Cyan4973 / Cyan4973/FiniteStateEntropy
Architecture specific optimizations
Open
help needed
- Dominant language
- C
- Stars
- 1.5k
- Forks
- 165
- PR merge metrics
- No merged PRs in 30d
Description
Hello, I would like to know if it is possible to have ARM's SIMD (neon) routines to be added in huff0 and/or FSE encode/decode parts? That way, I can make them run a bit faster on raspberry pi.
Contributor guide
No contributing guide indexed for this repository
Research direction
Start by reviewing the huff0 and FSE encode/decode entry points and the existing architecture-specific code, if any. Check how ARM NEON is detected and supported on Raspberry Pi, then define the affected routines and a way to compare their performance. Done means a focused SIMD implementation with correctness coverage and evidence of faster ARM execution.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- c
- Domain
- performance
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100