Data-intensive computing in radiative transfer modelling
|
|
- Michael Sullivan
- 6 years ago
- Views:
Transcription
1 German Aerospace Center (DLR) Remote Sensing Technology Institute (IMF) Data-intensive computing in radiative transfer modelling Dmitry Efremenko Diego Loyola Adrian Doicu Thomas Trautmann
2 Motivation SCIAMACHY S5P SCIAMACHY Sentinel 5 P Spatial resolution 30 km 60 km 7 km 7 km Amount of level 1 data per year 2 ТВ 180 TB
3 Performance requirements Earth surface area: ~ 5x10^8 km 2 Pixel area: ~ 50 km 2 Number of ground pixels per day: ~10,000,000 Processing time for one pixel: ~0.01 sec O spectral lines 1 spectral line per sec Radiative transfer solvers have to be accelerated to be used in nearreal-time trace gas retrieval algorithms
4 Loop hierarchy // loop over ground pixels foreach ground_pixel: // loop over wavelengths for wl_start to wl_end: // loop over cloud fractions for cloud_free and cloudy: call_rte_solver( );
5 // loop over wavelengths: PCA-based radiative transfer solver I I N 2 ( xw) ( x ) Correction factor w = f ( x ) w I N I 2 multi-stream model the two-stream model Approximation in the reduced data space T 1 T 2 f( xw) = f( x+ xw) f( x) + xw f( x) + xw f( x) xw f( x ) f( x ) + [ f( + ) f( )] y + [ f( + ) 2 f( ) + f( )] y 2 x a x a 2 x a x x a 2 w k k wk k k wk k= 1 k= 1 Computation of the spectrum I N 100 PCA (LPP, LPE, LEA, ) I I 5 N I 2 100
6 // loop over wavelengths: PCA-based radiative transfer solver The accuracy of the results is better than 0.5% while the performance enhancement is of about 8 for the ozone total column retrieval. Natraj et al. //JQSRT, 111 (2010) Efremenko et al // JQSRT V.133. P
7 // loop over cloud fraction: Optimization of the independent pixel approximation c 1-c I = ci + (1 c) I cloudy clear_sky +
8 // loop over cloud fraction: Optimization of the independent pixel approximation Ui + Ui = B Ui + Ui = B 1 2 j j j j+ 1 j U i + U i = B 1 2 N N N N+ 1 N Ui + Ui = B ˆ 1 ˆ 2 ˆ j j + j j+ 1 = j Ui Ui B U i + U i 1 = B exp( τ) 1 2 N N N N+ N cloud 2 cloud ( ) = clear ( ) clear I2 ( λ ) ( λ ) I I λ I λ K λ ( ) Efremenko et al. // JQSRT 135 (2014) 58-65
9 // loop over ground pixels: CUDA-based implementation Stand-alone C version of the discrete ordinate method Single precision code CPU/GPU overlapping Overlapping for the data transfer between CPU and GPU
10 // loop over ground pixels: Performance for matrix operations Matrix size 8x8 Matrix size 32x32 Matrix size 128x128 SGEMM - the matrix multiplication; EIG the eigenvalue problem; LU the LU-factorization. For CUBLAS, a dynamic parallelism was used.
11 // loop over ground pixels: Performance comparison Efremenko et al. Multi-core-CPU and GPU-accelerated // Computer Physics Communications, 185 (2014)
12 // loop over ground pixels: Performance comparison Workload Speedup Reduced workload Multi-stream RTM 50 % % Two-stream RTM 25% 53 7 % PCA 20% 6 52% Rest 5% 10 6% According to Amdahl s law, the speedup for the whole algorithm is limited: tot S 1 < β + (1 β ) S β the accelerated part, S the speedup factor for β-part of the algorithm. Further speedup of the PCA-based RTM due to improving the multi-stream RTM cannot be larger than 2.
13 Cumulative performance enhancement Acceleration technique PCA-based radiative transfer 8 IPA-optimization 2 GPU-computing 15 Performance enhancement Total: 240 (220) The maximum error introduced by all acceleration techniques does not exceed 0.1%
14 Example of ozone retrieval
15 Summary A fast radiative transfer solver has been developed. It encapsulates dimensionality reduction of optical parameters together with the discrete ordinate method; We introduced two optimization techniques for the independent pixel approximation; GPU solver has a 50 speedup factor for the two-stream model and 20 speedup for the multi-stream model with 8 discrete ordinates compared with single-threaded CPU code; GPU memory management is a crucial factor regarding the performance. The memory size is a major limitation of current generation of GPU cards; The total performance enhancement is of about 220 times.
