osobhandClaude Opus 5.5
63648c7000
h5py threads stay flat (global lock); clawhdf5 hyperslab reads of deflate data scale to 1244 MB/s at 16 threads (9.7x h5py threads, 0.89x h5py processes). Two deficits recorded as open issues: full chunked reads stop scaling at ~4 threads (chunk cache suspected), and contiguous reads are 4x (full) to 8x (hyperslab) slower than h5py single-threaded. Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>
ClawhDF5 Documentation
Getting Started
- Quickstart Guide — Get running in 5 minutes. Covers all use cases.
Reference
- Benchmarks — Full performance numbers with methodology
- Roadmap — Implementation status and planned features
Use Cases
- Use Cases — Detailed scenarios and how ClawhDF5 fits
Architecture
- README — Architecture diagrams, module map, research foundation