Dual-Purpose Hardware Algorithms and Architectures - Part 1: Floating-Point Division

被引：0
|
作者：
Seo, Jihee [1 ,2 ]
Kim, Dae Hyun [2 ]
机构：
[1] Synopsys Inc, Hillsboro, OR 97124 USA
[2] Washington State Univ, Sch Elect Engn & Comp Sci, Pullman, WA 99163 USA
来源：
2023 IEEE 30TH SYMPOSIUM ON COMPUTER ARITHMETIC, ARITH 2023 | 2023年
关键词：
Divider; Floating-Point Arithmetic; Online Division; ONLINE; DESIGN;
D O I：
10.1109/ARITH58626.2023.00013
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
Division is a time-consuming, but frequently-used arithmetic operation, so an enormous amount of effort has been made to improve the performance of dividers. Most of the division algorithms in the literature are offline algorithms that minimize the execution time of a single division, whereas some others are online algorithms that maximize the throughput (# divisions executed per time). In this paper, we propose an interval-analysis-based normal-binary floating-point division algorithm that can be used for both offline and online division. We implement two offline and four online dividers using the algorithm and compare them with recently-proposed offline and online dividers. The simulation results show that the offline versions are the best for a Binary64 offline division, whereas the online versions are the best for a Binary64 online division.
引用
收藏
页码：24 / 31
页数：8
相关论文
共 50 条
  • [11] Return of the hardware floating-point elementary function
    Detrey, Jeremie
    de Dinechin, Florent
    Pujol, Xavier
    18TH IEEE SYMPOSIUM ON COMPUTER ARITHMETIC, PROCEEDINGS, 2007, : 161 - +
  • [12] A hardware error estimate for floating-point computations
    Lang, Tomas
    Bruguera, Javier D.
    ADVANCED SIGNAL PROCESSING ALGORITHMS, ARCHITECTURES, AND IMPLEMENTATIONS XVIII, 2008, 7074
  • [13] SIMPLIFIED FLOATING-POINT DIVISION AND SQUARE ROOT
    Viitanen, Timo
    Jaaskelainen, Pekka
    Esko, Otto
    Takala, Jarmo
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 2707 - 2711
  • [14] Experiments for decimal floating-point division by recurrence
    Castellanos, Ivan D.
    Stine, James E.
    2006 FORTIETH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, VOLS 1-5, 2006, : 1716 - +
  • [15] SWIPT with Biased ASK Modulation and Dual-Purpose Hardware
    Claessens, Steven
    Schreurs, Dominique
    Pollin, Sofie
    2017 IEEE WIRELESS POWER TRANSFER CONFERENCE (WPTC 2017), 2017,
  • [16] Floating-point fused multiply-add architectures
    Quinnell, Eric
    Swartzlander, Earl E., Jr.
    Lemonds, Carl
    CONFERENCE RECORD OF THE FORTY-FIRST ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1-5, 2007, : 331 - +
  • [17] Study of floating-point architectures for pipelined RISC processors
    Reyes, Joy Alinda P.
    Alarcon, Louis P.
    Alarilla, Luis, Jr.
    2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS, 2006, : 2713 - +
  • [18] Algorithms for Manipulating Quaternions in Floating-Point Arithmetic
    Joldes, Mioara
    Muller, Jean-Michel
    2020 IEEE 27TH SYMPOSIUM ON COMPUTER ARITHMETIC (ARITH), 2020, : 48 - 55
  • [19] ALGORITHMS TO REVEAL PROPERTIES OF FLOATING-POINT ARITHMETIC
    MALCOLM, MA
    COMMUNICATIONS OF THE ACM, 1972, 15 (11) : 949 - &
  • [20] Potential speedup using decimal floating-point hardware
    Erle, MA
    Schulte, MJ
    Linebarger, JM
    THIRTY-SIXTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS - CONFERENCE RECORD, VOLS 1 AND 2, CONFERENCE RECORD, 2002, : 1073 - 1077
12345