From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 114421 invoked by alias); 19 Apr 2018 09:14:53 -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 114051 invoked by uid 89); 19 Apr 2018 09:14:17 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.9 required=5.0 tests=AWL,BAYES_00,KAM_NUMSUBJECT,RCVD_IN_DNSWL_NONE,SPF_HELO_PASS,SPF_PASS autolearn=no version=3.3.2 spammy=approximately, sk:szabolc, Szabolcs, U*szabolcs.nagy X-HELO: EUR01-HE1-obe.outbound.protection.outlook.com Authentication-Results: arm.com; dkim=none (message not signed) header.d=none;arm.com; dmarc=none action=none header.from=arm.com; Cc: nd@arm.com Subject: Re: [PATCH v2] Improves __ieee754_exp(x) performance by 18-37% when |x| < 1.0397 To: Patrick McGehearty , libc-alpha@sourceware.org References: <1523048295-90391-1-git-send-email-patrick.mcgehearty@oracle.com> From: Szabolcs Nagy Message-ID: Date: Thu, 19 Apr 2018 09:14:00 -0000 User-Agent: Mozilla/5.0 (X11; Linux aarch64; rv:52.0) Gecko/20100101 Thunderbird/52.7.0 MIME-Version: 1.0 In-Reply-To: <1523048295-90391-1-git-send-email-patrick.mcgehearty@oracle.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: 7bit X-ClientProxiedBy: VI1PR0701CA0062.eurprd07.prod.outlook.com (2603:10a6:800:5f::24) To VI1PR08MB3293.eurprd08.prod.outlook.com (2603:10a6:803:3e::10) X-MS-PublicTrafficType: Email X-MS-Office365-Filtering-HT: Tenant X-Microsoft-Antispam: UriScan:;BCL:0;PCL:0;RULEID:(7020095)(4652020)(5600026)(48565401081)(2017052603328)(7153060)(7193020);SRVR:VI1PR08MB3293; X-Microsoft-Exchange-Diagnostics: 1;VI1PR08MB3293;3:gaj3raqSEj7SGVlm+Qbe82kyNIjXKvK+ZCLfwZhY/KzJw4eqBY2bALMb998CzYcwJhtNkmWDLY1YoNWO4TVH9QsSW7Cg3XWRzqi3RwyZ9ZgZX5FZbQFzTCxGR9lm3n5DW1yhXUT2s1ktF3cBDKETvbg6gmm+OsGX2EANyVFK4Ch3a2eWuEqFADQG68tYcIsqkbII1zYpU3RvmQunX4+1Dso0MkV4qQXpgC4vKeMsO6TjsQEquEO4U66qQ60fy0+I;25:zpYk7mxJIiGiKX+PnYZqewWncfwOy7CKZiXF76UaR/PwVqj9ECOzHMcICICsawdDBKk+vef+u8VFYTx8U4QNxbK5pbF+sIfX0uuVeJaR8krc526/5sbVj8X9qA0X/H3o5a82tVnfwsjqCobOT4sUmQz7Lrx0gZrG6ykOCJnICLL6gjUUjtfCZ1jGW2IHQ1l8dhQF8YY32RTMLINl1pi9M+lkd/z61uGer1zh0AsVilcEihqJ+LHP9TU7lYdwY8No9Dq/gJKIoMvAM2rOtxM4NoykZH9SDGs9+6iPGsGuZ6QQEoHd1ac4UzOd8c0ZA+f6Owq4fO+td6SLxulEYQEIhw==;31:FcQ87e3N2Yg2MxeM6snpN+z+EwwrYJ+yAMsqUBVTW9eZZKCny2451jP48YVwLg/jGFvbp1XnwNOWzdW4shPrGkGApeGJ9tgihUmd7t6tGUeH09XOAdUa7YqNrYi6bUanG2HK1qMANNonBRFXzaO7TpfozV2QH2ROtFYAfTrCgLFOqiTUYRnYN70fGbWL8IZV/H+6MCOL3gKWgeHkI9XBvl2oyD6QUg7Nx2RMu/WhH3U= X-MS-TrafficTypeDiagnostic: