Runtime Address Space Computation for SDSM Systems
|
|
- Meredith Campbell
- 5 years ago
- Views:
Transcription
1 Runtime Address Space Computation for SDSM Systems Jairo Balart
2 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 2
3 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 3
4 Introduction Programming models for distributed memory systems Message passing (MPI) data distribution work distribution data communication/memory consistency SDSM systems Co-Array Fortran UPC OpenMP CAF UPC OpenMP data distribution NO NO/YES YES work distribution NO YES YES memory consistency NO YES YES 4
5 Introduction SDSM critical issues memory consistency data sharing Sources of overheads Memory monitoring memory access interception (UPC) page fault exception handling (OpenMP) Data & control communication memory consistency (UPC & OpenMP) 5
6 Introduction Chances of optimizations in current SDSM implementations related to address space information current implementations have limited information data & control communication on demand runtime can not foresee future communications Gather information at runtime Possible solution: code inspection prior to code execution 6
7 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 7
8 Inspector/executor model How to embed inspector/executor in a SDSM system to complement native mechanism for memory consistency and data sharing to generate an accurate description of the address space used Inspector information increases optimization chances communication & computation overlap group communications minimizes control messages for consistency 8
9 Inspector/executor model Issues to be considered Implicit overhead Optimized inspectors predictable memory accesses Reuse Parallel inspectors Control dependences & pointers Complex memory accesses that can not be inspected use SDSM original mechanisms Amount of data generated how to describe address space? 9
10 Inspector executor/model Implicit overhead Predictable accesses for (i=0; i<dimx; i++) for (j=0; j<dimy; j++) a[i][j]=b[i][j]+c[i][j]; a 0 0 j DIMY i DIMX 10
11 Inspector executor/model Implicit overhead Reusing inspector data #pragma omp parallel private (iteration) for (iteration=1; iteration<=max_iterations; iteration++) rank(iteration); void rank (int iteration) {... #pragma omp for nowait for (i=0; i<num_keys; i++) { }... } 11
12 Inspector executor/model Implicit overhead Parallel inspectors If code to be inspected is parallel nothing forbids parallel inspection The same scheduling for inspection and execution must be applied 12
13 Inspector executor/model Control dependences & pointers not very common on numerical applications for ( i = 0; i < NK; i++) { x1 = 2.0 * x[2*i] - 1.0; x2 = 2.0 * x[2*i+1] - 1.0; t1 = pow2(x1) + pow2(x2); if (t1 <= 1.0) { t2 = sqrt(-2.0 * log(t1) / t1); t3 = (x1 * t2); t4 = (x2 * t2); l = max(fabs(t3), fabs(t4)); qq[l] += 1.0; sx = sx + t3; sy = sy + t4; } } NAS EP for (j = 1; j <= lastrow-firstrow+1; j++) { sum = 0.0; for (k = rowstr[j]; k < rowstr[j+1]; k++) { sum = sum + a[k]*p[colidx[k]]; } w[j] = sum; } NAS CG 13
14 Inspector executor/model Amount of generated data at address level * * 3 = at 4KB-page level * * 3 / = #define SIZE #pragma omp for for (i = 0; i < SIZE; i++) for (k = 0; k < SIZE; k++) for (j = 0; j < SIZE; j++) matrixc[i][j] += (matrixa[i][k] * matrixb[k][j]); 14
15 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 15
16 Implementation SDSM totally relying on inspector/executor data Evaluate impact of building inspector data and distributing it Stress the inspector role to the limit Communication not allowed during execution (only during inspection) before execution all data has to be available on its nodes Communication/execution decoupled inspection phase communication phase execution phase 16
17 Implementation Relaxed consistency copies + diffs Inspection done at page level default 4KB special treatment for scalar objects (1B, 2B, 4B or 8B) Programming model: OpenMP compiler infrastructure only supports OpenMP transformations inspectors coded by hand limitations: loop parallelism, static scheduling Optimizations Predictable accesses Parallel Inspection Reuse done by hand 17
18 Implementation Inspector phase Master broadcast loop parameters: for (i = start; i < end; i+=step) scheduling Code inspection done in parallel Slaves send inspection data to master # pages read & base addresses # pages written & base addresses begin_for_sampling (low, upper, step, schedule, chunk, loop_id, reuse_flag); while (next_iters_sampling (&start, &end, &last)) for (p_i = start; (step >= 1)? (p_i <= end) : (p_i >= end); p_i += step) for (p_j=0; p_j<dimy; p_ j++) /* a[i][j]=b[i][j]+c[i][j];*/ sample_stmt (&a[p_i][p_j], 2, &b[p_i][p_j], &c[p_i][p_j]); end_for_sampling (); 18
