Discussion about this post

User's avatar
mzocyteae's avatar

285k doubled p-core core-to-core latency when comparing to 14900k, which also has 12 L3 slices.

285k L3 latency is similar to 14900k, but loses to 14900k over a variety of worklords.

It'd be great if you could further examine it when intel rolls out all 'fixes' and PMU events are published.

Expand full comment
Ivan's avatar

So ever since Intel moved to non-inclusive cache design, their strategy is to emphasize the private caches at the expense of the L3, while AMD's huge and fast L3 cache and relatively modest private caches strategy seems to gain more net performance.

Expand full comment
6 more comments...

No posts