Coming Events

February 27, 2008 - Petascale Data Storage BoF Session at FAST '08
The Petascale Data Storage Institute is a DOE-funded collaboration of three universities and five national labs with the objective of anticipating the challenges of data storage for computing systems operating in the peta-operations per second to exa-operations per second and working toward the resolution of these challenges in the community as a whole.  An important part of our agenda is outreach to other researchers and practitioners to share our resources and gather better understanding of the petascale issues ahead from all.

February 23, 2008 - Parallel I/O for Extreme-scale Platforms
The ORNL Future Technologies group with personnel from the ORNL National Center for Computational Sciences are to give a tutorial on parallel I/O for extreme-scale platforms such as the Cray XT, IBM Blue Gene, and ultra-scale Linux clusters. We will share our experiences and lessons learned from characterizing and optimizing I/O on these platforms, and discuss directions and issues that need to be addressed for I/O at the unprecedented scale needed for petaflop and even exaflop systems. Join us on February 23, 2008 in Salt Lake City for this enlightening, in-depth discussion. One of the tutorial presenters, Dr. Phil Roth, of ORNL, is a PDSI Principal Investigator.

 

Code and Data Releases

• Sandia's IOR software, for benchmarking parallel file systems using POSIX, MPIIO, or HDF5 interfaces.
• FSSTATS code release
• LANL PDSI Research Data and Open Source Code
• Computer Failure Data Repository (CFDR)
  • LANL Data
  • NERSC Data
  • PNNL Data

 

PDSI Overview

Petascale computing infrastructures for scientific discovery make petascale demands on information storage capacity, performance, concurrency, reliability, availability, and manageability. The last decade has shown that parallel file systems can barely keep pace with high performance computing along these dimensions; this poses a critical challenge when petascale requirements are considered. The Petascale Data Storage Institute will focus on the data storage problems found in petascale scientific computing environments, with special attention to community issues such as interoperability, community buy-in, and shared tools. Leveraging experience in applications and diverse file and storage systems expertise of its members, the institute allows a group of researchers to collaborate extensively on developing requirements, standards, algorithms, and development and performance tools. Mechanisms for petascale storage and results will be made available to the petascale computing community. The institute will hold periodic workshops and develop educational materials on petascale data storage for science.

The Petascale Data Storage Institute is a collaboration between researchers at Carnegie Mellon University, National Energy Research Scientific Computing Center, Pacific Northwest National Laboratory, Oak Ridge National Laboratory, Sandia National Laboratory, Los Alamos National Laboratory, University of Michigan, and the University of California at Santa Cruz.

The Drive to Petascale Computing Faster computers need more data, faster: Data movement at Terabytes/sec Petabyte sized files (100 Library of Congress equivalents) Trillions of files Challenges Scaling file system speeds and feeds Scalable interoperable interfaces and protocols Automating data distribution and fault mitigation Enumerate and search metadata of trillions of files

 

Contact Us

Garth Gibson, PDSI PI
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
phone:412-268-5890
email: garth@cs.cmu.edu

Angela Miller, Administrative Asst.
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
phone: 412-268-6645
email:amiller@cs.cmu.edu