IITH-Compilers/IR2Vec
Implementation of IR2Vec, LLVM IR Based Scalable Program Embeddings
This project helps compiler engineers convert source code into numerical representations, known as embeddings. You feed it an LLVM Intermediate Representation (IR) file, and it outputs a vector of numbers that captures the program's structure and behavior. This is useful for feeding program information into machine learning models to solve tasks like code optimization or bug detection. It's designed for compiler developers and researchers working with program analysis.
101 stars.
Use this if you need to represent LLVM IR code as numerical vectors for machine learning tasks within compiler design or program analysis.
Not ideal if you are an application developer looking to analyze high-level source code directly, or if you need to generate embeddings for languages not supported by LLVM IR.
Stars
101
Forks
43
Language
LLVM
License
—
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/IITH-Compilers/IR2Vec"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
shibing624/text2vec
text2vec, text to vector....
predict-idlab/pyRDF2Vec
đ Python Implementation and Extension of RDF2Vec
IntuitionEngineeringTeam/chars2vec
Character-based word embeddings model based on RNN for handling real world texts
ddangelov/Top2Vec
Top2Vec learns jointly embedded topic, document and word vectors.
natasha/navec
Compact high quality word embeddings for Russian language