perf(rendering): preserve alpha order with bindless particles

Carry each billboard particle's resident texture handle in the instance ABI so stable retail alpha ordering can batch mixed textures without rebinding and redrawing each short texture run. Keep DAT blend transitions as the only billboard draw boundary.

The connected 0xC95B stress scene improved from 6 FPS / 171 ms to about 153 FPS / 6.6 ms at the same roughly 21,000 visible entities. Release build succeeds and all 5,916 tests pass with five intentional skips.

Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Erik 2026-07-18 08:32:21 +02:00
parent 6b0472ee32
commit 2cbf34a668
7 changed files with 150 additions and 57 deletions

View file

@ -1,6 +1,7 @@
using System;
using System.Collections.Generic;
using System.Numerics;
using System.Runtime.InteropServices;
using AcDream.App.Rendering.Wb;
using AcDream.Content;
using AcDream.Core.Meshing;
@ -20,7 +21,10 @@ namespace AcDream.App.Rendering;
/// </summary>
public sealed unsafe class ParticleRenderer : IDisposable
{
private readonly record struct BatchKey(uint TextureHandle, bool UseTexture, bool Additive);
// The texture is per instance through GL_ARB_bindless_texture. Only blend
// state remains a draw-call boundary, so stable retail distance order no
// longer degenerates into one draw per alternating particle texture.
private readonly record struct BatchKey(bool Additive);
private readonly record struct ParticleDraw(BatchKey Key, ParticleInstance Instance);
private readonly record struct MeshBatchKey(uint GfxObjId, int BatchIndex);
private readonly record struct MeshParticleDraw(
@ -39,18 +43,42 @@ public sealed unsafe class ParticleRenderer : IDisposable
public readonly Vector3 AxisX;
public readonly Vector3 AxisY;
public readonly uint ColorArgb;
public readonly ulong TextureHandle;
public readonly float DistanceSq;
public ParticleInstance(Vector3 position, Vector3 axisX, Vector3 axisY, uint colorArgb, float distanceSq)
public ParticleInstance(
Vector3 position,
Vector3 axisX,
Vector3 axisY,
uint colorArgb,
ulong textureHandle,
float distanceSq)
{
Position = position;
AxisX = axisX;
AxisY = axisY;
ColorArgb = colorArgb;
TextureHandle = textureHandle;
DistanceSq = distanceSq;
}
}
/// <summary>
/// Vertex-instance ABI shared with particle.vert. The resident texture
/// handle is carried per particle so ordered particles using different
/// textures remain one instanced draw when their blend mode matches.
/// </summary>
[StructLayout(LayoutKind.Sequential)]
internal struct BillboardGpuInstance
{
public Vector4 Center;
public Vector4 AxisX;
public Vector4 AxisY;
public Vector4 Color;
public uint TextureHandleLow;
public uint TextureHandleHigh;
}
private readonly struct MeshParticleInstance
{
public readonly Matrix4x4 Model;
@ -89,7 +117,7 @@ public sealed unsafe class ParticleRenderer : IDisposable
private readonly uint _meshVao;
private readonly uint _meshInstanceVbo;
private float[] _instanceScratch = new float[256 * 16];
private BillboardGpuInstance[] _instanceScratch = new BillboardGpuInstance[256];
private float[] _meshInstanceScratch = new float[256 * 20];
// MP-Alloc (2026-07-05): Draw() is called up to ~11 times per frame
@ -193,20 +221,33 @@ public sealed unsafe class ParticleRenderer : IDisposable
_instanceVbo = _gl.GenBuffer();
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
_gl.BufferData(BufferTargetARB.ArrayBuffer, (nuint)(256 * 16 * sizeof(float)), (void*)0, BufferUsageARB.DynamicDraw);
uint instanceStride = (uint)sizeof(BillboardGpuInstance);
_gl.BufferData(
BufferTargetARB.ArrayBuffer,
(nuint)(256 * instanceStride),
(void*)0,
BufferUsageARB.DynamicDraw);
_gl.EnableVertexAttribArray(2);
_gl.VertexAttribPointer(2, 4, VertexAttribPointerType.Float, false, 16 * sizeof(float), (void*)0);
_gl.VertexAttribPointer(2, 4, VertexAttribPointerType.Float, false, instanceStride, (void*)0);
