CMRF: a Configurable Matrix Register File for accelerating matrix operations on SIMD processors

  • Zhang Kai
    School of Computer, National University of Defense Technology
  • Chen Shuming
    School of Computer, National University of Defense Technology
  • Chen Hu
    School of Computer, National University of Defense Technology
  • Wang Yaohua
    School of Computer, National University of Defense Technology
  • Chen Xiaowen
    School of Computer, National University of Defense Technology
  • Liu Sheng
    School of Computer, National University of Defense Technology
  • Liu Wei
    School of Computer, National University of Defense Technology

説明

Mapping matrix operations on SIMD processors brings a large amount of data rearrangement that decrease the system performance. This paper proposes a Configurable Matrix Register File (CMRF) that supports both row-wise and column-wise accesses. The CMRF can be dynamically configured into different operating modes in which one or several sub-matrices can be accessed in parallel. Experimental results show that, compared with the traditional Vector Register File (VRF) and the MRF, the CMRF can respectively achieve about 2.21x and 1.6x average performance improvement. Compared with TMS320C64x+, our SIMD processor can achieve about 5.65x to 7.71x performance improvement by employing the CMRF.

収録刊行物

参考文献 (2)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