-
parallel-hashmap
A family of header-only, very fast and memory-friendly hashmap and btree containers.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
std::unordered_map (std maps in general) is quite slow, as far as associative containers go. Try the flat_hash_map from here instead. Also, what are you using to implement the priority queue? Try using a priority heap or bucketed priority queue instead, it will likely outperform a normal priority queue. It may also be possible to optimise your open and closed lists. The book AI for Games talks about a variant the author calls “Node Array A*” which may be worth investigating.
Welcome to the curse of dimensionality! Jump point search might help.