Today we’re announcing Meta LLM Compiler, a family of models built on Meta Code Llama with additional code optimization and compiler capabilities. These models can emulate the compiler, predict ...

Meta's research team built a model based on the Code Llama model , training it on a corpus of compiler intermediate representations and assembly code totaling 546 billion tokens to create a model ...

LLVM-based optimization framework for analyzing and transforming IR using compiler techniques and ML-inspired heuristics. Includes a custom Memory Coalescing pass for GPU-style memory access ...

Tuning compiler heuristics and parameters is well known to improve optimization outcomes dramatically. Prior works have tuned command line flags and a few expert identified heuristics. However, there ...