VI1PR08MB3293: NoDisclaimer: True X-Microsoft-Exchange-Diagnostics: 1;VI1PR08MB3293;20:TcTkurFo4zStnaG86ji+resOpnHHDL+vVGTM6eq9rRrYD4OpOo/SAvavJINKa9itofrejIxSmdfarXPvM7cajPwDCjyHiajOv/tJqZdjoPWqJ/A0fMCR4MRDgVXfAT9uyCzophwo904aJ1Wzsmy+JW2VAhcsuOp/5EcvRwrwGrhVfCYSZdh95sGe8uDXX2GG4z11Yw1otrQ/1F9DYqEoKS7RYHnbEgPBtIVp1Is+got4I+RK4tS5TfZq99Bv+2Yz;4:Ule21sh2q2ZVkasKPtdGB5MUIjypJGCXZiPI6qFa9xzDt51i3uAHuRqFKVWhP7/7A0qfJQ5pcz2lw7WrC8GhcrBuc3eUN5Wq2Dcu6xsj2j6eaUx4GYQP+i/YT7kcYqXWHRXQrsOaqnYfRNvr+G1zhqb0B2wDcJHWuVX8Sw6ZNiYi3O5MQjv7E0b08DK/xtvUyClGunX50fJuTq45yaIMZJMccn8seSn5LkneSiKDxoRnZRsVmLZbkQ0SxpKzS+K91LmYNOajdLHhki0WkHr//Fyaup5JIXgZQEQuqvFYEj+zlJ0k+vGlaQmLQffSM64Suwh1+fY7MUxcj67E8vImdUupRJ+AotM7EZ8ji7210Sg= X-Microsoft-Antispam-PRVS: X-Exchange-Antispam-Report-Test: UriScan:(180628864354917)(146099531331640); X-Exchange-Antispam-Report-CFA-Test: BCL:0;PCL:0;RULEID:(8211001083)(6040522)(2401047)(8121501046)(5005006)(3002001)(10201501046)(3231232)(944501382)(52105095)(93006095)(93001095)(6055026)(6041310)(20161123558120)(20161123560045)(20161123562045)(20161123564045)(201703131423095)(201703011903075)(201702281528075)(20161123555045)(201703061421075)(6072148)(201708071742011);SRVR:VI1PR08MB3293;BCL:0;PCL:0;RULEID:;SRVR:VI1PR08MB3293; X-Forefront-PRVS: 0647963F84 X-Forefront-Antispam-Report: SFV:NSPM;SFS:(10009020)(6049001)(7966004)(346002)(396003)(366004)(39860400002)(39380400002)(376002)(377424004)(54534003)(16576012)(58126008)(26005)(77096007)(230700001)(6666003)(6116002)(229853002)(3846002)(6486002)(2906002)(65956001)(16526019)(36756003)(956004)(11346002)(446003)(76176011)(2616005)(476003)(52116002)(44832011)(31686004)(52146003)(23676004)(50466002)(53546011)(47776003)(66066001)(65806001)(64126003)(67846002)(2486003)(386003)(5660300001)(72206003)(65826007)(8676002)(4326008)(7736002)(25786009)(81166006)(316002)(508600001)(8936002)(305945005)(6246003)(86362001)(53936002)(31696002);DIR:OUT;SFP:1101;SCL:1;SRVR:VI1PR08MB3293;H:[10.2.206.57];FPR:;SPF:None;LANG:en;MLV:nov;PTR:InfoNoRecords; X-Microsoft-Exchange-Diagnostics: =?utf-8?B?MTtWSTFQUjA4TUIzMjkzOzIzOmUxL1ovdmFIYTRVQ1ovcTIrcWtSK3RJS3Jr?= =?utf-8?B?RjdTc3lHcDRvNDZBRkYrbk9tTHZXU21wRmdJdmFSQm9YbEpVVFgrZHB5alNP?= =?utf-8?B?SG1tQUQ3MzVGTU1EdG1wa2ZmUE1sUzJBdEpGU1FaVDJMSXZ2M1M3em1YTHNY?= =?utf-8?B?dmV0TFBFem0vMjJsbXVzV0szV0M4VkNTdm5YaTRWMTFqSkZmQjROVEUxY29M?= =?utf-8?B?ZnpSKzBWYXdCYmJmRkU4QkRFK20ySzZvU00ycmszUis4ZlZ5VkNObVpUK0Nk?