acdream/src/AcDream.App/Rendering/InstancedMeshRenderer.cs
Erik 31d3a4678f fix(lighting): port ACME lighting constants replacing guessed values
Replace guessed sun direction (0.5, 0.4, 0.6) with ACME's verified
value (0.5, 0.3, -0.3) from GameScene.cs:238. Replace hardcoded
ambient/diffuse (0.25/0.75) with ACME's ambient intensity 0.45 from
LandscapeEditorSettings.cs:108.

Terrain shaders now match ACME Landscape.vert/frag pattern:
- Vertex shader computes Lambert term with xLightDirection uniform
- Fragment shader applies: color * (clamp(lambert, 0, 1) + xAmbient)

Static object shader matches ACME StaticObject.vert:
- LightingFactor = max(dot(N, -L), 0) + ambient
- Removed separate uDiffuseIntensity (ACME doesn't have one)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 22:01:28 +02:00

466 lines
20 KiB
C#
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// src/AcDream.App/Rendering/InstancedMeshRenderer.cs
//
// True instanced rendering for static-object meshes.
// Groups entities by GfxObjId. All instance model matrices are written into
// a single shared instance VBO once per frame. Each sub-mesh is drawn with
// DrawElementsInstanced — one GL draw call per (GfxObj × sub-mesh) instead
// of one per entity. For a scene with N unique GfxObjs and M total entities
// this reduces draw calls from M*subMeshes to N*subMeshes.
//
// Matrix layout:
// System.Numerics.Matrix4x4 is row-major. Written to the float[] buffer in
// natural memory order (M11..M44). The GLSL shader reads 4 vec4 attributes
// (aInstanceRow0-3) and constructs mat4(row0, row1, row2, row3). Because
// GLSL mat4() takes column vectors, the rows of the C# matrix become the
// columns of the GLSL mat4 — which is the same transpose that UniformMatrix4
// with transpose=false produces. Visual result is identical to the old
// SetMatrix4("uModel", ...) path.
//
// Architecture note: public API matches StaticMeshRenderer so GameWindow only
// needs to update the shader and uniform setup at the call sites.
using System.Numerics;
using System.Runtime.InteropServices;
using AcDream.Core.Meshing;
using AcDream.Core.Terrain;
using AcDream.Core.World;
using Silk.NET.OpenGL;
namespace AcDream.App.Rendering;
public sealed unsafe class InstancedMeshRenderer : IDisposable
{
private readonly GL _gl;
private readonly Shader _shader;
private readonly TextureCache _textures;
// One GPU bundle per unique GfxObj id. Each GfxObj can have multiple sub-meshes.
private readonly Dictionary<uint, List<SubMeshGpu>> _gpuByGfxObj = new();
// Shared instance VBO — filled every frame with all instance model matrices.
private readonly uint _instanceVbo;
// Per-frame scratch: reused float buffer for instance matrix data.
// 16 floats per mat4. Grown on demand; never shrunk.
private float[] _instanceBuffer = new float[256 * 16]; // start at 256 instances
// ── Instance grouping scratch ─────────────────────────────────────────────
// Reused every frame to avoid per-frame allocation. Key = GfxObjId.
// Value = InstanceGroup (list of InstanceEntry + buffer offset for this group).
private readonly Dictionary<uint, InstanceGroup> _groups = new();
public InstancedMeshRenderer(GL gl, Shader shader, TextureCache textures)
{
_gl = gl;
_shader = shader;
_textures = textures;
_instanceVbo = _gl.GenBuffer();
}
// ── Upload ────────────────────────────────────────────────────────────────
public void EnsureUploaded(uint gfxObjId, IReadOnlyList<GfxObjSubMesh> subMeshes)
{
if (_gpuByGfxObj.ContainsKey(gfxObjId))
return;
var list = new List<SubMeshGpu>(subMeshes.Count);
foreach (var sm in subMeshes)
list.Add(UploadSubMesh(sm));
_gpuByGfxObj[gfxObjId] = list;
}
private SubMeshGpu UploadSubMesh(GfxObjSubMesh sm)
{
uint vao = _gl.GenVertexArray();
_gl.BindVertexArray(vao);
// ── Vertex buffer (positions, normals, UVs) ───────────────────────────
uint vbo = _gl.GenBuffer();
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, vbo);
fixed (void* p = sm.Vertices)
_gl.BufferData(BufferTargetARB.ArrayBuffer,
(nuint)(sm.Vertices.Length * sizeof(Vertex)), p, BufferUsageARB.StaticDraw);
uint stride = (uint)sizeof(Vertex);
_gl.EnableVertexAttribArray(0);
_gl.VertexAttribPointer(0, 3, VertexAttribPointerType.Float, false, stride, (void*)0);
_gl.EnableVertexAttribArray(1);
_gl.VertexAttribPointer(1, 3, VertexAttribPointerType.Float, false, stride, (void*)(3 * sizeof(float)));
_gl.EnableVertexAttribArray(2);
_gl.VertexAttribPointer(2, 2, VertexAttribPointerType.Float, false, stride, (void*)(6 * sizeof(float)));
// Note: location 3 (uint TerrainLayer) is NOT used by mesh_instanced.vert;
// that slot is reserved for per-instance mat4 row 0 from the instance VBO.
