PhD Student. Associate Professor, Co-Director, Center for Computational Earth and Environmental Science. Abdulrahman Manea.
|
|
- Edwin Miller
- 5 years ago
- Views:
Transcription
1 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 Stanford University 1
2 Introduction Background 2D Black Box Geometric MG (GMG) 3D Semicoarsening Multigrid Future Work 2
3 Reservoir Simulation (Black Oil): Mass Conservation of Component α: Incompressible: Total Balance: Incompressible Pressure Equation: Solver is the most computationally expensive component Unknowns have varying nature Pressure (elliptic) vs. Saturation (Hyperbolic) Multistage preconditioning scheme Constraints Pressure Residual (CPR)* CPR with Multigrid as the first stage: very robust and widely used scheme Aramco s GigaPOWERS * Wallis, J.R., et al. SPE (1985) 3
4 Objective Design and Implement a massively Parallel Reservoir Simulation Multigrid on GPU Architectures Plan 1. Implement an optimized serial version of Multigrid to have a reasonable serial performance baseline 2. Design and implement a parallel version of Multigrid that harnesses the power the massively parallel GPU architectures 4
5 Introduction Background 2D Black Box Geometric MG (GMG) 3D Semicoarsening Multigrid Future Work 5
6 Descretized equation is A f x f = b f Basic 2-Level Multigrid Algorithm (3 steps) 1. The Pre-smoothing Step x f smooth A f, b f, x 0, υ 1 presmoothing postsmoothing 2. The Coarse-Grid Correction Step r f = b f A f x f r c = I c f r f e c = A c 1 r c e f = I f c e c x f = x f + e f 3. The Post-smoothing Step: x f smooth(a f, b f, x f, υ 2 ) Solve the Problem on the Coarse Grid * Brandt, A. (1977) 6
7 The prolongation and restriction operators weights depends on the PDE discontinuous coefficients λ p = q i-1,j+1 i,j+1 i+1,j+1 nw T i,j n ne T i,j T i,j I-1,J+1 I,J+1 I+1,J+1 i-1,j+1 i,j+1 i+1,j+1 i+1,j T i,j w i,j e T i,j i+1,j I-1,J i-1,j I,J i+1,j I+1,J sw T i,j s T i,j se T i,j i-1,j-1 i,j-1 i+1,j-1 i-1,j-1 i,j-1 i+1,j-1 I-1,J-1 I,J-1 I+1,J-1 * Alcouffe, R.E., et al. (1981) 7
8 Coarse grid operator: Manual Explicit handling of PDE on each coarser level Automatic (Black Box Multigrid) Using grid transfer operators: A c = I c f A f I f c = (I f c ) T A f f I c No info. about coarser grid is needed Used in Algebraic multigrid Preserve operator symmetry In Black Box Multigrid, two stages: Setup Stage: The interpolation, restriction and coarse grid operators are calculated. Solution Stage: Carrying out the cycling process Anisotropic PDE Coefficients Line Relaxation (2D), plane relaxation (3D) Semicoarsening *Dendy, J.E, (1982), (1986), Schaffer, S., (1998) 8
9 To handle anisotropies in all three dimensions (x,y,z): Alternating plane relaxation (too expensive) Semicoarsening with plane relaxation (cheaper) One plane-solve, and semicoarsening in the dimension orthogonal to that plane. When semicoarsening approach is used, with exact grid transfer operators, MG becomes a direct solver (i.e. a Schur Complement). However, grid transfer operators are not sparse, where A more efficient way is to approximate the exact grid transfer operators using a sparse (block diagonal) operator. 2D MG is used to define the components of the operator between every two planes (details can be found in *) *Schaffer, S., (1998) 9
10 Introduction Background 2D Black Box Geometric MG (GMG) 3D Semicoarsening Multigrid Future Work 10
11 Need a Multigrid solver capable of handling highly heterogeneous and anisotropic structured 2D reservoirs, thus: 2D Black Box Multigrid, with Alternating line-relaxation Testing Solver s convergence behavior: Test the convergence ratio for the same problem with varying sizes (using grid refinement) Compare the performance with well-established and widely-used Multigrid solvers, e.g. SAMG: Algebraic Multigrid Solver form Fraunhofer Institute for Algorithms and Scientific Computing (SCAI) MGD9V, etc Test Models Geostatically Generated using the Stanford Geostatistical Modeling Software (SGeMS) Derived from SPE10 Comparative Solution Project Model. large permeability variations of 8-12 orders of magnitude 11
12 SPE10, Layer 70 Residual Reduction Factor = r k+1 2 r k 2 12
13 ¼ Million Cell 1 Million Cell Computational Time Comparison (SPE10 Layer 85 Refined to 1 Million Cells): GMG: ~ 4.5 sec SAMG: ~ 7.0 sec 13
14 Parallelization of every component of the algorithm Both setup stage and solution stage Does not sacrifice algorithmic scalability (convergence rate) Smoother Alternating zebra-line relaxation Effectively handles anisotropies Coarsest Solve 4-color GS relaxation (to handle 9-point stencils) 14
