ARCHITECTURE OF A FLOATING-POINT BUTTERFLY EXECUTION UNIT IN A 400-MFLOPS PROCESSOR VLSI AND ITS IMPLEMENTATION

被引:0
|
作者
YAMAUCHI, H
MIYANAGA, H
机构
关键词
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Some dedicated floating-point hardware arithmetic modules designed as processing elements for butterfly operations are described. They consist of Input Data Converters (IDC), Output Data Converters (ODC), and a 2's complementary 24-bit (16E8) floating-point Butterfly Execution Unit (BEU). The BEU executes the four multiplication and six additions/subtractions required for a complex butterfly operation in each 25-ns execution cycle by implementing four multipliers and four 3-input adders/subtracters. The arithmetic modules are fabricated using 0.8-mu-m CMOS technology. An overview of the hardware unit is presented with special attention given to the BEU for parallel pipelined processing. In addition, module design methodologies for hardware implementation and some sophisticated high-speed execution techniques for floating-point multiplication and addition are discussed.
引用
收藏
页码:3852 / 3860
页数:9
相关论文
共 50 条
  • [1] A 400 MFLOPS FFT PROCESSOR VLSI ARCHITECTURE
    MIYANAGA, H
    YAMAUCHI, H
    [J]. IEICE TRANSACTIONS ON COMMUNICATIONS ELECTRONICS INFORMATION AND SYSTEMS, 1991, 74 (11): : 3845 - 3851
  • [2] A VLSI RISC WITH 20-MFLOPS PEAK, 64-BIT FLOATING-POINT UNIT
    KANEKO, K
    OKAMOTO, T
    NAKAJIMA, M
    NAKAKURA, Y
    GOKITA, S
    NISHIKAWA, J
    TANIKAWA, Y
    KADOTA, H
    [J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1989, 24 (05) : 1331 - 1340
  • [3] VLSI implementation of a floating-point divider
    Patel, JN
    Abid, Z
    Wang, W
    [J]. 16TH INTERNATIONAL CONFERENCE ON MICROELECTRONICS, PROCEEDINGS, 2004, : 505 - 508
  • [4] POWER2 FLOATING-POINT UNIT - ARCHITECTURE AND IMPLEMENTATION
    HICKS, TN
    FRY, RE
    HARVEY, PE
    [J]. IBM JOURNAL OF RESEARCH AND DEVELOPMENT, 1994, 38 (05) : 525 - 536
  • [5] THE NS32081 FLOATING-POINT UNIT - ARCHITECTURE AND IMPLEMENTATION
    GAVRIELOV, M
    EPSTEIN, L
    [J]. IEEE MICRO, 1986, 6 (02) : 6 - 12
  • [6] A FLOATING-POINT CELL LIBRARY AND A 100-MFLOPS IMAGE SIGNAL PROCESSOR
    FUJII, H
    HORI, C
    TAKADA, T
    HATANAKA, N
    DEMURA, T
    OOTOMO, G
    [J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1992, 27 (07) : 1080 - 1088
  • [7] AN 80 MFLOPS FLOATING-POINT ENGINE IN THE INTEL I860 PROCESSOR
    SIT, HP
    NOFAL, MR
    KIMN, S
    [J]. PROCEEDINGS - IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN : VLSI IN COMPUTERS & PROCESSORS, 1989, : 374 - 379
  • [8] A 320-MFLOPS CMOS FLOATING-POINT PROCESSING UNIT FOR SUPERSCALAR PROCESSORS
    IDE, N
    FUKUHISA, H
    KONDO, Y
    YOSHIDA, T
    NAGAMATSU, M
    MORI, J
    YAMAZAKI, I
    UENO, K
    [J]. IEEE JOURNAL OF SOLID-STATE CIRCUITS, 1993, 28 (03) : 352 - 361
  • [9] High-Performance Floating-Point VLSI Architecture of a Lifting-Based Wavelet Processor
    Guntoro, Andre
    Momeni, Massoud
    Keil, Hans-Peter
    Glesner, Manfred
    [J]. ICSES 2008 INTERNATIONAL CONFERENCE ON SIGNALS AND ELECTRONIC SYSTEMS, CONFERENCE PROCEEDINGS, 2008, : 35 - 38
  • [10] The vector floating-point unit in a synergistic processor element of a CELL processor
    Mueller, SM
    Jacobi, C
    Oh, HJ
    Tran, KD
    Cottier, SR
    Michael, BW
    Nishikawa, H
    Totsuka, Y
    Namatame, T
    Yano, N
    Machida, T
    Dhong, SH
    [J]. 17th IEEE Symposium on Computer Arithmetic, Proceedings, 2005, : 59 - 67