Presented by The Harness Workbench: Unified and Adaptive Access to Diverse HPC Platforms Christian Engelmann Computer Science Research Group Computer Science.

Slides:



Advertisements
Similar presentations
Large-Scale, Adaptive Fabric Configuration for Grid Computing Peter Toft HP Labs, Bristol June 2003 (v1.03) Localised for UK English.
Advertisements

A Dynamic World, what can Grids do for Multi-Core computing? Daniel Goodman, Anne Trefethen and Douglas Creager
Copyright © Richard N. Taylor, Nenad Medvidovic, and Eric M. Dashofy. All rights reserved. Basic Concepts Software Architecture Lecture 3.
Goals Give you a feeling of what Eclipse is.
Software Frameworks for Acquisition and Control European PhD – 2009 Horácio Fernandes.
Chapter 13 Embedded Systems
Presented by IBM developer Works ibm.com/developerworks/ 2006 January – April © 2006 IBM Corporation. Making the most of Creating Eclipse plug-ins.
1 FM Overview of Adaptation. 2 FM RAPIDware: Component-Based Design of Adaptive and Dependable Middleware Project Investigators: Philip McKinley, Kurt.
–Streamline / organize Improve readability of code Decrease code volume/line count Simplify mechanisms Improve maintainability & clarity Decrease development.
Using the Drupal Content Management Software (CMS) as a framework for OMICS/Imaging-based collaboration.
Emerging Platform#4: Android Bina Ramamurthy.  Android is an Operating system.  Android is an emerging platform for mobile devices.  Initially developed.
EUROPEAN UNION Polish Infrastructure for Supporting Computational Science in the European Research Space Cracow Grid Workshop’10 Kraków, October 11-13,
Ontology-derived Activity Components for Composing Travel Web Services Matthias Flügge Diana Tourtchaninova
Katanosh Morovat.   This concept is a formal approach for identifying the rules that encapsulate the structure, constraint, and control of the operation.
Center for Component Technology for Terascale Simulation Software 122 June 2002Workshop on Performance Optimization via High Level Languages and Libraries.
OpenAlea An OpenSource platform for plant modeling C. Pradal, S. Dufour-Kowalski, F. Boudon, C. Fournier, C. Godin.
4.x Performance Technology drivers – Exascale systems will consist of complex configurations with a huge number of potentially heterogeneous components.
Introduction to the Atlas Platform Mobile & Pervasive Computing Laboratory Department of Computer and Information Sciences and Engineering University of.
UNIX SVR4 COSC513 Zhaohui Chen Jiefei Huang. UNIX SVR4 UNIX system V release 4 is a major new release of the UNIX operating system, developed by AT&T.
CGW 2003 Institute of Computer Science AGH Proposal of Adaptation of Legacy C/C++ Software to Grid Services Bartosz Baliś, Marian Bubak, Michał Węgiel,
Java Adaptive Mathematical Modeling Engine (JAMME) Leeland Artra, Cell Systems Initiative (CSI) Zheng Li, Department of Bioengineering University of Washington,
:: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: ::::: :: Dennis Hoppe (HLRS) ATOM: A near-real time Monitoring.
Flexibility and user-friendliness of grid portals: the PROGRESS approach Michal Kosiedowski
Architecting Web Services Unit – II – PART - III.
Through the development of advanced middleware, Grid computing has evolved to a mature technology in which scientists and researchers can leverage to gain.
2005 Materials Computation Center External Board Meeting The Materials Computation Center Duane D. Johnson and Richard M. Martin (PIs) Funded by NSF DMR.
Contents 1.Introduction, architecture 2.Live demonstration 3.Extensibility.
4.2.1 Programming Models Technology drivers – Node count, scale of parallelism within the node – Heterogeneity – Complex memory hierarchies – Failure rates.
Selected Topics in Software Engineering - Distributed Software Development.
Components for Beam Dynamics Douglas R. Dechow, Tech-X Lois Curfman McInnes, ANL Boyana Norris, ANL With thanks to the Common Component Architecture (CCA)
Introduction CS 3358 Data Structures. What is Computer Science? Computer Science is the study of algorithms, including their  Formal and mathematical.
Shannon Hastings Multiscale Computing Laboratory Department of Biomedical Informatics.
1 Geospatial and Business Intelligence Jean-Sébastien Turcotte Executive VP San Francisco - April 2007 Streamlining web mapping applications.
Refining middleware functions for verification purpose Jérôme Hugues Laurent Pautet Fabrice Kordon
EC-project number: Universal Grid Client: Grid Operation Invoker Tomasz Bartyński 1, Marian Bubak 1,2 Tomasz Gubała 1,3, Maciej Malawski 1,2 1 Academic.
OS and System Software for Ultrascale Architectures – Panel Jeffrey Vetter Oak Ridge National Laboratory Presented to SOS8 13 April 2004 ack.
DIPARTIMENTO DI ELETTRONICA E INFORMAZIONE Novel, Emerging Computing System Technologies Smart Technologies for Effective Reconfiguration: The FASTER approach.
Nature Reviews/2012. Next-Generation Sequencing (NGS): Data Generation NGS will generate more broadly applicable data for various novel functional assays.
Midterm Study Guide COP 4331 and EEL4884 OO Processes for Software Development © Dr. David A. Workman School of EE and Computer Science University of Central.
ProActive components and legacy code Matthieu MOREL.
Architecture View Models A model is a complete, simplified description of a system from a particular perspective or viewpoint. There is no single view.
Visualization in Problem Solving Environments Amit Goel Department of Computer Science Virginia Tech June 14, 1999.
Design Reuse Earlier we have covered the re-usable Architectural Styles as design patterns for High-Level Design. At mid-level and low-level, design patterns.
Visualization Four groups Design pattern for information visualization
SOFTWARE DESIGN AND ARCHITECTURE LECTURE 31. Review Creational Design Patterns – Singleton Pattern – Builder Pattern.
Development of e-Science Application Portal on GAP WeiLong Ueng Academia Sinica Grid Computing
Yazd University, Electrical and Computer Engineering Department Course Title: Advanced Software Engineering By: Mohammad Ali Zare Chahooki The Rational.
Computing Systems: Next Call for Proposals Dr. Panagiotis Tsarchopoulos Computing Systems ICT Programme European Commission.
Joint Polar Satellite System (JPSS) Common Ground System (CGS) Rapid Algorithm Updates Kerry Grant, JPSS CGS Chief Engineer Raytheon Intelligence and Information.
ATLAS Database Access Library Local Area LCG3D Meeting Fermilab, Batavia, USA October 21, 2004 Alexandre Vaniachine (ANL)
INFSO-RI JRA2 Test Management Tools Eva Takacs (4D SOFT) ETICS 2 Final Review Brussels - 11 May 2010.
Origami: Scientific Distributed Workflow in McIDAS-V Maciek Smuga-Otto, Bruce Flynn (also Bob Knuteson, Ray Garcia) SSEC.
By Adam Reimel. Outline Introduction Platform Architecture Future Conclusion.
Basic Concepts of Software Architecture. What is Software Architecture? Definition: – A software system’s architecture is the set of principal design.
INDIGO – DataCloud Security and Authorization in WP5 INFN RIA
Software Architecture Lecture 3
Architecting Web Services
Architecting Web Services
Using the Drupal Content Management Software (CMS) as a framework for OMICS/Imaging-based collaboration.
CMPE419 Mobile Application Development
Software Architecture Lecture 3
Software Architecture Lecture 3
The Vision of Autonomic Computing
Software Architecture Lecture 3
Chapter 7 –Implementation Issues
Software Architecture Lecture 3
Android Platform, Android App Basic Components
Software Architecture Lecture 3
CMPE419 Mobile Application Development
ONAP Architecture Principle Review
Presentation transcript:

