Multicore Parallelization of Determinant Quantum Monte Carlo Simulations

Size: px
Start display at page:

Download "Multicore Parallelization of Determinant Quantum Monte Carlo Simulations"

Transcription

1 Multicore Parallelization of Determinant Quantum Monte Carlo Simulations Andrés Tomás, Che-Rung Lee, Zhaojun Bai, Richard Scalettar UC Davis SIAM Conference on Computation Science & Engineering Reno, March 1st, 2011

2 Multicore / manycore Parallelization of Determinant Quantum Monte Carlo Simulations Andrés Tomás, Che-Rung Lee, Zhaojun Bai, Richard Scalettar UC Davis SIAM Conference on Computation Science & Engineering Reno, March 1st, 2011

3 Outline Introduction QUEST Hubbard model Determinant quantum Monte Carlo Green s function in QUEST Multicore parallelization GPU acceleration

4 QUantum Electron Simulation Toolbox (QUEST) Fortran 90 package that implements the Determinant Quantum Monte Carlo (DQMC) method for quantum electron simulations PETAMAT (DoE SciDAC project): Next Generation Multi-Scale Quantum Simulation Software for Strongly Correlated Materials

5 Hubbard model 1. Length parameters N: spatial lattice size (# electrons) L: temperature discretization steps 2. Energy parameters t: electron hopping between different atoms (kinetic energy) U: strength of interactions between electrons (potential energy) β: inverse temperature β = 1 k B T 3. τ = β/l connects length and energy scales Numerical Methods for Quantum Monte Carlo Simulations of the Hubbard Model, in Multi-Scale Phenomena in Complex Fluids, Thomas Y. Hou, Chun Liu and Jian-Guo Liu eds., pp.1-110, Higher Education Press and World Scientific, 2009

6 Hubbard matrix M σ (h) = I B 1,σ (h 1 ) B 2,σ (h 2 ) I B 3,σ (h 3 ) I B l,σ (h l ) = e t τk e σνdiag(h l) B L,σ (h L ) I N = n x n y, K R N N, h = (h 1, h 2,..., h L ) R N L, σ = ±

7 Determinant Quantum Monte Carlo 1. Flip h l,i = h l,i 2. Compute the Metropolis ratio r l,i = M +(h ) M (h ) M + (h) M (h) 3. Acceptance condition (random number r) 4. Update i and l, go to step 1 h l,i h l,i if r r l,i 5. Compute physical measurements

8 Green s function G σ (h) = (I + B L,σ (h L )B L 1,σ (h L 1 ) B 1,σ (h 1 )) 1 The Metropolis ratio can be computed from G σ (h), for example, r 11 = d + d where for σ = ± d σ = 1 + (e 2σνh 1,1 1)(1 G σ 1,1(h))

9 Green s function Flipping the spatial site h l,i+1 is a rank-1 update of G, for example, G σ (h) G σ (h) α 1,σ r 11 u σ w T σ where u σ = (I G σ (h))e 1 w σ = (G σ (h)) T e 1 α 1,σ = e 2σνh 1,1 1 Flipping the temporal site h l+1,1 is a similarity transformation of G, for example, G σ (h) B 1 1,σ (h 1)G σ (h)b 1,σ (h 1 ) Also used for physical measurements

10 DQMC in a nutshell for s = 1, 2, 3,... for i = 1, 2, 3,..., L if i mod l = 0 G (I + B i,σ (h i ) B 1,σ (h 1 )B L,σ (h L ) B i+1,σ (h i+1 )) 1 else G B1,σ 1 (h 1)G σ (h)b 1,σ (h 1 ) end for j = 1, 2, 3,..., N Compute G σ j,j (h) Update h and G σ (h) if accepted end end Compute physical measurements end Huge number of consecutive operations with small matrices

11 Outline Introduction QUEST Hubbard model Determinant quantum Monte Carlo Green s function in QUEST Multicore parallelization GPU acceleration

12 Stratification method Green s function G = (I + B L B L 1 B 2 B 1 ) 1 Q 0 = D 0 = T 0 = I for i = 1, 2,..., L/k C i = B (i 1)k+1 B (i 1)k+2 B ik C i = (C i Q i 1 )D i 1 C i = Q i R i P T D i = diag(r i ) T i = (Di 1 i DGEMM DORMQR DGEQP3 R i )(Pi T T i 1) DTRMM end G = T 1 L/k (QT L/k T 1 L/k + D L/k) 1 Q T L/k DGETRF, DGETRI,...

13 Stratification perfomance N = 32 32, L = 48, k = 12 NERSC Carver (2 quad-core Intel Nehalem 2.67 GHz) MKL netlib + MKL BLAS 1 core 8 cores 1 core 8 cores Routine # time time s-up time time s-up DGEMM DTRMM DGETRF DGETRI DGEQP DORMQR Overall Avoid QR with pivoting Improve chain of matrix multiplications performance

14 Structured Orthogonal Factorization (SOF) Green s function G = (I + B L B L 1 B 2 B 1 ) 1 C 1 = I A 1 = B 1 B 2 B k for i = 2, 3,..., L/k D [ i = B (i 1)k+1 ] [ B (i 1)k+2 ] [ B ik Ci 1 Q11 Q = 12 Ri D i Q 21 Q 22 0 A i = Q T 12 A i 1 C i = Q T 22 end G = (C L/k + A L/k ) 1 C L/k DGEMM ] DGEMM DGEQRF DORGQR DGEMM DGEQRF, DORMQR, DGEMM

15 SOF performance N = 32 32, L = 48, k = 12 NERSC Carver (2 quad-core Intel Nehalem 2.67 GHz) 1 core 8 cores Routine # time time speedup DGEMM DTRSM DORMQR DGEQRF DORGQR Overall Better scalability but slightly slower than stratification

16 Improved SOF Green s function G = (I + B L B L 1 B 2 B 1 ) 1 C 1 = I A 1 = B 1 B 2 B k for i = 2, 3,..., L/k D i = B (i 1)k+1 B (i 1)k+2 B ik [ ] ( [ ] Ci Vu = I T D i V d A i = V d T T Vu T A i 1 C i = I V d T T Vd T end G = (C L/k + A L/k ) 1 C L/k [ Vu V d DGEMM DGEMM ] ) T [ ] Ri DGEQRF, DLARFT 0 DGEMM, DTRMM DGEMM, DTRMM DGEQRF, DORMQR, DGEMM

