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…
Well, right now I haven’t seen any improvements from avoiding the HW blender. In fact it’s a significant regression…
-
-
But you are comparing two implementations/algorithms with various diffrrences from which perf win/loss could come from. Fixed function blending is one of them, but you could be hitting different register pressure, different branching, different heaps, atomics, alignment, etc
-
No, I’m not—I have a branch of Pathfinder that does blending in compute but keeps basically everything else the same. It’s a regression…
- 7 more replies
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.