ia64 rwsem using atomic primitive
Quoted 1 line
I have converted rw semaphore from current generic
spin_lockimplementation to use architecture specific atomic operation on ia64. This new scheme speeds up all the semaphore operations in the fast path with atomic instruction and fall back to a heavy function when there are read/write contention. I've also taken some raw measurement how fast it improves. The most significant gain comes from parallel reader lock acquire/release which has around 6.6X speed up with the new version. Here is a patch against 2.4.20.
I applied this patch to 2.4. I also picked up David's tweaks to improve the optimization of ia64_fetch_and_add, including the move of that function and related ones to intrinsics.h.
Bjorn