Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

John Carmack: Latency Mitigation Strategies

altdevblogaday.com

Post reply on HN
Print view View original

81–90 of 106 posts

Re: John Carmack: Latency Mitigation Strategies

#81

Post by newman314 »

bbatchelder wrote: post #53
Scene_Cast2 wrote: post #40

Earlier quoted context omitted.

Regarding your last point: it's getting better. Modern TVs have "game mode", where latency is minimized. The latest LCD panels use embedded Display Port, eDP. The latest eDP standard introduces a frame buffer on the LCD itself, where you can just write deltas and tell it to "swap". I think this is quite similar to what you're proposing, in concept.

You may already know this, but the "Game Mode" on modern TVs is just turning off the 120Hz/240Hz interpolation that is done to "improve" the picture (or is required for certain 3D systems to work). The interpolation introduces significant latency that its obvious (and frustrating) during gaming. I actually run my TV in game mode by default, because the interpolation done in 120/240Hz mode makes everything look like i…

This.

Some people aren't able to tell this apparently but it absolutely bothers the heck out of me. Probably the reason why I'm not a fan of 48fps either.

I still think it would be useful to have a variable rate player. 24fps for normal scenes and 48fps for action.

Re: John Carmack: Latency Mitigation Strategies

#82

Post by MichaelGG »

breckinloggins wrote: post #31

It sounds like we would benefit from GPU and display manufacturers providing a set of standard low-level control primitives so that people like Carmack who know what they are doing can really play around with the entire pipeline without having to worry about all the things the cards and the displays are doing behind their backs. For example, a GPU could have a set of standard settings with full buffering and all the…

Yea that works, until someone realises they can boost performance by changing the semantics of the "I know what I'm doing" call. Then you'll need yet another "no really I know what I'm doing" flag and on and on, or app black/whitelisting and so on.

Re: John Carmack: Latency Mitigation Strategies

#83

Post by jzwinck »

derefr wrote: post #77
bradleyjg wrote: post #73

Earlier quoted context omitted.

Let's say a hardware manufacturer writes a firmware that exposes calls that can degrade or destroy the device if misused, and the OS driver in turn exposes those calls to third party programs. If a program wreaks the device, who is the end user going to blame -- the program, the driver, the manufacturer, or all three?

Maybe the hardware manufacturer can certify and sign game binaries as being allowed to use the direct GPU API.

Didn't Secure Boot already show us what reaction people will have to mandatory signing?

Re: John Carmack: Latency Mitigation Strategies

#84

Post by derefr »

jzwinck wrote: post #83
derefr wrote: post #77

Earlier quoted context omitted.

Maybe the hardware manufacturer can certify and sign game binaries as being allowed to use the direct GPU API.

Didn't Secure Boot already show us what reaction people will have to mandatory signing?

Without the signature, the app would just go slower.

Re: John Carmack: Latency Mitigation Strategies

#85

Post by ansible »

You could cut latency further if you were able to measure the muscle contractions in your neck area.

Another option is smart eye tracking too. Generally if you are going to move your head in a particular direction, you'll likely start moving your eyes first.

Re: John Carmack: Latency Mitigation Strategies

#86

Post by gizmo686 »

newman314 wrote: post #81
bbatchelder wrote: post #53

Earlier quoted context omitted.

You may already know this, but the "Game Mode" on modern TVs is just turning off the 120Hz/240Hz interpolation that is done to "improve" the picture (or is required for certain 3D systems to work). The interpolation introduces significant latency that its obvious (and frustrating) during gaming. I actually run my TV in game mode by default, because the interpolation done in 120/240Hz mode makes everything look like i…

This. Some people aren't able to tell this apparently but it absolutely bothers the heck out of me. Probably the reason why I'm not a fan of 48fps either. I still think it would be useful to have a variable rate player. 24fps for normal scenes and 48fps for action.

Is there a detectable (to human) difference between a 24fps screen and a 48fps screen where the image only changes every other frame. I can see how this would work with film based projectors, but my understanding of TVs is that pixels are always on and simply change states between frames, so 'changing' to an identical frame should have no effect.

Re: John Carmack: Latency Mitigation Strategies

#89

Post by greggman »

breckinloggins wrote: post #31

It sounds like we would benefit from GPU and display manufacturers providing a set of standard low-level control primitives so that people like Carmack who know what they are doing can really play around with the entire pipeline without having to worry about all the things the cards and the displays are doing behind their backs. For example, a GPU could have a set of standard settings with full buffering and all the…

I don't think that's needed. What's needed is just to let competition work. If one GPU is less laggy in VR than another people will by that GPU for VR. No need to work around the driver, demand will make the drivers better.

Re: John Carmack: Latency Mitigation Strategies

#90

Post by Tuna-Fish »

gizmo686 wrote: post #86
newman314 wrote: post #81

Earlier quoted context omitted.

This. Some people aren't able to tell this apparently but it absolutely bothers the heck out of me. Probably the reason why I'm not a fan of 48fps either. I still think it would be useful to have a variable rate player. 24fps for normal scenes and 48fps for action.

Is there a detectable (to human) difference between a 24fps screen and a 48fps screen where the image only changes every other frame. I can see how this would work with film based projectors, but my understanding of TVs is that pixels are always on and simply change states between frames, so 'changing' to an identical frame should have no effect.

Having the frame change every second frame would mean that the screen would be changing the picture only half the time, while it normally is always changing the color of some pixel.

Not sure that this is not just a pure win.

Post reply on HN