Introduction to Lab Series DMS & MPI

Size: px
Start display at page:

Download "Introduction to Lab Series DMS & MPI"

Transcription

1 TDDC 78 Labs: Memory-based Taxonomy Introduction to Lab Series DMS & Mikhail Chalabine Linköping University Memory Lab(s) Use Distributed 1 Shared 2 3 Posix threads OpenMP Distributed LAB 5 (tools) at every stage. Saves your time. TDDC 78 Labs: Memory-based Taxonomy TDDC 78 Labs: Memory-based Taxonomy Memory Lab(s) Use Distributed 1 Memory Lab(s) Use Distributed 1 Shared 2 3 Posix threads OpenMP Shared 2 3 Posix threads OpenMP Distributed 4 Distributed 4 LAB 5 (tools) at every stage. Save your time. LAB 5 (tools) at every stage. Save your time.

2 Shared- and Distributed-memory systems Programming parallelism (typical problems) Approach and solve Partitioning Domain decomposition Functional decomposition Communication Agglomeration Mapping Load balancing Goals Your primary source of information Comprehensive Environment description Lab specification Step-by-step instructions Compendium intro (1) Message Passing Interface () a standard for programming parallel processors under the message-passing paradigm Processors exchange messages Point-to-point and collective communication Low-level (explicit) programming of parallelism Efficient but complex error-prone implementation Communication details Processor topologies Portable and language independent Widely used in practice Accepted by industry Available on virtually all platforms mpirun -np <nn> <program> <args> Structure ierr = _Init( argc, argv); Intro (2) _Comm_size( _COMM_WORLD, &nproc); _Comm_rank( _COMM_WORLD, &iproc); // Program code printf( Hello from proc %d\n, iproc); _Finalize();

3 Learn about Lab-1 TDDC78: Image Filters with Define types / Receive Broadcast Scatter / Gather Use virtual topologies _Issend / _Probe / _Reduce ing larger pieces of data Synchronize / _Barrier LAB-1 LAB-4 Blur & Threshold See compendium for details Your goal is to understand:! Define types! / Receive! Broadcast! Scatter / Gather For syntax and examples refer to the lecture slides and examples below! Decompose domains! Apply filter in parallel typedef struct {! int id;! double data[10]; } buf_t; // Composite type buf_t item; // Element of the type _Datatype buf_t_mpi; // type to commit int block_lengths [] = { 1, 10}; // Lengths of type elements _Datatype block_types [] = { _INT, _DOUBLE}; // Set types _Aint start, displ[2]; _Address( &item, &start ); _Address( &item.id, &displ[0] ); _Address( &item.data[0], &displ[1] ); Types Example displ[0] -= start; // Displacement relative to address of start displ[1] -= start; // Displacement relative to address of start _Type_struct( 2, block_lengths, displ, block_types, &buf_t_mpi ); _Type_commit( &buf_t_mpi ); message_t message = create_message( my_id ); -Receive _( &message, sizeof( message_t ), _BYTE,! (my_id == 0)?1:0, 0, _COMM_WORLD ); _Status status; _Recv( &message, sizeof( message_t ), _BYTE, (my_id == 0)?1:0, 0, _COMM_WORLD, &status );

4 -Receive Modes (1) SEND BLOCKING NON-BLOCKING Standard Isend Synchronous _Ssend _Issend Buffered _Bsend _Ibsend Ready _Rsend _Irsend RECEIVE BLOCKING NON-BLOCKING _Recv _Irecv -Receive Modes (2) Blocking send Returns after message safely stored away Free to access and overwrite send buffer May copy message into Matching receive buffer, or Temporary system buffer Can complete as soon as message buffered Receive May complete before send completes May complete only after send started Message buffering Decouples send and receive Can be expensive Additional memory-to-memory copying [ ORG ] -Receive Modes (3) Standard mode decides whether outgoing messages are buffered may buffer outgoing messages may complete before a matching receive posted Obs! Buffer space may be unavailable may choose not to buffer for performance will not complete until a matching receive posted Makes implementation run-system implementation dependent Starts whether or not a matching receive posted Is non-local Completion may depend on occurrence of a matching receive Core rational Correct programs do not rely on buffering in standard mode -Receive Modes (4) Buffered mode buffers sent messages Starts whether or not a matching receive posted May complete before a matching receive posted s messages in a non-blocking mode Unlike the standard mode Local completion independent of a matching receive If no matching receive posted must buffer Error if insufficient buffer space Buffering may improve performance but not affect the result [ ORG ]