= =?utf-8?B?VFBodksyaEtzNzRFcFJJajZQSXV0VmtvQk9xRzlCUFZPRWl0dUdTd0ZMakZL?= =?utf-8?B?OFN0a2MvMVY2dXpmVC9peGFnZW5wSkdJaGd2K2VVejZUQ1NMWWhoMVRCc2lQ?= =?utf-8?B?ckJnNjBSSGZqSkc3UWkxckNGZ2tRTlpMcGE0UzFEMVphSTJGQzgrSXRuMUoy?= =?utf-8?B?akZudUdUTkxjMkF2bUZUTXozcFB1cnJqWmRrb0NLUW1yTkFsTmN4TW0vR2lT?= =?utf-8?B?T3RGd1V3eldRSU9Jb3lnRVFVUjB6NGtUYnBWMk9OTDhRUGNlclNiVVRiN3Fr?= =?utf-8?B?M0NEbVZxemRQUGE1d21SNlo3Q1Rock0xQjQ5ZndhcG5ISzFlMnN6WHg0MHJJ?= =?utf-8?B?QitmcGZkdlN5YmtQOHFVaFp3Slc5OXBDcWdwRVFydUdIdmdqdHVXRzNPSUJo?= =?utf-8?B?cUUzWHhtN3pGb01UQjFwU0JLNGtuUmpCQ3QwRzRJbjBJbVhFWHJCOGNlQkxu?= =?utf-8?B?cmdHdGt6Q3VpampRcUIzNlJ4N212am1hbktFYTFyRG9QR252enNnQU1VT3Np?= =?utf-8?B?dnNxUkV0WmQxMkVYWEkvLys0blZlRWJnclBBbjA5TytvRitMZGc5TkFFQXNj?= =?utf-8?B?QlBTWTVsSXdUTG56SWlndlB3RHJIRnJxUkNEUXpHT0NYMlFoTWdpUlo0ODQ4?= =?utf-8?B?WVFjVDFUZ1F4RzBiSmwxNDhObWtDZVNZSDBiWUFHaHVoWm1IdFpSNWQ1a01I?= =?utf-8?B?VW1JVzlONHVHcFJHc0NIZWxsbEE1MnAxTEFUZW1JdXdqQUU2Rk56bGpFVm1j?= =?utf-8?B?dll4eUV2OGVvSTUyRmU3VkgvQldWZVlYWVZlbTVvREFQTVJOOGNJa3hvcjM2?= =?utf-8?B?Y0YzNTkwUEJwYUFqb0tVUUdUR1NIN0pPY1N2dGQxYVEyTkJ2STBjQ2pBaEJs?= =?utf-8?B?OVR6dm91dzlGK2lBNkNnaUdDT2JxbXY3UDFYTUl2WXFpWkg3RENXenJWVWlK?= =?utf-8?B?dXlWclRWNzdpM1d3cTNXVGVYd09lZmY3bzBXUFRaUlBtdlJVUytJUXhndGtp?= =?utf-8?B?ZGE1NW0wQ2FpYlJNTCswRWdWR05tRzg1L3laQkRkUG0vTkFKUEM5L2F1V0xE?= =?utf-8?B?SkJiWFNGMkdKV3V0YzQ1ZGkwZzFFN3R5TWtoNnVYK0ZOT0JFakhZN0hPSjBG?= =?utf-8?B?b21xWWtHV0Z1cFg3RGU4UlVNRjd5S2RpM0gvVStnQksrZnVLay90dnRMNlpn?= =?utf-8?B?bnMybVJBY0VoUW8xZkJ5aGJ3dDYyM3BZVHczOWVvak9teElEaWJOYVZ0dmJj?= =?utf-8?B?YXpqV3I5TldqZ25OQ2oxT3Z1TEs3SCtUOUtUUTlsTGo4bU9TZHlDVjZjN3NK?= =?utf-8?B?UnIzekV4UUJUa1Z0dnFWUGMxb3ZSckQyY0dRZGpOQ1lRYlFaM3BybUFXVUdC?= =?utf-8?B?cGo1YnFlT1E4bk0xS1RxS2pjd3V1ZzZLK3grdWkveUNLVzRFcko4OEZlRjVv?= =?utf-8?B?MllMbVdjRW4vL2VLVWFYYWcvNDJkQjhpbWRMcUI4cDBtakhvcEhEdjJRQU9X?= =?utf-8?B?czBPMC9WUmRySkF5UGdMNVd1bkdEMklmMk12dkxqWVlZQ0E9PQ==?= X-Microsoft-Antispam-Message-Info: sfTkHgW08S6roXiueaZGo9aBBIZH41sgVnne8139F50so49wW33WVQdXBlJcAqqcpbzaWZ9GLc0SgBb3K56D9MeeyC987omW8Wjo9ClT8MZBabmAtvYXNyeCgMkFODTmqmxcgS9oOhU7X2Nn0kCCrIbVH82FOhn+Bp6YAYZjtj5jqvLr/IlqWlIfkPf4OgWH X-Microsoft-Exchange-Diagnostics: 