Study on Deep Learning Automatic Scheduling Optimization Based on Feature Importance
With the rapid development of deep learning and hardware architectures,the diversity of models and hardware architec-tures make the deployment for deep learning models with high performance manually become increasingly challenging.So current Al compiler framework often adopts automatic scheduling.Since the existing optimization to TVM automatic scheduling has such issues as unbalanced data sets in cost model and overlong scheduling time,an automatic scheduling optimization strategy based on feature importance is designed in this paper.First,the feature importance is analyzed through the xgboost algorithm.Then a stra-tegy that reduce the data feature dimensions based on the importance coefficient and reassign the data labels is adopted to improve the precision of the cost model and optimize the efficiency of the automatic scheduling.Experiment results show that the proposed optimization method can reduce the automatic scheduling time of three kinds of deep learning models by 9.7％～17.2％,and re-duce the inference time by up to 15％.
AI compilerAutomatic schedulingxgboostFeature importanceDeep learning
NETL
NSTL
万方数据
