The workshop aims to bring together LLVM contributors and researchers that work on applying Artificial Intelligence or Machine Learning techniques to LLVM. Topics include: integration of agent-based workflows with or through LLVM, compiler optimizations, latency estimation, IR comprehension, code generation, or data set curation (to name a few). The goal is to discuss ongoing projects and explore ways to better collaborate and plot pathways for integration to LLVM.
Half-day workshop
8:30 – 9:00 AM | Using AI in LLVM Development or: Why AI Isn’t Going to Take Your Job
Andy Kaylor
9:00 – 9:15 AM | Craniumlift in Practice: Lessons from Google Hackathon and the Path Toward LLVM
Emily Qin, Ashna Nayak
9:15 – 9:30 AM | Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering
Amir Ashouri
9:30 – 9:45 AM | AI Discovered Feasible and Profitable Interprocedural BB Reordering in Peak-Optimized Production Binaries
Chaitanya Mamatha Ananda
9:45 – 10:00 AM | MLGO + EmitC is now live!
Ioana Ghiban, Bhavesh Mandalapu
10:00 – 10:30 AM | Break
10:30 AM – 12:30 PM | Unconference
12:30 – 1:00 PM | Lunch