ludic/packages/ludic.render3d/grass.ludic

# ============================================================================
# grass.ludic — procedural GPU ground cover with continuous density (no rings).
#
# The world is cut into 4 m cells; blade j of a cell always stands in the same place
# (shaders/grass.vert). Draws are per tile: the CPU walks tiles around the camera,
# frustum-culls them, and feeds each visible tile as many blade indices per cell as its
# NEAREST point could need; the vertex stage then keeps only the indices that exist at
# each blade's own distance, so density is one smooth function of distance everywhere.
# Tiles are 16 m near, 64 m in the middle distance and 256 m far, purely to keep the
# draw count down — the cells and their hashes are the same in every tile size.
# ============================================================================

const GRASS_CELL: int = 4
# A photographed blade, as an atlas of straightened blades side by side (the game sets
# this; the renderer does not name a game asset). 0 = the procedural gradient, which is
# what this was for a year: a two-tone ramp with a hard edge, and every blade in the
# valley the same blade. A real blade has a midrib, a colour that runs olive to straw,
# browning where it has dried and a tip that is its own shape - none of which can be
# written down, only photographed.
# Where a body is standing, and how wide it pushes. The grass has never known the player was
# in it: you walked through a meadow and every blade ignored you, which is the single most
# noticeable thing missing from every step the game asks you to take. The game sets this each
# frame; radius 0 means nobody is there.
# Vulkan with multi-draw indirect: every visible tile is a record in one buffer, uploaded once a
# frame, and each band draws its records GRASS_CHUNK at a time - one draw for up to 256 tiles. A
# record's firstInstance is its place in its chunk times 65536; grass.vert's TILES variant reads that
# place's corner and indices per cell from u_tiles. R3D_GRASS_TILES=1 keeps a draw per tile.
const GRASS_CHUNK: int = 256
const GRASS_RECS: int = 8192
# Mesh-shader grass (Settings, Video, Advanced): the chunked path's records, but each chunk is one
# mesh dispatch - work group y a tile, x a batch of GRASS_MESH_BLADES of its blades - so a blade the
# tests reject emits nothing instead of eight degenerate vertices. R3D_MESH_GRASS=1 / 0 overrides.
const GRASS_MESH_BLADES: int = 16
function r3d_mesh_grass(render3d_st: mut Render3dState, on: bool) -> void {
  render3d_st.grass_mesh_on = on
  if r3d_env_has(render3d_st, "R3D_MESH_GRASS") { render3d_st.grass_mesh_on = Text.to_int(r3d_env(render3d_st, "R3D_MESH_GRASS")) != 0 }
}
function grass_mesh_live(render3d_st: Render3dState) -> bool { return render3d_st.grass_mesh_on and render3d_st.grass_merge and render3d_st.grass_mesh_prog != 0 and gpu_has_mesh(render3d_st) }