16 Background The discrete ordinate method is used to obtain a numerically stable solution of the RTE The RT problem has a matrix solution and encapsulates mostly the LAPACK subroutines:?gemm?getrf +?getri?getrf +?getrs?geev (the matrix multiplication) (the matrix inversion) (the system of linear equations) (the eigenvalue problem) Number of discrete ordinate is a main parameter which governs the accuracy and the performance. For ozone retrieval in UV spectral range 4-8 discrete ordinates per hemisphere are used. The computations are implemented for several wavelengths (80) and pixels (20 000, in the nearest future ).
17 Parallel computing strategies
18 Parallalization on the level of math libraries Tool: Math Kernel Library Idea: Math Kernel library is used instead of LAPACK. It is optimized for multicore processors. Implementation: -L ${MKLPATH} -I ${MKLINCLUDE} -Wl,--start-group ${MKLPATH}/libmkl_intel.a ${MKLPATH}/libmkl_intel_thread.a ${MKLPATH}/libmkl_core.a ${MKLPATH}/libmkl_scalapack_core.a - Wl,--end-group -liomp5 -lpthread Result: On 2-core CPU we got acceleration ~ 2 times, 4-core CPU ~ 4 times. Simultaneously only 1 task (1 wavelength for 1 pixel) is processed. The code should not be changed (FORTRAN and C support), only the linking option is added.
19 Parallalization on the level of tasks Tool: Open Multi-Processing Idea: a master thread forks a specified number of slave threads and a task is divided among them. Implementation: #include <omp.h>... omp_set_num_threads(total_n_threads); #pragma omp parallel private(th_id) { th_id = omp_get_thread_num();... call_rtmodel(th_id); } The slightly changes should be made one should add OpenMP directives and the compiler flag -fopenmp.
20 Running on several CPUs White dots refer to OpenMP-accelerated code; black dots refer to executing several singlethreaded codes (GNU Parallel tool). DrepperU. What every programmer should know about memory Intel Xeon CPU E ,60GHz with 8 CPUs on 4 cores (250 euro) AMD Opteron 4176 HE 2.4GHz with 12 CPUs on 6 cores AMD Opteron 6282 SE 2.6GHz with 32 CPUs on 8 cores (1000 euro)
21 GPU: possible performance enhancement Mielikainen et al. // IEEE Selected Topics in Applied Earth Observations and Remote Sensing V.4. P times Chen et al. // Computers & Geoscience V. 46. P times Sui et al. // Computers & Geoscience V. 43. P times Humphrey et al. // Proc. SPIE V P Lee et al. Debunking the 100x GPU vs. CPU myth... // SIGARCH Comput. Archit. News V.38. P times
22 Memory management
23 Summary The PCA-based radiative transfer model is developed for the GPU and multicore CPU hardware. GPU solver has a 50 speedup factor for the two-stream model and 20 speedup for the multi-stream model with 8 discrete ordinates compared with single-threaded CPU code. GPU memory management is a crucial factor regarding the performance. The memory size is a major limitation of current generation of GPU cards Future generation of GPUs are a promising option for Sentinel 5 Precursor
24 Philosophical conclusion If you optimize everything, you will always be unhappy. Donald Knuth
25 Thread and memory hierarchies CUDA C programming Guide
Parallel Algorithm Engineering
Parallel Algorithm Engineering Kenneth S. Bøgh PhD Fellow Based on slides by Darius Sidlauskas Outline Background Current multicore architectures UMA vs NUMA The openmp framework and numa control Examples
More informationGPU Acceleration of the Longwave Rapid Radiative Transfer Model in WRF using CUDA Fortran. G. Ruetsch, M. Fatica, E. Phillips, N.
