Reading List
Curated resources for AI-driven Multi-Level Compilers — research papers, books, videos, and more.
Core MLIR Papers
MLIR: A Compiler Infrastructure for the End of Moore's Law
Foundational MLIR paper describing the motivation and architecture of multi-level IR.
Getting Started with MLIR
MLIR Main Website
Official MLIR project documentation and core infrastructure overview.
MLIR Getting Started
Practical introduction to MLIR concepts and basic workflow.
MLIR Toy Tutorial
End-to-end tutorial for building a toy language compiler with MLIR.
Lab Publications
DSP-MLIR: A Domain-Specific Language and MLIR Dialect for Digital Signal Processing
Abhinav Kumar, Atharva Khedkar, Hwisoo So, Megan Kuo, Ameya Gurjar, Partha Biswas, Aviral Shrivastava
MPS Lab work on DSL and MLIR dialect support for DSP workloads.
Prerequisites
Introduction to LLVM
Background on LLVM architecture and compiler pipeline fundamentals.
Recent Papers
UFront: Toward A Unified MLIR Frontend for Deep Learning
A recent effort to build a unified frontend stack for MLIR-based deep learning compilation.
RL-based Compilation
A Reinforcement Learning Environment for Automatic Code Optimization in the MLIR Compiler
Research direction on applying reinforcement learning to optimization pass decisions in MLIR.
Tooling
xDSL
A Python-native framework inspired by MLIR for rapid IR prototyping.