A fast and efficient SIMD track reconstruction algorithm for the LHCb upgrade 1 VELO-PIX detector

被引：3
作者：
Hennequin, A. [1 ,2 ]
Couturier, B. [1 ]
Gligorov, V. V. [3 ]
Ponce, S. [1 ]
Quagliani, R. [3 ]
Lacassagne, L. [2 ]
机构：
[1] CERN, LHCb Expt, Geneva, Switzerland
[2] Sorbonne Univ, CNRS, LIP6, Paris, France
[3] Sorbonne Univ, Paris Diderot Sorbonne Paris Cite, LPNHE, CNRS,IN2P3, Paris, France
来源：
JOURNAL OF INSTRUMENTATION | 2020年 / 15卷 / 06期
关键词：
Data processing methods; Data reduction methods; Pattern recognition; cluster finding; calibration and fitting methods; Computing; (architecture; farms; GRID for recording storage; archiving; and distribution of data);
D O I：
10.1088/1748-0221/15/06/P06018
中图分类号：
TH7 [仪器、仪表];
学科分类号：
0804 ; 080401 ; 081102 ;
摘要：
The upgraded CERN LHCb detector, due to start data taking in 2021, will have to reconstruct 4 TB/s of raw detector data in real time using commodity processors. This is one of the biggest real-time data processing challenges in any scientific domain. We present an intrinsically parallel reconstruction algorithm for the vertex detector of the LHCb experiment designed to optimally exploit multi-core general purpose architectures. We evaluate the algorithm on two high-end architectures from two different vendors and discuss in detail the impact of different SIMD Instruction Set Architecture extensions on the performance. We further compare the algorithm to current state-of-the-art scalar pattern recognition algorithms. We show a factor 2 speedup while achieving similar or better levels of physics performance.
引用
收藏
页数：22
相关论文
共 46 条
  • [21] A New Parallel Algorithm for Two-Pass Connected Component Labeling
    Gupta, Siddharth
    Palsetia, Diana
    Patwary, Md. Mostofa Ali
    Agrawal, Ankit
    Choudhary, Alok
    [J]. PROCEEDINGS OF 2014 IEEE INTERNATIONAL PARALLEL & DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2014, : 1356 - 1363
  • [22] Haralick R. M., 1981, Real-Time/Parallel Computing. Image Analysis. Proceedings of Part of the Japan-United States Seminar on Research Towards Real-Time Parallel Image Analysis and Recognition, P11
  • [23] The connected-component labeling problem: A review of state-of-the-art algorithms
    He, Lifeng
    Ren, Xiwei
    Gao, Qihang
    Zhao, Xiao
    Yao, Bin
    Chao, Yuyan
    [J]. PATTERN RECOGNITION, 2017, 70 : 25 - 43
  • [24] Hennequin A., 2019, 2019 C DES ARCH SIGN
  • [25] Hennequin A., 2019, P 5 WORKSH PROGR MOD
  • [26] Hennequin A., 2018, IEEE INT C DES ARCH, P1
  • [27] LHCb VELO upgrade
    Hennessy, Karol
    [J]. NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2017, 845 : 97 - 100
  • [28] Hough P.V.C., 1959, C P C, V590914, P554
  • [29] Karpinski P., 2017, P 8 INT WORKSH PROGR, P21, DOI DOI 10.1145/3026937.3026939
  • [30] A single-cycle parallel multi-slice connected components analysis hardware architecture
    Klaiber, Michael J.
    Bailey, Donald G.
    Simon, Sven
    [J]. JOURNAL OF REAL-TIME IMAGE PROCESSING, 2019, 16 (04) : 1165 - 1175
12345