1.jpg
Home Committees Program Journal Parallel Computing Registration Welcome reception Conference dinner Participants Accomodation General information Poster Session Past PMAA Contact

Program Overview

Click on a talk title to see the abstract. The schedule and book of abstracts is available as PDF.

Tuesday, June 29, 2010
05:00 PMRegistration
06:30 PMWelcome Reception (Wildt'sches Haus)
Prof. Ahmed Sameh, Basler Regierungsrat Dr. Hans-Peter Wessels
Wednesday, June 30, 2010
09:00 AMConference Opening
Peter Arbenz, Olaf Schenk
09:15 AMPlenary Talk:
Prof. George Biros
A parallel adaptive fast-multipole method on heterogeneous architectures

Session Chair: Olaf Schenk
Location: Lecture Room 102
10:15 AMCoffee and refreshment break
10:45 AMMinisymposium 1.1.A:
Sparse Matrix Computations on GPUs

Session Chair: Michael Garland
Location: Lecture Room 102
10:45 AMVasily Volkov: Use registers and multiple outputs per thread on GPU.
11:10 AMJee Choi: Model-driven Autotuning of Sparse Matrix-Vector Multiply on GPUs.
11:35 AMJohn D. Owens: Efficient GPU Tridiagonal Solvers.
12:00 PMWeichung Wang: On the GPU-accelerated Multifrontal.
10:45 AMMinisymposium 1.1.B:
Large Dense Eigenvalue Problems

Session Chair: Michael Bader
Location: Lecture Room 001
10:45 AMMatthias Petschow: The MRRR algorithm for multi-core processors.
11:10 AMKonrad Waldherr: Large eigenvalue problems: computation of ground states.
11:35 AMThomas Auckenthaler: A two-step tridiagonalization for the parallel symmetric eigenproblem.
12:00 PMBruno Lang: Partial Eigensystems of Symmetric Tridiagonals.
12:25 PMLunch (on your own)
02:00 PMMinisymposium 1.2.A:
Sparse Matrix Computations on GPUs

Session Chair: Olaf Schenk
Location: Lecture Room 102
02:00 PMMichael Garland: Sparse Matrix Computations on GPUs.
02:25 PMRobert Strzodka: GPU-Multigrid Solvers with Strong Smoothers .
02:50 PMTimothy Warburton: GPU Accelerated Discontinuous Galerkin Methods.
03:15 PMDimitri Komatitsch: A spectral-element seismic wave propagation algorithm on a cluster of 192 GPUs.
02:00 PMMinisymposium 1.2.B:
Dense Matrix Computations

Session Chair: Martin Becka
Location: Lecture Room 001
02:00 PMInge Gutheil: Performance Evaluation of ScaLAPACK Eigensolver Routnines on two HPC Systems.
02:25 PMZvonimir Bujanović: A hybrid $m$-Hessenberg reduction algorithm.
02:50 PMJürgen Götze: Parallel Jacobi Methods on Nanoscale Integrated Circuits.
03:15 PMMartin Becka: NEW ORDERING FOR THE PARALLEL ONE-SIDED BLOCK-JACOBI SVD ALGORITHM.
03:40 PMPoster Session and Coffee and refreshment break
04:10 PMPlenary Talk:
Prof. Laura Grigori
Minimizing Communication in Linear Algebra, Part 1

Session Chair: Ahmed Sameh
Location: Lecture Room 102
Thursday, July 1, 2010
08:40 AMMinisymposium 2.1.A:
Combinatorial Scientific Computing

Session Chair: Laura Grigori
Location: Lecture Room 120
08:40 AMJohannes Langguth: A parallel distributed memory algorithm for bipartite matchings.
09:05 AMMadan Sathe: Parallel Exact Matching in Massively-Parallel Large-Scale Nonlinear Optimization.
09:30 AMFrançois Pellegrini: Current challenges for parallel graph partitioning and static mapping.
09:55 AMRob H. Bisseling: Sparse matrix partitioning, ordering, and visualing by Mondriaan 3.0.
08:40 AMMinisymposium 2.1.B:
Parallel Monte-Carlo

Session Chair: Aneta Karaivanova
Location: Lecture Room 117
08:40 AMYasunori Futamura: Parallel stochastic estimation method for matrix eigenvalue distribution.
09:05 AMAndrew Gilpin: Speeding Up Modern Gradient-Based Algorithms for Large Sequential Games.
09:30 AMYongji Zhou: Matrix Aided Task Scheduling – A Scheduling Scheme with Mathematical Representation of Task Dependency.
09:55 AMAneta Karaivanova: GPU-based quasi-Monte Carlo algorithms for matrix computations.
08:40 AMMinisymposium 2.1.C:
Multilevel Methods

