llvm / llvm/lighthouse

Integrate RL auto-tuner into Lighthouse

Open
#125 0 comments 3 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
55
Forks
19
Avg merge
1d 23h
Merged PRs (30d)
15

Description

As seen in MLIR workshop:
* https://llvm.swoogo.com/2026eurollvm/session/4050964/multi-stage-sequential-rl-for-mlir-meta-optimization

@prakanth97

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the linked MLIR workshop session to understand the proposed multi-stage sequential RL approach, then inspect Lighthouse's existing tuning entry points. The issue names no files or tests, so define the integration scope and success criteria before implementation; done should mean the agreed RL auto-tuner is integrated and demonstrably runs within Lighthouse.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
compilers, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.