15 Shared-Memory Parallelization OpenMP Coarse threads Hence coarse-scale parallelization Multiple cells (multiple lines) per thread Sparse Matrix Format CSR for cache coherence Tridiagonal Solver: Thomas Algorithm Serial within each line (i.e. thread) but several lines are handled in parallel (zebra-coloring) Architecture: 12 Intel Xeon X GHz cores with 48 GB Memory 15
16 Fine Threads Fine-scale parallelization Single cell per thread Sparse Matrix Format Diagonal with column major ordering Ideal for structured problems Coalesces memory accesses Minimizing storage requirements Exploits the banded matrix structure for efficient data access Minimize expensive communication with host Fit the whole problem on the GPU (up to 16M double precision) 16
17 non-coalesced Tridiagonal Solver Parallel cyclic reduction (PCR) in Batch* to exploit: fine scale parallelism within the line coarse scale parallelism exposed by the zebra ordering of lines Threads operates in two stages: Preparation Stage Solution Stage For coalescing memory accesses during the Preparation Stage (NOTE: grid points are numbered along x-direction): In X-line Relaxation: Each x-line is assigned to a block of threads In Y-line Relaxation: Points with the same x-coordinate are assigned to a block of threads y x coalesced *Using NVIDIA CUSPARSE Library: ( 17
18 Criteria Multicore GPU Architecture Specs 12 Intel Xeon X GHz cores with 48 GB Memory Nvidia Fermi-Based C2070 with 448 CUDA Cores and 6 GB Memory Matrix Structure CSR Format for cache coherence Diagonal Format with column major format (for coalescing memory accesses) Parallelization API Parallelization Granularity Tridiagonal Solver Algorithm (for line relaxation) OpenMP Multiple cells per thread (coarse) Thomas Algorithm (serial within each line, but multiple lines are handled in parallel by zebra coloring) CUDA One cell per thread (fine) Parallel Cyclic Reduction in Batch (Parallel within each line and multiple lines are handled in parallel as well) 18
19 Homogeneous Permeability Case: Solved with just one V(0,1) cycle Residual reduction by 10 9 Focuses on the scalability of the setup stage Heterogeneous Permeability Case: Derived from SPE10 85 th Layer by grid refinement Solved with six V(0,1) cycles Residual reduction by 10 9 Focuses on the scalability of the solution stage Problem Sizes: 1 Million, 4 Million and 16 Million cells 19
20 20
21 21
22 22
23 23
24 Introduction Background 2D Black Box Geometric MG (GMG) 3D Semicoarsening Multigrid Future Work 24
25 In reservoir simulation, z-direction Huge variations due to natural deposition Severe anisotropy compared to x/y directions An effect of discretization (pancake models). Semicoarsening in z-direction, and plane relaxation in the x-y plane We can use 2D MG for both: Setup Stage: construction of grid transfer operators Solution Stage: x-y plane relaxation 25
26 Parallelize plane solve kernel in both: Setup Stage: construction of grid transfer operators Five V(0,1) cycles/plane for approximating an exact solve Solution Stage: red/black plane relaxation One V(0,1) cycle/plane for doing plan-relaxation z 2D MG for Plane Solve Note that those 2D V(0,1) cycles are already parallelized (using the 2D GMG algorithm explained earlier) Other kernels are amenable to parallelization on the GPU, but are not tackled yet (under progress). 26
27 Implementation: CPU: Use OpenMP threads to distribute the plane solves across multiple cores GPU: Use CUDA with OpenMP to distribute the plane solves to multiple GPU s Platform: CPU: 24 Intel(R) Xeon(R) CPU 2.80GHz with HT and 180 GB Memory GPU: 6 Nvidia Fermi-Based M2090 s Test cases: homogeneous and heterogeneous (SPE 10) with various sizes Results: average time for the plane solves for both setup and solution stages 27
28 Speed Up K x 129 ~ 2M cells 66K x 33 ~ 2M cells 1M x 17 ~ 18M cells 4M x 17 ~ 71M cells cores 1 GPU 2 GPU's 3 GPU's 4 GPU's 5 GPU's 6 GPU's 28
29 Speed Up K x 129 ~ 2M cells 66K x 33 ~ 2M cells 1M x 17 ~ 18M cells 4M x 17 ~ 71M cells cores 1 GPU 2 GPU's 3 GPU's 4 GPU's 5 GPU's 6 GPU's 29
30 Planes need to be sufficiently large ( > 1M cells) for a noticeable advantage This is good for reservoir simulation, as grid refinement studies are usually made by refining the horizontal planes. Beyond 2-3 GPU s, no performance is gained Could be due to number of planes, or plane size.. Needs more investigation and profiling 30
31 Accelerate other kernels of 3D Semicoarsening Multigrid using GPU s (such as coarse operator construction, etc) Algebraic Multiscale Solver on GPU s is Next! 31
32 Thank you for your listening Questions 32
