COMP Superscalar: Bringing GRID superscalar and GCM together Enric Tejedor Universitat Politècnica de Catalunya V ProActive and GCM.

Slides:



Advertisements
Similar presentations
Programming a service Cloud Rosa M. Badia, Jorge Ejarque, Daniele Lezzi, Raul Sirvent, Enric Tejedor Grid Computing and Clusters Group Barcelona Supercomputing.
Advertisements

Grid Component Model and Platform: An Overview Workshop on Evolutions of GRIDs Towards SOKUs OGF20, Manchester, 8 May 2007 Vladimir Getov CoreGRID STE.
1 (OASIS) INRIAs Interests in Grids: programming Grids OASIS (Objets Actifs, Semantique et Securite) team Others INRIA teams (high perf. Networking, P2P.
User-driven resource selection in GRID superscalar Last developments and future plans in the framework of CoreGRID Rosa M. Badia Grid and Clusters Manager.
European Commission Directorate-General Information Society Unit F2 – Grid Technologies INSERT PROJECT ACRONYM HERE BY EDITING THE MASTER SLIDE (VIEW /
Elton Mathias and Jean Michael Legait 1 Elton Mathias, Jean Michael Legait, Denis Caromel, et al. OASIS Team INRIA -- CNRS - I3S -- Univ. of Nice Sophia-Antipolis,
UPC MICRO35 Istanbul Nov Effective Instruction Scheduling Techniques for an Interleaved Cache Clustered VLIW Processor Enric Gibert 1 Jesús Sánchez.
IDEW06 Barcelona, September 5, Modeling and design of on-chip inter-block decoupling capacitors for PSN and EMI reduction Josep Rius 1 and Maurice.
Kensington Oracle Edition: Open Discovery Workflow Meets Oracle 10g Professor Yike Guo.
U P C CGO’03 San Francisco March 2003 Local Scheduling Techniques for Memory Coherence in a Clustered VLIW Processor with a Distributed Data Cache Enric.
European Commission Directorate-General Information Society Unit F2 – Grid Technologies INSERT PROJECT ACRONYM HERE BY EDITING THE MASTER SLIDE (VIEW.
15 th International Conference on Design Theory and Methodology 2-6 September 2003, Chicago, Illinois Intelligent Agents in Design Zbigniew Skolicki Tomasz.
Presentation title Sophia Antipolis, France juin / 2 – 4 June Authors name.
InfraStruxure for Small IT Spaces Solution Introduction.
WP3 plenary meeting London, Jan 17-18, 2006 Status of the Virtual Institute Marco Danelutto Workpackage leader University of Pisa - Italy.
Session 2: task 3.2 GCM, Kracow, June l Current status of GCM Denis Caromel (10 mn each talk) l Wrapping CCA Components as GCM Components Maciej.
Monitoring OSGi platforms with ProActive Virginie Legrand OASIS Team - INRIA Sophia Antipolis.
Grid programming with components: an advanced COMPonent platform for an effective invisible grid © 2006 GridCOMP Grids Programming with components. An.
A Case Study in Componentising a Scientific Application for the Grid  Nikos Parlavantzas, Matthieu Morel, Françoise Baude, Fabrice Huet, Denis Caromel,
Luis H. Bibiano, Enric Mayol, Joan A. Pastor
Dynamic Runtime Testing for Cycle-Accurate Simulators Saša Tomić, Adrián Cristal, Osman Unsal, Mateo Valero Barcelona Supercomputing Center (BSC) Universitat.
Programming the Cell Multiprocessor Işıl ÖZ. Outline Cell processor – Objectives – Design and architecture Programming the cell – Programming models CellSs.
G RID R ESOURCE BROKER FOR SCHEDULING COMPONENT - BASED APPLICATIONS ON DISTRIBUTED RESOURCES Reporter : Yi-Wei Wu.
© CaaSt Consortium. All rights reserved. The research leading to these results has received funding from the European Union's Seventh Framework Programme.
C# Overview and Features. Content I.History of C# II.Architecture III.How to install IV.Features V.Code Sample VI.Microsoft.NET Platform VII.Why use C#
SOFTWARE DESIGN AND ARCHITECTURE LECTURE 07. Review Architectural Representation – Using UML – Using ADL.
The Grid Component Model: an Overview “Proposal for a Grid Component Model” DPM02 “Basic Features of the Grid Component Model (assessed)” -- DPM04 CoreGrid.
The Grid Component Model and its Implementation in ProActive CoreGrid Network of Excellence, Institute on Programming Models D.PM02 “Proposal for a Grid.
Transparent Grid Enablement Using Transparent Shaping and GRID superscalar I. Description and Motivation II. Background Information: Transparent Shaping.
Leaders in Asset Management Big Plans for your Property System? How to plan for a Property System Project Prepared by: Yudiann Carlo, CPPS
Odyssey A Reuse Environment based on Domain Models Prepared By: Mahmud Gabareen Eliad Cohen.
