Parameterized Posit Arithmetic Hardware Generator

被引:65
作者
Chaurasiya, Rohit [1 ]
Gustafson, John [2 ]
Shrestha, Rahul [1 ]
Neudorfer, Jonathan [3 ]
Nambiar, Sangeeth [3 ]
Niyogi, Kaustav [3 ]
Merchant, Farhad [4 ]
Leupers, Rainer [4 ]
机构
[1] Indian Inst Technol, Mandi, India
[2] Natl Univ Singapore, Singapore, Singapore
[3] Bosch Res & Technol Ctr India, Bangalore, Karnataka, India
[4] Rhein Westfal TH Aachen, Inst Commun Technol & Embedded Syst, Aachen, Germany
来源
2018 IEEE 36TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD) | 2018年
关键词
computer arithmetic; floating point arithmetic; numerical error; posit arithmetic;
D O I
10.1109/ICCD.2018.00057
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Hardware implementation of Floating Point Units (FPUs) has been a key area of research due to their massive area and energy footprints. Recently, a proposal was made to replace IEEE 754-2008 technical standard compliant FPUs with Posit Arithmetic Units (PAUs) due to the greater accuracy, speed, and simpler hardware design. In this paper, we present the architecture of a parameterized PAU generator that can generate PAU adders and PAU multipliers of any bit-width pre-synthesis. We synthesize generated arithmetic units using the parameterized PAU generator for 8-bit, 16-bit, and 32-bit adders and multipliers and compare them with IEEE 754-2008 compliant adders and multipliers. Both, synthesis for Field Programmable Gate Array (FPGA) and Application Specific Integrated Circuit (ASIC) are performed. In our comparison of m-bit PAU units with n-bit IEEE 754-2008 compliant units, it is observed that the area and energy of a PAU adder and multiplier are comparable to their IEEE 754-2008 compliant counterparts where m = n. We argue that an n-bit IEEE 754-2008 adder and multiplier can be safely replaced with an m-bit PAU adder and multiplier where m < n, due to superior numerical accuracy of the PAU; we also compare m-bit PAU adders and multipliers with n-bit IEEE 754-2008 compliant adders and multipliers. As an application example, we examine performance in the domain of signal processing with and without PAU adders and multipliers, and show the advantage of our approach.
引用
收藏
页码:334 / 341
页数:8
相关论文
共 29 条
  • [1] PACoGen: A Hardware Posit Arithmetic Core Generator
    Jaiswal, Manish Kumar
    So, Hayden K-H
    IEEE ACCESS, 2019, 7 : 74586 - 74601
  • [2] Posit Arithmetic Hardware Implementations with The Minimum Cost Divider and SquareRoot
    Xiao, Feibao
    Liang, Feng
    Wu, Bin
    Liang, Junzhe
    Cheng, Shuting
    Zhang, Guohe
    ELECTRONICS, 2020, 9 (10) : 1 - 16
  • [3] A Hardware Generator for SORN Arithmetic
    Rust, Jochen
    Baerthel, Moritz
    Seidel, Pascal
    Paul, Steffen
    IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 39 (12) : 4842 - 4853
  • [4] A Suite of Division Algorithms for Posit Arithmetic
    Murillo, Raul
    Del Barrio, Alberto A.
    Botella, Guillermo
    2023 IEEE 34TH INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS, ASAP, 2023, : 41 - 44
  • [5] Comparing Different Decodings for Posit Arithmetic
    Murillo, Raul
    Mallasen, David
    Del Barrio, Alberto A.
    Botella, Guillermo
    NEXT GENERATION ARITHMETIC, CONGA 2022, 2022, 13253 : 84 - 99
  • [6] Energy-Efficient MAC Units for Fused Posit Arithmetic
    Murillo, Raul
    Mallasen, David
    Del Barrio, Alberto A.
    Botella, Guillermo
    2021 IEEE 39TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD 2021), 2021, : 138 - 145
  • [7] HUB Meets Posit: Arithmetic Units Implementation
    Murillo, Raul
    Hormigo, Javier
    Barrio, Alberto A. Del
    Botella, Guillermo
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2024, 71 (01) : 440 - 444
  • [8] Brightening the Optical Flow through Posit Arithmetic
    Saxena, Vinay
    Reddy, Ankitha
    Neudorfer, Jonathan
    Gustafson, John
    Nambiar, Sangeeth
    Teupers, Rainer
    Merchant, Farhad
    PROCEEDINGS OF THE 2021 TWENTY SECOND INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN (ISQED 2021), 2021, : 463 - 468
  • [9] Posit and floating-point based Izhikevich neuron: A Comparison of arithmetic
    Fernandez-Hart, T.
    Knight, James C.
    Kalganova, T.
    NEUROCOMPUTING, 2024, 597
  • [10] Square Root Unit with Minimum Iterations for Posit Arithmetic
    Murillo, Raul
    Del Barrio, Alberto A.
    Botella, Guillermo
    PROCEEDINGS 2024 IEEE 31ST SYMPOSIUM ON COMPUTER ARITHMETIC, ARITH 2024, 2024, : 132 - 138