GPU Acceleration of the Longwave Rapid Radiative Transfer Model in WRF using CUDA Fortran G. Ruetsch, M. Fatica, E. Phillips, N. Juffa Outline WRF and RRTM Previous Work CUDA Fortran Features RRTM in CUDA
More informationParallel Systems. Project topics
Parallel Systems Project topics 2016-2017 1. Scheduling Scheduling is a common problem which however is NP-complete, so that we are never sure about the optimality of the solution. Parallelisation is a
More informationHyperspectral Unmixing on GPUs and Multi-Core Processors: A Comparison
Hyperspectral Unmixing on GPUs and Multi-Core Processors: A Comparison Dept. of Mechanical and Environmental Informatics Kimura-Nakao lab. Uehara Daiki Today s outline 1. Self-introduction 2. Basics of
More informationStudy and implementation of computational methods for Differential Equations in heterogeneous systems. Asimina Vouronikoy - Eleni Zisiou
Study and implementation of computational methods for Differential Equations in heterogeneous systems Asimina Vouronikoy - Eleni Zisiou Outline Introduction Review of related work Cyclic Reduction Algorithm
More informationMulti-GPU Scaling of Direct Sparse Linear System Solver for Finite-Difference Frequency-Domain Photonic Simulation
Multi-GPU Scaling of Direct Sparse Linear System Solver for Finite-Difference Frequency-Domain Photonic Simulation 1 Cheng-Han Du* I-Hsin Chung** Weichung Wang* * I n s t i t u t e o f A p p l i e d M
More informationOn Level Scheduling for Incomplete LU Factorization Preconditioners on Accelerators
On Level Scheduling for Incomplete LU Factorization Preconditioners on Accelerators Karl Rupp, Barry Smith rupp@mcs.anl.gov Mathematics and Computer Science Division Argonne National Laboratory FEMTEC
More informationSerial and Parallel Sobel Filtering for multimedia applications
Serial and Parallel Sobel Filtering for multimedia applications Gunay Abdullayeva Institute of Computer Science University of Tartu Email: gunay@ut.ee Abstract GSteamer contains various plugins to apply
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 2X So far Why and
More informationReview of previous examinations TMA4280 Introduction to Supercomputing
Review of previous examinations TMA4280 Introduction to Supercomputing NTNU, IMF April 24. 2017 1 Examination The examination is usually comprised of: one problem related to linear algebra operations with
More informationIntroduction to Parallel and Distributed Computing. Linh B. Ngo CPSC 3620
Introduction to Parallel and Distributed Computing Linh B. Ngo CPSC 3620 Overview: What is Parallel Computing To be run using multiple processors A problem is broken into discrete parts that can be solved
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 informationThe Uintah Framework: A Unified Heterogeneous Task Scheduling and Runtime System
The Uintah Framework: A Unified Heterogeneous Task Scheduling and Runtime System Alan Humphrey, Qingyu Meng, Martin Berzins Scientific Computing and Imaging Institute & University of Utah I. Uintah Overview
More informationMAGMA a New Generation of Linear Algebra Libraries for GPU and Multicore Architectures
MAGMA a New Generation of Linear Algebra Libraries for GPU and Multicore Architectures Stan Tomov Innovative Computing Laboratory University of Tennessee, Knoxville OLCF Seminar Series, ORNL June 16, 2010
More informationParallel Computing. November 20, W.Homberg
Mitglied der Helmholtz-Gemeinschaft Parallel Computing November 20, 2017 W.Homberg Why go parallel? Problem too large for single node Job requires more memory Shorter time to solution essential Better
More informationGTC 2013: DEVELOPMENTS IN GPU-ACCELERATED SPARSE LINEAR ALGEBRA ALGORITHMS. Kyle Spagnoli. Research EM Photonics 3/20/2013
GTC 2013: DEVELOPMENTS IN GPU-ACCELERATED SPARSE LINEAR ALGEBRA ALGORITHMS Kyle Spagnoli Research Engineer @ EM Photonics 3/20/2013 INTRODUCTION» Sparse systems» Iterative solvers» High level benchmarks»
More informationDigital Earth Routine on Tegra K1
Digital Earth Routine on Tegra K1 Aerosol Optical Depth Retrieval Performance Comparison and Energy Efficiency Energy matters! Ecological A topic that affects us all Economical Reasons Practical Curiosity
More informationAn Extension of the StarSs Programming Model for Platforms with Multiple GPUs
An Extension of the StarSs Programming Model for Platforms with Multiple GPUs Eduard Ayguadé 2 Rosa M. Badia 2 Francisco Igual 1 Jesús Labarta 2 Rafael Mayo 1 Enrique S. Quintana-Ortí 1 1 Departamento
More informationHybrid Implementation of 3D Kirchhoff Migration
Hybrid Implementation of 3D Kirchhoff Migration Max Grossman, Mauricio Araya-Polo, Gladys Gonzalez GTC, San Jose March 19, 2013 Agenda 1. Motivation 2. The Problem at Hand 3. Solution Strategy 4. GPU Implementation
More informationChapter 6. Parallel Processors from Client to Cloud. Copyright 2014 Elsevier Inc. All rights reserved.