# a blade: `rows` rows of 2 vertices (x across, y along, z bend), attribute 2 = uv
function grass_blade_mesh(render3d_st: mut Render3dState, rows: int) -> Mesh {
  let m = gpu_mesh_new(render3d_st)
  let v = gl_floats(rows * 2 * 5)
  var k = 0
  # The blade's PROFILE, and it is the whole difference between grass and a green spike.
  # It used to be `1 - t^2.5` floored at 0.12 with a bend of 0.28t^2: widest at the very
  # bottom, narrowing to a needle, and standing almost straight. That is the silhouette of
  # a pine needle, and eighty of them to the square metre read as a bed of nails.
  #
  # A real blade is narrow where it leaves the sheath, WIDEST about a fifth of the way up,
  # and then tapers the rest of the way to a fine point - and it arches over under its own
  # weight. Both terms below say that. The tip is floored just off zero rather than at 0.12
  # so the point is a point and not a cut-off stub, but not so low that the last quad is
  # degenerate.
  #
  # grass.mesh carries A COPY of these two lines for the mesh-shader path; change both or
  # the Windows blades stop matching the ones everywhere else.
  for r in 0 .. rows {
    let t = float(r) / float(rows - 1)
    let grow = Math.min(t / 0.22, 1.0)
    let wide = (0.50 + 0.33 * grow) * (1.0 - t * (t * t))
    let taper = Math.max(wide, 0.05)
    let bend = t * t * 0.52
    for sd in 0 .. 2 {
      var x = -0.5
      if sd == 1 { x = 0.5 }
      gl_put_bits(v, k, float_bits(x * taper));  gl_put_bits(v, k + 1, float_bits(t));  gl_put_bits(v, k + 2, float_bits(bend))
      gl_put_bits(v, k + 3, float_bits(float(sd)));  gl_put_bits(v, k + 4, float_bits(t))
      k += 5
    }
  }
  gpu_mesh_vertices(render3d_st, m, v, gl_bytes_of(rows * 2 * 5), GPU_STATIC)
  gpu_mesh_attr(render3d_st, m, 0, 3, GPU_F32, 20, 0, false)
  gpu_mesh_attr(render3d_st, m, 2, 2, GPU_F32, 20, 12, false)
  free(v)
  let nq = rows - 1
  let idx = words(nq * 6)
  for q in 0 .. nq {
    let b = q * 2
    idx[q * 6] = b;  idx[q * 6 + 1] = b + 1;  idx[q * 6 + 2] = b + 2
    idx[q * 6 + 3] = b + 1;  idx[q * 6 + 4] = b + 3;  idx[q * 6 + 5] = b + 2
  }
  gpu_mesh_indices(render3d_st, m, data_of(idx), nq * 6 * 4, 4)
  free(idx)
  m.count = nq * 6
  gpu_mesh_done(render3d_st, m)
  return m
}

function grass_init(render3d_st: mut Render3dState) -> void {
  render3d_st.grass_merge = gpu_has_mdi(render3d_st) and not r3d_env_has(render3d_st, "R3D_GRASS_TILES")
  var defs = "#define FOLIAGE\n#define BLADE\n#define GBLADE\n"
  if render3d_st.grass_merge {
    defs = defs + "#define TILES\n"
    render3d_st.grass_rec = words(GRASS_RECS * 5);  render3d_st.grass_tv = floats(GRASS_RECS * 4);  render3d_st.grass_chunk_tv = floats(GRASS_CHUNK * 4)
    render3d_st.grass_band_start = words(4);  render3d_st.grass_band_cells = words(4)
    render3d_st.grass_band_mesh = new []Mesh
    for b in 0 .. 4 { push(render3d_st.grass_band_mesh, null) }
    render3d_st.grass_cmds = gpu_buffer_new(render3d_st)
  }
  render3d_st.grass_prog = r3d_program(render3d_st, "grass.vert", "model.frag", defs)
  if render3d_st.grass_merge and gpu_has_mesh(render3d_st) { render3d_st.grass_mesh_prog = r3d_program(render3d_st, "grass.mesh", "model.frag", "#define FOLIAGE\n#define BLADE\n#define MESH\n") }
  # five rows, four quads: the arch above needs somewhere to bend, and at four rows a
  # blade that leans over is three straight segments and shows every join
  render3d_st.grass_mesh = grass_blade_mesh(render3d_st, 5)
  render3d_st.grass_mesh3 = grass_blade_mesh(render3d_st, 3)
  render3d_st.grass_mesh2 = grass_blade_mesh(render3d_st, 2)
  render3d_st.grass_wind = 2.4
  # Matched to the blade's width: a 1 cm blade at 0.11 m spacing covers a third of what a
  # 2.8 cm blade did, and the meadow goes bare. The game's graphics settings override this
  # (gfx_grass_spacing), but only once game_init has run - a plain headless render never
  # gets there, so the two have to agree or a shot shows something no player will see.
  # That is exactly how the last change measured as "no effect": the render was identical
  # because this line, not the settings, was deciding.
  # The spacing doubles every 18 m and the blades stop at 70 m: at 45 m and 1600 m a 1 cm blade
  # was under a pixel from 20 m on, costing a full blade's vertices to shimmer (5 ms of 9.7 on GL).
  render3d_st.grass_s0 = 0.066
  render3d_st.grass_d0 = 18.0
  render3d_st.grass_radius = 70.0
  if r3d_env_has(render3d_st, "R3D_NOBLADES") { render3d_st.grass_on = false }
  if r3d_env_has(render3d_st, "R3D_GRASS_R") { render3d_st.grass_radius = float(Text.to_int(r3d_env(render3d_st, "R3D_GRASS_R"))) }
  if r3d_env_has(render3d_st, "R3D_GRASS_S0") { render3d_st.grass_s0 = float(Text.to_int(r3d_env(render3d_st, "R3D_GRASS_S0"))) / 1000.0 }
  if r3d_env_has(render3d_st, "R3D_GRASS_D0") { render3d_st.grass_d0 = float(Text.to_int(r3d_env(render3d_st, "R3D_GRASS_D0"))) }
  if r3d_env_has(render3d_st, "R3D_GRASS_DBG") { render3d_st.grass_dbg = Text.to_int(r3d_env(render3d_st, "R3D_GRASS_DBG")) }
  gg_init(render3d_st)
}

