From Domain-Specific Languages to Memory-Optimized Accelerators for Fluid Dynamics

Publikation: Beitrag in Buch/Konferenzbericht/Sammelband/GutachtenBeitrag in KonferenzbandBeigetragenBegutachtung

Beitragende

Abstract

Many applications are increasingly requiring numerical simulations for solving complex problems. Most of these numerical algorithms are massively parallel and often implemented on parallel high-performance computers. However, classic CPUbased platforms suffers due to the demand of higher resolutions and the exponential growth of data. FPGAs offer a powerful and flexible alternative that can host accelerators to complement such platforms. Developing such application-specific accelerators is still challenging because it is hard to provide efficient code for hardware synthesis. In this paper, we study the challenges for porting a numerical simulation kernels onto FPGA. We propose an automated tool flow from a domain-specific language (DSL) to generate accelerators for computational fluid dynamics on FPGA. Our DSL-based flow simplifies the exploration of parameters and constraints such as on-chip memory usage. We also propose a decoupled optimization of memory and logic resources, which allows us to better use the limited FPGA resources. In our preliminary evaluation, this enabled doubling the amount of parallel kernels, increasing the accelerator speedup versus ARM execution from 7 to 12 times.

Details

OriginalspracheEnglisch
Titel2021 IEEE International Conference on Cluster Computing (CLUSTER)
Herausgeber (Verlag)IEEE Xplore
Seiten759-766
Seitenumfang8
ISBN (elektronisch)978-1-7281-9666-4
ISBN (Print)978-1-7281-9667-1
PublikationsstatusVeröffentlicht - 2021
Peer-Review-StatusJa

Publikationsreihe

ReiheIEEE International Conference on Cluster Computing
ISSN1552-5244

Konferenz

Titel2021 IEEE International Conference on Cluster Computing
KurztitelCLUSTER 2021
Dauer7 - 10 September 2021
Webseite
BekanntheitsgradInternationale Veranstaltung
Ortonline
StadtPortland
LandUSA/Vereinigte Staaten

Externe IDs

ORCID /0000-0002-5007-445X/work/141545620

Schlagworte

Forschungsprofillinien der TU Dresden

Schlagwörter

  • CFD, DSL, FPGA, HLS

Bibliotheksschlagworte