An Area-Efficient Consolidated Configurable Error Correction for Approximate Hardware Accelerators

被引:8
|
作者
Mazahir, Sana [1 ]
Hasan, Osman [1 ]
Hafiz, Rehan [2 ]
Shafique, Muhammad [3 ]
Henkel, Joerg [3 ]
机构
[1] Natl Univ Sci & Technol, Sch Elect Engn & Comp Sci, Islamabad, Pakistan
[2] Informat Technol Univ, Dept Elect Engn, Lahore, Pakistan
[3] Karlsruhe Inst Technol, Chair Embedded Syst, D-76021 Karlsruhe, Germany
关键词
D O I
10.1145/2897937.2897981
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Approximate adders are widely being advocated for developing hardware accelerators to perform complex arithmetic operations. Most of the state-of-the-art accuracy configurable approximate adders utilize some integrated Error Detection and Correction (EDC) circuitry. Consequently, the accumulated area overhead due to the EDC (integrated within individual adders) is significant. In this paper, we propose a low-cost Consolidated Error Correction (CEC) unit, that essentially corrects the accumulated error at the accelerator output. The proposed CEC is based on a mathematical model of approximation error. We integrate our CEC unit in approximate hardware accelerators deployed in different applications to demonstrate its area savings and speed enhancement compared to state-of-the-art.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] An Energy- and Area-Efficient Approximate Ternary Adder Based on CNTFET Switching Logic
    Narges Hajizadeh Bastani
    Mohammad Hossein Moaiyeri
    Keivan Navi
    Circuits, Systems, and Signal Processing, 2018, 37 : 1863 - 1883
  • [42] SOMALib : Library of Exact and Approximate Activation Functions for Hardware-efficient Neural Network Accelerators
    Prashanth, H. C.
    Rao, Madhav
    2022 IEEE 40TH INTERNATIONAL CONFERENCE ON COMPUTER DESIGN (ICCD 2022), 2022, : 746 - 753
  • [43] An Energy- and Area-Efficient Approximate Ternary Adder Based on CNTFET Switching Logic
    Bastani, Narges Hajizadeh
    Moaiyeri, Mohammad Hossein
    Navi, Keivan
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2018, 37 (05) : 1863 - 1883
  • [44] Hardware -Efficient FPGA-Based. Approximate Multipliers for Error -Tolerant Computing
    Yao, Shangshang
    Zhang, Liang
    2022 21ST INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT 2022), 2022, : 20 - 27
  • [45] Area-Optimized Low-Latency Approximate Multipliers for FPGA-based Hardware Accelerators
    Ullah, Salim
    Rehman, Semeen
    Prabakaran, Bharath Srinivas
    Kriebel, Florian
    Hanif, Muhammad Abdullah
    Shafique, Muhammad
    Kumar, Akash
    2018 55TH ACM/ESDA/IEEE DESIGN AUTOMATION CONFERENCE (DAC), 2018,
  • [46] Area, Time and Energy Efficient Multicore Hardware Accelerators for Extended Merkle Signature Scheme
    Cao, Yuan
    Wu, Yanze
    Qin, Lan
    Chen, Shuai
    Chang, Chip-Hong
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 2022, 69 (12) : 4908 - 4918
  • [47] High-throughput, area-efficient hardware architecture of CABAC-Binarization for UHD applications
    Nagaraju, Mamidi
    Gupta, Santosh Kumar
    Bhadauria, Vijaya
    MICROELECTRONICS JOURNAL, 2022, 123
  • [48] Hardware Realization of High-Speed Area-Efficient Floating Point Arithmetic Unit on FPGA
    Yacoub, Mohammed H.
    Ismail, Samar M.
    Said, Lobna A.
    2024 INTERNATIONAL CONFERENCE ON MACHINE INTELLIGENCE AND SMART INNOVATION, ICMISI 2024, 2024, : 190 - 193
  • [49] An Area-Efficient Hardware Implementation for Real-time Window-based Image Filtering
    Javadi, M. H. Seyed
    Rafi, H.
    Tabatabaei, S.
    Haghighat, A. T.
    SITIS 2007: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON SIGNAL IMAGE TECHNOLOGIES & INTERNET BASED SYSTEMS, 2008, : 515 - 519