PACO 2019: 3rd Workshop on Power-Aware Computing

Exploiting Nested Task-Parallelism in the LU Factorization of Hierarchical Matrices

5 Nov 2019, 09:50

30m

Main/groundfloor-V0.05/2+3 - Prigogine (Max Planck Institute for Dynamics of Complex Technical Systems)

Talk Day I

Speaker

Rocío Carratalá-Sáez (Universitat Jaume I)

Description

Hierarchical matrices (H-matrices) lie in-between dense and sparse scenarios. Therefore, it is natural to tackle the LU factorization of H-Matrices via a task-parallel approach, which has recently reported successful results for related linear algebra problems. In this work, we will describe how to discover 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 data structures dimensions vary during the execution.