We present the parallel implementation on Graphics Processing Units (GPUs) of a type-3 Non-Uniform FFT (NUFFT) approach, namely, of a NUFFT for which data and results are located at irregular points. The performance of the algorithm is assessed against that of a parallel implementation of the same algorithm on multi-core CPUs using OpenMP directives.

The 2D type-3 non-uniform FFT in CUDA

Amedeo Capozzoli;Claudio Curcio;Angelo Liseno;
2018

Abstract

We present the parallel implementation on Graphics Processing Units (GPUs) of a type-3 Non-Uniform FFT (NUFFT) approach, namely, of a NUFFT for which data and results are located at irregular points. The performance of the algorithm is assessed against that of a parallel implementation of the same algorithm on multi-core CPUs using OpenMP directives.
File in questo prodotto:
File Dimensione Formato  
ACES_Journal_August_2018_Paper_16.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Dominio pubblico
Dimensione 1.87 MB
Formato Adobe PDF
1.87 MB 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/11588/723648
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 3
social impact