Pipeline Design of Nonvolatile-based Computing in Memory for Convolutional Neural Networks Inference Accelerators

Nonvolatile-based computing-in-memory inference chips show great potential to accelerate convolutional neural networks. The intrinsic weight stationary characteristic makes pipeline design a crucial solution to further enhance throughput. In this work, we propose a balanced pipeline design and establish performance/area evaluation models for the optimal pipeline solution. The evaluation results indicate that our pipeline design achieves
$30\times$
computational efficiency improvement.