# indices per 16 m cell that could exist at distance d (the count the shader computes)
function grass_count_at(render3d_st: Render3dState, d: float) -> int {
  let spacing = render3d_st.grass_s0 * (1.0 + d / render3d_st.grass_d0)
  let n = float(GRASS_CELL * GRASS_CELL) / (spacing * spacing)
  return int(n) + 1
}

# one tile size over one distance band
function grass_tiles(render3d_st: mut Render3dState, size: int, d_min: float, d_max: float, blade: Mesh) -> void {
  let p = render3d_st.grass_prog
  let cells = size / GRASS_CELL
  if d_min >= render3d_st.grass_radius { return }
  if render3d_st.grass_merge {
    render3d_st.grass_band_start[render3d_st.grass_band_n] = render3d_st.grass_n;  render3d_st.grass_band_cells[render3d_st.grass_band_n] = cells
    render3d_st.grass_band_mesh[render3d_st.grass_band_n] = blade;  render3d_st.grass_band_n += 1
  } else {
    u_i(render3d_st, gpu_uniform(render3d_st, p, "u_tile_cells"), cells)
  }
  let sz = float(size)
  let half = sz * 0.5
  let reach = d_max + half * 1.5
  let tx0 = int(Math.floor((render3d_st.cam_pos[0] - reach) / sz))
  let tx1 = int(Math.floor((render3d_st.cam_pos[0] + reach) / sz))
  let tz0 = int(Math.floor((render3d_st.cam_pos[2] - reach) / sz))
  let tz1 = int(Math.floor((render3d_st.cam_pos[2] + reach) / sz))
  let corner_r = half * 1.42
  var tz = tz0
  while tz <= tz1 {
    var tx = tx0
    while tx <= tx1 {
      let ox = float(tx) * sz;  let oz = float(tz) * sz
      let cx = ox + half;  let cz = oz + half
      let dx = cx - render3d_st.cam_pos[0];  let dz = cz - render3d_st.cam_pos[2]
      let dc = Math.sqrt(dx * dx + dz * dz)
      # the tile's nearest and farthest points decide which band it belongs to
      let dnear = Math.max(dc - corner_r, 0.0)
      if dc < d_min or not (dnear < d_max) { tx += 1;  continue }
      let cy = terrain_height(render3d_st, cx, cz)
      if cam_sphere_visible(render3d_st, cx, cy, cz, corner_r + 6.0) {
        let per = grass_count_at(render3d_st, dnear)
        if per > 0 and render3d_st.grass_merge {
          if render3d_st.grass_n < GRASS_RECS {
            var inst = per * cells * cells
            if inst > 65535 { inst = 65535 }
            let r = render3d_st.grass_n * 5
            render3d_st.grass_rec[r] = blade.count;  render3d_st.grass_rec[r + 1] = inst;  render3d_st.grass_rec[r + 2] = 0;  render3d_st.grass_rec[r + 3] = 0
            render3d_st.grass_rec[r + 4] = ((render3d_st.grass_n - render3d_st.grass_band_start[render3d_st.grass_band_n - 1]) % GRASS_CHUNK) * 65536
            let t = render3d_st.grass_n * 4
            render3d_st.grass_tv[t] = ox;  render3d_st.grass_tv[t + 1] = oz;  render3d_st.grass_tv[t + 2] = float(per);  render3d_st.grass_tv[t + 3] = 0.0
            render3d_st.grass_n += 1
          }
        } else if per > 0 {
          u_f2(render3d_st, gpu_uniform(render3d_st, p, "u_tile"), ox, oz)
          u_i(render3d_st, gpu_uniform(render3d_st, p, "u_per_cell"), per)
          mesh_draw_instanced(render3d_st, blade, per * cells * cells)
          render3d_st.grass_draws += 1
        }
      }
      tx += 1
    }
    tz += 1
  }
}

