From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.1.3 (2006-06-01) on yquem.inria.fr X-Spam-Level: X-Spam-Status: No, score=0.3 required=5.0 tests=AWL autolearn=disabled version=3.1.3 X-Original-To: caml-list@yquem.inria.fr Delivered-To: caml-list@yquem.inria.fr Received: from mail3-relais-sop.national.inria.fr (mail3-relais-sop.national.inria.fr [192.134.164.104]) by yquem.inria.fr (Postfix) with ESMTP id 4A7DEBBAF for ; Thu, 29 May 2008 15:06:10 +0200 (CEST) X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: Ai0IAKBGPkjB/BYfZGdsb2JhbACSHBgHAgQIEgOdCA X-IronPort-AV: E=Sophos;i="4.27,561,1204498800"; d="scan'208";a="13210483" Received: from smtp20.orange.fr ([193.252.22.31]) by mail3-smtp-sop.national.inria.fr with ESMTP; 29 May 2008 15:06:09 +0200 Received: from me-wanadoo.net (localhost [127.0.0.1]) by mwinf2019.orange.fr (SMTP Server) with ESMTP id 7A1B61C017D7 for ; Thu, 29 May 2008 14:02:46 +0200 (CEST) Received: from [192.168.0.50] (ARouen-156-1-100-250.w90-8.abo.wanadoo.fr [90.8.43.250]) by mwinf2019.orange.fr (SMTP Server) with ESMTP id 314A61C017D1 for ; Thu, 29 May 2008 14:02:46 +0200 (CEST) X-ME-UUID: 20080529120246201.314A61C017D1@mwinf2019.orange.fr Message-ID: <483E9B68.5010606@univ-paris12.fr> Date: Thu, 29 May 2008 14:02:48 +0200 From: =?ISO-8859-1?Q?Fr=E9d=E9ric_Gava?= Reply-To: gava@univ-paris12.fr Organization: =?ISO-8859-1?Q?Universit=E9_de_Paris_12=2C_LACL?= User-Agent: Thunderbird 1.5.0.13 (X11/20070824) MIME-Version: 1.0 To: caml-list@yquem.inria.fr Subject: Re: [Caml-list] Re: Where's my non-classical shared memory concurrency technology? References: <200805181735.50621.jon@ffconsultancy.com> <4831686F.8010903@doc.ic.ac.uk> <1211206144.11053.15.camel@flake.lan.gerd-stolpmann.de> <4833D7E8.8060502@doc.ic.ac.uk> <4EDC5A3B-DFD2-47EA-9C22-F0B355D7BBC7@inria.fr> <483BD594.7050504@doc.ic.ac.uk> In-Reply-To: Content-Type: text/plain; charset=US-ASCII; format=flowed Content-Transfer-Encoding: 7bit X-Spam: no; 0.00; gava:01 gava:01 pointer:01 12.:98 caml-list:01 data:02 frederic:03 concurrency:04 optimized:04 barrier:05 drawbacks:05 shared:06 shared:06 channel:06 memory:09 > That wasn't my point. My point was that there is no return channel. > If you want to know when your write is done, you have to use a lock > or a memory barrier. Both are very expensive. Barriers of synchronisation are a little expensive (one of the main drawbacks with a too restricted way of communication) but have many advantages as deadlock free and possibility to optimized the "communications" (copy of the data in the shared memory or juste the pointer). FG