© The Institution of Engineering and Technology
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.
References
-
-
1)
-
11. Niki, Y., Kawasumi, A., Suzuki, A., et al: ‘A digitized replica bitline delay technique for random-variation-tolerant timing generation of SRAM sense amplifiers’, J. Solid-State Circuits, 2011, 46, (11), pp. 2545–2551 (doi: 10.1109/JSSC.2011.2164294).
-
2)
-
5. Kang, M., Yamaoka, M., Morimoto, M., et al: .
-
3)
-
9. Zhiting, L., Xiulong, W., Li, Z., et al: ‘A pipeline replica bitline technique for suppressing timing variation of SRAM sense amplifiers in a 28-nm CMOS process’, J. Solid-State Circuits, 2017, 52, (3), pp. 669–677 (doi: 10.1109/JSSC.2016.2634701).
-
4)
-
2. Elliott, D.G., Stumm, M., Snelgrove, W.M., et al: ‘Computational RAM: implementing processors in memory’, Design Test Comput., 1999, 16, (1), pp. 32–41 (doi: 10.1109/54.748803).
-
5)
-
7. Dong, Q., Jeloka, S., Saligane, M., et al: ‘A 4 + 2 T SRAM for searching and in-memory computing with 0.3-V VDDmin’, J. Solid-State Circuits, 2018, 53, (4), pp. 1006–1015 (doi: 10.1109/JSSC.2017.2776309).
-
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. 701–704.
-
7)
-
9. Amrutur, B.S., Horowitz, M.A.: ‘A replica technique for wordline and sense control in low-power sram's’, J. Solid-State Circuits, 1998, 33, (8), pp. 1208–1219 (doi: 10.1109/4.705359).
-
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. 8326–8330.
-
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. 224–225.
-
10)
-
13. Wu, J.H., Zhu, J.F., Xia, Y.C., et al: ‘A multiple-stage parallel replica-bitline delay addition technique for reducing timing variation of SRAM sense amplifiers’, IEEE Trans. Circuits Syst. II, Express Briefs, 2014, 61, (4), pp. 264–268 (doi: 10.1109/TCSII.2014.2304893).
-
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. 161–171.
-
12)
-
8. Agrawal, A., Jaiswal, A., Lee, C., et al: ‘Enabling in-memory Boolean computations in CMOS static random access memories’, Trans. Circuits Syst. I, 2018, 65, (12), pp. 4219–4232 (doi: 10.1109/TCSI.2018.2848999).
-
13)
-
6. Zhang, J., Wang, Z., Verma, N., et al: ‘In-memory computation of a machine-learning classifier in a standard 6 T SRAM array’, J. Solid-State Circuits, 2017, 52, (4), pp. 915–924 (doi: 10.1109/JSSC.2016.2642198).
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2019.2415
Related content
content/journals/10.1049/el.2019.2415
pub_keyword,iet_inspecKeyword,pub_concept
6
6