TY - GEN
T1 - Victor
T2 - 60th ACM/IEEE Design Automation Conference, DAC 2023
AU - Lee, Mingyen
AU - Tang, Wenjun
AU - Chen, Yiming
AU - Wu, Juejian
AU - Zhong, Hongtao
AU - Xu, Yixin
AU - Liu, Yongpan
AU - Yang, Huazhong
AU - Narayanan, Vijaykrishnan
AU - Li, Xueqing
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Multi-level cell (MLC) NVM-based CiM has become a promising candidate in computing-in-memory (CiM) designs because of its non-volatility, high cell density, and improving compatibility with the CMOS process. However, most MLC CiM faces the challenges of non-ideal device limitations, including the low on/off ratio, large device-to-device variations, and read disturbances, which limit the computing accuracy, reliability, and throughput performance. This work proposes Victor, a variation-resilient approach using cell-clustered charge-domain computing for high-density and high-throughput MLC CiM. A cell-clustered-computing with local recovery unit (LRU) design methodology is proposed to improve matrix-vector-multiplication (MVM) reliability and throughput. To showcase the capability of Victor, 2b-4b MLC Resistive RAM (RRAM) is taken as an example for design and evaluation. Results show that Victor reaches 3.56x energy efficiency, 4x variation tolerance compared with the prior ratio-based MLC CiM. In addition, the throughput is improved by 3.1x with less than 1% DNN accuracy loss. Moreover, a dynamic boundary adaption approach is proposed to restore the accuracy loss of state drifting, which in return reduces the energy and latency overhead by 100x and 1.25x, respectively, compared with the conventional write-and-verify approach.
AB - Multi-level cell (MLC) NVM-based CiM has become a promising candidate in computing-in-memory (CiM) designs because of its non-volatility, high cell density, and improving compatibility with the CMOS process. However, most MLC CiM faces the challenges of non-ideal device limitations, including the low on/off ratio, large device-to-device variations, and read disturbances, which limit the computing accuracy, reliability, and throughput performance. This work proposes Victor, a variation-resilient approach using cell-clustered charge-domain computing for high-density and high-throughput MLC CiM. A cell-clustered-computing with local recovery unit (LRU) design methodology is proposed to improve matrix-vector-multiplication (MVM) reliability and throughput. To showcase the capability of Victor, 2b-4b MLC Resistive RAM (RRAM) is taken as an example for design and evaluation. Results show that Victor reaches 3.56x energy efficiency, 4x variation tolerance compared with the prior ratio-based MLC CiM. In addition, the throughput is improved by 3.1x with less than 1% DNN accuracy loss. Moreover, a dynamic boundary adaption approach is proposed to restore the accuracy loss of state drifting, which in return reduces the energy and latency overhead by 100x and 1.25x, respectively, compared with the conventional write-and-verify approach.
UR - http://www.scopus.com/inward/record.url?scp=85173117998&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85173117998&partnerID=8YFLogxK
U2 - 10.1109/DAC56929.2023.10247934
DO - 10.1109/DAC56929.2023.10247934
M3 - Conference contribution
AN - SCOPUS:85173117998
T3 - Proceedings - Design Automation Conference
BT - 2023 60th ACM/IEEE Design Automation Conference, DAC 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 9 July 2023 through 13 July 2023
ER -