E-ReCON presents a precision-configurable sparse nvCIM macro with 3T1R ReRAM bitcells and interleaved 10T/28T adder tree achieving up to 419 TOPS/W for both conventional and spiking neural edge inference.
Efficient and robust nonvolatile computing-in- memory based on voltage division in 2T2R RRAM with input-dependent sensing control,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
E-ReCON: An Energy- and Resource-Efficient Precision-Configurable Sparse nvCIM Macro for Conventional and Spiking Neural Edge Inference
E-ReCON presents a precision-configurable sparse nvCIM macro with 3T1R ReRAM bitcells and interleaved 10T/28T adder tree achieving up to 419 TOPS/W for both conventional and spiking neural edge inference.