[flurrything]

> It's not really fair to compare a custom implementation against the standard unordered_map implementations, which

But he is comparing the standard unordered_map implementation to his own implementation of the standard unordered_map (same API).

[allenz]

It's the same API, but I highly doubt that his implementation is fully compliant with the C++ standard.

[flurrything]

It is, and so is boost::unordered_map, that's the whole point of the comparison. Just check the implementation out.

[allenz]

Source on that claim? Here's a comment chain where the author admits that his library is noncompliant: https://probablydance.com/2017/02/26/i-wrote-the-fastest-has.... Also note the complete lack of a standards test suite.

This library uses Robin Hood hashing for speed. As my original link explains, standard implementations use chained buckets so that users can cache lookups and to have better worst-case performance: https://news.ycombinator.com/item?id=9675964