I’ve now implemented an all-GPU-compute pipeline in a Pathfinder branch, avoiding the rasterizer entirely (CPU still used for tiling). However, so far it seems that using compute shader to create vector tiles and the standard GPU rasterizer to composite them is fastest…
Pathfinder with compute doesn’t need concurrent write access to pixels either!
-
-
To be clear: I am not using atomics anywhere. (GL doesn’t support atomics on non-integer image formats anyway)
-
I’m basically doing what piet-metal is doing. Major differences are (1) tiling is on CPU not GPU (but I’m only talking about rendering time here, not tiling); (2) strokes are converted to fills first on GPU instead of being handled natively.
- 1 more reply
New conversation -
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.