 4f1d9a6315
			
		
	
	
		4f1d9a6315
		
			
		
	
	
	
	
		
			
			This is a continuation of this PR: #8062 # Objective - Reorder render schedule sets to allow data preparation when phase item order is known to support improved batching - Part of the batching/instancing etc plan from here: https://github.com/bevyengine/bevy/issues/89#issuecomment-1379249074 - The original idea came from @inodentry and proved to be a good one. Thanks! - Refactor `bevy_sprite` and `bevy_ui` to take advantage of the new ordering ## Solution - Move `Prepare` and `PrepareFlush` after `PhaseSortFlush` - Add a `PrepareAssets` set that runs in parallel with other systems and sets in the render schedule. - Put prepare_assets systems in the `PrepareAssets` set - If explicit dependencies are needed on Mesh or Material RenderAssets then depend on the appropriate system. - Add `ManageViews` and `ManageViewsFlush` sets between `ExtractCommands` and Queue - Move `queue_mesh*_bind_group` to the Prepare stage - Rename them to `prepare_` - Put systems that prepare resources (buffers, textures, etc.) into a `PrepareResources` set inside `Prepare` - Put the `prepare_..._bind_group` systems into a `PrepareBindGroup` set after `PrepareResources` - Move `prepare_lights` to the `ManageViews` set - `prepare_lights` creates views and this must happen before `Queue` - This system needs refactoring to stop handling all responsibilities - Gather lights, sort, and create shadow map views. Store sorted light entities in a resource - Remove `BatchedPhaseItem` - Replace `batch_range` with `batch_size` representing how many items to skip after rendering the item or to skip the item entirely if `batch_size` is 0. - `queue_sprites` has been split into `queue_sprites` for queueing phase items and `prepare_sprites` for batching after the `PhaseSort` - `PhaseItem`s are still inserted in `queue_sprites` - After sorting adjacent compatible sprite phase items are accumulated into `SpriteBatch` components on the first entity of each batch, containing a range of vertex indices. The associated `PhaseItem`'s `batch_size` is updated appropriately. - `SpriteBatch` items are then drawn skipping over the other items in the batch based on the value in `batch_size` - A very similar refactor was performed on `bevy_ui` --- ## Changelog Changed: - Reordered and reworked render app schedule sets. The main change is that data is extracted, queued, sorted, and then prepared when the order of data is known. - Refactor `bevy_sprite` and `bevy_ui` to take advantage of the reordering. ## Migration Guide - Assets such as materials and meshes should now be created in `PrepareAssets` e.g. `prepare_assets<Mesh>` - Queueing entities to `RenderPhase`s continues to be done in `Queue` e.g. `queue_sprites` - Preparing resources (textures, buffers, etc.) should now be done in `PrepareResources`, e.g. `prepare_prepass_textures`, `prepare_mesh_uniforms` - Prepare bind groups should now be done in `PrepareBindGroups` e.g. `prepare_mesh_bind_group` - Any batching or instancing can now be done in `Prepare` where the order of the phase items is known e.g. `prepare_sprites` ## Next Steps - Introduce some generic mechanism to ensure items that can be batched are grouped in the phase item order, currently you could easily have `[sprite at z 0, mesh at z 0, sprite at z 0]` preventing batching. - Investigate improved orderings for building the MeshUniform buffer - Implementing batching across the rest of bevy --------- Co-authored-by: Robert Swain <robert.swain@gmail.com> Co-authored-by: robtfm <50659922+robtfm@users.noreply.github.com>
		
			
				
	
	
		
			276 lines
		
	
	
		
			9.2 KiB
		
	
	
	
		
			Rust
		
	
	
	
	
	
			
		
		
	
	
			276 lines
		
	
	
		
			9.2 KiB
		
	
	
	
		
			Rust
		
	
	