Chapter 6 Parallel Processors from Client to Cloud FIGURE 6.1 Hardware/software categorization and examples of application perspective on concurrency versus hardware perspective on parallelism. 2 FIGURE
More informationThe Art of Parallel Processing
The Art of Parallel Processing Ahmad Siavashi April 2017 The Software Crisis As long as there were no machines, programming was no problem at all; when we had a few weak computers, programming became a
More informationCUDA. Matthew Joyner, Jeremy Williams
CUDA Matthew Joyner, Jeremy Williams Agenda What is CUDA? CUDA GPU Architecture CPU/GPU Communication Coding in CUDA Use cases of CUDA Comparison to OpenCL What is CUDA? What is CUDA? CUDA is a parallel
More informationProgramming Models for Multi- Threading. Brian Marshall, Advanced Research Computing
Programming Models for Multi- Threading Brian Marshall, Advanced Research Computing Why Do Parallel Computing? Limits of single CPU computing performance available memory I/O rates Parallel computing allows
More informationThe Spherical Harmonics Discrete Ordinate Method for Atmospheric Radiative Transfer
The Spherical Harmonics Discrete Ordinate Method for Atmospheric Radiative Transfer K. Franklin Evans Program in Atmospheric and Oceanic Sciences University of Colorado, Boulder Computational Methods in
More informationLecture 2: Introduction to OpenMP with application to a simple PDE solver
Lecture 2: Introduction to OpenMP with application to a simple PDE solver Mike Giles Mathematical Institute Mike Giles Lecture 2: Introduction to OpenMP 1 / 24 Hardware and software Hardware: a processor
More informationAchieve Better Performance with PEAK on XSEDE Resources
Achieve Better Performance with PEAK on XSEDE Resources Haihang You, Bilel Hadri, Shirley Moore XSEDE 12 July 18 th 2012 Motivations FACTS ALTD ( Automatic Tracking Library Database ) ref Fahey, Jones,
More informationBrief notes on setting up semi-high performance computing environments. July 25, 2014
Brief notes on setting up semi-high performance computing environments July 25, 2014 1 We have two different computing environments for fitting demanding models to large space and/or time data sets. 1
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 informationParallel Programming. Exploring local computational resources OpenMP Parallel programming for multiprocessors for loops
Parallel Programming Exploring local computational resources OpenMP Parallel programming for multiprocessors for loops Single computers nowadays Several CPUs (cores) 4 to 8 cores on a single chip Hyper-threading
More informationTechnology for a better society. hetcomp.com
Technology for a better society hetcomp.com 1 J. Seland, C. Dyken, T. R. Hagen, A. R. Brodtkorb, J. Hjelmervik,E Bjønnes GPU Computing USIT Course Week 16th November 2011 hetcomp.com 2 9:30 10:15 Introduction
More informationAdaptive Mesh Astrophysical Fluid Simulations on GPU. San Jose 10/2/2009 Peng Wang, NVIDIA
Adaptive Mesh Astrophysical Fluid Simulations on GPU San Jose 10/2/2009 Peng Wang, NVIDIA Overview Astrophysical motivation & the Enzo code Finite volume method and adaptive mesh refinement (AMR) CUDA
More informationHigh performance 2D Discrete Fourier Transform on Heterogeneous Platforms. Shrenik Lad, IIIT Hyderabad Advisor : Dr. Kishore Kothapalli
High performance 2D Discrete Fourier Transform on Heterogeneous Platforms Shrenik Lad, IIIT Hyderabad Advisor : Dr. Kishore Kothapalli Motivation Fourier Transform widely used in Physics, Astronomy, Engineering
More informationSTRATEGIES TO ACCELERATE VASP WITH GPUS USING OPENACC. Stefan Maintz, Dr. Markus Wetzstein
STRATEGIES TO ACCELERATE VASP WITH GPUS USING OPENACC Stefan Maintz, Dr. Markus Wetzstein smaintz@nvidia.com; mwetzstein@nvidia.com Companies Academia VASP USERS AND USAGE 12-25% of CPU cycles @ supercomputing
More informationHow to perform HPL on CPU&GPU clusters. Dr.sc. Draško Tomić
How to perform HPL on CPU&GPU clusters Dr.sc. Draško Tomić email: drasko.tomic@hp.com Forecasting is not so easy, HPL benchmarking could be even more difficult Agenda TOP500 GPU trends Some basics about
More informationGPU ACCELERATION OF WSMP (WATSON SPARSE MATRIX PACKAGE)
GPU ACCELERATION OF WSMP (WATSON SPARSE MATRIX PACKAGE) NATALIA GIMELSHEIN ANSHUL GUPTA STEVE RENNICH SEID KORIC NVIDIA IBM NVIDIA NCSA WATSON SPARSE MATRIX PACKAGE (WSMP) Cholesky, LDL T, LU factorization
More informationChapter 4: Threads. Chapter 4: Threads
Chapter 4: Threads Silberschatz, Galvin and Gagne 2013 Chapter 4: Threads Overview Multicore Programming Multithreading Models Thread Libraries Implicit Threading Threading Issues Operating System Examples
More informationCS691/SC791: Parallel & Distributed Computing
CS691/SC791: Parallel & Distributed Computing Introduction to OpenMP 1 Contents Introduction OpenMP Programming Model and Examples OpenMP programming examples Task parallelism. Explicit thread synchronization.
