JuliaSIMD / JuliaSIMD/StrideArraysCore.jl
Don't carry stride information for dense axes
Open
- Dominant language
- Julia
- Stars
- 19
- Forks
- 10
- PR merge metrics
- No merged PRs in 30d
Description
Given an axis is dense, its stride can be computed from the size. This has the advantages of
1. decreasing the size of the object
2. allowing a sufficiently smart compiler to uncover the orthogonality of memory accesses along separate strides when the size determines iteration bounds.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.