Recently, multi-bit slicing has emerged as a promising technique to improve the energy efficiency of charge-domain Compute-In-Memory (CIM) accelerators by reducing the number of Analog-to-Digital (A/D) conversions. However, multi-bit slicing requires shift-and-add operations to reconstruct outputs, which exponentially amplify errors and cause significant accuracy degradation. Existing works mainly rely on hardware-aware retraining or noise-suppression techniques, incurring considerable design or power overhead. Thus, multi-bit CIM designs often face the dilemma of trading off energy efficiency for error resilience.

In this paper, we propose BASES, a charge-domain multibit CIM accelerator that achieves both high energy efficiency and strong error resilience, without requiring retraining. The core insight is that the error amplification is proportional to digit weights; and by redefining these digit weights with smaller non-binary coding bases, it is possible to reduce the total error amplification. Leveraging this principle, BASES dynamically selects the minimal coding bases for every analog dot-product. With novel circuit and architectural support, BASES enables fast, low-overhead reconfiguration of coding bases at runtime. Experimental results show that BASES achieves 2.27× energy efficiency and 3.06× performance over RAELLA, a state-of-theart error-resilient multi-bit slicing CIM architecture.