Radiation-Hardened-By-Design (RHBD) FPGAs have gained a lot of attention thanks to their excellent compromise between costs and performance. Being of very limited use due to a lack of performance a few years ago, these devices are now capable of implementing a wide range of applications requiring high computational capabilities. This work describes an implementation of a Very Long Instruction Word (VLIW) soft-core convolutional accelerator in the NanoXplore RHBD NG-Medium chip. Feasibility and timing performances have been analyzed in order to discover whether and how multi-core solutions can affect parallel acceleration. Placement also showed to heavily affect the delays, up to 70% more, based on the proximity to the output buffers.

Design Techniques for Multi-Core Neural Network Accelerators on Radiation-Hardened FPGAs / Portaluri, Andrea; Azimi, Sarah; Sterpone, Luca. - ELETTRONICO. - (2023), pp. 16-22. (Intervento presentato al convegno IEEE International Symposium on Parallel and Distributed Computing tenutosi a Bucharest (Romania) nel 10-12 July 2023) [10.1109/ISPDC59212.2023.00023].

Design Techniques for Multi-Core Neural Network Accelerators on Radiation-Hardened FPGAs

Andrea Portaluri;Sarah Azimi;Luca Sterpone
2023

Abstract

Radiation-Hardened-By-Design (RHBD) FPGAs have gained a lot of attention thanks to their excellent compromise between costs and performance. Being of very limited use due to a lack of performance a few years ago, these devices are now capable of implementing a wide range of applications requiring high computational capabilities. This work describes an implementation of a Very Long Instruction Word (VLIW) soft-core convolutional accelerator in the NanoXplore RHBD NG-Medium chip. Feasibility and timing performances have been analyzed in order to discover whether and how multi-core solutions can affect parallel acceleration. Placement also showed to heavily affect the delays, up to 70% more, based on the proximity to the output buffers.
2023
979-8-3503-4127-0
File in questo prodotto:
File Dimensione Formato  
ISPDC23_camera_ready.pdf

accesso aperto

Descrizione: ISPDC 2023 - Camera Ready
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 583.61 kB
Formato Adobe PDF
583.61 kB Adobe PDF Visualizza/Apri
Design_Techniques_for_Multi-Core_Neural_Network_Accelerators_on_Radiation-Hardened_FPGAs.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 2.04 MB
Formato Adobe PDF
2.04 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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/11583/2979316