• DocumentCode
    2190901
  • Title

    Design and Power Performance Evaluation of On-Chip Memory Processor with Arithmetic Accelerators

  • Author

    Takahashi, Chikafumi ; Sato, Mitsuhisa ; Takahashi, Daisuke ; Boku, Taisuke ; Ukawa, Akira ; Nakamura, Hiroshi ; Aoki, Hidetaka ; Sawamoto, Hideo ; Sukegawa, Naonobu

  • Author_Institution
    Univ. of Tsukuba, Tsukuba, Japan
  • fYear
    2008
  • fDate
    21-23 Jan. 2008
  • Firstpage
    51
  • Lastpage
    57
  • Abstract
    In this paper, we design an on-chip memory processor with arithmetic accelerators, which are expected to improve power consumption. In addition, we evaluate the power performance of the processor. We propose implementing vector-type arithmetic accelerators and SIMD-type arithmetic accelerators in the on-chip memory processor. The evaluation results obtained using our simulator indicate that the performance of the 4FMAs SIMD-type accelerators is similar to that of the 4FMAs vector-type accelerators on DAXPY, Livermore kernel 1 and 3. However, the performance of the 4FMAs vector-type accelerator exceeds that of the 4FMAs SIMD-type accelerator with respect to matrix multiplication and QCD because of difference in element size of the registers. On Livermore kernel 7, the power performance of the 4FMAs SIMD-type accelerators exceeds that of the 4FMAs vector-type because of register reuse. However, the 16FMAs vector-type accelerators have an advantage in almost all simulations, excluding main memory bandwidth intensive benchmarks.
  • Keywords
    matrix multiplication; memory architecture; microprocessor chips; operating system kernels; parallel processing; performance evaluation; power consumption; quantum chromodynamics; system-on-chip; vector processor systems; 4FMAs SIMD-type accelerators; 4FMAs vector-type accelerators; DAXPY; Livermore kernel; QCD; SIMD-type arithmetic accelerators; fused multiply-add; matrix multiplication; on-chip memory processor; power consumption; power performance evaluation; quantum chromo dynamics; register reuse; vector-type arithmetic accelerators; Acceleration; Arithmetic; Clocks; Energy consumption; Frequency; Kernel; Memory architecture; Microprocessors; Prefetching; Registers; arithmetic accelerators; multi-core processors; on-chip memory; power consumption; simulator;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Innovative Architecture for Future Generation High-Performance Processors and Systems (IWIA), 2008 International Workshop on
  • Conference_Location
    Hilo, HI
  • ISSN
    1537-3223
  • Print_ISBN
    978-1-4244-6465-4
  • Electronic_ISBN
    1537-3223
  • Type

    conf

  • DOI
    10.1109/IWIA.2008.9
  • Filename
    5453551