Turnerj / Quickenshtein

Making the quickest and most memory efficient implementation of Levenshtein Distance with SIMD and Threading support

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Improving Threading Calculation Performance

Turnerj opened this issue · comments

For example, use the Concurrency Visualizer extension to identify if there are any areas that can be improved.

This is more a curiousity than anything - my own testing so far has seen great gains in multi-threaded workloads however there could still be more room for improvement.

If possible, there likely are big gains by supporting diagonal calculation in a multi-threaded scenario however that would likely require a major re-write.