RCE - Super Computers

MPI-3 Forum Survey

Password: mpi3

MPI Comments email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Brock Palen and Jeff Squyres speak with Dr. Bill Gropp of University of Illinois Urbana-Champaign Urbana and Dr. Richard Graham of ORNL (Oak Ridge National Lab) on the MPI Forum, MPI-2.2 and the upcoming MPI-3 standards for parallel programming with MPI.

William Gropp is the Paul and Cynthia Saylor Professor in the Department of Computer Science and Deputy Directory for Research for the Institute of Advanced Computing Applications and Technologies at the University of Illinois in Urbana-Champaign. He received his Ph.D. in Computer Science from Stanford University in 1982 and worked at Yale University and Argonne National Laboratory. His research interests are in parallel computing, software for scientific computing, and numerical methods for partial differential equations, and he is well known for the MPICH2 and PETSc libraries.

Richard Graham has been at ONRL since Jan, 2007 and is the Group Leader for the Application Performance Tools group in the Computer Science and Mathematics division at ONRL, and is a Distinguished member of the Research Staff. Prior to joining ORNL he spent eight years at ORNL serving in a range of technical and managerial roles, leaving as the acting group leader for the Advanced Computing Laboratory. He is currently chairman of the MPI Forum, and is leading the MPI-3 effort. He led the LA-MPI development effort, and is one of three founders of the Open MPI project. Dr. Graham received his PhD in Theoretical Chemistry from Texas A&M University in 1990, and a BS in Chemistry from Seattle Pacific University in 1983.

Show page: https://www.rce-cast.com/Podcast/rce-22-mpi-3-forum.html · Licensed CC BY 4.0

MPI-3 Forum Survey

Password: mpi3

Brock Palen and Jeff Squyres speak about our trip to Supercomputing 2009 in Portland OR. This is a short show with our limited view of the show.

Show page: https://www.rce-cast.com/Podcast/rce-21-sc09-supercomputing-09.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Mark Miller on the Silo (wci.llnl.gov/codes/silo) storage format.  Mark also works on the Visit (wci.llnl.gov/codes/visit) project which were our guests on RCE 6.

Be sure to catch Jeff and Brock at SC09 this year in Portland!

Mark received his Ph.D. from U.C. Davis in EE with emphasis on compression of very large datasets for real-time signal processing. I started at LLNL in May of 1995 working on I/O analysis of Silo. From there, I became involved in the ASCI Data Models and Formats effort leading the development of the Sets and Fields (SAF, pronounced 'safe') data modeling system where I also became involved in scalable, parallel I/O. Then, I moved to VisIt, adding scalable rendering as my first major enhancement. Since then, I have been working about 50-75% time on VisIt, 25% time on Silo and, more recently, on ITAPS SciDAC project.

Show page: https://www.rce-cast.com/Podcast/rce-20-silo.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Josh Bernstein of Penguin Computing (www.penguincomputing.com) about Scyld ClusterWare.

Joshua Bernstein is a Software Engineer with Penguin Computing. Prior to working at Penguin Computing, Joshua was a Linux System Administrator at NASA's Lunar and Planetary Lab, where he worked on several missions including Cassini, HiRISE, and the Phoenix Mars Lander. Joshua has been actively involved with the Open Source community and has contributed to projects such as SAMBA, MythTV and Gallery. Joshua studied computer engineering at the University of Arizona.

Show page: https://www.rce-cast.com/Podcast/rce-19-scyld-clusterware.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Dr. Will Schroeder and Dr. Berk Geveci of Kitware (http://kitware.com) about The Visualization Toolkit (VTK).

Dr. Schroeder is President, CEO and co-founder of Kitware, Inc. Will's role at Kitware is to identify technology and business opportunities, and to obtain the necessary support for Kitware to meet these opportunities. Dr. Schroeder provides technical leadership in projects such as NLM's Insight Toolkit project (itk.org), NSF-funded projects for higher-order finite element visualization and visual databases, DOE grid computing, and various projects for medical image analysis.

Dr. Geveci leads the scientific visualization and infomatics teams at Kitware Inc. He is one of the leading developers of the ParaView visualization application and the Visualization Toolkit (VTK). Hisresearch interests include large scale parallel computing, computational dynamics, finite elements and visualization algorithms. Dr. Geveci regularly publishes and teaches courses at conferences including IEEE Visualization and Supercomputing conferences.

Show page: https://www.rce-cast.com/Podcast/rce-18-vtk.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Dr. Peter Honeyman and Dr. Bruce Fields of Center for Information Technology Integration on NFSv4.

