Machine learning algorithms continue to receive significant attention from industry and research. As the models increase in complexity and accuracy, their computational and memory demands also grow, pushing for more powerful, heterogeneous architectures; custom FPGA/ASIC accelerators are often the best solution to efficiently process large amounts of data close to the sensors in large-scale scientific experiments. Previous works exploited high-level synthesis to help design dedicated compute units for machine learning inference, proposing frameworks that translate high-level models into annotated C/C++. Our proposal, instead, integrates HLS in a compiler-based tool flow with multiple levels of abstraction, enabling analysis, optimization and design space exploration along the whole process. Such an approach will also allow to explore models beyond multi-layer perceptrons and convolutional neural networks (which are often the main target of "classic" HLS frameworks), for example to address the different challenges posed by sparse and graph-based neural networks.

Hardware Acceleration of Complex Machine Learning Models through Modern High-Level Synthesis

Serena Curzel;Antonino Tumeo;Fabrizio Ferrandi
2021-01-01

Abstract

Machine learning algorithms continue to receive significant attention from industry and research. As the models increase in complexity and accuracy, their computational and memory demands also grow, pushing for more powerful, heterogeneous architectures; custom FPGA/ASIC accelerators are often the best solution to efficiently process large amounts of data close to the sensors in large-scale scientific experiments. Previous works exploited high-level synthesis to help design dedicated compute units for machine learning inference, proposing frameworks that translate high-level models into annotated C/C++. Our proposal, instead, integrates HLS in a compiler-based tool flow with multiple levels of abstraction, enabling analysis, optimization and design space exploration along the whole process. Such an approach will also allow to explore models beyond multi-layer perceptrons and convolutional neural networks (which are often the main target of "classic" HLS frameworks), for example to address the different challenges posed by sparse and graph-based neural networks.
2021
File in questo prodotto:
File Dimensione Formato  
rpost131s2-file2.pdf

accesso aperto

Descrizione: Poster
: Publisher’s version
Dimensione 1.62 MB
Formato Adobe PDF
1.62 MB Adobe PDF Visualizza/Apri
rpost131s2-file3.pdf

accesso aperto

Descrizione: Poster summary
: Publisher’s version
Dimensione 456.59 kB
Formato Adobe PDF
456.59 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/11311/1194317
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact