Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels

Although heterogeneous systems based on hardware accelerators are a trending topic in the HPC community, exploring the trade-offs of reconfigurable hardware-based ones in linear algebra libraries for high-performance systems, has not been deeply studied. Therefore, in this research, we aim to take...

Full description

Saved in:
Bibliographic Details
Main Authors: Alejandro Morales-Peña, Esteban Meneses
Format: Article
Language:English
Published: Universidad Autónoma de Bucaramanga 2025-01-01
Series:Revista Colombiana de Computación
Subjects:
Online Access:https://revistas.unab.edu.co/index.php/rcc/article/view/5276
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832584099419652096
author Alejandro Morales-Peña
Esteban Meneses
author_facet Alejandro Morales-Peña
Esteban Meneses
author_sort Alejandro Morales-Peña
collection DOAJ
description Although heterogeneous systems based on hardware accelerators are a trending topic in the HPC community, exploring the trade-offs of reconfigurable hardware-based ones in linear algebra libraries for high-performance systems, has not been deeply studied. Therefore, in this research, we aim to take advantage of FPGAs' reconfigurability, adaptability, and capacity to reduce power consumption to generate FPGA-based kernels in Ginkgo, a specialized high-performance linear algebra library for many-core systems. We generated 3 FPGA-based kernels for the CSR, SELLP, and SELL SpMV formats, and obtained speedups of at least 10x concerning CPU-based kernels. Furthermore, we demonstrated via a performance characterization study that FPGAs outperform general-purpose processors in terms of compute time.
format Article
id doaj-art-d76163f8b3144dedaeac77366e45d4ef
institution Kabale University
issn 1657-2831
2539-2115
language English
publishDate 2025-01-01
publisher Universidad Autónoma de Bucaramanga
record_format Article
series Revista Colombiana de Computación
spelling doaj-art-d76163f8b3144dedaeac77366e45d4ef2025-01-27T19:31:13ZengUniversidad Autónoma de BucaramangaRevista Colombiana de Computación1657-28312539-21152025-01-0125210.29375/25392115.5276Extending Ginkgo to Manage Reconfigurable Hardware-Based KernelsAlejandro Morales-Peña0Esteban Meneses1Costa Rica Institute of TechnologyCosta Rica Institute of Technology Although heterogeneous systems based on hardware accelerators are a trending topic in the HPC community, exploring the trade-offs of reconfigurable hardware-based ones in linear algebra libraries for high-performance systems, has not been deeply studied. Therefore, in this research, we aim to take advantage of FPGAs' reconfigurability, adaptability, and capacity to reduce power consumption to generate FPGA-based kernels in Ginkgo, a specialized high-performance linear algebra library for many-core systems. We generated 3 FPGA-based kernels for the CSR, SELLP, and SELL SpMV formats, and obtained speedups of at least 10x concerning CPU-based kernels. Furthermore, we demonstrated via a performance characterization study that FPGAs outperform general-purpose processors in terms of compute time. https://revistas.unab.edu.co/index.php/rcc/article/view/5276HPCGinkgoFPGAsSpMV
spellingShingle Alejandro Morales-Peña
Esteban Meneses
Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
Revista Colombiana de Computación
HPC
Ginkgo
FPGAs
SpMV
title Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
title_full Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
title_fullStr Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
title_full_unstemmed Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
title_short Extending Ginkgo to Manage Reconfigurable Hardware-Based Kernels
title_sort extending ginkgo to manage reconfigurable hardware based kernels
topic HPC
Ginkgo
FPGAs
SpMV
url https://revistas.unab.edu.co/index.php/rcc/article/view/5276
work_keys_str_mv AT alejandromoralespena extendingginkgotomanagereconfigurablehardwarebasedkernels
AT estebanmeneses extendingginkgotomanagereconfigurablehardwarebasedkernels