17 Improved SOF performance N = 32 32, L = 48, k = 12 NERSC Carver (2 quad-core Intel Nehalem 2.67 GHz) 1 core 8 cores Routine # time time speedup DGEMM DTRMM DTRSM DORMQR DGEQRF DLARFT Overall

18 Compute G performance L = 48, k = 12 NERSC Carver (2 quad-core Intel Nehalem 2.67 GHz) B i B i+1 B i+k 1 takes more than half of the time

19 CUDA parallel model for Tesla C2050 Improved double precision performance 14 multiprocessors (up to 448 threads) Blocks of threads All threads share the same code (kernel) Up to 8 blocks are scheduled to each processor Threads are executed in parallel via warps (32), synchronized at instruction level

20 CUDA memory model for Tesla C2050 Memory hierarchy Register private to each thread (128 Kb) Shared private to each processor (up to 48 Kb) Global shared among all threads and CPU (3 Gb) Cache memories L1 up to 48 Kb per processor L2 768 Kb Explicit Read only, texture (8 Kb) and constant (64 Kb)

21 CUBLAS Chain of matrix multiplications A B 1 B 2 B k A B i = h i B (diagonal h i ) cublassetmatrix for i = 1, 2,..., k C B A for j = 1, 2,..., n C j,1:n h i,j C j,1:n end A C end cublasgetmatrix cublasdgemm cublasdscal cublasdcopy

22 CUBLAS + CUDA Chain of matrix multiplications A B 1 B 2 B k A B i = h i B (diagonal h i ) cublassetmatrix for i = 1, 2,..., k C B A A h i C end cublasgetmatrix cublasdgemm scalerow

23 CUBLAS + CUDA void scalerow_kernel(int n, double *h, double *C, double *A) { int j, i = blockidx.x * blockdim.x + threadidx.x; if (i < n) { double f = h[i]; for (j = 0; j < n; j++) A[i + j * n] = f * C[i + j * n]; } } Each thread computes one row of A h is read once A and C are stored column-wise so memory access is coalesced

24 GPU performance L = 48, k = 12 NERSC Carver + Tesla C2050 (double precision) Chain of matrix multiplications A B 1 B 2 B k A

25 GPU performance L = 48, k = 12 NERSC Carver + Tesla C2050 (double precision) Chain of matrix multiplications A B 1 B 2 B k A

26 GPU performance L = 48, k = 12 NERSC Carver + Tesla C2050 (double precision) Green s function (improved SOF) G = (I + B L B L 1 B 2 B 1 ) 1

27 Conclusions How to accelerate a huge number of consecutive operations with small matrices? Multicore: MKL BLAS + netlib LAPACK GPU acceleration: CUBLAS + small kernel Future work Fully implement SOF in GPU (MAGMA QR, TSQR,...) Acknowledgments NERSC computing resources

Advancing Large Scale Many-Body QMC Simulations on GPU Accelerated Multicore Systems

Advancing Large Scale Many-Body QMC Simulations on GPU Accelerated Multicore Systems Advancing Large Scale Many-Body QMC Simulations on GPU Accelerated Multicore Systems Andres Tomas, Chia-Chen Chang, Richard Scalettar and Zhaojun Bai Department of Computer Science, University of California,

More information

Re-design of Higher level Matrix Algorithms for Multicore and Heterogeneous Architectures. Based on the presentation at UC Berkeley, October 7, 2009

Re-design of Higher level Matrix Algorithms for Multicore and Heterogeneous Architectures. Based on the presentation at UC Berkeley, October 7, 2009 III.1 Re-design of Higher level Matrix Algorithms for Multicore and Heterogeneous Architectures Based on the presentation at UC Berkeley, October 7, 2009 Background and motivation Running time of an algorithm

More information

MAGMA. Matrix Algebra on GPU and Multicore Architectures. Mark Gates. February 2012

MAGMA. Matrix Algebra on GPU and Multicore Architectures. Mark Gates. February 2012 MAGMA Matrix Algebra on GPU and Multicore Architectures Mark Gates February 2012 1 Hardware trends Scale # cores instead of clock speed Hardware issue became software issue Multicore Hybrid 1.E+07 1e7

More information

Multi-Length Scale Matrix Computations and Applications in Quantum Mechanical Simulations

Multi-Length Scale Matrix Computations and Applications in Quantum Mechanical Simulations Multi-Length Scale Matrix Computations and Applications in Quantum Mechanical Simulations Zhaojun Bai http://www.cs.ucdavis.edu/ bai joint work with Wenbin Chen, Roger Lee, Richard Scalettar, Ichitaro

More information

Structured Orthogonal Inversion of Block p-cyclic Matrices on Multicore with GPU Accelerators

Structured Orthogonal Inversion of Block p-cyclic Matrices on Multicore with GPU Accelerators Structured Orthogonal Inversion of Block p-cyclic Matrices on Multicore with GPU Accelerators Sergiy Gogolenko, Zhaojun Bai 2, and Richard Scalettar 2 Donetsk National Technical University, Donetsk, 8300,

More information

Dynamic Scheduling for Work Agglomeration on Heterogeneous Clusters

Dynamic Scheduling for Work Agglomeration on Heterogeneous Clusters Dynamic Scheduling for Work Agglomeration on Heterogeneous Clusters Jonathan Lifflander, G. Carl Evans, Anshu Arya, Laxmikant Kale University of Illinois Urbana-Champaign May 25, 2012 Work is overdecomposed

More information

Direct Self-Consistent Field Computations on GPU Clusters

Direct Self-Consistent Field Computations on GPU Clusters Direct Self-Consistent Field Computations on GPU Clusters Guochun Shi, Volodymyr Kindratenko National Center for Supercomputing Applications University of Illinois at UrbanaChampaign Ivan Ufimtsev, Todd

More information

Accelerating Linear Algebra on Heterogeneous Architectures of Multicore and GPUs using MAGMA and DPLASMA and StarPU Schedulers

Accelerating Linear Algebra on Heterogeneous Architectures of Multicore and GPUs using MAGMA and DPLASMA and StarPU Schedulers UT College of Engineering Tutorial Accelerating Linear Algebra on Heterogeneous Architectures of Multicore and GPUs using MAGMA and DPLASMA and StarPU Schedulers Stan Tomov 1, George Bosilca 1, and Cédric

More information

Dynamic Scheduling within MAGMA

Dynamic Scheduling within MAGMA Dynamic Scheduling within MAGMA Emmanuel Agullo, Cedric Augonnet, Jack Dongarra, Mathieu Faverge, Julien Langou, Hatem Ltaief, Samuel Thibault and Stanimire Tomov April 5, 2012 Innovative and Computing

More information

Accelerating linear algebra computations with hybrid GPU-multicore systems.

