The GAP project: GPU applications for High Level Trigger and Medical Imaging

The aim of the GAP project is the deployment of Graphic Processing Units in real-time applications, ranging from the online event selection (trigger) in High-Energy Physics to medical imaging reconstruction. The final goal of the project is to demonstrate that GPUs can have a positive impact in sectors different for rate, bandwidth, and computational intensity. Most crucial aspects currently under study are the analysis of the total latency of the system, the algorithms optimisations, and the integration with the data acquisition systems. In this paper we focus on the application of GPUs in asynchronous trigger systems, employed for the high level trigger of LHC experiments. The benefit obtained from the GPU deployement is particularly relevant for the foreseen LHC luminosity upgrade where highly selective algorithms will be crucial to maintain a sustainable trigger rates with very high pileup. As a study case, we will consider the ATLAS experimental environment and propose a GPU implementation for a typical muon selection in a high-level trigger system.

[1]  F. Englert,et al.  Broken Symmetry and the Mass of Gauge Vector Mesons , 1964 .

[2]  Davide Rossetti,et al.  APEnet+ 34 Gbps data transmission system and custom transmission logic , 2013 .

[3]  Davide Rossetti,et al.  APEnet+: a 3D Torus network optimized for GPU-based HPC Systems , 2012 .

[4]  M. Fiorini,et al.  The NA62 experiment at CERN. , 2012 .

[5]  Yijie Han,et al.  Concurrent threads and optimal parallel minimum spanning trees algorithm , 2001, JACM.

[6]  G. Lepage,et al.  VEGAS - an adaptive multi-dimensional integration program , 1980 .

[7]  G. Guralnik,et al.  Global Conservation Laws and Massless Particles , 1964 .

[8]  Pier Stanislao Paolucci,et al.  NaNet: a flexible and configurable low-latency NIC for real-time trigger systems based on GPUs , 2013, ArXiv.

[9]  Lars Sonnenschein.  Algebraic approach to solve tt dilepton equations , 2005 .

[10]  John E. Stone,et al.  OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems , 2010, Computing in Science & Engineering.

[11]  P. W. Higgs.  Broken Symmetries and the Masses of Gauge Bosons , 1964 .

[12]  A. Margiotta,et al.  Status of the KM3NeT project , 2014, 1408.1132.

[13]  Henry D. Shapiro,et al.  An Empirical Assessment of Algorithms for Constructing a Minimum Spanning Tree , 1992, Computational Support for Discrete Mathematics.

[14]  Vincenzo Izzo,et al.  The NEMO experiment data acquisition and timing distribution systems , 2011, 2011 IEEE Nuclear Science Symposium Conference Record.

[15]  Davide Rossetti,et al.  NaNet:a low-latency NIC enabling GPU-based, real-time low level trigger systems , 2014 .

[16]  C. Grojean,et al.  Probing top-Higgs non-standard interactions at the LHC , 2012, 1205.1065.

[17]  G. Lepage.  A new algorithm for adaptive multidimensional integration , 1978 .

[18]  William Link,et al.  ALOHA: Automatic libraries of helicity amplitudes for Feynman diagram computations , 2011, Comput. Phys. Commun..

[19]  Hitoshi Murayama,et al.  HELAS: HELicity amplitude subroutines for Feynman diagram evaluations , 1992 .

[20]  Kevin Skadron,et al.  Scalable parallel programming , 2008, 2008 IEEE Hot Chips 20 Symposium (HCS).

[21]  Dimitri Bourilkov,et al.  The Les Houches accord PDFs (LHAPDF) and LHAGLUE , 2005, hep-ph/0508110.

[22]  Uzi Vishkin,et al.  An O(log n) Parallel Connectivity Algorithm , 1982, J. Algorithms.

[23]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[24]  Volker Lindenstruth,et al.  Vc: A C++ library for explicit vectorization , 2012, Softw. Pract. Exp..

[25]  Nicolas Pinto,et al.  PyCUDA and PyOpenCL: A scripting-based approach to GPU run-time code generation , 2009, Parallel Comput..

[26]  F. Spinella,et al.  The FPGA based Trigger and Data Acquisition system for the CERN NA62 experiment , 2014 .