function grass_live(render3d_st: Render3dState) -> bool { return not render3d_st.grass_env_off and (render3d_st.grass_on or render3d_st.grass_force) and render3d_st.grass_prog != 0 }

function grass_draw(render3d_st: mut Render3dState) -> void {
  if not grass_live(render3d_st) or render3d_st.ter_reflect { return }
  if render3d_st.gg_on { gg_draw(render3d_st);  return }
  var p = render3d_st.grass_prog
  if grass_mesh_live(render3d_st) { p = render3d_st.grass_mesh_prog }
  gpu_use_program(render3d_st, p)
  grass_bind(render3d_st, p)
  gpu_cull(render3d_st, false)
  render3d_st.grass_draws = 0
  render3d_st.grass_n = 0
  render3d_st.grass_band_n = 0
  gpu_mesh_bind(render3d_st, render3d_st.grass_mesh)
  grass_bands(render3d_st)
  if render3d_st.grass_merge { grass_flush(render3d_st) }
  gpu_cull(render3d_st, true)
}

# the blades' uniforms, shared by the per-vertex path and the culled one (grass_gpu.ludic)
function grass_bind(render3d_st: mut Render3dState, p: int) -> void {
  u_mat4(render3d_st, gpu_uniform(render3d_st, p, "u_view"), render3d_st.cam_view)
  u_mat4(render3d_st, gpu_uniform(render3d_st, p, "u_proj"), render3d_st.cam_proj)
  u_mat4(render3d_st, gpu_uniform(render3d_st, p, "u_vp"), render3d_st.cam_vp_clean)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_wind"), render3d_st.grass_wind)
  # copied into a local first: a global reaching a uniform call is the codegen fault
  # CLAUDE.md records against u_wade and u_flutter, and it costs a day every time
  let btex = render3d_st.grass_blade_tex
  let bcols = render3d_st.grass_blade_cols
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_blade_cols"), float(bcols))
  var bon = 0.0
  if btex != 0 { bon = 1.0;  r3d_bind_2d(render3d_st, p, "u_blade_tex", 12, btex) }
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_blade_tex_on"), bon)
  u_f3(render3d_st, gpu_uniform(render3d_st, p, "u_push"), render3d_st.grass_push_x, render3d_st.grass_push_z, render3d_st.grass_push_r)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_rough_scale"), 1.0)
  u_v3(render3d_st, gpu_uniform(render3d_st, p, "u_tint"), render3d_st.sc_blade_tint)
  u_v3(render3d_st, gpu_uniform(render3d_st, p, "u_blade_base"), render3d_st.sc_blade_base)
  u_v3(render3d_st, gpu_uniform(render3d_st, p, "u_blade_tip"), render3d_st.sc_blade_tip)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_cull"), render3d_st.grass_radius)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_model_h"), 0.0)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_s0"), render3d_st.grass_s0)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_d0"), render3d_st.grass_d0)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_radius"), render3d_st.grass_radius)
  var ph = render3d_st.post_h
  if ph <= 0 { ph = gl_height() }
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_px"), 2.0 * Math.tan(render3d_st.cam_fov * 0.5) / float(ph))
  u_i(render3d_st, gpu_uniform(render3d_st, p, "u_dbg"), render3d_st.grass_dbg)
  var orthotex = render3d_st.ter_ortho_tex
  var oon = 1.0
  if orthotex == 0 { orthotex = render3d_st.ter_height_tex;  oon = 0.0 }
  r3d_bind_2d(render3d_st, p, "u_ortho", 4, orthotex)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_ortho_on"), oon)
  var lake = -100000.0
  if render3d_st.ter_lake_ex != 0.0 { lake = render3d_st.ter_lake_level }
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_lake_level"), lake)
  var sea = lake
  if render3d_st.ter_sea_set { sea = render3d_st.ter_sea_level }
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_sea_level"), sea)
  u_f4(render3d_st, gpu_uniform(render3d_st, p, "u_lake"), render3d_st.ter_lake_cx, render3d_st.ter_lake_cz, render3d_st.ter_lake_ex, render3d_st.ter_lake_ez)
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_snow_line"), render3d_st.ter_snow_line)
  sky_bind_lighting(render3d_st, p)
  shadow_bind(render3d_st, p)
  fog_bind(render3d_st, p)
  # 0.15 was enough to put a hard white highlight down the length of a blade whenever it
  # caught the sun, and a white blade of grass is the one thing grass is never. Measured:
  # at 0.15, 0.70% of a near-ground frame was over 210 of 255; at 0.0 it is 0.05%. A blade
  # does have a faint sheen, so this is small rather than nothing - the foliage layers have
  # used 0.05 all along and never showed the fault.
  u_f(render3d_st, gpu_uniform(render3d_st, p, "u_spec_scale"), 0.008)
}

