3

Background

I'm considering a 4k monitor with 120Hz support that uses two DP1.2 connectors; they each render half the screen at 120hz, it's effectively two monitors glued together.

Question

For gaming, would I see a performance benefit from using a dedicated GPU for each half of the screen? I'm not sure how this'd work under DX11 or 12.

Thanks!

user1560261
  • 33
  • 2

2 Answers2

1

Probably none.

You're most likely using MST - in a very unusual fashion, similar to how 5k monitors, and the old IBM T220 did. Your graphics card likely is aware that its "one monitor with very high refresh rates, and I need to render it as seperate tiles", and I somehow suspect its rendering as 4x1080px120hz 'tiles'

I'm unaware of MST even working on multiple video cards.

In practice, 4k60 gaming on a single video card is tough - so you'd want to take advantage of SLI/Crossfire or the DX12 multigpu options anyway, which still don't need you to plug in the monitor into different cards.

So for regular use, I'm doubtful multiple cards are better than one card capable of presumably handling 2 or more 4k60 monitors. For gaming, you will likely need a eyewateringly powerful setup.

Journeyman Geek
  • 3,681
  • 1
  • 12
  • 27
-1

The GPUs, contrary the CPUs, are already massively parallel devices. On the CPUs, running a program simultanously on multiple ones, requires to make it parallel, which can be a significant re-factoring (and sometimes it is even impossible). On the GPUs, this problem doesn't exist: they already have a lot of internal processing units working parallel.

However, the chips still have manufacturing constraints. This is improving quickly (see Moore's Law), but as we can see, there are always a newest game which requires yet another VGA card invention. :-)

A single GPU can handle multiple displays, it is not a problem for that since a long time. Similarly, as a CPU can run multiple programs at once.

I can't see the reason, why would it needed to have multiple GPUs for the different displays.

However, if there is the manufacturing limit, then it can be feasible. You have to compare, which is better for you:

  1. Having a single, probably costlier GPU, handling both of the displays
  2. Handling the multiple displays with different GPUs

(1) may be too costly, or if your requirements are strong, this chip may be even not existing.

peterh
  • 688
  • 2
  • 10
  • 24