9 papers
Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Accelerators
Alaa Zniber, Arne Symons, Ouassim Karrakchou +2
Deployment of dynamic neural networks on edge accelerators requires careful consideration of hardware constraints beyond conventional complexity metrics such as Multiply-Accumulate…
MONET: Modeling and Optimization of neural NEtwork Training from Edge to Data Centers
Jérémy Morlier, Robin Geens, Stef Cuyckens +4
While hardware-software co-design has significantly improved the efficiency of neural network inference, modeling the training phase remains a critical yet underexplored challenge.…
Stream: Design Space Exploration of Layer-Fused DNNs on Heterogeneous Dataflow Accelerators
Arne Symons, Linyan Mei, Steven Colleman +3
As the landscape of deep neural networks evolves, heterogeneous dataflow accelerators, in the form of multi-core architectures or chiplet-based designs, promise more flexibility an…
Fine-Grained Fusion: The Missing Piece in Area-Efficient State Space Model Acceleration
Robin Geens, Arne Symons, Marian Verhelst
State Space Models (SSMs) offer a promising alternative to transformers for long-sequence processing. However, their efficiency remains hindered by memory-bound operations, particu…
Anda: Unlocking Efficient LLM Inference with a Variable-Length Grouped Activation Data Format
Chao Fang, Man Shi, Robin Geens +3
The widely-used, weight-only quantized large language models (LLMs), which leverage low-bit integer (INT) weights and retain floating-point (FP) activations, reduce storage require…
MATCH: Model-Aware TVM-based Compilation for Heterogeneous Edge Devices
Mohamed Amine Hamdi, Francesco Daghero, Giuseppe Maria Sarda +6
Streamlining the deployment of Deep Neural Networks (DNNs) on heterogeneous edge platforms, coupling within the same micro-controller unit (MCU) instruction processors and hardware…