19 Implementation Inspector phase Master broadcast loop parameters: for (i = start; i < end; i+=step) scheduling Code inspection done in parallel Slaves send inspection data to master # pages read & base addresses # pages written & base addresses begin_for_sampling (low, upper, step, schedule, chunk, loop_id, reuse_flag); while (next_iters_sampling (&start, &end, &last)) { sample_vector (&a[start][0], (end - start) * DIMY, WRITE); sample_vector (&b[start][0], (end - start) * DIMY, READ); sample_vector (&c[start][0], (end - start) * DIMY, READ); } end_for_sampling (); 19
20 Implementation Communication phase Master computes needed page interchanges Master sends page interchanges queries Pages are interchanged Master computes pages written in more than 1 node and does copies begin_for_sampling (low, upper, step, schedule, chunk, loop_id, reuse_flag); while (next_iters_sampling (&start, &end, &last)) { sample_vector (&a[start][0], (end - start) * DIMY, WRITE); sample_vector (&b[start][0], (end - start) * DIMY, READ); sample_vector (&c[start][0], (end - start) * DIMY, READ); } end_for_sampling (); 20
21 Implementation Execution phase Each node has all pages execution requires No runtime entries on execution After execution conflictive pages are returned to master Master find differences on conflictive pages and updates its pages begin_for (); while (next_iters (&start, &end, &last)) for (p_i = start; (step >= 1)? (p_i <= end) : (p_i >= end); p_i += step) for (p_j=0; p_j <DIMY; p_j++) a[p_i][p_j]=b[p_i][p_j]+c[p_i][p_j]; end_for_sampling (); 21
22 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 22
23 Evaluation: the environment 8 nodes of MareNostrum v1 (hosted at BSC, Barcelona) Each node 2 Power PC 970FX at 2.2 Ghz 4GB RAM/node Myrinet network 4 Gb/s gcc 3.3 linux NPBC 2.3 Omni EP IS FT 23
24 Evaluation: EP.A Works mainly with private data Communications only for reduction variable Single loop executed just one no reuse Non Non optimized EP CLASS A A Optimized EP CLASS A A Execution Time (sec) ,60 3, Runtime Application Control Comm. Data Comm. Exection Time (sec) ,96 3,91 7, Runtime Application Control Comm. Data Comm. Number of threads Number of threads 24
25 Evaluation: IS.B 2 shared vectors of 128MB (32768 pages of 4KB) strided & via index vector accesses Reuse (10 iterations) Reduction 30,00 Non optimized inspection IS CLASS B Non optimized IS CLASS B 1,63 30,00 1,86 B Optimized IS CLASS B Execution Time 25,00 20,00 15,00 10,00 5,00 2,73 3,17 Runtime Application Control Comm. Data Comm. Execution Time(sec) 25,00 20,00 15,00 10,00 5,00 3,27 4,71 Runtime Application Control Comm. Data Comm. 0, , Number of threads Number of threads 25
26 Evaluation: FT.B 3 3-dimensional matrixes of 512 MB ( pages of 4KB) strided accesses 20 iterations 4 loops: 3 reused 1 not reused Data distribution changes at each iteration cffts3 () #pragma omp for for (j = ) for (i = ) for (k = ) main () for (iter = 1; iter < niter; iter++) evolve () cffts3 () cffts2 () cffts1 () cffts1 & cffts2 () #pragma omp for for (k = ) for (j = ) for (i = ) Execution Time (sec) B Optimized FT CLASS B 1,17 1,26 1, Number of threads Runtime Application Control Comm. Data Comm. 26
27 Outline Introduction Inspector/executor model Implementation Evaluation Conclusions & future work 27
28 Conclusions Explore the possibility of embedding an inspector/executor model to a SDSM system The role of the inspector is to supply with an as much as possible accurate address space description The inspector must be optimized to be affordable: predictable accesses using parallel inspection reuse if possible 28
29 Future work More evaluation Rest of NPB benchmarks Spec OpenMP (non numerical applications) Embed inspector executor model in a real SDSM system Automatic reuse mechanism Simultaneous inspection and execution Start to work in the compiler infrastructure Support the rest of OpenMP constructions 29
30 Questions? Thanks! 30
31 Evaluation: CG Non optimized inspection FT CLASS B , Execution 200 Time 0, Number of threads 0,68 Runtime Application Control Comm. Data Comm. Non optimized inspection CG CLASS B Optimized CG CLASS B , Execution 200 Time 100 Runtime Application Control Comm. Data Comm Execution 200 Time 100 2,94 3,09 Runtime Application Control Comm. Data Comm Number of threads Number of threads 31
OpenMP on the FDSM software distributed shared memory. Hiroya Matsuba Yutaka Ishikawa
OpenMP on the FDSM software distributed shared memory Hiroya Matsuba Yutaka Ishikawa 1 2 Software DSM OpenMP programs usually run on the shared memory computers OpenMP programs work on the distributed
More informationHPC Challenge Awards 2010 Class2 XcalableMP Submission
HPC Challenge Awards 2010 Class2 XcalableMP Submission Jinpil Lee, Masahiro Nakao, Mitsuhisa Sato University of Tsukuba Submission Overview XcalableMP Language and model, proposed by XMP spec WG Fortran
More informationThe Performance Analysis of Portable Parallel Programming Interface MpC for SDSM and pthread