More informationImproved Event Generation at NLO and NNLO. or Extending MCFM to include NNLO processes
Improved Event Generation at NLO and NNLO or Extending MCFM to include NNLO processes W. Giele, RadCor 2015 NNLO in MCFM: Jettiness approach: Using already well tested NLO MCFM as the double real and virtual-real
More informationSpeedup Altair RADIOSS Solvers Using NVIDIA GPU
Innovation Intelligence Speedup Altair RADIOSS Solvers Using NVIDIA GPU Eric LEQUINIOU, HPC Director Hongwei Zhou, Senior Software Developer May 16, 2012 Innovation Intelligence ALTAIR OVERVIEW Altair
More informationPython for Development of OpenMP and CUDA Kernels for Multidimensional Data
Python for Development of OpenMP and CUDA Kernels for Multidimensional Data Zane W. Bell 1, Greg G. Davidson 2, Ed D Azevedo 3, Thomas M. Evans 2, Wayne Joubert 4, John K. Munro, Jr. 5, Dilip R. Patlolla
More informationBig Data Analytics Performance for Large Out-Of- Core Matrix Solvers on Advanced Hybrid Architectures
Procedia Computer Science Volume 51, 2015, Pages 2774 2778 ICCS 2015 International Conference On Computational Science Big Data Analytics Performance for Large Out-Of- Core Matrix Solvers on Advanced Hybrid
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 informationCellSs Making it easier to program the Cell Broadband Engine processor
Perez, Bellens, Badia, and Labarta CellSs Making it easier to program the Cell Broadband Engine processor Presented by: Mujahed Eleyat Outline Motivation Architecture of the cell processor Challenges of
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 informationIntel C++ Compiler User's Guide With Support For The Streaming Simd Extensions 2
Intel C++ Compiler User's Guide With Support For The Streaming Simd Extensions 2 This release of the Intel C++ Compiler 16.0 product is a Pre-Release, and as such is 64 architecture processor supporting
More informationGenerating Efficient Data Movement Code for Heterogeneous Architectures with Distributed-Memory
Generating Efficient Data Movement Code for Heterogeneous Architectures with Distributed-Memory Roshan Dathathri Thejas Ramashekar Chandan Reddy Uday Bondhugula Department of Computer Science and Automation
More informationIssues In Implementing The Primal-Dual Method for SDP. Brian Borchers Department of Mathematics New Mexico Tech Socorro, NM
Issues In Implementing The Primal-Dual Method for SDP Brian Borchers Department of Mathematics New Mexico Tech Socorro, NM 87801 borchers@nmt.edu Outline 1. Cache and shared memory parallel computing concepts.
More informationG P G P U : H I G H - P E R F O R M A N C E C O M P U T I N G
Joined Advanced Student School (JASS) 2009 March 29 - April 7, 2009 St. Petersburg, Russia G P G P U : H I G H - P E R F O R M A N C E C O M P U T I N G Dmitry Puzyrev St. Petersburg State University Faculty
More informationOptimising the Mantevo benchmark suite for multi- and many-core architectures
Optimising the Mantevo benchmark suite for multi- and many-core architectures Simon McIntosh-Smith Department of Computer Science University of Bristol 1 Bristol's rich heritage in HPC The University of
More informationApplications of Berkeley s Dwarfs on Nvidia GPUs
Applications of Berkeley s Dwarfs on Nvidia GPUs Seminar: Topics in High-Performance and Scientific Computing Team N2: Yang Zhang, Haiqing Wang 05.02.2015 Overview CUDA The Dwarfs Dynamic Programming Sparse
More informationCSCI 402: Computer Architectures. Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI.
CSCI 402: Computer Architectures Parallel Processors (2) Fengguang Song Department of Computer & Information Science IUPUI 6.6 - End Today s Contents GPU Cluster and its network topology The Roofline performance
More informationMAGMA. Matrix Algebra on GPU and Multicore Architectures
MAGMA Matrix Algebra on GPU and Multicore Architectures Innovative Computing Laboratory Electrical Engineering and Computer Science University of Tennessee Piotr Luszczek (presenter) web.eecs.utk.edu/~luszczek/conf/
More informationPorting CPU-based Multiprocessing Algorithms to GPU for Distributed Acoustic Sensing
GTC2014 S4470 Porting CPU-based Multiprocessing Algorithms to GPU for Distributed Acoustic Sensing Steve Jankly Halliburton Energy Services, Inc. Introduction Halliburton Halliburton is one of the world
More informationPhD Student. Associate Professor, Co-Director, Center for Computational Earth and Environmental Science. Abdulrahman Manea.
