18 citations · 21 across the 2 of their papers we have counts for
3 papers · 1 filter
Tuna: A Static Analysis Approach to Optimizing Deep Neural Networks
Yao Wang, Xingyu Zhou, Yanming Wang +3
We introduce Tuna, a static analysis approach to optimizing deep neural network programs. The optimization of tensor operations such as convolutions and matrix multiplications is t…
Efficient Execution of Quantized Deep Learning Models: A Compiler Approach
Animesh Jain, Shoubhik Bhattacharya, Masahiro Masuda +2
A growing number of applications implement predictive functions using deep learning models, which require heavy use of compute and memory. One popular technique for increasing reso…
Optimizing CNN Model Inference on CPUs
Yizhi Liu, Yao Wang, Ruofei Yu +3
The popularity of Convolutional Neural Network (CNN) models and the ubiquity of CPUs imply that better performance of CNN model inference on CPUs can deliver significant gain to a…