RSS FeedSponsor
(Opens New Window)
- Websites
- Streaming Audio
- Podcast
- Virtual Servers
PodcastRCE 35: PVFS Parallel Virtual FileSystem
Update Required
To play the media you will need to either update your browser to a recent version or update your Flash plugin.
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
Update Required
To play the media you will need to either update your browser to a recent version or update your Flash plugin.
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 32: Puppet a tool for data center automation
Update Required
To play the media you will need to either update your browser to a recent version or update your Flash plugin.
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 33: Hwloc Portable Hardware Locality
Update Required
To play the media you will need to either update your browser to a recent version or update your Flash plugin.
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 31: lammps Clasical Molecular Dynamics
Update Required
To play the media you will need to either update your browser to a recent version or update your Flash plugin.
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. More Articles... |
