Introduction to StarNEig—A Task-Based Library for Solving Nonsymmetric Eigenvalue Problems

Abstract

In this paper, we present the StarNEig library for solving dense non-symmetric (generalized) eigenvalue problems. The library is built on top of the StarPU runtime system and targets both shared and distributed memory machines. Some components of the library support GPUs. The library is currently in an early beta state and only real arithmetic is supported. Support for complex data types is planned for a future release. This paper is aimed for potential users of the library. We describe the design choices and capabilities of the library, and contrast them to existing software such as ScaLAPACK. StarNEig implements a ScaLAPACK compatibility layer that should make it easy for a new user to transition to StarNEig. We demonstrate the performance of the library with a small set of computational experiments.

Task‐based, GPU‐accelerated and robust library for solving dense nonsymmetric eigenvalue problems

“…In the eigenvalue reordering experiments, 35% of the diagonal blocks were randomly selected. The distributed memory experiments were initially reported in the NLAFET Deliverable Report D2.7 8 and the original conference paper 9 …”

“…In the best case, the speedup when moving from a single V100 GPU to two V100 GPUs is 1.83. This experiment was initially reported in the NLAFET Deliverable Report D2.7 8 and the original conference paper 9 …”

“…Remark This paper is an extended version of a conference paper by the authors 9 . The original conference paper only discussed extensively two of the four phases (Schur reduction and eigenvalue reordering).…”

Parallel Robust Computation of Generalized Eigenvectors of Matrix Pencils

“…It is straightforward to derived a blocked algorithm for solving the homogeneous matrix equation (9). Specifically, redefine…”

Peer Review #2 of "Improving parallel executions by increasing task granularity in task-based runtime systems using acyclic DAG clustering (v0.1)"

“…Moreover, the well-known and widely used OpenMP standard [8] also supports the tasks and dependencies paradigm since version 4. The advantage of the method to achieve high-performance and facilitate the use of heterogeneous computing nodes has been demonstrated by the development of many applications in various fields [9,10,11,12,13,14,15].…”