Session Chair: Yvan Notay
Location: Lecture Room 116
08:40 AMYavor Vutov: Large Scale Finite Element Modeling on Unstructured Grids.
09:05 AMPascal Hénon: Improve ILU preconditioners by recursive solves.
09:30 AMVit Vondrak: MatSol – parallel implementation of scalable algorithms for large multibody contact problems.
09:55 AMYvan Notay: A parallel algebraic multigrid method.
10:20 AMCoffee and refreshment break
10:50 AMMinisymposium 2.1.D:
Combinatorial Scientific Computing

Session Chair: Olaf Schenk
Location: Lecture Room 120
10:50 AMBora Uçar: On finding dense submatrices of a sparse matrix.
11:15 AMCédric Chevalier: Combinatorial models for mesh partitioning.
11:40 AMMeisam Sharify: A parallel preprocessing for the optimal assignment problem based on diagonal scaling.
12:05 PMGiorgos Kollias: Parallel Algorithms for Graph Similarity.
10:50 AMMinisymposium 2.1.E:
Sparse Matrices and Applications

Session Chair: Pascal Hénon
Location: Lecture Room 116
10:50 AMGergana Bencheva: Parallel Algorithms for Solution of a Chemotaxis System in Haematology.
11:15 AMUrban Borštnik: Parallel Sparse Matrix Library and Preconditioner Construction for Quantum Chemical Calculations of Large Systems.
11:40 AMNao Kuroiwa: A parallel space-time finite difference solver for the steady-state shallow-water equation.
12:05 PMPasqua D'Ambra: High-Performance Preconditioners for the Solution of Pressure Systems in the LES of Turbulent Channel Flows.
10:50 AMMinisymposium 2.1.F:
Recent advances in Eigenvalues and least-squares computation

Session Chair: Jose E. Roman and Paulo Vasconcelos
Location: Lecture Room 117
10:50 AMMarc Baboulin: Computational issues in least squares conditioning.
11:15 AMRui Ralha: Mixed precision computation of eigenvalues.
11:40 AMAndres Tomas: Efficient Gram-Schmidt orthogonalization with CUDA for iterative eigensolvers.
12:05 PMJose E. Roman: Parallel linearization-based solvers for the quadratic eigenproblem.
12:30 PMLunch (on your own)
02:00 PMMinisymposium 2.2.A:
Voxel based Computations

Session Chair: Peter Arbenz
Location: Lecture Room 120
02:00 PMDieter H. Pahr: Virtual Diagnosis - Voxel-based Simulations of Human Bones .
02:25 PMCyril Flaig: A Memory Efficient Multigrid Preconditioner for Micro-Finite Element Analysis based on Voxel Images.
02:50 PMNikola Kosturski: Efficient Parallel Solution Algorithms for μFEM Elasticity Systems.
03:15 PMMichael Bader: Memory-Efficient Sierpinski-order Traversals on Dynamically Adaptive, Recursively Structured Triangular Grids.
02:00 PMMinisymposium 2.2.B:
Hybrid Solvers for Fluid Flow

Session Chair: Achim Basermann
Location: Lecture Room 117
02:00 PMLuc Giraud: Parallel scalability and complexity analysis of sparse hybrid linear solvers.
02:25 PMJonas Thies: A robust parallel hybrid solver for fluid flow problems.
02:50 PMAchim Basermann: Distributed Schur Complement Solvers for Real and Complex Block-Structured CFD Problems.
02:00 PMMinisymposium 2.2.C:
Miscellaneous A

Session Chair: Jennifer Scott
Location: Lecture Room 116
02:00 PMTamas Kurics: Equivalent operator preconditioning for elliptic problems with nonhomogeneous mixed boundary conditions.
02:25 PMT.B. Jonsthovel: On the Performance and Implementation of the Parallel Deflated Preconditioned Conjugate Gradient method.
02:50 PMKrzysztof Rojek: Model-Driven Adaptation of Double-Precision Matrix Multiplication to the Cell Processor Architecture.
03:15 PMJennifer Scott: Designing sparse direct solvers for multicore architectures.
03:40 PMCoffee and refreshment break
04:10 PMMinisymposium 2.2.D:
Voxel based Computations

