Implement experimental GPU two-phase occlusion culling for the standard 3D mesh pipeline.

Cargo.toml

@@ -4132,3 +4132,14 @@ name = "Clustered Decals"
 description = "Demonstrates clustered decals"
 category = "3D Rendering"
 wasm = false
+
+[[example]]
+name = "occlusion_culling"
+path = "examples/3d/occlusion_culling.rs"
+doc-scrape-examples = true
+
+[package.metadata.example.occlusion_culling]
+name = "Occlusion Culling"
+description = "Demonstration of Occlusion Culling"
+category = "3D Rendering"
+wasm = false

crates/bevy_core_pipeline/Cargo.toml

@@ -47,6 +47,7 @@ nonmax = "0.5"
 smallvec = "1"
 thiserror = { version = "2", default-features = false }
 tracing = { version = "0.1", default-features = false, features = ["std"] }
+bytemuck = { version = "1" }
 
 [lints]
 workspace = true

crates/bevy_core_pipeline/src/core_2d/mod.rs

@@ -312,6 +312,8 @@ impl PhaseItem for AlphaMask2d {
 }
 
 impl BinnedPhaseItem for AlphaMask2d {
+    // Since 2D meshes presently can't be multidrawn, the batch set key is
+    // irrelevant.
     type BatchSetKey = BatchSetKey2d;
 
     type BinKey = AlphaMask2dBinKey;

crates/bevy_core_pipeline/src/core_3d/mod.rs

@@ -16,7 +16,9 @@ pub mod graph {
     #[derive(Debug, Hash, PartialEq, Eq, Clone, RenderLabel)]
     pub enum Node3d {
         MsaaWriteback,
-        Prepass,
+        EarlyPrepass,
+        EarlyDownsampleDepth,
+        LatePrepass,
         DeferredPrepass,
         CopyDeferredLightingId,
         EndPrepasses,
@@ -25,6 +27,7 @@ pub mod graph {
         MainTransmissivePass,
         MainTransparentPass,
         EndMainPass,
+        LateDownsampleDepth,
         Taa,
         MotionBlur,
         Bloom,
@@ -67,9 +70,10 @@ use core::ops::Range;
 
 use bevy_render::{
     batching::gpu_preprocessing::{GpuPreprocessingMode, GpuPreprocessingSupport},
+    experimental::occlusion_culling::OcclusionCulling,
     mesh::allocator::SlabId,
     render_phase::PhaseItemBatchSetKey,
-    view::{NoIndirectDrawing, RetainedViewEntity},
+    view::{prepare_view_targets, NoIndirectDrawing, RetainedViewEntity},
 };
 pub use camera_3d::*;
 pub use main_opaque_pass_3d_node::*;
@@ -114,8 +118,9 @@ use crate::{
     },
     dof::DepthOfFieldNode,
     prepass::{
-        node::PrepassNode, AlphaMask3dPrepass, DeferredPrepass, DepthPrepass, MotionVectorPrepass,
-        NormalPrepass, Opaque3dPrepass, OpaqueNoLightmap3dBatchSetKey, OpaqueNoLightmap3dBinKey,
+        node::{EarlyPrepassNode, LatePrepassNode},
+        AlphaMask3dPrepass, DeferredPrepass, DepthPrepass, MotionVectorPrepass, NormalPrepass,
+        Opaque3dPrepass, OpaqueNoLightmap3dBatchSetKey, OpaqueNoLightmap3dBinKey,
         ViewPrepassTextures, MOTION_VECTOR_PREPASS_FORMAT, NORMAL_PREPASS_FORMAT,
     },
     skybox::SkyboxPlugin,
@@ -161,6 +166,9 @@ impl Plugin for Core3dPlugin {
                 (
                     sort_phase_system::<Transmissive3d>.in_set(RenderSet::PhaseSort),
                     sort_phase_system::<Transparent3d>.in_set(RenderSet::PhaseSort),
+                    configure_occlusion_culling_view_targets
+                        .after(prepare_view_targets)
+                        .in_set(RenderSet::ManageViews),
                     prepare_core_3d_depth_textures.in_set(RenderSet::PrepareResources),
                     prepare_core_3d_transmission_textures.in_set(RenderSet::PrepareResources),
                     prepare_prepass_textures.in_set(RenderSet::PrepareResources),
@@ -169,7 +177,8 @@ impl Plugin for Core3dPlugin {
 
