;BCL:0;PCL:0;RULEID:;SRVR:DB6PR0801MB2008; x-forefront-prvs: 06098A2863 x-forefront-antispam-report: SFV:NSPM;SFS:(10009020)(376002)(396003)(39380400002)(366004)(346002)(39860400002)(199004)(189003)(81156014)(305945005)(97736004)(106356001)(2906002)(105586002)(3660700001)(6506007)(3846002)(14454004)(6116002)(5660300001)(74316002)(478600001)(25786009)(7736002)(72206003)(86362001)(4326008)(8676002)(8936002)(81166006)(6246003)(2501003)(55016002)(9686003)(2950100002)(6436002)(53936002)(33656002)(5250100002)(7696005)(26005)(229853002)(68736007)(316002)(3280700002)(66066001)(99286004)(102836004)(76176011)(2900100001)(110136005);DIR:OUT;SFP:1101;SCL:1;SRVR:DB6PR0801MB2008;H:DB6PR0801MB2053.eurprd08.prod.outlook.com;FPR:;SPF:None;PTR:InfoNoRecords;A:1;MX:1;LANG:en; received-spf: None (protection.outlook.com: arm.com does not designate permitted sender hosts) x-microsoft-antispam-message-info: EJ9kn5KmzUcM6U1UsNAe27jeIvDaazH6v+8RjcTLiDt2R/yirN4883io+4rA7W0D2kKq9MUl2UaDVpBUeA0oPRUENPLEHWXdFAMFZQK8hOaiPwTdJbMr1ykQVs6DKgSWXdyJ+9GQ1sykmTcDKMkhEgY4FCBNzIhEPSeFEIlnG06YVcTmtPRfi1SMq2xnPH0IKcR3N0z5ba/LGMsKqFLhnC5wMscw80r47Dl54p83GH3SSpoPqnDtvisvwPCG41klqvQxcXiagCybDagMGz8dR5sllWv7EUhdAh5lRj2ebhSTDwQRoQlNM9q8PypOdy+hOs81fibZjFn0hKpIMcfZ7g== spamdiagnosticoutput: 1:99 spamdiagnosticmetadata: NSPM Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-Network-Message-Id: 58622db1-6cc0-4151-6aa1-08d5883f1069 X-MS-Exchange-CrossTenant-originalarrivaltime: 12 Mar 2018 17:31:18.1360 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-Transport-CrossTenantHeadersStamped: DB6PR0801MB2008 X-SW-Source: 2018-03/txt/msg00292.txt.bz2 Siddhesh Poyarekar wrote: > The intention of keeping the inlines was to avoid duplicating code > across files.=A0 With this change one now must remember to make changes in > both files at all times, increasing the chances of an error.=A0 Do you see > any gain from duplicating code? I had lots of issues due to parts of functions being included in sincos.c, = so I had to disable sincos during development. The new version is much easier to mainta= in. This patch on its own gives a 16-20% speedup between 0 and 8*PI (this speed= up continues up to 2^27). The overall speedup of sincos is 48% over this range= , and between 0 and PI it is 66% faster. So I'd say specializing the small cases = in sincos gives a significant gain. Wilco