Abdulrahman Manea PhD Student Hamdi Tchelepi Associate Professor, Co-Director, Center for Computational Earth and Environmental Science Energy Resources Engineering Department School of Earth Sciences
More informationLIDORT family of Radiative Transfer Models Applications to the TEMPO Project
LIDORT family of Radiative Transfer Models Applications to the TEMPO Project Robert Spurr, RT Solutions Inc. 9 Channing Street, Cambridge, Mass. First TEMPO Science Team Meeting Harvard-Smithsonian CfA,
More informationHierarchical DAG Scheduling for Hybrid Distributed Systems
June 16, 2015 Hierarchical DAG Scheduling for Hybrid Distributed Systems Wei Wu, Aurelien Bouteiller, George Bosilca, Mathieu Faverge, Jack Dongarra IPDPS 2015 Outline! Introduction & Motivation! Hierarchical
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 informationScientific Computing
Lecture on Scientific Computing Dr. Kersten Schmidt Lecture 20 Technische Universität Berlin Institut für Mathematik Wintersemester 2014/2015 Syllabus Linear Regression, Fast Fourier transform Modelling
More informationFinite Element Integration and Assembly on Modern Multi and Many-core Processors
Finite Element Integration and Assembly on Modern Multi and Many-core Processors Krzysztof Banaś, Jan Bielański, Kazimierz Chłoń AGH University of Science and Technology, Mickiewicza 30, 30-059 Kraków,
More informationAn evaluation of the Performance and Scalability of a Yellowstone Test-System in 5 Benchmarks
An evaluation of the Performance and Scalability of a Yellowstone Test-System in 5 Benchmarks WRF Model NASA Parallel Benchmark Intel MPI Bench My own personal benchmark HPC Challenge Benchmark Abstract
More informationParallel Processing/Programming
Parallel Processing/Programming with the applications to image processing Lectures: 1. Parallel Processing & Programming from high performance mono cores to multi- and many-cores 2. Programming Interfaces
More informationGPU-ACCELERATED SPECKLE MASKING RECONSTRUCTION ALGORITHM
Journal of the Korean Astronomical Society https://doi.org/10.5303/jkas.2018.51.3.65 51: 65 71, 2018 June pissn: 1225-4614 eissn: 2288-890X c 2018. The Korean Astronomical Society. All rights reserved.
More informationHigh performance Computing and O&G Challenges
High performance Computing and O&G Challenges 2 Seismic exploration challenges High Performance Computing and O&G challenges Worldwide Context Seismic,sub-surface imaging Computing Power needs Accelerating
More informationChapter 4: Multithreaded Programming
Chapter 4: Multithreaded Programming Silberschatz, Galvin and Gagne 2013 Chapter 4: Multithreaded Programming Overview Multicore Programming Multithreading Models Thread Libraries Implicit Threading Threading
More informationHeterogeneous platforms
Heterogeneous platforms Systems combining main processors and accelerators e.g., CPU + GPU, CPU + Intel MIC, AMD APU, ARM SoC Any platform using a GPU is a heterogeneous platform! Further in this talk
More informationCURRENT STATUS OF THE PROJECT TO ENABLE GAUSSIAN 09 ON GPGPUS
CURRENT STATUS OF THE PROJECT TO ENABLE GAUSSIAN 09 ON GPGPUS Roberto Gomperts (NVIDIA, Corp.) Michael Frisch (Gaussian, Inc.) Giovanni Scalmani (Gaussian, Inc.) Brent Leback (PGI) TOPICS Gaussian Design
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 informationApplying Multi-Core Model Checking to Hardware-Software Partitioning in Embedded Systems
V Brazilian Symposium on Computing Systems Engineering Applying Multi-Core Model Checking to Hardware-Software Partitioning in Embedded Systems Alessandro Trindade, Hussama Ismail, and Lucas Cordeiro Foz
More informationOpenACC. Part I. Ned Nedialkov. McMaster University Canada. October 2016
OpenACC. Part I Ned Nedialkov McMaster University Canada October 2016 Outline Introduction Execution model Memory model Compiling pgaccelinfo Example Speedups Profiling c 2016 Ned Nedialkov 2/23 Why accelerators
More informationOpenMP. A parallel language standard that support both data and functional Parallelism on a shared memory system
OpenMP A parallel language standard that support both data and functional Parallelism on a shared memory system Use by system programmers more than application programmers Considered a low level primitives