         render_app
             .add_render_sub_graph(Core3d)
-            .add_render_graph_node::<ViewNodeRunner<PrepassNode>>(Core3d, Node3d::Prepass)
+            .add_render_graph_node::<ViewNodeRunner<EarlyPrepassNode>>(Core3d, Node3d::EarlyPrepass)
+            .add_render_graph_node::<ViewNodeRunner<LatePrepassNode>>(Core3d, Node3d::LatePrepass)
             .add_render_graph_node::<ViewNodeRunner<DeferredGBufferPrepassNode>>(
                 Core3d,
                 Node3d::DeferredPrepass,
@@ -200,7 +209,8 @@ impl Plugin for Core3dPlugin {
             .add_render_graph_edges(
                 Core3d,
                 (
-                    Node3d::Prepass,
+                    Node3d::EarlyPrepass,
+                    Node3d::LatePrepass,
                     Node3d::DeferredPrepass,
                     Node3d::CopyDeferredLightingId,
                     Node3d::EndPrepasses,
@@ -898,6 +908,28 @@ pub fn prepare_core_3d_transmission_textures(
     }
 }
 
+/// Sets the `TEXTURE_BINDING` flag on the depth texture if necessary for
+/// occlusion culling.
+///
+/// We need that flag to be set in order to read from the texture.
+fn configure_occlusion_culling_view_targets(
+    mut view_targets: Query<
+        &mut Camera3d,
+        (
+            With<OcclusionCulling>,
+            Without<NoIndirectDrawing>,
+            With<DepthPrepass>,
+            Without<DeferredPrepass>,
+        ),
+    >,
+) {
+    for mut camera_3d in &mut view_targets {
+        let mut depth_texture_usages = TextureUsages::from(camera_3d.depth_texture_usages);
+        depth_texture_usages |= TextureUsages::TEXTURE_BINDING;
+        camera_3d.depth_texture_usages = depth_texture_usages.into();
+    }
+}
+
 // Disable MSAA and warn if using deferred rendering
 pub fn check_msaa(mut deferred_views: Query<&mut Msaa, (With<Camera>, With<DeferredPrepass>)>) {
     for mut msaa in deferred_views.iter_mut() {

crates/bevy_pbr/src/meshlet/downsample_depth.wgsl → crates/bevy_core_pipeline/src/experimental/mip_generation/downsample_depth.wgsl

@@ -1,8 +1,16 @@
 #ifdef MESHLET_VISIBILITY_BUFFER_RASTER_PASS_OUTPUT
 @group(0) @binding(0) var<storage, read> mip_0: array<u64>; // Per pixel
 #else
+#ifdef MESHLET
 @group(0) @binding(0) var<storage, read> mip_0: array<u32>; // Per pixel
-#endif
+#else   // MESHLET
+#ifdef MULTISAMPLE
+@group(0) @binding(0) var mip_0: texture_depth_multisampled_2d;
+#else   // MULTISAMPLE
+@group(0) @binding(0) var mip_0: texture_depth_2d;
+#endif  // MULTISAMPLE
+#endif  // MESHLET
+#endif  // MESHLET_VISIBILITY_BUFFER_RASTER_PASS_OUTPUT
 @group(0) @binding(1) var mip_1: texture_storage_2d<r32float, write>;
 @group(0) @binding(2) var mip_2: texture_storage_2d<r32float, write>;
 @group(0) @binding(3) var mip_3: texture_storage_2d<r32float, write>;
@@ -304,9 +312,25 @@ fn load_mip_0(x: u32, y: u32) -> f32 {
     let i = y * constants.view_width + x;
 #ifdef MESHLET_VISIBILITY_BUFFER_RASTER_PASS_OUTPUT
     return bitcast<f32>(u32(mip_0[i] >> 32u));
-#else
+#else   // MESHLET_VISIBILITY_BUFFER_RASTER_PASS_OUTPUT
+#ifdef MESHLET
     return bitcast<f32>(mip_0[i]);
-#endif
+#else   // MESHLET
+    // Downsample the top level.
+#ifdef MULTISAMPLE
+    // The top level is multisampled, so we need to loop over all the samples
+    // and reduce them to 1.
+    var result = textureLoad(mip_0, vec2(x, y), 0);
+    let sample_count = i32(textureNumSamples(mip_0));
+    for (var sample = 1; sample < sample_count; sample += 1) {
+        result = min(result, textureLoad(mip_0, vec2(x, y), sample));
+    }
+    return result;
+#else   // MULTISAMPLE
+    return textureLoad(mip_0, vec2(x, y), 0);
+#endif  // MULTISAMPLE
+#endif  // MESHLET
+#endif  // MESHLET_VISIBILITY_BUFFER_RASTER_PASS_OUTPUT
 }
 
 fn reduce_4(v: vec4f) -> f32 {