[ARROW-7460] [Rust] Improve some kernels with autovectorisation

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: 0.15.1
• Fix Version/s: 0.16.0
• Component/s: Rust
• Labels: pull-request-available
• External issue URL: https://github.com/apache/arrow/issues/23730
• Assignee: Neville Dipale
• Reporter: Neville Dipale
• Created: 22/Dec/19 13:29
• Updated: 11/Jan/23 07:53
• Resolved: 23/Dec/19 17:27

Description

In a comment to an open ticket for optimising a cast kernel by using SIMD, andy-thomason mentioned that LLVM does autovec well for Rust.

I'd like to explore whether we could improve the kernel performance by simplifying the loops enough to allow the compiler to vectorise.

Issue Links

• links to: GitHub Pull Request #6086