Hardware Accelerator for Sparse Matrix-Matrix Multiplication (SpGEMM)

Lite Transformer is an efficient mobile NLP architecture. The key primitive is the Long-Short Range Attention (LSRA), where one group of heads specializes in the local context modeling (by convolution) while another group specializes in the long-distance relationship modeling (by attention).

PVCNN represents the 3D data in points to reduce the memory consumption, while performing the convolutions in voxels to reduce the irregular, sparse data access and improve the locality.

Deep Gradient Compression (DGC) reduces the communication bandwidth in the large-scale distributed training via four techniques: momentum correction, local gradient clipping, momentum factor masking, and warm-up training.

AutoML for Model Compression (AMC) leverages reinforcement learning to provide the model compression policy. This learning-based compression policy outperforms conventional rule-based compression policy by having higher compression ratio, better preserving the accuracy and freeing human labor.

We propose an energy efficient inference engine (EIE) that performs inference on this compressed network model and accelerates the resulting sparse matrix-vector multiplication with weight sharing.