Load-balanced parallel banded-system solvers
نویسندگان
چکیده
منابع مشابه
On some parallel banded system solvers
We consider algorithms for solving narrow-banded diagonally dominant linear systems which are suitable for multiprocessors. We describe a direct solver similar to that in [12] for tridiagonal systems, and in [9] for solving a banded system on a linearly connected set of processors. We will also provide and analyze a parallel implementation of the partitioning algorithm and the matrix decomposit...
متن کاملA Note on ScaLAPACK's Banded System Solvers
We suggest modiications in the local computations of the ScaLAPACK subroutines for solving diagonally dominant and arbitrary narrow-banded linear systems. The modiications concern the way auxiliary variables are stored. The numerical properties of the algorithms are not aaected. However, as the way the memory is accessed is changed the performance of the solvers is signiicantly improved. We dis...
متن کاملWeighted Matrix Ordering and Parallel Banded Preconditioners for Iterative Linear System Solvers
The emergence of multicore architectures and highly scalable platforms motivates the development of novel algorithms and techniques that emphasize concurrency and are tolerant of deep memory hierarchies, as opposed to minimizing raw FLOP counts. While direct solvers are reliable, they are often slow and memory-intensive for large problems. Iterative solvers, on the other hand, are more efficien...
متن کاملFast Banded Linear Equation Solvers
A new algorithm for solving triangular linear equations is reported that is signiicantly faster than conventional methods on vector and parallel architectures for small bandwidths. In essence, it is a block version of the cyclic reduction algorithm used for tridiagonal systems of equations, and is applicable to general banded systems as well.
متن کاملPerfectly load-balanced, optimal, stable, parallel merge
We present a simple, work-optimal and synchronization-free solution to the problem of stably merging in parallel two given, ordered arrays of m and n elements into an ordered array of m+ n elements. The main contribution is a new, simple, fast and direct algorithm that determines, for any prefix of the stably merged output sequence, the exact prefixes of each of the two input sequences needed t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Theoretical Computer Science
سال: 2002
ISSN: 0304-3975
DOI: 10.1016/s0304-3975(01)00284-5