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...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |