A Survey on FPGA-Based Heterogeneous Clusters Architectures

In recent years, the most powerful supercomputers have already reached megawatt power consumption levels, an important issue that challenges sustainability and shows the impossibility of maintaining this trend. To this date, the prevalent approach to supercomputing is dominated by CPUs and GPUs. Giv...

Full description

Saved in:
Bibliographic Details
Main Authors: Werner Florian Samayoa, Maria Liz Crespo, Andres Cicuttin, Sergio Carrato
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10158531/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128586389454848
author Werner Florian Samayoa
Maria Liz Crespo
Andres Cicuttin
Sergio Carrato
author_facet Werner Florian Samayoa
Maria Liz Crespo
Andres Cicuttin
Sergio Carrato
author_sort Werner Florian Samayoa
collection DOAJ
description In recent years, the most powerful supercomputers have already reached megawatt power consumption levels, an important issue that challenges sustainability and shows the impossibility of maintaining this trend. To this date, the prevalent approach to supercomputing is dominated by CPUs and GPUs. Given their fixed architectures with generic instruction sets, they have been favored with lots of tools and mature workflows which led to mass adoption and further growth. However, reconfigurable hardware such as FPGAs has repeatedly proven that it offers substantial advantages over this supercomputing approach concerning performance and power consumption. In this survey, we review the most relevant works that advanced the field of heterogeneous supercomputing using FPGAs focusing on their architectural characteristics. Each work was divided into three main parts: network, hardware, and software tools. All implementations face challenges that involve all three parts. These dependencies result in compromises that designers must take into account. The advantages and limitations of each approach are discussed and compared in detail. The classification and study of the architectures illustrate the trade-offs of the solutions and help identify open problems and research lines.
format Article
id doaj-art-0acc050fd85a4163925c8709c60a4c52
institution Kabale University
issn 2169-3536
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-0acc050fd85a4163925c8709c60a4c522024-12-11T00:01:26ZengIEEEIEEE Access2169-35362023-01-0111676796770610.1109/ACCESS.2023.328843110158531A Survey on FPGA-Based Heterogeneous Clusters ArchitecturesWerner Florian Samayoa0https://orcid.org/0000-0002-2951-3059Maria Liz Crespo1https://orcid.org/0000-0002-5483-3388Andres Cicuttin2https://orcid.org/0000-0002-3645-9791Sergio Carrato3https://orcid.org/0000-0003-2953-8886Multidisciplinary Laboratory (MLab), The Abdus Salam International Centre for Theoretical Physics, Trieste, ItalyMultidisciplinary Laboratory (MLab), The Abdus Salam International Centre for Theoretical Physics, Trieste, ItalyMultidisciplinary Laboratory (MLab), The Abdus Salam International Centre for Theoretical Physics, Trieste, ItalyDipartimento di Ingegneria e Architettura (DIA), Universitã degli Studi di Trieste, Trieste, ItalyIn recent years, the most powerful supercomputers have already reached megawatt power consumption levels, an important issue that challenges sustainability and shows the impossibility of maintaining this trend. To this date, the prevalent approach to supercomputing is dominated by CPUs and GPUs. Given their fixed architectures with generic instruction sets, they have been favored with lots of tools and mature workflows which led to mass adoption and further growth. However, reconfigurable hardware such as FPGAs has repeatedly proven that it offers substantial advantages over this supercomputing approach concerning performance and power consumption. In this survey, we review the most relevant works that advanced the field of heterogeneous supercomputing using FPGAs focusing on their architectural characteristics. Each work was divided into three main parts: network, hardware, and software tools. All implementations face challenges that involve all three parts. These dependencies result in compromises that designers must take into account. The advantages and limitations of each approach are discussed and compared in detail. The classification and study of the architectures illustrate the trade-offs of the solutions and help identify open problems and research lines.https://ieeexplore.ieee.org/document/10158531/FPGASoCheterogeneous computingsupercomputingreconfigurable computing
spellingShingle Werner Florian Samayoa
Maria Liz Crespo
Andres Cicuttin
Sergio Carrato
A Survey on FPGA-Based Heterogeneous Clusters Architectures
IEEE Access
FPGA
SoC
heterogeneous computing
supercomputing
reconfigurable computing
title A Survey on FPGA-Based Heterogeneous Clusters Architectures
title_full A Survey on FPGA-Based Heterogeneous Clusters Architectures
title_fullStr A Survey on FPGA-Based Heterogeneous Clusters Architectures
title_full_unstemmed A Survey on FPGA-Based Heterogeneous Clusters Architectures
title_short A Survey on FPGA-Based Heterogeneous Clusters Architectures
title_sort survey on fpga based heterogeneous clusters architectures
topic FPGA
SoC
heterogeneous computing
supercomputing
reconfigurable computing
url https://ieeexplore.ieee.org/document/10158531/
work_keys_str_mv AT wernerfloriansamayoa asurveyonfpgabasedheterogeneousclustersarchitectures
AT marializcrespo asurveyonfpgabasedheterogeneousclustersarchitectures
AT andrescicuttin asurveyonfpgabasedheterogeneousclustersarchitectures
AT sergiocarrato asurveyonfpgabasedheterogeneousclustersarchitectures
AT wernerfloriansamayoa surveyonfpgabasedheterogeneousclustersarchitectures
AT marializcrespo surveyonfpgabasedheterogeneousclustersarchitectures
AT andrescicuttin surveyonfpgabasedheterogeneousclustersarchitectures
AT sergiocarrato surveyonfpgabasedheterogeneousclustersarchitectures