	
	
	
| //! A shader that renders a mesh multiple times in one draw call.
 | |
| 
 | |
| use bevy::{
 | |
|     core_pipeline::core_3d::Transparent3d,
 | |
|     ecs::{
 | |
|         query::QueryItem,
 | |
|         system::{lifetimeless::*, SystemParamItem},
 | |
|     },
 | |
|     pbr::{MeshPipeline, MeshPipelineKey, MeshTransforms, SetMeshBindGroup, SetMeshViewBindGroup},
 | |
|     prelude::*,
 | |
|     render::{
 | |
|         extract_component::{ExtractComponent, ExtractComponentPlugin},
 | |
|         mesh::{GpuBufferInfo, MeshVertexBufferLayout},
 | |
|         render_asset::RenderAssets,
 | |
|         render_phase::{
 | |
|             AddRenderCommand, DrawFunctions, PhaseItem, RenderCommand, RenderCommandResult,
 | |
|             RenderPhase, SetItemPipeline, TrackedRenderPass,
 | |
|         },
 | |
|         render_resource::*,
 | |
|         renderer::RenderDevice,
 | |
|         view::{ExtractedView, NoFrustumCulling},
 | |
|         Render, RenderApp, RenderSet,
 | |
|     },
 | |
| };
 | |
| use bytemuck::{Pod, Zeroable};
 | |
| 
 | |
| fn main() {
 | |
|     App::new()
 | |
|         .add_plugins((DefaultPlugins, CustomMaterialPlugin))
 | |
|         .add_systems(Startup, setup)
 | |
|         .run();
 | |
| }
 | |
| 
 | |
| fn setup(mut commands: Commands, mut meshes: ResMut<Assets<Mesh>>) {
 | |
|     commands.spawn((
 | |
|         meshes.add(Mesh::from(shape::Cube { size: 0.5 })),
 | |
|         SpatialBundle::INHERITED_IDENTITY,
 | |
|         InstanceMaterialData(
 | |
|             (1..=10)
 | |
|                 .flat_map(|x| (1..=10).map(move |y| (x as f32 / 10.0, y as f32 / 10.0)))
 | |
|                 .map(|(x, y)| InstanceData {
 | |
|                     position: Vec3::new(x * 10.0 - 5.0, y * 10.0 - 5.0, 0.0),
 | |
|                     scale: 1.0,
 | |
|                     color: Color::hsla(x * 360., y, 0.5, 1.0).as_rgba_f32(),
 | |
|                 })
 | |
|                 .collect(),
 | |
|         ),
 | |
|         // NOTE: Frustum culling is done based on the Aabb of the Mesh and the GlobalTransform.
 | |
|         // As the cube is at the origin, if its Aabb moves outside the view frustum, all the
 | |
|         // instanced cubes will be culled.
 | |
|         // The InstanceMaterialData contains the 'GlobalTransform' information for this custom
 | |
|         // instancing, and that is not taken into account with the built-in frustum culling.
 | |
|         // We must disable the built-in frustum culling by adding the `NoFrustumCulling` marker
 | |
|         // component to avoid incorrect culling.
 | |
|         NoFrustumCulling,
 | |
|     ));
 | |
| 
 | |
|     // camera
 | |
|     commands.spawn(Camera3dBundle {
 | |
|         transform: Transform::from_xyz(0.0, 0.0, 15.0).looking_at(Vec3::ZERO, Vec3::Y),
 | |
|         ..default()
 | |
|     });
 | |
| }
 | |
| 
 | |
| #[derive(Component, Deref)]
 | |
| struct InstanceMaterialData(Vec<InstanceData>);
 | |
| 
 | |
| impl ExtractComponent for InstanceMaterialData {
 | |
|     type Query = &'static InstanceMaterialData;
 | |
|     type Filter = ();
 | |
|     type Out = Self;
 | |
| 
 | |
|     fn extract_component(item: QueryItem<'_, Self::Query>) -> Option<Self> {
 | |
|         Some(InstanceMaterialData(item.0.clone()))
 | |
|     }
 | |
| }
 | |
| 
 | |
| pub struct CustomMaterialPlugin;
 | |
| 
 | |
| impl Plugin for CustomMaterialPlugin {
 | |
|     fn build(&self, app: &mut App) {
 | |