// ── Index buffer ──────────────────────────────────────────────────────
uint ebo = _gl.GenBuffer();
_gl.BindBuffer(BufferTargetARB.ElementArrayBuffer, ebo);
fixed (void* p = sm.Indices)
_gl.BufferData(BufferTargetARB.ElementArrayBuffer,
(nuint)(sm.Indices.Length * sizeof(uint)), p, BufferUsageARB.StaticDraw);
// ── Per-instance model matrix (locations 3-6) ─────────────────────────
// Bind the shared instance VBO. The VAO captures this binding at each
// attribute location. At draw time we re-call VertexAttribPointer with
// the per-group byte offset (to address different groups in the VBO
// without DrawElementsInstancedBaseInstance).
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
// mat4 = 4 × vec4, stride = 64 bytes, divisor = 1 (advance once per instance)
for (uint row = 0; row < 4; row++)
{
uint loc = 3 + row;
_gl.EnableVertexAttribArray(loc);
_gl.VertexAttribPointer(loc, 4, VertexAttribPointerType.Float, false, 64, (void*)(row * 16));
_gl.VertexAttribDivisor(loc, 1);
}
_gl.BindVertexArray(0);
return new SubMeshGpu
{
Vao = vao,
Vbo = vbo,
Ebo = ebo,
IndexCount = sm.Indices.Length,
SurfaceId = sm.SurfaceId,
Translucency = sm.Translucency,
};
}
// ── Draw ──────────────────────────────────────────────────────────────────
public void Draw(ICamera camera,
IEnumerable<(uint LandblockId, Vector3 AabbMin, Vector3 AabbMax, IReadOnlyList<WorldEntity> Entities)> landblockEntries,
FrustumPlanes? frustum = null,
uint? neverCullLandblockId = null)
{
_shader.Use();
// Compute combined view-projection once. System.Numerics uses row-major
// convention; multiplying View * Projection gives the correct combined
// matrix that maps world → clip space when applied as M*v in the shader.
var vp = camera.View * camera.Projection;
_shader.SetMatrix4("uViewProjection", vp);
// Lighting uniforms matching ACME StaticObject.vert:
// LightingFactor = max(dot(Normal, -uLightDirection), 0.0) + uAmbientIntensity
// LightDirection (0.5, 0.3, -0.3) from ACME GameScene.cs:238.
// AmbientLightIntensity 0.45 from ACME LandscapeEditorSettings.cs:108.
var lightDir = Vector3.Normalize(new Vector3(0.5f, 0.3f, -0.3f));
_shader.SetVec3("uLightDirection", lightDir);
_shader.SetFloat("uAmbientIntensity", 0.45f);
// ── Collect and group instances ───────────────────────────────────────
CollectGroups(landblockEntries, frustum, neverCullLandblockId);
// ── Build and upload the instance buffer ──────────────────────────────
// Count total instances.
int totalInstances = 0;
foreach (var grp in _groups.Values)
totalInstances += grp.Count;
// Grow the scratch buffer if needed.
int needed = totalInstances * 16;
if (_instanceBuffer.Length < needed)
_instanceBuffer = new float[needed + 256 * 16]; // extra headroom
// Write all groups contiguously. Record each group's starting offset
// (in units of instances, not bytes) so we can address them at draw time.
int instanceOffset = 0;
foreach (var grp in _groups.Values)
{
grp.BufferOffset = instanceOffset;
foreach (ref readonly var inst in CollectionsMarshal.AsSpan(grp.Entries))
WriteMatrix(_instanceBuffer, instanceOffset++ * 16, inst.Model);
}
// Upload all instance data in a single DynamicDraw call.
if (totalInstances > 0)
{
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
fixed (void* p = _instanceBuffer)
_gl.BufferData(BufferTargetARB.ArrayBuffer,
(nuint)(totalInstances * 16 * sizeof(float)), p, BufferUsageARB.DynamicDraw);
}
// ── Pass 1: Opaque + ClipMap ──────────────────────────────────────────
foreach (var (gfxObjId, grp) in _groups)
{
if (!_gpuByGfxObj.TryGetValue(gfxObjId, out var subMeshes))
continue;
bool hasOpaqueSubMesh = false;
foreach (var sub in subMeshes)
{
if (sub.Translucency == TranslucencyKind.Opaque ||
sub.Translucency == TranslucencyKind.ClipMap)
{
hasOpaqueSubMesh = true;
break;
}
}
if (!hasOpaqueSubMesh) continue;
// For this group, instance data starts at grp.BufferOffset in the VBO.
