A Podcast for HPC Folk

A Podcast for HPC Folk

Podcast Feed

Sponsor

(Opens New Window)

www.mlds-networks.com

  • Websites
  • E-Mail
  • Streaming Audio
  • Podcast
  • Virtual Servers

Podcast

RCE 35: PVFS Parallel Virtual FileSystem

MP3 (Right Click Save As)

UPDATE: The first version of this show had some encoding issues. The current copy does not.

Brock Palen and Jeff Squyres speak with Walter Ligon about PVFS2 the parallel file system.

Walt Ligon completed his PhD in Computer Science at the Georgia Institute of Technology in 1992. Since then he has been a member of the faculty in the Holcombe Department of Electrical and Computer Engineering at Clemson University, where he teaches computer engineering and performs research on high performance computing. Walt’s group developed the Parallel Virtual File System (PVFS) – an open source parallel file system for Linux as part of the Beowulf project at Goddard Space Flight Center in the mid 1990’s. PVFS has since become a project jointly developed at several national labs and universities world wide. Currently Walt’s group is working on techniques for improving small file accesses, metadata accesses, security, and reliability for parallel file systems. Other research activities Walt has been part of have included parallel programming environments and reconfigurable computing architectures. Walt continues to be active in conducting funded research, publishing, and teaching.

RCE 34: OFED OpenFabrics Enterprise Distribution

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Betsy Zeller of Qlogic and Tziporet Koren of Mellanox about OFED the OpenFabrics Enterprise Distribution, the backbone of most Infiniband and iWARP networks.

RCE 33: Hwloc Portable Hardware Locality

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Samuel Thibault of the University of Bordeaux and INRIA, about hwloc.

Samuel Thibault is an Assistant Professor in the University of Bordeaux (France), working in the Runtime INRIA team. He received his PhD in distribution of HPC application threads over hierarchical machines in 2007, the hierarchy part of which was turned and improved into the hwloc library and tools in 2009. His current research interests now also include scheduling tasks on both CPUs and GPUs, and the use of virtualization for HPC. In a second life, he is also a Debian Developer focused on accessibility support (particularly for blind users), and a GNU/Hurd developer.

RCE 32: Puppet a tool for data center automation

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Michael DeHaan of Puppet Labs about Puppet, a tool for data center automation.

Michael DeHaan is the product manager for Puppet Labs (http://puppetlabs.com), the makers of Puppet, an open source data center automation and configuration management framework. Puppet provides system administrators with a simplified platform that allows for consistent, transparent, and flexible systems management. Before joining Puppet Labs, Michael created and ran the Cobbler (http://fedorahosted.org/cobbler) project at Red Hat and also helped create Func (http://fedorahosted.org/func).

@puppetlabs on twitter, #puppet on irc.freenode.net

RCE 31: lammps Clasical Molecular Dynamics

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Steve Plimpton about the classical MD code Lammps.

Steve Plimpton is a staff member at Sandia National Laboratories, a US DOE laboratory, where he's been a member of the Computation, Computers, Information, and Mathematics center for the past 20 years, currently in the Scalable Algorithms group. His work involves implementing and using scientific simulations designed for parallel supercomputers. Often this includes the creation of efficient parallel algorithms; see http://www.sandia.gov/~sjplimp. He has written and distributes a variety of open-source software, including molecular dynamics, kinetic Monte Carlo, and biological cell simulators, as well as a MapReduce library written on top of MPI.

RCE 30 Condor High Throughput Computing

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Jason Stowe of Cycle Computing and Greg Thain of UofW Madison about Condor.

Jason Stowe is the founder and CEO of Cycle Computing(http://www.cyclecomputing.com), a leading provider of open-source, High Performance Computing (HPC) technology on internal desktops, servers, and in the Cloud. Leveraging its expertise with internal HPC, Cycle helps clients provision large-scale, secure HPC clusters in the cloud on demand. Cycle supports open-source Condor & Hadoop, as well as PBS/SGE, to provide innovative administrative functionality and reduce costs in managing small clusters to environments of 30,000+ CPUs. Jason attended Carnegie Mellon and Cornell Universities, guest lectured at Cornell's Johnson Business School, and sits on Amazon's Customer Advisory Board.

Greg Thain is a systems programmer working as a staff member of the Condor Project at the University of Wisconsin - Madison. As part of the core condor flighworthy team, he was worked on many aspects of Condor, including the Condor Parallel Universe, the master-worker framework for parallel computing, and tuning the performance of the system as a whole. Greg has a BS in Computer Sciences from the University of Wisconsin.

RCE 29 Blue Waters, Allocations use and history

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with John Ziebarth of the Krell Institute and William Kramer of NCSA about the Blue Waters project and who can use it. 

A detailed podcast about the system will be held latter.

RCE 28 MPICH2

>

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Dr. Ewing "Rusty" Lusk and Dr. William "Bill" Gropp about MPICH2.

Ewing “Rusty” Lusk is director of the Mathematics and Computer Science Division at Argonne National Laboratory and an Argonne Distinguished Fellow. He received his B.A. in mathematics from the University of Notre Dame in 1965 and his Ph.D. in mathematics from the University of Maryland in 1970. He was a professor of computer science at Northern Illinois University before joining Argonne in 1982. His current research interests include programming models for scalable parallel computing, implementation issues for the MPI Message-Passing Interface standard, parallel performance analysis tools, and system software for large-scale machines. He is the author of five books and more than a hundred research articles in mathematics, automated deduction, and parallel computing.

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.

RCE 26: PLASMA - Parallel Linear Algebra Software for Multicore Architectures

MP3 (Right Click Save As)

Brock Palen and Jeff Squyres speak with Dr. Jack Dongarra and Dr. Jakub Kurzak on PLASMA (http://icl.cs.utk.edu/plasma/) Parallel Linear Algebra for Scalable Multi-core Architectures. The main purpose of PLASMA is to address the performance shortcomings of the LAPACK and ScaLAPACK libraries on multicore processors and multi-socket systems of multicore processors.

Jack Dongarra received a Bachelor of Science in Mathematics from Chicago State University in 1972 and a Master of Science in Computer Science from the Illinois Institute of Technology in 1973. He received his Ph.D. in Applied Mathematics from the University of New Mexico in 1980. He worked at the Argonne National Laboratory until 1989, becoming a senior scientist. He now holds an appointment as University Distinguished Professor of Computer Science in the Computer Science Department at the University of Tennessee and holds the title of Distinguished Research Staff in the Computer Science and Mathematics Division at Oak Ridge National Laboratory (ORNL), Turing Fellow at Manchester University, and an Adjunct Professor in the Computer Science Department at Rice University. He is the director of the Innovative Computing Laboratory at the University of Tennessee. He is also the director of the Center for Information Technology Research at the University of Tennessee which coordinates and facilitates IT research efforts at the University.

Jakub Kurzak received his M.Sc. degree in Electrical Engineering from Wrocław University of Technology, Poland, in 2000 and a Ph.D. degree in Computer Science from the University of Houston, Texas, in 2005. Afterwards, he joined the Innovative Computing Laboratory in the EECS Department, University of Tennessee, as a Senior Research Associate and is now a Research Scientist in that laboratory. His research focuses on the development of parallel software for numerical scientific computing, with an emphasis on multicore processors and accelerators. He is a member of the team behind ICL's flagship projects, PLASMA and MAGMA.

 
Joomla 1.5 Templates by Joomlashack