Objectives
Objective 1
Achieve multi-level functionality in hafnia-based thin films by investigating the trade-off in memory window, film thickness & stability of the ferroelectric state.
The success of the project will be measured by the achievement of five specific objectives, each tightly linked to project work on one part of the value chain, starting from materials optimisation, running through devices design and characterisation, array integration to accelerator prototype and finally specific AI systems simulations.
Objective 2
Achieve low operating voltage for the NVM and robust ML operation of the FeFET-2 for high density logic operations and data storage. A low operating voltage is mandatory for power rating reduction, while robust low power ML operation is necessary for analogue inference at the edge.
Objective 4
Define, design, build and demonstrate a low power, scalable, ferroelectric AI accelerator suitable for scalable systems integration.
Objective 3
Back-End of Line design, fabrication and characterisation of multi-level, low voltage, FeFET-2 arrays.
Objective 5
Systems simulation of ultra-low power ferroelectric accelerator enhanced edge processing for voice and image recognition.
