CERN Accélérateur de science

Published Articles
Report number	FERMILAB-CONF-17-045-CD
Title	Performance of GeantV EM Physics Models
Author(s)	Amadio, G (Sao Paulo State U.) ; Ananya, A (CERN) ; Apostolakis, J (CERN) ; Aurora, A (CERN) ; Bandieramonte, M (CERN) ; Bhattacharyya, A (Bhabha Atomic Res. Ctr.) ; Bianchini, C (Sao Paulo State U. ; Mackenzie Presbiteriana U.) ; Brun, R (CERN) ; Canal P (Fermilab) ; Carminati, F (CERN) ; Cosmo, G (CERN) ; Duhem, L (Intel, Santa Clara) ; Elvira, D (Fermilab) ; Folger, G (CERN) ; Gheata, A (CERN) ; Gheata, M (CERN ; Bucharest, Inst. Space Science) ; Goulas, I (CERN) ; Iope, R (Sao Paulo State U.) ; Jun, S Y (Fermilab) ; Lima, G (Fermilab) ; Mohanty, A (Bhabha Atomic Res. Ctr.) ; Nikitina, T (CERN) ; Novak, M (CERN) ; Pokorski, W (CERN) ; Ribon, A (CERN) ; Seghal, R (Bhabha Atomic Res. Ctr.) ; Shadura, O (CERN) ; Vallecorsa, S (CERN) ; Wenzel, S (CERN) ; Zhang, Y (CERN)
Publication	2017
Number of pages	8
In:	J. Phys.: Conf. Ser. 898 (2017) 072017
In:	22nd International Conference on Computing in High Energy and Nuclear Physics, CHEP 2016, San Francisco, Usa, 10 - 14 Oct 2016, pp.072017
DOI	10.1088/1742-6596/898/7/072017
Subject category	Computing and Computers ; Particle Physics - Phenomenology ; Computing and Computers
Abstract	The recent progress in parallel hardware architectures with deeper vector pipelines or many-cores technologies brings opportunities for HEP experiments to take advantage of SIMD and SIMT computing models. Launched in 2013, the GeantV project studies performance gains in propagating multiple particles in parallel, improving instruction throughput and data locality in HEP event simulation on modern parallel hardware architecture. Due to the complexity of geometry description and physics algorithms of a typical HEP application, performance analysis is indispensable in identifying factors limiting parallel execution. In this report, we will present design considerations and preliminary computing performance of GeantV physics models on coprocessors (Intel Xeon Phi and NVidia GPUs) as well as on mainstream CPUs.
Copyright/License	publication: (License: CC-BY-3.0)

Corresponding record in: Inspire