Architectural-Space Exploration of Approximate Multipliers

被引:79
|
作者
Rehman, Semeen [1 ]
El-Harouni, Walaa [2 ]
Shafique, Muhammad [2 ,3 ]
Kumar, Akash [1 ]
Henkel, Joerg [2 ]
机构
[1] Tech Univ Dresden, Chair Processor Design, Dresden, Germany
[2] Karlsruhe Inst Technol, Chair Embedded Syst, D-76021 Karlsruhe, Germany
[3] Vienna Univ Technol TU Wien, Vienna, Austria
关键词
Approximate Computing; Multiplier; Adder; Arithmetic; Design Space Exploration; Performance; Area; Power; Configurable Accuracy; Low Power Image Processing; Open Source; Library;
D O I
10.1145/2966986.2967005
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper presents an architectural-space exploration methodology for designing approximate multipliers. Unlike state-of-the-art, our methodology generates various design points by adapting three key parameters: (1) different types of elementary approximate multiply modules, (2) different types of elementary adder modules for summing the partial products, and (3) selection of bits for approximation in a wide-bit multiplier design. Generation and exploration of such a design space enables a wide-range of multipliers with varying approximation levels, each exhibiting distinct area, power, and output quality, and thereby facilitates approximate computing at higher abstraction levels. We synthesized our designs using Synopsys Design Compiler with a TSMC 45nm technology library and verified using ModelSim gate-level simulations. Power and quality evaluations for various designs are performed using PrimeTime and behavioral models, respectively. The selected designs are then deployed in a JPEG application. For reproducibility and to facilitate further research and development at higher abstraction layers, we have released the RTL and behavioral models of these approximate multipliers and adders as an open-source library at https://sourceforge.net/projects/lpaclib/.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Architectural-Space Exploration of Energy-Efficient Approximate Arithmetic Units for Error-Tolerant Applications
    Waris, Haroon
    Wang, Chenghua
    Liu, Weiqiang
    [J]. 2022 IEEE COMPUTER SOCIETY ANNUAL SYMPOSIUM ON VLSI (ISVLSI 2022), 2022, : 440 - 445
  • [2] SHINOHARA,KAZUO - ARCHITECTURAL-SPACE EXPLORATION - 5 RECENT HOUSES
    SHINOHARA, K
    [J]. JAPAN ARCHITECT, 1979, 54 (03): : 9 - 45
  • [3] Architectural-Space Exploration of Heterogeneous Reliability and Checkpointing Modes for Out-of-Order Superscalar Processors
    Prabakaran, Bharath Srinivas
    Dave, Mihika
    Kriebel, Florian
    Rehman, Semeen
    Shafique, Muhammad
    [J]. IEEE ACCESS, 2019, 7 : 145324 - 145339
  • [4] A Time Efficient Comprehensive Model of Approximate Multipliers for Design Space Exploration
    Cui, Ziying
    Chen, Ke
    Wu, Bi
    Yan, Chenggang
    Gong, Yu
    Liu, Weiqiang
    [J]. PROCEEDINGS 2024 IEEE 31ST SYMPOSIUM ON COMPUTER ARITHMETIC, ARITH 2024, 2024, : 116 - 123
  • [5] Exploration of Approximate Multipliers Design Space using Carry Propagation Free Compressors
    Boroumand, Sina
    Afshar, Hadi P.
    Brisk, Philip
    Mohammadi, Siamak
    [J]. 2018 23RD ASIA AND SOUTH PACIFIC DESIGN AUTOMATION CONFERENCE (ASP-DAC), 2018, : 611 - 616
  • [6] Exploration of Modular Build of Architectural Space
    Li, Xixuan
    Li, Gulan
    [J]. ARCHITECTURE, BUILDING MATERIALS AND ENGINEERING MANAGEMENT, PTS 1-4, 2013, 357-360 : 338 - 344
  • [7] Bit level architectural exploration technique for the design of low power multipliers
    Economakos, George
    Anagnostopoulos, Kostas
    [J]. 2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS, 2006, : 1483 - +
  • [8] Design Space Exploration of Modular Multipliers for ASIC FHE accelerators
    Soni, Deepraj
    Nabeel, Mohammed
    Gamil, Homer
    Mazonka, Oleg
    Reagen, Brandon
    Karri, Ramesh
    Maniatakos, Michail
    [J]. 2023 24TH INTERNATIONAL SYMPOSIUM ON QUALITY ELECTRONIC DESIGN, ISQED, 2023, : 618 - 625
  • [9] Approximate Array Multipliers
    Balasubramanian, Padmanabhan
    Nayar, Raunaq
    Maskell, Douglas L.
    [J]. ELECTRONICS, 2021, 10 (05) : 1 - 20
  • [10] Design Space Exploration for Architectural Synthesis-A Survey
    Shathanaa, R.
    Ramasubramanian, N.
    [J]. RECENT FINDINGS IN INTELLIGENT COMPUTING TECHNIQUES, VOL 2, 2018, 708 : 519 - 527