Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures
Abstract
Faced with physical and energy density limitations on clock speed, contemporary microprocessor designers have increasingly turned to on-chip parallelism for performance gains. Algorithms should accordingly be designed with ample amounts of fine-grained parallelism if they are to realize the full performance of the hardware. This requirement can be challenging for algorithms that are naturally expressed as a sequence of small-matrix operations, such as the Kalman filter methods widely in use in high-energy physics experiments. In the High-Luminosity Large Hadron Collider (HL-LHC), for example, one of the dominant computational problems is expected to be finding and fitting charged-particle tracks during event reconstruction; today, the most common track-finding methods are those based on the Kalman filter. Experience at the LHC, both in the trigger and offline, has shown that these methods are robust and provide high physics performance. Previously we reported the significant parallel speedups that resulted from our efforts to adapt Kalman-filter-based tracking to many-core architectures such as Intel Xeon Phi. Here we report on how effectively those techniques can be applied to more realistic detector configurations and event complexity.
- Authors:
-
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Princeton Univ., Princeton, NJ (United States)
- Univ. of California San Diego, La Jolla, CA (United States)
- Cornell Univ., Ithaca, NY (United States)
- Publication Date:
- Research Org.:
- Fermi National Accelerator Lab. (FNAL), Batavia, IL (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- OSTI Identifier:
- 1423237
- Report Number(s):
- FERMILAB-CONF-17-655-CD; arXiv:1711.06571
Journal ID: ISSN 1742-6588; 1636972
- Grant/Contract Number:
- AC02-07CH11359
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Physics. Conference Series
- Additional Journal Information:
- Journal Volume: 1085; Journal Issue: 4; Conference: 18th International Workshop on Advanced Computing and Analysis Techniques in Physics Research, Seattle, WA (United States), 21-25 Aug 2017; Journal ID: ISSN 1742-6588
- Publisher:
- IOP Publishing
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND TECHNOLOGY; 72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS
Citation Formats
Cerati, Giuseppe, Elmer, Peter, Krutelyov, Slava, Lantz, Steven, Lefebvre, Matthieu, Masciovecchio, Mario, McDermott, Kevin, Riley, Daniel, Tadel, Matevz, Wittich, Peter, Wurthwein, Frank, and Yagil, Avi. Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures. United States: N. p., 2018.
Web. doi:10.1088/1742-6596/1085/4/042016.
Cerati, Giuseppe, Elmer, Peter, Krutelyov, Slava, Lantz, Steven, Lefebvre, Matthieu, Masciovecchio, Mario, McDermott, Kevin, Riley, Daniel, Tadel, Matevz, Wittich, Peter, Wurthwein, Frank, & Yagil, Avi. Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures. United States. https://doi.org/10.1088/1742-6596/1085/4/042016
Cerati, Giuseppe, Elmer, Peter, Krutelyov, Slava, Lantz, Steven, Lefebvre, Matthieu, Masciovecchio, Mario, McDermott, Kevin, Riley, Daniel, Tadel, Matevz, Wittich, Peter, Wurthwein, Frank, and Yagil, Avi. Thu .
"Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures". United States. https://doi.org/10.1088/1742-6596/1085/4/042016. https://www.osti.gov/servlets/purl/1423237.
@article{osti_1423237,
title = {Parallelized Kalman-Filter-Based Reconstruction of Particle Tracks on Many-Core Architectures},
author = {Cerati, Giuseppe and Elmer, Peter and Krutelyov, Slava and Lantz, Steven and Lefebvre, Matthieu and Masciovecchio, Mario and McDermott, Kevin and Riley, Daniel and Tadel, Matevz and Wittich, Peter and Wurthwein, Frank and Yagil, Avi},
abstractNote = {Faced with physical and energy density limitations on clock speed, contemporary microprocessor designers have increasingly turned to on-chip parallelism for performance gains. Algorithms should accordingly be designed with ample amounts of fine-grained parallelism if they are to realize the full performance of the hardware. This requirement can be challenging for algorithms that are naturally expressed as a sequence of small-matrix operations, such as the Kalman filter methods widely in use in high-energy physics experiments. In the High-Luminosity Large Hadron Collider (HL-LHC), for example, one of the dominant computational problems is expected to be finding and fitting charged-particle tracks during event reconstruction; today, the most common track-finding methods are those based on the Kalman filter. Experience at the LHC, both in the trigger and offline, has shown that these methods are robust and provide high physics performance. Previously we reported the significant parallel speedups that resulted from our efforts to adapt Kalman-filter-based tracking to many-core architectures such as Intel Xeon Phi. Here we report on how effectively those techniques can be applied to more realistic detector configurations and event complexity.},
doi = {10.1088/1742-6596/1085/4/042016},
journal = {Journal of Physics. Conference Series},
number = 4,
volume = 1085,
place = {United States},
year = {Thu Oct 18 00:00:00 EDT 2018},
month = {Thu Oct 18 00:00:00 EDT 2018}
}
Web of Science