The Performance Analysis of Portable Parallel Programming Interface MpC for SDSM and pthread Workshop DSM2005 CCGrig2005 Seikei University Tokyo, Japan midori@st.seikei.ac.jp Hiroko Midorikawa 1 Outline
More informationCMSC 714 Lecture 4 OpenMP and UPC. Chau-Wen Tseng (from A. Sussman)
CMSC 714 Lecture 4 OpenMP and UPC Chau-Wen Tseng (from A. Sussman) Programming Model Overview Message passing (MPI, PVM) Separate address spaces Explicit messages to access shared data Send / receive (MPI
More informationOverview: The OpenMP Programming Model
Overview: The OpenMP Programming Model motivation and overview the parallel directive: clauses, equivalent pthread code, examples the for directive and scheduling of loop iterations Pi example in OpenMP
More informationPerformance Evaluation of OpenMP Applications on Virtualized Multicore Machines
Performance Evaluation of OpenMP Applications on Virtualized Multicore Machines Jie Tao 1 Karl Fuerlinger 2 Holger Marten 1 jie.tao@kit.edu karl.fuerlinger@nm.ifi.lmu.de holger.marten@kit.edu 1 : Steinbuch
More informationOpenMP on the IBM Cell BE
OpenMP on the IBM Cell BE PRACE Barcelona Supercomputing Center (BSC) 21-23 October 2009 Marc Gonzalez Tallada Index OpenMP programming and code transformations Tiling and Software Cache transformations
More informationPiecewise Holistic Autotuning of Compiler and Runtime Parameters
Piecewise Holistic Autotuning of Compiler and Runtime Parameters Mihail Popov, Chadi Akel, William Jalby, Pablo de Oliveira Castro University of Versailles Exascale Computing Research August 2016 C E R
More informationScientific Programming in C XIV. Parallel programming
Scientific Programming in C XIV. Parallel programming Susi Lehtola 11 December 2012 Introduction The development of microchips will soon reach the fundamental physical limits of operation quantum coherence
More informationAcknowledgments. Amdahl s Law. Contents. Programming with MPI Parallel programming. 1 speedup = (1 P )+ P N. Type to enter text
Acknowledgments Programming with MPI Parallel ming Jan Thorbecke Type to enter text This course is partly based on the MPI courses developed by Rolf Rabenseifner at the High-Performance Computing-Center
More information/Users/engelen/Sites/HPC folder/hpc/openmpexamples.c
/* Subset of these examples adapted from: 1. http://www.llnl.gov/computing/tutorials/openmp/exercise.html 2. NAS benchmarks */ #include #include #ifdef _OPENMP #include #endif
More informationCilk Plus GETTING STARTED
Cilk Plus GETTING STARTED Overview Fundamentals of Cilk Plus Hyperobjects Compiler Support Case Study 3/17/2015 CHRIS SZALWINSKI 2 Fundamentals of Cilk Plus Terminology Execution Model Language Extensions
More informationCommunication and Optimization Aspects of Parallel Programming Models on Hybrid Architectures
Communication and Optimization Aspects of Parallel Programming Models on Hybrid Architectures Rolf Rabenseifner rabenseifner@hlrs.de Gerhard Wellein gerhard.wellein@rrze.uni-erlangen.de University of Stuttgart
More informationSession 4: Parallel Programming with OpenMP
Session 4: Parallel Programming with OpenMP Xavier Martorell Barcelona Supercomputing Center Agenda Agenda 10:00-11:00 OpenMP fundamentals, parallel regions 11:00-11:30 Worksharing constructs 11:30-12:00
More informationLecture 4: OpenMP Open Multi-Processing
CS 4230: Parallel Programming Lecture 4: OpenMP Open Multi-Processing January 23, 2017 01/23/2017 CS4230 1 Outline OpenMP another approach for thread parallel programming Fork-Join execution model OpenMP
More informationBarbara Chapman, Gabriele Jost, Ruud van der Pas
Using OpenMP Portable Shared Memory Parallel Programming Barbara Chapman, Gabriele Jost, Ruud van der Pas The MIT Press Cambridge, Massachusetts London, England c 2008 Massachusetts Institute of Technology
More informationC PGAS XcalableMP(XMP) Unified Parallel
PGAS XcalableMP Unified Parallel C 1 2 1, 2 1, 2, 3 C PGAS XcalableMP(XMP) Unified Parallel C(UPC) XMP UPC XMP UPC 1 Berkeley UPC GASNet 1. MPI MPI 1 Center for Computational Sciences, University of Tsukuba
More informationxsim The Extreme-Scale Simulator
www.bsc.es xsim The Extreme-Scale Simulator Janko Strassburg Severo Ochoa Seminar @ BSC, 28 Feb 2014 Motivation Future exascale systems are predicted to have hundreds of thousands of nodes, thousands of
More informationOpenMP - II. Diego Fabregat-Traver and Prof. Paolo Bientinesi WS15/16. HPAC, RWTH Aachen
OpenMP - II Diego Fabregat-Traver and Prof. Paolo Bientinesi HPAC, RWTH Aachen fabregat@aices.rwth-aachen.de WS15/16 OpenMP References Using OpenMP: Portable Shared Memory Parallel Programming. The MIT
More informationOpenMP: Open Multiprocessing
OpenMP: Open Multiprocessing Erik Schnetter May 20-22, 2013, IHPC 2013, Iowa City 2,500 BC: Military Invents Parallelism Outline 1. Basic concepts, hardware architectures 2. OpenMP Programming 3. How to
More informationIntroduction to OpenMP.
