ludic/packages/ludic.render3d/shadow.ludic

# ============================================================================
# shadow.ludic — cascaded shadow maps for the sun: four 2048^2 depth layers,
# each an orthographic light frustum fitted to the bounding sphere of a slice
# of the camera frustum and snapped to its own texel grid (no swimming).
# ============================================================================

# the size of each cascade's depth layer; shadow_set_res changes it at run time
var shadow_res: int = 2048
var shadow_refused: int = 0          # the last size the graphics card had no memory for (0: none)
const SHADOW_CASCADES: int = 5

var sh_tex: int = 0
var sh_fbo: int = 0
var sh_vp: words = null            # 4 x 16 float bits
var sh_split: words = null         # view-space far distance of each cascade
var sh_range: words = null         # 4 light-frustum depth extents (metres)
var sh_texel: words = null         # 4 shadow texel sizes (metres)
var sh_tmp_proj: words = null
var sh_tmp_vp: words = null
var sh_tmp_inv: words = null
var sh_tmp_view: words = null
var sh_corner: words = null
var sh_cascade: int = 0            # the cascade being rendered (for casters that skip far ones)

function shadow_init() -> void {
  shadow_make_tex()
  sh_fbo = gpu_fb_new()
  gpu_fb_bind(sh_fbo)
  gpu_fb_no_color()
  gpu_fb_bind(0)
  sh_vp = words(16 * SHADOW_CASCADES)
  sh_split = words(SHADOW_CASCADES)
  sh_range = words(SHADOW_CASCADES)
  sh_texel = words(SHADOW_CASCADES)
  # the fourth slice keeps a tree-sized texel out to a kilometre; only the massif uses the last
  sh_split[0] = fi(16);  sh_split[1] = fi(60);  sh_split[2] = fi(250);  sh_split[3] = fi(1100);  sh_split[4] = fi(6000)
  sh_tmp_proj = m4_new();  sh_tmp_vp = m4_new();  sh_tmp_inv = m4_new();  sh_tmp_view = m4_new()
  sh_corner = words(3)
}

# A shadow resolution setting: 1024, 2048 or 4096 per cascade. The depth layers are made again at
# the new size; the pass attaches a layer per cascade every frame, and the lighting reads the
# texel size from the map itself, so nothing else has to follow.
function shadow_set_res(r: int) -> void {
  if r < 256 or r == shadow_res { return }
  let was = shadow_res
  shadow_res = r
  if sh_tex == 0 { return }
  gpu_tex_free(sh_tex)
  shadow_make_tex()
  # not enough video memory for that size: go back to the one that worked, and smaller again if even
  # that is refused now, rather than ending with no shadow map at all
  if not gpu_tex_ok(sh_tex) {
    shadow_refused = r
    print(`r3d: shadows: no memory for {r} x {r} cascades; keeping {was}`)
    var size = was
    shadow_res = size
    gpu_tex_free(sh_tex)
    shadow_make_tex()
    while not gpu_tex_ok(sh_tex) and size > 512 {
      size = size / 2
      shadow_res = size
      gpu_tex_free(sh_tex)
      shadow_make_tex()
    }
  }
}

function shadow_make_tex() -> void {
  sh_tex = gpu_tex_new()
  gpu_tex_bind(GPU_TEX2D_ARRAY, sh_tex)
  gpu_tex_image3d(GL_DEPTH_COMPONENT32F, shadow_res, shadow_res, SHADOW_CASCADES, GL_DEPTH_COMPONENT, GL_FLOAT, null)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_MIN_FILTER, GL_LINEAR)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_MAG_FILTER, GL_LINEAR)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_WRAP_S, GL_CLAMP_TO_BORDER)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_WRAP_T, GL_CLAMP_TO_BORDER)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_COMPARE_MODE, GL_COMPARE_REF_TO_TEXTURE)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_COMPARE_FUNC, GL_LEQUAL)
  let border = gl_floats(4)
  gl_put(border, 0, 1.0);  gl_put(border, 1, 1.0);  gl_put(border, 2, 1.0);  gl_put(border, 3, 1.0)
  gpu_tex_border(GPU_TEX2D_ARRAY, border)
  free(border)
}

