If you're in trouble and cannot find an answer to a question which goes beyond Stack Overflow...
If you have a not-so-usual solution for your problems but need to justify it to your boss...
If you like to think on your own rather than blindly follow "common wisdom" and "profound truth"...
...then 'No Bugs' Hare on Soft.ware might be the right place for you.
Your mileage may vary. Batteries not included

Premature and/or over-optimization is often claimed to be a root of most evil in the programming world. However, what to do when optimization IS neccessary?

IT Hares discuss certain not-so-trivial optimization techniques. It doesn’t mean that you should use them at all costs (and most likely, you don’t); however, if you do have a reason to optimize – this information may be handy.

Optimizations, page 1:

‘Speedy Gonzales’ Serializing (Re)Actors via Allocators

Quote: “Allocator-based serialization for (Re)Actors is extremely fast (for x64 – around tens of ms per 100MB of state)”
Another Quote: “Per-(Re)Actor allocators can be implemented without any changes within (Re)Actor itself (i.e. all the necessary changes can be confined to Infrastructure Code).”
[]

Parallel STL for Newbies: Reduce and Independent Modifications

Quote: “with std::reduce() such code, while it compiles at least under MSVC, MAY occasionally provide wrong results”
Another Quote: “if you happen to need something beyond that – take a deep breath and allocate at least several months to understand how does parallelism really work under the hood.”
[]

Using Parallel <algorithm> Without a Clue: 90x Performance Loss Instead of 8x Gain

Abstract: “I made an experiment which demonstrates Big Fat Dangers(tm) of implying that parallelization can be made as simple as just adding a policy parameter to your std:: call.”
Quote: “it is still necessary to understand what we’re doing”
[]