1;VI1PR08MB3293;6:wTZsRyPyvwOSNM02rHznuxj49DxDug/jrb0wC8WKjkqgVhGnopMDEzrkObHp3+EgCK56TiNOE2gLeHTdC79SaPnnnNtrYSZNXKzkLu4HyPkOCV2i4jOujHk32en8CZArAmePNMafFSmcXnr0mPecsFjdpJPE2RtkiouXOP236iKDYAvI4TmuCRMSULF54qF4CK3HSkIKvctk8JxZp+TgcIIXqgyBt1kTxa3GErGADv8TEf9mrFJIeqMfk9+ZZi22KfGS9yzvEQC4vT40A+A5p0QIrKtj3Ue/F9A9B5GQnCeok3OYb2iavCxkOBxXH28GEcVS5UZ1a3RKp4KuNB+IV21sCc4hmHQMCgmwf4UJ9ttP+mjWgqfJ3JpvNE3PtaO1ombidFsI9v+iRSYzSuSk8QjocjV9Juxxm8MDMYwMKfKBtn3WKP1rRAxOhbYf9QFSby981OrFcnX4K09FpvqEJA==;5:q5bwW9Pr4EHRFcJIW5SO8x5AGc/dGweRzGPAv9epubpUEwbeDdVOitzxZmQ1VbDds7Um7vTOXpBiokME9JByDwoXkbdzyOLEAkQzQTBlkP60NVycMU5OicsoIZuNmftC6OCIVkWULqUHSr0oAft0vOFAEhwcP/KxTTMMx4/DiNw=;24:GUhpi866mKiNc1w0DPjdADr7Raxw6cffndzibK1J3ttMuD5jpzi6EVm3CF5NoHXX+V8Z3TmQ1GyHrHbrVe6gZ0aLP5R+shWYoSD+CDpFp0Y= SpamDiagnosticOutput: 1:99 SpamDiagnosticMetadata: NSPM X-Microsoft-Exchange-Diagnostics: 1;VI1PR08MB3293;7:BuiN9eAzwR7j1olM4EkaoyqBlxusTyEHcCPmDewm+JvlwkSs5ewMUUTKXwPubBjE2+MoIXca43HVizGdkiFwc4ULvWHBr0hVzb0csEEHrYrAwhdEbLITi3ZUhAgLD0iFh4fdYCZdW1i6yv/YXLtiQpoazbd0AgcDhdLbvXFyJmZmYbmDEznSi/wHYh3DTdMh6mRahJOyjwdQYPO3A+49nM9gyXKh5chvVp/eTLLbz/QBXbi1rs7rHsXCqHsSaaqA X-MS-Office365-Filtering-Correlation-Id: 0176a9d4-db06-4fd9-538b-08d5a5d5e9de X-OriginatorOrg: arm.com X-MS-Exchange-CrossTenant-OriginalArrivalTime: 19 Apr 2018 09:14:11.1196 (UTC) X-MS-Exchange-CrossTenant-Network-Message-Id: 0176a9d4-db06-4fd9-538b-08d5a5d5e9de X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-Transport-CrossTenantHeadersStamped: VI1PR08MB3293 X-SW-Source: 2018-04/txt/msg00391.txt.bz2 On 06/04/18 21:58, Patrick McGehearty wrote: > Adds a fast path to e_exp.c when |x| < 1.03972053527832. > When values are tested in isolation, reduction in execution > time is: aarch 30%, sparc 18%, x86 37%. > When comparing benchtests/bench.out which includes values > outside that range, the gains are: > aarch 8%, sparc 5%, x86 9%. > > make check is clean (no increase in ulp for any math test). > Testing 20M values for each rounding mode in that range shows > approximately one in 200 values is off by 1 ulp. No value tested > for exp(x) changed by 2 or more ulp. > > No observed change in performance or accuracy for x outside > fast path range. > > These changes will be active for all platforms that don't provide > their own exp() routines. They will also be active for ieee754 > versions of ccos, ccosh, cosh, csin, csinh, sinh, exp10, gamma, and > erf. > > New in this version: > Copyright year for eexp.tbl changed from 2017 to 2018. > Spurious white space diff e_exp.c removed. > > ChangeLog: > 2018-03-20 Patrick McGehearty > > * sysdeps/ieee754/dbl-64/e_exp.c: faster __ieee754_exp() > * sysdeps/ieee754/dbl-64/eexp.tbl: New file for e_exp.c looks ok to me. Reviewed-by: Szabolcs Nagy