Open
Description
Hi,
First off, thank you for writing this library, it's a really neat project.
However, I couldn't help but notice the lack of parallelization. This is of consequence, as simulations slow down to a crawl given enough nodes. SIMD may also help a lot. Going one step further, one could run the computations on GPU.
@grantshandy, you mentioned plans to rewrite this or change the API. I wonder if this is already in the pipeline in some way? i.e., would there be interest in a PR to add support for parallelization / SIMD / general performance improvements, or would it get broken very soon by the said refactoring?
Metadata
Metadata
Assignees
Labels
No labels