From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) by sourceware.org (Postfix) with ESMTPS id 0CF123857C46 for ; Tue, 1 Dec 2020 14:24:51 +0000 (GMT) DMARC-Filter: OpenDMARC Filter v1.3.2 sourceware.org 0CF123857C46 Received: from pps.filterd (m0098399.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id 0B1E6gMF018812 for ; Tue, 1 Dec 2020 09:24:51 -0500 Received: from ppma03wdc.us.ibm.com (ba.79.3fa9.ip4.static.sl-reverse.com [169.63.121.186]) by mx0a-001b2d01.pphosted.com with ESMTP id 355he3vjqh-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT) for ; Tue, 01 Dec 2020 09:24:49 -0500 Received: from pps.filterd (ppma03wdc.us.ibm.com [127.0.0.1]) by ppma03wdc.us.ibm.com (8.16.0.42/8.16.0.42) with SMTP id 0B1ELMdU003626 for ; Tue, 1 Dec 2020 14:24:43 GMT Received: from b03cxnp08028.gho.boulder.ibm.com (b03cxnp08028.gho.boulder.ibm.com [9.17.130.20]) by ppma03wdc.us.ibm.com with ESMTP id 353e690pdq-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT) for ; Tue, 01 Dec 2020 14:24:42 +0000 Received: from b03ledav006.gho.boulder.ibm.com (b03ledav006.gho.boulder.ibm.com [9.17.130.237]) by b03cxnp08028.gho.boulder.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 0B1EOf8f10093226 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Tue, 1 Dec 2020 14:24:41 GMT Received: from b03ledav006.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 9E43FC6084; Tue, 1 Dec 2020 14:24:41 +0000 (GMT) Received: from b03ledav006.gho.boulder.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 3A5FDC6072; Tue, 1 Dec 2020 14:24:41 +0000 (GMT) Received: from [9.80.237.241] (unknown [9.80.237.241]) by b03ledav006.gho.boulder.ibm.com (Postfix) with ESMTP; Tue, 1 Dec 2020 14:24:40 +0000 (GMT) Subject: Re: [PATCHv5] powerpc64le: ifunc select *f128 routines in multiarch mode To: Raphael M Zinsly , libc-alpha@sourceware.org, Tulio Magno Quites Machado Filho References: <20201102152742.97585-1-murphyp@linux.ibm.com> <4ed32327-5395-dff2-1add-6b3b5b0fc721@linux.ibm.com> From: Paul E Murphy Message-ID: <93f8ecae-0697-ed82-6522-374a75961abd@linux.ibm.com> Date: Tue, 1 Dec 2020 08:24:40 -0600 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.4.0 MIME-Version: 1.0 In-Reply-To: <4ed32327-5395-dff2-1add-6b3b5b0fc721@linux.ibm.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 8bit X-TM-AS-GCONF: 00 X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.312, 18.0.737 definitions=2020-12-01_05:2020-11-30, 2020-12-01 signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 phishscore=0 impostorscore=0 lowpriorityscore=0 spamscore=0 priorityscore=1501 clxscore=1015 malwarescore=0 suspectscore=0 bulkscore=0 mlxscore=0 mlxlogscore=999 adultscore=0 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2009150000 definitions=main-2012010087 X-Spam-Status: No, score=-4.3 required=5.0 tests=BAYES_00, DKIM_SIGNED, DKIM_VALID, DKIM_VALID_EF, NICE_REPLY_A, RCVD_IN_DNSWL_NONE, RCVD_IN_MSPIKE_H2, SPF_HELO_NONE, SPF_PASS, TXREP autolearn=ham autolearn_force=no version=3.4.2 X-Spam-Checker-Version: SpamAssassin 3.4.2 (2018-09-13) on server2.sourceware.org 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: , X-List-Received-Date: Tue, 01 Dec 2020 14:24:53 -0000 On 11/30/20 11:00 AM, Raphael M Zinsly wrote: > On 02/11/2020 12:27, Paul E. Murphy via Libc-alpha wrote: >> Programatically generate simple wrappers for interesting libm *f128 >> objects.  Selected functions are transcendental functions or >> those with trivial compiler builtins.  This can result in a 2-3x >> speedup (e.g logf128 and expf128). >> >> A second set of implementation files are generated which include >> the first implementation encountered along the search path.  This >> usually works, except when a wrapper is overriden and makefile >> search order slightly diverges from include order.  Likewise, >> wrapper object files are created for each generated file.  These >> hold the ifunc selection routines which export ABI. >> >> Next, several shared headers are intercepted to control renaming of >> asm function redirects are used first, and sometimes macro renames >> if the former is impractical. >> >> Notably, if the request machine supports hardware IEEE128 (i.e POWER9 >> and newer) this ifunc machinery is disabled.  Likewise existing >> ifunc support for float128 is consolidated into this (e.g sqrtf128 >> and fmaf128). > > > LGTM, I tested on POWER8 and POWER9. > Pushed. Thank you all for the feedback.