News for hackers. Stuff that matters.
Re:Mozilla can produce near-native performance on the Web by ux-app on Thursday May 23, 2013 @03:17AM (#5755689)
That is very cool. I got quite bad rubber banding initially (with a reported 60fps), however after turning off v-sync in chrome://flags I got super smooth 120fps performance.

Would be great if Chrome had this option off by default.

Re:Mozilla can produce near-native performance on the Web by exDM69 on Thursday May 23, 2013 @03:49AM (#5755747)
> Would be great if Chrome had this option off by default.

Disabling Vsync causes page tearing artifacts (https://en.wikipedia.org/wiki/Page_tearing). It should always be enabled by default. Some new gpu drivers also have "adaptive vsync", where it's enabled by default but gets temporarily disabled when deadlines are not met.

Re:Mozilla can produce near-native performance on the Web by ux-app on Thursday May 23, 2013 @04:13AM (#5755791)
isn't tearing preferable to input lag? As I mentioned, with v-sync on there is a very noticeable rubber-banding effect, with it off the result is (perceptually) far smoother.

>It [vsync] should always be enabled by default

Not sure about this. Surely the goal is to maximize perceived performance not 'correctness' (where correctness in this context is defined as each frame being fully drawn before the next one starts).

Re:Mozilla can produce near-native performance on the Web by exDM69 on Thursday May 23, 2013 @04:57AM (#5755874)
> isn't tearing preferable to input lag?

In a properly written app, vsync should not cause input lag despite gamer superstitions. But there are lots of not-properly written apps where this is a problem.

WebGL / Chrome should solve the problem in some other way, not disabling vsync. Or using adaptive vsync if available as a workaround.

The culprit here might be the ANGLE OpenGLES2-on-D3D9 wrapper that Chrome uses, which is notoriously slow on synchronous operations like vsync, glGetError or glFinish.

Re:Mozilla can produce near-native performance on the Web by just2n on Sunday June 02, 2013 @12:03AM (#5807251)
That was just caused by me not processing input properly. I've set up a proper rendering loop here and now only render the most recent mouse position on each frame:

http://jsfiddle.net/eymAS/84/

It's better, but still limited to 60fps, and since I render to the state at 0s, the worst delay we can see is ~16.6ms + rendering time.