The aim of the GAP project is the deployment of Graphic Processing Units (GPUs) in real-time applications, ranging from online event selection (trigger) in high energy physics (HEP) experiments to medical imaging reconstruction. The final goal of the project is to demonstrate that GPUs have a positive impact in sectors different for rate, bandwidth, and computational intensity. The relevant aspects under study are the analysis of the latency of the system, the optimisation of the computational algorithms, and the integration with the data acquisition system. As a benchmark application we consider the trigger algorithms of two HEP experiments: NA62 and Atlas, different for event complexity and processing latency requirements. In particular we discuss how specific algorithms can be parallelized and thus benefit from the implementation on the GPU architecture, in terms of increased execution speed and more favourable dependency on the complexity of the analyzed events. Such improvements are particularly relevant for the foreseen LHC luminosity upgrade where highly selective algorithms will be crucial to maintain a sustainable trigger rate with the many multiple pp interactions per bunch crossing. We give details on how these devices are integrated in typical trigger systems and benchmark their performances. GPUs can provide a feasible solution also to accelerate the reconstruction of medical images. We discuss the implementation of new computational intense algorithms boosting the performances of Nuclear Magnetic Resonance and Computed Tomography. The deployment of GPUs can significantly reduce the processing time, making it suitable for the use in realtime diagnostic.

The GAP Project - GPU for Realtime Applications in High Level Trigger and Medical Imaging

DI DOMENICO, Giovanni;FIORINI, Massimiliano;CORVO, Marco;
2014

Abstract

The aim of the GAP project is the deployment of Graphic Processing Units (GPUs) in real-time applications, ranging from online event selection (trigger) in high energy physics (HEP) experiments to medical imaging reconstruction. The final goal of the project is to demonstrate that GPUs have a positive impact in sectors different for rate, bandwidth, and computational intensity. The relevant aspects under study are the analysis of the latency of the system, the optimisation of the computational algorithms, and the integration with the data acquisition system. As a benchmark application we consider the trigger algorithms of two HEP experiments: NA62 and Atlas, different for event complexity and processing latency requirements. In particular we discuss how specific algorithms can be parallelized and thus benefit from the implementation on the GPU architecture, in terms of increased execution speed and more favourable dependency on the complexity of the analyzed events. Such improvements are particularly relevant for the foreseen LHC luminosity upgrade where highly selective algorithms will be crucial to maintain a sustainable trigger rate with the many multiple pp interactions per bunch crossing. We give details on how these devices are integrated in typical trigger systems and benchmark their performances. GPUs can provide a feasible solution also to accelerate the reconstruction of medical images. We discuss the implementation of new computational intense algorithms boosting the performances of Nuclear Magnetic Resonance and Computed Tomography. The deployment of GPUs can significantly reduce the processing time, making it suitable for the use in realtime diagnostic.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in SFERA 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/11392/2145412
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact