A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor

N. Kimura, A. Annovi, M. Beretta, M. Gatta, S. Gkaitatzis, T. Iizawa, K. Kordas, T. Korikawa, S. Nikolaidis, C. Petridou, C. L. Sotiropoulou, Kohei Yorita, G. Volpi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    The highly parallel 2D-clustering FPGA implementation used for the input system of the Fast TracKer (FTK) processor for the ATLAS experiment of the Large Hadron Collider (LHC) at CERN is presented. The LHC after the 2013-2014 shutdown periods is planned to have increased luminosity, which will make it more difficult to have efficient online selection of rare events due to the increase of the overlapping collisions. FTK is a highly-parallelized hardware system that improves the online selection by executing real time track finding using the information from the silicon inner detector. The FTK system requires fast and robust clustering of the hits retrieved from the silicon detector on FPGA devices. We show the development of the original input boards and the implemented clustering algorithm. For the complicated 2D-clustering, a moving window technique is used to minimize the use of FPGA resources. The combination of custom developed boards and implementation of the clustering algorithm provides sufficient processing power to meet the specifications for the silicon inner detector of ATLAS up to the maximum LHC luminosity planned until 2022. The developed algorithm is easily adjustable to other image processing applications that require real-time 2D-clustering.

    Original languageEnglish
    Title of host publication2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    ISBN (Print)9781479936595
    DOIs
    Publication statusPublished - 2015 Apr 28
    Event2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Nara, Japan
    Duration: 2014 May 262014 May 30

    Other

    Other2014 19th IEEE-NPSS Real Time Conference, RT 2014
    CountryJapan
    CityNara
    Period14/5/2614/5/30

    Fingerprint

    Silicon detectors
    Colliding beam accelerators
    Clustering algorithms
    Field programmable gate arrays (FPGA)
    Luminance
    Image processing
    Specifications
    Hardware
    Processing
    Experiments

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Computer Networks and Communications
    • Software
    • Electrical and Electronic Engineering
    • Information Systems

    Cite this

    Kimura, N., Annovi, A., Beretta, M., Gatta, M., Gkaitatzis, S., Iizawa, T., ... Volpi, G. (2015). A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor. In 2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records [7097431] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RTC.2014.7097431

    A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor. / Kimura, N.; Annovi, A.; Beretta, M.; Gatta, M.; Gkaitatzis, S.; Iizawa, T.; Kordas, K.; Korikawa, T.; Nikolaidis, S.; Petridou, C.; Sotiropoulou, C. L.; Yorita, Kohei; Volpi, G.

    2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records. Institute of Electrical and Electronics Engineers Inc., 2015. 7097431.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kimura, N, Annovi, A, Beretta, M, Gatta, M, Gkaitatzis, S, Iizawa, T, Kordas, K, Korikawa, T, Nikolaidis, S, Petridou, C, Sotiropoulou, CL, Yorita, K & Volpi, G 2015, A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor. in 2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records., 7097431, Institute of Electrical and Electronics Engineers Inc., 2014 19th IEEE-NPSS Real Time Conference, RT 2014, Nara, Japan, 14/5/26. https://doi.org/10.1109/RTC.2014.7097431
    Kimura N, Annovi A, Beretta M, Gatta M, Gkaitatzis S, Iizawa T et al. A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor. In 2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records. Institute of Electrical and Electronics Engineers Inc. 2015. 7097431 https://doi.org/10.1109/RTC.2014.7097431
    Kimura, N. ; Annovi, A. ; Beretta, M. ; Gatta, M. ; Gkaitatzis, S. ; Iizawa, T. ; Kordas, K. ; Korikawa, T. ; Nikolaidis, S. ; Petridou, C. ; Sotiropoulou, C. L. ; Yorita, Kohei ; Volpi, G. / A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor. 2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records. Institute of Electrical and Electronics Engineers Inc., 2015.
    @inproceedings{03a1be213d704817ab4226072d7f177c,
    title = "A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor",
    abstract = "The highly parallel 2D-clustering FPGA implementation used for the input system of the Fast TracKer (FTK) processor for the ATLAS experiment of the Large Hadron Collider (LHC) at CERN is presented. The LHC after the 2013-2014 shutdown periods is planned to have increased luminosity, which will make it more difficult to have efficient online selection of rare events due to the increase of the overlapping collisions. FTK is a highly-parallelized hardware system that improves the online selection by executing real time track finding using the information from the silicon inner detector. The FTK system requires fast and robust clustering of the hits retrieved from the silicon detector on FPGA devices. We show the development of the original input boards and the implemented clustering algorithm. For the complicated 2D-clustering, a moving window technique is used to minimize the use of FPGA resources. The combination of custom developed boards and implementation of the clustering algorithm provides sufficient processing power to meet the specifications for the silicon inner detector of ATLAS up to the maximum LHC luminosity planned until 2022. The developed algorithm is easily adjustable to other image processing applications that require real-time 2D-clustering.",
    author = "N. Kimura and A. Annovi and M. Beretta and M. Gatta and S. Gkaitatzis and T. Iizawa and K. Kordas and T. Korikawa and S. Nikolaidis and C. Petridou and Sotiropoulou, {C. L.} and Kohei Yorita and G. Volpi",
    year = "2015",
    month = "4",
    day = "28",
    doi = "10.1109/RTC.2014.7097431",
    language = "English",
    isbn = "9781479936595",
    booktitle = "2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - A highly parallel FPGA implementation of a 2D-clustering algorithm for the ATLAS Fast TracKer (FTK) processor