Introduction to OpenMP www.openmp.org Motivation Parallelize the following code using threads: for (i=0; i
More informationCopyright The McGraw-Hill Companies, Inc. Permission required for reproduction or display. Chapter 18. Combining MPI and OpenMP
Chapter 18 Combining MPI and OpenMP Outline Advantages of using both MPI and OpenMP Case Study: Conjugate gradient method Case Study: Jacobi method C+MPI vs. C+MPI+OpenMP Interconnection Network P P P
More informationExercise: OpenMP Programming
Exercise: OpenMP Programming Multicore programming with OpenMP 19.04.2016 A. Marongiu - amarongiu@iis.ee.ethz.ch D. Palossi dpalossi@iis.ee.ethz.ch ETH zürich Odroid Board Board Specs Exynos5 Octa Cortex
More informationGCC Developers Summit Ottawa, Canada, June 2006
OpenMP Implementation in GCC Diego Novillo dnovillo@redhat.com Red Hat Canada GCC Developers Summit Ottawa, Canada, June 2006 OpenMP Language extensions for shared memory concurrency (C, C++ and Fortran)
More informationOpenMP Programming. Prof. Thomas Sterling. High Performance Computing: Concepts, Methods & Means
High Performance Computing: Concepts, Methods & Means OpenMP Programming Prof. Thomas Sterling Department of Computer Science Louisiana State University February 8 th, 2007 Topics Introduction Overview
More informationCOMP4510 Introduction to Parallel Computation. Shared Memory and OpenMP. Outline (cont d) Shared Memory and OpenMP
COMP4510 Introduction to Parallel Computation Shared Memory and OpenMP Thanks to Jon Aronsson (UofM HPC consultant) for some of the material in these notes. Outline (cont d) Shared Memory and OpenMP Including
More informationpage migration Implementation and Evaluation of Dynamic Load Balancing Using Runtime Performance Monitoring on Omni/SCASH
Omni/SCASH 1 2 3 4 heterogeneity Omni/SCASH page migration Implementation and Evaluation of Dynamic Load Balancing Using Runtime Performance Monitoring on Omni/SCASH Yoshiaki Sakae, 1 Satoshi Matsuoka,
More informationGetting the most out of your CPUs Parallel computing strategies in R
Getting the most out of your CPUs Parallel computing strategies in R Stefan Theussl Department of Statistics and Mathematics Wirtschaftsuniversität Wien July 2, 2008 Outline Introduction Parallel Computing
More informationOmni Compiler and XcodeML: An Infrastructure for Source-to- Source Transformation
http://omni compiler.org/ Omni Compiler and XcodeML: An Infrastructure for Source-to- Source Transformation MS03 Code Generation Techniques for HPC Earth Science Applications Mitsuhisa Sato (RIKEN / Advanced
More informationXcalableMP Implementation and
XcalableMP Implementation and Performance of NAS Parallel Benchmarks Mitsuhisa Sato Masahiro Nakao, Jinpil Lee and Taisuke Boku University of Tsukuba, Japan What s XcalableMP? XcalableMP (XMP for short)
More informationParallel Programming
Parallel Programming OpenMP Nils Moschüring PhD Student (LMU) Nils Moschüring PhD Student (LMU), OpenMP 1 1 Overview What is parallel software development Why do we need parallel computation? Problems
More informationParallel Programming with OpenMP. CS240A, T. Yang
Parallel Programming with OpenMP CS240A, T. Yang 1 A Programmer s View of OpenMP What is OpenMP? Open specification for Multi-Processing Standard API for defining multi-threaded shared-memory programs
More informationRuntime Support for Scalable Task-parallel Programs
Runtime Support for Scalable Task-parallel Programs Pacific Northwest National Lab xsig workshop May 2018 http://hpc.pnl.gov/people/sriram/ Single Program Multiple Data int main () {... } 2 Task Parallelism
More informationEvaluation of Asynchronous Offloading Capabilities of Accelerator Programming Models for Multiple Devices
Evaluation of Asynchronous Offloading Capabilities of Accelerator Programming Models for Multiple Devices Jonas Hahnfeld 1, Christian Terboven 1, James Price 2, Hans Joachim Pflug 1, Matthias S. Müller
More informationLittle Motivation Outline Introduction OpenMP Architecture Working with OpenMP Future of OpenMP End. OpenMP. Amasis Brauch German University in Cairo