# the per-vertex path's tiles, in four bands
function grass_bands(render3d_st: mut Render3dState) -> void {
  # four bands: the tile grows and the blade loses rows with distance (a band past the radius is
  # skipped); a tile asks for what its NEAREST point needs, so a wide tile far out wastes the rest
  grass_tiles(render3d_st, 4, 0.0, 6.0, render3d_st.grass_mesh)
  grass_tiles(render3d_st, 4, 6.0, 16.0, render3d_st.grass_mesh3)
  grass_tiles(render3d_st, 8, 16.0, 40.0, render3d_st.grass_mesh2)
  grass_tiles(render3d_st, 16, 40.0, render3d_st.grass_radius, render3d_st.grass_mesh2)
}

# the records gathered this frame: uploaded once, then each band GRASS_CHUNK records a draw
function grass_flush(render3d_st: mut Render3dState) -> void {
  if render3d_st.grass_n == 0 { return }
  var p = render3d_st.grass_prog
  let mesh = grass_mesh_live(render3d_st)
  if mesh { p = render3d_st.grass_mesh_prog } else { gpu_buffer_upload(render3d_st, render3d_st.grass_cmds, render3d_st.grass_n * 20, data_of(render3d_st.grass_rec), GPU_DYNAMIC) }
  for b in 0 .. render3d_st.grass_band_n {
    let s = render3d_st.grass_band_start[b]
    var e = render3d_st.grass_n
    if b + 1 < render3d_st.grass_band_n { e = render3d_st.grass_band_start[b + 1] }
    if e > s { u_i(render3d_st, gpu_uniform(render3d_st, p, "u_tile_cells"), render3d_st.grass_band_cells[b]) }
    let blade = render3d_st.grass_band_mesh[b]
    if e > s and not mesh { gpu_mesh_bind(render3d_st, blade) }
    var k = s
    while k < e {
      var m = e - k
      if m > GRASS_CHUNK { m = GRASS_CHUNK }
      for q in 0 .. m * 4 { render3d_st.grass_chunk_tv[q] = render3d_st.grass_tv[k * 4 + q] }
      if mesh {
        # 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 = render3d_st.grass_band_cells[b]
        for q in 0 .. m {
          var total = int(render3d_st.grass_tv[(k + q) * 4 + 2]) * cells * cells
          if total > 65535 { total = 65535 }
          if total > 0 {
            for c in 0 .. 4 { render3d_st.grass_chunk_tv[c] = render3d_st.grass_tv[(k + q) * 4 + c] }
            u_f4v(render3d_st, gpu_uniform(render3d_st, p, "u_tiles"), 1, render3d_st.grass_chunk_tv)
            gpu_draw_mesh_tasks(render3d_st, (total + GRASS_MESH_BLADES - 1) / GRASS_MESH_BLADES, 1, 1)
            render3d_st.grass_draws += 1
          }
        }
      } else {
        u_f4v(render3d_st, gpu_uniform(render3d_st, p, "u_tiles"), m, render3d_st.grass_chunk_tv)
        gpu_draw_mesh_indirect(render3d_st, blade, render3d_st.grass_cmds, k * 20, m, 0, 0)
      }
      if not mesh { render3d_st.grass_draws += 1 }
      k += m
    }
  }
}