Topic 11: Multicore and manycore programming (Introduction)

Luiz DeRose, Jan Treibig, David Abramson, Alastair Donaldson, William Jalby, Alba Cristina M A De Melo, Tomàs Margalef

    Research output: Chapter in Book/Report/Conference proceedingForeword / PostscriptOther

    Abstract

    Today's compute node architectures leverage impressive performance by offering more parallel resources on the chip as well as on the node level. Among parallel resources are memory interfaces (ccNUMA), cores, caches and data parallel execution units. On the other hand modern multicore designs also exhibit shared resources such as memory bandwidth on the chip level, last level cache bandwidth and capacity, and access to the network interface. An additional performancelimiting factor is the frequently high cost for synchronization. The task to make full use of parallel resources while keeping an eye on the bottlenecks imposed by the shared resources is non-trivial. Common programming models often address issues related to parallel programming in general while not covering topological issues introduced by multi- and manycore architectures. The industry is still pushing forward introducing even more powerful manycore systems like, e.g., the Nvidia Kepler and Intel MIC architectures.

    Original languageEnglish
    Title of host publicationEuro-Par 2013 Parallel Processing
    Subtitle of host publication19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings
    EditorsFelix Wolf, Bernd Mohr, Dieter an Mey
    PublisherSpringer
    Pages545-546
    Number of pages2
    ISBN (Print)9783642400476, 9783642400469
    DOIs
    Publication statusPublished - 2013
    EventInternational Conference on Parallel Processing 2013 - Aachen, Germany
    Duration: 26 Aug 201330 Aug 2013
    Conference number: 19th

    Conference

    ConferenceInternational Conference on Parallel Processing 2013
    Abbreviated titleEuro-Par 2013
    CountryGermany
    CityAachen
    Period26/08/1330/08/13

    Cite this

    DeRose, L., Treibig, J., Abramson, D., Donaldson, A., Jalby, W., De Melo, A. C. M. A., & Margalef, T. (2013). Topic 11: Multicore and manycore programming (Introduction). In F. Wolf, B. Mohr, & D. an Mey (Eds.), Euro-Par 2013 Parallel Processing: 19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings (pp. 545-546). Springer. https://doi.org/10.1007/978-3-642-40047-6_55
    DeRose, Luiz ; Treibig, Jan ; Abramson, David ; Donaldson, Alastair ; Jalby, William ; De Melo, Alba Cristina M A ; Margalef, Tomàs. / Topic 11: Multicore and manycore programming (Introduction). Euro-Par 2013 Parallel Processing: 19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings. editor / Felix Wolf ; Bernd Mohr ; Dieter an Mey. Springer, 2013. pp. 545-546
    @inbook{8c2084ae2e50480db1c53e8314eb140f,
    title = "Topic 11: Multicore and manycore programming (Introduction)",
    abstract = "Today's compute node architectures leverage impressive performance by offering more parallel resources on the chip as well as on the node level. Among parallel resources are memory interfaces (ccNUMA), cores, caches and data parallel execution units. On the other hand modern multicore designs also exhibit shared resources such as memory bandwidth on the chip level, last level cache bandwidth and capacity, and access to the network interface. An additional performancelimiting factor is the frequently high cost for synchronization. The task to make full use of parallel resources while keeping an eye on the bottlenecks imposed by the shared resources is non-trivial. Common programming models often address issues related to parallel programming in general while not covering topological issues introduced by multi- and manycore architectures. The industry is still pushing forward introducing even more powerful manycore systems like, e.g., the Nvidia Kepler and Intel MIC architectures.",
    author = "Luiz DeRose and Jan Treibig and David Abramson and Alastair Donaldson and William Jalby and {De Melo}, {Alba Cristina M A} and Tom{\`a}s Margalef",
    year = "2013",
    doi = "10.1007/978-3-642-40047-6_55",
    language = "English",
    isbn = "9783642400476",
    pages = "545--546",
    editor = "Felix Wolf and Bernd Mohr and {an Mey}, {Dieter }",
    booktitle = "Euro-Par 2013 Parallel Processing",
    publisher = "Springer",

