polito.it
Politecnico di Torino (logo)

Preliminary integration of a neuromorphic coprocessor in the Risc-V Pulp platform

Jonathan Damone

Preliminary integration of a neuromorphic coprocessor in the Risc-V Pulp platform.

Rel. Gianvito Urgese. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering), 2023

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (4MB) | Preview
Abstract:

The purpose of this thesis is to provide a clear understanding of how to construct the proposed SOC, which is a platform with a traditional processor and a neuromorphic coprocessor. For this reason, I analyzed the state-of-the-art of all PULP platforms and the most innovative neuromorphic processors. After identifying the best candidates that meet high standards of power and flexibility, I selected the final configuration, which is PULPissimo and Reckon with interconnection through the uDMA module. Subsequently, I performed an initial test of launching data from memory serially to Reckon and verified the sending through uDMA using the PULP toolchain. The results provided a clear reference on how to simulate the various modules through QuestaSim and a precise guide on how to operate with the PULP platform.

Relatori: Gianvito Urgese
Anno accademico: 2022/23
Tipo di pubblicazione: Elettronica
Numero di pagine: 94
Soggetti:
Corso di laurea: Corso di laurea magistrale in Ingegneria Informatica (Computer Engineering)
Classe di laurea: Nuovo ordinamento > Laurea magistrale > LM-32 - INGEGNERIA INFORMATICA
Aziende collaboratrici: Politecnico di Torino
URI: http://webthesis.biblio.polito.it/id/eprint/26763
Modifica (riservato agli operatori) Modifica (riservato agli operatori)