A Flexible In-Memory Computing Architecture for Heterogeneously Quantized CNNs
2021 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)(2021)
摘要
Inferences using Convolutional Neural Networks (CNNs) are resource and energy intensive. Therefore, their execution on highly constrained edge devices demands the careful co-optimization of algorithms and hardware. Addressing this challenge, in this paper we present a flexible In-Memory Computing (IMC) architecture and circuit, able to scale data representations to varying bitwidths at run-time, w...
更多查看译文
关键词
Degradation,Quantization (signal),Computer architecture,Parallel processing,Very large scale integration,Robustness,Inference algorithms
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