Matrix-free multi-gpu Implementation of Elliptic Solvers for strongly anisotropic PDEs
Iterative Solvers Numerical Results Conclusion and outlook 1/18 Matrix-free multi-gpu Implementation of Elliptic Solvers for strongly anisotropic PDEs Eike Hermann Müller, Robert Scheichl, Eero Vainikko
More informationEfficient multigrid solvers for strongly anisotropic PDEs in atmospheric modelling
Iterative Solvers Numerical Results Conclusion and outlook 1/22 Efficient multigrid solvers for strongly anisotropic PDEs in atmospheric modelling Part II: GPU Implementation and Scaling on Titan Eike
More informationIntroduction to Multigrid and its Parallelization
Introduction to Multigrid and its Parallelization! Thomas D. Economon Lecture 14a May 28, 2014 Announcements 2 HW 1 & 2 have been returned. Any questions? Final projects are due June 11, 5 pm. If you are
More informationHow to Optimize Geometric Multigrid Methods on GPUs
How to Optimize Geometric Multigrid Methods on GPUs Markus Stürmer, Harald Köstler, Ulrich Rüde System Simulation Group University Erlangen March 31st 2011 at Copper Schedule motivation imaging in gradient
More informationD036 Accelerating Reservoir Simulation with GPUs
D036 Accelerating Reservoir Simulation with GPUs K.P. Esler* (Stone Ridge Technology), S. Atan (Marathon Oil Corp.), B. Ramirez (Marathon Oil Corp.) & V. Natoli (Stone Ridge Technology) SUMMARY Over the
More informationAlgebraic Multigrid (AMG) for Ground Water Flow and Oil Reservoir Simulation
lgebraic Multigrid (MG) for Ground Water Flow and Oil Reservoir Simulation Klaus Stüben, Patrick Delaney 2, Serguei Chmakov 3 Fraunhofer Institute SCI, Klaus.Stueben@scai.fhg.de, St. ugustin, Germany 2
More informationEfficient Finite Element Geometric Multigrid Solvers for Unstructured Grids on GPUs
Efficient Finite Element Geometric Multigrid Solvers for Unstructured Grids on GPUs Markus Geveler, Dirk Ribbrock, Dominik Göddeke, Peter Zajac, Stefan Turek Institut für Angewandte Mathematik TU Dortmund,
More informationACCELERATING CFD AND RESERVOIR SIMULATIONS WITH ALGEBRAIC MULTI GRID Chris Gottbrath, Nov 2016
ACCELERATING CFD AND RESERVOIR SIMULATIONS WITH ALGEBRAIC MULTI GRID Chris Gottbrath, Nov 2016 Challenges What is Algebraic Multi-Grid (AMG)? AGENDA Why use AMG? When to use AMG? NVIDIA AmgX Results 2
More informationHighly Parallel Multigrid Solvers for Multicore and Manycore Processors
Highly Parallel Multigrid Solvers for Multicore and Manycore Processors Oleg Bessonov (B) Institute for Problems in Mechanics of the Russian Academy of Sciences, 101, Vernadsky Avenue, 119526 Moscow, Russia
More informationSoftware and Performance Engineering for numerical codes on GPU clusters
Software and Performance Engineering for numerical codes on GPU clusters H. Köstler International Workshop of GPU Solutions to Multiscale Problems in Science and Engineering Harbin, China 28.7.2010 2 3
More informationS0432 NEW IDEAS FOR MASSIVELY PARALLEL PRECONDITIONERS
S0432 NEW IDEAS FOR MASSIVELY PARALLEL PRECONDITIONERS John R Appleyard Jeremy D Appleyard Polyhedron Software with acknowledgements to Mark A Wakefield Garf Bowen Schlumberger Outline of Talk Reservoir
More informationGPU Implementation of Elliptic Solvers in NWP. Numerical Weather- and Climate- Prediction
1/8 GPU Implementation of Elliptic Solvers in Numerical Weather- and Climate- Prediction Eike Hermann Müller, Robert Scheichl Department of Mathematical Sciences EHM, Xu Guo, Sinan Shi and RS: http://arxiv.org/abs/1302.7193
More informationParallel High-Order Geometric Multigrid Methods on Adaptive Meshes for Highly Heterogeneous Nonlinear Stokes Flow Simulations of Earth s Mantle
ICES Student Forum The University of Texas at Austin, USA November 4, 204 Parallel High-Order Geometric Multigrid Methods on Adaptive Meshes for Highly Heterogeneous Nonlinear Stokes Flow Simulations of
More information3D Helmholtz Krylov Solver Preconditioned by a Shifted Laplace Multigrid Method on Multi-GPUs
3D Helmholtz Krylov Solver Preconditioned by a Shifted Laplace Multigrid Method on Multi-GPUs H. Knibbe, C. W. Oosterlee, C. Vuik Abstract We are focusing on an iterative solver for the three-dimensional
More informationsmooth coefficients H. Köstler, U. Rüde
A robust multigrid solver for the optical flow problem with non- smooth coefficients H. Köstler, U. Rüde Overview Optical Flow Problem Data term and various regularizers A Robust Multigrid Solver Galerkin
More informationTowards a complete FEM-based simulation toolkit on GPUs: Geometric Multigrid solvers
Towards a complete FEM-based simulation toolkit on GPUs: Geometric Multigrid solvers Markus Geveler, Dirk Ribbrock, Dominik Göddeke, Peter Zajac, Stefan Turek Institut für Angewandte Mathematik TU Dortmund,
