Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks

The increasing demand for solving larger and more complex problems in computational science and engineering is a major driving factor to deploy computer systems with ever-advancing performance capabilities. To increase the available performance, modern HPC platforms come with multiple levels of para...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Autor principal: Kreutzer, Moritz
Formato: Online
Idioma:inglês
Publicado em: FAU University Press 2025
Assuntos:
Acesso em linha:ONIX_20250828T094736_9783961471041_3
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
_version_ 1869531025409835008
author Kreutzer, Moritz
author_browse Kreutzer, Moritz
author_facet Kreutzer, Moritz
author_sort Kreutzer, Moritz
collection Directory of Open Access Books
description The increasing demand for solving larger and more complex problems in computational science and engineering is a major driving factor to deploy computer systems with ever-advancing performance capabilities. To increase the available performance, modern HPC platforms come with multiple levels of parallelism, complex memory hierarchies, heterogeneous architectures, and extreme scales. To match the need for sustainable and efficient software under these premises, special value has to be attached to the inherent challenges like efficiency on all scales and performance portability across heterogeneous architectures. This work addresses the development of high-performance scientific software for sparse linear algebra, which is an important field of research and forms the foundation of many applications of computational science and engineering, with a special focus on sparse eigenvalue solvers on current and future supercomputers. Consequent employment of performance models as well as a holistic view on applications, algorithms, and hardware architectures enable the creation of basic computational building blocks, custom compute kernels, and optimized algorithmic formulations with provably high efficiency. To demonstrate the applicability of the developed software components, full-application performance of selected sparse eigenvalue solvers for real-world problems on some of the world‘s largest supercomputers with completely different hardware architectures – including homogeneous multi-core CPU clusters, GPU-accelerated clusters, and selfhosted many-core CPU clusters – is presented.
format Online
id doab-20.500.12854ir-166259
institution Directory of Open Access Books
language eng
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher FAU University Press
publisherStr FAU University Press
record_format ojs
spelling doab-20.500.12854ir-1662592025-10-16T12:53:16Z Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks Kreutzer, Moritz Grafikprozessor Software Hochleistungsrechnen Computerarchitektur Leistungssteigerung Matrizenrechnung thema EDItEUR::U Computing and Information Technology The increasing demand for solving larger and more complex problems in computational science and engineering is a major driving factor to deploy computer systems with ever-advancing performance capabilities. To increase the available performance, modern HPC platforms come with multiple levels of parallelism, complex memory hierarchies, heterogeneous architectures, and extreme scales. To match the need for sustainable and efficient software under these premises, special value has to be attached to the inherent challenges like efficiency on all scales and performance portability across heterogeneous architectures. This work addresses the development of high-performance scientific software for sparse linear algebra, which is an important field of research and forms the foundation of many applications of computational science and engineering, with a special focus on sparse eigenvalue solvers on current and future supercomputers. Consequent employment of performance models as well as a holistic view on applications, algorithms, and hardware architectures enable the creation of basic computational building blocks, custom compute kernels, and optimized algorithmic formulations with provably high efficiency. To demonstrate the applicability of the developed software components, full-application performance of selected sparse eigenvalue solvers for real-world problems on some of the world‘s largest supercomputers with completely different hardware architectures – including homogeneous multi-core CPU clusters, GPU-accelerated clusters, and selfhosted many-core CPU clusters – is presented. 2025-08-29T05:06:55Z 2025-08-29T05:06:55Z 2025-08-28T07:58:19Z 2018 book ONIX_20250828T094736_9783961471041_3 https://library.oapen.org/handle/20.500.12657/105759 9783961471041 9783961471034 https://directory.doabooks.org/handle/20.500.12854/166259 eng FAU Forschungen : Reihe B open access image/jpeg image/jpeg n/a n/a https://library.oapen.org/bitstream/20.500.12657/105759/1/9783961471041.pdf https://library.oapen.org/bitstream/20.500.12657/105759/1/9783961471041.pdf FAU University Press 10.25593/978-3-96147-104-1 10.25593/978-3-96147-104-1 2c600dea-eece-4066-87be-da335e323fdb 9783961471041 9783961471034 AG Universitätsverlage 213 Erlangen open access
spellingShingle Grafikprozessor
Software
Hochleistungsrechnen
Computerarchitektur
Leistungssteigerung
Matrizenrechnung
thema EDItEUR::U Computing and Information Technology
Kreutzer, Moritz
Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title_full Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title_fullStr Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title_full_unstemmed Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title_short Performance Engineering for Exascale-Enabled Sparse Linear Algebra Building Blocks
title_sort performance engineering for exascale enabled sparse linear algebra building blocks
topic Grafikprozessor
Software
Hochleistungsrechnen
Computerarchitektur
Leistungssteigerung
Matrizenrechnung
thema EDItEUR::U Computing and Information Technology
topic_facet Grafikprozessor
Software
Hochleistungsrechnen
Computerarchitektur
Leistungssteigerung
Matrizenrechnung
thema EDItEUR::U Computing and Information Technology
url ONIX_20250828T094736_9783961471041_3
work_keys_str_mv AT kreutzermoritz performanceengineeringforexascaleenabledsparselinearalgebrabuildingblocks