A 28nm CMOS subthreshold SRAM-based CIM macro for SNNs with in-situ regulation achieves 93.64% accuracy on keyword spotting, 1181.42 TOPS/W energy efficiency, and 7.24 TOPS/mm² density.
34.3 a 22nm 64kb lightning-like hybrid computing-in-memory macro with a compressed adder tree and analog-storage quantizers for transformer and CNNs,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A PVT-Resilient Subthreshold SRAM-Based In-Memory Computing Accelerator with In-Situ Regulation for Energy-Efficient Spiking Neural Networks
A 28nm CMOS subthreshold SRAM-based CIM macro for SNNs with in-situ regulation achieves 93.64% accuracy on keyword spotting, 1181.42 TOPS/W energy efficiency, and 7.24 TOPS/mm² density.