Presented by The Harness Workbench: Unified and Adaptive Access to Diverse HPC Platforms Christian Engelmann Computer Science Research Group Computer Science and Mathematics Division Oak Ridge National Laboratory

2 Engelmann_Harness_SC07  The diversity of HPC platforms and associated software complexity often pose challenges that lead to slow or hampered scientific discovery.  Application scientists expend considerable time and effort dealing with development, deployment, and runtime interfacing activities.  Additionally, the short HPC system deployment and upgrade interval requires frequent redeployment of scientific application to different system software stacks. Existing scientific application development and deployment issues

3 Engelmann_Harness_SC07 Research and development goals  Increasing the overall productivity of developing and executing computational codes  Optimizing the development and deployment processes of scientific applications  Simplifying the activities of application scientists, using uniform and adaptive solutions  “Automagically” supporting the diversity of existing and emerging HPC architectures Typical scientific application development, deployment, and execution activities

4 Engelmann_Harness_SC07  Harness Workbench Toolkit  Unified development, deployment, and execution  Common view across diverse HPC platforms  User-space installation and virtual environments  Next-generation runtime environment  Flexible, adaptive, lightweight framework  Management of runtime tasks  Support for diverse HPC platforms Harness workbench core components

5 Engelmann_Harness_SC07 Harness workbench core technologies  Automatic adaptation using pluggable modules  Harness Workbench Toolkit plug-ins  Runtime environment plug-ins  Development environment and toolkit interfaces  Easy-to-use interfaces for scientific application development, deployment, and execution

6 Engelmann_Harness_SC07 Common view across diverse platforms  Various interfaces and bindings to external development and deployment tools and environments  Generalized model for unified access to common development and deployment activities  Mapping of generalized activities onto platform- specific toolkits and runtime environments (RTEs) via pluggable modules

7 Engelmann_Harness_SC07 Harness Workbench Toolkit  Unifying abstraction over heterogeneous HPC resources  Command line and GUI tools  Translation into fine-tuned invocations of native toolkits  Behavior encapsulated in plug-ins  Configurable through profiles  Tunable by end users

8 Engelmann_Harness_SC07  Uniform interface to various front-end systems  Virtualized baseline platform runtime environment capabilities  Advanced runtime environment capabilities via high-level plug-ins Next-generation runtime environment

9 Engelmann_Harness_SC07 Virtualized environments  Virtualized adaptation of system properties to actual application needs  System and runtime environment virtualization  Problem:  Application dependencies may cause conflicts with system-wide installed libraries.  Solution:  Use co-existing, alternative user-space installations.  Approach:  Provide isolated installation environments (“sandboxes”).  These can inherit from one another to build nested hierarchies.

10 Engelmann_Harness_SC07 Configurable “sandboxes” for scientific applications hwb – env install conf 1. Install environment System 1.1 Configure system configuration System configuration 2.1 Start Harness runtime environment Runtime environment 2.2 Configure runtime environment configuration Runtime configuration 2.3 Execute application Application hwb – env start conf application 2. Execute application Scientific application Scientific application Virtualized environment XML configuration description Virtualized environment XML configuration description

11 Engelmann_Harness_SC07 The Harness workbench: Unified and adaptive access to diverse HPC platforms  Virtualized adaptation of system properties to actual application needs  System and runtime environment virtualization

12 Engelmann_Harness_SC07 Contacts Christian Engelmann Computer Science Research Group Computer Science and Mathematics Division (865) Al Geist Oak Ridge National Laboratory (865) Jack Dongarra University of Tennessee (865) Vaidy Sunderam Emory University (404) Englemann_Harness_SC07