Autotuning Production Machine Learning Compilers | SAMPL Talk 2021/11/04

SAMPL Talk 2021/11/04 Title: Autotuning Production Machine Learning Compilers Speaker: Mangpo Phothilimthana(Google Brain) Abstract: Search-based techniques have been demonstrated effective in solving complex optimization problems that arise in domain-specific compilers for machine learning (ML). Unfortunately, deploying such techniques in production compilers is impeded by several limitations. In this talk, I will present an autotuner for production ML compilers that can tune both graph-level and subgraph-level optimizations at multiple compilation stages. The autotuner applies a flexible search methodology that defines a search formulation for joint optimizations by accurately modeling the interactions between different compiler passes. The autotuner tunes tensor layouts, operator fusion decisions, tile sizes, and code generation parameters in XLA, a production ML compiler, using various search strategies. We demonstrate how to incorporate machine learning techniques such as a learned co