More informationAccelerating image registration on GPUs
Accelerating image registration on GPUs Harald Köstler, Sunil Ramgopal Tatavarty SIAM Conference on Imaging Science (IS10) 13.4.2010 Contents Motivation: Image registration with FAIR GPU Programming Combining
More informationAmgX 2.0: Scaling toward CORAL Joe Eaton, November 19, 2015
AmgX 2.0: Scaling toward CORAL Joe Eaton, November 19, 2015 Agenda Introduction to AmgX Current Capabilities Scaling V2.0 Roadmap for the future 2 AmgX Fast, scalable linear solvers, emphasis on iterative
More informationMathematical Methods in Fluid Dynamics and Simulation of Giant Oil and Gas Reservoirs. 3-5 September 2012 Swissotel The Bosphorus, Istanbul, Turkey
Mathematical Methods in Fluid Dynamics and Simulation of Giant Oil and Gas Reservoirs 3-5 September 2012 Swissotel The Bosphorus, Istanbul, Turkey Fast and robust solvers for pressure systems on the GPU
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 informationAlgorithms, System and Data Centre Optimisation for Energy Efficient HPC
2015-09-14 Algorithms, System and Data Centre Optimisation for Energy Efficient HPC Vincent Heuveline URZ Computing Centre of Heidelberg University EMCL Engineering Mathematics and Computing Lab 1 Energy
More informationCommunication-Avoiding Optimization of Geometric Multigrid on GPUs
Communication-Avoiding Optimization of Geometric Multigrid on GPUs Amik Singh James Demmel, Ed. Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2012-258
More informationEfficient AMG on Hybrid GPU Clusters. ScicomP Jiri Kraus, Malte Förster, Thomas Brandes, Thomas Soddemann. Fraunhofer SCAI
Efficient AMG on Hybrid GPU Clusters ScicomP 2012 Jiri Kraus, Malte Förster, Thomas Brandes, Thomas Soddemann Fraunhofer SCAI Illustration: Darin McInnis Motivation Sparse iterative solvers benefit from
More informationSELECTIVE ALGEBRAIC MULTIGRID IN FOAM-EXTEND
Student Submission for the 5 th OpenFOAM User Conference 2017, Wiesbaden - Germany: SELECTIVE ALGEBRAIC MULTIGRID IN FOAM-EXTEND TESSA UROIĆ Faculty of Mechanical Engineering and Naval Architecture, Ivana
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 informationHYPERDRIVE IMPLEMENTATION AND ANALYSIS OF A PARALLEL, CONJUGATE GRADIENT LINEAR SOLVER PROF. BRYANT PROF. KAYVON 15618: PARALLEL COMPUTER ARCHITECTURE
HYPERDRIVE IMPLEMENTATION AND ANALYSIS OF A PARALLEL, CONJUGATE GRADIENT LINEAR SOLVER AVISHA DHISLE PRERIT RODNEY ADHISLE PRODNEY 15618: PARALLEL COMPUTER ARCHITECTURE PROF. BRYANT PROF. KAYVON LET S
More informationReconstruction of Trees from Laser Scan Data and further Simulation Topics
Reconstruction of Trees from Laser Scan Data and further Simulation Topics Helmholtz-Research Center, Munich Daniel Ritter http://www10.informatik.uni-erlangen.de Overview 1. Introduction of the Chair
More informationLarge scale Imaging on Current Many- Core Platforms
Large scale Imaging on Current Many- Core Platforms SIAM Conf. on Imaging Science 2012 May 20, 2012 Dr. Harald Köstler Chair for System Simulation Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen,
More informationMultigrid Algorithms for Three-Dimensional RANS Calculations - The SUmb Solver
Multigrid Algorithms for Three-Dimensional RANS Calculations - The SUmb Solver Juan J. Alonso Department of Aeronautics & Astronautics Stanford University CME342 Lecture 14 May 26, 2014 Outline Non-linear
More informationScalability of Elliptic Solvers in NWP. Weather and Climate- Prediction
Background Scaling results Tensor product geometric multigrid Summary and Outlook 1/21 Scalability of Elliptic Solvers in Numerical Weather and Climate- Prediction Eike Hermann Müller, Robert Scheichl
More informationAutomatic Generation of Algorithms and Data Structures for Geometric Multigrid. Harald Köstler, Sebastian Kuckuk Siam Parallel Processing 02/21/2014
Automatic Generation of Algorithms and Data Structures for Geometric Multigrid Harald Köstler, Sebastian Kuckuk Siam Parallel Processing 02/21/2014 Introduction Multigrid Goal: Solve a partial differential
More informationSmoothers. < interactive example > Partial Differential Equations Numerical Methods for PDEs Sparse Linear Systems
Smoothers Partial Differential Equations Disappointing convergence rates observed for stationary iterative methods are asymptotic Much better progress may be made initially before eventually settling into
More information14MMFD-34 Parallel Efficiency and Algorithmic Optimality in Reservoir Simulation on GPUs