# light view-projection for the camera-frustum slice [near, far]
function shadow_fit(c: int, near: int, far: int) -> void {
  # Fit the slice in VIEW space, not world space. The bounding sphere of a frustum
  # slice depends only on near/far/fov/aspect — never on where the camera is pointing —
  # so computing it here makes the radius a constant per cascade. Doing it in world
  # space (as this did) let the radius wobble as the camera turned, which changed the
  # texel size, which moved the grid the projection is snapped to, so the whole shadow
  # map resampled every frame: that is the crawl and flicker seen while moving.
  m4_perspective(sh_tmp_proj, cam_fov, cam_aspect, near, far)
  m4_inverse(sh_tmp_inv, sh_tmp_proj)          # NDC -> view space
  let cview = v3_new(F_ZERO, F_ZERO, F_ZERO)
  let corners = words(24)
  for i in 0 .. 8 {
    var x = f_neg1();  var y = f_neg1();  var z = f_neg1()
    if (i & 1) != 0 { x = F_ONE }
    if (i & 2) != 0 { y = F_ONE }
    if (i & 4) != 0 { z = F_ONE }
    let w = m4_xform_point(sh_corner, sh_tmp_inv, x, y, z)
    let iw = f_div(F_ONE, w)
    corners[i * 3] = f_mul(sh_corner[0], iw);  corners[i * 3 + 1] = f_mul(sh_corner[1], iw);  corners[i * 3 + 2] = f_mul(sh_corner[2], iw)
    cview[0] = f_add(cview[0], corners[i * 3]);  cview[1] = f_add(cview[1], corners[i * 3 + 1]);  cview[2] = f_add(cview[2], corners[i * 3 + 2])
  }
  v3_scale(cview, cview, fr(1, 8))
  var radius = F_ZERO
  for i in 0 .. 8 {
    v3_set(sh_corner, corners[i * 3], corners[i * 3 + 1], corners[i * 3 + 2])
    let d = v3_dist(sh_corner, cview)
    if f_gt(d, radius) { radius = d }
  }
  radius = f_mul(radius, fl(1.05))
  # the slice centre back into world space
  m4_inverse(sh_tmp_vp, cam_view)
  let center = words(3)
  m4_xform_point(center, sh_tmp_vp, cview[0], cview[1], cview[2])
  free(cview)
  # light view: from far along the sun direction, looking at the centre
  let eye = words(3)
  # casters up to ~900 m toward the sun (a mountain across the valley), and the
  # slice itself behind the centre: a tight depth range keeps the bias small
  let back = f_add(radius, fi(900))
  v3_madd(eye, center, sun_dir, back)
  let up = v3_new(F_ZERO, F_ONE, F_ZERO)
  m4_look_at(sh_tmp_view, eye, center, up)
  # snap the ortho window to the shadow texel grid
  let texel = f_div(f_mul(radius, F_TWO), fi(shadow_res))
  m4_xform_point(sh_corner, sh_tmp_view, center[0], center[1], center[2])
  let ox = f_sub(f_mul(f_floor(f_div(sh_corner[0], texel)), texel), sh_corner[0])
  let oy = f_sub(f_mul(f_floor(f_div(sh_corner[1], texel)), texel), sh_corner[1])
  let nr = f_neg(radius)
  let zfar = f_add(f_add(back, radius), fi(100))
  m4_ortho(sh_tmp_proj, f_add(nr, ox), f_add(radius, ox), f_add(nr, oy), f_add(radius, oy), F_ONE, zfar)
  sh_range[c] = f_sub(zfar, F_ONE)
  sh_texel[c] = texel
  let out = words(16)
  m4_mul(out, sh_tmp_proj, sh_tmp_view)
  for i in 0 .. 16 { sh_vp[c * 16 + i] = out[i] }
  free(out);  free(eye);  free(up);  free(center);  free(corners)
}

