The growing interest in FPGA-based solutions for accelerating compute demanding algorithms is pushing the need for new tools and methods to improve productivity. In this work, we propose a methodology to support designers in generating optimal FPGA hardware implementations using High-Level Synthesis (HLS). First, we propose an automated roofline model generation that operates directly on a C/C++ description of the algorithm. The approach enables fast evaluation of the operational intensity of the target function and visualizes the main bottlenecks of the current HLS implementation, providing guidance on how to improve it. Second, we integrate it with a Design Space Exploration (DSE) methodology for quickly evaluating different HLS directives to identify an optimal implementation.

Automated design space exploration and roofline analysis for FPGA-based hls applications

Siracusa M.;Rabozzi M.;Del Sozzo E.;Santambrogio M. D.;Di Tucci L.
2019-01-01

Abstract

The growing interest in FPGA-based solutions for accelerating compute demanding algorithms is pushing the need for new tools and methods to improve productivity. In this work, we propose a methodology to support designers in generating optimal FPGA hardware implementations using High-Level Synthesis (HLS). First, we propose an automated roofline model generation that operates directly on a C/C++ description of the algorithm. The approach enables fast evaluation of the operational intensity of the target function and visualizes the main bottlenecks of the current HLS implementation, providing guidance on how to improve it. Second, we integrate it with a Design Space Exploration (DSE) methodology for quickly evaluating different HLS directives to identify an optimal implementation.
2019
978-1-7281-1131-5
Design Space Exploration; FPGA; High Level Synthesis; Roofline Model
File in questo prodotto:
File Dimensione Formato  
08735547.pdf

Accesso riservato

: Publisher’s version
Dimensione 87.52 kB
Formato Adobe PDF
87.52 kB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11311/1127891
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 4
social impact