OpenMP Amasis Brauch German University in Cairo May 4, 2010 Simple Algorithm 1 void i n c r e m e n t e r ( short a r r a y ) 2 { 3 long i ; 4 5 for ( i = 0 ; i < 1000000; i ++) 6 { 7 a r r a y [ i ]++;
More informationParallel programming using OpenMP
Parallel programming using OpenMP Computer Architecture J. Daniel García Sánchez (coordinator) David Expósito Singh Francisco Javier García Blas ARCOS Group Computer Science and Engineering Department
More informationIntroduction to OpenMP. OpenMP basics OpenMP directives, clauses, and library routines
Introduction to OpenMP Introduction OpenMP basics OpenMP directives, clauses, and library routines What is OpenMP? What does OpenMP stands for? What does OpenMP stands for? Open specifications for Multi
More informationModule 10: Open Multi-Processing Lecture 19: What is Parallelization? The Lecture Contains: What is Parallelization? Perfectly Load-Balanced Program
The Lecture Contains: What is Parallelization? Perfectly Load-Balanced Program Amdahl's Law About Data What is Data Race? Overview to OpenMP Components of OpenMP OpenMP Programming Model OpenMP Directives
More informationA ROSE-based OpenMP 3.0 Research Compiler Supporting Multiple Runtime Libraries
A ROSE-based OpenMP 3.0 Research Compiler Supporting Multiple Runtime Libraries Chunhua Liao, Daniel J. Quinlan, Thomas Panas and Bronis R. de Supinski Center for Applied Scientific Computing Lawrence
More informationOur new HPC-Cluster An overview
Our new HPC-Cluster An overview Christian Hagen Universität Regensburg Regensburg, 15.05.2009 Outline 1 Layout 2 Hardware 3 Software 4 Getting an account 5 Compiling 6 Queueing system 7 Parallelization
More informationOpen Multi-Processing: Basic Course
HPC2N, UmeåUniversity, 901 87, Sweden. May 26, 2015 Table of contents Overview of Paralellism 1 Overview of Paralellism Parallelism Importance Partitioning Data Distributed Memory Working on Abisko 2 Pragmas/Sentinels
More informationConcurrent Programming with OpenMP
Concurrent Programming with OpenMP Parallel and Distributed Computing Department of Computer Science and Engineering (DEI) Instituto Superior Técnico October 11, 2012 CPD (DEI / IST) Parallel and Distributed
More informationHigh Performance Computing: Tools and Applications
High Performance Computing: Tools and Applications Edmond Chow School of Computational Science and Engineering Georgia Institute of Technology Lecture 2 OpenMP Shared address space programming High-level
More informationAllows program to be incrementally parallelized
Basic OpenMP What is OpenMP An open standard for shared memory programming in C/C+ + and Fortran supported by Intel, Gnu, Microsoft, Apple, IBM, HP and others Compiler directives and library support OpenMP
More informationA Local-View Array Library for Partitioned Global Address Space C++ Programs
Lawrence Berkeley National Laboratory A Local-View Array Library for Partitioned Global Address Space C++ Programs Amir Kamil, Yili Zheng, and Katherine Yelick Lawrence Berkeley Lab Berkeley, CA, USA June
More informationOpenMP: Open Multiprocessing
OpenMP: Open Multiprocessing Erik Schnetter June 7, 2012, IHPC 2012, Iowa City Outline 1. Basic concepts, hardware architectures 2. OpenMP Programming 3. How to parallelise an existing code 4. Advanced
More informationOpenMP on the IBM Cell BE
OpenMP on the IBM Cell BE 15th meeting of ScicomP Barcelona Supercomputing Center (BSC) May 18-22 2009 Marc Gonzalez Tallada Index OpenMP programming and code transformations Tiling and Software cache
More informationParallel Programming: OpenMP
Parallel Programming: OpenMP Xianyi Zeng xzeng@utep.edu Department of Mathematical Sciences The University of Texas at El Paso. November 10, 2016. An Overview of OpenMP OpenMP: Open Multi-Processing An
More informationOpenMP. Dr. William McDoniel and Prof. Paolo Bientinesi WS17/18. HPAC, RWTH Aachen
OpenMP Dr. William McDoniel and Prof. Paolo Bientinesi HPAC, RWTH Aachen mcdoniel@aices.rwth-aachen.de WS17/18 Loop construct - Clauses #pragma omp for [clause [, clause]...] The following clauses apply:
More informationChip Multiprocessors COMP Lecture 9 - OpenMP & MPI
Chip Multiprocessors COMP35112 Lecture 9 - OpenMP & MPI Graham Riley 14 February 2018 1 Today s Lecture Dividing work to be done in parallel between threads in Java (as you are doing in the labs) is rather