More informationPerformance Analysis of BLAS Libraries in SuperLU_DIST for SuperLU_MCDT (Multi Core Distributed) Development
Available online at www.prace-ri.eu Partnership for Advanced Computing in Europe Performance Analysis of BLAS Libraries in SuperLU_DIST for SuperLU_MCDT (Multi Core Distributed) Development M. Serdar Celebi
More informationHigh Performance Radar Signal Processsing
High Performance Radar Signal Processsing First Semester Report Fall 2012 by Justin Haze Prepared to partially fulfill the requirements for ECE401 Department of Electrical and Computer Engineering Colorado
More informationSome notes on efficient computing and high performance computing environments
Some notes on efficient computing and high performance computing environments Abhi Datta 1, Sudipto Banerjee 2 and Andrew O. Finley 3 July 31, 2017 1 Department of Biostatistics, Bloomberg School of Public
More informationINTRODUCTION TO OPENACC. Analyzing and Parallelizing with OpenACC, Feb 22, 2017
INTRODUCTION TO OPENACC Analyzing and Parallelizing with OpenACC, Feb 22, 2017 Objective: Enable you to to accelerate your applications with OpenACC. 2 Today s Objectives Understand what OpenACC is and
More informationParticle-in-Cell Simulations on Modern Computing Platforms. Viktor K. Decyk and Tajendra V. Singh UCLA
Particle-in-Cell Simulations on Modern Computing Platforms Viktor K. Decyk and Tajendra V. Singh UCLA Outline of Presentation Abstraction of future computer hardware PIC on GPUs OpenCL and Cuda Fortran
More informationParallel Computing. Hwansoo Han (SKKU)
Parallel Computing Hwansoo Han (SKKU) Unicore Limitations Performance scaling stopped due to Power consumption Wire delay DRAM latency Limitation in ILP 10000 SPEC CINT2000 2 cores/chip Xeon 3.0GHz Core2duo
More informationCUDA and OpenCL Implementations of 3D CT Reconstruction for Biomedical Imaging
CUDA and OpenCL Implementations of 3D CT Reconstruction for Biomedical Imaging Saoni Mukherjee, Nicholas Moore, James Brock and Miriam Leeser September 12, 2012 1 Outline Introduction to CT Scan, 3D reconstruction
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 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 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 informationOpenACC (Open Accelerators - Introduced in 2012)
OpenACC (Open Accelerators - Introduced in 2012) Open, portable standard for parallel computing (Cray, CAPS, Nvidia and PGI); introduced in 2012; GNU has an incomplete implementation. Uses directives in
More informationCMSC 714 Lecture 6 MPI vs. OpenMP and OpenACC. Guest Lecturer: Sukhyun Song (original slides by Alan Sussman)
CMSC 714 Lecture 6 MPI vs. OpenMP and OpenACC Guest Lecturer: Sukhyun Song (original slides by Alan Sussman) Parallel Programming with Message Passing and Directives 2 MPI + OpenMP Some applications can
More informationNVIDIA GTX200: TeraFLOPS Visual Computing. August 26, 2008 John Tynefield
NVIDIA GTX200: TeraFLOPS Visual Computing August 26, 2008 John Tynefield 2 Outline Execution Model Architecture Demo 3 Execution Model 4 Software Architecture Applications DX10 OpenGL OpenCL CUDA C Host
More informationLecture 13: Memory Consistency. + a Course-So-Far Review. Parallel Computer Architecture and Programming CMU , Spring 2013
Lecture 13: Memory Consistency + a Course-So-Far Review Parallel Computer Architecture and Programming Today: what you should know Understand the motivation for relaxed consistency models Understand the
More informationACCELERATING THE PRODUCTION OF SYNTHETIC SEISMOGRAMS BY A MULTICORE PROCESSOR CLUSTER WITH MULTIPLE GPUS
ACCELERATING THE PRODUCTION OF SYNTHETIC SEISMOGRAMS BY A MULTICORE PROCESSOR CLUSTER WITH MULTIPLE GPUS Ferdinando Alessi Annalisa Massini Roberto Basili INGV Introduction The simulation of wave propagation
More informationGeoImaging Accelerator Pansharpen Test Results. Executive Summary
Executive Summary After demonstrating the exceptional performance improvement in the orthorectification module (approximately fourteen-fold see GXL Ortho Performance Whitepaper), the same approach has