Accelerating linear algebra computations with hybrid GPU-multicore systems. Accelerating linear algebra computations with hybrid GPU-multicore systems. Marc Baboulin INRIA/Université Paris-Sud joint work with Jack Dongarra (University of Tennessee and Oak Ridge National Laboratory)

More information

A model leading to self-consistent iteration computation with need for HP LA (e.g, diagonalization and orthogonalization)

A model leading to self-consistent iteration computation with need for HP LA (e.g, diagonalization and orthogonalization) A model leading to self-consistent iteration computation with need for HP LA (e.g, diagonalization and orthogonalization) Schodinger equation: Hψ = Eψ Choose a basis set of wave functions Two cases: Orthonormal

More information

Computing least squares condition numbers on hybrid multicore/gpu systems

Computing least squares condition numbers on hybrid multicore/gpu systems Computing least squares condition numbers on hybrid multicore/gpu systems M. Baboulin and J. Dongarra and R. Lacroix Abstract This paper presents an efficient computation for least squares conditioning

More information

arxiv: v1 [hep-lat] 7 Oct 2010

arxiv: v1 [hep-lat] 7 Oct 2010 arxiv:.486v [hep-lat] 7 Oct 2 Nuno Cardoso CFTP, Instituto Superior Técnico E-mail: nunocardoso@cftp.ist.utl.pt Pedro Bicudo CFTP, Instituto Superior Técnico E-mail: bicudo@ist.utl.pt We discuss the CUDA

More information

TR A Comparison of the Performance of SaP::GPU and Intel s Math Kernel Library (MKL) for Solving Dense Banded Linear Systems

TR A Comparison of the Performance of SaP::GPU and Intel s Math Kernel Library (MKL) for Solving Dense Banded Linear Systems TR-0-07 A Comparison of the Performance of ::GPU and Intel s Math Kernel Library (MKL) for Solving Dense Banded Linear Systems Ang Li, Omkar Deshmukh, Radu Serban, Dan Negrut May, 0 Abstract ::GPU is a

More information

Jacobi-Based Eigenvalue Solver on GPU. Lung-Sheng Chien, NVIDIA

Jacobi-Based Eigenvalue Solver on GPU. Lung-Sheng Chien, NVIDIA Jacobi-Based Eigenvalue Solver on GPU Lung-Sheng Chien, NVIDIA lchien@nvidia.com Outline Symmetric eigenvalue solver Experiment Applications Conclusions Symmetric eigenvalue solver The standard form is

More information

Scalable Hybrid Programming and Performance for SuperLU Sparse Direct Solver

Scalable Hybrid Programming and Performance for SuperLU Sparse Direct Solver Scalable Hybrid Programming and Performance for SuperLU Sparse Direct Solver Sherry Li Lawrence Berkeley National Laboratory Piyush Sao Rich Vuduc Georgia Institute of Technology CUG 14, May 4-8, 14, Lugano,

More information

Accelerating Model Reduction of Large Linear Systems with Graphics Processors

Accelerating Model Reduction of Large Linear Systems with Graphics Processors Accelerating Model Reduction of Large Linear Systems with Graphics Processors P. Benner 1, P. Ezzatti 2, D. Kressner 3, E.S. Quintana-Ortí 4, Alfredo Remón 4 1 Max-Plank-Institute for Dynamics of Complex

More information

GPU accelerated Arnoldi solver for small batched matrix

GPU accelerated Arnoldi solver for small batched matrix 15. 09. 22 GPU accelerated Arnoldi solver for small batched matrix Samsung Advanced Institute of Technology Hyung-Jin Kim Contents - Eigen value problems - Solution - Arnoldi Algorithm - Target - CUDA

More information

A Massively Parallel Eigenvalue Solver for Small Matrices on Multicore and Manycore Architectures

A Massively Parallel Eigenvalue Solver for Small Matrices on Multicore and Manycore Architectures A Massively Parallel Eigenvalue Solver for Small Matrices on Multicore and Manycore Architectures Manfred Liebmann Technische Universität München Chair of Optimal Control Center for Mathematical Sciences,

More information

Binding Performance and Power of Dense Linear Algebra Operations

Binding Performance and Power of Dense Linear Algebra Operations 10th IEEE International Symposium on Parallel and Distributed Processing with Applications Binding Performance and Power of Dense Linear Algebra Operations Maria Barreda, Manuel F. Dolz, Rafael Mayo, Enrique

More information

Introduction to numerical computations on the GPU

Introduction to numerical computations on the GPU Introduction to numerical computations on the GPU Lucian Covaci http://lucian.covaci.org/cuda.pdf Tuesday 1 November 11 1 2 Outline: NVIDIA Tesla and Geforce video cards: architecture CUDA - C: programming

More information

SPARSE SOLVERS POISSON EQUATION. Margreet Nool. November 9, 2015 FOR THE. CWI, Multiscale Dynamics

SPARSE SOLVERS POISSON EQUATION. Margreet Nool. November 9, 2015 FOR THE. CWI, Multiscale Dynamics SPARSE SOLVERS FOR THE POISSON EQUATION Margreet Nool CWI, Multiscale Dynamics November 9, 2015 OUTLINE OF THIS TALK 1 FISHPACK, LAPACK, PARDISO 2 SYSTEM OVERVIEW OF CARTESIUS 3 POISSON EQUATION 4 SOLVERS

More information

Two case studies of Monte Carlo simulation on GPU

Two case studies of Monte Carlo simulation on GPU Two case studies of Monte Carlo simulation on GPU National Institute for Computational Sciences University of Tennessee Seminar series on HPC, Feb. 27, 2014 Outline 1 Introduction 2 Discrete energy lattice

