Toolboxes & Code Repositories
Stream
Tool for hardware-mapping design space exploration of deep learning accelerators
Description:
Stream is a HW architecture-mapping design space exploration (DSE) framework for multi-core deep learning accelerators. The mapping can be explored at different granularities, ranging from classical layer-by-layer processing to fine-grained layer-fused processing.
More Information:
Related research challenge: Situated AI
Responsible Research Lead: Marian Verhelst
Authors: Arne Symons, Linyan Mei, Steven Colleman, Pouya Houshmand, Sebastian Karl, Marian Verhelst
Programming Language: Python
Categories: Embedded systems, Optimization
Publications:
Towards Heterogeneous Multi-core Accelerators Exploiting Fine-grained Scheduling of Layer-Fused Deep Neural Networks (https://arxiv.org/pdf/2212.10612.pdf)