HUB Floating Point for Improving FPGA Implementations of DSP Applications

被引:11
|
作者
Hormigo, Javier [1 ]
Villalba, Julio [1 ]
机构
[1] Univ Malaga, Dept Comp Architecture, E-29071 Malaga, Spain
关键词
Digital signal processing (DSP) applications; floating point (FP); field-programmable gate array (FPGA); half-unit biased (HUB) format;
D O I
10.1109/TCSII.2016.2563798
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
The increasing complexity of new digital signal processing (DSP) applications is forcing the use of floating point (FP) numbers in their hardware implementations. In this brief, we investigate the advantages of using half-unit biased (HUB) formats to implement these FP applications on field-programmable gate arrays (FPGAs). These new FP formats allow for the effective elimination of the rounding logic on FP arithmetic units. First, we experimentally show that HUB and standard formats provide equivalent signal-to-noise ratio on DSP application implementations. We then present a detailed study of the improvement achieved when implementing FP adders andmultipliers on FPGAs by using HUB numbers. In most of the cases studied, the HUB approach reduces resource use and increases the speed of these FP units while always providing statistically equivalent accuracy as that of conventional formats. However, for some specific sizes, HUB multipliers require far more resources than the corresponding conventional approach.
引用
收藏
页码:319 / 323
页数:5
相关论文
共 50 条
  • [1] FPGA Implementation of DSP Applications Using HUB Floating Point Technique
    Pal, Oindrila
    Paldurai, K.
    [J]. 2017 INTERNATIONAL CONFERENCE ON NEXTGEN ELECTRONIC TECHNOLOGIES: SILICON TO SOFTWARE (ICNETS2), 2017, : 242 - 245
  • [2] Fast HUB Floating-Point Adder for FPGA
    Villalba, Julio
    Hormigo, Javier
    Gonzalez-Navarro, Sonia
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2019, 66 (06) : 1028 - 1032
  • [3] Audio application implementations on a block-floating-point DSP
    Kobayashi, S
    Lee, SY
    Kino, T
    Kozuka, L
    Tokui, T
    [J]. 2002 IEEE WORKSHOP ON SIGNAL PROCESSING SYSTEMS, 2002, : 51 - 56
  • [4] Design and Implementation of an Embedded FPGA Floating Point DSP Block
    Langhammer, Martin
    Pasca, Bogdan
    [J]. IEEE 22ND SYMPOSIUM ON COMPUTER ARITHMETIC ARITH 22, 2015, : 26 - 33
  • [5] Rapid prototyping of FPGA based floating point DSP systems
    Ho, CH
    Leong, MP
    Leong, PHW
    Becker, J
    Glesner, M
    [J]. 13TH IEEE INTERNATIONAL WORKSHOP ON RAPID SYSTEM PROTOTYPING, PROCEEDINGS, 2002, : 19 - 24
  • [6] ITERATIVE FLOATING POINT COMPUTATION USING FPGA DSP BLOCKS
    Brosser, Fredrik
    Cheah, Hui Yan
    Fahmy, Suhaib A.
    [J]. 2013 23RD INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE LOGIC AND APPLICATIONS (FPL 2013) PROCEEDINGS, 2013,
  • [7] High-Radix Formats for Enhancing Floating-Point FPGA Implementations
    Julio Villalba
    Javier Hormigo
    [J]. Circuits, Systems, and Signal Processing, 2022, 41 : 1683 - 1703
  • [8] High-Radix Formats for Enhancing Floating-Point FPGA Implementations
    Villalba, Julio
    Hormigo, Javier
    [J]. CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2022, 41 (03) : 1683 - 1703
  • [9] Design of Reversible Floating Point Adder for DSP Applications
    Nagamani, A. N.
    Kavyashree, C. K.
    Saraswathy, R. M.
    Kartika, C. H. V.
    Agrawal, Vinod Kumar
    [J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SIGNAL, NETWORKS, COMPUTING, AND SYSTEMS (ICSNCS 2016), VOL 2, 2016, 396 : 123 - 135
  • [10] Reconfigurable Floating Point Arithmetic Components for DSP Applications
    Karthik, K. Raghavendra
    Reddy, Diwakara K. L.
    Pawar, Chetan K.
    Sunitha, K.
    Javashrcc, H., V
    [J]. 2016 IEEE ANNUAL INDIA CONFERENCE (INDICON), 2016,