AxNoC: Low-power Approximate Network-on-Chips using Critical-Path Isolation

被引:0
|
作者
Ben Ahmed, Akram [1 ]
Fujiki, Daichi [2 ]
Matsutani, Hiroki [1 ]
Koibuchi, Michihiro [3 ]
Amano, Hideharu [1 ]
机构
[1] Keio Univ, Yokohama, Kanagawa, Japan
[2] Univ Michigan, Ann Arbor, MI 48109 USA
[3] Natl Inst Informat, Tokyo, Japan
关键词
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Various parallel applications, such as numerical convergent computation and multimedia processing, have intrinsic tolerance to inaccuracies that allow soft errors, i.e. bit flips, on a chip. However, existing Network-on-Chips (NoCs) guarantee error-free data transfer; thus, encountering limits to reduce the power consumption. In this context, we propose an approximate dual-voltage NoC, called AxNoC. An AxNoC router uses a per-flit look-ahead power management so that headers and important-data flits are perfectly transferred at a high voltage while the remaining flits may incur bit flips by decreasing the supply voltage. An AxNoC router isolates the critical path when the supply voltage is low since such a critical path is enabled only at high voltage. The critical path isolation enables low-voltage operation to work at the same operating frequency at high voltage. An AxNoC router was implemented using a 28nm process and the evaluation results illustrate its efficiency to reduce the power consumption reaching up to 43% while incurring a small area overhead that does not exceed 6.2%. We also demonstrate that AxNoC exhibits an acceptable accuracy illustrated in a sufficiently small geomean of error.
引用
收藏
页数:8
相关论文
共 50 条
  • [21] ALGORITHMIC AND IMPLEMENTATION ISSUES IN ANALOG LOW-POWER LEARNING NEURAL-NETWORK CHIPS
    JABRI, M
    PICKARD, S
    LEONG, P
    XIE, Y
    JOURNAL OF VLSI SIGNAL PROCESSING, 1993, 6 (01): : 67 - 76
  • [22] Locate: Low-Power Viterbi Decoder Exploration using Approximate Adders
    Bhattacharjya, Rajat
    Maity, Biswadip
    Dutt, Nikil
    PROCEEDINGS OF THE GREAT LAKES SYMPOSIUM ON VLSI 2023, GLSVLSI 2023, 2023, : 409 - 413
  • [23] A low-power digital filter for decimation and interpolation using approximate processing
    Pan, CJ
    1997 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE - DIGEST OF TECHNICAL PAPERS, 1997, 40 : 102 - 103
  • [24] Low-Power Design Methodology of Voltage Over-Scalable Circuit with Critical Path Isolation and Bit-Width Scaling
    Masuda, Yutaka
    Nagayama, Jun
    Cheng, TaiYu
    Ishihara, Tohru
    Momiyama, Yoichi
    Hashimoto, Masanori
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2022, E105A (03) : 509 - 517
  • [25] FinFET-based Low-Power Approximate Multiplier for Neural Network Hardware Accelerator
    Baraati, Faraz
    Nasab, Milad Tanavardi
    Ghaderi, Reza
    Jafari, Kian
    2022 IRANIAN INTERNATIONAL CONFERENCE ON MICROELECTRONICS, IICM, 2022, : 17 - 20
  • [26] Low-Power FPGA Design Using Memoization-Based Approximate Computing
    Sinha, Sharad
    Zhang, Wei
    IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2016, 24 (08) : 2665 - 2678
  • [27] Design and Analysis of Low-Power and High Speed Approximate Adders Using CNFETs
    Bhargav, Avireni
    Huynh, Phat
    SENSORS, 2021, 21 (24)
  • [28] Low-Power High-Accuracy Approximate Multiplier Using Approximate High-Order Compressors
    Tung, Che-Wei
    Huang, Shih-Hsu
    PROCEEDINGS OF 2019 2ND INTERNATIONAL CONFERENCE ON COMMUNICATION ENGINEERING AND TECHNOLOGY (ICCET 2019), 2019, : 163 - 167
  • [29] Low-Power Approximate Multiplier With Error Recovery Using a New Approximate 4-2 Compressor
    Strollo, Antonio G. M.
    De Caro, Davide
    Napoli, Ettore
    Petra, Nicola
    Di Meo, Gennaro
    2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [30] Bus optimization for low-power data path synthesis based on network flow method
    Hong, S
    Kim, T
    ICCAD - 2000 : IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, 2000, : 312 - 317