A Preliminary Out-of-Core Extension of a Parallel Multifrontal Solver
نویسندگان
چکیده
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems. This paper describes a first implementation of an out-of-core extension to a parallel multifrontal solver (MUMPS). We show that larger problems can be solved on limited-memory machines with reasonable performance, and we illustrate the behaviour of our parallel out-of-core factorization. Then we use simulations to discuss how our algorithms can be modified to solve much larger problems.
منابع مشابه
An out-of-core extension of a parallel sparse multifrontal solver
We describe an out-of-core extension of a parallel sparse multifrontal solver, MUMPS. In a first implementation factors are written to disk as soon as computed whereas the stack memory remains in-core. We then overlap disk accesses with computation and allow some factors to stay incore after factorization, thus enhancing the performance of both the factorization and solution steps. Finally we a...
متن کاملParallel multifrontal method with out-of-core techniques
The memory usage of sparse direct solvers can be the bottleneck to solve large-scale problems. We describe the ongoing work on the implementation of an out-of-core extension to a parallel multifrontal solver (MUMPS). We show that larger problems can be solved on limited-memory machines with reasonable performance, and we illustrate the behaviour of both the parallel out-of-core factorization an...
متن کاملAnalysis of the out-of-core solution phase of a parallel multifrontal approach
ABSTRACT We consider the parallel solution of sparse linear systems of equations in a limited memory environment. A preliminary out-of core version of a sparse multifrontal code called MUMPS (MUltifrontal Massively Parallel Solver) has been developed as part of a collaboration with members of the INRIA project GRAAL. In this context, we assume that the factors have been written on the hard disk...
متن کاملAnalysis of the solution phase of a parallel multifrontal approach
We study the forward and backward substitution phases of a sparse multifrontal factorization. These phases are often neglected in papers on sparse direct factorization but, in many applications, they can be the bottleneck so it is crucial to implement them efficiently. In this work, we assume that the factors have been written on disk during the factorization phase, and we discuss the design of...
متن کاملMemory and performance issues in parallel multifrontal factorizations and triangular solutions with sparse right-hand sides
We consider the solution of very large sparse systems of linear equations on parallel architectures. In this context, memory is often a bottleneck that prevents or limits the use of direct solvers, especially those based on the multifrontal method. This work focuses on memory and performance issues of the two memory and computationally intensive phases of direct methods, namely, the numerical f...
متن کامل