An NVM Non-Idealities Mitigation Solution Using Cell-Clustered Calibration for Analog High-Density Edge Multi-Level Cell Compute-in-Memory

Multi-level cell (MLC) non-volatile memory (NVM) has become a promising candidate for compute-in-memory (CiM) designs because of its non-volatility, high density, and improving CMOS compatibility. However, most MLC NVMs suffer from device non-idealities, including large variation, low on/off ratio, and read disturb, which compromise the computational accuracy, reliability, and throughput of MLC NVM-based CiMs. To alleviate the impact of these non-idealities, this work proposes a comprehensive mitigation solution, providing a new paradigm for achieving high-density MLC NVM-based CiM. Without loss of generality, MLC RRAM and STT-MRAM are taken as examples for design and evaluation in this paper. The highlight of the solution is the proposed cell-clustered computing paradigm with local recovery units (LRUs), which enables highly reliable local calibration and efficient in-memory computing. Besides, a dynamic boundary adaption technique is explored to restore the accuracy loss due to the RRAM state drift, and a segmented adaptive LRU configuration approach is proposed to improve the variation and temperature resilience of the MRAM-based design. Results show that the RRAM-based design achieves 152.3TOPS/W energy efficiency and improves the compute and storage density by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$37.0\times $</tex-math> </inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$131.3\times $</tex-math> </inline-formula> with 91.4% inference accuracy under 20% variation compared with the state-of-the-art (SOTA) MLC RRAM-CiM using on-chip write-and-verify. The MRAM counterpart achieves 182.0TOPS/W energy efficiency, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2.7\times $</tex-math> </inline-formula> compute density, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$253.6\times $</tex-math> </inline-formula> storage density and 91.5% inference accuracy under 4% variation compared with the SOTA differential offset cancellation MLC MRAM-CiM. The performance reveals the significantly improved balance of the proposed MLC CiM between efficiency, density, and accuracy.