• DocumentCode
    598614
  • Title

    Compass: A scalable simulator for an architecture for cognitive computing

  • Author

    Preissl, R. ; Wong, Theodore M. ; Datta, Piyali ; Flickner, Myron ; Singh, Rajdeep ; Esser, Steven K. ; Risk, William P. ; Simon, Horst D. ; Modha, Dharmendra S.

  • Author_Institution
    IBM Res. - Almaden, San Jose, CA, USA
  • fYear
    2012
  • fDate
    10-16 Nov. 2012
  • Firstpage
    1
  • Lastpage
    11
  • Abstract
    Inspired by the function, power, and volume of the organic brain, we are developing TrueNorth, a novel modular, non-von Neumann, ultra-low power, compact architecture. TrueNorth consists of a scalable network of neurosynaptic cores, with each core containing neurons, dendrites, synapses, and axons. To set sail for TrueNorth, we developed Compass, a multi-threaded, massively parallel functional simulator and a parallel compiler that maps a network of long-distance pathways in the macaque monkey brain to TrueNorth. We demonstrate near-perfect weak scaling on a 16 rack IBM® Blue Gene®/Q (262144 CPUs, 256 TB memory), achieving an unprecedented scale of 256 million neurosynaptic cores containing 65 billion neurons and 16 trillion synapses running only 388x slower than real time with an average spiking rate of 8.1 Hz. By using emerging PGAS communication primitives, we also demonstrate 2x better real-time performance over MPI primitives on a 4 rack Blue Gene/P (16384 CPUs, 16 TB memory).
  • Keywords
    biocomputing; digital simulation; low-power electronics; multi-threading; neural net architecture; parallelising compilers; performance evaluation; 16 rack IBM Blue Gene/Q; Compass; PGAS communication primitives; TrueNorth; axons; cognitive computing architecture; dendrites; long-distance pathways; macaque monkey brain; modular nonvon Neumann architecture; multithreaded massively parallel functional simulator; neurons; neurosynaptic cores; parallel compiler; real-time performance; scalable network; scalable simulator; synapses; ultra-low power compact architecture; Brain modeling; Compass; Computational modeling; Computer architecture; Message systems; Nerve fibers;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    High Performance Computing, Networking, Storage and Analysis (SC), 2012 International Conference for
  • Conference_Location
    Salt Lake City, UT
  • ISSN
    2167-4329
  • Print_ISBN
    978-1-4673-0805-2
  • Type

    conf

  • DOI
    10.1109/SC.2012.34
  • Filename
    6468524