Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis

Schulz, Martin; Galarowicz, Jim; Maghrak, Don; Hachfeld, William; Montoya, David; Cranford, Scott

doi:10.1155/2008/713705

Title: Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis

Full Record
Other Related Research

Abstract

Over the last decades a large number of performance tools has been developed to analyze and optimize high performance applications. Their acceptance by end users, however, has been slow: each tool alone is often limited in scope and comes with widely varying interfaces and workflow constraints, requiring different changes in the often complex build and execution infrastructure of the target application. We started the Open | SpeedShop project about 3 years ago to overcome these limitations and provide efficient, easy to apply, and integrated performance analysis for parallel systems. Open | SpeedShop has two different faces: it provides an interoperable tool set covering the most common analysis steps as well as a comprehensive plugin infrastructure for building new tools. In both cases, the tools can be deployed to large scale parallel applications using DPCL/Dyninst for distributed binary instrumentation. Further, all tools developed within or on top of Open | SpeedShop are accessible through multiple fully equivalent interfaces including an easy-to-use GUI as well as an interactive command line interface reducing the usage threshold for those tools.

Authors:

Schulz, Martin ^[1]; Galarowicz, Jim ^[2]; Maghrak, Don ^[2]; Hachfeld, William ^[2]; Montoya, David ^[3]; Cranford, Scott ^[4]

Lawrence Livermore National Laboratory, Livermore, CA, USA
Krell Insititute, Ames, IA, USA
Los Alamos National Laboratory, Los Alamos, NM, USA
Sandia National Laboratories, Livermore, CA, USA

Publication Date:: Tue Jan 01 00:00:00 EST 2008

Sponsoring Org.:: USDOE

OSTI Identifier:: 1198001

Grant/Contract Number:: AC52-07NA27344

Resource Type:: Published Article

Journal Name:: Scientific Programming

Additional Journal Information:: Journal Name: Scientific Programming Journal Volume: 16 Journal Issue: 2-3; Journal ID: ISSN 1058-9244

Publisher:: Hindawi Publishing Corporation

Country of Publication:: Egypt

Language:: English

Citation Formats


                    Schulz, Martin, Galarowicz, Jim, Maghrak, Don, Hachfeld, William, Montoya, David, and Cranford, Scott. Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis.  Egypt: N. p., 2008. 
Web.  doi:10.1155/2008/713705.

Copy to clipboard


                    Schulz, Martin, Galarowicz, Jim, Maghrak, Don, Hachfeld, William, Montoya, David, & Cranford, Scott. Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis.  Egypt.  https://doi.org/10.1155/2008/713705

Copy to clipboard


                    Schulz, Martin, Galarowicz, Jim, Maghrak, Don, Hachfeld, William, Montoya, David, and Cranford, Scott. Tue .  
"Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis".  Egypt.  https://doi.org/10.1155/2008/713705.

Copy to clipboard


                    
@article{osti_1198001,

  title        = {Open | SpeedShop: An Open Source Infrastructure for Parallel Performance Analysis},

  author       = {Schulz, Martin and Galarowicz, Jim and Maghrak, Don and Hachfeld, William and Montoya, David and Cranford, Scott},

  abstractNote = {Over the last decades a large number of performance tools has been developed to analyze and optimize high performance applications. Their acceptance by end users, however, has been slow: each tool alone is often limited in scope and comes with widely varying interfaces and workflow constraints, requiring different changes in the often complex build and execution infrastructure of the target application. We started the Open | SpeedShop project about 3 years ago to overcome these limitations and provide efficient, easy to apply, and integrated performance analysis for parallel systems. Open | SpeedShop has two different faces: it provides an interoperable tool set covering the most common analysis steps as well as a comprehensive plugin infrastructure for building new tools. In both cases, the tools can be deployed to large scale parallel applications using DPCL/Dyninst for distributed binary instrumentation. Further, all tools developed within or on top of Open | SpeedShop are accessible through multiple fully equivalent interfaces including an easy-to-use GUI as well as an interactive command line interface reducing the usage threshold for those tools.},

  doi          = {10.1155/2008/713705},

  journal      = {Scientific Programming},

  number       = 2-3,

  volume       = 16,

  place        = {Egypt},

  year         = {Tue Jan 01 00:00:00 EST 2008},

  month        = {Tue Jan 01 00:00:00 EST 2008}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Publisher's Version of Record
https://doi.org/10.1155/2008/713705