5 -Receive Modes (5) Synchronous mode Synchronous communication semantics (non-local) If both send and receive blocking Communication completes at both ends only after both processes rendezvous at communication Control flow er sends a request to send Receiver permits when matching receive posted Starts whether or not a matching receive posted Completes if Matching receive posted Receive operation began executing Completion indicates buffer can be reused Receiver reached a certain ctrl. point exec matching receive -Receive Modes (6) Ready mode Message sent as soon as possible Same semantics as Standard send operation, or Synchronous send operation er provides additional info to the system namely that a matching receive is already posted), that Saves overhead In a correct program can be replaced by a standard send On some systems Removes the need of a hand-shake operation Improved performance. Starts only if matching receive is posted Otherwise erroneous and outcome undefined Completion independent of matching receive Merely indicates that send buffer can be reused SR Modes: sense the difference (1) SR Modes: sense the difference (2) message_t message = create_message(iproc); _Request request; _Isend( &message, sizeof(message_t), _BYTE,!!! (iproc == 0)?1:0, 0, _COMM_WORLD,!!! &request); // Non-blocking send _Status status; _Recv( &message, sizeof(message_t), _BYTE,!!! (iproc == 0)?1:0, 0, _COMM_WORLD,!!! &status); // Receive // Synchronize sender & receiver _Wait( &request, &status); Non-blocking SEND: returns even if the message data have not been safely stored away, i.e., it is neither buffered nor read. message_t message = create_message(iproc); _Status status; _Irecv( &message, sizeof( message_t), _BYTE,!!! (iproc == 0)?1:0, 0, _COMM_WORLD,!!! &status); // Non-blocking receive _( &message, sizeof( message_t), _BYTE,!!! (iproc == 0)?1:0, 0, _COMM_WORLD); //

6 Typical Master-Slave (1) Typical Master-Slave (2) // The root sends jobs (synchronous mode) task_t task[nproc-1]; _Request request[nproc-1]; for(int i=1; i < nproc; i++) {! _Issend( &(task[i-1], sizeof( task_t), _BYTE,!!! i, 0, _COMM_WORLD,&request); } _Status status[nproc-1]; _Waitall( nproc-1, request, status); // Each CPU receives data to process result_t result[nproc-1]; for(int j=1; j < nproc; j++){! _Status rstat;! _Probe( _ANY_SOURCE, 0, _COMM_WORLD, &rstat);! int from = rstat._source;! int data_size;! _Get_count( &rstat, _DOUBLE, &data_size);! result[from-1].buf = new double[data_size];! _Recv( result[from-1].buf, data_size, _DOUBLE, from, 0, _COMM_WORLD, &status); } Collective Communication (CC) CC: Scatter & Gather // One processor _(&message, sizeof(message_t), ); // All the others _Recv(&message,sizeof(message_t), ); All processors: _Bcast(message, sizeof(message_t), _BYTE, 0, _COMM_WORLD );! Distributing (unevenly sized) chunks of data sendbuf = (int *) malloc( nproc * stride * sizeof(int)); displs = (int *) malloc( nproc * sizeof( int)); scounts = (int *) malloc( nproc * sizeof( int)); for (i = 0; i < nproc; ++i) { displs[i] = scounts[i] = } _Scatterv( sendbuf, scounts, displs, _INT,!! rbuf, 100, _INT, root, comm);

7 ! Define types! / Receive! Broadcast! Scatter / Gather! Use virtual topologies Learn about LAB-1! _Issend / _Probe / _Reduce LAB-4! ing larger pieces of data! Synchronize / _Barrier Moving particles Validate the pressure law Lab-4: Particles Dynamic interaction patterns # of particles that fly across borders is not static You need advanced domain decomposition Motivate your choice! Process Topologies (0)! By default processors are arranged into 1- dimensional arrays! Processor ranks are computed accordingly What if processors need to communicate in 2 dimensions or more?! Use virtual topologies achieving 2D instead of 1D arrangement of processors with convenient ranking schemes int dims[2]; dims[0]= 2; dims[1]= 3; Process Topologies (1) // 2D matrix / grid // 2 rows // 3 columns _Dims_create( nproc, 2, dims); int periods[2]; periods[0]= 1; periods[1]= 0; int reorder = 1; _Comm grid_comm; // Row-periodic // Column-non-periodic // Re-oder allowed _Cart_create( _COMM_WORLD, 2, dims, periods,! reorder, &grid_comm);

8 int my_coords[2]; int my_rank; int right_nbr[2]; int right_nbr_rank; // Cartesian Process coordinates // Process rank _Cart_get( grid_comm, 2,!! dims, periods, my_coords); _Cart_rank( grid_comm, my_coords, &my_rank); right_nbr[0] = my_coords[0]+1; right_nbr[1] = my_coords[1]; Process Topologies (2) _Cart_rank( grid_comm, right_nbr,!!! & right_nbr_rank); Learning goals Point-to-point communication Probing / Non-blocking send (choose) Barriers & Wait = Synchronization Derived data types Collective communications Virtual topologies /Receive modes Use with care to keep your code portable It works there but not here! Summary Labs at home? No problem Simple to install Simple to use

Introduction to TDDC78 Lab Series. Lu Li Linköping University Parts of Slides developed by Usman Dastgeer

Introduction to TDDC78 Lab Series. Lu Li Linköping University Parts of Slides developed by Usman Dastgeer Introduction to TDDC78 Lab Series Lu Li Linköping University Parts of Slides developed by Usman Dastgeer Goals Shared- and Distributed-memory systems Programming parallelism (typical problems) Goals Shared-

More information

Introduction to MPI, the Message Passing Library

Introduction to MPI, the Message Passing Library Chapter 3, p. 1/57 Basics of Basic Messages -To-? Introduction to, the Message Passing Library School of Engineering Sciences Computations for Large-Scale Problems I Chapter 3, p. 2/57 Outline Basics of

More information

Advanced Message-Passing Interface (MPI)

