• DocumentCode
    147953
  • Title

    Efficient Dense and Sparse Matrix Multiplication on GP-SIMD

  • Author

    Morad, Amir ; Yavits, Leonid ; Ginosar, Ran

  • Author_Institution
    Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel
  • fYear
    2014
  • fDate
    Sept. 29 2014-Oct. 1 2014
  • Firstpage
    1
  • Lastpage
    8
  • Abstract
    We present efficient Dense and Sparse Matrix Multiplication on GP-SIMD, a hybrid general purpose SIMD computer architecture that eliminates synchronization by in-memory computing, combining data storage and massively parallel processing. Cycle-accurate simulation of on a large set of matrices shows enhanced power efficiency relative to conventional architectures.
  • Keywords
    matrix multiplication; parallel architectures; GP-SIMD; data storage; dense matrix multiplication; hybrid general purpose SIMD computer architecture; in-memory computing; massively parallel processing; sparse matrix multiplication; Artificial intelligence; Gold; Hardware; Memory architecture; Radio access networks; Vectors; Associative Processor; GP-SIMD; In-Memory Computing; Memory Intensive Computing; Sparse Linear Algebra;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Power and Timing Modeling, Optimization and Simulation (PATMOS), 2014 24th International Workshop on
  • Conference_Location
    Palma de Mallorca
  • Type

    conf

  • DOI
    10.1109/PATMOS.2014.6951895
  • Filename
    6951895
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=147953