Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Guangli Li

Guangli Li

Pinpointing the Memory Behaviors of DNN Training

Apr 01, 2021
Jiansong Li, Xiao Dong, Guangli Li, Peng Zhao, Xueying Wang, Xiaobing Chen, Xianzhi Yu, Yongxin Yang, Zihan Jiang, Wei Cao, Lei Liu, Xiaobing Feng

Figure 1 for Pinpointing the Memory Behaviors of DNN Training

Figure 2 for Pinpointing the Memory Behaviors of DNN Training

Figure 3 for Pinpointing the Memory Behaviors of DNN Training

Figure 4 for Pinpointing the Memory Behaviors of DNN Training

* Submitted to ISPASS'21 poster

Access Paper or Ask Questions

Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

Oct 30, 2020
Guangli Li, Xiu Ma, Xueying Wang, Lei Liu, Jingling Xue, Xiaobing Feng

Figure 1 for Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

Figure 2 for Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

Figure 3 for Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

Figure 4 for Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

* Published in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)

Access Paper or Ask Questions

LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

Mar 20, 2020
Guangli Li, Lei Liu, Xueying Wang, Xiu Ma, Xiaobing Feng

Figure 1 for LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

Figure 2 for LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

Figure 3 for LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

Figure 4 for LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units

* Accepted by ICASSP 2020

Access Paper or Ask Questions

LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

Mar 19, 2020
Guangli Li, Lei Liu, Xueying Wang, Xiu Ma, Xiaobing Feng

Figure 1 for LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

Figure 2 for LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

Figure 3 for LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

Figure 4 for LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units

* Accepted by ICASSP 2020

Access Paper or Ask Questions

Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Dec 16, 2018
Guangli Li, Lei Liu, Xueying Wang, Xiao Dong, Peng Zhao, Xiaobing Feng

Figure 1 for Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Figure 2 for Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Figure 3 for Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

Figure 4 for Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge

* Published at ICANN 2018

Access Paper or Ask Questions