// We need to tell the VAO to read from that offset.
uint byteOffset = (uint)(grp.BufferOffset * 64); // 64 bytes per mat4
foreach (var sub in subMeshes)
{
if (sub.Translucency != TranslucencyKind.Opaque &&
sub.Translucency != TranslucencyKind.ClipMap)
continue;
_shader.SetInt("uTranslucencyKind", (int)sub.Translucency);
// Bind VAO + re-point instance attributes to the group's slice
// in the shared VBO. This updates the VAO's stored offset for
// locations 3-6 without touching the vertex or index bindings.
_gl.BindVertexArray(sub.Vao);
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
for (uint row = 0; row < 4; row++)
{
_gl.VertexAttribPointer(3 + row, 4, VertexAttribPointerType.Float,
false, 64, (void*)(byteOffset + row * 16));
}
// Resolve texture from the first instance (all instances in this
// group share the same GfxObj so they have compatible overrides
// only in the degenerate case of mixed-palette entities using the
// same GfxObj — rare enough to accept the approximation here).
if (grp.Count == 0) continue;
var firstEntry = grp.Entries[0];
uint tex = ResolveTex(firstEntry.Entity, firstEntry.MeshRef, sub);
_gl.ActiveTexture(TextureUnit.Texture0);
_gl.BindTexture(TextureTarget.Texture2D, tex);
_gl.DrawElementsInstanced(PrimitiveType.Triangles,
(uint)sub.IndexCount,
DrawElementsType.UnsignedInt,
(void*)0,
(uint)grp.Count);
}
}
// ── Pass 2: Translucent (AlphaBlend, Additive, InvAlpha) ─────────────
_gl.Enable(EnableCap.Blend);
_gl.DepthMask(false);
_gl.Enable(EnableCap.CullFace);
_gl.CullFace(TriangleFace.Back);
_gl.FrontFace(FrontFaceDirection.Ccw);
foreach (var (gfxObjId, grp) in _groups)
{
if (!_gpuByGfxObj.TryGetValue(gfxObjId, out var subMeshes))
continue;
bool hasTranslucentSubMesh = false;
foreach (var sub in subMeshes)
{
if (sub.Translucency != TranslucencyKind.Opaque &&
sub.Translucency != TranslucencyKind.ClipMap)
{
hasTranslucentSubMesh = true;
break;
}
}
if (!hasTranslucentSubMesh) continue;
uint byteOffset = (uint)(grp.BufferOffset * 64);
foreach (var sub in subMeshes)
{
if (sub.Translucency == TranslucencyKind.Opaque ||
sub.Translucency == TranslucencyKind.ClipMap)
continue;
switch (sub.Translucency)
{
case TranslucencyKind.Additive:
_gl.BlendFunc(BlendingFactor.SrcAlpha, BlendingFactor.One);
break;
case TranslucencyKind.InvAlpha:
_gl.BlendFunc(BlendingFactor.OneMinusSrcAlpha, BlendingFactor.SrcAlpha);
break;
default: // AlphaBlend
_gl.BlendFunc(BlendingFactor.SrcAlpha, BlendingFactor.OneMinusSrcAlpha);
break;
}
_shader.SetInt("uTranslucencyKind", (int)sub.Translucency);
_gl.BindVertexArray(sub.Vao);
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
for (uint row = 0; row < 4; row++)
{
_gl.VertexAttribPointer(3 + row, 4, VertexAttribPointerType.Float,
false, 64, (void*)(byteOffset + row * 16));
}
if (grp.Count == 0) continue;
var firstEntry = grp.Entries[0];
uint tex = ResolveTex(firstEntry.Entity, firstEntry.MeshRef, sub);
_gl.ActiveTexture(TextureUnit.Texture0);
_gl.BindTexture(TextureTarget.Texture2D, tex);
_gl.DrawElementsInstanced(PrimitiveType.Triangles,
(uint)sub.IndexCount,
DrawElementsType.UnsignedInt,
(void*)0,
(uint)grp.Count);
}
}
// Restore default GL state.
_gl.DepthMask(true);
_gl.Disable(EnableCap.Blend);
_gl.Disable(EnableCap.CullFace);
_gl.BindVertexArray(0);
}
// ── Grouping ──────────────────────────────────────────────────────────────
/// <summary>
/// Iterates all visible landblock entries and groups every (entity, meshRef)
/// pair by GfxObjId. Clears previous frame's groups before filling.