Advanced Message-Passing Interface (MPI) Outline of the workshop 2 Advanced Message-Passing Interface (MPI) Bart Oldeman, Calcul Québec McGill HPC Bart.Oldeman@mcgill.ca Morning: Advanced MPI Revision More on Collectives More on Point-to-Point

More information

Parallel Programming

Parallel Programming Parallel Programming for Multicore and Cluster Systems von Thomas Rauber, Gudula Rünger 1. Auflage Parallel Programming Rauber / Rünger schnell und portofrei erhältlich bei beck-shop.de DIE FACHBUCHHANDLUNG

More information

Welcome to the introductory workshop in MPI programming at UNICC

Welcome to the introductory workshop in MPI programming at UNICC Welcome...... to the introductory workshop in MPI programming at UNICC Schedule: 08.00-12.00 Hard work and a short coffee break Scope of the workshop: We will go through the basics of MPI-programming and

More information

Message Passing Interface: Basic Course

Message Passing Interface: Basic Course Overview of DM- HPC2N, UmeåUniversity, 901 87, Sweden. April 23, 2015 Table of contents Overview of DM- 1 Overview of DM- Parallelism Importance Partitioning Data Distributed Memory Working on Abisko 2

More information

Topic Notes: Message Passing Interface (MPI)

Topic Notes: Message Passing Interface (MPI) Computer Science 400 Parallel Processing Siena College Fall 2008 Topic Notes: Message Passing Interface (MPI) The Message Passing Interface (MPI) was created by a standards committee in the early 1990

More information

Review of MPI Part 2

Review of MPI Part 2 Review of MPI Part Russian-German School on High Performance Computer Systems, June, 7 th until July, 6 th 005, Novosibirsk 3. Day, 9 th of June, 005 HLRS, University of Stuttgart Slide Chap. 5 Virtual

More information

Optimization of MPI Applications Rolf Rabenseifner

Optimization of MPI Applications Rolf Rabenseifner Optimization of MPI Applications Rolf Rabenseifner University of Stuttgart High-Performance Computing-Center Stuttgart (HLRS) www.hlrs.de Optimization of MPI Applications Slide 1 Optimization and Standardization

More information

Practical Introduction to Message-Passing Interface (MPI)

Practical Introduction to Message-Passing Interface (MPI) 1 Outline of the workshop 2 Practical Introduction to Message-Passing Interface (MPI) Bart Oldeman, Calcul Québec McGill HPC Bart.Oldeman@mcgill.ca Theoretical / practical introduction Parallelizing your

More information

Intermediate MPI features

Intermediate MPI features Intermediate MPI features Advanced message passing Collective communication Topologies Group communication Forms of message passing (1) Communication modes: Standard: system decides whether message is

More information

A few words about MPI (Message Passing Interface) T. Edwald 10 June 2008

A few words about MPI (Message Passing Interface) T. Edwald 10 June 2008 A few words about MPI (Message Passing Interface) T. Edwald 10 June 2008 1 Overview Introduction and very short historical review MPI - as simple as it comes Communications Process Topologies (I have no

More information

Practical Scientific Computing: Performanceoptimized

Practical Scientific Computing: Performanceoptimized Practical Scientific Computing: Performanceoptimized Programming Advanced MPI Programming December 13, 2006 Dr. Ralf-Peter Mundani Department of Computer Science Chair V Technische Universität München,

More information

Parallel Computing Paradigms

Parallel Computing Paradigms Parallel Computing Paradigms Message Passing João Luís Ferreira Sobral Departamento do Informática Universidade do Minho 31 October 2017 Communication paradigms for distributed memory Message passing is

More information

Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI

Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI Agenda 1) MPI für Java Installation OK? 2) 2. Übungszettel Grundidee klar? 3) Projektpräferenzen? 4) Nächste Woche: 3. Übungszettel,

More information

Parallel Computing MPI. Christoph Beetz. September 7, Parallel Computing. Introduction. Parallel Computing

Parallel Computing MPI. Christoph Beetz. September 7, Parallel Computing. Introduction. Parallel Computing Christoph Beetz Theoretical Physics I, Ruhr-Universität Bochum September 7, 2010 What is Basic Overview to code What is Basic Why Calculation is too big to fit in memory of one machine domain on several

More information

Distributed Memory Parallel Programming

Distributed Memory Parallel Programming COSC Big Data Analytics Parallel Programming using MPI Edgar Gabriel Spring 201 Distributed Memory Parallel Programming Vast majority of clusters are homogeneous Necessitated by the complexity of maintaining

More information

HPC Parallel Programing Multi-node Computation with MPI - I

HPC Parallel Programing Multi-node Computation with MPI - I HPC Parallel Programing Multi-node Computation with MPI - I Parallelization and Optimization Group TATA Consultancy Services, Sahyadri Park Pune, India TCS all rights reserved April 29, 2013 Copyright

More information

Cluster Computing MPI. Industrial Standard Message Passing

Cluster Computing MPI. Industrial Standard Message Passing MPI Industrial Standard Message Passing MPI Features Industrial Standard Highly portable Widely available SPMD programming model Synchronous execution MPI Outer scope int MPI_Init( int *argc, char ** argv)

More information

Lecture 7: More about MPI programming. Lecture 7: More about MPI programming p. 1

Lecture 7: More about MPI programming. Lecture 7: More about MPI programming p. 1 Lecture 7: More about MPI programming Lecture 7: More about MPI programming p. 1 Some recaps (1) One way of categorizing parallel computers is by looking at the memory configuration: In shared-memory systems