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 39 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Building a Community Infrastructure for Scalable On-Line Performance Analysis Tools around Open|Speedshop

Technical Report Miller, Barton

Peta-scale computing environments pose significant challenges for both system and application developers and addressing them required more than simply scaling up existing tera-scale solutions. Performance analysis tools play an important role in gaining this understanding, but previous monolithic tools with fixed feature sets have not sufficed. Instead, this project worked on the design, implementation, and evaluation of a general, flexible tool infrastructure supporting the construction of performance tools as “pipelines” of high-quality tool building blocks. These tool building blocks provide common performance tool functionality, and are designed for scalability, lightweight data acquisition and analysis, and interoperability. For this project, wemore »« less
https://doi.org/10.2172/1135802

Full Text Available
Building a Community Infrastructure for Scalable On-Line Performance Analysis Tools around Open|SpeedShop

Technical Report Galarowicz, James E. ; Miller, Barton P. ; Hollingsworth, Jeffrey K. ; ...

In this project we created a community tool infrastructure for program development tools targeting Petascale class machines and beyond. This includes tools for performance analysis, debugging, and correctness tools, as well as tuning and optimization frameworks. The developed infrastructure provides a comprehensive and extensible set of individual tool building components. We started with the basic elements necessary across all tools in such an infrastructure followed by a set of generic core modules that allow a comprehensive performance analysis at scale. Further, we developed a methodology and workflow that allows others to add or replace modules, to integrate parts into theirmore »« less
https://doi.org/10.2172/1113668

Full Text Available
A Cross-Platform Infrastructure for Scalable Runtime Application Performance Analysis

Technical Report Dongarra, Jack ; Moore, Shirley ; Bart Miller, Jeffrey Hollingsworth ; ...

The purpose of this project was to build an extensible cross-platform infrastructure to facilitate the development of accurate and portable performance analysis tools for current and future high performance computing (HPC) architectures. Major accomplishments include tools and techniques for multidimensional performance analysis, as well as improved support for dynamic performance monitoring of multithreaded and multiprocess applications. Previous performance tool development has been limited by the burden of having to re-write a platform-dependent low-level substrate for each architecture/operating system pair in order to obtain the necessary performance data from the system. Manual interpretation of performance data is not scalable for large-scalemore »« less
https://doi.org/10.2172/841192

Full Text Available
Parallel tools GUI framework-DOE SBIR phase I final technical report

Technical Report Galarowicz, James

Many parallel performance, profiling, and debugging tools require a graphical way of displaying the very large datasets typically gathered from high performance computing (HPC) applications. Most tool projects create their graphical user interfaces (GUI) from scratch, many times spending their project resources on simply redeveloping commonly used infrastructure. Our goal was to create a multiplatform GUI framework, based on Nokia/Digia’s popular Qt libraries, which will specifically address the needs of these parallel tools. The Parallel Tools GUI Framework (PTGF) uses a plugin architecture facilitating rapid GUI development and reduced development costs for new and existing tool projects by allowing themore »« less
https://doi.org/10.2172/1110783

Full Text Available
Scalable Dynamic Instrumentation for BlueGene/L

Conference Schulz, M ; Ahn, D ; Bernat, A ; ...

Dynamic binary instrumentation for performance analysis on new, large scale architectures such as the IBM Blue Gene/L system (BG/L) poses new challenges. Their scale--with potentially hundreds of thousands of compute nodes--requires new, more scalable mechanisms to deploy and to organize binary instrumentation and to collect the resulting data gathered by the inserted probes. Further, many of these new machines don't support full operating systems on the compute nodes; rather, they rely on light-weight custom compute kernels that do not support daemon-based implementations. We describe the design and current status of a new implementation of the DPCL (Dynamic Probe Class Library)more »« less
Full Text Available

Similar Records