|         app.add_plugins(ExtractComponentPlugin::<InstanceMaterialData>::default());
 | |
|         app.sub_app_mut(RenderApp)
 | |
|             .add_render_command::<Transparent3d, DrawCustom>()
 | |
|             .init_resource::<SpecializedMeshPipelines<CustomPipeline>>()
 | |
|             .add_systems(
 | |
|                 Render,
 | |
|                 (
 | |
|                     queue_custom.in_set(RenderSet::QueueMeshes),
 | |
|                     prepare_instance_buffers.in_set(RenderSet::PrepareResources),
 | |
|                 ),
 | |
|             );
 | |
|     }
 | |
| 
 | |
|     fn finish(&self, app: &mut App) {
 | |
|         app.sub_app_mut(RenderApp).init_resource::<CustomPipeline>();
 | |
|     }
 | |
| }
 | |
| 
 | |
| #[derive(Clone, Copy, Pod, Zeroable)]
 | |
| #[repr(C)]
 | |
| struct InstanceData {
 | |
|     position: Vec3,
 | |
|     scale: f32,
 | |
|     color: [f32; 4],
 | |
| }
 | |
| 
 | |
| #[allow(clippy::too_many_arguments)]
 | |
| fn queue_custom(
 | |
|     transparent_3d_draw_functions: Res<DrawFunctions<Transparent3d>>,
 | |
|     custom_pipeline: Res<CustomPipeline>,
 | |
|     msaa: Res<Msaa>,
 | |
|     mut pipelines: ResMut<SpecializedMeshPipelines<CustomPipeline>>,
 | |
|     pipeline_cache: Res<PipelineCache>,
 | |
|     meshes: Res<RenderAssets<Mesh>>,
 | |
|     material_meshes: Query<(Entity, &MeshTransforms, &Handle<Mesh>), With<InstanceMaterialData>>,
 | |
|     mut views: Query<(&ExtractedView, &mut RenderPhase<Transparent3d>)>,
 | |
| ) {
 | |
|     let draw_custom = transparent_3d_draw_functions.read().id::<DrawCustom>();
 | |
| 
 | |
|     let msaa_key = MeshPipelineKey::from_msaa_samples(msaa.samples());
 | |
| 
 | |
|     for (view, mut transparent_phase) in &mut views {
 | |
|         let view_key = msaa_key | MeshPipelineKey::from_hdr(view.hdr);
 | |
|         let rangefinder = view.rangefinder3d();
 | |
|         for (entity, mesh_transforms, mesh_handle) in &material_meshes {
 | |
|             if let Some(mesh) = meshes.get(mesh_handle) {
 | |
|                 let key =
 | |
|                     view_key | MeshPipelineKey::from_primitive_topology(mesh.primitive_topology);
 | |
|                 let pipeline = pipelines
 | |
|                     .specialize(&pipeline_cache, &custom_pipeline, key, &mesh.layout)
 | |
|                     .unwrap();
 | |
|                 transparent_phase.add(Transparent3d {
 | |
|                     entity,
 | |
|                     pipeline,
 | |
|                     draw_function: draw_custom,
 | |
|                     distance: rangefinder
 | |
|                         .distance_translation(&mesh_transforms.transform.translation),
 | |
|                     batch_size: 1,
 | |
|                 });
 | |
|             }
 | |
|         }
 | |
|     }
 | |
| }
 | |
| 
 | |
| #[derive(Component)]
 | |
| pub struct InstanceBuffer {
 | |
|     buffer: Buffer,
 | |
|     length: usize,
 | |
| }
 | |
| 
 | |
| fn prepare_instance_buffers(
 | |
|     mut commands: Commands,
 | |
|     query: Query<(Entity, &InstanceMaterialData)>,
 | |
|     render_device: Res<RenderDevice>,
 | |
| ) {
 | |
|     for (entity, instance_data) in &query {
 | |
|         let buffer = render_device.create_buffer_with_data(&BufferInitDescriptor {
 | |
|             label: Some("instance data buffer"),
 | |
|             contents: bytemuck::cast_slice(instance_data.as_slice()),
 | |
|             usage: BufferUsages::VERTEX | BufferUsages::COPY_DST,
 | |
|         });
 | |