More information

. Programming Distributed Memory Machines in MPI and UPC. Kenjiro Taura. University of Tokyo

. Programming Distributed Memory Machines in MPI and UPC. Kenjiro Taura. University of Tokyo .. Programming Distributed Memory Machines in MPI and UPC Kenjiro Taura University of Tokyo 1 / 57 Distributed memory machines chip (socket, node, CPU) (physical) core hardware thread (virtual core, CPU)

More information

More Communication (cont d)

More Communication (cont d) Data types and the use of communicators can simplify parallel program development and improve code readability Sometimes, however, simply treating the processors as an unstructured collection is less than

More information

MPI Message Passing Interface

MPI Message Passing Interface MPI Message Passing Interface Portable Parallel Programs Parallel Computing A problem is broken down into tasks, performed by separate workers or processes Processes interact by exchanging information

More information

Introduction to MPI. May 20, Daniel J. Bodony Department of Aerospace Engineering University of Illinois at Urbana-Champaign

Introduction to MPI. May 20, Daniel J. Bodony Department of Aerospace Engineering University of Illinois at Urbana-Champaign Introduction to MPI May 20, 2013 Daniel J. Bodony Department of Aerospace Engineering University of Illinois at Urbana-Champaign Top500.org PERFORMANCE DEVELOPMENT 1 Eflop/s 162 Pflop/s PROJECTED 100 Pflop/s

More information

Part - II. Message Passing Interface. Dheeraj Bhardwaj

Part - II. Message Passing Interface. Dheeraj Bhardwaj Part - II Dheeraj Bhardwaj Department of Computer Science & Engineering Indian Institute of Technology, Delhi 110016 India http://www.cse.iitd.ac.in/~dheerajb 1 Outlines Basics of MPI How to compile and

More information

Collective Communication: Gatherv. MPI v Operations. root

Collective Communication: Gatherv. MPI v Operations. root Collective Communication: Gather MPI v Operations A Gather operation has data from all processes collected, or gathered, at a central process, referred to as the root Even the root process contributes

More information

Acknowledgments. Programming with MPI Basic send and receive. A Minimal MPI Program (C) Contents. Type to enter text

Acknowledgments. Programming with MPI Basic send and receive. A Minimal MPI Program (C) Contents. Type to enter text Acknowledgments Programming with MPI Basic send and receive Jan Thorbecke Type to enter text This course is partly based on the MPI course developed by Rolf Rabenseifner at the High-Performance Computing-Center

More information

Programming with MPI Basic send and receive

Programming with MPI Basic send and receive Programming with MPI Basic send and receive Jan Thorbecke Type to enter text Delft University of Technology Challenge the future Acknowledgments This course is partly based on the MPI course developed

More information

Parallel programming MPI

Parallel programming MPI Parallel programming MPI Distributed memory Each unit has its own memory space If a unit needs data in some other memory space, explicit communication (often through network) is required Point-to-point

More information

A Message Passing Standard for MPP and Workstations

A Message Passing Standard for MPP and Workstations A Message Passing Standard for MPP and Workstations Communications of the ACM, July 1996 J.J. Dongarra, S.W. Otto, M. Snir, and D.W. Walker Message Passing Interface (MPI) Message passing library Can be

More information

Copyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 8

Copyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 8 Chapter 8 Matrix-vector Multiplication Chapter Objectives Review matrix-vector multiplicaiton Propose replication of vectors Develop three parallel programs, each based on a different data decomposition

More information

The MPI Message-passing Standard Lab Time Hands-on. SPD Course Massimo Coppola

The MPI Message-passing Standard Lab Time Hands-on. SPD Course Massimo Coppola The MPI Message-passing Standard Lab Time Hands-on SPD Course 2016-2017 Massimo Coppola Remember! Simplest programs do not need much beyond Send and Recv, still... Each process lives in a separate memory

More information

More about MPI programming. More about MPI programming p. 1

More about MPI programming. More about MPI programming p. 1 More about MPI programming More about MPI programming p. 1 Some recaps (1) One way of categorizing parallel computers is by looking at the memory configuration: In shared-memory systems, the CPUs share

More information

Collective Communication: Gather. MPI - v Operations. Collective Communication: Gather. MPI_Gather. root WORKS A OK

Collective Communication: Gather. MPI - v Operations. Collective Communication: Gather. MPI_Gather. root WORKS A OK Collective Communication: Gather MPI - v Operations A Gather operation has data from all processes collected, or gathered, at a central process, referred to as the root Even the root process contributes

More information

Standard MPI - Message Passing Interface

Standard MPI - Message Passing Interface c Ewa Szynkiewicz, 2007 1 Standard MPI - Message Passing Interface The message-passing paradigm is one of the oldest and most widely used approaches for programming parallel machines, especially those

More information

Agenda. MPI Application Example. Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI. 1) Recap: MPI. 2) 2.

