Huawei Li

TL;DR: A design automation tool allowing the application developers to build from scratch learning accelerators that targets their specific NN models with custom configurations and optimized performance, and greatly simplifies the design flow of NN accelerators for the machine learning or AI application developers.

TL;DR: The abacus-turn-model (AbTM) is proposed for designing time/space-efficient reconfigurable wormhole routing algorithms and its applicability with scalable performance in large-scale NoC applications is proved.

TL;DR: In this paper, the authors propose to achieve fault tolerance by employing redundancy at the core level instead of at the micro-architecture level, which not only maximizes the performance of the on-chip communication scheme, but also provides a unified topology to operating system and application software running on the processor.

TL;DR: The proposed EnGN is designed to accelerate the three key stages of GNN propagation, which is abstracted as common computing patterns shared by typical GNNs, and proposes the ring-edge-reduce(RER) dataflow that tames the poor locality of sparsely-and-randomly connected vertices, and the RER PE-array to practice RER dataflow.

TL;DR: EnGN as discussed by the authors proposes a specialized accelerator architecture to accelerate the three key stages of GNN propagation, which is abstracted as common computing patterns shared by typical GNNs, and uses graph tiling strategy to fit large graphs into EnGN and make good use of the hierarchical onchip buffers through adaptive computation reordering and tile scheduling.