Use GpuArrayBuffer for MeshUniform

assets/shaders/custom_vertex_attribute.wgsl

@@ -8,6 +8,7 @@ struct CustomMaterial {
 var<uniform> material: CustomMaterial;
 
 struct Vertex {
+    @builtin(instance_index) instance_index: u32,
     @location(0) position: vec3<f32>,
     @location(1) blend_color: vec4<f32>,
 };
@@ -21,8 +22,8 @@ struct VertexOutput {
 fn vertex(vertex: Vertex) -> VertexOutput {
     var out: VertexOutput;
     out.clip_position = mesh_position_local_to_clip(
-        mesh.model,
-        vec4<f32>(vertex.position, 1.0)
+        mesh[vertex.instance_index].model,
+        vec4<f32>(vertex.position, 1.0),
     );
     out.blend_color = vertex.blend_color;
     return out;

assets/shaders/instancing.wgsl

@@ -19,8 +19,12 @@ struct VertexOutput {
 fn vertex(vertex: Vertex) -> VertexOutput {
     let position = vertex.position * vertex.i_pos_scale.w + vertex.i_pos_scale.xyz;
     var out: VertexOutput;
+    // NOTE: The 0 index into the Mesh array is a hack for this example as the
+    // instance_index builtin would map to the wrong index in the Mesh array.
+    // This index could be passed in via another uniform instead but it's
+    // unnecessary for the example.
     out.clip_position = mesh_position_local_to_clip(
-        mesh.model, 
+        mesh[0].model,
         vec4<f32>(position, 1.0)
     );
     out.color = vertex.i_color;

crates/bevy_core_pipeline/src/core_3d/mod.rs

@@ -136,14 +136,18 @@ impl Plugin for Core3dPlugin {
 
 pub struct Opaque3d {
     pub distance: f32,
+    // Per-object data may be bound at different dynamic offsets within a buffer. If it is, then
+    // each batch of per-object data starts at the same dynamic offset.
+    pub per_object_binding_dynamic_offset: u32,
     pub pipeline: CachedRenderPipelineId,
     pub entity: Entity,
     pub draw_function: DrawFunctionId,
 }
 
 impl PhaseItem for Opaque3d {
+    // NOTE: (dynamic offset, -distance)
     // NOTE: Values increase towards the camera. Front-to-back ordering for opaque means we need a descending sort.
-    type SortKey = Reverse<FloatOrd>;
+    type SortKey = (u32, Reverse<FloatOrd>);
 
     #[inline]
     fn entity(&self) -> Entity {
@@ -152,7 +156,10 @@ impl PhaseItem for Opaque3d {
 
     #[inline]
     fn sort_key(&self) -> Self::SortKey {
-        Reverse(FloatOrd(self.distance))
+        (
+            self.per_object_binding_dynamic_offset,
+            Reverse(FloatOrd(self.distance)),
+        )
     }
 
     #[inline]
@@ -163,7 +170,9 @@ impl PhaseItem for Opaque3d {
     #[inline]
     fn sort(items: &mut [Self]) {
         // Key negated to match reversed SortKey ordering
-        radsort::sort_by_key(items, |item| -item.distance);
+        radsort::sort_by_key(items, |item| {
+            (item.per_object_binding_dynamic_offset, -item.distance)
+        });
     }
 }
 
@@ -176,14 +185,18 @@ impl CachedRenderPipelinePhaseItem for Opaque3d {
 
 pub struct AlphaMask3d {
     pub distance: f32,
+    // Per-object data may be bound at different dynamic offsets within a buffer. If it is, then
+    // each batch of per-object data starts at the same dynamic offset.
+    pub per_object_binding_dynamic_offset: u32,
     pub pipeline: CachedRenderPipelineId,
     pub entity: Entity,
     pub draw_function: DrawFunctionId,
 }
 
 impl PhaseItem for AlphaMask3d {
+    // NOTE: (dynamic offset, -distance)
     // NOTE: Values increase towards the camera. Front-to-back ordering for alpha mask means we need a descending sort.
-    type SortKey = Reverse<FloatOrd>;
+    type SortKey = (u32, Reverse<FloatOrd>);
 
     #[inline]
     fn entity(&self) -> Entity {
@@ -192,7 +205,10 @@ impl PhaseItem for AlphaMask3d {
 
     #[inline]
     fn sort_key(&self) -> Self::SortKey {
-        Reverse(FloatOrd(self.distance))
+        (
+            self.per_object_binding_dynamic_offset,
+            Reverse(FloatOrd(self.distance)),
+        )
     }
 
