libxsmm/tpp-mlir

TPP experimentation on MLIR for linear algebra

57
/ 100
Established

This project helps high-performance computing (HPC) and deep learning engineers optimize linear algebra operations. It takes in MLIR-based code and outputs highly optimized kernels that run efficiently on various CPU architectures. The ideal user is a system or performance engineer working on machine learning compilers or HPC libraries.

146 stars.

Use this if you are a system engineer or compiler developer looking to experiment with automatically selecting the best Tensor Processing Primitives for linear algebra within an MLIR framework to achieve higher performance.

Not ideal if you are an application developer simply looking to use an existing machine learning framework or library, as this is a low-level compiler infrastructure project.

compiler-development high-performance-computing deep-learning-optimization linear-algebra system-programming
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

146

Forks

38

Language

MLIR

License

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/libxsmm/tpp-mlir"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.