Towards a high performance geometry library for particle-detector simulations

16th International workshop on Advanced Computing and Analysis Techniques in physics research

物理学;计算机科学

Apostolakis, J.^1 ; Bandieramonte, M.^2 ; Bitzes, G.^1 ; Brun, R.^1 ; Canal, P.^3 ; Carminati, F.^1 ; Cosmo, G.^1 ; Licht, J. C. De Fine^1 ; Duhem, L.^4 ; Elvira, V.D.^3 ; Gheata, A.^1 ; Jun, S.Y.^3 ; Lima, G.^3 ; Nikitina, T.^1 ; Novak, M.^1 ; Sehgal, R.^5 ; Shadura, O.^6 ; Wenzel, S.^1

European Organization for Nuclear Research (CERN), Geneva, Switzerland^1

University of Catania and INAF (IT), Italy^2

Fermi National Accelerator Laboratory (US)., United States^3

Intel Corporation, United States^4

Bhabha Atomic Research Center (IN)., India^5

National Technical University of Ukraine, Kyiv Politechnic Institute, Ukraine^6

关键词: Computing hardware;    Detector simulations;    Different architectures;    Simulation projects;    Simulation software;    Single instruction multiple data;    Software component;    Software development approach;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/608/1/012023/pdf
DOI  :  10.1088/1742-6596/608/1/012023

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Thread-parallelisation and single-instruction multiple data (SIMD) "vectorisation" of software components in HEP computing has become a necessity to fully benefit from current and future computing hardware. In this context, the Geant-Vector/GPU simulation project aims to re-engineer current software for the simulation of the passage of particles through detectors in order to increase the overall event throughput. As one of the core modules in this area, the geometry library plays a central role and vectorising its algorithms will be one of the cornerstones towards achieving good CPU performance. Here, we report on the progress made in vectorising the shape primitives, as well as in applying new C++ template based optimisations of existing code available in the Geant4, ROOT or USolids geometry libraries. We will focus on a presentation of our software development approach that aims to provide optimised code for all use cases of the library (e.g., single particle and many-particle APIs) and to support different architectures (CPU and GPU) while keeping the code base small, manageable and maintainable. We report on a generic and templated C++ geometry library as a continuation of the AIDA USolids project. The experience gained with these developments will be beneficial to other parts of the simulation software, such as for the optimisation of the physics library, and possibly to other parts of the experiment software stack, such as reconstruction and analysis.