Agenda. MPI Application Example. Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI. 1) Recap: MPI. 2) 2. Praktikum: Verteiltes Rechnen und Parallelprogrammierung Introduction to MPI Agenda 1) Recap: MPI 2) 2. Übungszettel 3) Projektpräferenzen? 4) Nächste Woche: 3. Übungszettel, Projektauswahl, Konzepte 5)

More information

MPI - v Operations. Collective Communication: Gather

MPI - v Operations. Collective Communication: Gather MPI - v Operations Based on notes by Dr. David Cronk Innovative Computing Lab University of Tennessee Cluster Computing 1 Collective Communication: Gather A Gather operation has data from all processes

More information

High Performance Computing

High Performance Computing High Performance Computing Course Notes 2009-2010 2010 Message Passing Programming II 1 Communications Point-to-point communications: involving exact two processes, one sender and one receiver For example,

More information

Masterpraktikum - Scientific Computing, High Performance Computing

Masterpraktikum - Scientific Computing, High Performance Computing Masterpraktikum - Scientific Computing, High Performance Computing Message Passing Interface (MPI) Thomas Auckenthaler Wolfgang Eckhardt Technische Universität München, Germany Outline Hello World P2P

More information

Collective Communication in MPI and Advanced Features

Collective Communication in MPI and Advanced Features Collective Communication in MPI and Advanced Features Pacheco s book. Chapter 3 T. Yang, CS240A. Part of slides from the text book, CS267 K. Yelick from UC Berkeley and B. Gropp, ANL Outline Collective

More information

30 Nov Dec Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy

30 Nov Dec Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy Why serial is not enough Computing architectures Parallel paradigms Message Passing Interface How

More information

ECE 574 Cluster Computing Lecture 13

ECE 574 Cluster Computing Lecture 13 ECE 574 Cluster Computing Lecture 13 Vince Weaver http://web.eece.maine.edu/~vweaver vincent.weaver@maine.edu 21 March 2017 Announcements HW#5 Finally Graded Had right idea, but often result not an *exact*

More information

CDP. MPI Derived Data Types and Collective Communication

CDP. MPI Derived Data Types and Collective Communication CDP MPI Derived Data Types and Collective Communication Why Derived Data Types? Elements in an MPI message are of the same type. Complex data, requires two separate messages. Bad example: typedef struct

More information

Outline. Communication modes MPI Message Passing Interface Standard. Khoa Coâng Ngheä Thoâng Tin Ñaïi Hoïc Baùch Khoa Tp.HCM

Outline. Communication modes MPI Message Passing Interface Standard. Khoa Coâng Ngheä Thoâng Tin Ñaïi Hoïc Baùch Khoa Tp.HCM THOAI NAM Outline Communication modes MPI Message Passing Interface Standard TERMs (1) Blocking If return from the procedure indicates the user is allowed to reuse resources specified in the call Non-blocking

More information

Message-Passing Computing

Message-Passing Computing Chapter 2 Slide 41þþ Message-Passing Computing Slide 42þþ Basics of Message-Passing Programming using userlevel message passing libraries Two primary mechanisms needed: 1. A method of creating separate

More information

Parallel Programming in C with MPI and OpenMP

Parallel Programming in C with MPI and OpenMP Parallel Programming in C with MPI and OpenMP Michael J. Quinn Chapter 8 Matrix-vector Multiplication Chapter Objectives Review matrix-vector multiplication Propose replication of vectors Develop three

More information

Parallel Programming

Parallel Programming Parallel Programming Point-to-point communication Prof. Paolo Bientinesi pauldj@aices.rwth-aachen.de WS 18/19 Scenario Process P i owns matrix A i, with i = 0,..., p 1. Objective { Even(i) : compute Ti

More information

Introduction to MPI part II. Fabio AFFINITO

Introduction to MPI part II. Fabio AFFINITO Introduction to MPI part II Fabio AFFINITO (f.affinito@cineca.it) Collective communications Communications involving a group of processes. They are called by all the ranks involved in a communicator (or

More information

mpi4py HPC Python R. Todd Evans January 23, 2015

mpi4py HPC Python R. Todd Evans January 23, 2015 mpi4py HPC Python R. Todd Evans rtevans@tacc.utexas.edu January 23, 2015 What is MPI Message Passing Interface Most useful on distributed memory machines Many implementations, interfaces in C/C++/Fortran

More information

Masterpraktikum - Scientific Computing, High Performance Computing

Masterpraktikum - Scientific Computing, High Performance Computing Masterpraktikum - Scientific Computing, High Performance Computing Message Passing Interface (MPI) and CG-method Michael Bader Alexander Heinecke Technische Universität München, Germany Outline MPI Hello

More information

Parallel Computing and the MPI environment

Parallel Computing and the MPI environment Parallel Computing and the MPI environment Claudio Chiaruttini Dipartimento di Matematica e Informatica Centro Interdipartimentale per le Scienze Computazionali (CISC) Università di Trieste http://www.dmi.units.it/~chiarutt/didattica/parallela

More information

Programming with Message Passing PART I: Basics. HPC Fall 2012 Prof. Robert van Engelen

Programming with Message Passing PART I: Basics. HPC Fall 2012 Prof. Robert van Engelen Programming with Message Passing PART I: Basics HPC Fall 2012 Prof. Robert van Engelen Overview Communicating processes MPMD and SPMD Point-to-point communications Send and receive Synchronous, blocking,

More information

Distributed Memory Programming with Message-Passing

Distributed Memory Programming with Message-Passing Distributed Memory Programming with Message-Passing Pacheco s book Chapter 3 T. Yang, CS240A Part of slides from the text book and B. Gropp Outline An overview of MPI programming Six MPI functions and