     #[inline]
@@ -203,7 +219,9 @@ impl PhaseItem for AlphaMask3d {
     #[inline]
     fn sort(items: &mut [Self]) {
         // Key negated to match reversed SortKey ordering
-        radsort::sort_by_key(items, |item| -item.distance);
+        radsort::sort_by_key(items, |item| {
+            (item.per_object_binding_dynamic_offset, -item.distance)
+        });
     }
 }
 

crates/bevy_core_pipeline/src/prepass/mod.rs

@@ -80,14 +80,18 @@ pub struct ViewPrepassTextures {
 /// Used to render all 3D meshes with materials that have no transparency.
 pub struct Opaque3dPrepass {
     pub distance: f32,
+    // Per-object data may be bound at different dynamic offsets within a buffer. If it is, then
+    // each batch of per-object data starts at the same dynamic offset.
+    pub per_object_binding_dynamic_offset: u32,
     pub entity: Entity,
     pub pipeline_id: CachedRenderPipelineId,
     pub draw_function: DrawFunctionId,
 }
 
 impl PhaseItem for Opaque3dPrepass {
+    // NOTE: (dynamic offset, -distance)
     // NOTE: Values increase towards the camera. Front-to-back ordering for opaque means we need a descending sort.
-    type SortKey = Reverse<FloatOrd>;
+    type SortKey = (u32, Reverse<FloatOrd>);
 
     #[inline]
     fn entity(&self) -> Entity {
@@ -96,7 +100,10 @@ impl PhaseItem for Opaque3dPrepass {
 
     #[inline]
     fn sort_key(&self) -> Self::SortKey {
-        Reverse(FloatOrd(self.distance))
+        (
+            self.per_object_binding_dynamic_offset,
+            Reverse(FloatOrd(self.distance)),
+        )
     }
 
     #[inline]
@@ -107,7 +114,9 @@ impl PhaseItem for Opaque3dPrepass {
     #[inline]
     fn sort(items: &mut [Self]) {
         // Key negated to match reversed SortKey ordering
-        radsort::sort_by_key(items, |item| -item.distance);
+        radsort::sort_by_key(items, |item| {
+            (item.per_object_binding_dynamic_offset, -item.distance)
+        });
     }
 }
 
@@ -125,14 +134,18 @@ impl CachedRenderPipelinePhaseItem for Opaque3dPrepass {
 /// Used to render all meshes with a material with an alpha mask.
 pub struct AlphaMask3dPrepass {
     pub distance: f32,
+    // Per-object data may be bound at different dynamic offsets within a buffer. If it is, then
+    // each batch of per-object data starts at the same dynamic offset.
+    pub per_object_binding_dynamic_offset: u32,
     pub entity: Entity,
     pub pipeline_id: CachedRenderPipelineId,
     pub draw_function: DrawFunctionId,
 }
 
 impl PhaseItem for AlphaMask3dPrepass {
-    // NOTE: Values increase towards the camera. Front-to-back ordering for alpha mask means we need a descending sort.
-    type SortKey = Reverse<FloatOrd>;
+    // NOTE: (dynamic offset, -distance)
+    // NOTE: Values increase towards the camera. Front-to-back ordering for opaque means we need a descending sort.
+    type SortKey = (u32, Reverse<FloatOrd>);
 
     #[inline]
     fn entity(&self) -> Entity {
@@ -141,7 +154,10 @@ impl PhaseItem for AlphaMask3dPrepass {
 
     #[inline]
     fn sort_key(&self) -> Self::SortKey {
-        Reverse(FloatOrd(self.distance))
+        (
+            self.per_object_binding_dynamic_offset,
+            Reverse(FloatOrd(self.distance)),
+        )
     }
 
     #[inline]
@@ -152,7 +168,9 @@ impl PhaseItem for AlphaMask3dPrepass {
     #[inline]
     fn sort(items: &mut [Self]) {
         // Key negated to match reversed SortKey ordering
-        radsort::sort_by_key(items, |item| -item.distance);
+        radsort::sort_by_key(items, |item| {
+            (item.per_object_binding_dynamic_offset, -item.distance)
+        });
     }
 }
 

crates/bevy_pbr/Cargo.toml

@@ -29,5 +29,6 @@ bevy_derive = { path = "../bevy_derive", version = "0.12.0-dev" }
 bitflags = "2.3"
 # direct dependency required for derive macro
 bytemuck = { version = "1", features = ["derive"] }
-radsort = "0.1"
 naga_oil = "0.8"
+radsort = "0.1"
+smallvec = "1.6"

