MOSDA: On-Chip Memory Optimized Sparse Deep Neural Network Accelerator With Efficient Index Matching

The irregular data access pattern caused by sparsity brings great challenges to efficient processing accelerators. Focusing on the index-matching property in DNN, this article aims to decompose sparse DNN processing into easy-to-handle processing tasks to maintain the utilization of processing elements. According to the proposed sparse processing dataflow, this article proposes an efficient general-purpose hardware accelerator called MOSDA, which can be effectively applied for operations of convolutional layers, fully-connected layers, and matrix multiplications. Compared to the state-of-art CNN accelerators, MOSDA achieves 1.1 \times better throughput and 2.1 \times better energy efficiency than Eyeriss v2 in sparse Alexnet in our case study.