More information

MMPI: Asynchronous Message Management for the. Message-Passing Interface. Harold Carter Edwards. The University of Texas at Austin

MMPI: Asynchronous Message Management for the. Message-Passing Interface. Harold Carter Edwards. The University of Texas at Austin MMPI: Asynchronous Message Management for the Message-Passing Interface Harold Carter Edwards Texas Institute for Computational and Applied Mathematics The University of Texas at Austin Austin, Texas,

More information

High Performance Computing Course Notes Message Passing Programming I

High Performance Computing Course Notes Message Passing Programming I High Performance Computing Course Notes 2008-2009 2009 Message Passing Programming I Message Passing Programming Message Passing is the most widely used parallel programming model Message passing works

More information

Chapter 8 Matrix-Vector Multiplication

Chapter 8 Matrix-Vector Multiplication Chapter 8 Matrix-Vector Multiplication We can't solve problems by using the same kind of thinking we used when we created them. - Albert Einstein 8. Introduction The purpose of this chapter is two-fold:

More information

MPI: Parallel Programming for Extreme Machines. Si Hammond, High Performance Systems Group

MPI: Parallel Programming for Extreme Machines. Si Hammond, High Performance Systems Group MPI: Parallel Programming for Extreme Machines Si Hammond, High Performance Systems Group Quick Introduction Si Hammond, (sdh@dcs.warwick.ac.uk) WPRF/PhD Research student, High Performance Systems Group,

More information

Outline. Communication modes MPI Message Passing Interface Standard

Outline. Communication modes MPI Message Passing Interface Standard MPI THOAI NAM Outline Communication modes MPI Message Passing Interface Standard TERMs (1) Blocking If return from the procedure indicates the user is allowed to reuse resources specified in the call Non-blocking

More information

Programming with MPI Collectives

Programming with MPI Collectives Programming with MPI Collectives Jan Thorbecke Type to enter text Delft University of Technology Challenge the future Collectives Classes Communication types exercise: BroadcastBarrier Gather Scatter exercise:

More information

Hybrid MPI/OpenMP parallelization. Recall: MPI uses processes for parallelism. Each process has its own, separate address space.

Hybrid MPI/OpenMP parallelization. Recall: MPI uses processes for parallelism. Each process has its own, separate address space. Hybrid MPI/OpenMP parallelization Recall: MPI uses processes for parallelism. Each process has its own, separate address space. Thread parallelism (such as OpenMP or Pthreads) can provide additional parallelism

More information

CS4961 Parallel Programming. Lecture 18: Introduction to Message Passing 11/3/10. Final Project Purpose: Mary Hall November 2, 2010.

CS4961 Parallel Programming. Lecture 18: Introduction to Message Passing 11/3/10. Final Project Purpose: Mary Hall November 2, 2010. Parallel Programming Lecture 18: Introduction to Message Passing Mary Hall November 2, 2010 Final Project Purpose: - A chance to dig in deeper into a parallel programming model and explore concepts. -

More information

Matrix-vector Multiplication

Matrix-vector Multiplication Matrix-vector Multiplication Review matrix-vector multiplication Propose replication of vectors Develop three parallel programs, each based on a different data decomposition Outline Sequential algorithm

More information

Slides prepared by : Farzana Rahman 1

Slides prepared by : Farzana Rahman 1 Introduction to MPI 1 Background on MPI MPI - Message Passing Interface Library standard defined by a committee of vendors, implementers, and parallel programmers Used to create parallel programs based

More information

Introduction to Parallel Programming with MPI

Introduction to Parallel Programming with MPI Introduction to Parallel Programming with MPI PICASso Tutorial October 25-26, 2006 Stéphane Ethier (ethier@pppl.gov) Computational Plasma Physics Group Princeton Plasma Physics Lab Why Parallel Computing?

More information

EE/CSCI 451: Parallel and Distributed Computation

EE/CSCI 451: Parallel and Distributed Computation EE/CSCI 451: Parallel and Distributed Computation Lecture #15 3/7/2017 Xuehai Qian Xuehai.qian@usc.edu http://alchem.usc.edu/portal/xuehaiq.html University of Southern California 1 From last class Outline

More information

An Introduction to MPI

An Introduction to MPI An Introduction to MPI Parallel Programming with the Message Passing Interface William Gropp Ewing Lusk Argonne National Laboratory 1 Outline Background The message-passing model Origins of MPI and current

More information

MPI: the Message Passing Interface

MPI: the Message Passing Interface 15 Parallel Programming with MPI Lab Objective: In the world of parallel computing, MPI is the most widespread and standardized message passing library. As such, it is used in the majority of parallel

More information

Message Passing Interface

Message Passing Interface MPSoC Architectures MPI Alberto Bosio, Associate Professor UM Microelectronic Departement bosio@lirmm.fr Message Passing Interface API for distributed-memory programming parallel code that runs across

More information

The Message Passing Interface (MPI) TMA4280 Introduction to Supercomputing

The Message Passing Interface (MPI) TMA4280 Introduction to Supercomputing The Message Passing Interface (MPI) TMA4280 Introduction to Supercomputing NTNU, IMF January 16. 2017 1 Parallelism Decompose the execution into several tasks according to the work to be done: Function/Task