More information

Claude Tadonki. MINES ParisTech PSL Research University Centre de Recherche Informatique

Claude Tadonki. MINES ParisTech PSL Research University Centre de Recherche Informatique Claude Tadonki MINES ParisTech PSL Research University Centre de Recherche Informatique claude.tadonki@mines-paristech.fr Monthly CRI Seminar MINES ParisTech - CRI June 06, 2016, Fontainebleau (France)

More information

PSEUDORANDOM numbers are very important in practice

PSEUDORANDOM numbers are very important in practice Proceedings of the Federated Conference on Computer Science and Information Systems pp 571 578 ISBN 978-83-681-51-4 Parallel GPU-accelerated Recursion-based Generators of Pseudorandom Numbers Przemysław

More information

c 2015 Society for Industrial and Applied Mathematics

c 2015 Society for Industrial and Applied Mathematics SIAM J. SCI. COMPUT. Vol. 37, No. 3, pp. C307 C330 c 2015 Society for Industrial and Applied Mathematics MIXED-PRECISION CHOLESKY QR FACTORIZATION AND ITS CASE STUDIES ON MULTICORE CPU WITH MULTIPLE GPUS

More information

Antti-Pekka Hynninen, 5/10/2017, GTC2017, San Jose CA

Antti-Pekka Hynninen, 5/10/2017, GTC2017, San Jose CA S7255: CUTT: A HIGH- PERFORMANCE TENSOR TRANSPOSE LIBRARY FOR GPUS Antti-Pekka Hynninen, 5/10/2017, GTC2017, San Jose CA MOTIVATION Tensor contractions are the most computationally intensive part of quantum

More information

Some notes on efficient computing and setting up high performance computing environments

Some notes on efficient computing and setting up high performance computing environments Some notes on efficient computing and setting up high performance computing environments Andrew O. Finley Department of Forestry, Michigan State University, Lansing, Michigan. April 17, 2017 1 Efficient

More information

Solving PDEs with CUDA Jonathan Cohen

Solving PDEs with CUDA Jonathan Cohen Solving PDEs with CUDA Jonathan Cohen jocohen@nvidia.com NVIDIA Research PDEs (Partial Differential Equations) Big topic Some common strategies Focus on one type of PDE in this talk Poisson Equation Linear

More information

Population annealing study of the frustrated Ising antiferromagnet on the stacked triangular lattice

Population annealing study of the frustrated Ising antiferromagnet on the stacked triangular lattice Population annealing study of the frustrated Ising antiferromagnet on the stacked triangular lattice Michal Borovský Department of Theoretical Physics and Astrophysics, University of P. J. Šafárik in Košice,

More information

Acceleration of Deterministic Boltzmann Solver with Graphics Processing Units

Acceleration of Deterministic Boltzmann Solver with Graphics Processing Units Acceleration of Deterministic Boltzmann Solver with Graphics Processing Units V.V.Aristov a, A.A.Frolova a, S.A.Zabelok a, V.I.Kolobov b and R.R.Arslanbekov b a Dorodnicn Computing Centre of the Russian

More information

Communication-avoiding LU and QR factorizations for multicore architectures

Communication-avoiding LU and QR factorizations for multicore architectures Communication-avoiding LU and QR factorizations for multicore architectures DONFACK Simplice INRIA Saclay Joint work with Laura Grigori INRIA Saclay Alok Kumar Gupta BCCS,Norway-5075 16th April 2010 Communication-avoiding

More information

Sparse LU Factorization on GPUs for Accelerating SPICE Simulation

Sparse LU Factorization on GPUs for Accelerating SPICE Simulation Nano-scale Integrated Circuit and System (NICS) Laboratory Sparse LU Factorization on GPUs for Accelerating SPICE Simulation Xiaoming Chen PhD Candidate Department of Electronic Engineering Tsinghua University,

More information

PuReMD-GPU: A Reactive Molecular Dynamic Simulation Package for GPUs

PuReMD-GPU: A Reactive Molecular Dynamic Simulation Package for GPUs Purdue University Purdue e-pubs Department of Computer Science Technical Reports Department of Computer Science 2012 PuReMD-GPU: A Reactive Molecular Dynamic Simulation Package for GPUs Sudhir B. Kylasa

More information

MAGMA MIC 1.0: Linear Algebra Library for Intel Xeon Phi Coprocessors

MAGMA MIC 1.0: Linear Algebra Library for Intel Xeon Phi Coprocessors MAGMA MIC 1.0: Linear Algebra Library for Intel Xeon Phi Coprocessors J. Dongarra, M. Gates, A. Haidar, Y. Jia, K. Kabir, P. Luszczek, and S. Tomov University of Tennessee, Knoxville 05 / 03 / 2013 MAGMA:

More information

Tile QR Factorization with Parallel Panel Processing for Multicore Architectures

Tile QR Factorization with Parallel Panel Processing for Multicore Architectures Tile QR Factorization with Parallel Panel Processing for Multicore Architectures Bilel Hadri, Hatem Ltaief, Emmanuel Agullo, Jack Dongarra Department of Electrical Engineering and Computer Science, University

More information

GPU acceleration of Newton s method for large systems of polynomial equations in double double and quad double arithmetic

GPU acceleration of Newton s method for large systems of polynomial equations in double double and quad double arithmetic GPU acceleration of Newton s method for large systems of polynomial equations in double double and quad double arithmetic Jan Verschelde joint work with Xiangcheng Yu University of Illinois at Chicago

More information

Implementing QR Factorization Updating Algorithms on GPUs. Andrew, Robert and Dingle, Nicholas J. MIMS EPrint:

Implementing QR Factorization Updating Algorithms on GPUs. Andrew, Robert and Dingle, Nicholas J. MIMS EPrint: Implementing QR Factorization Updating Algorithms on GPUs Andrew, Robert and Dingle, Nicholas J. 214 MIMS EPrint: 212.114 Manchester Institute for Mathematical Sciences School of Mathematics The University

More information

A Fast Selected Inversion Algorithm for Green s Function Calculation in Many-body Quantum Monte Carlo Simulations

A Fast Selected Inversion Algorithm for Green s Function Calculation in Many-body Quantum Monte Carlo Simulations A Fast Selected nversion Algorithm for Green s Function Calculation in Many-body Quantum Monte Carlo Simulations Chengming Jiang Dept of Computer Science University of California, Davis Davis, CA USA cmjiang@ucdavisedu

More information

A Quantum Chemistry Domain-Specific Language for Heterogeneous Clusters

A Quantum Chemistry Domain-Specific Language for Heterogeneous Clusters A Quantum Chemistry Domain-Specific Language for Heterogeneous Clusters ANTONINO TUMEO, ORESTE VILLA Collaborators: Karol Kowalski, Sriram Krishnamoorthy, Wenjing Ma, Simone Secchi May 15, 2012 1 Outline!