function shadow_cascade_vp(c: int) -> words { return mem_off(sh_vp, c * 64) }


# render every cascade; `draw` happens through terrain_draw_shadow + the scene's casters
function shadow_pass() -> void {
  var near = cam_near
  gpu_fb_bind(sh_fbo)
  gpu_viewport(0, 0, shadow_res, shadow_res)
  gpu_depth_test(true)
  gpu_depth_func(GL_LESS)
  gpu_depth_bias(2.0, 4.0)
  gpu_cull(false)
  for c in 0 .. SHADOW_CASCADES {
    sh_cascade = c
    shadow_fit(c, near, sh_split[c])
    prof_cpu_mark("shadow fit")
    near = sh_split[c]
    gpu_fb_depth_layer(sh_tex, c)
    if r3d_debug and c == 0 { let st = gpu_fb_status();  print(`shadow fbo status {st}`) }
    gpu_clear(GL_DEPTH_BUFFER_BIT)
    let vp = shadow_cascade_vp(c)
    # shadows off (a video setting): the cascades stay cleared, so everything reads lit
    if sh_enabled {
      if not sh_skip_terrain { terrain_draw_shadow(vp) }
      scene_draw_casters(vp)
    }
  }
  gpu_depth_bias(0.0, 0.0)
  gpu_fb_bind(0)
  if r3d_debug_shadow { shadow_dump() }
  if r3d_debug_shadow and not sh_printed2 {
    sh_printed2 = true
    let q = words(3)
    if sh_probe_x != 0 {
      let vp = shadow_cascade_vp(2)
      m4_xform_point(q, vp, sh_probe_x, sh_probe_y, sh_probe_z)
      print(`probe base ndc {f_fx(q[0])} {f_fx(q[1])} {f_fx(q[2])}`)
      m4_xform_point(q, vp, sh_probe_x, f_add(sh_probe_y, fi(15)), sh_probe_z)
      print(`probe top  ndc {f_fx(q[0])} {f_fx(q[1])} {f_fx(q[2])}  -> map texel {f_to_int(f_mul(f_add(f_mul(q[0], F_HALF), F_HALF), fi(shadow_res)))} {f_to_int(f_mul(f_add(f_mul(q[1], F_HALF), F_HALF), fi(shadow_res)))}`)
      # where the top's shadow lands on the ground: walk down the sun ray
      let gx = f_sub(f_add(sh_probe_x, F_ZERO), f_mul(sun_dir[0], f_div(fi(15), sun_dir[1])))
      let gz = f_sub(sh_probe_z, f_mul(sun_dir[2], f_div(fi(15), sun_dir[1])))
      m4_xform_point(q, vp, gx, terrain_height(gx, gz), gz)
      print(`shadow-of-top ground ndc {f_fx(q[0])} {f_fx(q[1])} {f_fx(q[2])} at {f_fx(gx)} {f_fx(gz)}`)
    }
    for c in 0 .. SHADOW_CASCADES {
      let vp = shadow_cascade_vp(c)
      # a point 5 m ahead of the camera on the ground
      let px = f_add(cam_pos[0], f_mul(cam_fwd[0], fi(5)));  let pz = f_add(cam_pos[2], f_mul(cam_fwd[2], fi(5)))
      let w = m4_xform_point(q, vp, px, terrain_height(px, pz), pz)
      print(`cascade {c}: ndc {f_fx(q[0])} {f_fx(q[1])} {f_fx(q[2])} w {f_fx(w)}  m0 {f_fx(vp[0])} m5 {f_fx(vp[5])} m14 {f_fx(vp[14])}`)
    }
    free(q)
  }
}
var sh_printed2: bool = false
var sh_printed3: bool = false
var sh_enabled: bool = true
var sh_force: int = -1   # R3D_FORCE=<c> pins every pixel to cascade c (debug)
var sh_skip_terrain: bool = false
var sh_probe_x: int = 0
var sh_probe_y: int = 0
var sh_probe_z: int = 0

