From owner-hpff Mon Sep 23 13:51:55 1996 Received: (from daemon@localhost) by cs.rice.edu (8.7.1/8.7.1) id NAA15308 for hpff-out; Mon, 23 Sep 1996 13:51:55 -0500 (CDT) Received: from helium.nrlmry.navy.mil.nrlmry.navy.mil (HELIUM.NRLMRY.NAVY.MIL [199.9.2.40]) by cs.rice.edu (8.7.1/8.7.1) with SMTP id NAA15303 for ; Mon, 23 Sep 1996 13:51:50 -0500 (CDT) Received: from norton.nrlmry.navy.mil by helium.nrlmry.navy.mil.nrlmry.navy.mil (4.1/SMI-4.1) id AA15772; Mon, 23 Sep 96 11:52:05 PDT Received: by norton.nrlmry.navy.mil (SMI-8.6/SMI-SVR4) id LAA06450; Mon, 23 Sep 1996 11:51:28 -0700 Date: Mon, 23 Sep 1996 11:51:28 -0700 Message-Id: <199609231851.LAA06450@norton.nrlmry.navy.mil> From: To: hpff@cs.rice.edu Subject: hpff: TEMPLATE scoping Sender: owner-hpff Precedence: bulk --------------------------------------------------------------------------- hpff@cs.rice.edu is a mailing list for announcements related to High Performance Fortran. Instructions for adding or deleting yourself from this list appear at the bottom of this message. --------------------------------------------------------------------------- I have been experimenting with TEMPLATEs a bit lately and have found that when used in MODULEs, I would like to be able to limit their scoping to just the module. Has there been any discussion of templates having the ability to use PRIVATE or PUBLIC in the future? Also - Array alignment in subroutines seems to be pretty well addressed for the codes that I am working on. Dummy arrays I declare with: !HPF$ DISTRIBUTE *(aaaaaaaaaaaa) :: yyy !HPF$ DISTRIBUTE *(bbbbbbbbbbbb) :: zzz and locals I can declare with: !HPF$ ALIGN WITH yyy :: !HPF$ ALIGN WITH zzz :: and presumably somewhere higher up in the call tree the relationship between different distributions is described so as to maximize alignment of arrays. MODULEs seem to introduce an interesting situation. Currently, I am using them only to replace COMMON blocks. It seems that there is not a way to explicitly tell the compiler about the alignment relationship between arrays in the module and arrays in the routines that USE the module. Even TEMPLATEs, if you could limit their scoping via PRIVATE, would only implicitly address this. Have I missed something? Is there any preferred method for addressing alignment of arrays in COMMON block type MODULEs with arrays in subroutines? thanks -dave --------------------------------------------------------------------------- To (un)subscribe to this list, send mail to hpff-request@cs.rice.edu. Leave the subject line blank, and in the body put the line (un)subscribe --------------------------------------------------------------------------- From owner-hpff Wed Sep 25 20:30:28 1996 Received: (from daemon@localhost) by cs.rice.edu (8.7.1/8.7.1) id UAA10236 for hpff-out; Wed, 25 Sep 1996 20:30:28 -0500 (CDT) Received: from antares.mcs.anl.gov (antares10.mcs.anl.gov [140.221.10.64]) by cs.rice.edu (8.7.1/8.7.1) with SMTP id UAA10230 for ; Wed, 25 Sep 1996 20:30:24 -0500 (CDT) Received: from abacus (abacus.mcs.anl.gov [140.221.6.130]) by antares.mcs.anl.gov (8.6.10/8.6.10) with ESMTP id UAA13045; Wed, 25 Sep 1996 20:30:22 -0500 Date: Wed, 25 Sep 1996 20:30:21 -0500 Message-Id: <199609260130.UAA06838@abacus> From: Rajeev Thakur To: hpff@cs.rice.edu Subject: hpff: CFP: IOPADS '97 Sender: owner-hpff Precedence: bulk --------------------------------------------------------------------------- hpff@cs.rice.edu is a mailing list for announcements related to High Performance Fortran. Instructions for adding or deleting yourself from this list appear at the bottom of this message. --------------------------------------------------------------------------- CALL FOR PAPERS Fifth Annual Workshop on I/O in Parallel and Distributed Systems (IOPADS) URL: http://www.cs.dartmouth.edu/iopads in conjunction with SC97: High Performance Networking and Computing November 17, 1997 San Jose, CA, USA Current Sponsors: ACM SIGACT, SIGARCH, and SIGOPS IOPADS brings together researchers in all aspects of storage-related I/O in parallel and distributed systems, including algorithms, applications, architecture, and systems software. It is our opinion that the research problems are most effectively addressed by investigating all these areas rather than working in each area in isolation. Although I/O-related papers appear in many other conferences, the value of IOPADS is in gathering interested researchers from all these areas of computer science, encouraging cross-disciplinary interaction. IOPADS '96 was held in conjunction with the FCRC group of conferences and was a huge success. IOPADS '97 will be co-located with SC97 (the 1997 entry in the former "Supercomputing 'XY" series). We expect that ACM Press will again publish the IOPADS proceedings, which will be provided to all registrants and will be available for sale at SC97 and afterwards. We invite you to submit papers that focus on storage-related I/O in high-performance parallel and distributed systems, in the context of parallel or distributed applications. Suggested topics include: * Experimental characterization of I/O demand * Design and implementation of I/O-intensive applications * Real-time and multimedia I/O * Theory and implementation of parallel-I/O algorithms * Interconnect issues, e.g., network-attached storage devices * Devices, including disk arrays and tape robots * Language and compiler support * Run-time libraries * Database systems * File systems Papers submitted to IOPADS must be unpublished and must not be submitted for publication elsewhere. The manuscript should be at most twelve pages long (including figures, tables, and excluding references), single- or double-spaced, using an 11-point font. Electronic submission (of PostScript) is required (details will be posted; check the web page). All submissions must arrive by 6 P.M. Eastern Time on March 25, 1997. Decisions will be announced by June 1, 1997. General Chairs Program Chair ------------------------------------------------- ----------------------- Thomas H. Cormen Alok Choudhary David Kotz Department of Department of Department of Computer Science Elec. and Computer Eng. Computer Science Dartmouth College Northwestern University Dartmouth College 6211 Sudikoff Lab 2145 Sheridan Road 6211 Sudikoff Lab Hanover, NH 03755-3510 Evanston, IL 60208-3118 Hanover, NH 03755-3510 (603) 646-2417 (847) 467-4129 (603) 646-1439 thc@cs.dartmouth.edu choudhar@ece.nwu.edu dfk@cs.dartmouth.edu Program Committee ----------------- Rajesh Bordawekar (Caltech) Garth Gibson (Carnegie Mellon) Leana Golubchik (Columbia University) Jim Gray (Microsoft) Phil Hatcher (Univ. New Hampshire) David Kotz (Dartmouth College) Orran Krieger (IBM T.J. Watson) Jai Menon (IBM Almaden) David Nagle (Carnegie Mellon) Bill Nitzberg (NASA Ames) Sivan Toledo (IBM T.J. Watson) Darren Vengroff (Univ. Delaware) Jeffrey Vitter (Duke University) Marianne Winslett (Univ. Illinois Urbana) Publicity Chair: Rajeev Thakur, Argonne National Laboratory For updates and more information, see http://www.cs.dartmouth.edu/iopads For general inquiries, send e-mail to iopads@cs.dartmouth.edu --------------------------------------------------------------------------- To (un)subscribe to this list, send mail to hpff-request@cs.rice.edu. Leave the subject line blank, and in the body put the line (un)subscribe ---------------------------------------------------------------------------