Skip to Main content Skip to Navigation
Reports

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

Abstract : We describe an efficient and innovative parallel tiled algorithm for solving symmetric indefinite systems on multicore architectures. This solver avoids pivoting by using a multiplicative preconditioning based on symmetric randomization. This randomization prevents the communication overhead due to pivoting, is computationally inexpensive and requires very little storage. Following randomization, a tiled LDLT factorization is used that reduces synchronization by using static or dynamic scheduling. We compare Gflop/s performance of our solver with other types of factorizations on a current multicore machine and we provide tests on accuracy using LAPACK test cases.
Document type :
Reports
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/inria-00631361
Contributor : Marc Baboulin <>
Submitted on : Wednesday, October 12, 2011 - 11:14:41 AM
Last modification on : Wednesday, October 14, 2020 - 4:00:32 AM
Long-term archiving on: : Sunday, December 4, 2016 - 6:20:59 AM

File

RR-7762.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00631361, version 1

Collections

Citation

Marc Baboulin, Dulceneia Becker, Jack Dongarra. A parallel tiled solver for dense symmetric indefinite systems on multicore architectures. [Research Report] RR-7762, INRIA. 2011. ⟨inria-00631361⟩

Share

Metrics

Record views

289

Files downloads

473