Stefano Crescenza
Exploration of FPGA-Based Ising Machine Architectures.
Rel. Guido Masera, Ana Rusu. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Elettronica (Electronic Engineering), 2026
|
|
PDF (Tesi_di_laurea)
- Tesi
Accesso limitato a: Solo utenti staff fino al 2 Ottobre 2027 (data di embargo). Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (24MB) |
Abstract
The challenge presented by Non-deterministic Polynomial (NP) problems and combinatorial optimization algorithms represents one of the main limitations to modern computation. Conventional computing machines have failed to solve this class of problems in an appropriate amount of time, so other kind of architectures have been explored. Among those, Ising Machines (IMs) stood out for their ability to provide accurate solutions in a short period of time. Different technologies and models have been tested to implement this kind of machine. In this work, the focus will be on a Field Programmable Gate Array (FPGA)-based Oscillator Ising Machine (OIM) implementation. Inspired by a recently developed FPGA-based OIM, this work focuses on further simplifying the algorithm and FPGA implementation, to reduce Time-To-Solution (TTS) and resource consumption, without a significant impact on accuracy.
This approach allows the implementation of a 2000-node OIM on a single FPGA able to solve large Max-Cut problems
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
Ente in cotutela
Aziende collaboratrici
URI
![]() |
Modifica (riservato agli operatori) |
