Battery-powered tiny-AI edge devices require large-capacity nonvolatile compute-in-memory (nvCIM), with multibit input (IN), weight (W), and output (OUT) precision to support complex applications, high-energy efficiency (EF MAC ), and short computing latency (t AC ) for multiply-and-accumulate (M AC ) operations. Due to the low read-disturb-free voltage of nonvolatile memory (NVM) devices and the large parasitic load on the bitline, most existing Mb-level nvCIM macros use a current-mode read scheme [1-5] and only achieve a low IN-W precision (binary to 4b).
No takes yet. Share an insight, caveat, or question.
Xue et al. (2021) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: