From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 93077 invoked by alias); 27 May 2017 12:55:34 -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 93014 invoked by uid 89); 27 May 2017 12:55:32 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.9 required=5.0 tests=BAYES_00,RCVD_IN_DNSWL_NONE,SPF_HELO_PASS,SPF_PASS autolearn=ham version=3.3.2 spammy=beats, beat, Hx-exchange-antispam-report-cfa-test:100000701073, Hx-exchange-antispam-report-cfa-test:100000800073 X-HELO: EUR03-AM5-obe.outbound.protection.outlook.com From: Wilco Dijkstra To: "munroesj@linux.vnet.ibm.com" , "adhemerval.zanella@linaro.org" CC: "libc-alpha@sourceware.org" , nd Subject: Re: [PATCH] powerpc: Add a POWER8-optimized version of powf() Date: Sat, 27 May 2017 12:55:00 -0000 Message-ID: authentication-results: sourceware.org; dkim=none (message not signed) header.d=none;sourceware.org; dmarc=none action=none header.from=arm.com; x-ms-publictraffictype: Email x-microsoft-exchange-diagnostics: 1;AM5PR0802MB2610;7:4S0DjotY0Xhv/PX2ZFSkykm54S+5VWT9nWDWMv43ZKvlYed3cKldcXKISl+FQyQ6+r3YZYAXsrmnJCGbcwGJP7sAmfgl1tkIM5INY2qGpO8z2DezsL4jzUrDjEgYK8Pe48PYEodFleSaerXlpuMWkTiKUTjWHJUz8onSHc7IossCvoU4KqkXXFKWSXgTODgJrIeO5EUUzH6IPykvXQz670uqXhTopPEoNhUmKR5Q4k/3yfzmX8igvOLg5j0gMXnM5NykF0YQ5tt2aHmd8qlWyT14kJFIDJTAd5K+2JkMKgqkLE4CylCKbSSceHUlbH6AU82NWjyChYf0bN8gtNwYoQ== x-ms-traffictypediagnostic: AM5PR0802MB2610: x-ms-office365-filtering-correlation-id: 417bdd53-8f07-40ab-9e9d-08d4a4ffa7e0 x-ms-office365-filtering-ht: Tenant x-microsoft-antispam: UriScan:;BCL:0;PCL:0;RULEID:(22001)(2017030254075)(48565401081)(201703131423075)(201703031133081);SRVR:AM5PR0802MB2610; nodisclaimer: True x-microsoft-antispam-prvs: x-exchange-antispam-report-test: UriScan:; x-exchange-antispam-report-cfa-test: BCL:0;PCL:0;RULEID:(100000700073)(100105000095)(100000701073)(100105300095)(100000702073)(100105100095)(6040450)(601004)(2401047)(5005006)(8121501046)(93006095)(93001095)(3002001)(10201501046)(100000703073)(100105400095)(6055026)(6041248)(20161123562025)(20161123558100)(20161123555025)(201703131423075)(201702281528075)(201703061421075)(201703061406153)(20161123564025)(20161123560025)(6072148)(100000704073)(100105200095)(100000705073)(100105500095);SRVR:AM5PR0802MB2610;BCL:0;PCL:0;RULEID:(100000800073)(100110000095)(100000801073)(100110300095)(100000802073)(100110100095)(100000803073)(100110400095)(100000804073)(100110200095)(100000805073)(100110500095);SRVR:AM5PR0802MB2610; x-forefront-prvs: 0320B28BE1 x-forefront-antispam-report: SFV:NSPM;SFS:(10009020)(6009001)(39400400002)(39860400002)(39850400002)(39840400002)(39450400003)(39410400002)(377424004)(24454002)(25786009)(6506006)(6436002)(38730400002)(5250100002)(74316002)(72206003)(3280700002)(55016002)(305945005)(478600001)(99286003)(53936002)(8676002)(7696004)(54906002)(2501003)(229853002)(9686003)(14454004)(3660700001)(86362001)(4326008)(8936002)(6116002)(81166006)(102836003)(189998001)(2906002)(54356999)(50986999)(2900100001)(33656002)(7736002)(6246003)(5660300001);DIR:OUT;SFP:1101;SCL:1;SRVR:AM5PR0802MB2610;H:AM5PR0802MB2610.eurprd08.prod.outlook.com;FPR:;SPF:None;MLV:sfv;LANG:en; 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-originalarrivaltime: 27 May 2017 12:55:30.4495 (UTC) X-MS-Exchange-CrossTenant-fromentityheader: Hosted X-MS-Exchange-CrossTenant-id: f34e5979-57d9-4aaa-ad4d-b122a662184d X-MS-Exchange-Transport-CrossTenantHeadersStamped: AM5PR0802MB2610 X-SW-Source: 2017-05/txt/msg00820.txt.bz2 Steven Munroe wrote: > On Fri, 2017-05-26 at 16:55 -0300, Adhemerval Zanella wrote: > > > > This changes seems to be arch independent and I would like to avoid add= ing > > even more arch specific. Is there any reason why this can't be used as > > the default implementation? Do you have number on different architectu= re > > for it?=20 > >=20 > If other platform maintainer what to try this implementation and report > that would be OK.=20 > > But I don't this it is correct or fair to ask Paul to prove a negative. > These quests tend to be very labor intensive and usually don't work out > (as really common) in the end. I disagree. We've seen time and time again that well-written generic code b= eats target specific code. So I would suggest to focus on improving the algorithms in g= eneric code rather than do target specific hacks that don't turn out to be useful in th= e long run. This will not only result in more efficient code, but it is also far cheape= r in development time as it only needs to be done once and can be shared across all targets. For this function I can't see why you'd ever want an ifunc unless there are= cases where=20 it doesn't beat the default powf implementation (presumably due to using 2 = double=20 precision divisions?). As it happens Szabolcs wrote a prototype powf that i= s not only more accurate but also 4x faster, all using generic code. With these gains,= target specific math functions will be obsolete... Wilco