Workflow Resource Allocation through Auctions Universitat de Girona Albert Plà, Beatriz López, Javier Murillo eXiT 16/7/ AILOG Barcelona Universitat.
XTREEMOS APPLICATION EXECUTION MANAGEMENT: A SCALABLE APPROACH Ramon Nou, Jacobo Giralt, Julita Corbalan, Enric Tejedor, J.Oriol Fitó, Josep M. Perez,
The roots of innovation Future and Emerging Technologies (FET) Future and Emerging Technologies (FET) The roots of innovation Proactive initiative on:
CellSs: A Programming Model for the Cell BE Architecture Pieter Bellens, Josep M. Perez, Rosa M. Badia, Jesus Labarta Barcelona Supercomputing Center (BSC-CNS)
Open Service Gateway Initiative (OSGi) Reporter : 林學灝 侯承育 1.
Presentation on Issues and Challenges in Evaluation of Agent-Oriented Software Engineering Methodologies By: kanika singhal.
Advanced Spectrum Management in Multicell OFDMA Networks enabling Cognitive Radio Usage F. Bernardo, J. Pérez-Romero, O. Sallent, R. Agustí Radio Communications.
Enabling Self-management Of Component Based Distributed Applications Ahmad Al-Shishtawy 1, Joel Höglund 2, Konstantin Popov 2, Nikos Parlavantzas 3, Vladimir.
Asynchronous Components with Futures: Semantics, Specification, and Proofs in a Theorem Prover Components (Distributed) Futures Formalisations (and proofs)
ServiceSs, a new programming model for the Cloud Daniele Lezzi, Rosa M. Badia, Jorge Ejarque, Raul Sirvent, Enric Tejedor Grid Computing and Clusters Group.
 Apache Airavata Architecture Overview Shameera Rathnayaka Graduate Assistant Science Gateways Group Indiana University 07/27/2015.
Grid programming with components: an advanced COMPonent platform for an effective invisible grid © GridCOMP Grids Programming with components.
Reducing Energy Consumption in Human- centric Wireless Sensor Networks The 2012 IEEE International Conference on Systems, Man, and Cybernetics October.
BalticGrid Project Educational Activities of the BalticGrid Project Per Öster KTH, Stockholm Zofia Mosurska CYFRONET, Cracow.
Grid programming with components: an advanced COMPonent platform for an effective invisible grid © 2006 GridCOMP Grids Programming with components. An.
SOFTWARE DESIGN AND ARCHITECTURE LECTURE 13. Review Shared Data Software Architectures – Black board Style architecture.
ProActive components and legacy code Matthieu MOREL.
CSE 303 – Software Design and Architecture
Adaptive Computing on the Grid Using AppLeS Francine Berman, Richard Wolski, Henri Casanova, Walfredo Cirne, Holly Dail, Marcio Faerman, Silvia Figueira,
CoreGRID Workpackage 5 Virtual Institute on Grid Information and Monitoring Services Michał Jankowski, Paweł Wolniewicz, Jiří Denemark, Norbert Meyer,
Light Weight Grid Platform: Design Methodology Vladimir Getov University of Westminster.
MVC WITH CODEIGNITER Presented By Bhanu Priya.
What’s New in Windows Forms 2.0 Stephen Turner Software Design Engineer
VERIFYING THE CORRECT COMPOSITION OF DISTRIBUTED COMPONENTS: FORMALISATION AND TOOL Ludovic Henrio 1, Oleksandra Kulankhina 1,2, Dongqian Liu 3, Eric Madelaine.
1 ProActive GCM – CCA Interoperability Maciej Malawski, Ludovic Henrio, Matthieu Morel, Francoise Baude, Denis Caromel, Marian Bubak Institute of Computer.
1st ACS Workshop UTFSM, Valparaiso, Chile ACS Course The Big Picture of ACS H. Sommer, G.Chiozzi.
Eric MADELAINE -- GridComp -- OASIS 1 E. Madelaine (A. Cansado) GridComp project OASIS team INRIA -- CNRS - I3S -- Univ. of Nice Sophia-Antipolis GridComp.
© Geodise Project, University of Southampton, Workflow Support for Advanced Grid-Enabled Computing Fenglian Xu *, M.
Cloud interoperability and elasticity with COMPSs Federated Cloud F2F Jan , Amsterdam Daniele Lezzi – Barcelona Supercomputing Center.
University of California Cloud Computing Task Force Russ Hobby.
Context-Aware Middleware for Resource Management in the Wireless Internet US Lab 신현정.
New initiatives at ETSI Ultan Mulligan Director, Strategy & New Initiatives, ETSI © ETSI All rights reserved The infinity Initiative Fusing Research.
Behavioural Models for Distributed Hierarchical Components
Componentising and Deploying a Scientific Application on the Grid
Enabling Self-management Of Component Based Distributed Applications
What is Robotic Process Automation ? By Sumit Seth.
A short governmental view on standards and interoperability
Improving Cache Management Policies Using Dynamic Reuse Distances
The Grid Component Model and its Implementation in ProActive
Presentation transcript:

