SIMD-Microkernels-for-ML-Workloads Mattral · COMPLETED
open-source C++17 library of clean, well-documented hand-vectorized microkernels for core ML primitives. It deliberately occupies the middle ground between toy textbook code and opaque production BLAS: production techniques (panel packing, register blocking, software prefetching)
github.com/Mattral/SIMD-Microkernels-for-ML-Workloads · ★ 15 · Forks 5 · Size 3.5 MB
SUMMARY
Technologies 12
Scored 12
Observed 12
Practices 6
Evidence 13
Skips 0
COVERAGE
Analyzed 75 files · 203 commits · 0 API calls
TECHNOLOGIES & DEPTH
Dockerfile LANGUAGE Depth 70
1 files · PRODUCTION
C++ LANGUAGE Depth 70
34 files · PRODUCTION
Shell LANGUAGE Depth 70
1 files · PRODUCTION
JSON LANGUAGE Depth 70
2 files · PRODUCTION
Markdown LANGUAGE Depth 70
17 files · PRODUCTION
TOML LANGUAGE Depth 70
1 files · PRODUCTION
YAML LANGUAGE Depth 70
4 files · PRODUCTION
Python LANGUAGE Depth 70
7 files · PRODUCTION
Poetry BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 74
5 files · PRODUCTION, TEST
TypeScript LANGUAGE Depth 66
3 files · PRODUCTION
pytest TESTING Depth 41
2 files · TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · observedlinting · observedformatting · absent
ACTIVITY & OWNERSHIP
First commit 2024-01-29
Last commit 2026-08-10
Active months 8
Commits 203