From owner-sc22wg5@open-std.org Fri Nov 7 00:23:41 2008 Return-Path: X-Original-To: sc22wg5-dom7 Delivered-To: sc22wg5-dom7@www2.open-std.org Received: by www2.open-std.org (Postfix, from userid 521) id 76842CA5FE8; Fri, 7 Nov 2008 00:23:41 +0100 (CET) X-Original-To: sc22wg5@open-std.org Delivered-To: sc22wg5@open-std.org Received: from mail1.cray.com (mail1.cray.com [136.162.0.111]) by www2.open-std.org (Postfix) with ESMTP id 7850ACA343A for ; Fri, 7 Nov 2008 00:23:39 +0100 (CET) Received: from mh1750-1.us.cray.com (mh1750-1.us.cray.com [172.31.74.55]) by mail1.cray.com (8.13.6/8.13.3/gw-5323) with ESMTP id mA6NNSbW010891 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Thu, 6 Nov 2008 17:23:38 -0600 (CST) Received: from mh2650-1.us.cray.com (mh2650-1.us.cray.com [172.31.74.50]) by mh1750-1.us.cray.com (8.13.8/8.13.3/hub-5273) with ESMTP id mA6NNSja014020; Thu, 6 Nov 2008 17:23:28 -0600 Received: from mh-dhcp-172-31-16-226.us.cray.com (mh-dhcp-172-31-16-226.us.cray.com [172.31.16.226]) by mh2650-1.us.cray.com (8.13.8/8.13.3/spool-5907) with ESMTP id mA6NNQfc012357; Thu, 6 Nov 2008 17:23:27 -0600 Message-ID: <49137CD5.4010603@cray.com> Date: Thu, 06 Nov 2008 17:25:09 -0600 From: Bill Long Reply-To: longb@cray.com Organization: Cray Inc. User-Agent: Thunderbird 2.0.0.9 (Macintosh/20071031) MIME-Version: 1.0 Cc: sc22wg5 Subject: Re: (j3.2006) (SC22WG5.3623) [ukfortran] A comment on John Wallin's comments on Nick MacLaren's comments References: <20081105225653.DCEA7CA3428@www2.open-std.org> <20081105232803.42621CA3434@www2.open-std.org> In-Reply-To: <20081105232803.42621CA3434@www2.open-std.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Cray-VirusStatus: clean Sender: owner-sc22wg5@open-std.org Precedence: bulk N.M. Maclaren wrote: > John Wallin wrote: > > >> In short, coarrays would make my head hurt less. >> > > Most of the users I have dealt with have backed off shared-memory > paradigms when they found that they couldn't debug or tune them, and > gone back to MPI. The problem is that there are, and can be, no tools > to trap race conditions. > This is, of course, one of the main arguments in favor of coarrays. The programming model, is SPMD, as with MPI, which experience has shown to work, and to be the most popular. Shared-memory models, like OpenMP, do have their place, but have limitations. > >> I would suggest talking to the UPC forum about this. They have a lot >> of experience with this, and can address it directly. >> > > Not much, actually. There aren't many versions, and UPC isn't much > used by real scientists. Well, "real" scientists would not be using any variant of C. :) However, I think UPC will gain even more traction once it is formally standardized. User's want some assurance of language stability before they dive into a large coding project. Similarly for vendors providing compilers. Same argument applies for why standardization of coarrays is needed. > > > I am talking about programs that have no deadlocks in, but where they > are introduced by the implementation. > > > Deadlocks introduced by the implementation should be reported as bugs to the vendor. Cheers, Bill -- Bill Long longb@cray.com Fortran Technical Support & voice: 651-605-9024 Bioinformatics Software Development fax: 651-605-9142 Cray Inc., 1340 Mendota Heights Rd., Mendota Heights, MN, 55120