_gl.VertexAttribDivisor(2, 1);
_gl.EnableVertexAttribArray(3);
_gl.VertexAttribPointer(3, 4, VertexAttribPointerType.Float, false, 16 * sizeof(float), (void*)(4 * sizeof(float)));
_gl.VertexAttribPointer(3, 4, VertexAttribPointerType.Float, false, instanceStride, (void*)(4 * sizeof(float)));
_gl.VertexAttribDivisor(3, 1);
_gl.EnableVertexAttribArray(4);
_gl.VertexAttribPointer(4, 4, VertexAttribPointerType.Float, false, 16 * sizeof(float), (void*)(8 * sizeof(float)));
_gl.VertexAttribPointer(4, 4, VertexAttribPointerType.Float, false, instanceStride, (void*)(8 * sizeof(float)));
_gl.VertexAttribDivisor(4, 1);
_gl.EnableVertexAttribArray(5);
_gl.VertexAttribPointer(5, 4, VertexAttribPointerType.Float, false, 16 * sizeof(float), (void*)(12 * sizeof(float)));
_gl.VertexAttribPointer(5, 4, VertexAttribPointerType.Float, false, instanceStride, (void*)(12 * sizeof(float)));
_gl.VertexAttribDivisor(5, 1);
_gl.EnableVertexAttribArray(6);
_gl.VertexAttribIPointer(
6,
2,
VertexAttribIType.UnsignedInt,
instanceStride,
(void*)(16 * sizeof(float)));
_gl.VertexAttribDivisor(6, 1);
_gl.BindVertexArray(0);
@ -289,7 +330,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
_gl.Enable(EnableCap.DepthTest);
_gl.Enable(EnableCap.Blend);
_gl.DepthMask(false);
_gl.ActiveTexture(TextureUnit.Texture0);
ParticleSubmissionKind? activeKind = null;
for (int i = 0; i < _submissionScratch.Count;)
@ -320,8 +360,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
_gl.BlendFunc(
BlendingFactor.SrcAlpha,
key.Additive ? BlendingFactor.One : BlendingFactor.OneMinusSrcAlpha);
_shader.SetInt("uUseTexture", key.UseTexture ? 1 : 0);
_gl.BindTexture(TextureTarget.Texture2D, key.UseTexture ? key.TextureHandle : 0);
DrawInstances(_runScratch);
continue;
}
@ -383,7 +421,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
(int)batch.BaseVertex);
}
_gl.BindTexture(TextureTarget.Texture2D, 0);
_gl.BindVertexArray(0);
_gl.DepthMask(true);
_gl.Disable(EnableCap.Blend);
@ -399,7 +436,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
_gl.Enable(EnableCap.DepthTest);
_gl.Enable(EnableCap.Blend);
_gl.DepthMask(false);
_gl.ActiveTexture(TextureUnit.Texture0);
ParticleSubmissionKind? activeKind = null;
Matrix4x4 activeViewProjection = default;
@ -435,8 +471,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
_gl.BlendFunc(
BlendingFactor.SrcAlpha,
key.Additive ? BlendingFactor.One : BlendingFactor.OneMinusSrcAlpha);
_shader.SetInt("uUseTexture", key.UseTexture ? 1 : 0);
_gl.BindTexture(TextureTarget.Texture2D, key.UseTexture ? key.TextureHandle : 0);
DrawInstances(_runScratch);
continue;
}
@ -501,7 +535,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
(int)batch.BaseVertex);
}
_gl.BindTexture(TextureTarget.Texture2D, 0);
_gl.BindVertexArray(0);
_gl.DepthMask(true);
_gl.Disable(EnableCap.Blend);
@ -512,7 +545,6 @@ public sealed unsafe class ParticleRenderer : IDisposable
{
_shader.Use();
_shader.SetMatrix4("uViewProjection", viewProjection);
_shader.SetInt("uParticleTexture", 0);
_gl.Disable(EnableCap.CullFace);
_gl.BindVertexArray(_quadVao);
}
@ -598,12 +630,10 @@ public sealed unsafe class ParticleRenderer : IDisposable
}
var gfxInfo = ResolveParticleGfxInfo(em.Desc);
uint texture = gfxInfo.TextureHandle;
bool useTexture = texture != 0;
bool additive = gfxInfo.HasMaterial
? gfxInfo.Additive
: (em.Desc.Flags & EmitterFlags.Additive) != 0;
var key = new BatchKey(texture, useTexture, additive);
var key = new BatchKey(additive);
Vector3 axisX;
Vector3 axisY;
if (gfxInfo.IsBillboard)
@ -623,7 +653,15 @@ public sealed unsafe class ParticleRenderer : IDisposable
float distSq = Vector3.DistanceSquared(pos, cameraWorldPos);
int drawIndex = draws.Count;
draws.Add(new ParticleDraw(key, new ParticleInstance(pos, axisX, axisY, p.ColorArgb, distSq)));
draws.Add(new ParticleDraw(
key,
new ParticleInstance(
pos,
