Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application

With the growing popularity of FPGA-based accelerators in HPC applications, new challenges have emerged, particularly in terms of programming and portability. This paper provides an overview of the current state of FPGA tools and their limitations. This study evaluates the performance and portabilit...

Full description

Saved in:
Bibliographic Details
Main Authors: Manuel De Castro, Roberto R. Osorio, Francisco J. Andujar, Rocio Carratala-Saez, Yuri Torres, Diego R. Llanos
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10926827/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067313116577792
author Manuel De Castro
Roberto R. Osorio
Francisco J. Andujar
Rocio Carratala-Saez
Yuri Torres
Diego R. Llanos
author_facet Manuel De Castro
Roberto R. Osorio
Francisco J. Andujar
Rocio Carratala-Saez
Yuri Torres
Diego R. Llanos
author_sort Manuel De Castro
collection DOAJ
description With the growing popularity of FPGA-based accelerators in HPC applications, new challenges have emerged, particularly in terms of programming and portability. This paper provides an overview of the current state of FPGA tools and their limitations. This study evaluates the performance and portability of two frameworks, SYCL and OpenCL, for developing HPC FPGA solutions. The case of porting a highly-parallel application to FPGAs is studied. First, naïve, low-development-effort implementations are presented using both ND-range and single-task types of kernels, and their performance is evaluated. Subsequently, an optimized FPGA-centric approach is presented and assessed using metrics from the compilation framework. Finally, the different approaches presented are implemented using OpenCL and SYCL and their performance is evaluated. Results reveal that ND-range kernels offer high portability for highly parallel applications, while single-task codes exhibit significantly lower portability. Additionally, SYCL struggles to generate efficient hardware architectures for this kind of application when described as single-task codes, although its performance when following the ND-range approach is surprisingly high.
format Article
id doaj-art-140b98ea81304cbca3ec2d5bdbaf74a2
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-140b98ea81304cbca3ec2d5bdbaf74a22025-08-20T02:48:22ZengIEEEIEEE Access2169-35362025-01-0113503945041010.1109/ACCESS.2025.355142810926827Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel ApplicationManuel De Castro0https://orcid.org/0000-0003-3080-5136Roberto R. Osorio1https://orcid.org/0000-0001-8768-2240Francisco J. Andujar2Rocio Carratala-Saez3https://orcid.org/0000-0001-8409-2421Yuri Torres4https://orcid.org/0000-0002-3037-3567Diego R. Llanos5https://orcid.org/0000-0001-6240-9109Department of Computer Science, Universidad de Valladolid, Campus Miguel Delibes, Valladolid, SpainComputer Architecture Group, CITIC, Universidade da Coruña, Campus de Elviña s/n, A Coruña, SpainDepartment of Computer Science, Universidad de Valladolid, Campus Miguel Delibes, Valladolid, SpainDpto. Informática, Universitat de València, Valencia, SpainDepartment of Computer Science, Universidad de Valladolid, Campus Miguel Delibes, Valladolid, SpainDepartment of Computer Science, Universidad de Valladolid, Campus Miguel Delibes, Valladolid, SpainWith the growing popularity of FPGA-based accelerators in HPC applications, new challenges have emerged, particularly in terms of programming and portability. This paper provides an overview of the current state of FPGA tools and their limitations. This study evaluates the performance and portability of two frameworks, SYCL and OpenCL, for developing HPC FPGA solutions. The case of porting a highly-parallel application to FPGAs is studied. First, naïve, low-development-effort implementations are presented using both ND-range and single-task types of kernels, and their performance is evaluated. Subsequently, an optimized FPGA-centric approach is presented and assessed using metrics from the compilation framework. Finally, the different approaches presented are implemented using OpenCL and SYCL and their performance is evaluated. Results reveal that ND-range kernels offer high portability for highly parallel applications, while single-task codes exhibit significantly lower portability. Additionally, SYCL struggles to generate efficient hardware architectures for this kind of application when described as single-task codes, although its performance when following the ND-range approach is surprisingly high.https://ieeexplore.ieee.org/document/10926827/Data parallelismFPGAHLSOpenCLportabilitySYCL
spellingShingle Manuel De Castro
Roberto R. Osorio
Francisco J. Andujar
Rocio Carratala-Saez
Yuri Torres
Diego R. Llanos
Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
IEEE Access
Data parallelism
FPGA
HLS
OpenCL
portability
SYCL
title Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
title_full Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
title_fullStr Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
title_full_unstemmed Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
title_short Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
title_sort comparing portability of fpga high level synthesis frameworks in the context of a highly parallel application
topic Data parallelism
FPGA
HLS
OpenCL
portability
SYCL
url https://ieeexplore.ieee.org/document/10926827/
work_keys_str_mv AT manueldecastro comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication
AT robertorosorio comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication
AT franciscojandujar comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication
AT rociocarratalasaez comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication
AT yuritorres comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication
AT diegorllanos comparingportabilityoffpgahighlevelsynthesisframeworksinthecontextofahighlyparallelapplication