Figured I’d throw this out there: does anyone know the fastest way to *conservatively* rasterize lines on GPU? I’ve tried: (1) drawing instanced thin quads; (2) drawing thin quads w/o instancing (~15% faster); (3) glLineWidth(2.0) (fastest on NVIDIA, but deprecated)
-
Show this thread
-
Replying to @pcwalton
Wait, LineWidth is deprecated? How are we supposed to draw wide lines then?
1 reply 0 retweets 3 likes -
Replying to @crzwdjk
Dunno, that’s why I’m asking :) Worse, GL only mandates support for line width of 1. And Metal and D3D have no support for wide lines at all!
1 reply 0 retweets 2 likes -
Replying to @pcwalton
Wide lines are such a pain that I kind of understand not requiring drivers to support it.
1 reply 0 retweets 0 likes -
Replying to @crzwdjk
I don’t need wide lines per se, I just want some efficient way to conservatively rasterize potentially millions of lines (over 2M for paris-30k.svg). (This is for Pathfinder tiling—I render at 1/16 resolution and bucket into 16x16 tiles in the fragment shader.)
1 reply 0 retweets 2 likes
(This isn’t a perfect fit for the GPU rasterizer but it seems to perform about as well as compute and it’s a lot less complex. Depending on the machine it can be a lot faster to do this on GPU or about the same speed as CPU.)
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.