crates/bevy_pbr/src/material.rs

@@ -30,9 +30,9 @@ use bevy_render::{
         RenderPhase, SetItemPipeline, TrackedRenderPass,
     },
     render_resource::{
-        AsBindGroup, AsBindGroupError, BindGroup, BindGroupLayout, OwnedBindingResource,
-        PipelineCache, RenderPipelineDescriptor, Shader, ShaderRef, SpecializedMeshPipeline,
-        SpecializedMeshPipelineError, SpecializedMeshPipelines,
+        AsBindGroup, AsBindGroupError, BindGroup, BindGroupLayout, GpuArrayBufferIndex,
+        OwnedBindingResource, PipelineCache, RenderPipelineDescriptor, Shader, ShaderRef,
+        SpecializedMeshPipeline, SpecializedMeshPipelineError, SpecializedMeshPipelines,
     },
     renderer::RenderDevice,
     texture::FallbackImage,
@@ -379,7 +379,12 @@ pub fn queue_material_meshes<M: Material>(
     msaa: Res<Msaa>,
     render_meshes: Res<RenderAssets<Mesh>>,
     render_materials: Res<RenderMaterials<M>>,
-    material_meshes: Query<(&Handle<M>, &Handle<Mesh>, &MeshUniform)>,
+    material_meshes: Query<(
+        &Handle<M>,
+        &Handle<Mesh>,
+        &MeshUniform,
+        &GpuArrayBufferIndex<MeshUniform>,
+    )>,
     images: Res<RenderAssets<Image>>,
     mut views: Query<(
         &ExtractedView,
@@ -463,7 +468,7 @@ pub fn queue_material_meshes<M: Material>(
 
         let rangefinder = view.rangefinder3d();
         for visible_entity in &visible_entities.entities {
-            if let Ok((material_handle, mesh_handle, mesh_uniform)) =
+            if let Ok((material_handle, mesh_handle, mesh_uniform, batch_indices)) =
                 material_meshes.get(*visible_entity)
             {
                 if let (Some(mesh), Some(material)) = (
@@ -520,6 +525,9 @@ pub fn queue_material_meshes<M: Material>(
                                 draw_function: draw_opaque_pbr,
                                 pipeline: pipeline_id,
                                 distance,
+                                per_object_binding_dynamic_offset: batch_indices
+                                    .dynamic_offset
+                                    .unwrap_or_default(),
                             });
                         }
                         AlphaMode::Mask(_) => {
@@ -528,6 +536,9 @@ pub fn queue_material_meshes<M: Material>(
                                 draw_function: draw_alpha_mask_pbr,
                                 pipeline: pipeline_id,
                                 distance,
+                                per_object_binding_dynamic_offset: batch_indices
+                                    .dynamic_offset
+                                    .unwrap_or_default(),
                             });
                         }
                         AlphaMode::Blend

crates/bevy_pbr/src/prepass/mod.rs

@@ -30,9 +30,9 @@ use bevy_render::{
         BindGroup, BindGroupDescriptor, BindGroupEntry, BindGroupLayout, BindGroupLayoutDescriptor,
         BindGroupLayoutEntry, BindingResource, BindingType, BlendState, BufferBindingType,
         ColorTargetState, ColorWrites, CompareFunction, DepthBiasState, DepthStencilState,
-        DynamicUniformBuffer, FragmentState, FrontFace, MultisampleState, PipelineCache,
-        PolygonMode, PrimitiveState, RenderPipelineDescriptor, Shader, ShaderRef, ShaderStages,
-        ShaderType, SpecializedMeshPipeline, SpecializedMeshPipelineError,
+        DynamicUniformBuffer, FragmentState, FrontFace, GpuArrayBufferIndex, MultisampleState,
+        PipelineCache, PolygonMode, PrimitiveState, RenderPipelineDescriptor, Shader, ShaderRef,
+        ShaderStages, ShaderType, SpecializedMeshPipeline, SpecializedMeshPipelineError,
         SpecializedMeshPipelines, StencilFaceState, StencilState, TextureSampleType,
         TextureViewDimension, VertexState,
     },
@@ -751,7 +751,12 @@ pub fn queue_prepass_material_meshes<M: Material>(
     msaa: Res<Msaa>,
     render_meshes: Res<RenderAssets<Mesh>>,
     render_materials: Res<RenderMaterials<M>>,
-    material_meshes: Query<(&Handle<M>, &Handle<Mesh>, &MeshUniform)>,
+    material_meshes: Query<(
+        &Handle<M>,
+        &Handle<Mesh>,
+        &MeshUniform,
+        &GpuArrayBufferIndex<MeshUniform>,
+    )>,
     mut views: Query<(
         &ExtractedView,
         &VisibleEntities,
@@ -796,7 +801,7 @@ pub fn queue_prepass_material_meshes<M: Material>(
         let rangefinder = view.rangefinder3d();
 
         for visible_entity in &visible_entities.entities {
-            let Ok((material_handle, mesh_handle, mesh_uniform)) = material_meshes.get(*visible_entity) else {
+            let Ok((material_handle, mesh_handle, mesh_uniform, batch_indices)) = material_meshes.get(*visible_entity) else {
                 continue;
             };
 