axisX,
axisY,
p.ColorArgb,
gfxInfo.TextureHandle,
distSq)));
_submissionScratch.Add(new ParticleSubmission(
ParticleSubmissionKind.Billboard,
drawIndex,
@ -689,33 +727,25 @@ public sealed unsafe class ParticleRenderer : IDisposable
if (instances.Count == 0)
return;
int needed = instances.Count * 16;
if (_instanceScratch.Length < needed)
_instanceScratch = new float[needed + 256 * 16];
if (_instanceScratch.Length < instances.Count)
_instanceScratch = new BillboardGpuInstance[instances.Count + 256];
for (int i = 0; i < instances.Count; i++)
{
var p = instances[i];
int o = i * 16;
_instanceScratch[o + 0] = p.Position.X;
_instanceScratch[o + 1] = p.Position.Y;
_instanceScratch[o + 2] = p.Position.Z;
_instanceScratch[o + 3] = 0f;
_instanceScratch[o + 4] = p.AxisX.X;
_instanceScratch[o + 5] = p.AxisX.Y;
_instanceScratch[o + 6] = p.AxisX.Z;
_instanceScratch[o + 7] = 0f;
_instanceScratch[o + 8] = p.AxisY.X;
_instanceScratch[o + 9] = p.AxisY.Y;
_instanceScratch[o + 10] = p.AxisY.Z;
_instanceScratch[o + 11] = 0f;
_instanceScratch[o + 12] = ((p.ColorArgb >> 16) & 0xFF) / 255f;
_instanceScratch[o + 13] = ((p.ColorArgb >> 8) & 0xFF) / 255f;
_instanceScratch[o + 14] = (p.ColorArgb & 0xFF) / 255f;
_instanceScratch[o + 15] = ((p.ColorArgb >> 24) & 0xFF) / 255f;
_instanceScratch[i] = new BillboardGpuInstance
{
Center = new Vector4(p.Position, 0f),
AxisX = new Vector4(p.AxisX, 0f),
AxisY = new Vector4(p.AxisY, 0f),
Color = new Vector4(
((p.ColorArgb >> 16) & 0xFF) / 255f,
((p.ColorArgb >> 8) & 0xFF) / 255f,
(p.ColorArgb & 0xFF) / 255f,
((p.ColorArgb >> 24) & 0xFF) / 255f),
TextureHandleLow = (uint)(p.TextureHandle & 0xFFFFFFFFu),
TextureHandleHigh = (uint)(p.TextureHandle >> 32),
};
}
_gl.BindBuffer(BufferTargetARB.ArrayBuffer, _instanceVbo);
@ -723,7 +753,7 @@ public sealed unsafe class ParticleRenderer : IDisposable
{
_gl.BufferData(
BufferTargetARB.ArrayBuffer,
(nuint)(instances.Count * 16 * sizeof(float)),
(nuint)(instances.Count * sizeof(BillboardGpuInstance)),
bp,
BufferUsageARB.DynamicDraw);
}
@ -853,7 +883,7 @@ public sealed unsafe class ParticleRenderer : IDisposable
if (desc.TextureSurfaceId != 0)
return ParticleGfxInfo.Billboard(
_textures.GetOrUpload(desc.TextureSurfaceId),
_textures.GetOrUploadBindless(desc.TextureSurfaceId),
Vector2.One,
Vector3.Zero,
additive: (desc.Flags & EmitterFlags.Additive) != 0,
@ -881,7 +911,9 @@ public sealed unsafe class ParticleRenderer : IDisposable
return ParticleGfxInfo.Default;
uint surfaceId = gfx.Surfaces.Count > 0 ? gfx.Surfaces[0].DataId : 0u;
uint texture = surfaceId != 0 && _textures is not null ? _textures.GetOrUpload(surfaceId) : 0u;
ulong texture = surfaceId != 0 && _textures is not null
? _textures.GetOrUploadBindless(surfaceId)
: 0u;
bool additive = false;
if (surfaceId != 0)
{
@ -896,7 +928,7 @@ public sealed unsafe class ParticleRenderer : IDisposable
}
}
private ParticleGfxInfo AuthoredParticleGfxInfo(GfxObj gfx, uint texture, bool additive, bool hasMaterial)
private ParticleGfxInfo AuthoredParticleGfxInfo(GfxObj gfx, ulong texture, bool additive, bool hasMaterial)
{
if (gfx.VertexArray.Vertices.Count == 0)
return ParticleGfxInfo.Billboard(texture, Vector2.One, Vector3.Zero, additive, hasMaterial);
@ -1026,7 +1058,7 @@ public sealed unsafe class ParticleRenderer : IDisposable
}
private readonly record struct ParticleGfxInfo(
uint TextureHandle,
ulong TextureHandle,
Vector2 Size,
Vector3 AxisX,
Vector3 AxisY,
@ -1036,10 +1068,10 @@ public sealed unsafe class ParticleRenderer : IDisposable
bool HasMaterial)
{
public static ParticleGfxInfo Default { get; } =
Billboard(0u, Vector2.One, Vector3.Zero, additive: false, hasMaterial: false);
Billboard(0ul, Vector2.One, Vector3.Zero, additive: false, hasMaterial: false);
public static ParticleGfxInfo Billboard(
uint textureHandle,
ulong textureHandle,
Vector2 size,
Vector3 centerOffset,
bool additive,

