[C79] Row-Column Hybrid Grouping for Fault-Resilient Multi-Bit Weight Representation on IMC Arrays

Abstract

This paper addresses two critical challenges in analog Compute-in-Memory (CIM) systems: the computational unreliability caused by stuck-at faults (SAFs) and the high compilation overhead of existing fault-mitigation algorithms, namely Fault-Free (FF). These challenges collectively limit the scalability and deployability of CIM systems. To overcome these limitations, we first propose a novel multi-bit weight representation technique, termed row–column hybrid grouping, which generalizes conventional column grouping by introducing redundancy across both rows and columns. This structural redundancy enhances fault tolerance and can be effectively combined with existing fault-mitigation solutions. Second, we design a compiler pipeline that reformulates the fault-aware weight decomposition problem as an Integer Linear Programming (ILP) task, enabling fast and scalable compilation through off-the-shelf solvers. Further acceleration is achieved through theoretical insights that identify fault patterns amenable to trivial solutions, significantly reducing computation. Experimental results on convolutional networks and small language models demonstrate the effectiveness of our approach, achieving up to 8 percentage point improvement in accuracy, 150× faster compilation, and 2× energy efficiency gain compared to existing baselines.