COMP Superscalar: Bringing GRID superscalar and GCM together Enric Tejedor Universitat Politècnica de Catalunya V ProActive and GCM User Group, GridCOMP conference October 21, INRIA, Sophia Antipolis, France Rosa M. Badia Barcelona Supercomputing Center

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Outline Introduction Grid Component Model GRID superscalar Programming model Runtime operation Initialisation Task processing Finalisation and error handling Conclusions

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) 1. Introduction

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Basic concepts The Grid Component Model (GCM) CoreGRID NoE, GridCOMP Distributed, based on Fractal, intended for the Grid GRID superscalar Framework to ease the development of Grid-unaware applications Simple programming model: Grid as transparent as possible Runtime that optimises the performance of the application (exploiting possible concurrency)

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) A componentised Grid framework GRID superscalar is suitable to benefit from the GCM features Componentisation process: identify the inner functionalities of the runtime, and assign each one to a separate component Result: COMP Superscalar, whose runtime gains in: Reusability Flexibility Deployability Separation of concerns Ease of development

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Componentised runtime

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) 2. Programming model

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France)... for (i=0; i<N; i++){ T1 (data1, data2); T2 (data4, data5); T3 (data2, data5, data6); T4 (data7, data8); T5 (data6, data8, data9); }... Sequential Application T1 0 T2 0 T3 0 T4 0 T5 0 T1 1 T2 1 T3 1 T4 1 T5 1 T1 2 … Resource 1 Resource 2 Resource 3 Resource N Task graph creation based on data precedence Task selection + parameters direction (input, output, inout)‏ Scheduling, data transfer, task execution Synchronization, results transfer Parallel Resources (multicore,SMP, cluster, grid)‏ Programming model

