Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

On the Performance of an Algebraic Multigrid Solver on Multicore Clusters

Conference ·
Algebraic multigrid (AMG) solvers have proven to be extremely efficient on distributed-memory architectures. However, when executed on modern multicore cluster architectures, we face new challenges that can significantly harm AMG's performance. We discuss our experiences on such an architecture and present a set of techniques that help users to overcome the associated problems, including thread and process pinning and correct memory associations. We have implemented most of the techniques in a MultiCore SUPport library (MCSup), which helps to map OpenMP applications to multicore machines. We present results using both an MPI-only and a hybrid MPI/OpenMP model.
Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA
Sponsoring Organization:
USDOE
DOE Contract Number:
W-7405-ENG-48
OSTI ID:
986057
Report Number(s):
LLNL-CONF-420726
Country of Publication:
United States
Language:
English

References (13)

Optimization of sparse matrix–vector multiplication on emerging multicore platforms journal March 2009
Pursuing scalability for hypre 's conceptual interfaces journal September 2005
Towards Cache-Optimized Multigrid Using Patch-Adaptive Relaxation book January 2006
BoomerAMG: A parallel algebraic multigrid solver and preconditioner journal April 2002
Distance-two interpolation for parallel algebraic multigrid journal January 2008
Enhancing the Performance of Multigrid Smoothers in Simultaneous Multithreading Architectures book January 2007
A Multigrid Tutorial, Second Edition book January 2000
Scientific Computing Kernels on the Cell Processor journal April 2007
Reducing Complexity in Parallel Algebraic Multigrid Preconditioners journal January 2006
Multigrid and Gauss-Seidel smoothers revisited: parallelization on chip multiprocessors conference January 2006
The Impact of Multicore on Math Software book January 2006
Optimization of sparse matrix-vector multiplication on emerging multicore platforms conference January 2007
An introduction to algebraic multigrid journal November 2006

Similar Records

On the Performance of an Algebraic MultigridSolver on Multicore Clusters
Conference · Thu Apr 29 00:00:00 EDT 2010 · OSTI ID:1012429

Challenges of Algebraic Multigrid across Multicore Architectures
Conference · Mon Apr 12 00:00:00 EDT 2010 · OSTI ID:1013213

Modeling the Performance of an Algebraic Multigrid Cycle Using Hybrid MPI/OpenMP
Conference · Sat Sep 01 00:00:00 EDT 2012 · 2012 41st International Conference on Parallel Processing; 10-13 Sept. 2012; Pittsburgh, PA, USA · OSTI ID:1567579