A New Generic HLS Approach for Heterogeneous Computing: On the Feasibility of High-Level Synthesis in HSA-Compatible Systems
Holzinger P, Reichenbach M, Fey D (2018)
Publication Language: English
Publication Type: Conference contribution, Conference Contribution
Publication year: 2018
Publisher: ACM
City/Town: New York, NY, USA
Pages Range: 18-27
Conference Proceedings Title: SAMOS XVIII: 2018 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation
Event location: Pythagorion, Samos Island
ISBN: 978-1-4503-6494-2
URI: https://dl.acm.org/citation.cfm?doid=3229631.3229634
Abstract
Recent advances like deep learning algorithms or virtual reality applications require an amount of computational power in increasingly smaller devices never seen before. Heterogeneous architectures are seen as a solution to this problem, since they provide a significantly better performance per watt. However, their comparatively difficult integration and programming are a major drawback of this solution. The Heterogeneous System Architecture (HSA) Foundation accepted this problem and published a set of specifications to provide a uniform solution for different architectures. This has been successfully applied to GPUs and DSPs, but is insufficiently researched for FPGAs. However, the usage of reconfigurable logic can further increase the efficiency of embedded systems, while the hurdle of integration can be lowered by high-level synthesis (HLS).
Therefore, a combination of the HSA specifications with HLS seems worthwhile to increase the heterogeneity and ease the programmability of FPGAs. This paper provides a suitability analysis of the HSA Intermediate Language (HSAIL) for HLS with suggestions for further improvements to the specification as well as an associated proof of concept. The results show that it is indeed possible to build such a hybrid HLS flow based on the HSA standard, where parts of the process can be shared with other classes of accelerators like GPUs. This implies that progress in the GPU sector like the available source languages can faster carry over to FPGAs and improve the general accessibility.
Authors with CRIS profile
Philipp Holzinger
Lehrstuhl für Informatik 3 (Rechnerarchitektur)
Marc Reichenbach
Lehrstuhl für Informatik 3 (Rechnerarchitektur)
Dietmar Fey
Lehrstuhl für Informatik 3 (Rechnerarchitektur)
How to cite
APA:
Holzinger, P., Reichenbach, M., & Fey, D. (2018). A New Generic HLS Approach for Heterogeneous Computing: On the Feasibility of High-Level Synthesis in HSA-Compatible Systems. In Mudge Trevor, Pnevmatikatos Dionisios N. (Eds.), SAMOS XVIII: 2018 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation (pp. 18-27). Pythagorion, Samos Island, GR: New York, NY, USA: ACM.
MLA:
Holzinger, Philipp, Marc Reichenbach, and Dietmar Fey. "A New Generic HLS Approach for Heterogeneous Computing: On the Feasibility of High-Level Synthesis in HSA-Compatible Systems." Proceedings of the SAMOS XVIII: 2018 International Conference on Embedded Computer Systems: Architectures, Modeling, and Simulation, Pythagorion, Samos Island Ed. Mudge Trevor, Pnevmatikatos Dionisios N., New York, NY, USA: ACM, 2018. 18-27.
BibTeX: Download