• 1 Post
  • 25 Comments
Joined 1 year ago
cake
Cake day: July 1st, 2023

help-circle

















  • The problem is that only half of the chiplets have access to the large cache. If the scheduler isn’t aware of that and a lot of data is shared across cores (as in the case for many games), you’ll miss out on most of that performance. AMD wrote a driver for Windows to help optimally schedule threads with high cache intensity to the expanded cache chiplets, but they didn’t do it for Linux. If your workload is not very chatty between cores, and threads don’t need to synchronize at 60Hz, it won’t matter as much. But for game workloads, it makes a big difference, and can actually result in worse performance than the homogenous chiplet design of the mid-tier 7800X3D if you get it wrong.


  • That’s kind of my point. Linux supports it, but Windows doesn’t anymore. Why? Money - OEMs aren’t selling them anymore, so why spend time to support new features on them? On the flip side, the heterogeneous chiplet structure of the 7950X3D was supported on Windows from day 1, while on Linux the scheduler is still unaware of the different perf characteristics to this day. Why? Same answer - money. AMD doesn’t make money selling 7950X3D on Linux, so they’re not going to spend time writing a kernel driver to optimize perf on it.