# Debug: cascade depths as grey PPMs (build/dbg_shadow_<c>.ppm)
function shadow_dump() -> void {
  let n = shadow_res * shadow_res
  let buf = words(n * SHADOW_CASCADES)
  gpu_tex_bind(GPU_TEX2D_ARRAY, sh_tex)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_COMPARE_MODE, GL_NONE)
  gpu_tex_read(GPU_TEX2D_ARRAY, GL_DEPTH_COMPONENT, GL_FLOAT, buf)
  gpu_tex_param(GPU_TEX2D_ARRAY, GL_TEXTURE_COMPARE_MODE, GL_COMPARE_REF_TO_TEXTURE)
  if sh_probe_x != 0 {
    let vp = shadow_cascade_vp(2)
    let q = words(3)
    m4_xform_point(q, vp, sh_probe_x, f_add(sh_probe_y, fi(12)), sh_probe_z)
    let tx = f_to_int(f_mul(f_add(f_mul(q[0], F_HALF), F_HALF), fi(shadow_res)))
    let ty = f_to_int(f_mul(f_add(f_mul(q[1], F_HALF), F_HALF), fi(shadow_res)))
    let want = f_add(f_mul(q[2], F_HALF), F_HALF)
    print(`probe (12 m up) texel {tx} {ty} card depth {f_fx(f_mul(want, fi(1000)))}/1000`)
    for dy in 0 .. 5 {
      let yy = ty - 40 + dy * 20
      print(`  row {yy}: {f_fx(f_mul(buf[2 * n + yy * shadow_res + tx - 20], fi(1000)))} {f_fx(f_mul(buf[2 * n + yy * shadow_res + tx], fi(1000)))} {f_fx(f_mul(buf[2 * n + yy * shadow_res + tx + 20], fi(1000)))} /1000`)
    }
    free(q)
  }
  let sm = 512
  let row = bytes(sm * 3)
  for c in 0 .. SHADOW_CASCADES {
    # stretch between the map's own min and max (ignoring the far plane)
    var lo = F_ONE;  var hi = F_ZERO
    var i = 0
    while i < n { let d = buf[c * n + i];  if f_ls(d, fl(0.999)) { if f_ls(d, lo) { lo = d };  if f_gt(d, hi) { hi = d } };  i += 97 }
    print(`cascade {c} depth range {f_fx(lo)} .. {f_fx(hi)}`)
    let f = file_open(`build/dbg_shadow_{c}.ppm`, "wb")
    let hdr = `P6\n{sm} {sm}\n255\n`
    file_write(f, hdr, len(hdr))
    let st = shadow_res / sm
    for y in 0 .. sm {
      for x in 0 .. sm {
        let d = buf[c * n + (y * st) * shadow_res + x * st]
        let g = f_to_int(f_mul(f_clamp(f_div(f_sub(d, lo), f_max(f_sub(hi, lo), fl(0.0001))), F_ZERO, F_ONE), fi(255)))
        row[x * 3] = g;  row[x * 3 + 1] = g;  row[x * 3 + 2] = g
      }
      file_write(f, row, sm * 3)
    }
    file_close(f)
  }
  free(buf);  free(row)
}

var sh_printed: bool = false
# a uniform array's location: some drivers only answer to the "[0]" spelling
function sh_loc(prog: int, name: string) -> int {
  var loc = gpu_uniform(prog, name + "[0]")
  if loc < 0 { loc = gpu_uniform(prog, name) }
  return loc
}
function shadow_bind(prog: int) -> void {
  r3d_bind_tex(prog, "u_shadow", 15, GPU_TEX2D_ARRAY, sh_tex)
  # the height-field shadow (terrain.ludic); a stand-in texture keeps the unit valid before the bake
  var ts = ter_shadow_tex
  var ts_on = F_ONE
  if ts == 0 { ts = ter_height_tex;  ts_on = F_ZERO }
  r3d_bind_2d(prog, "u_tershadow", 6, ts)
  terrain_bind_height(prog)
  u_f(gpu_uniform(prog, "u_ts_on"), ts_on)
  u_f(gpu_uniform(prog, "u_ts_half"), fi(TERRAIN_HALF))
  u_f2(gpu_uniform(prog, "u_ts_origin"), ter_ox, ter_oz)
  var loc = gpu_uniform(prog, "u_cascade_vp[0]")
  if loc < 0 { loc = gpu_uniform(prog, "u_cascade_vp") }
  if r3d_debug_shadow and not sh_printed { sh_printed = true;  print(`cascade vp loc {loc} / {gpu_uniform(prog, "u_cascade_vp")}  split loc {gpu_uniform(prog, "u_cascade_split")} shadow loc {gpu_uniform(prog, "u_shadow")}`) }
  u_mat4n(loc, SHADOW_CASCADES, sh_vp)
  u_fv(sh_loc(prog, "u_cascade_split"), SHADOW_CASCADES, sh_split)
  if r3d_debug_shadow and not sh_printed3 { sh_printed3 = true;  print(`range {f_fx(sh_range[0])} {f_fx(sh_range[1])} {f_fx(sh_range[2])} {f_fx(sh_range[3])} texel*1000 {f_fx(f_mul(sh_texel[0], fi(1000)))} {f_fx(f_mul(sh_texel[1], fi(1000)))} {f_fx(f_mul(sh_texel[2], fi(1000)))} {f_fx(f_mul(sh_texel[3], fi(1000)))} locs {gpu_uniform(prog, "u_cascade_range")} {gpu_uniform(prog, "u_cascade_texel")}`) }
  u_fv(sh_loc(prog, "u_cascade_range"), SHADOW_CASCADES, sh_range)
  if r3d_env_has("R3D_FORCE") { sh_force = Text.to_int(r3d_env("R3D_FORCE")) }
  u_i(gpu_uniform(prog, "u_force_cascade"), sh_force)
  u_fv(sh_loc(prog, "u_cascade_texel"), SHADOW_CASCADES, sh_texel)
}