@@ -848,6 +853,9 @@ pub fn queue_prepass_material_meshes<M: Material>(
                         draw_function: opaque_draw_prepass,
                         pipeline_id,
                         distance,
+                        per_object_binding_dynamic_offset: batch_indices
+                            .dynamic_offset
+                            .unwrap_or_default(),
                     });
                 }
                 AlphaMode::Mask(_) => {
@@ -856,6 +864,9 @@ pub fn queue_prepass_material_meshes<M: Material>(
                         draw_function: alpha_mask_draw_prepass,
                         pipeline_id,
                         distance,
+                        per_object_binding_dynamic_offset: batch_indices
+                            .dynamic_offset
+                            .unwrap_or_default(),
                     });
                 }
                 AlphaMode::Blend

crates/bevy_pbr/src/prepass/prepass.wgsl

@@ -7,6 +7,7 @@
 // Most of these attributes are not used in the default prepass fragment shader, but they are still needed so we can
 // pass them to custom prepass shaders like pbr_prepass.wgsl.
 struct Vertex {
+    @builtin(instance_index) instance_index: u32,
     @location(0) position: vec3<f32>,
 
 #ifdef VERTEX_UVS
@@ -88,7 +89,9 @@ fn vertex(vertex_no_morph: Vertex) -> VertexOutput {
 #ifdef SKINNED
     var model = bevy_pbr::skinning::skin_model(vertex.joint_indices, vertex.joint_weights);
 #else // SKINNED
-    var model = mesh.model;
+    // Use vertex_no_morph.instance_index instead of vertex.instance_index to work around a wgpu dx12 bug.
+    // See https://github.com/gfx-rs/naga/issues/2416
+    var model = mesh[vertex_no_morph.instance_index].model;
 #endif // SKINNED
 
     out.clip_position = bevy_pbr::mesh_functions::mesh_position_local_to_clip(model, vec4(vertex.position, 1.0));
@@ -105,17 +108,33 @@ fn vertex(vertex_no_morph: Vertex) -> VertexOutput {
 #ifdef SKINNED
     out.world_normal = bevy_pbr::skinning::skin_normals(model, vertex.normal);
 #else // SKINNED
-    out.world_normal = bevy_pbr::mesh_functions::mesh_normal_local_to_world(vertex.normal);
+    out.world_normal = bevy_pbr::mesh_functions::mesh_normal_local_to_world(
+        vertex.normal,
+        // Use vertex_no_morph.instance_index instead of vertex.instance_index to work around a wgpu dx12 bug.
+        // See https://github.com/gfx-rs/naga/issues/2416
+        vertex_no_morph.instance_index
+    );
 #endif // SKINNED
 
 #ifdef VERTEX_TANGENTS
-    out.world_tangent = bevy_pbr::mesh_functions::mesh_tangent_local_to_world(model, vertex.tangent);
+    out.world_tangent = bevy_pbr::mesh_functions::mesh_tangent_local_to_world(
+        model,
+        vertex.tangent,
+        // Use vertex_no_morph.instance_index instead of vertex.instance_index to work around a wgpu dx12 bug.
+        // See https://github.com/gfx-rs/naga/issues/2416
+        vertex_no_morph.instance_index
+    );
 #endif // VERTEX_TANGENTS
 #endif // NORMAL_PREPASS
 
 #ifdef MOTION_VECTOR_PREPASS
     out.world_position = bevy_pbr::mesh_functions::mesh_position_local_to_world(model, vec4<f32>(vertex.position, 1.0));
-    out.previous_world_position = bevy_pbr::mesh_functions::mesh_position_local_to_world(mesh.previous_model, vec4<f32>(vertex.position, 1.0));
+    // Use vertex_no_morph.instance_index instead of vertex.instance_index to work around a wgpu dx12 bug.
+    // See https://github.com/gfx-rs/naga/issues/2416
+    out.previous_world_position = bevy_pbr::mesh_functions::mesh_position_local_to_world(
+        mesh[vertex_no_morph.instance_index].previous_model,
+        vec4<f32>(vertex.position, 1.0)
+    );
 #endif // MOTION_VECTOR_PREPASS
 
     return out;

crates/bevy_pbr/src/prepass/prepass_bindings.wgsl

@@ -15,5 +15,4 @@ var<uniform> previous_view_proj: mat4x4<f32>;
 
 // Material bindings will be in @group(1)
 
-@group(2) @binding(0)
-var<uniform> mesh: bevy_pbr::mesh_types::Mesh;
+#import bevy_pbr::mesh_bindings   mesh