当前位置: X-MOL 学术ACM Trans. Math. Softw. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
PHIST
ACM Transactions on Mathematical Software ( IF 2.7 ) Pub Date : 2020-10-16 , DOI: 10.1145/3402227
Jonas Thies 1 , Melven Röhrig-Zöllner 1 , Nigel Overmars 1 , Achim Basermann 1 , Dominik Ernst 2 , Georg Hager 2 , Gerhard Wellein 2
Affiliation  

The increasing complexity of hardware and software environments in high-performance computing poses big challenges on the development of sustainable and hardware-efficient numerical software. This article addresses these challenges in the context of sparse solvers. Existing solutions typically target sustainability, flexibility, or performance, but rarely all of them. Our new library PHIST provides implementations of solvers for sparse linear systems and eigenvalue problems. It is a productivity platform for performance-aware developers of algorithms and application software with abstractions that do not obscure the view on hardware-software interaction. The PHIST software architecture and the PHIST development process were designed to overcome shortcomings of existing packages. An interface layer for basic sparse linear algebra functionality that can be provided by multiple backends ensures sustainability, and PHIST supports common techniques for improving scalability and performance of algorithms such as blocking and kernel fusion. We showcase these concepts using the PHIST implementation of a block Jacobi-Davidson solver for non-Hermitian and generalized eigenproblems. We study its performance on a multi-core CPU, a GPU, and a large-scale many-core system. Furthermore, we show how an existing implementation of a block Krylov-Schur method in the Trilinos package Anasazi can benefit from the performance engineering techniques used in PHIST.

中文翻译:

PHIST

高性能计算中硬件和软件环境的日益复杂性对可持续和硬件高效的数值软件的开发提出了巨大挑战。本文在稀疏求解器的背景下解决了这些挑战。现有解决方案通常针对可持续性、灵活性或性能,但很少针对所有这些。我们的新库 PHIST 为稀疏线性系统和特征值问题提供求解器的实现。它是一个生产力平台,适用于算法和应用软件的性能感知开发人员,其抽象不会模糊硬件-软件交互的观点。PHIST 软件架构和 PHIST 开发过程旨在克服现有软件包的缺点。可以由多个后端提供的基本稀疏线性代数功能的接口层确保了可持续性,并且 PHIST 支持用于提高算法的可扩展性和性能的常用技术,例如阻塞和内核融合。我们使用用于非厄米特和广义特征问题的块 Jacobi-Davidson 求解器的 PHIST 实现来展示这些概念。我们研究了它在多核 CPU、GPU 和大规模多核系统上的性能。此外,我们展示了 Trilinos 包 Anasazi 中块 Krylov-Schur 方法的现有实现如何从 PHIST 中使用的性能工程技术中受益。PHIST 支持提高算法可扩展性和性能的常用技术,例如阻塞和内核融合。我们使用用于非厄米特和广义特征问题的块 Jacobi-Davidson 求解器的 PHIST 实现来展示这些概念。我们研究了它在多核 CPU、GPU 和大规模多核系统上的性能。此外,我们展示了 Trilinos 包 Anasazi 中块 Krylov-Schur 方法的现有实现如何从 PHIST 中使用的性能工程技术中受益。PHIST 支持提高算法可扩展性和性能的常用技术,例如阻塞和内核融合。我们使用用于非厄米特和广义特征问题的块 Jacobi-Davidson 求解器的 PHIST 实现来展示这些概念。我们研究了它在多核 CPU、GPU 和大规模多核系统上的性能。此外,我们展示了 Trilinos 包 Anasazi 中块 Krylov-Schur 方法的现有实现如何从 PHIST 中使用的性能工程技术中受益。
更新日期:2020-10-16
down
wechat
bug