- Joined
- Jul 13, 2016
- Messages
- 3,290 (1.08/day)
Processor | Ryzen 7800X3D |
---|---|
Motherboard | ASRock X670E Taichi |
Cooling | Noctua NH-D15 Chromax |
Memory | 32GB DDR5 6000 CL30 |
Video Card(s) | MSI RTX 4090 Trio |
Storage | Too much |
Display(s) | Acer Predator XB3 27" 240 Hz |
Case | Thermaltake Core X9 |
Audio Device(s) | Topping DX5, DCA Aeon II |
Power Supply | Seasonic Prime Titanium 850w |
Mouse | G305 |
Keyboard | Wooting HE60 |
VR HMD | Valve Index |
Software | Win 10 |
9950X3D won't have any extra cache for the 8 cores that will be used in games though, even if they put it on both dies. Maybe they'll clock it sky high this time and possible gains from there, considering 7950X3D with a CCD disabled was generally faster than 7800X3D.
The 9950X3D is likely to be a better bin.
Can we say with certainty that data that would otherwise be a cache miss cannot be fetched from the other CCD's X3D cache? If we can't, I'll wait for reviews to reserve judgement. If that's implemented, while it wouldn't be as ideal as fetching from the local X3D it's still far faster than fetching from main system memory.
Plus you have to wonder if that other large L3 cache can soak up background applications and windows so the CCD where the game is actually running is completely free.
Too many questions given we haven't see a dual X3D cache consumer part.