access icon free Current mirror-based compensation circuit for multi-row read in-memory computing

Multi-row read plays an important role in in-memory computing and its precision affects the accuracy of the calculation. In this brief Letter, a discharge compensation method is proposed for the linearisation of multi-row read operations in static RAM. Current mirrors are added to bitlines to compensate for the discharge voltage. With compensation, the integral non-linearity decreases by 72% compared with the situation without compensation. In addition, a wordline signal generation circuit based on replica bitline is proposed to reduce area cost.

Inspec keywords: signal generators; SRAM chips; current mirrors; compensation

Other keywords: static RAM; integral nonlinearity; current mirrors; discharge compensation method; multi-row read in-memory computing; multirow read operations; current mirror-based compensation circuit; discharge voltage; wordline signal generation circuit

Subjects: Amplifiers; Signal generators; Memory circuits; Semiconductor storage

References

    1. 1)
    2. 2)
      • 5. Kang, M., Yamaoka, M., Morimoto, M., et al: ‘A 481pJ/decision 3.4M decision/s Multifunctional Deep In-memory Inference Processor using Standard 6 T SRAM Array’, arXiv Preprint, 2016, https://arxiv.org/abs/1610.07501.
    3. 3)
    4. 4)
    5. 5)
    6. 6)
      • 10. Komatsu, S., et al: ‘A 40-nm low-power SRAM with multi-stage replica-bitline technique for reducing timing variation’. IEEE Custom Integrated Circuits Conf., Rome, Italy, September 2009, pp. 701704.
    7. 7)
    8. 8)
      • 4. Kang, M., Keel, M.-S., Shanbhag, N.R., et al: ‘An energy-efficient VLSI architecture for pattern recognition via deep embedding of computation in SRAM’. Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP 2014), Florence, Italy, May 2014, pp. 83268330.
    9. 9)
      • 1. Patterson, D., Anderson, T., Cardwell, N., et al: ‘Intelligent RAM (IRAM): chips that remember and compute’. IEEE Int. Solid-state Circuits Conf., San Francisco, CA, USA, February 1997, pp. 224225.
    10. 10)
    11. 11)
      • 3. Mai, K., Paaske, T., Jayasena, N., et al: ‘Smart memories: a modular reconfigurable architecture’. Int. Symp. on Computer Architecture, Vancouver, BC, Canada, June 2000, pp. 161171.
    12. 12)
    13. 13)
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2019.2415
Loading

Related content

content/journals/10.1049/el.2019.2415
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading