3 papers
cs.AR2026
ETHEREAL: A 25.6-s/inf. Low-latency Event-driven Graph-neural-network Processor for High-resolution Vision at the Edge
Adrian Kneip, Martin Lefebvre, Daniel Gehrig +4
Dynamic vision sensors (DVS) are enticing candidates to reach the low-latency, sub-ms target of edge-vision applications, as they generate events with a s-level time resolution.…
cs.AR2024
IMAGINE: An 8-to-1b 22nm FD-SOI Compute-In-Memory CNN Accelerator With an End-to-End Analog Charge-Based 0.15-8POPS/W Macro Featuring Distribution-Aware Data Reshaping
Adrian Kneip, Martin Lefebvre, Pol Maistriaux +1
Charge-domain compute-in-memory (CIM) SRAMs have recently become an enticing compromise between computing efficiency and accuracy to process sub-8b convolutional neural networks (C…
cs.AR2024
An Event-Based Digital Compute-In-Memory Accelerator with Flexible Operand Resolution and Layer-Wise Weight/Output Stationarity
Nicolas Chauvaux, Adrian Kneip, Christoph Posch +2
Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) are promising solutions to enable s-level inference latency and ultra-low energy in edge vision applicati…