A Left-Looking Selected Inversion Algorithm and Task Parallelism on Shared Memory Systems

TL;DR

This paper introduces a left-looking selected inversion algorithm optimized for shared memory systems, demonstrating improved scalability and potential for parallelization on multicore and manycore architectures.

Contribution

It presents the first implementation of a left-looking selected inversion algorithm using task parallelism, enhancing scalability on shared memory architectures.

Findings

The left-looking algorithm scales well on multicore and manycore systems.

Task scheduling with OpenMP 4.0 improves parallel efficiency.

Left-looking formulation enables pipelining and better parallelization.

Abstract

Given a sparse matrix $A$, the selected inversion algorithm is an efficient method for computing certain selected elements of $A^{-1}$. These selected elements correspond to all or some nonzero elements of the LU factors of $A$. In many ways, the type of matrix updates performed in the selected inversion algorithm is similar to that performed in the LU factorization, although the sequence of operation is different. In the context of LU factorization, it is known that the left-looking and right-looking algorithms exhibit different memory access and data communication patterns, and hence different behavior on shared memory and distributed memory parallel machines. Corresponding to right-looking and left-looking LU factorization, selected inversion algorithm can be organized as a left-looking and a right-looking algorithm. The parallel right-looking version of the algorithm has been developed in [1]. The sequence of operations performed in this version of the selected inversion algorithm is similar to those performed in a left-looking LU factorization algorithm. In this paper, we describe the left-looking variant of the selected inversion algorithm, and based on task parallel method, present an efficient implementation of the algorithm for shared memory machines. We demonstrate that with the task scheduling features provided by OpenMP 4.0, the left-looking selected inversion algorithm can scale well both on the Intel Haswell multicore architecture and on the Intel Knights Corner (KNC) manycore architecture. Compared to the right-looking selected inversion algorithm, the left-looking formulation facilitates pipelining of work along different branches of the elimination tree, and can be a promising candidate for future development of massively parallel selected inversion algorithms on heterogeneous architecture.