ixed precision is an approximate computing technique that can be used to trade-off computation accuracy for performance and/or energy. It can be applied to many error-tolerant applications, but manual precision tuning is both tedious and error-prone. Furthermore, the effectiveness of the technique heavily depends on hardware characteristics. Therefore, a hardware/software co-design approach is necessary for an effective exploitation of precision tuning opportunities offered by the applications. In this paper, we propose, based on the state of the art of precision tuning software and mixed precision hardware, a roadmap for the evolution of hardware designs and compiler-based precision tuning support, which is ongoing in the context of the European projects TEXTAROSSA and APROPOS

Hardware and Software Support for Mixed Precision Computing: A Roadmap for Embedded and HPC Systems

Fornaciari W.;Agosta G.;Cattaneo D.;Denisov L.;Galimberti A.;Magnani G.;Zoni D.
2023-01-01

Abstract

ixed precision is an approximate computing technique that can be used to trade-off computation accuracy for performance and/or energy. It can be applied to many error-tolerant applications, but manual precision tuning is both tedious and error-prone. Furthermore, the effectiveness of the technique heavily depends on hardware characteristics. Therefore, a hardware/software co-design approach is necessary for an effective exploitation of precision tuning opportunities offered by the applications. In this paper, we propose, based on the state of the art of precision tuning software and mixed precision hardware, a roadmap for the evolution of hardware designs and compiler-based precision tuning support, which is ongoing in the context of the European projects TEXTAROSSA and APROPOS
2023
Proceedings of 2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)
Embedded systems , Approximate computing , Hardware , Software , Precision Tuning
File in questo prodotto:
File Dimensione Formato  
2023_TEXTAROSSA_APROPOS_DATE.pdf

accesso aperto

: Pre-Print (o Pre-Refereeing)
Dimensione 502.88 kB
Formato Adobe PDF
502.88 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/11311/1248561
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact