Hybrid parallel discrete adjoints in SU2

IF 2.5 3区工程技术 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Fluids Pub Date : 2024-12-24 DOI:10.1016/j.compfluid.2024.106528

Johannes Blühdorn , Pedro Gomes , Max Aehle , Nicolas R. Gauger

{"title":"Hybrid parallel discrete adjoints in SU2","authors":"Johannes Blühdorn , Pedro Gomes , Max Aehle , Nicolas R. Gauger","doi":"10.1016/j.compfluid.2024.106528","DOIUrl":null,"url":null,"abstract":"<div><div>The open-source multiphysics suite SU2 features discrete adjoints by means of operator overloading automatic differentiation (AD). While both primal and discrete adjoint solvers support MPI parallelism, hybrid parallelism using both MPI and OpenMP has only been introduced for the primal solvers so far. In this work, we enable hybrid parallel discrete adjoint solvers. Coupling SU2 with OpDiLib, an add-on for operator overloading AD tools that extends AD to OpenMP parallelism, marks a key step in this endeavour. We identify the affected parts of SU2’s advanced AD workflow and discuss the required changes and their tradeoffs. Detailed performance studies compare MPI parallel and hybrid parallel discrete adjoints in terms of memory and runtime and unveil key performance characteristics. We showcase the effectiveness of performance optimizations and highlight perspectives for future improvements. At the same time, this study demonstrates the applicability of OpDiLib in a large code base and its scalability on large test cases, providing valuable insights for future applications both within and beyond SU2.</div></div>","PeriodicalId":287,"journal":{"name":"Computers & Fluids","volume":"289 ","pages":"Article 106528"},"PeriodicalIF":2.5000,"publicationDate":"2024-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Fluids","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0045793024003591","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}

引用次数: 0

Abstract

The open-source multiphysics suite SU2 features discrete adjoints by means of operator overloading automatic differentiation (AD). While both primal and discrete adjoint solvers support MPI parallelism, hybrid parallelism using both MPI and OpenMP has only been introduced for the primal solvers so far. In this work, we enable hybrid parallel discrete adjoint solvers. Coupling SU2 with OpDiLib, an add-on for operator overloading AD tools that extends AD to OpenMP parallelism, marks a key step in this endeavour. We identify the affected parts of SU2’s advanced AD workflow and discuss the required changes and their tradeoffs. Detailed performance studies compare MPI parallel and hybrid parallel discrete adjoints in terms of memory and runtime and unveil key performance characteristics. We showcase the effectiveness of performance optimizations and highlight perspectives for future improvements. At the same time, this study demonstrates the applicability of OpDiLib in a large code base and its scalability on large test cases, providing valuable insights for future applications both within and beyond SU2.

查看原文本刊更多论文

SU2中的混合并行离散伴随

开源多物理场套件SU2通过操作符重载自动微分（AD）实现离散伴随。虽然原始和离散伴随求解器都支持MPI并行性，但到目前为止，使用MPI和OpenMP的混合并行性仅用于原始求解器。在这项工作中，我们启用了混合并行离散伴随求解器。将SU2与OpDiLib（一种用于操作符重载AD工具的附加组件，可将AD扩展到OpenMP并行性）相结合，标志着这一努力的关键一步。我们确定了SU2高级AD工作流程中受影响的部分，并讨论了所需的更改及其权衡。详细的性能研究比较了MPI并行和混合并行离散伴随在内存和运行时间方面的性能，并揭示了关键的性能特征。我们展示了性能优化的有效性，并强调了未来改进的前景。同时，本研究展示了OpDiLib在大型代码库中的适用性及其在大型测试用例中的可伸缩性，为未来的SU2内外的应用程序提供了有价值的见解。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computers & Fluids 物理-计算机：跨学科应用

CiteScore

5.30

自引率

7.10%

发文量

242

审稿时长

10.8 months

期刊介绍： Computers & Fluids is multidisciplinary. The term ''fluid'' is interpreted in the broadest sense. Hydro- and aerodynamics, high-speed and physical gas dynamics, turbulence and flow stability, multiphase flow, rheology, tribology and fluid-structure interaction are all of interest, provided that computer technique plays a significant role in the associated studies or design methodology.