SuperSonic, a new open-source framework to allow compiler developers to integrate RL into compilers easily, regardless of their RL expertise

Last update: Nov 28, 2022

Overview

Automating reinforcement learning architecture design for code optimization.

Check the website for more information.

Introduction

SUPERSONIC is a tool to automate reinforcement learning (RL) policy searching and tuning. It is designed to help compiler developers to find the right RL architecture and algorithm to use for an optimization task. It finds the right RL exploration algorithm, the reward function and a method for modeling the environment state.

Given an RL search space defined by the Supersonic Python API, the Supersonic meta-optimizer automatically searches for a suitable RL component composition for an optimization task. It also automatically tunes a set of tunable hyperparameters of the chosen components. No RL expertise is needed to use Supersonic.

Check our paper for detailed information.

Installation

Supersonic builds upon:

Python v3.8
CompilerGym
Ray

The system was tested on the following operating systems:

Ubuntu 18.04
Fedora 28
Debian 10

See INSTALL.md for further details.

Useage

See artifact_evaluation for an out-of-the-box demo of Supersonic.

Contributing

We welcome contributions to SuperSonic. If you are interested in contributing please see this document.

SuperSonic, a new open-source framework to allow compiler developers to integrate RL into compilers easily, regardless of their RL expertise

Related tags

Overview

Introduction

Installation

Useage

Contributing

Owner

RL algorithm PPO and IRL algorithm AIRL written with Tensorflow.

This repository contains all code and data for the Inside Out Visual Place Recognition task

A multi-entity Transformer for multi-agent spatiotemporal modeling.

Our VMAgent is a platform for exploiting Reinforcement Learning (RL) on Virtual Machine (VM) scheduling tasks.

Python wrappers to the C++ library SymEngine, a fast C++ symbolic manipulation library.

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

The Codebase for Causal Distillation for Language Models.

[ICCV 2021] Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

Code for "Learning the Best Pooling Strategy for Visual Semantic Embedding", CVPR 2021

Self-Supervised Monocular DepthEstimation with Internal Feature Fusion(arXiv), BMVC2021

VOneNet: CNNs with a Primary Visual Cortex Front-End

Unofficial keras(tensorflow) implementation of MAE model from Masked Autoencoders Are Scalable Vision Learners

Training data extraction on GPT-2

Source code for "Progressive Transformers for End-to-End Sign Language Production" (ECCV 2020)

Background Matting: The World is Your Green Screen

Fedlearn支持前沿算法研发的Python工具库 | Fedlearn algorithm toolkit for researchers

Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning

Official Implementation for "StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery" (ICCV 2021 Oral)

Learning Lightweight Low-Light Enhancement Network using Pseudo Well-Exposed Images

Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR