(More specifically, any time we use translucency or polygon offset, we introduce a dependency in the order that things are rendered. Since both of these techniques are used heavily, the order in which x-plane scenes are drawn is quite important.)

I think the second core could be more useful for moving computational and loading tasks from the main thread than from subdividing rendering.

(Remember also that if there is a single access point to the GPU, e.g. a single PCIe bus, rendering from two threads may reveal bottlenecks.)

– Sometimes we are taking one task and splitting it in half via recording. Further splits mean more code, if the task has no natural parallelization.

– Sometimes a given task needs to be run by itself and is simply not done on the main CPU.

On the other hand, if enough things “run in the background” we could find ourselves needing more than 2 cores.

At this point I don’t think quad-core is worth the money based on the sim’s utilization, but I don’t think I’m qualified to predict industry trends. We’re going to focus on configurations that are common, so if quad core remains “exotic”, I think we’ll put our efforts into other kinds of acceleration.

(Remember, this is a zero sum game – time spent working on quad-core optimization is time taken away from performance tuning for all systems and performance tuning around the GPU, which is also developing new features that we can be using.)