Bruce Fields is an assistant research scientist at CITI, working mainly on Linux and NFS, and he maintains the Linux kernel's NFS server.  He came to CITI after receiving a PhD in mathematics from the University of Michigan in 2000

Peter Honeyman is Research Professor of Computer Science and Engineering and Director of the Center for Information Technology Integration at the University of Michigan.

Show page: https://www.rce-cast.com/Podcast/rce-17-nfs-v4.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Mason Katz and Greg Bruno of UCSD (University of California San Diego)  about the Rocks Cluster (http://www.rocksclusters.org/) distribution.

Greg Bruno is a core architect and developer of the Rocks Cluster Distribution and he has been involved with the project since its inception. Over the past 10 years, Rocks has helped "make clusters easy" for scientists from around the world as proven by the Rocks Cluster Registration Page (www.rocksclusters.org/register) where, as of August 2009, over 1,200 clusters have been voluntarily registered. Additionally, Rocks has been recognized by the HPC community by winning six HPCwire awards. He has co-authored four refereed technical conference papers on the topic of Rocks. Dr. Bruno received his Ph.D. from the University of California at San Diego in Computer Science in 2008. Prior to co-founding the Rocks Development Group, he worked at NCR where he developed cluster management software for systems that support the world's largest databases. During his 10 year employment at NCR, he co-authored three awarded patents (Patent Numbers:6,119,159 - 6,308,207 - 6,081,812).

Mason J. Katz is currently the Group Leader for Cluster Development for the San Diego Supercomputer Center (SDSC) at the University of California (UCSD). Mr. Katz received his BS in Systems Engineering from the University of Arizona. He worked for five years as an embedded software engineer on networks of lightning detection sensors. Following this his spent three years working at the University of Arizona on network security protocols (IPSec), and operating systems (x-kernel, Scout). Recently he has spent the last six years working on Windows and Linux commodity clustering (HPVM, Rocks). The focus of his current work is on the Rocks Clustering Distribution, a complete software stack building high performance computing clusters. Rocks has an international user community of several thousand users, and has an international development team of a dozen software developers. In addition, Mr. Katz is actively involved in Pacific Rim Applications and Grid Middleware Assembly (PRAGMA) having served as co-chair for two meetings, and as co-lead for the Resources Working Group.

Show page: https://www.rce-cast.com/Podcast/rce-16-rocks-clusters.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Narayan Desai and Cory Lueninghoener of Argonne National Laboratory, about BCFG2 (http://trac.mcs.anl.gov/projects/bcfg2).

Narayan Desai is a principal experimental systems engineer at Argonne National Laboratory. He specializes in system software and system management issues, specifically for very large scale parallel computing systems. He has written and spoken widely on these issues, and leads the Bcfg2 configuration management project.

Cory Lueninghoener is a high performance computing system administrator at Argonne National Laboratory.  After starting out on modest-sized clusters while a grad student at the University of Nebraska, he worked his way up the Top500 list and is currently a lead administrator on Intrepid, Argonne's 40 rack BlueGene/P system.  He is especially interested in configuration management on large HPC resources and is an active participant in the Bcfg2 project.

Show page: https://www.rce-cast.com/Podcast/rce-15-bcfg2.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with Andreas Dilger of Sun on the Lustre (www.lustre.org) cluster filesystem.

 Andreas Dilger is currently one of the principal filesystem architects for the Lustre filesystem, on which he has been working since its inception. He has started doing filesystems and storage development in 1999, when hedeveloped a patch for online resizing ext2 and ext3 filesystems, and was a contributor to the Linux LVM code.  He also contributed to the PNG specification, and was a maintainer of the libpng library and the POV-Ray ray tracer.

Show page: https://www.rce-cast.com/Podcast/rce-14-lustre-cluster-filesystem.html · Licensed CC BY 4.0

Brock Palen and Jeff Squyres speak with David Anderson (http://boinc.berkeley.edu/anderson/) of the Boinc (http://boinc.berkeley.edu/) Project.  

 Dr. David P. Anderson received an MA in Mathematics and PhD in Computer Science from the University of Wisconsin, Madison. From 1985 to 1992 he served on the faculty of the U.C. Berkeley Computer Science Department. His research areas include volunteer computing, distributed systems, realtime and multimedia systems, graphics, computer music, and psychometrics applied to learning and aesthetic preference. Since 1998 he has directed SETI@home, a pioneering project in volunteer computing. In 2002 he founded the Berkeley Open Infrastructure for Network Computing (BOINC) project, which develops middleware for volunteer computing. He also directs Bossa (software for distributed thinking) and Bolt (software for web-based training and education).

Show page: https://www.rce-cast.com/Podcast/rce-13-boinc.html · Licensed CC BY 4.0