Comparing Portability of FPGA High-Level Synthesis Frameworks in the Context of a Highly-Parallel Application
Open Access
- 14 March 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 50394-50410
Abstract
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.Keywords
Funding Information
- Consejer?a de Educaci?n, Junta de Castilla y Le?n (VA226P20)
- Ministerio de Ciencia e Innovación (PID2022-136435NB-I00, PID2022-142292NB-I00, TED2021?130367B?I00)
This publication has 41 references indexed in Scilit:
- Design Optimization for High-Performance Computing Using FPGA2024
- Developing performance portable plasma edge simulations: A surveyComputer Physics Communications, 2024
- UVaFTLE: Lagrangian finite time Lyapunov exponent extraction for fluid dynamic applicationsThe Journal of Supercomputing, 2023
- Flow topology and targeted drug delivery in cardiovascular diseaseJournal of Biomechanics, 2021
- FPGA-Based Computational Fluid Dynamics Simulation Architecture via High-Level Synthesis Design Method2020
- Productivity, performance, and portability for computational fluid dynamics applicationsComputers & Fluids, 2020
- Implications of a metric for performance portabilityFuture Generation Computer Systems, 2019
- Highly efficient computation of Finite-Time Lyapunov Exponents (FTLE) on GPUs based on three-dimensional SPH datasetsComputers & Fluids, 2018
- Time-Dependent Visualization of Lagrangian Coherent Structures by Grid Advection2010
- Visualization of Coherent Structures in Transient 2D Flows2009