[ News | IPCA | Mirrors | Add | Search | Mail | Help | WoTUG ]
Pablo is not public domain but is freely available without fee for education, research, and non-profit purposes.
Pablo is a registered trademark of the Board of Trustees of the University of Illinois, registered in the U.S. Patent and Trademark Office.
Author: Roger J. Noe, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA
Author: Ruth A. Aydt, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA
Author: Ruth A. Aydt, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA
Abstract: As massively parallel, distributed memory systems replace traditional vector supercomputers, effective application program optimization and system resource management become more than research curiosities | they are crucial to achieving substantial fractions of peak performance for scientific application codes. By recording dynamic activity, either at the application or system software level, one can identify and remove performance bottlenecks. Pablo is a performance analysis environment designed to provide performance data capture, analysis, and presentation across a wide variety of scalable parallel systems. The Pablo environment includes software performance instrumentation, graphical performance data reduction and analysis, and support for mapping performance data to both graphics and sound. Current research directions include complete performance data immersion via head-mounted displays and the integration of Pablo with data parallel Fortran compilers based on the emerging High Performance Fortran (HPF) standard.
Authors: Daniel A. Reed; Ruth A. Aydt; Tara M. Madhyastha; Roger J. Noe; Keith A. Shields and Bradley W. Schwartz. Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA.
Author: The Picasso Research Group, University of Illinois at Urbana-Champaign, Department of Computer Science, 1304 West Springfield Avenue, Urbana, Illinois 61801, USA
Author: Tara Maja Madhyastha, University of Illinois at Urbana-Champaign, Urbana, Illinois, USA
Abstract: Porsonify is a portable system for mapping data to sound. Sound is an interesting medium for presenting data because it can potentially highlight characteristics of data that cannot easily be seen. For example, a movie soundtrack or sound effects that accompany a vidio game convey information complementary to the imagery. The elements of sound (e.g., pitch, volume, duration and timbre) can be used in the same way that visual elements (such as color, form, and line) are manipulated to present and analyze data in visual displays. The use of sound to present data, the auditory equivalent of visualization, is called sonification. Porsonify is designed to encourage experimentation with aural data presentation, or sonification, on a variety of sound devices.
Author: Tara M. Madhyastha, Department of Computer Science, University of Illinois, 1304 West Springfield Avenue, Urbana, Illinois 61801, USA
Abstract: This manual documents the Pablo Self-Defining Data Format (SDDF), a flexible file meta-format designed to describe the structural layout of event records in performance trace files. We present our motivation for developing SDDF, high-level and in-depth coverage of the format itself, an explanation of the C ++ interface library, and sample files and code demonstrating the use of SDDF.
Author: Ruth A. Aydt, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA
Abstract: The SDDFStatistics program gathers a variety of statistics about the data fields of SDDF files, and can save these statistics to summary files which are themselves in SDDF format. These summary files are used by SDDFStatistics as "caches" of summary data, to minimize startup time when interactively browsing SDDF data files using the graphical user interface provided by SDDFStatistics. They may also be used by other Pablo tools, including the main Pablo Visualization Environment, whose displays may be configured more easily using information contained in the summaries. This document defines and describes the format of the summary files produced by SDDFStatistics, and includes an example consisting of an input SDDF data file and the corresponding summary file generated by SDDFStatistics.
Author: Dave Kohr
Author: The Picasso Research Group, University of Illinois at Urbana-Champaign, Department of Computer Science, 1304 West Springfield Avenue, Urbana, Illinois 61801, USA
Abstract: This document is a guide to the use of the iPablo graphical user interface to the Pablo Instrumentation Environment. Although using iPablo is not mandatory, it will allow you to quickly and easily specify the most common source code instrumentations without laboriously modifying your source code manually. Because this document is intended as a user's guide to the iPablo graphical interface of the Pablo Instrumentation Environment, its focus is on using iPablo to instrument application program source code in a variety of ways. iPablo is a Motif-based, X Windows application that currently supports the interactive instrumentation of procedure calls and outer loops in C source programs. Future versions of iPablo will support the interactive instrumentation of Fortran 77 programs as well.
Author: Keith A. Shields, Department of Computer Science, University of Illinois, Urbana, Illinois 61801, USA