14MMFD-34 Parallel Efficiency and Algorithmic Optimality in Reservoir Simulation on GPUs K. Esler, D. Dembeck, K. Mukundakrishnan, V. Natoli, J. Shumway and Y. Zhang Stone Ridge Technology, Bel Air, MD
More informationHigh Performance Computing for PDE Towards Petascale Computing
High Performance Computing for PDE Towards Petascale Computing S. Turek, D. Göddeke with support by: Chr. Becker, S. Buijssen, M. Grajewski, H. Wobker Institut für Angewandte Mathematik, Univ. Dortmund
More informationMultigrid Pattern. I. Problem. II. Driving Forces. III. Solution
Multigrid Pattern I. Problem Problem domain is decomposed into a set of geometric grids, where each element participates in a local computation followed by data exchanges with adjacent neighbors. The grids
More informationAccelerated ANSYS Fluent: Algebraic Multigrid on a GPU. Robert Strzodka NVAMG Project Lead
Accelerated ANSYS Fluent: Algebraic Multigrid on a GPU Robert Strzodka NVAMG Project Lead A Parallel Success Story in Five Steps 2 Step 1: Understand Application ANSYS Fluent Computational Fluid Dynamics
More informationEfficient Tridiagonal Solvers for ADI methods and Fluid Simulation
Efficient Tridiagonal Solvers for ADI methods and Fluid Simulation Nikolai Sakharnykh - NVIDIA San Jose Convention Center, San Jose, CA September 21, 2010 Introduction Tridiagonal solvers very popular
More informationETNA Kent State University
Electronic Transactions on Numerical Analysis. Volume, 2, pp. 92. Copyright 2,. ISSN 68-963. ETNA BEHAVIOR OF PLANE RELAXATION METHODS AS MULTIGRID SMOOTHERS IGNACIO M. LLORENTE AND N. DUANE MELSON Abstract.
More informationA Comparison of Algebraic Multigrid Preconditioners using Graphics Processing Units and Multi-Core Central Processing Units
A Comparison of Algebraic Multigrid Preconditioners using Graphics Processing Units and Multi-Core Central Processing Units Markus Wagner, Karl Rupp,2, Josef Weinbub Institute for Microelectronics, TU
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 informationGPU-Accelerated Algebraic Multigrid for Commercial Applications. Joe Eaton, Ph.D. Manager, NVAMG CUDA Library NVIDIA
GPU-Accelerated Algebraic Multigrid for Commercial Applications Joe Eaton, Ph.D. Manager, NVAMG CUDA Library NVIDIA ANSYS Fluent 2 Fluent control flow Accelerate this first Non-linear iterations Assemble
More informationFOR P3: A monolithic multigrid FEM solver for fluid structure interaction
FOR 493 - P3: A monolithic multigrid FEM solver for fluid structure interaction Stefan Turek 1 Jaroslav Hron 1,2 Hilmar Wobker 1 Mudassar Razzaq 1 1 Institute of Applied Mathematics, TU Dortmund, Germany
More informationS4289: Efficient solution of multiple scalar and block-tridiagonal equations
S4289: Efficient solution of multiple scalar and block-tridiagonal equations Endre László endre.laszlo [at] oerc.ox.ac.uk Oxford e-research Centre, University of Oxford, UK Pázmány Péter Catholic University,
More informationEfficient Imaging Algorithms on Many-Core Platforms
Efficient Imaging Algorithms on Many-Core Platforms H. Köstler Dagstuhl, 22.11.2011 Contents Imaging Applications HDR Compression performance of PDE-based models Image Denoising performance of patch-based
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 informationGPU Implementation of Implicit Runge-Kutta Methods
GPU Implementation of Implicit Runge-Kutta Methods Navchetan Awasthi, Abhijith J Supercomputer Education and Research Centre Indian Institute of Science, Bangalore, India navchetanawasthi@gmail.com, abhijith31792@gmail.com
More informationPROGRAMMING OF MULTIGRID METHODS
PROGRAMMING OF MULTIGRID METHODS LONG CHEN In this note, we explain the implementation detail of multigrid methods. We will use the approach by space decomposition and subspace correction method; see Chapter:
More informationAdvances of parallel computing. Kirill Bogachev May 2016
Advances of parallel computing Kirill Bogachev May 2016 Demands in Simulations Field development relies more and more on static and dynamic modeling of the reservoirs that has come a long way from being
More informationDistributed NVAMG. Design and Implementation of a Scalable Algebraic Multigrid Framework for a Cluster of GPUs
Distributed NVAMG Design and Implementation of a Scalable Algebraic Multigrid Framework for a Cluster of GPUs Istvan Reguly (istvan.reguly at oerc.ox.ac.uk) Oxford e-research Centre NVIDIA Summer Internship
More informationAuto-tuning Multigrid with PetaBricks
Auto-tuning with PetaBricks Cy Chan Joint Work with: Jason Ansel Yee Lok Wong Saman Amarasinghe Alan Edelman Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology
More informationINTEGRATION OF LOCAL-GLOBAL UPSCALING AND GRID ADAPTIVITY FOR SIMULATION OF SUBSURFACE FLOW IN HETEROGENEOUS FORMATIONS
