Xeon E5 v3 Cluster on die technology

manpreet Best Answer 2 years ago

I am currently investigating how to enhance performance isolation and predictability on the latest Intel platforms, in particular on Xeon E5 v3 (Haswell).

To this aim, I am envisioning to exploit the Cluster-on-die mechanism, but I have some questions.

1) on multiple internet sources I read that it is available only in models with 10 or more cores, since they arrange cores and LLC slices on two ring buses, each one with a System Agent. Can someone confirm this?

2) if I enable Cluster-on-die, LLC misses are handled by the SA on the same ring of the core that generated the miss, right?

3) most importantly, in case of a miss from a certain core, are data placed on LLC slices on the same ring of the requesting core, or are they spread to all slices across both rings?

Thanks in advance for any information!