1. SPRING: A Sparsity-Aware Reduced-Precision Monolithic 3D CNN Accelerator Architecture for Training and Inference
- Author
-
Ye Yu and Niraj K. Jha
- Subjects
FOS: Computer and information sciences ,Computational complexity theory ,Computer science ,02 engineering and technology ,01 natural sciences ,Convolutional neural network ,Bottleneck ,Hardware Architecture (cs.AR) ,0103 physical sciences ,0202 electrical engineering, electronic engineering, information engineering ,Computer Science (miscellaneous) ,Computer Science - Hardware Architecture ,010302 applied physics ,business.industry ,Deep learning ,Memory bandwidth ,020202 computer hardware & architecture ,Computer Science Applications ,Human-Computer Interaction ,Computer engineering ,Memory footprint ,Hardware acceleration ,Artificial intelligence ,Performance improvement ,business ,Information Systems - Abstract
CNNs outperform traditional machine learning algorithms across a wide range of applications. However, their computational complexity makes it necessary to design efficient hardware accelerators. Most CNN accelerators focus on exploring dataflow styles that exploit computational parallelism. However, potential performance speedup from sparsity has not been adequately addressed. The computation and memory footprint of CNNs can be significantly reduced if sparsity is exploited in network evaluations. To take advantage of sparsity, some accelerator designs explore sparsity encoding and evaluation on CNN accelerators. However, sparsity encoding is just performed on activation or weight and only in inference. It has been shown that activation and weight also have high sparsity levels during training. Hence, sparsity-aware computation should also be considered in training. To further improve performance and energy efficiency, some accelerators evaluate CNNs with limited precision. However, this is limited to the inference since reduced precision sacrifices network accuracy if used in training. In addition, CNN evaluation is usually memory-intensive, especially in training. In this paper, we propose SPRING, a SParsity-aware Reduced-precision Monolithic 3D CNN accelerator for trainING and inference. SPRING supports both CNN training and inference. It uses a binary mask scheme to encode sparsities in activation and weight. It uses the stochastic rounding algorithm to train CNNs with reduced precision without accuracy loss. To alleviate the memory bottleneck in CNN evaluation, especially in training, SPRING uses an efficient monolithic 3D NVM interface to increase memory bandwidth. Compared to GTX 1080 Ti, SPRING achieves 15.6X, 4.2X and 66.0X improvements in performance, power reduction, and energy efficiency, respectively, for CNN training, and 15.5X, 4.5X and 69.1X improvements for inference.
- Published
- 2022