INTEGRATION OF LOCAL-GLOBAL UPSCALING AND GRID ADAPTIVITY FOR SIMULATION OF SUBSURFACE FLOW IN HETEROGENEOUS FORMATIONS M. GERRITSEN AND J. V. LAMBERS Abstract. We propose a methodology, called multi-level
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 the Comparative Performance of Parallel Algorithms on Small GPU/CUDA Clusters
1 On the Comparative Performance of Parallel Algorithms on Small GPU/CUDA Clusters N. P. Karunadasa & D. N. Ranasinghe University of Colombo School of Computing, Sri Lanka nishantha@opensource.lk, dnr@ucsc.cmb.ac.lk
More informationHybrid KAUST Many Cores and OpenACC. Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS
+ Hybrid Computing @ KAUST Many Cores and OpenACC Alain Clo - KAUST Research Computing Saber Feki KAUST Supercomputing Lab Florent Lebeau - CAPS + Agenda Hybrid Computing n Hybrid Computing n From Multi-Physics
More informationTurbostream: A CFD solver for manycore
Turbostream: A CFD solver for manycore processors Tobias Brandvik Whittle Laboratory University of Cambridge Aim To produce an order of magnitude reduction in the run-time of CFD solvers for the same hardware
More informationWhy Use the GPU? How to Exploit? New Hardware Features. Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid. Semiconductor trends
Imagine stream processor; Bill Dally, Stanford Connection Machine CM; Thinking Machines Sparse Matrix Solvers on the GPU: Conjugate Gradients and Multigrid Jeffrey Bolz Eitan Grinspun Caltech Ian Farmer
More informationFast Tridiagonal Solvers on GPU
Fast Tridiagonal Solvers on GPU Yao Zhang John Owens UC Davis Jonathan Cohen NVIDIA GPU Technology Conference 2009 Outline Introduction Algorithms Design algorithms for GPU architecture Performance Bottleneck-based
More informationLarge-scale Gas Turbine Simulations on GPU clusters
Large-scale Gas Turbine Simulations on GPU clusters Tobias Brandvik and Graham Pullan Whittle Laboratory University of Cambridge A large-scale simulation Overview PART I: Turbomachinery PART II: Stencil-based
More informationMultigrid Solvers in CFD. David Emerson. Scientific Computing Department STFC Daresbury Laboratory Daresbury, Warrington, WA4 4AD, UK
Multigrid Solvers in CFD David Emerson Scientific Computing Department STFC Daresbury Laboratory Daresbury, Warrington, WA4 4AD, UK david.emerson@stfc.ac.uk 1 Outline Multigrid: general comments Incompressible
More informationFOR ALL GRID SIZES. Thor Gjesdal. Christian Michelsen Research A/S. N-5036 Fantoft, Norway SUMMARY
A CELL-CENTERED MULTIGRID ALGORITHM FOR ALL GRID SIZES Thor Gjesdal Christian Michelsen Research A/S N-5036 Fantoft, Norway SUMMARY Multigrid methods are optimal; that is, their rate of convergence is
More informationVery fast simulation of nonlinear water waves in very large numerical wave tanks on affordable graphics cards
Very fast simulation of nonlinear water waves in very large numerical wave tanks on affordable graphics cards By Allan P. Engsig-Karup, Morten Gorm Madsen and Stefan L. Glimberg DTU Informatics Workshop
More informationEfficient Multi-GPU CUDA Linear Solvers for OpenFOAM
Efficient Multi-GPU CUDA Linear Solvers for OpenFOAM Alexander Monakov, amonakov@ispras.ru Institute for System Programming of Russian Academy of Sciences March 20, 2013 1 / 17 Problem Statement In OpenFOAM,
More informationComputational Acceleration of Image Inpainting Alternating-Direction Implicit (ADI) Method Using GPU CUDA
Computational Acceleration of Inpainting Alternating-Direction Implicit (ADI) Method Using GPU CUDA Mutaqin Akbar mutaqin.akbar@gmail.com Pranowo pran@mail.uajy.ac.id Suyoto suyoto@mail.uajy.ac.id Abstract
More informationSummer 2009 REU: Introduction to Some Advanced Topics in Computational Mathematics
Summer 2009 REU: Introduction to Some Advanced Topics in Computational Mathematics Moysey Brio & Paul Dostert July 4, 2009 1 / 18 Sparse Matrices In many areas of applied mathematics and modeling, one
More informationContents. I The Basic Framework for Stationary Problems 1
page v Preface xiii I The Basic Framework for Stationary Problems 1 1 Some model PDEs 3 1.1 Laplace s equation; elliptic BVPs... 3 1.1.1 Physical experiments modeled by Laplace s equation... 5 1.2 Other
More informationGPU-based Parallel Reservoir Simulators
GPU-based Parallel Reservoir Simulators Zhangxin Chen 1, Hui Liu 1, Song Yu 1, Ben Hsieh 1 and Lei Shao 1 Key words: GPU computing, reservoir simulation, linear solver, parallel 1 Introduction Nowadays
More informationFast Iterative Solvers for Markov Chains, with Application to Google's PageRank. Hans De Sterck
