This WORK-IN-PROGRESS patch uses an atomic unsigned and futex operations
to optimize the synchronization code in std::future. The current code
uses a mutex/condvar combination, which is both slower (e.g., due to
mutex contention, stronger ordering requirements for condvars, using an
additional
Oing libstdc++@, as required for all libstdc++ patches.
Original patch at
https://gcc.gnu.org/ml/gcc-patches/2014-11/msg02004.html
This WORK-IN-PROGRESS patch uses an atomic unsigned and futex operations
to optimize the synchronization code in std::future. The current code
uses a