More information

MPI Collective communication

MPI Collective communication MPI Collective communication CPS343 Parallel and High Performance Computing Spring 2018 CPS343 (Parallel and HPC) MPI Collective communication Spring 2018 1 / 43 Outline 1 MPI Collective communication

More information

MPI and OpenMP (Lecture 25, cs262a) Ion Stoica, UC Berkeley November 19, 2016

MPI and OpenMP (Lecture 25, cs262a) Ion Stoica, UC Berkeley November 19, 2016 MPI and OpenMP (Lecture 25, cs262a) Ion Stoica, UC Berkeley November 19, 2016 Message passing vs. Shared memory Client Client Client Client send(msg) recv(msg) send(msg) recv(msg) MSG MSG MSG IPC Shared

More information

Introduction to parallel computing concepts and technics

Introduction to parallel computing concepts and technics Introduction to parallel computing concepts and technics Paschalis Korosoglou (support@grid.auth.gr) User and Application Support Unit Scientific Computing Center @ AUTH Overview of Parallel computing

More information

Parallel Programming Using MPI

Parallel Programming Using MPI Parallel Programming Using MPI Short Course on HPC 15th February 2019 Aditya Krishna Swamy adityaks@iisc.ac.in SERC, Indian Institute of Science When Parallel Computing Helps? Want to speed up your calculation

More information

OpenMP and MPI parallelization

OpenMP and MPI parallelization OpenMP and MPI parallelization Gundolf Haase Institute for Mathematics and Scientific Computing University of Graz, Austria Chile, Jan. 2015 OpenMP for our example OpenMP generation in code Determine matrix

More information

CS 426. Building and Running a Parallel Application

CS 426. Building and Running a Parallel Application CS 426 Building and Running a Parallel Application 1 Task/Channel Model Design Efficient Parallel Programs (or Algorithms) Mainly for distributed memory systems (e.g. Clusters) Break Parallel Computations

More information

MPI Tutorial. Shao-Ching Huang. High Performance Computing Group UCLA Institute for Digital Research and Education

MPI Tutorial. Shao-Ching Huang. High Performance Computing Group UCLA Institute for Digital Research and Education MPI Tutorial Shao-Ching Huang High Performance Computing Group UCLA Institute for Digital Research and Education Center for Vision, Cognition, Learning and Art, UCLA July 15 22, 2013 A few words before

More information

Introduction to MPI. HY555 Parallel Systems and Grids Fall 2003

Introduction to MPI. HY555 Parallel Systems and Grids Fall 2003 Introduction to MPI HY555 Parallel Systems and Grids Fall 2003 Outline MPI layout Sending and receiving messages Collective communication Datatypes An example Compiling and running Typical layout of an

More information

Programming with MPI

Programming with MPI Programming with MPI p. 1/?? Programming with MPI Point-to-Point Transfers Nick Maclaren nmm1@cam.ac.uk May 2008 Programming with MPI p. 2/?? Digression Most books and courses teach point--to--point first

More information

A Message Passing Standard for MPP and Workstations. Communications of the ACM, July 1996 J.J. Dongarra, S.W. Otto, M. Snir, and D.W.

A Message Passing Standard for MPP and Workstations. Communications of the ACM, July 1996 J.J. Dongarra, S.W. Otto, M. Snir, and D.W. 1 A Message Passing Standard for MPP and Workstations Communications of the ACM, July 1996 J.J. Dongarra, S.W. Otto, M. Snir, and D.W. Walker 2 Message Passing Interface (MPI) Message passing library Can

More information

Parallelization Principles. Sathish Vadhiyar

Parallelization Principles. Sathish Vadhiyar Parallelization Principles Sathish Vadhiyar Parallel Programming and Challenges Recall the advantages and motivation of parallelism But parallel programs incur overheads not seen in sequential programs

More information

Message Passing Interface - MPI

Message Passing Interface - MPI Message Passing Interface - MPI Parallel and Distributed Computing Department of Computer Science and Engineering (DEI) Instituto Superior Técnico October 24, 2011 Many slides adapted from lectures by

More information

Programming Scalable Systems with MPI. UvA / SURFsara High Performance Computing and Big Data. Clemens Grelck, University of Amsterdam

Programming Scalable Systems with MPI. UvA / SURFsara High Performance Computing and Big Data. Clemens Grelck, University of Amsterdam Clemens Grelck University of Amsterdam UvA / SURFsara High Performance Computing and Big Data Message Passing as a Programming Paradigm Gentle Introduction to MPI Point-to-point Communication Message Passing

More information

Introduction to MPI: Part II

Introduction to MPI: Part II Introduction to MPI: Part II Pawel Pomorski, University of Waterloo, SHARCNET ppomorsk@sharcnetca November 25, 2015 Summary of Part I: To write working MPI (Message Passing Interface) parallel programs

More information

The Message Passing Interface (MPI): Parallelism on Multiple (Possibly Heterogeneous) CPUs

The Message Passing Interface (MPI): Parallelism on Multiple (Possibly Heterogeneous) CPUs 1 The Message Passing Interface (MPI): Parallelism on Multiple (Possibly Heterogeneous) s http://mpi-forum.org https://www.open-mpi.org/ Mike Bailey mjb@cs.oregonstate.edu Oregon State University mpi.pptx

