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

Research output: Contribution to book/Conference proceedings/Anthology/ReportConference contributionContributedpeer-review

Contributors

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

Original languageEnglish
Title of host publication2021 IEEE International Conference on Cluster Computing (CLUSTER)
PublisherIEEE Xplore
Pages759-766
Number of pages8
ISBN (electronic)978-1-7281-9666-4
ISBN (print)978-1-7281-9667-1
Publication statusPublished - 2021
Peer-reviewedYes

Publication series

SeriesIEEE International Conference on Cluster Computing
ISSN1552-5244

Conference

Title2021 IEEE International Conference on Cluster Computing
Abbreviated titleCLUSTER 2021
Duration7 - 10 September 2021
Website
Degree of recognitionInternational event
Locationonline
CityPortland
CountryUnited States of America

External IDs

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

Keywords

Research priority areas of TU Dresden

Keywords

  • CFD, DSL, FPGA, HLS

Library keywords