CERN Accelerating science

Published Articles
Title	Recent progress with the top to bottom approach to vectorization in GeantV
Author(s)	Amadio, Guilherme (CERN) ; Ananya ; Apostolakis, John (CERN) ; Bandieramonte, Marilena (CERN ; U. Pittsburgh (main)) ; Behera, Shiba (Bhabha Atomic Res. Ctr.) ; Bhattacharyya, Abhijit (Bhabha Atomic Res. Ctr.) ; Brun, René (CERN) ; Canal, Philippe (Fermilab) ; Carminati, Federico (CERN) ; Cosmo, Gabriele (CERN) ; Drohan, Vitaliy ; Elvira, Daniel (Fermilab) ; Genser, Krzysztof (Fermilab) ; Gheata, Andrei (CERN) ; Gheata, Mihaela (CERN ; Bucharest, Inst. Space Science) ; Goulas, Ilias (CERN) ; Hariri, Farah (CERN) ; Ivanchenko, Vladimir (CERN ; Tomsk State U.) ; Karpinski, Przemislaw ; Khattak, Gulrukh (CERN) ; Konstantinov, Dmitri (CERN ; Serpukhov, IHEP) ; Kumawat, Harphool (Bhabha Atomic Res. Ctr.) ; Lima, Guilherme (Fermilab) ; Martínez Castro, Jesús (CIC, IPN) ; Mendez, Patricia (CERN) ; Miranda Aguillar, Aldo (CIC, IPN) ; Nikolics, Katalin (CERN) ; Novak, Mihaly (CERN) ; Orlova, Elena ; Pedro, Kevin (Fermilab) ; Pokorski, Witold (CERN) ; Ribon, Alberto (CERN) ; Savin, Dmitry ; Schmitz, Ryan ; Sehgal, Raman (Bhabha Atomic Res. Ctr.) ; Shadura, Oksana (CERN) ; Sharan, Shruti ; Vallecorsa, Sofia (CERN) ; Wenzel, Sandro (CERN) ; Jun, Soon Yung (Fermilab)
Publication	2019
Number of pages	8
In:	EPJ Web Conf. 214 (2019) 02007
In:	23rd International Conference on Computing in High Energy and Nuclear Physics, CHEP 2018, Sofia, Bulgaria, 9 - 13 Jul 2018, pp.02007
DOI	10.1051/epjconf/201921402007
Subject category	Computing and Computers
Abstract	SIMD acceleration can potentially boost by factors the application throughput. Achieving efficient SIMD vectorization for scalar code with complex data flow and branching logic, goes however way beyond breaking some loop dependencies and relying on the compiler. Since the refactoring effort scales with the number of lines of code, it is important to understand what kind of performance gains can be expected in such complex cases. We started to investigate a couple of years ago a top to bottom vectorization approach to particle transport simulation. Percolating vector data to algorithms was mandatory since not all the components can internally vectorize. Vectorizing low-level algorithms is certainly necessary, but not sufficient to achieve relevant SIMD gains. In addition, the overheads for maintaining the concurrent vector data flow and copy data have to be minimized. In the context of a vectorization R&D; for simulation we developed a framework to allow different categories of scalar and vectorized components to co-exist, dealing with data flow management and real-time heuristic optimizations. The paper describes our approach on coordinating SIMD vectorization at framework level, making a detailed quantitative analysis of the SIMD gain versus overheads, with a breakdown by components in terms of geometry, physics and magnetic field propagation. We also present the more general context of this R&D; work and goals for 2018.
Copyright/License	publication: © 2019-2024 The Authors (License: CC-BY-4.0)

Corresponding record in: Inspire