    }

    DeRose, L, Treibig, J, Abramson, D, Donaldson, A, Jalby, W, De Melo, ACMA & Margalef, T 2013, Topic 11: Multicore and manycore programming (Introduction). in F Wolf, B Mohr & D an Mey (eds), Euro-Par 2013 Parallel Processing: 19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings. Springer, pp. 545-546, International Conference on Parallel Processing 2013, Aachen, Germany, 26/08/13. https://doi.org/10.1007/978-3-642-40047-6_55

    Topic 11: Multicore and manycore programming (Introduction). / DeRose, Luiz; Treibig, Jan; Abramson, David; Donaldson, Alastair; Jalby, William; De Melo, Alba Cristina M A; Margalef, Tomàs.

    Euro-Par 2013 Parallel Processing: 19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings. ed. / Felix Wolf; Bernd Mohr; Dieter an Mey. Springer, 2013. p. 545-546.

    Research output: Chapter in Book/Report/Conference proceedingForeword / PostscriptOther

    TY - CHAP

    T1 - Topic 11: Multicore and manycore programming (Introduction)

    AU - DeRose, Luiz

    AU - Treibig, Jan

    AU - Abramson, David

    AU - Donaldson, Alastair

    AU - Jalby, William

    AU - De Melo, Alba Cristina M A

    AU - Margalef, Tomàs

    PY - 2013

    Y1 - 2013

    N2 - Today's compute node architectures leverage impressive performance by offering more parallel resources on the chip as well as on the node level. Among parallel resources are memory interfaces (ccNUMA), cores, caches and data parallel execution units. On the other hand modern multicore designs also exhibit shared resources such as memory bandwidth on the chip level, last level cache bandwidth and capacity, and access to the network interface. An additional performancelimiting factor is the frequently high cost for synchronization. The task to make full use of parallel resources while keeping an eye on the bottlenecks imposed by the shared resources is non-trivial. Common programming models often address issues related to parallel programming in general while not covering topological issues introduced by multi- and manycore architectures. The industry is still pushing forward introducing even more powerful manycore systems like, e.g., the Nvidia Kepler and Intel MIC architectures.

    AB - Today's compute node architectures leverage impressive performance by offering more parallel resources on the chip as well as on the node level. Among parallel resources are memory interfaces (ccNUMA), cores, caches and data parallel execution units. On the other hand modern multicore designs also exhibit shared resources such as memory bandwidth on the chip level, last level cache bandwidth and capacity, and access to the network interface. An additional performancelimiting factor is the frequently high cost for synchronization. The task to make full use of parallel resources while keeping an eye on the bottlenecks imposed by the shared resources is non-trivial. Common programming models often address issues related to parallel programming in general while not covering topological issues introduced by multi- and manycore architectures. The industry is still pushing forward introducing even more powerful manycore systems like, e.g., the Nvidia Kepler and Intel MIC architectures.

    UR - http://www.scopus.com/inward/record.url?scp=84883136150&partnerID=8YFLogxK

    U2 - 10.1007/978-3-642-40047-6_55

    DO - 10.1007/978-3-642-40047-6_55

    M3 - Foreword / Postscript

    SN - 9783642400476

    SN - 9783642400469

    SP - 545

    EP - 546

    BT - Euro-Par 2013 Parallel Processing

    A2 - Wolf, Felix

    A2 - Mohr, Bernd

    A2 - an Mey, Dieter

    PB - Springer

    ER -

    DeRose L, Treibig J, Abramson D, Donaldson A, Jalby W, De Melo ACMA et al. Topic 11: Multicore and manycore programming (Introduction). In Wolf F, Mohr B, an Mey D, editors, Euro-Par 2013 Parallel Processing: 19th International Conference Aachen, Germany, August 26-30, 2013, Proceedings. Springer. 2013. p. 545-546 https://doi.org/10.1007/978-3-642-40047-6_55