[concurrency-interest] The very best CAS loop

Andrew Haley aph at redhat.com
Wed Sep 28 11:19:47 EDT 2016


On 28/09/16 15:29, Peter Levart wrote:
> Yes, but that's an entirely different benchmark. This just tests raw 
> speed of a single thread in its own cache-line.

Well, exactly, that's the idea.  I wanted to make sure that we really
had false sharing in the test case; I can do that by making sure that
when there is no false sharing things really are much faster.

Andrew.



More information about the Concurrency-interest mailing list