More information

Scalable and Power-Efficient Data Mining Kernels

Scalable and Power-Efficient Data Mining Kernels Scalable and Power-Efficient Data Mining Kernels Alok Choudhary, John G. Searle Professor Dept. of Electrical Engineering and Computer Science and Professor, Kellogg School of Management Director of the

More information

CS-206 Concurrency. Lecture 13. Wrap Up. Spring 2015 Prof. Babak Falsafi parsa.epfl.ch/courses/cs206/

CS-206 Concurrency. Lecture 13. Wrap Up. Spring 2015 Prof. Babak Falsafi parsa.epfl.ch/courses/cs206/ CS-206 Concurrency Lecture 13 Wrap Up Spring 2015 Prof. Babak Falsafi parsa.epfl.ch/courses/cs206/ Created by Nooshin Mirzadeh, Georgios Psaropoulos and Babak Falsafi EPFL Copyright 2015 EPFL CS-206 Spring

More information

Tall and Skinny QR Matrix Factorization Using Tile Algorithms on Multicore Architectures LAPACK Working Note - 222

Tall and Skinny QR Matrix Factorization Using Tile Algorithms on Multicore Architectures LAPACK Working Note - 222 Tall and Skinny QR Matrix Factorization Using Tile Algorithms on Multicore Architectures LAPACK Working Note - 222 Bilel Hadri 1, Hatem Ltaief 1, Emmanuel Agullo 1, and Jack Dongarra 1,2,3 1 Department

More information

ECS289: Scalable Machine Learning

ECS289: Scalable Machine Learning ECS289: Scalable Machine Learning Cho-Jui Hsieh UC Davis Sept 27, 2015 Outline Linear regression Ridge regression and Lasso Time complexity (closed form solution) Iterative Solvers Regression Input: training

More information

Accelerating computation of eigenvectors in the nonsymmetric eigenvalue problem

Accelerating computation of eigenvectors in the nonsymmetric eigenvalue problem Accelerating computation of eigenvectors in the nonsymmetric eigenvalue problem Mark Gates 1, Azzam Haidar 1, and Jack Dongarra 1,2,3 1 University of Tennessee, Knoxville, TN, USA 2 Oak Ridge National

More information

Practical Combustion Kinetics with CUDA

Practical Combustion Kinetics with CUDA Funded by: U.S. Department of Energy Vehicle Technologies Program Program Manager: Gurpreet Singh & Leo Breton Practical Combustion Kinetics with CUDA GPU Technology Conference March 20, 2015 Russell Whitesides

More information

Review for the Midterm Exam

Review for the Midterm Exam Review for the Midterm Exam 1 Three Questions of the Computational Science Prelim scaled speedup network topologies work stealing 2 The in-class Spring 2012 Midterm Exam pleasingly parallel computations

More information

Accelerating computation of eigenvectors in the dense nonsymmetric eigenvalue problem

Accelerating computation of eigenvectors in the dense nonsymmetric eigenvalue problem Accelerating computation of eigenvectors in the dense nonsymmetric eigenvalue problem Mark Gates 1, Azzam Haidar 1, and Jack Dongarra 1,2,3 1 University of Tennessee, Knoxville, TN, USA 2 Oak Ridge National

More information

A hybrid Hermitian general eigenvalue solver

A hybrid Hermitian general eigenvalue solver Available online at www.prace-ri.eu Partnership for Advanced Computing in Europe A hybrid Hermitian general eigenvalue solver Raffaele Solcà *, Thomas C. Schulthess Institute fortheoretical Physics ETHZ,

More information

Level-3 BLAS on a GPU

Level-3 BLAS on a GPU Level-3 BLAS on a GPU Picking the Low Hanging Fruit Francisco Igual 1 Gregorio Quintana-Ortí 1 Robert A. van de Geijn 2 1 Departamento de Ingeniería y Ciencia de los Computadores. University Jaume I. Castellón

More information

Static-scheduling and hybrid-programming in SuperLU DIST on multicore cluster systems

Static-scheduling and hybrid-programming in SuperLU DIST on multicore cluster systems Static-scheduling and hybrid-programming in SuperLU DIST on multicore cluster systems Ichitaro Yamazaki University of Tennessee, Knoxville Xiaoye Sherry Li Lawrence Berkeley National Laboratory MS49: Sparse

More information

POLITECNICO DI MILANO DATA PARALLEL OPTIMIZATIONS ON GPU ARCHITECTURES FOR MOLECULAR DYNAMIC SIMULATIONS

POLITECNICO DI MILANO DATA PARALLEL OPTIMIZATIONS ON GPU ARCHITECTURES FOR MOLECULAR DYNAMIC SIMULATIONS POLITECNICO DI MILANO Facoltà di Ingegneria dell Informazione Corso di Laurea in Ingegneria Informatica DATA PARALLEL OPTIMIZATIONS ON GPU ARCHITECTURES FOR MOLECULAR DYNAMIC SIMULATIONS Relatore: Prof.

