From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 28986 invoked by alias); 2 Jun 2017 16:28:00 -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 27687 invoked by uid 89); 2 Jun 2017 16:27:59 -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,RCVD_IN_DNSWL_NONE,SPF_PASS,URIBL_RED autolearn=ham version=3.3.2 spammy= X-HELO: relay1.mentorg.com Date: Fri, 02 Jun 2017 16:28:00 -0000 From: Joseph Myers To: Wilco Dijkstra CC: "munroesj@linux.vnet.ibm.com" , "adhemerval.zanella@linaro.org" , "pc@us.ibm.com" , "libc-alpha@sourceware.org" , nd Subject: Re: [PATCH] powerpc: Add a POWER8-optimized version of powf() In-Reply-To: Message-ID: References: ,<0f81b30e-b8c9-60e9-4fa3-3528ad21e0d7@us.ibm.com> User-Agent: Alpine 2.20 (DEB 67 2015-01-07) MIME-Version: 1.0 Content-Type: text/plain; charset="US-ASCII" X-ClientProxiedBy: svr-ies-mbx-01.mgc.mentorg.com (139.181.222.1) To SVR-ORW-MBX-06.mgc.mentorg.com (147.34.90.206) X-SW-Source: 2017-06/txt/msg00106.txt.bz2 On Fri, 2 Jun 2017, Wilco Dijkstra wrote: > >> As it happens Szabolcs wrote a prototype powf that is not only more > >> accurate but also 4x faster, all using generic code. With these > >> gains, target specific math functions will be obsolete... > > > > Is that forthcoming? > > Yes - after they are published under a less restrictive license. In > GLIBC we'll need to agree on how to deal with the wrappers and establish > a good place to add new math functions. It's fine to put float functions implemented using double internally in sysdeps/ieee754/flt-32; some already use double internally. For functions not using type-generic templates, the sysdeps/ieee754 structure seems reasonable to me (given the need to handle different long double formats), although code outside there may also assume that float is binary32 and double is binary64. -- Joseph S. Myers joseph@codesourcery.com