[magicalist]

> You need heuristics of some kind to get good performance, and I can't blame Microsoft for using the DOM for that.

which, again, that's fine, but mayyyyybe they were a little lax in checking performance on nearly any other popular video site on the web to see if that heuristic is a good one?

Or maybe changing page layout in an extremely common way wasn't an effort to undermine a hyper specific benchmark?

[pcwalton]

How many sites put invisible DOM elements over the videos?

Remember, if you put visible DOM elements on top of the videos, then you lose scanout compositing no matter what.

[magicalist]

> How many sites put invisible DOM elements over the videos?

A lot of them? Vimeo, for instance, has a number of opacity: 0 and hidden divs over the video. Twitch has at least a couple of opacity: 0 divs on top.

Maybe we're interpreting the phrase

> hidden empty div over YouTube videos

differently? That's the structure I assume they were talking about.

[seba_dos1]

I'd assume that it was actually an invisible, but not technically hidden div, leading to a fully transparent blending pass - divs with opacity:0 or display:none are trivial to optimize for this case.

[magicalist]

> I'd assume that it was actually an invisible, but not technically hidden div

Considering that it's now optimized and that's not what the original post said, I don't know why you'd assume that.

[catwell]

There are visible elements on top of YouTube videos.

That's what this "empty div" is for if that's the one I think it is. It is the container for things like branding and annotations.