Add IEEE Floating-Point Numbers
Open
planning
- Dominant language
- C++
- Stars
- 5
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
Use 80-bits from each NEON register for holding IEEE-styled Floating Point Numbers.
Each NEON register should hold two data entries. When one of the data entries is a float, the other entry is restricted to 32-bit types and smaller.
More information on this can be found in the description for the `-a32f` optimization setting in the XCS Tech Spec, chapter 1.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.