NCSA Home
Contact Us | Intranet | Search

data link Story: Pablo Press Release

News
datalink
0006
Current issue
Archives

URBANA, IL---May 9, 2000
The University of Illinois' Pablo Research Group today announced the opening of a national facility for high-performance I/O characterization and optimization. Embodying insight gained through development of the Pablo I/O characterization toolkit, the NSF CADRE facility contains, and continues to build, a substantial base of empirical data on I/O access patterns of single and multiple processor systems. Its goal is to enable researchers and educators to overcome limitations imposed by I/O on the overall performance of petascale computing systems.

CADRE is a web-based facility that is extending, documenting, archiving, and disseminating software tools, sample applications, and experimental data to stimulate research on I/O system design, analysis, and optimization for high-performance computing environments. Primarily aimed at outreach, CADRE is deploying:

  • The Pablo portable I/O performance analysis tools that capture and reveal the I/O patterns of data-intensive applications executing on high-performance systems.
  • Tutorial material covering I/O characterization and analysis, as well as material specific to use of Pablo tools for I/O optimization.
  • A repository of I/O traces, obtained from execution of instrumented I/O-intensive applications. This repository contains both the raw traces as well as a database of I/O data that can be searched and queried for specific metrics and data. These traces provide file system and storage hierarchy designers and other I/O researchers with ready access to empirical data exposing the interdependencies among access patterns, I/O APIs, library implementations, file system features and policies, and storage hardware configurations. Trace files contained in the database can be downloaded, ordered for delivery on CD-ROM or DVD, or used with analysis tools online. See bugle.cs.uiuc.edu:1303/cgi-bin/cadre.pl .
  • Instrumented I/O benchmarks, along with traces and software tools, which are available for download or email-order delivery on CD-ROM and DVD.

The high-performance community is already tapping the resources made available by the CADRE facility. A team from Northwestern University recently used the Pablo tools to analyze the I/O activity of a parallel 3-D cosmology hydrodynamics code, Enzo. Running the code successively on 32, 64, and 128 processors at the National Center Supercomputing Application (NCSA), trace files were generated and analyzed using the Pablo performance toolkit. The results of the Enzo code analyses are summarized in statistical tables and graphics plots.

The Pablo TracelibraryŠ 5.1.2 has also been adopted and made available by the National Computational Science Alliance. It has been installed on both the SGI Cray Origin2000 at NCSA and the RoadRunner high-performance Linux PC cluster at the University of New Mexico. Additional information can be obtained at: www-pablo.cs.uiuc.edu/So ft ware/softwareReleases.htm.

The software is installed in the /usr/apps/Pablo directory on the Origin2000 and the /usr/local/Pablo directory on RoadRunner. For directory contents and hints on how to use the Pablo Trace and Trace Analysis software, refer to the README files in the installation directory. Additional information can be obtained at: www-pablo.cs.uiuc.edu/So ft ware/softwareReleases.htm.

Founded in 1984, the University of Illinois Pablo Research Group is an academic research group within the Department of Computer Science at the University of Illinois at Urbana-Champaign. Under the direction of Professor Dan Reed, members of the group investigate the interaction of architecture, system software, and applications on large-scale parallel and distributed computer systems. Key research foci are exploration of performance analysis techniques and compiler-aided scalability analysis, scalable parallel file systems, and real-time adaptive systems for resource policy control.

More information about Pablo and the Pablo suite of scalable performance tools is available online. §

Pablo is a registered trademark of the University of Illinois Board of Trustees in the United States and/or other countries. Other product and company names herein may be trademarks of their respective owners.


Mail this article to a colleague!