More information

Practical Scientific Computing: Performanceoptimized

Practical Scientific Computing: Performanceoptimized Practical Scientific Computing: Performanceoptimized Programming Programming with MPI November 29, 2006 Dr. Ralf-Peter Mundani Department of Computer Science Chair V Technische Universität München, Germany

More information

A short overview of parallel paradigms. Fabio Affinito, SCAI

A short overview of parallel paradigms. Fabio Affinito, SCAI A short overview of parallel paradigms Fabio Affinito, SCAI Why parallel? In principle, if you have more than one computing processing unit you can exploit that to: -Decrease the time to solution - Increase

More information

Parallel Programming. Matrix Decomposition Options (Matrix-Vector Product)

Parallel Programming. Matrix Decomposition Options (Matrix-Vector Product) Parallel Programming Matrix Decomposition Options (Matrix-Vector Product) Matrix Decomposition Sequential algorithm and its complexity Design, analysis, and implementation of three parallel programs using

More information

CSE 613: Parallel Programming. Lecture 21 ( The Message Passing Interface )

CSE 613: Parallel Programming. Lecture 21 ( The Message Passing Interface ) CSE 613: Parallel Programming Lecture 21 ( The Message Passing Interface ) Jesmin Jahan Tithi Department of Computer Science SUNY Stony Brook Fall 2013 ( Slides from Rezaul A. Chowdhury ) Principles of

More information

Lecture 6. Programming with Message Passing Message Passing Interface (MPI)

Lecture 6. Programming with Message Passing Message Passing Interface (MPI) Lecture 6 Programming with Message Passing Message Passing Interface (MPI) Announcements 2011 Scott B. Baden / CSE 262 / Spring 2011 2 Finish CUDA Today s lecture Programming with message passing 2011

More information

Cornell Theory Center. Discussion: MPI Collective Communication I. Table of Contents. 1. Introduction

Cornell Theory Center. Discussion: MPI Collective Communication I. Table of Contents. 1. Introduction 1 of 18 11/1/2006 3:59 PM Cornell Theory Center Discussion: MPI Collective Communication I This is the in-depth discussion layer of a two-part module. For an explanation of the layers and how to navigate

More information

Copyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 8

Copyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 8 Chapter 8 Matrix-vector Multiplication Chapter Objectives Review matrix-vector multiplication Propose replication of vectors Develop three parallel programs, each based on a different data decomposition

More information

INTRODUCTION TO MPI VIRTUAL TOPOLOGIES

INTRODUCTION TO MPI VIRTUAL TOPOLOGIES INTRODUCTION TO MPI VIRTUAL TOPOLOGIES Introduction to Parallel Computing with MPI and OpenMP 18-19-20 november 2013 a.marani@cineca.it g.muscianisi@cineca.it l.ferraro@cineca.it VIRTUAL TOPOLOGY Topology:

More information

What s in this talk? Quick Introduction. Programming in Parallel

What s in this talk? Quick Introduction. Programming in Parallel What s in this talk? Parallel programming methodologies - why MPI? Where can I use MPI? MPI in action Getting MPI to work at Warwick Examples MPI: Parallel Programming for Extreme Machines Si Hammond,

More information

Programming with MPI

Programming with MPI Programming with MPI p. 1/?? Programming with MPI One-sided Communication Nick Maclaren nmm1@cam.ac.uk October 2010 Programming with MPI p. 2/?? What Is It? This corresponds to what is often called RDMA

More information

Advanced Parallel Programming

Advanced Parallel Programming Advanced Parallel Programming Derived Datatypes Dr Daniel Holmes Applications Consultant dholmes@epcc.ed.ac.uk Overview Lecture will cover derived datatypes memory layouts vector datatypes floating vs

More information

Advanced Parallel Programming

Advanced Parallel Programming Advanced Parallel Programming Derived Datatypes Dr David Henty HPC Training and Support Manager d.henty@epcc.ed.ac.uk +44 131 650 5960 16/01/2014 MPI-IO 2: Derived Datatypes 2 Overview Lecture will cover

More information

Message Passing Interface. most of the slides taken from Hanjun Kim

Message Passing Interface. most of the slides taken from Hanjun Kim Message Passing Interface most of the slides taken from Hanjun Kim Message Passing Pros Scalable, Flexible Cons Someone says it s more difficult than DSM MPI (Message Passing Interface) A standard message

More information

Collective Communications II

Collective Communications II Collective Communications II Ned Nedialkov McMaster University Canada SE/CS 4F03 January 2014 Outline Scatter Example: parallel A b Distributing a matrix Gather Serial A b Parallel A b Allocating memory

More information

Lecture 6: Parallel Matrix Algorithms (part 3)

Lecture 6: Parallel Matrix Algorithms (part 3) Lecture 6: Parallel Matrix Algorithms (part 3) 1 A Simple Parallel Dense Matrix-Matrix Multiplication Let A = [a ij ] n n and B = [b ij ] n n be n n matrices. Compute C = AB Computational complexity of

More information

CME 194 Introduc0on to MPI

CME 194 Introduc0on to MPI CME 194 Introduc0on to MPI Essen0a Callidus h8p://cme194.stanford.edu Recap Last class: Communicators & Derived Datatypes Communica0on between arbitrary subsets of processes Grid style communica0on Communicate

More information