More informationECE 574 Cluster Computing Lecture 10
ECE 574 Cluster Computing Lecture 10 Vince Weaver http://www.eece.maine.edu/~vweaver vincent.weaver@maine.edu 1 October 2015 Announcements Homework #4 will be posted eventually 1 HW#4 Notes How granular
More informationIntroduction to OpenMP
Introduction to OpenMP Le Yan Scientific computing consultant User services group High Performance Computing @ LSU Goals Acquaint users with the concept of shared memory parallelism Acquaint users with
More informationDPHPC: Introduction to OpenMP Recitation session
SALVATORE DI GIROLAMO DPHPC: Introduction to OpenMP Recitation session Based on http://openmp.org/mp-documents/intro_to_openmp_mattson.pdf OpenMP An Introduction What is it? A set of compiler directives
More informationTask-based Execution of Nested OpenMP Loops
Task-based Execution of Nested OpenMP Loops Spiros N. Agathos Panagiotis E. Hadjidoukas Vassilios V. Dimakopoulos Department of Computer Science UNIVERSITY OF IOANNINA Ioannina, Greece Presentation Layout
More informationParallel Programming. Libraries and Implementations
Parallel Programming Libraries and Implementations Reusing this material This work is licensed under a Creative Commons Attribution- NonCommercial-ShareAlike 4.0 International License. http://creativecommons.org/licenses/by-nc-sa/4.0/deed.en_us
More informationIntroduction to OpenMP. Lecture 4: Work sharing directives
Introduction to OpenMP Lecture 4: Work sharing directives Work sharing directives Directives which appear inside a parallel region and indicate how work should be shared out between threads Parallel do/for
More informationBasic Communication Operations (Chapter 4)
Basic Communication Operations (Chapter 4) Vivek Sarkar Department of Computer Science Rice University vsarkar@cs.rice.edu COMP 422 Lecture 17 13 March 2008 Review of Midterm Exam Outline MPI Example Program:
More informationCS4961 Parallel Programming. Lecture 5: More OpenMP, Introduction to Data Parallel Algorithms 9/5/12. Administrative. Mary Hall September 4, 2012
CS4961 Parallel Programming Lecture 5: More OpenMP, Introduction to Data Parallel Algorithms Administrative Mailing list set up, everyone should be on it - You should have received a test mail last night
More informationCo-array Fortran Performance and Potential: an NPB Experimental Study. Department of Computer Science Rice University
Co-array Fortran Performance and Potential: an NPB Experimental Study Cristian Coarfa Jason Lee Eckhardt Yuri Dotsenko John Mellor-Crummey Department of Computer Science Rice University Parallel Programming
More informationTopics. Introduction. Shared Memory Parallelization. Example. Lecture 11. OpenMP Execution Model Fork-Join model 5/15/2012. Introduction OpenMP
Topics Lecture 11 Introduction OpenMP Some Examples Library functions Environment variables 1 2 Introduction Shared Memory Parallelization OpenMP is: a standard for parallel programming in C, C++, and
More informationOpenMP examples. Sergeev Efim. Singularis Lab, Ltd. Senior software engineer
OpenMP examples Sergeev Efim Senior software engineer Singularis Lab, Ltd. OpenMP Is: An Application Program Interface (API) that may be used to explicitly direct multi-threaded, shared memory parallelism.
More informationOpenMP Algoritmi e Calcolo Parallelo. Daniele Loiacono
OpenMP Algoritmi e Calcolo Parallelo References Useful references Using OpenMP: Portable Shared Memory Parallel Programming, Barbara Chapman, Gabriele Jost and Ruud van der Pas OpenMP.org http://openmp.org/
More informationOpenMP Overview. in 30 Minutes. Christian Terboven / Aachen, Germany Stand: Version 2.
OpenMP Overview in 30 Minutes Christian Terboven 06.12.2010 / Aachen, Germany Stand: 03.12.2010 Version 2.3 Rechen- und Kommunikationszentrum (RZ) Agenda OpenMP: Parallel Regions,
More informationParallel Programming Libraries and implementations
Parallel Programming Libraries and implementations Partners Funding Reusing this material This work is licensed under a Creative Commons Attribution- NonCommercial-ShareAlike 4.0 International License.
