John H (john.delete@this.not.com) on April 27, 2022 5:20 pm wrote:
> 5800X3D appears to do really really well in simulator games. Microsoft Flight Simulator,
> and Star Citizen show huge (40-50%) gains over similar Ryzen products with 5800X3D.
>
> In a lot of other games, X3D shows more like 5-20% gains, and applications
> show 0-10% gains vs say a 5800X set to the same clock speeds.
>
> I'm curious what kind of software behavior is causing the simulators to see such a large
> improvement relative to other games and applications. Is it the main code game loop
> is likely a bit too large for the existing caches to handle effectively? Is the X3D
> cache not yet big enough or maybe already big enough for other game types?
>
> Just looking for theories..

I don't really know, but I think it's possible you are looking at this from wrong direction. It may be that simulator games benefit more simply because they are less GPU constrained. Other games may benefit just as much, but they just spent more time waiting for GPU.

I haven't really looked 5800X3D reviews much (first glance pretty much told me that it isn't an interesting product for myself or my employer), so I don't know what sort of settings they are using. Most games are so GPU limited that getting significant differencies requires running a high-end GPU with low-end resolution. It's a bit better when measuring highest frame latencies instead of average frame rate (as everyone should and hopefully does these days), but it's still pretty hard to make a meaningful comparisons.

-JLarja