Skip to yearly menu bar Skip to main content


Tensor Program Optimization with Probabilistic Programs

Junru Shao · Xiyou Zhou · Siyuan Feng · Bohan Hou · Ruihang Lai · Hongyi Jin · Wuwei Lin · Masahiro Masuda · Cody Hao Yu · Tianqi Chen

Hall J (level 1) #702

Keywords: [ Tensor Program Optimization ] [ Machine Learning Compilation ] [ Probabilistic Programming ] [ Deep Learning Deployment ]


Automatic optimization for tensor programs becomes increasingly important as we deploy deep learning in various environments, and efficient optimization relies on a rich search space and effective search. Most existing efforts adopt a search space which lacks the ability to efficiently enable domain experts to grow the search space. This paper introduces MetaSchedule, a domain-specific probabilistic programming language abstraction to construct a rich search space of tensor programs. Our abstraction allows domain experts to analyze the program, and easily propose stochastic choices in a modular way to compose program transformation accordingly. We also build an end-to-end learning-driven framework to find an optimized program for a given search space. Experimental results show that MetaSchedule can cover the search space used in the state-of-the-art tensor program optimization frameworks in a modular way. Additionally, it empowers domain experts to conveniently grow the search space and modularly enhance the system, which brings 48% speedup on end-to-end deep learning workloads.

Chat is not available.