Fast Iterative Solvers for Markov Chains, with Application to Google's PageRank Hans De Sterck Department of Applied Mathematics University of Waterloo, Ontario, Canada joint work with Steve McCormick,
More informationLarge Displacement Optical Flow & Applications
Large Displacement Optical Flow & Applications Narayanan Sundaram, Kurt Keutzer (Parlab) In collaboration with Thomas Brox (University of Freiburg) Michael Tao (University of California Berkeley) Parlab
More informationGeometric Multigrid on Multicore Architectures: Performance-Optimized Complex Diffusion
Geometric Multigrid on Multicore Architectures: Performance-Optimized Complex Diffusion M. Stürmer, H. Köstler, and U. Rüde Lehrstuhl für Systemsimulation Friedrich-Alexander-Universität Erlangen-Nürnberg
More informationGPU Cluster Computing for FEM
GPU Cluster Computing for FEM Dominik Göddeke Sven H.M. Buijssen, Hilmar Wobker and Stefan Turek Angewandte Mathematik und Numerik TU Dortmund, Germany dominik.goeddeke@math.tu-dortmund.de GPU Computing
More informationIntegrating GPUs as fast co-processors into the existing parallel FE package FEAST
Integrating GPUs as fast co-processors into the existing parallel FE package FEAST Dipl.-Inform. Dominik Göddeke (dominik.goeddeke@math.uni-dortmund.de) Mathematics III: Applied Mathematics and Numerics
More informationTwo-Phase flows on massively parallel multi-gpu clusters
Two-Phase flows on massively parallel multi-gpu clusters Peter Zaspel Michael Griebel Institute for Numerical Simulation Rheinische Friedrich-Wilhelms-Universität Bonn Workshop Programming of Heterogeneous
More informationCase study: GPU acceleration of parallel multigrid solvers
Case study: GPU acceleration of parallel multigrid solvers Dominik Göddeke Architecture of Computing Systems GPGPU and CUDA Tutorials Dresden, Germany, February 25 2008 2 Acknowledgements Hilmar Wobker,
More informationNumerical Algorithms on Multi-GPU Architectures
Numerical Algorithms on Multi-GPU Architectures Dr.-Ing. Harald Köstler 2 nd International Workshops on Advances in Computational Mechanics Yokohama, Japan 30.3.2010 2 3 Contents Motivation: Applications
More informationWhat is Multigrid? They have been extended to solve a wide variety of other problems, linear and nonlinear.
AMSC 600/CMSC 760 Fall 2007 Solution of Sparse Linear Systems Multigrid, Part 1 Dianne P. O Leary c 2006, 2007 What is Multigrid? Originally, multigrid algorithms were proposed as an iterative method to
More informationCUDA GPGPU Workshop 2012
CUDA GPGPU Workshop 2012 Parallel Programming: C thread, Open MP, and Open MPI Presenter: Nasrin Sultana Wichita State University 07/10/2012 Parallel Programming: Open MP, MPI, Open MPI & CUDA Outline
More informationSampling Using GPU Accelerated Sparse Hierarchical Models
Sampling Using GPU Accelerated Sparse Hierarchical Models Miroslav Stoyanov Oak Ridge National Laboratory supported by Exascale Computing Project (ECP) exascaleproject.org April 9, 28 Miroslav Stoyanov
More informationAccelerating Double Precision FEM Simulations with GPUs
Accelerating Double Precision FEM Simulations with GPUs Dominik Göddeke 1 3 Robert Strzodka 2 Stefan Turek 1 dominik.goeddeke@math.uni-dortmund.de 1 Mathematics III: Applied Mathematics and Numerics, University
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 informationKrishnan Suresh Associate Professor Mechanical Engineering
Large Scale FEA on the GPU Krishnan Suresh Associate Professor Mechanical Engineering High-Performance Trick Computations (i.e., 3.4*1.22): essentially free Memory access determines speed of code Pick
More informationGeneric framework for taking geological models as input for reservoir simulation
Generic framework for taking geological models as input for reservoir simulation Collaborators: SINTEF: Texas A&M: NTNU: Stanford Stein Krogstad, Knut-Andreas Lie, Vera L. Hauge Yalchin Efendiev and Akhil
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 informationData mining with sparse grids using simplicial basis functions
Data mining with sparse grids using simplicial basis functions Jochen Garcke and Michael Griebel Institut für Angewandte Mathematik Universität Bonn Part of the work was supported within the project 03GRM6BN
More informationMixed-Precision GPU-Multigrid Solvers with Strong Smoothers and Applications in CFD and CSM
Mixed-Precision GPU-Multigrid Solvers with Strong Smoothers and Applications in CFD and CSM Dominik Göddeke and Robert Strzodka Institut für Angewandte Mathematik (LS3), TU Dortmund Max Planck Institut
More informationHigh Performance Computing for PDE Some numerical aspects of Petascale Computing