More informationSynchronization. Event Synchronization
Synchronization Synchronization: mechanisms by which a parallel program can coordinate the execution of multiple threads Implicit synchronizations Explicit synchronizations Main use of explicit synchronization
More informationParallel Programming in C with MPI and OpenMP
Parallel Programming in C with MPI and OpenMP Michael J. Quinn Chapter 17 Shared-memory Programming 1 Outline n OpenMP n Shared-memory model n Parallel for loops n Declaring private variables n Critical
More information2
1 2 3 4 5 Code transformation Every time the compiler finds a #pragma omp parallel directive creates a new function in which the code belonging to the scope of the pragma itself is moved The directive
More informationExploiting Object-Oriented Abstractions to parallelize Sparse Linear Algebra Codes
Exploiting Object-Oriented Abstractions to parallelize Sparse Linear Algebra Codes Christian Terboven, Dieter an Mey, Paul Kapinos, Christopher Schleiden, Igor Merkulow {terboven, anmey, kapinos, schleiden,
More informationIntroduction to OpenMP
Introduction to OpenMP Le Yan Objectives of Training Acquaint users with the concept of shared memory parallelism Acquaint users with the basics of programming with OpenMP Memory System: Shared Memory
More informationCOMP528: Multi-core and Multi-Processor Computing
COMP528: Multi-core and Multi-Processor Computing Dr Michael K Bane, G14, Computer Science, University of Liverpool m.k.bane@liverpool.ac.uk https://cgi.csc.liv.ac.uk/~mkbane/comp528 17 Background Reading
More informationMasterpraktikum - High Performance Computing
Masterpraktikum - High Performance Computing OpenMP Michael Bader Alexander Heinecke Alexander Breuer Technische Universität München, Germany 2 #include ... #pragma omp parallel for for(i = 0; i
More informationParallelising Scientific Codes Using OpenMP. Wadud Miah Research Computing Group
Parallelising Scientific Codes Using OpenMP Wadud Miah Research Computing Group Software Performance Lifecycle Scientific Programming Early scientific codes were mainly sequential and were executed on
More informationLab: Scientific Computing Tsunami-Simulation
Lab: Scientific Computing Tsunami-Simulation Session 4: Optimization and OMP Sebastian Rettenberger, Michael Bader 23.11.15 Session 4: Optimization and OMP, 23.11.15 1 Department of Informatics V Linux-Cluster
More informationIntroduction to OpenMP
Introduction to OpenMP Ekpe Okorafor School of Parallel Programming & Parallel Architecture for HPC ICTP October, 2014 A little about me! PhD Computer Engineering Texas A&M University Computer Science
More informationOptimizing Irregular Shared-Memory Applications for Distributed-Memory Systems
Optimizing Irregular Shared-Memory Applications for Distributed-Memory Systems Ayon Basumallik Rudolf Eigenmann School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 4797-1285
More informationShared memory programming model OpenMP TMA4280 Introduction to Supercomputing
Shared memory programming model OpenMP TMA4280 Introduction to Supercomputing NTNU, IMF February 16. 2018 1 Recap: Distributed memory programming model Parallelism with MPI. An MPI execution is started
More informationA Characterization of Shared Data Access Patterns in UPC Programs
IBM T.J. Watson Research Center A Characterization of Shared Data Access Patterns in UPC Programs Christopher Barton, Calin Cascaval, Jose Nelson Amaral LCPC `06 November 2, 2006 Outline Motivation Overview
More informationParallel Processing Top manufacturer of multiprocessing video & imaging solutions.
1 of 10 3/3/2005 10:51 AM Linux Magazine March 2004 C++ Parallel Increase application performance without changing your source code. Parallel Processing Top manufacturer of multiprocessing video & imaging
More informationParallel Programming. OpenMP Parallel programming for multiprocessors for loops
Parallel Programming OpenMP Parallel programming for multiprocessors for loops OpenMP OpenMP An application programming interface (API) for parallel programming on multiprocessors Assumes shared memory
More informationOpenMP - III. Diego Fabregat-Traver and Prof. Paolo Bientinesi WS15/16. HPAC, RWTH Aachen
OpenMP - III Diego Fabregat-Traver and Prof. Paolo Bientinesi HPAC, RWTH Aachen fabregat@aices.rwth-aachen.de WS15/16 OpenMP References Using OpenMP: Portable Shared Memory Parallel Programming. The MIT
More informationA common scenario... Most of us have probably been here. Where did my performance go? It disappeared into overheads...
OPENMP PERFORMANCE 2 A common scenario... So I wrote my OpenMP program, and I checked it gave the right answers, so I ran some timing tests, and the speedup was, well, a bit disappointing really. Now what?.