More informationA Parallelizing Compiler for Multicore Systems
A Parallelizing Compiler for Multicore Systems José M. Andión, Manuel Arenaz, Gabriel Rodríguez and Juan Touriño 17th International Workshop on Software and Compilers for Embedded Systems (SCOPES 2014)
More informationOpenMP. António Abreu. Instituto Politécnico de Setúbal. 1 de Março de 2013
OpenMP António Abreu Instituto Politécnico de Setúbal 1 de Março de 2013 António Abreu (Instituto Politécnico de Setúbal) OpenMP 1 de Março de 2013 1 / 37 openmp what? It s an Application Program Interface
More informationLinear Algebra libraries in Debian. DebConf 10 New York 05/08/2010 Sylvestre
Linear Algebra libraries in Debian Who I am? Core developer of Scilab (daily job) Debian Developer Involved in Debian mainly in Science and Java aspects sylvestre.ledru@scilab.org / sylvestre@debian.org
More informationAACE: Applications. Director, Application Acceleration Center of Excellence National Institute for Computational Sciences glenn-
AACE: Applications R. Glenn Brook Director, Application Acceleration Center of Excellence National Institute for Computational Sciences glenn- brook@tennessee.edu Ryan C. Hulguin Computational Science
More informationOpenMP Shared Memory Programming
OpenMP Shared Memory Programming John Burkardt, Information Technology Department, Virginia Tech.... Mathematics Department, Ajou University, Suwon, Korea, 13 May 2009.... http://people.sc.fsu.edu/ jburkardt/presentations/
More informationDepartment of Informatics V. Tsunami-Lab. Session 4: Optimization and OMP Michael Bader, Alex Breuer. Alex Breuer
Tsunami-Lab Session 4: Optimization and OMP Michael Bader, MAC-Cluster: Overview Intel Sandy Bridge (snb) AMD Bulldozer (bdz) Product Name (base frequency) Xeon E5-2670 (2.6 GHz) AMD Opteron 6274 (2.2
More informationDense Linear Algebra on Heterogeneous Platforms: State of the Art and Trends
Dense Linear Algebra on Heterogeneous Platforms: State of the Art and Trends Paolo Bientinesi AICES, RWTH Aachen pauldj@aices.rwth-aachen.de ComplexHPC Spring School 2013 Heterogeneous computing - Impact
More informationSolving Dense Linear Systems on Graphics Processors
Solving Dense Linear Systems on Graphics Processors Sergio Barrachina Maribel Castillo Francisco Igual Rafael Mayo Enrique S. Quintana-Ortí High Performance Computing & Architectures Group Universidad
More informationQuestions from last time
Questions from last time Pthreads vs regular thread? Pthreads are POSIX-standard threads (1995). There exist earlier and newer standards (C++11). Pthread is probably most common. Pthread API: about a 100
More informationDi Zhao Ohio State University MVAPICH User Group (MUG) Meeting, August , Columbus Ohio
Di Zhao zhao.1029@osu.edu Ohio State University MVAPICH User Group (MUG) Meeting, August 26-27 2013, Columbus Ohio Nvidia Kepler K20X Intel Xeon Phi 7120 Launch Date November 2012 Q2 2013 Processor Per-processor
More informationParallelization of Shortest Path Graph Kernels on Multi-Core CPUs and GPU
Parallelization of Shortest Path Graph Kernels on Multi-Core CPUs and GPU Lifan Xu Wei Wang Marco A. Alvarez John Cavazos Dongping Zhang Department of Computer and Information Science University of Delaware
More informationHigh-Performance Data Loading and Augmentation for Deep Neural Network Training
High-Performance Data Loading and Augmentation for Deep Neural Network Training Trevor Gale tgale@ece.neu.edu Steven Eliuk steven.eliuk@gmail.com Cameron Upright c.upright@samsung.com Roadmap 1. The General-Purpose
More informationDealing with Heterogeneous Multicores
Dealing with Heterogeneous Multicores François Bodin INRIA-UIUC, June 12 th, 2009 Introduction Main stream applications will rely on new multicore / manycore architectures It is about performance not parallelism
More informationDepartment of Informatics V. HPC-Lab. Session 2: OpenMP M. Bader, A. Breuer. Alex Breuer
HPC-Lab Session 2: OpenMP M. Bader, A. Breuer Meetings Date Schedule 10/13/14 Kickoff 10/20/14 Q&A 10/27/14 Presentation 1 11/03/14 H. Bast, Intel 11/10/14 Presentation 2 12/01/14 Presentation 3 12/08/14
More information