View file

@ -1,16 +1,16 @@
#version 430 core
#extension GL_ARB_bindless_texture : require
in vec2 vTex;
in vec4 vColor;
flat in uvec2 vTextureHandle;
out vec4 fragColor;
uniform sampler2D uParticleTexture;
uniform bool uUseTexture;
void main() {
vec4 texel;
if (uUseTexture) {
texel = texture(uParticleTexture, vTex);
if (any(notEqual(vTextureHandle, uvec2(0)))) {
sampler2DArray particleTexture = sampler2DArray(vTextureHandle);
texel = texture(particleTexture, vec3(vTex, 0.0));
} else {
vec2 d = vTex - vec2(0.5, 0.5);
float r = length(d) * 2.0;

View file

@ -9,11 +9,13 @@ layout(location = 2) in vec4 aCenter;
layout(location = 3) in vec4 aAxisX;
layout(location = 4) in vec4 aAxisY;
layout(location = 5) in vec4 aColor;
layout(location = 6) in uvec2 aTextureHandle;
uniform mat4 uViewProjection;
out vec2 vTex;
out vec4 vColor;
flat out uvec2 vTextureHandle;
void main() {
vec3 world = aCenter.xyz
@ -22,5 +24,6 @@ void main() {
vTex = aTex;
vColor = aColor;
vTextureHandle = aTextureHandle;
gl_Position = uViewProjection * vec4(world, 1.0);
}