Leveraging Fine-grained Structured Sparsity for CNN Inference on Systolic Array Architectures
2021 31st International Conference on Field-Programmable Logic and Applications (FPL)(2021)
摘要
The high computational complexity of convolutional neural networks (CNNs) has motivated many studies of accelerating CNN inference on field-programmable gate arrays (FPGAs). Among these, designs that feature systolic arrays can effectively leverage the parallelism in CNNs while acheiving good placement and routing quality. Weight sparsity – the presence of zeros in CNN weights – can further reduce...
更多查看译文
关键词
Degradation,Computer architecture,Performance gain,Parallel processing,Routing,Systolic arrays,Convolutional neural networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要