/// </summary>
private void CollectGroups(
IEnumerable<(uint LandblockId, Vector3 AabbMin, Vector3 AabbMax, IReadOnlyList<WorldEntity> Entities)> landblockEntries,
FrustumPlanes? frustum,
uint? neverCullLandblockId)
{
foreach (var grp in _groups.Values)
grp.Entries.Clear();
foreach (var entry in landblockEntries)
{
if (frustum is not null &&
entry.LandblockId != neverCullLandblockId &&
!FrustumCuller.IsAabbVisible(frustum.Value, entry.AabbMin, entry.AabbMax))
continue;
foreach (var entity in entry.Entities)
{
if (entity.MeshRefs.Count == 0)
continue;
var entityRoot =
Matrix4x4.CreateFromQuaternion(entity.Rotation) *
Matrix4x4.CreateTranslation(entity.Position);
foreach (var meshRef in entity.MeshRefs)
{
if (!_gpuByGfxObj.ContainsKey(meshRef.GfxObjId))
continue;
var model = meshRef.PartTransform * entityRoot;
if (!_groups.TryGetValue(meshRef.GfxObjId, out var group))
{
group = new InstanceGroup();
_groups[meshRef.GfxObjId] = group;
}
group.Entries.Add(new InstanceEntry(model, entity, meshRef));
}
}
}
}
// ── Matrix write ──────────────────────────────────────────────────────────
/// <summary>
/// Writes a System.Numerics Matrix4x4 into <paramref name="buf"/> starting
/// at <paramref name="offset"/> as 16 consecutive floats in row-major order
/// (the C# natural memory layout). The GLSL shader reads each 4-float row
/// as a column of the mat4 — identical to what UniformMatrix4(transpose=false)
/// produces for the uniform path.
/// </summary>
private static void WriteMatrix(float[] buf, int offset, in Matrix4x4 m)
{
buf[offset + 0] = m.M11; buf[offset + 1] = m.M12; buf[offset + 2] = m.M13; buf[offset + 3] = m.M14;
buf[offset + 4] = m.M21; buf[offset + 5] = m.M22; buf[offset + 6] = m.M23; buf[offset + 7] = m.M24;
buf[offset + 8] = m.M31; buf[offset + 9] = m.M32; buf[offset + 10] = m.M33; buf[offset + 11] = m.M34;
buf[offset + 12] = m.M41; buf[offset + 13] = m.M42; buf[offset + 14] = m.M43; buf[offset + 15] = m.M44;
}
// ── Texture resolution ────────────────────────────────────────────────────
private uint ResolveTex(WorldEntity entity, MeshRef meshRef, SubMeshGpu sub)
{
uint overrideOrigTex = 0;
bool hasOrigTexOverride = meshRef.SurfaceOverrides is not null
&& meshRef.SurfaceOverrides.TryGetValue(sub.SurfaceId, out overrideOrigTex);
uint? origTexOverride = hasOrigTexOverride ? overrideOrigTex : (uint?)null;
if (entity.PaletteOverride is not null)
{
return _textures.GetOrUploadWithPaletteOverride(
sub.SurfaceId, origTexOverride, entity.PaletteOverride);
}
else if (hasOrigTexOverride)
{
return _textures.GetOrUploadWithOrigTextureOverride(sub.SurfaceId, overrideOrigTex);
}
else
{
return _textures.GetOrUpload(sub.SurfaceId);
}
}
// ── Disposal ──────────────────────────────────────────────────────────────
public void Dispose()
{
foreach (var subs in _gpuByGfxObj.Values)
{
foreach (var sub in subs)
{
_gl.DeleteBuffer(sub.Vbo);
_gl.DeleteBuffer(sub.Ebo);
_gl.DeleteVertexArray(sub.Vao);
}
}
_gl.DeleteBuffer(_instanceVbo);
_gpuByGfxObj.Clear();
_groups.Clear();
}
// ── Private types ─────────────────────────────────────────────────────────
private sealed class SubMeshGpu
{
public uint Vao;
public uint Vbo;
public uint Ebo;
public int IndexCount;
public uint SurfaceId;
public TranslucencyKind Translucency;
}
/// <summary>
/// All instances of one GfxObj for this frame, plus their starting offset
/// in the shared instance VBO (in units of instances, not bytes).
/// </summary>
private sealed class InstanceGroup
{
public readonly List<InstanceEntry> Entries = new();
public int BufferOffset;
public int Count => Entries.Count;
}
private readonly struct InstanceEntry
{
public readonly Matrix4x4 Model;
public readonly WorldEntity Entity;
public readonly MeshRef MeshRef;
public InstanceEntry(Matrix4x4 model, WorldEntity entity, MeshRef meshRef)
{
Model = model;
Entity = entity;
MeshRef = meshRef;
}
}
}