On Fri, 25 Sep 2026 14:49:46 GMT, Nir Lisker <[email protected]> wrote:
>> Looking at JavaFX code there should be no cap unless there is some driver or >> runtime limitation. JavaFX immediately fires the next pulse with this >> setting, and VSync should be disabled fully. >> >> Today I'm on my weaker Intel iGPU machine, I will give it a closer look at >> my stronger PC with an NVidia card next week. I don't expect this to be a >> JavaFX cap, but it might be worth looking into. Timer limitations/precision >> on Windows maybe? >> >> **EDIT:** I forgot to add, I do see the 1000FPS cap on my current machine as >> well. > > I was going to say that even on an iGPU, if you draw only 1 quad it should > easily pass the 1000 fps mark. > > I don't know about Windows' build-in limitations or the driver's. Except for > testing, I don't see a need for such high numbers, and testing can always > create heavier workloads to avoid the cap. I get the same results on my dGPU system. Not quite sure what would cause it, but I also don't see it as a big problem, rather it's more of a curiosity thing for myself I might look at later. That cap is not that important anyway IMO, to be viable benchmarks should exhaust the system rather than run just 1 quad. Regardless, interesting find! ------------- PR Review Comment: https://git.openjdk.org/jfx/pull/1387#discussion_r4121700159
