VSCNN: Convolution Neural Network Accelerator With Vector Sparsity

Abstract

Hardware accelerator for convolution neural network (CNNs) enables real time applications of artificial intelligence technology. However, most of the accelerators only support dense CNN computations or suffers complex control to support fine grained sparse networks. To solve above problem, this paper presents an efficient CNN accelerator with 1-D vector broadcasted input to support both dense network as well as vector sparse network with the same hardware and low overhead. The presented design achieves 1.93X speedup over the dense CNN computations.

arXiv comment5 pages, 13 figures, published in IEEE ISCAS 2019

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Text-Attentional Convolutional Neural Networks for Scene Text Detection
• Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
• Deep convolutional neural networks for pedestrian detection
• SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks

Cited by in corpus (2)

• RNNFast: An Accelerator for Recurrent Neural Networks Using Domain Wall Memory
• A Real Time 1280x720 Object Detection Chip With 585MB/s Memory Traffic