Comparative Analysis of Executing GPU Applications on FPGA: HLS vs. Soft GPU Approaches

With the development of the GPU, parallel languages are widely used for developing modern parallel applications. Given its low energy cost and programmable hardware, the FPGA emerges as a promising candidate to run GPU applications. Therefore, executing applications described in GPU programming lang...

Full description

Saved in:
Bibliographic Details
Published in2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) pp. 634 - 641
Main Authors Ahn, Chihyo, Jeong, Shinnung, Cooper, Liam Paul, Parnenzini, Nicholas, Kim, Hyesoon
Format Conference Proceeding
LanguageEnglish
Published IEEE 27.05.2024
Subjects
FPGA
Graphics processing units
Hardware
High level Synthesis
Kernel
OpenCL
Parallel languages
Parallel programming
Pipelines
Soft GPU
User experience
Online AccessGet full text

Cover

More Information
Summary:With the development of the GPU, parallel languages are widely used for developing modern parallel applications. Given its low energy cost and programmable hardware, the FPGA emerges as a promising candidate to run GPU applications. Therefore, executing applications described in GPU programming languages on FPGA can offer new opportunities in terms of performance and energy efficiency. However, the gap between GPU programming languages and hardware description languages (HDL) poses a significant challenge for this transition. To overcome this problem, existing works have attempted to bridge this gap through high-level synthesis (HLS) or soft GPU. In this paper, we examine how HLS and soft GPU compile GPU languages for FPGA by discussing the detailed compilation and execution flow of two representative works: Intel FPGA SDK for OpenCL and Vortex. This paper also evaluates the coverage of both approaches and discusses methods for addressing the challenges each approach faces. Consequently, this paper explores the challenges HLS and GPU encounter, aiming to identify new problems and opportunities each approach introduces.
DOI:10.1109/IPDPSW63119.2024.00123