More information

A parallel tiled solver for dense symmetric indefinite systems on multicore architectures

A parallel tiled solver for dense symmetric indefinite systems on multicore architectures A parallel tiled solver for dense symmetric indefinite systems on multicore architectures Marc Baboulin, Dulceneia Becker, Jack Dongarra INRIA Saclay-Île de France, F-91893 Orsay, France Université Paris

More information

PRECONDITIONING IN THE PARALLEL BLOCK-JACOBI SVD ALGORITHM

PRECONDITIONING IN THE PARALLEL BLOCK-JACOBI SVD ALGORITHM Proceedings of ALGORITMY 25 pp. 22 211 PRECONDITIONING IN THE PARALLEL BLOCK-JACOBI SVD ALGORITHM GABRIEL OKŠA AND MARIÁN VAJTERŠIC Abstract. One way, how to speed up the computation of the singular value

More information

Julian Merten. GPU Computing and Alternative Architecture

Julian Merten. GPU Computing and Alternative Architecture Future Directions of Cosmological Simulations / Edinburgh 1 / 16 Julian Merten GPU Computing and Alternative Architecture Institut für Theoretische Astrophysik Zentrum für Astronomie Universität Heidelberg

More information

Information Sciences Institute 22 June 2012 Bob Lucas, Gene Wagenbreth, Dan Davis, Roger Grimes and

Information Sciences Institute 22 June 2012 Bob Lucas, Gene Wagenbreth, Dan Davis, Roger Grimes and Accelerating the Multifrontal Method Information Sciences Institute 22 June 2012 Bob Lucas, Gene Wagenbreth, Dan Davis, Roger Grimes {rflucas,genew,ddavis}@isi.edu and grimes@lstc.com 3D Finite Element

More information

INITIAL INTEGRATION AND EVALUATION

INITIAL INTEGRATION AND EVALUATION INITIAL INTEGRATION AND EVALUATION OF SLATE PARALLEL BLAS IN LATTE Marc Cawkwell, Danny Perez, Arthur Voter Asim YarKhan, Gerald Ragghianti, Jack Dongarra, Introduction The aim of the joint milestone STMS10-52

More information

Parallel Sparse Tensor Decompositions using HiCOO Format

Parallel Sparse Tensor Decompositions using HiCOO Format Figure sources: A brief survey of tensors by Berton Earnshaw and NVIDIA Tensor Cores Parallel Sparse Tensor Decompositions using HiCOO Format Jiajia Li, Jee Choi, Richard Vuduc May 8, 8 @ SIAM ALA 8 Outline

More information

An Integrative Model for Parallelism

An Integrative Model for Parallelism An Integrative Model for Parallelism Victor Eijkhout ICERM workshop 2012/01/09 Introduction Formal part Examples Extension to other memory models Conclusion tw-12-exascale 2012/01/09 2 Introduction tw-12-exascale

More information

Symmetric Pivoting in ScaLAPACK Craig Lucas University of Manchester Cray User Group 8 May 2006, Lugano

Symmetric Pivoting in ScaLAPACK Craig Lucas University of Manchester Cray User Group 8 May 2006, Lugano Symmetric Pivoting in ScaLAPACK Craig Lucas University of Manchester Cray User Group 8 May 2006, Lugano Introduction Introduction We wanted to parallelize a serial algorithm for the pivoted Cholesky factorization

More information

A dissection solver with kernel detection for unsymmetric matrices in FreeFem++

A dissection solver with kernel detection for unsymmetric matrices in FreeFem++ . p.1/21 11 Dec. 2014, LJLL, Paris FreeFem++ workshop A dissection solver with kernel detection for unsymmetric matrices in FreeFem++ Atsushi Suzuki Atsushi.Suzuki@ann.jussieu.fr Joint work with François-Xavier

More information

Algorithm 853: an Efficient Algorithm for Solving Rank-Deficient Least Squares Problems

Algorithm 853: an Efficient Algorithm for Solving Rank-Deficient Least Squares Problems Algorithm 853: an Efficient Algorithm for Solving Rank-Deficient Least Squares Problems LESLIE FOSTER and RAJESH KOMMU San Jose State University Existing routines, such as xgelsy or xgelsd in LAPACK, for

More information

Jacobi-Davidson Eigensolver in Cusolver Library. Lung-Sheng Chien, NVIDIA

Jacobi-Davidson Eigensolver in Cusolver Library. Lung-Sheng Chien, NVIDIA Jacobi-Davidson Eigensolver in Cusolver Library Lung-Sheng Chien, NVIDIA lchien@nvidia.com Outline CuSolver library - cusolverdn: dense LAPACK - cusolversp: sparse LAPACK - cusolverrf: refactorization

More information

LAPACK-Style Codes for Pivoted Cholesky and QR Updating

LAPACK-Style Codes for Pivoted Cholesky and QR Updating LAPACK-Style Codes for Pivoted Cholesky and QR Updating Sven Hammarling 1, Nicholas J. Higham 2, and Craig Lucas 3 1 NAG Ltd.,Wilkinson House, Jordan Hill Road, Oxford, OX2 8DR, England, sven@nag.co.uk,

More information

Prof. Brant Robertson Department of Astronomy and Astrophysics University of California, Santa

Prof. Brant Robertson Department of Astronomy and Astrophysics University of California, Santa Accelerated Astrophysics: Using NVIDIA GPUs to Simulate and Understand the Universe Prof. Brant Robertson Department of Astronomy and Astrophysics University of California, Santa Cruz brant@ucsc.edu, UC

More information

Beam dynamics calculation

Beam dynamics calculation September 6 Beam dynamics calculation S.B. Vorozhtsov, Е.Е. Perepelkin and V.L. Smirnov Dubna, JINR http://parallel-compute.com Outline Problem formulation Numerical methods OpenMP and CUDA realization

More information

Algorithms and Methods for Fast Model Predictive Control

Algorithms and Methods for Fast Model Predictive Control Algorithms and Methods for Fast Model Predictive Control Technical University of Denmark Department of Applied Mathematics and Computer Science 13 April 2016 Background: Model Predictive Control Model

More information

QUEST: QUantum Electron Simulation Toolbox

QUEST: QUantum Electron Simulation Toolbox San Jose State University From the SelectedWorks of Ehsan Khatami July, 2010 QUEST: QUantum Electron Simulation Toolbox C.-R. Lee, National Tsinghua University S. Chiesa, University of California, Davis

More information

Incomplete-LU and Cholesky Preconditioned Iterative Methods Using CUSPARSE and CUBLAS

Incomplete-LU and Cholesky Preconditioned Iterative Methods Using CUSPARSE and CUBLAS Incomplete-LU and Cholesky Preconditioned Iterative Methods Using CUSPARSE and CUBLAS Maxim Naumov NVIDIA, 2701 San Tomas Expressway, Santa Clara, CA 95050 June 21, 2011 Abstract In this white paper we

