Exploiting nested task-parallelism in the H-LU factorization
Scholar | Other documents of the author: Carratalá Sáez, Rocío; Christophersen, Sven; Aliaga Estellés, José Ignacio; Beltran, Vicenç; Börm, Steffen; Quintana Ortí, Enrique S.
MetadataShow full item record
TitleExploiting nested task-parallelism in the H-LU factorization
We address the parallelization of the LU factorization of hierarchical matrices (-matrices) arising from boundary element methods. Our approach exploits task-parallelism via the OmpSs programming model and runtime, ... [+]
We address the parallelization of the LU factorization of hierarchical matrices (-matrices) arising from boundary element methods. Our approach exploits task-parallelism via the OmpSs programming model and runtime, which discovers the data-flow parallelism intrinsic to the operation at execution time, via the analysis of data dependencies based on the memory addresses of the tasks’ operands. This is especially challenging for H-matrices, as the structures containing the data vary in dimension during the execution. We tackle this issue by decoupling the data structure from that used to detect dependencies. Furthermore, we leverage the support for weak operands and early release of dependencies, recently introduced in OmpSs-2, to accelerate the execution of parallel codes with nested task-parallelism and fine-grain tasks. As a result, we obtain a significant improvement in the parallel performance with respect to our previous work. [-]
Investigation projectMINECO (CICYT TIN2014-53495-R) ; FEDER (TIN2017-82972-R) ; Universitat Jaume I (UJI-B2017-46); MECD (FPU program)
Bibliographic citationCARRATALÁ-SÁEZ, Rocío, et al. Exploiting Nested Task-Parallelism in the H-LU Factorization. Journal of Computational Science, 2019, 33:20-33
© 2019 Elsevier B.V. All rights reserved.
This item appears in the folowing collection(s)
- ICC_Articles