Session Chair: Maya Neytcheva
Location: Lecture Room 120
04:10 PMFumihiko Ino: Accelerating Iterative Stencil Computations on the GPU.
04:35 PMMiriam Mehl: Parallel Multigrid Methods on Octree-Like Grids in the Peano Framework.
05:00 PMVojtěch Sokol: Voxel based analysis of geomaterials with Schwarz-type parallel solvers.
05:25 PMYves Ineichen: A Fast Parallel Poisson Solver on Irregular Domains.
04:10 PMMinisymposium 2.2.E:
Miscellaneous B

Session Chair: Pasqua D'Ambra
Location: Lecture Room 116
04:10 PMTetsuya Sakurai: A hierarchical parallel eigenvalue solver: parallelism on top of multicore linear solvers.
04:35 PMJulien Callant: Towards a robust algorithm for computing the rightmost eigenvalue..
05:00 PMMatous Sedlacek: Smoothing and Regularization with Modified Sparse Approximate Inverses.
05:25 PMMikolaj Szydlarski: Algebraic Optimized Schwarz Domain Decomposition Methods.
04:10 PMMinisymposium 2.2.F:
Helmholtz and Maxwell Solvers

Session Chair: Rob H. Bisseling
Location: Lecture Room 117
04:10 PMDan Gordon: A robust and efficient, highly scalable parallel solution of the Helmholtz equation with large wave numbers.
04:35 PMRafael Lago: Solution of three-dimensional heterogeneous Helmholtz problems in geophysics.
05:00 PMChristian Wieners: A Multigrid Method for Maxwell's Equations with Parallel Nearly Direct Coarse Grid Solver.
05:25 PMGiorgos Kollias: Asynchronous Row Projections.
07:00 PMConference Dinner
Friday, July 2, 2010
09:15 AMPlenary Talk:
Prof. Jim Demmel
Minimizing Communication in Linear Algebra, Part 2

Session Chair: Costas Bekas
Location: Lecture Room 102
10:15 AMCoffee and refreshment break
10:45 AMMinisymposium 3.1.A:
Autotuning

Session Chair: Rich Vuduc
Location: Lecture Room 102
10:45 AMEmmanuel Agullo: Autotuning dense linear algebra libraries on multicore architectures.
11:10 AMCédric Augonnet: Auto-tuned performance models to improve task scheduling on accelerator-based platforms.
11:35 AMMatthias Christen: Code Generation and Autotunig for Stencil Codes for Multi- and Manycore Architectures.
12:00 PMDiego Fabregat Traver: Linear Algebra Algorithms for Automatic Differentiation.
10:45 AMMinisymposium 3.1.B:
Accelerating the solution of linear systems and eigenvalue problems on Heterogeneous Computing Environments

Session Chair: Costas Bekas
Location: Lecture Room 001
10:45 AMFrancisco D. Igual: Accelerating PLAPACK on Hybrid CPU-GPU Clusters.
11:10 AMLars Karlsson: Fast Reduction to Hessenberg Form on Multicore Architectures.
11:35 AMDaniel Kressner: Iterative Refinement of Spectral Decompositions in Heterogeneous Computing Environments.
12:00 PMCostas Bekas: Multicore Computers Can Protect Your Bones: Rendering the Computerized Diagnosis of Osteoporosis a Routine Clinical Practice .
12:25 PMLunch (on your own)
02:00 PMMinisymposium 3.2.A:
Autotuning

Session Chair: Emmanuel Agullo
Location: Lecture Room 102
02:00 PMP. Sadayappan: Parametric Tiling for Auto Tuning.
02:25 PMReiji Suda: Online Automatic Tuning of Parallel Sparse Matrix Computations.
02:50 PMEmmanuel Agullo: Autotuning dense linear algebra libraries on GPUs.
02:00 PMMinisymposium 3.2.B:
Accelerating the solution of linear systems and eigenvalue problems on Heterogeneous Computing Environments

Session Chair: Daniel Kressner
Location: Lecture Room 001
02:00 PMJulien Langou: Choosing a Reduction Tree for Communication Avoiding QR.
02:25 PMEric Polizzi: The FEAST eigenvalue parallel algorithm and solver.
02:50 PMJonathan Hogg: The challenge of the solve phase of a multicore solver.
03:15 PMPoster Session and Coffee and refreshment break
03:45 PMPlenary Talk:
Prof. Ahmed Sameh
A Scalable Parallel Sparse Linear System Solver

Session Chair: Peter Arbenz
Location: Lecture Room 102
04:45 PMClosing Remarks
Erricos J. Kontoghiorghes