In class "hardware lock elision" was briefly discussed, and I googled a little what that is and it seems like a very interesting idea:
https://brooker.co.za/blog/2013/12/14/intel-hle.html
"If multiple threads execute critical sections protected by the same lock but they do not perform any conflicting operations on eachother's data, then the threads can execute concurrently and without serialization. Even though the software uses lock acquisition operations on a common lock, the hardware is allowed to recognize this, elide the lock, and execute the critical sections on the two threads without requiring any communication through the lock if such communication was dynamically unnecessary."
Also the graphs in the link are very interesting. I think the main point is that when there are massive contentions, you can see HLE performs significantly better than non-HLE.
In class "hardware lock elision" was briefly discussed, and I googled a little what that is and it seems like a very interesting idea: https://brooker.co.za/blog/2013/12/14/intel-hle.html "If multiple threads execute critical sections protected by the same lock but they do not perform any conflicting operations on eachother's data, then the threads can execute concurrently and without serialization. Even though the software uses lock acquisition operations on a common lock, the hardware is allowed to recognize this, elide the lock, and execute the critical sections on the two threads without requiring any communication through the lock if such communication was dynamically unnecessary."
Also the graphs in the link are very interesting. I think the main point is that when there are massive contentions, you can see HLE performs significantly better than non-HLE.