High Performance Computing for PDE Some numerical aspects of Petascale Computing S. Turek, D. Göddeke with support by: Chr. Becker, S. Buijssen, M. Grajewski, H. Wobker Institut für Angewandte Mathematik,
More informationAn introduction to mesh generation Part IV : elliptic meshing
Elliptic An introduction to mesh generation Part IV : elliptic meshing Department of Civil Engineering, Université catholique de Louvain, Belgium Elliptic Curvilinear Meshes Basic concept A curvilinear
More information3D ADI Method for Fluid Simulation on Multiple GPUs. Nikolai Sakharnykh, NVIDIA Nikolay Markovskiy, NVIDIA
3D ADI Method for Fluid Simulation on Multiple GPUs Nikolai Sakharnykh, NVIDIA Nikolay Markovskiy, NVIDIA Introduction Fluid simulation using direct numerical methods Gives the most accurate result Requires
More informationGPU Acceleration of Unmodified CSM and CFD Solvers
GPU Acceleration of Unmodified CSM and CFD Solvers Dominik Göddeke Sven H.M. Buijssen, Hilmar Wobker and Stefan Turek Angewandte Mathematik und Numerik TU Dortmund, Germany dominik.goeddeke@math.tu-dortmund.de
More informationPARALUTION - a Library for Iterative Sparse Methods on CPU and GPU
- a Library for Iterative Sparse Methods on CPU and GPU Dimitar Lukarski Division of Scientific Computing Department of Information Technology Uppsala Programming for Multicore Architectures Research Center
More informationAccelerating GPU computation through mixed-precision methods. Michael Clark Harvard-Smithsonian Center for Astrophysics Harvard University
Accelerating GPU computation through mixed-precision methods Michael Clark Harvard-Smithsonian Center for Astrophysics Harvard University Outline Motivation Truncated Precision using CUDA Solving Linear
More informationFast Radial Basis Functions for Engineering Applications. Prof. Marco Evangelos Biancolini University of Rome Tor Vergata
Fast Radial Basis Functions for Engineering Applications Prof. Marco Evangelos Biancolini University of Rome Tor Vergata Outline 2 RBF background Fast RBF on HPC Engineering Applications Mesh morphing
More informationAsynchronous OpenCL/MPI numerical simulations of conservation laws
Asynchronous OpenCL/MPI numerical simulations of conservation laws Philippe HELLUY 1,3, Thomas STRUB 2. 1 IRMA, Université de Strasbourg, 2 AxesSim, 3 Inria Tonus, France IWOCL 2015, Stanford Conservation
More informationRAMSES on the GPU: An OpenACC-Based Approach
RAMSES on the GPU: An OpenACC-Based Approach Claudio Gheller (ETHZ-CSCS) Giacomo Rosilho de Souza (EPFL Lausanne) Romain Teyssier (University of Zurich) Markus Wetzstein (ETHZ-CSCS) PRACE-2IP project EU
More informationMultigrid solvers M. M. Sussman sussmanm@math.pitt.edu Office Hours: 11:10AM-12:10PM, Thack 622 May 12 June 19, 2014 1 / 43 Multigrid Geometrical multigrid Introduction Details of GMG Summary Algebraic
More informationPerformance and accuracy of hardware-oriented native-, solvers in FEM simulations
Performance and accuracy of hardware-oriented native-, emulated- and mixed-precision solvers in FEM simulations Dominik Göddeke Angewandte Mathematik und Numerik, Universität Dortmund Acknowledgments Joint
More informationLecture 15: More Iterative Ideas
Lecture 15: More Iterative Ideas David Bindel 15 Mar 2010 Logistics HW 2 due! Some notes on HW 2. Where we are / where we re going More iterative ideas. Intro to HW 3. More HW 2 notes See solution code!
More informationRecent developments for the multigrid scheme of the DLR TAU-Code
www.dlr.de Chart 1 > 21st NIA CFD Seminar > Axel Schwöppe Recent development s for the multigrid scheme of the DLR TAU-Code > Apr 11, 2013 Recent developments for the multigrid scheme of the DLR TAU-Code
More informationAn Efficient, Geometric Multigrid Solver for the Anisotropic Diffusion Equation in Two and Three Dimensions
1 n Efficient, Geometric Multigrid Solver for the nisotropic Diffusion Equation in Two and Three Dimensions Tolga Tasdizen, Ross Whitaker UUSCI-2004-002 Scientific Computing and Imaging Institute University
More informationFinite Element Multigrid Solvers for PDE Problems on GPUs and GPU Clusters
Finite Element Multigrid Solvers for PDE Problems on GPUs and GPU Clusters Robert Strzodka Integrative Scientific Computing Max Planck Institut Informatik www.mpi-inf.mpg.de/ ~strzodka Dominik Göddeke
More informationME964 High Performance Computing for Engineering Applications
ME964 High Performance Computing for Engineering Applications Outlining Midterm Projects Topic 3: GPU-based FEA Topic 4: GPU Direct Solver for Sparse Linear Algebra March 01, 2011 Dan Negrut, 2011 ME964
More information