ABSTRACT
The ANDANTE project aims to tackle the hardware/software co-design challenge that arises from the development of novel (neuromorphic) edge-AI accelerators. For this purpose, Fraunhofer IIS and EMFT among other partners developed several tools to facilitate design, training and deployment of artificial neural networks in dedicated hardware accelerators. These tools provide hardware-aware training, automatic hardware generation, compilers, estimation of KPIs like energy consumption, and simulation under consideration of the constraints imposed by the targeted hardware implementation and use cases. The development of such a tool chain is a multidisciplinary effort combining neural network algorithm design, software development and integrated circuit design. We show how such a toolchain allows to optimize and verify the hardware design, reach the targeted KPIs, and reduce the time-to-market.