More informationCOMP Parallel Computing. SMM (2) OpenMP Programming Model
COMP 633 - Parallel Computing Lecture 7 September 12, 2017 SMM (2) OpenMP Programming Model Reading for next time look through sections 7-9 of the Open MP tutorial Topics OpenMP shared-memory parallel
More informationECE 563 Spring 2012 First Exam
ECE 563 Spring 2012 First Exam version 1 This is a take-home test. You must work, if found cheating you will be failed in the course and you will be turned in to the Dean of Students. To make it easy not
More informationOpenMP Doacross Loops Case Study
National Aeronautics and Space Administration OpenMP Doacross Loops Case Study November 14, 2017 Gabriele Jost and Henry Jin www.nasa.gov Background Outline - The OpenMP doacross concept LU-OMP implementations
More informationA brief introduction to OpenMP
A brief introduction to OpenMP Alejandro Duran Barcelona Supercomputing Center Outline 1 Introduction 2 Writing OpenMP programs 3 Data-sharing attributes 4 Synchronization 5 Worksharings 6 Task parallelism
More informationIntroduction to OpenMP
Introduction to OpenMP Lecture 4: Work sharing directives Work sharing directives Directives which appear inside a parallel region and indicate how work should be shared out between threads Parallel do/for
More informationUvA-SARA High Performance Computing Course June Clemens Grelck, University of Amsterdam. Parallel Programming with Compiler Directives: OpenMP
Parallel Programming with Compiler Directives OpenMP Clemens Grelck University of Amsterdam UvA-SARA High Performance Computing Course June 2013 OpenMP at a Glance Loop Parallelization Scheduling Parallel
More informationOpenMP 4.0/4.5: New Features and Protocols. Jemmy Hu
OpenMP 4.0/4.5: New Features and Protocols Jemmy Hu SHARCNET HPC Consultant University of Waterloo May 10, 2017 General Interest Seminar Outline OpenMP overview Task constructs in OpenMP SIMP constructs
More informationLecture 16: Recapitulations. Lecture 16: Recapitulations p. 1
Lecture 16: Recapitulations Lecture 16: Recapitulations p. 1 Parallel computing and programming in general Parallel computing a form of parallel processing by utilizing multiple computing units concurrently
More informationIntroduction to OpenMP
Introduction to OpenMP Christian Terboven 10.04.2013 / Darmstadt, Germany Stand: 06.03.2013 Version 2.3 Rechen- und Kommunikationszentrum (RZ) History De-facto standard for
More informationA Dynamic Periodicity Detector: Application to Speedup Computation
A Dynamic Periodicity Detector: Application to Speedup Computation Felix Freitag, Julita Corbalan, Jesus Labarta Departament d Arquitectura de Computadors (DAC),Universitat Politècnica de Catalunya(UPC)
More informationParallel Programming with OpenMP. CS240A, T. Yang, 2013 Modified from Demmel/Yelick s and Mary Hall s Slides
Parallel Programming with OpenMP CS240A, T. Yang, 203 Modified from Demmel/Yelick s and Mary Hall s Slides Introduction to OpenMP What is OpenMP? Open specification for Multi-Processing Standard API for
More informationEE/CSCI 451: Parallel and Distributed Computation
EE/CSCI 451: Parallel and Distributed Computation Lecture #7 2/5/2017 Xuehai Qian Xuehai.qian@usc.edu http://alchem.usc.edu/portal/xuehaiq.html University of Southern California 1 Outline From last class
More informationIntroduction to HPC and Optimization Tutorial VI
Felix Eckhofer Institut für numerische Mathematik und Optimierung Introduction to HPC and Optimization Tutorial VI January 8, 2013 TU Bergakademie Freiberg Going parallel HPC cluster in Freiberg 144 nodes,
More informationPGAS Languages (Par//oned Global Address Space) Marc Snir
PGAS Languages (Par//oned Global Address Space) Marc Snir Goal Global address space is more convenient to users: OpenMP programs are simpler than MPI programs Languages such as OpenMP do not provide mechanisms
More informationShared Memory Programming Model
Shared Memory Programming Model Ahmed El-Mahdy and Waleed Lotfy What is a shared memory system? Activity! Consider the board as a shared memory Consider a sheet of paper in front of you as a local cache
More informationMultithreading in C with OpenMP
Multithreading in C with OpenMP ICS432 - Spring 2017 Concurrent and High-Performance Programming Henri Casanova (henric@hawaii.edu) Pthreads are good and bad! Multi-threaded programming in C with Pthreads
More informationNanos Mercurium: a Research Compiler for OpenMP
Nanos Mercurium: a Research Compiler for OpenMP J. Balart, A. Duran, M. Gonzàlez, X. Martorell, E. Ayguadé and J. Labarta Computer Architecture Department, Technical University of Catalonia, cr. Jordi
More informationOmni OpenMP compiler. C++ Frontend. C- Front. F77 Frontend. Intermediate representation (Xobject) Exc Java tool. Exc Tool
Design of OpenMP Compiler for an SMP Cluster Mitsuhisa Sato, Shigehisa Satoh, Kazuhiro Kusano and Yoshio Tanaka Real World Computing Partnership, Tsukuba, Ibaraki 305-0032, Japan E-mail:fmsato,sh-sato,kusano,yoshiog@trc.rwcp.or.jp
More informationITCS 4/5145 Parallel Computing Test 1 5:00 pm - 6:15 pm, Wednesday February 17, 2016 Solutions Name:...
ITCS 4/5145 Parallel Computing Test 1 5:00 pm - 6:15 pm, Wednesday February 17, 016 Solutions Name:... Answer questions in space provided below questions. Use additional paper if necessary but make sure
More information