Chris Kennelly

@dominichamon I only have an internal microbenchmark, which demonstrated higher variability across runs (especially when combined with a change to TCMalloc) without the alignment attribute.

I'm one of the authors of P0401. When drafting this (and P0901), I had primarily anticipated a use case for types like `std::vector`, `std::string`, etc.--basically, array-like types. So that I...

I think the good news here is that P0401 is now part of C++23. That said, I don't think this is currently practical in the implementation of `flat_hash_map`, since it...

The benchmarks are now located in https://github.com/google/fleetbench