Intel Parallel Computing Center
EPCC and Intel have collaborated since 2014 on the exploitation of Xeon Phi processors for computational simulation. Current work has switched focus from first generation Xeon Phi’s – Knights Corner (KNC) – to the latest version, Knights Landing (KNL).
We are currently working to understand the MPI performance across both the many-core processor and the networks KNL can now be directly attached to. Furthermore, we are investigating the performance of a range of different applications on KNL.
We are also working on tools to help application programmers efficiently exploit the more complex memory hierarchy on the KNL.
Find out more
You can read more about this work in Adrian Jackson's blog posts.