From owner-freebsd-ports Tue Jul 28 11:22:44 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id LAA08413 for freebsd-ports-outgoing; Tue, 28 Jul 1998 11:22:44 -0700 (PDT) (envelope-from owner-freebsd-ports@FreeBSD.ORG) Received: from ConSys.COM (ConSys.COM [209.141.107.2]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id LAA08300 for ; Tue, 28 Jul 1998 11:21:55 -0700 (PDT) (envelope-from rcarter@pinyon.org) Received: (from pinyon@localhost) by ConSys.COM (8.8.6/8.8.6) id LAA14805; Tue, 28 Jul 1998 11:11:15 -0700 (MST) Date: Tue, 28 Jul 1998 11:11:15 -0700 (MST) From: "Russell L. Carter" Message-Id: <199807281811.LAA14805@ConSys.COM> To: dbader@eece.unm.edu, dfrasnel@csee.wvu.edu Subject: Re: Ports category submission (fwd) Cc: ports@FreeBSD.ORG Sender: owner-freebsd-ports@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.org |Daniel, | |> Herein lay a "sticky point" which I may or may not catch flak for |> bringing up. The folks at the Beowulf project (and now ExtremeLinux) are |> building computational clusters, some which include facilities for DSM. |> Personally, I define a true "parallel cluster" as something which provides |> not only shared processor power, but also shared memory, a distributed |> filesystem, and (to some degree) a shared userspace. | |I would include DSM, DFS, etc., as parallel computing tools, but I |certainly wouldn't call them a "true 'parallel cluster'". Many current |supercomputers are logically equivalent to a cluster of workstations |with high speed interconnect, where tasks in a program communicate by |passing messages (e.g. MPI). In my research for high performance |computing, I develop the most efficient algorithms which dictate use |of message passing, rather than virtual shared memory, for |performance. This category should be inclusive -- *ANY* tools (above |and beyond standard OS and networking infrastructure) which enable |multiple CPUs to cooperate together to solve a computational problem. And certainly include middleware, for instance move the ORBs out of devel. And queuing systems, too. I build distributed applications now that use both on "clusters", which in some cases run over things like SCI. Russell To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-ports" in the body of the message