Fully Pipelined Soft Vector Processor as a CPU Accelerator

被引:0
|
作者
PANG Yeyong [1 ]
WANG Shaojun [1 ]
PENG Yu [1 ]
PENG Xiyuan [1 ]
机构
[1] Department of Automatic Test and Control, Harbin Institute of Technology
基金
中央高校基本科研业务费专项资金资助; 中国国家自然科学基金;
关键词
FPGA; Vector processor; Microprocessor; Accelerator;
D O I
暂无
中图分类号
TP332 [运算器和控制器(CPU)];
学科分类号
081201 ;
摘要
FPGA based soft vector processing accelerators are used frequently to perform highly parallel data processing tasks. Since they are not able to implement complex control manipulations using software, most FPGA systems now incorporate either a soft processor or hard processor. A FPGA based AXI bus compatible vector accelerator architecture is proposed which utilises fully pipelined and heterogeneous ALU for performance, and microcoding is employed for reusability. The design is tested with several design examples in four different lane configurations.Compared with Central processing unit(CPU), Digital signal processor(DSP), Altera C2H tool and Open CL SDK implementations, the vector processor improves on execution time and energy consumption by factors of up to 6.6 and 6.4 respectively.
引用
收藏
页码:1198 / 1205
页数:8
相关论文
共 50 条
  • [1] Fully Pipelined Soft Vector Processor as a CPU Accelerator
    Pang Yeyong
    Wang Shaojun
    Peng Yu
    Peng Xiyuan
    [J]. CHINESE JOURNAL OF ELECTRONICS, 2017, 26 (06) : 1198 - 1205
  • [2] Vector Processing as a Soft Processor Accelerator
    Yu, Jason
    Eagleston, Christopher
    Chou, Christopher Han-Yu
    Perreault, Maxime
    Lemieux, Guy
    [J]. ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS, 2009, 2 (02)
  • [3] Vector Processing as a Soft-core CPU Accelerator
    Yu, Jason
    Lemieux, Guy
    Eagleston, Christopher
    [J]. FPGA 2008: SIXTEENTH ACM/SIGDA INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE GATE ARRAYS, 2008, : 222 - 231
  • [4] MICROPROGRAMMABLE PIPELINED VECTOR PROCESSOR
    MADESWARAN, V
    MATHIALAGAN, A
    [J]. COMPUTERS IN INDUSTRY, 1990, 13 (04) : 367 - 370
  • [5] VECTOR COMPUTATIONS ON A PARALLEL-PIPELINED PROCESSOR
    IGNATUSHCHENKO, VV
    KOGAN, YA
    SIGNAEVSKII, VA
    [J]. AUTOMATION AND REMOTE CONTROL, 1982, 43 (09) : 1202 - 1212
  • [6] Accelerator Compiler for the VENICE Vector Processor
    Liu, Zhiduo
    Severance, Aaron
    Singh, Satnam
    Lemieux, Guy G. F.
    [J]. FPGA 12: PROCEEDINGS OF THE 2012 ACM-SIGDA INTERNATIONAL SYMPOSIUM ON FIELD PROGRAMMABLE GATE ARRAYS, 2012, : 229 - 232
  • [7] VECTORIZATION OF ROBOT INVERSE DYNAMICS ON A PIPELINED VECTOR PROCESSOR
    CHENG, HH
    GUPTA, KC
    [J]. IEEE TRANSACTIONS ON ROBOTICS AND AUTOMATION, 1993, 9 (06): : 858 - 863
  • [8] Analysis and Optimization of a Deeply Pipelined FPGA Soft Processor
    Cheah, Hui Yan
    Fahmy, Suhaib A.
    Kapre, Nachiket
    [J]. PROCEEDINGS OF THE 2014 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (FPT), 2014, : 235 - 238
  • [9] A 21.54 Gbits/s fully pipelined AES processor on FPGA
    Hodjat, A
    Verbauwhede, I
    [J]. 12TH ANNUAL IEEE SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES, PROCEEDINGS, 2004, : 308 - 309
  • [10] A vector quantizer with fully pipelined data and control flow
    Kwai, DM
    Parhami, B
    [J]. 40TH MIDWEST SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1 AND 2, 1998, : 1057 - 1060