From owner-sc22wg5+sc22wg5-dom8=www.open-std.org@open-std.org Sat Mar 30 15:14:40 2013 Return-Path: X-Original-To: sc22wg5-dom8 Delivered-To: sc22wg5-dom8@www.open-std.org Received: by www.open-std.org (Postfix, from userid 521) id B08FE356DD0; Sat, 30 Mar 2013 15:14:40 +0100 (CET) Delivered-To: sc22wg5@open-std.org Received: from ppsw-51.csi.cam.ac.uk (ppsw-51.csi.cam.ac.uk [131.111.8.151]) by www.open-std.org (Postfix) with ESMTP id 56198356D8C for ; Sat, 30 Mar 2013 15:14:40 +0100 (CET) X-Cam-AntiVirus: no malware found X-Cam-SpamDetails: not scanned X-Cam-ScannerInfo: http://www.ucs.cam.ac.uk/email/scanner/ Received: from hermes-1.csi.cam.ac.uk ([131.111.8.51]:58298) by ppsw-51.csi.cam.ac.uk (smtp.hermes.cam.ac.uk [131.111.8.158]:25) with esmtpa (EXTERNAL:nmm1) id 1ULwYI-0006Gl-YD (Exim 4.72) (return-path ); Sat, 30 Mar 2013 14:14:38 +0000 Received: from prayer by hermes-1.csi.cam.ac.uk (hermes.cam.ac.uk) with local (PRAYER:nmm1) id 1ULwYI-0003UF-Hf (Exim 4.72) (return-path ); Sat, 30 Mar 2013 14:14:38 +0000 Received: from [87.115.144.83] by webmail.hermes.cam.ac.uk with HTTP (Prayer-1.3.5); 30 Mar 2013 14:14:38 +0000 Date: 30 Mar 2013 14:14:38 +0000 From: "N.M. Maclaren" To: "Bader, Reinhold" Cc: "longb@cray.com" , sc22wg5 Subject: Re: [ukfortran] (SC22WG5.4956) AW: (j3.2006) AW: WG5 ballot on first draft TS 18508, Additional Parallel Features in Fortran (Update) Message-ID: In-Reply-To: <20130330132208.D7468356DDA@www.open-std.org> References: <20130329104945.2C28A356BB3@www.open-std.org> <20130329232930.A368A356DC2@www.open-std.org> <20130330132208.D7468356DDA@www.open-std.org> X-Mailer: Prayer v1.3.5 Mime-Version: 1.0 Content-Type: text/plain; format=flowed; charset=ISO-8859-1 Sender: owner-sc22wg5@open-std.org Precedence: bulk On Mar 30 2013, Bader, Reinhold wrote: >> >> If we added this, it would be CO_PRODUCT since the local one is PRODUCT. >> The previous proposal had CO_PRODUCT. It was removed because the >> corresponding MPI_REDUCE for that operation almost never occurs in real >> codes. Is there any common usage of this operation? Also, is there >> hardware support in network hardware for a multiply reduction? > > According to Mellanox' FCA documentation, all commonly used numeric data > types (except complex) support MPI_Reduce and MPI_Allreduce; I would > assume that this includes the argument variants MPI_SUM and MPI_PRODUCT. Complex summation isn't exactly hard to build on top of real summation in the software interface :-) > I must however admit that a significant (if not the bulk) part of the FCA > optimization is concerned with topology awareness, so will also be > applicable to the general reduction facility. How much of that gets through the driver layer is less clear. When I last looked, OpenIB didn't support RDMA, which makes a lot of the fancy MPI one-sided and PGAS stuff irrelevant. Regards, Nick Maclaren.