ELSA is a near-SRAM dataflow architecture realizing elastic inference in SNNs via fine-grained spine/token pipelines, bundled AER, and mini-batch Gustavson products, delivering up to 3.4x speedup and 22.1x energy gains over SOTA accelerators on ResNet-50.
Spinalflow: An architecture and dataflow tailored for spiking neural networks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.AR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing
ELSA is a near-SRAM dataflow architecture realizing elastic inference in SNNs via fine-grained spine/token pipelines, bundled AER, and mini-batch Gustavson products, delivering up to 3.4x speedup and 22.1x energy gains over SOTA accelerators on ResNet-50.
-
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.