SUPERSONIC is a toolkit for applying reinforcement learning to compiler optimizations.

User Guide

• Getting Started
• About
• Frequently Asked Questions

Python API Reference

• SuperSonic.TasksDefinition
  • SuperOptimizer
  • RLAlgorithms
  • action_functions
  • observation_function
  • reward_function
• SuperSonic.policy_search
  • PolSearch_main
• SuperSonic.utils
  • TaskEngine
  • Optimizing Image Pipelines
  • Neural Network Code Generation Reduction
  • Code Size
  • Superoptimization
  • Optimizing Image Pipelines RL Environments
  • Neural Network Code Generation Reduction RL Environments
  • Code Size Reduction RL Environments
  • Superoptimization RL Environments

Tutorial Reference

• Tutorial.Halide.Env_register
  • HalideEnv
  • BanditHalideEnv
• Tutorial.AutoTvm.Env_register
  • TvmEnv
  • BanditTvmEnv
• Tutorial.CSR.Env_register
  • BanditCSREnv
• Tutorial.Stoke.Env_register
  • StokeEnv
  • BanditStokeEnv

Indices and tables

• Index

• Module Index

• Search Page