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) initialize(f1); for (int i = 0; i < 2; i++) { genRandom(f2); add(f1, f2); } print(f2); Java application COMPSs programming model public interface = "Linux") void = Type.FILE, direction = Direction.OUT) String f } Task constraints Parameter metadata Implementation Java interface

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Usage example: original code initialize(f1); for (int i = 0; i < 2; i++) { genRandom(f2); add(f1, f2); } print(f1);

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) PM steps (1): selecting the tasks public interface = "Linux") void = Type.FILE, direction = Direction.OUT) String = "Intel", processorSpeed = 1.8f) void = Type.FILE, direction = Direction.INOUT) String = Type.FILE, direction = Direction.IN) String f2 ); } Task constraints Parameter metadata Implementation

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) PM steps (2a): using API calls initialize(f1); COMPSs css = new COMPSsImpl(); css.start(); for (int i = 0; i < 2; i++) { genRandom(f2); add(f1, f2); } String resF2 = css.openFile(f2, OpenMode.READ); print(resF2); css.stop(true);

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) PM steps(2b): no changes! initialize(f1); for (int i = 0; i < 2; i++) { genRandom(f2); add(f1, f2); } print(f1);

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Custom Java Class Loader Java app code COMPSs runtime Annotated interface Javassist inserts calls to Custom Loader uses input

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) 3. Runtime operation

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Implementation details Base technologies: Java as programming language ProActive: implementation of the GCM model, used to build the components JavaGAT: used for job submission and file transfer

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Initialization Multicast invocation Forwarded to all subcomponents TATS JM FM FIPFTM init()

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Initialization Multicast invocation Reduction of return values TATS JM FM FIPFTM Reduction

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (1) Application submits task Task Analyser receives the request TATSJM FM FIPFTM executeTask(…) T1 genRd T3 genRd T2 add T4 add f1 f2

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (2) TA JM FM FIPFTM TS File Information Provider is contacted File accesses of the task are registered executeTask(…)

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (3) Task Analyser discovers dependencies Dependency-free tasks are sent for scheduling TATSJM FM FIPFTM executeTask(…)

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (4) Task Scheduler decides where to execute tasks Job Manager is informed of this decision TA TSJM FM FIPFTM executeTask(…) Scheduling algorithm Resource capabilitie s Task constraints

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (5) Job Manager checks the necessary file transfers File Transfer Manager actually performs them TATSJM FM FIPFTM executeTask(…) GAT

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (6) FTM informs of the end of transfers for a task Task Grid job, submitted for execution TATSJM FM FIPFTM executeTask(…) GAT

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Task processing (7) Callback for the end of a job is received The notification is forwarded to the Task Analyser TATSJM FM FIPFTM executeTask(…) GAT

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Opening a file JM FM FIPFTM TSTA Java Application … String ren = openFile(f); print(ren); … APIAPI Local host Remote host f10v6.IT

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Error handling The COMPSs runtime could experience errors of different kinds (e.g. a job submission failure) Default response to an error: stopping the components But a structure of components cannot be stopped in any arbitrary order! C A LCC stopFc() B stopFc on B is never served!

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Safe stopping process for the runtime COMPSs subcomponents have data dependencies Modification of the Life Cycle Controller Components stopped in a safe order: T S, T A, JM, FTM, FIP Otherwise, a deadlock could happen TA TSJM FM FIP FTM LCC

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) 4. Conclusions

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Conclusions COMP Superscalar: componentised version of GRID superscalar GCM-based Hierarchical runtime: separation of concerns Task scheduling, file and resource management Straightforward programming model for Grid-unaware Java applications Feedback about GCM-ProActive Component distribution Performance: no noticeable overhead for a medium number of tasks Component composition and dynamic reconfiguration: Grid IDE

V ProActive and GCM User Group. October 21 st 2008, Sophia Antipolis (France) Thank you! Questions?