More information

On GPU Acceleration of Common Solvers for (Quasi-) Triangular Generalized Lyapunov Equations

On GPU Acceleration of Common Solvers for (Quasi-) Triangular Generalized Lyapunov Equations Max Planck Institute Magdeburg Preprints Martin Köhler Jens Saak On GPU Acceleration of Common Solvers for (Quasi-) Triangular Generalized Lyapunov Equations MAX PLANCK INSTITUT FÜR DYNAMIK KOMPLEXER TECHNISCHER

More information

Performance and Energy Analysis of the Iterative Solution of Sparse Linear Systems on Multicore and Manycore Architectures

Performance and Energy Analysis of the Iterative Solution of Sparse Linear Systems on Multicore and Manycore Architectures Performance and Energy Analysis of the Iterative Solution of Sparse Linear Systems on Multicore and Manycore Architectures José I. Aliaga Performance and Energy Analysis of the Iterative Solution of Sparse

More information

LAPACK-Style Codes for Pivoted Cholesky and QR Updating. Hammarling, Sven and Higham, Nicholas J. and Lucas, Craig. MIMS EPrint: 2006.

LAPACK-Style Codes for Pivoted Cholesky and QR Updating. Hammarling, Sven and Higham, Nicholas J. and Lucas, Craig. MIMS EPrint: 2006. LAPACK-Style Codes for Pivoted Cholesky and QR Updating Hammarling, Sven and Higham, Nicholas J. and Lucas, Craig 2007 MIMS EPrint: 2006.385 Manchester Institute for Mathematical Sciences School of Mathematics

More information

On the design of parallel linear solvers for large scale problems

On the design of parallel linear solvers for large scale problems On the design of parallel linear solvers for large scale problems ICIAM - August 2015 - Mini-Symposium on Recent advances in matrix computations for extreme-scale computers M. Faverge, X. Lacoste, G. Pichon,

More information

Multiphase Flow Simulations in Inclined Tubes with Lattice Boltzmann Method on GPU

Multiphase Flow Simulations in Inclined Tubes with Lattice Boltzmann Method on GPU Multiphase Flow Simulations in Inclined Tubes with Lattice Boltzmann Method on GPU Khramtsov D.P., Nekrasov D.A., Pokusaev B.G. Department of Thermodynamics, Thermal Engineering and Energy Saving Technologies,

More information

On Portability, Performance and Scalability of a MPI OpenCL Lattice Boltzmann Code

On Portability, Performance and Scalability of a MPI OpenCL Lattice Boltzmann Code On Portability, Performance and Scalability of a MPI OpenCL Lattice Boltzmann Code E Calore, S F Schifano, R Tripiccione Enrico Calore INFN Ferrara, Italy 7 th Workshop on UnConventional High Performance

More information

Dense Arithmetic over Finite Fields with CUMODP

Dense Arithmetic over Finite Fields with CUMODP Dense Arithmetic over Finite Fields with CUMODP Sardar Anisul Haque 1 Xin Li 2 Farnam Mansouri 1 Marc Moreno Maza 1 Wei Pan 3 Ning Xie 1 1 University of Western Ontario, Canada 2 Universidad Carlos III,

More information

Background. Another interests. Sieve method. Parallel Sieve Processing on Vector Processor and GPU. RSA Cryptography

Background. Another interests. Sieve method. Parallel Sieve Processing on Vector Processor and GPU. RSA Cryptography Background Parallel Sieve Processing on Vector Processor and GPU Yasunori Ushiro (Earth Simulator Center) Yoshinari Fukui (Earth Simulator Center) Hidehiko Hasegawa (Univ. of Tsukuba) () RSA Cryptography

More information

MARCH 24-27, 2014 SAN JOSE, CA

MARCH 24-27, 2014 SAN JOSE, CA MARCH 24-27, 2014 SAN JOSE, CA Sparse HPC on modern architectures Important scientific applications rely on sparse linear algebra HPCG a new benchmark proposal to complement Top500 (HPL) To solve A x =

More information

AUTHOR QUERY FORM. Fax: For correction or revision of any artwork, please consult

AUTHOR QUERY FORM. Fax: For correction or revision of any artwork, please consult Our reference: YJCPH 52 P-authorquery-v7 AUTHOR QUERY FORM Journal: YJCPH Please e-mail or fax your responses and any corrections to: Article Number: 52 E-mail: corrections.esch@elsevier.vtex.lt Fax: +

More information

Parallelization Strategies for Density Matrix Renormalization Group algorithms on Shared-Memory Systems

Parallelization Strategies for Density Matrix Renormalization Group algorithms on Shared-Memory Systems Parallelization Strategies for Density Matrix Renormalization Group algorithms on Shared-Memory Systems G. Hager HPC Services, Computing Center Erlangen, Germany E. Jeckelmann Theoretical Physics, Univ.

More information

Performance Analysis and Design of a Hessenberg Reduction using Stabilized Blocked Elementary Transformations for New Architectures

Performance Analysis and Design of a Hessenberg Reduction using Stabilized Blocked Elementary Transformations for New Architectures Performance Analysis and Design of a Hessenberg Reduction using Stabilized Blocked Elementary Transformations for New Architectures Khairul Kabir University of Tennessee kkabir@vols.utk.edu Azzam Haidar

More information

Tips Geared Towards R. Adam J. Suarez. Arpil 10, 2015

Tips Geared Towards R. Adam J. Suarez. Arpil 10, 2015 Tips Geared Towards R Departments of Statistics North Carolina State University Arpil 10, 2015 1 / 30 Advantages of R As an interpretive and interactive language, developing an algorithm in R can be done

More information

Communication avoiding parallel algorithms for dense matrix factorizations

Communication avoiding parallel algorithms for dense matrix factorizations Communication avoiding parallel dense matrix factorizations 1/ 44 Communication avoiding parallel algorithms for dense matrix factorizations Edgar Solomonik Department of EECS, UC Berkeley October 2013

More information

Ilya A. Kaliman* and Anna I. Krylov. Introduction

Ilya A. Kaliman* and Anna I. Krylov. Introduction SOFTWARE NEWS AND UPDATES WWW.C-CHEM.ORG New Algorithm for Tensor Contractions on Multi-Core CPUs, GPUs, and Accelerators Enables CCSD and EOM-CCSD Calculations with over 1000 Basis Functions on a Single

More information

Graphics Card Computing for Materials Modelling

Graphics Card Computing for Materials Modelling Graphics Card Computing for Materials Modelling Case study: Analytic Bond Order Potentials B. Seiser, T. Hammerschmidt, R. Drautz, D. Pettifor Funded by EPSRC within the collaborative multi-scale project

More information

A dissection solver with kernel detection for symmetric finite element matrices on shared memory computers

A dissection solver with kernel detection for symmetric finite element matrices on shared memory computers A dissection solver with kernel detection for symmetric finite element matrices on shared memory computers Atsushi Suzuki, François-Xavier Roux To cite this version: Atsushi Suzuki, François-Xavier Roux.

