HENNEQUIN Arthur
Supervision : Lionel LACASSAGNE
Co-supervision : Vladimir GLIGOROV (LPNHE) Benjamen COUTURIER (CERN)
Performance optimisation for the LHCb experiment
The LHCb experiment, at CERN, is preparing a major upgrade of its detector and a change from an hardware-based to a fully software-based trigger system. It is now facing the challenge of being able to process incoming events at a rate of 30 million events per second. To cope with this massive data input, the software must be optimized to use the processing power of the filtering farm more efficiently. This thesis focus on the first algorithm of LHCb's High Level Trigger software: the Vertex Locator (VELO) reconstruction algorithm. The VELO is the first detector encountered by particles, directly surrounding the interaction region. Its goal is to find the initial track candidate that are then followed through the other layers of the LHCb detector with a good enough resolution that they could also be used to locate the location of the collisions. The first step of this algorithm is to prepare the data by grouping pixels of the silicon sensors into hits; this process is called connected component analysis (CCA). This thesis presents multiple new CCA algorithms for both CPU and GPU architectures. The first algorithm, HA4, was developed at the very start of this thesis and improved the state-of-the-art in connected component labeling on GPUs, as well as being the first efficient implementation of connected component analysis on GPUs. The second algorithm is a GPU port of the FLSL SIMD CPU algorithm, inspired by the LSL algorithm. FLSL on GPUs improved upon HA4 by reducing the memory accesses conflicts that are especially presents on new hardware with a lot of cores. Along with FLSL, two other optimisations aimed at further reducing conflicts are presented and evaluated. On CPU, two new algorithms were made for this thesis. The first one is a modification of the classic Rosenfeld algorithm to use SIMD. The second one is a new algorithm, named SparseCCL, which takes advantage of the sparsity of the input images. A new VELO reconstruction algorithm using SIMD is presented, that enable LHCb to process events in real time and improve the quality of the reconstruction. The SIMDWrapper library, developed for the new VELO algorithm, is now part of LHCb's software and is used in other algorithms.
Defence : 01/31/2022
Jury members :
François Irigoin (CRI, Mines ParisTech) [Rapporteur]
Denis Barthou (INRIA Bordeaux) [Rapporteur]
Lionel Lacassagne (LIP6, Sorbonne Université)
Stef Graillat (LIP6, Sorbonne Université)
Caroline Collange (INRIA Rennes)
Vladimir Gligorov (LPNHE, Sorbonne Université)
2018-2022 Publications
-
2022
- A. Hennequin : “Optimisation de performance pour l’expĂ©rience LHCb ”, thesis, phd defence 01/31/2022, supervision Lacassagne, Lionel, co-supervision : Vladimir, GLIGOROV (LPNHE) Benjamen COUTURIER (CERN) (2022)
-
2021
- F. Lemaitre, A. Hennequin, L. Lacassagne : “Taming Voting Algorithms on Gpus for an Efficient Connected Component Analysis Algorithm”, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, pp. 7903-7907, (IEEE) (2021)
- F. Lemaitre, A. Hennequin, L. Lacassagne : “Taming Voting Algorithms on GPUs for an Efficient Connected Component Analysis Algorithm”, GPU Technical Conference, San Jose, United States (2021)
- R. Aaij, D. Cámpora PĂ©rez, T. Colombo, C. Fitzpatrick, V. Gligorov, A. Hennequin, N. Neufeld, N. Nolte, R. Schwemmer, D. Vom Bruch : “Evolution of the energy efficiency of LHCb’s real-time processing”, EPJ Web Conf., vol. 251, Online, France, pp. 04009 (2021)
-
2020
- F. Lemaitre, A. Hennequin, L. Lacassagne : “How to speed Connected Component Labeling up with SIMD RLE algorithms”, Workshop on Programming Models for SIMD/Vector Processing (WPMVP@PPoPP), San Diego, Californie, United States (2020)
- A. Hennequin, B. Couturier, V. Gligorov, S. Ponce, R. Quagliani, L. Lacassagne : “A fast and efficient SIMD track reconstruction algorithm for the LHCb Upgrade 1 VELO-PIX detector”, Journal of Instrumentation, vol. 15 (06), pp. p06018, (IOP Publishing) (2020)
-
2019
- A. Hennequin, L. Lacassagne, I. Masliah : “Étiquetage et analyse en composantes connexes sur GPUs”, COMPAS, Anglet, France (2019)
- A. Hennequin, L. Lacassagne : “A new Direct Connected Component Labeling and Analysis Algorithm for GPUs”, GPU Technology Conference (GTC), San Jose, United States (2019)
- A. Hennequin, I. Masliah, L. Lacassagne : “Designing efficient SIMD algorithms for direct Connected Component Labeling”, WPMVP'19 Proceedings of the 5th Workshop on Programming Models for SIMD/Vector Processing, Washington, United States, pp. 4:1-4:8, (ACM) (2019)
- A. Hennequin, B. Couturier, V. Gligorov, L. Lacassagne : “SparseCCL: Connected Components Labeling and Analysis for sparse images”, DASIP 2019 - The Conference on Design and Architectures for Signal and Image Processing, MontrĂ©al, Canada (2019)
-
2018
- A. Hennequin, L. Lacassagne, L. Cabaret, Q. Meunier : “A new Direct Connected Component Labeling and Analysis Algorithms for GPUs”, 2018 Conference on Design and Architectures for Signal and Image Processing (DASIP), Porto, Portugal (2018)
- A. Petreto, A. Hennequin, Th. Koehler, Th. Romera, Y. Fargeix, B. Gaillard, M. Bouyer, Q. Meunier, L. Lacassagne : “Energy and Execution Time Comparison of Optical Flow Algorithms on SIMD and GPU Architectures”, Conference on Design and Architectures for Signal and Image Processing (Dasip 2018), Porto, Portugal (2018)
- N. Rambaux, D. Galayko, G. Guignan, J. Vaubaillon, L. Lacassagne, Ph. Keckhut, A. Levasseur‑Regourd, A. Hauchecorne, M. Birlan, G. Augarde, S. Barnier, S. Ben Kemmoum, A. Bigot, P. Boisse, M. Capderou, A. Chu, F. Colas, F. DESHOURS, Y. Fargeix, A. Hennequin, Th. Koehler, M. Lumbroso, J.‑F. Mariscal, D. Portela‑Moreira, J. Raffard, J.‑L. Rault, Th. Romera, C. Tob, B. Zanda : “METEORIX: a cubesat mission dedicated to the detection of meteors”, COSPAR 2018, 42nd Assembly, Pasadena, United States (2018)
- A. Petreto, A. Hennequin, Th. Koehler, Th. Romera, Y. Fargeix, B. Gaillard, M. Bouyer, Q. Meunier, L. Lacassagne : “Comparaison de la consommation Ă©nergĂ©tique et du temps d’exĂ©cution d’un algorithme de traitement d’images optimisĂ© sur des architectures SIMD et GPU”, ConfĂ©rence d’informatique en ParallĂ©lisme, Architecture et Système (COMPAS 2018), Toulouse, France (2018)
- A. Petreto, A. Hennequin, Th. Koehler, Th. Romera, Y. Fargeix, B. Gaillard, M. Bouyer, Q. Meunier, L. Lacassagne : “Comparaison de la consommation Ă©nergĂ©tique et du temps d’exĂ©cution d’un algorithme de traitement d’images optimisĂ© sur des architectures SIMD et GPU”, GdR SOC2, Paris, France (2018)