Page 2 of 2

Re: NVIDIA may have implemented a synchronous framerate limi

Posted: 11 Feb 2017, 22:52
by lexlazootin
Woops, you're right. I downloaded the newer one but it still doesn't feel very good. I'll do some latency tests when i get the camera back tomorrow.

I think we talk about this at one point. I think it was MasterTaco said that nQuake/ezQuake and GeDoSaTo had a predictive fps limit feature or what ever you want to call it.

http://www.neogaf.com/forum/showthread.php?t=1043959

Re: NVIDIA may have implemented a synchronous framerate limi

Posted: 12 Feb 2017, 00:59
by RealNC
Chief Blur Buster wrote:I haven't studied RTSS closely, but:

Does RTSS use predictive waiting before input reads? To do just-in-time rendering before VSYNC?
I don't think so. It seems to use a fixed target (1000/framerate milliseconds.) It just blocks until at least that amount of time has passed since the last frame.

Although Jorimt's tests didn't specifically test for this, the "up to 1 frame of latency with vsync enabled" result should probably be interpreted as RTSS not doing prediction.

Re: NVIDIA may have implemented a synchronous framerate limi

Posted: 12 Feb 2017, 10:29
by Bouttime
RealNC wrote:
Chief Blur Buster wrote:I haven't studied RTSS closely, but:

Does RTSS use predictive waiting before input reads? To do just-in-time rendering before VSYNC?
I don't think so. It seems to use a fixed target (1000/framerate milliseconds.) It just blocks until at least that amount of time has passed since the last frame.

Although Jorimt's tests didn't specifically test for this, the "up to 1 frame of latency with vsync enabled" result should probably be interpreted as RTSS not doing prediction.
Jorimt's tests show that Gysnc + VSync with RTSS limiting FPS just below refresh rate is the best solution.


Sent from my Nexus 6 using Tapatalk