More information

Parallel Transposition of Sparse Data Structures

Parallel Transposition of Sparse Data Structures Parallel Transposition of Sparse Data Structures Hao Wang, Weifeng Liu, Kaixi Hou, Wu-chun Feng Department of Computer Science, Virginia Tech Niels Bohr Institute, University of Copenhagen Scientific Computing

More information

Lecture 1: Numerical Issues from Inverse Problems (Parameter Estimation, Regularization Theory, and Parallel Algorithms)

Lecture 1: Numerical Issues from Inverse Problems (Parameter Estimation, Regularization Theory, and Parallel Algorithms) Lecture 1: Numerical Issues from Inverse Problems (Parameter Estimation, Regularization Theory, and Parallel Algorithms) Youzuo Lin 1 Joint work with: Rosemary A. Renaut 2 Brendt Wohlberg 1 Hongbin Guo

More information

Efficient algorithms for symmetric tensor contractions

Efficient algorithms for symmetric tensor contractions Efficient algorithms for symmetric tensor contractions Edgar Solomonik 1 Department of EECS, UC Berkeley Oct 22, 2013 1 / 42 Edgar Solomonik Symmetric tensor contractions 1/ 42 Motivation The goal is to

More information

GPU Acceleration of BCP Procedure for SAT Algorithms

GPU Acceleration of BCP Procedure for SAT Algorithms GPU Acceleration of BCP Procedure for SAT Algorithms Hironori Fujii 1 and Noriyuki Fujimoto 1 1 Graduate School of Science Osaka Prefecture University 1-1 Gakuencho, Nakaku, Sakai, Osaka 599-8531, Japan

More information

Targeting Extreme Scale Computational Challenges with Heterogeneous Systems

Targeting Extreme Scale Computational Challenges with Heterogeneous Systems Targeting Extreme Scale Computational Challenges with Heterogeneous Systems Oreste Villa, Antonino Tumeo Pacific Northwest Na/onal Laboratory (PNNL) 1 Introduction! PNNL Laboratory Directed Research &

More information

GPU Computing Activities in KISTI

GPU Computing Activities in KISTI International Advanced Research Workshop on High Performance Computing, Grids and Clouds 2010 June 21~June 25 2010, Cetraro, Italy HPC Infrastructure and GPU Computing Activities in KISTI Hongsuk Yi hsyi@kisti.re.kr

More information

Parallel Longest Common Subsequence using Graphics Hardware

Parallel Longest Common Subsequence using Graphics Hardware Parallel Longest Common Subsequence using Graphics Hardware John Kloetzli rian Strege Jonathan Decker Dr. Marc Olano Presented by: rian Strege 1 Overview Introduction Problem Statement ackground and Related

More information

Evaluation and Benchmarking of Highly Scalable Parallel Numerical Libraries

Evaluation and Benchmarking of Highly Scalable Parallel Numerical Libraries Evaluation and Benchmarking of Highly Scalable Parallel Numerical Libraries Christos Theodosiou (ctheodos@grid.auth.gr) User and Application Support Scientific Computing Centre @ AUTH Presentation Outline

More information

Quantum Computer Simulation Using CUDA (Quantum Fourier Transform Algorithm)

Quantum Computer Simulation Using CUDA (Quantum Fourier Transform Algorithm) Quantum Computer Simulation Using CUDA (Quantum Fourier Transform Algorithm) Alexander Smith & Khashayar Khavari Department of Electrical and Computer Engineering University of Toronto April 15, 2009 Alexander

More information

ExaGeoStat: A High Performance Unified Software for Geostatistics on Manycore Systems

ExaGeoStat: A High Performance Unified Software for Geostatistics on Manycore Systems IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, VOL. XX, NO. X, M YYYY 1 ExaGeoStat: A High Performance Unified Software for Geostatistics on Manycore Systems Sameh Abdulah, Hatem Ltaief, Ying Sun,

More information

SIMULATION OF ISING SPIN MODEL USING CUDA

SIMULATION OF ISING SPIN MODEL USING CUDA SIMULATION OF ISING SPIN MODEL USING CUDA MIRO JURIŠIĆ Supervisor: dr.sc. Dejan Vinković Split, November 2011 Master Thesis in Physics Department of Physics Faculty of Natural Sciences and Mathematics

More information

S0214 : GPU Based Stacking Sequence Generation For Composite Skins Using GA

S0214 : GPU Based Stacking Sequence Generation For Composite Skins Using GA S0214 : GPU Based Stacking Sequence Generation For Composite Skins Using GA Date: 16th May 2012 Wed, 3pm to 3.25pm(Adv. Session) Sathyanarayana K., Manish Banga, and Ravi Kumar G. V. V. Engineering Services,

More information

HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU

HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU April 4-7, 2016 Silicon Valley HIGH PERFORMANCE CTC TRAINING FOR END-TO-END SPEECH RECOGNITION ON GPU Minmin Sun, NVIDIA minmins@nvidia.com April 5th Brief Introduction of CTC AGENDA Alpha/Beta Matrix

More information

Parallel stochastic simulation using graphics processing units for the Systems Biology Toolbox for MATLAB

Parallel stochastic simulation using graphics processing units for the Systems Biology Toolbox for MATLAB Parallel stochastic simulation using graphics processing units for the Systems Biology Toolbox for MATLAB Supplemental material Guido Klingbeil, Radek Erban, Mike Giles, and Philip K. Maini This document

More information