I noticed in https://www.microsoft.com/en-us/research/blog/mimalloc-a-high-performance-scalable-memory-allocator-for-the-modern-era/ that v3 uses a slower mi_ptr_page variant than older versions. How impactful is that?
Would it be worth having a config flag or a mi_free_fast variant (which a Rust global allocator could use) which uses the faster alignment variant?
I noticed in https://www.microsoft.com/en-us/research/blog/mimalloc-a-high-performance-scalable-memory-allocator-for-the-modern-era/ that v3 uses a slower
mi_ptr_pagevariant than older versions. How impactful is that?Would it be worth having a config flag or a
mi_free_fastvariant (which a Rust global allocator could use) which uses the faster alignment variant?