    AU - Kimura, N.

    AU - Annovi, A.

    AU - Beretta, M.

    AU - Gatta, M.

    AU - Gkaitatzis, S.

    AU - Iizawa, T.

    AU - Kordas, K.

    AU - Korikawa, T.

    AU - Nikolaidis, S.

    AU - Petridou, C.

    AU - Sotiropoulou, C. L.

    AU - Yorita, Kohei

    AU - Volpi, G.

    PY - 2015/4/28

    Y1 - 2015/4/28

    N2 - The highly parallel 2D-clustering FPGA implementation used for the input system of the Fast TracKer (FTK) processor for the ATLAS experiment of the Large Hadron Collider (LHC) at CERN is presented. The LHC after the 2013-2014 shutdown periods is planned to have increased luminosity, which will make it more difficult to have efficient online selection of rare events due to the increase of the overlapping collisions. FTK is a highly-parallelized hardware system that improves the online selection by executing real time track finding using the information from the silicon inner detector. The FTK system requires fast and robust clustering of the hits retrieved from the silicon detector on FPGA devices. We show the development of the original input boards and the implemented clustering algorithm. For the complicated 2D-clustering, a moving window technique is used to minimize the use of FPGA resources. The combination of custom developed boards and implementation of the clustering algorithm provides sufficient processing power to meet the specifications for the silicon inner detector of ATLAS up to the maximum LHC luminosity planned until 2022. The developed algorithm is easily adjustable to other image processing applications that require real-time 2D-clustering.

    AB - The highly parallel 2D-clustering FPGA implementation used for the input system of the Fast TracKer (FTK) processor for the ATLAS experiment of the Large Hadron Collider (LHC) at CERN is presented. The LHC after the 2013-2014 shutdown periods is planned to have increased luminosity, which will make it more difficult to have efficient online selection of rare events due to the increase of the overlapping collisions. FTK is a highly-parallelized hardware system that improves the online selection by executing real time track finding using the information from the silicon inner detector. The FTK system requires fast and robust clustering of the hits retrieved from the silicon detector on FPGA devices. We show the development of the original input boards and the implemented clustering algorithm. For the complicated 2D-clustering, a moving window technique is used to minimize the use of FPGA resources. The combination of custom developed boards and implementation of the clustering algorithm provides sufficient processing power to meet the specifications for the silicon inner detector of ATLAS up to the maximum LHC luminosity planned until 2022. The developed algorithm is easily adjustable to other image processing applications that require real-time 2D-clustering.

    UR - http://www.scopus.com/inward/record.url?scp=84937115556&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84937115556&partnerID=8YFLogxK

    U2 - 10.1109/RTC.2014.7097431

    DO - 10.1109/RTC.2014.7097431

    M3 - Conference contribution

    AN - SCOPUS:84937115556

    SN - 9781479936595

    BT - 2014 19th IEEE-NPSS Real Time Conference, RT 2014 - Conference Records

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -