workshopsoft/ludic
2
0
Fork 0
Code Issues Pull requests Projects Releases 26 Packages Wiki Activity Actions

perf(render3d): mesh-shader grass dispatches each tile with its own count; not yet counted as implemented

Browse source 
A chunk's dispatch was sized for its largest tile, so the far tiles beside a
near one ran thousands of empty invocations: 9.8 ms of grass at 4K on an RTX
3070 Ti. One dispatch per tile, sized to that tile, brings it to 5.0 ms - still
three times the chunked path's 1.7 (36 fps against 41), so GF_MESH_GRASS is not
implemented yet and the Advanced row says a coming update.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Orkun ÇAKILKAYA 2026-09-15 20:40:47 +03:00
parent a868378b99
commit d80786e99a
3 changed files with 23 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

22
packages/ludic.render3d/grass.ludic
View file

@ -229,18 +229,26 @@ function grass_flush() -> void {
var m = e - k
if m > GRASS_CHUNK { m = GRASS_CHUNK }
for q in 0 .. m * 4 { grass_chunk_tv[q] = grass_tv[k * 4 + q] }
u_f4v(gpu_uniform(p, "u_tiles"), m, grass_chunk_tv)
if mesh {
# enough blade batches for the chunk's largest tile, capped as the instanced path caps a tile
# one dispatch per tile, as many blade batches as that tile has: sized for a chunk's largest
# tile, the far tiles beside a near one ran thousands of empty invocations (9.8 ms against the
# chunked path's 2 at 4K on an RTX 3070 Ti)
let cells = grass_band_cells[b]
var most = 0
for q in 0 .. m { let t = f_to_int(grass_tv[(k + q) * 4 + 2]) * cells * cells; if t > most { most = t } }
if most > 65535 { most = 65535 }
gpu_draw_mesh_tasks((most + GRASS_MESH_BLADES - 1) / GRASS_MESH_BLADES, m, 1)
for q in 0 .. m {
var total = f_to_int(grass_tv[(k + q) * 4 + 2]) * cells * cells
if total > 65535 { total = 65535 }
if total > 0 {
for c in 0 .. 4 { grass_chunk_tv[c] = grass_tv[(k + q) * 4 + c] }
u_f4v(gpu_uniform(p, "u_tiles"), 1, grass_chunk_tv)
gpu_draw_mesh_tasks((total + GRASS_MESH_BLADES - 1) / GRASS_MESH_BLADES, 1, 1)
grass_draws += 1
}
}
} else {
u_f4v(gpu_uniform(p, "u_tiles"), m, grass_chunk_tv)
gpu_draw_mesh_indirect(grass_mesh, grass_cmds, k * 20, m, 0, 0)
}
grass_draws += 1
if not mesh { grass_draws += 1 }
k += m
}
}