|         commands.entity(entity).insert(InstanceBuffer {
 | |
|             buffer,
 | |
|             length: instance_data.len(),
 | |
|         });
 | |
|     }
 | |
| }
 | |
| 
 | |
| #[derive(Resource)]
 | |
| pub struct CustomPipeline {
 | |
|     shader: Handle<Shader>,
 | |
|     mesh_pipeline: MeshPipeline,
 | |
| }
 | |
| 
 | |
| impl FromWorld for CustomPipeline {
 | |
|     fn from_world(world: &mut World) -> Self {
 | |
|         let asset_server = world.resource::<AssetServer>();
 | |
|         let shader = asset_server.load("shaders/instancing.wgsl");
 | |
| 
 | |
|         let mesh_pipeline = world.resource::<MeshPipeline>();
 | |
| 
 | |
|         CustomPipeline {
 | |
|             shader,
 | |
|             mesh_pipeline: mesh_pipeline.clone(),
 | |
|         }
 | |
|     }
 | |
| }
 | |
| 
 | |
| impl SpecializedMeshPipeline for CustomPipeline {
 | |
|     type Key = MeshPipelineKey;
 | |
| 
 | |
|     fn specialize(
 | |
|         &self,
 | |
|         key: Self::Key,
 | |
|         layout: &MeshVertexBufferLayout,
 | |
|     ) -> Result<RenderPipelineDescriptor, SpecializedMeshPipelineError> {
 | |
|         let mut descriptor = self.mesh_pipeline.specialize(key, layout)?;
 | |
| 
 | |
|         // meshes typically live in bind group 2. because we are using bindgroup 1
 | |
|         // we need to add MESH_BINDGROUP_1 shader def so that the bindings are correctly
 | |
|         // linked in the shader
 | |
|         descriptor
 | |
|             .vertex
 | |
|             .shader_defs
 | |
|             .push("MESH_BINDGROUP_1".into());
 | |
| 
 | |
|         descriptor.vertex.shader = self.shader.clone();
 | |
|         descriptor.vertex.buffers.push(VertexBufferLayout {
 | |
|             array_stride: std::mem::size_of::<InstanceData>() as u64,
 | |
|             step_mode: VertexStepMode::Instance,
 | |
|             attributes: vec![
 | |
|                 VertexAttribute {
 | |
|                     format: VertexFormat::Float32x4,
 | |
|                     offset: 0,
 | |
|                     shader_location: 3, // shader locations 0-2 are taken up by Position, Normal and UV attributes
 | |
|                 },
 | |
|                 VertexAttribute {
 | |
|                     format: VertexFormat::Float32x4,
 | |
|                     offset: VertexFormat::Float32x4.size(),
 | |
|                     shader_location: 4,
 | |
|                 },
 | |
|             ],
 | |
|         });
 | |
|         descriptor.fragment.as_mut().unwrap().shader = self.shader.clone();
 | |
|         Ok(descriptor)
 | |
|     }
 | |
| }
 | |
| 
 | |
| type DrawCustom = (
 | |
|     SetItemPipeline,
 | |
|     SetMeshViewBindGroup<0>,
 | |
|     SetMeshBindGroup<1>,
 | |
|     DrawMeshInstanced,
 | |
| );
 | |
| 
 | |
| pub struct DrawMeshInstanced;
 | |
| 
 | |
| impl<P: PhaseItem> RenderCommand<P> for DrawMeshInstanced {
 | |
|     type Param = SRes<RenderAssets<Mesh>>;
 | |
|     type ViewWorldQuery = ();
 | |
|     type ItemWorldQuery = (Read<Handle<Mesh>>, Read<InstanceBuffer>);
 | |
| 
 | |
|     #[inline]
 | |
|     fn render<'w>(
 | |
|         _item: &P,
 | |
|         _view: (),
 | |
|         (mesh_handle, instance_buffer): (&'w Handle<Mesh>, &'w InstanceBuffer),
 | |
|         meshes: SystemParamItem<'w, '_, Self::Param>,
 | |
|         pass: &mut TrackedRenderPass<'w>,
 | |
|     ) -> RenderCommandResult {
 | |
|         let gpu_mesh = match meshes.into_inner().get(mesh_handle) {
 | |
|             Some(gpu_mesh) => gpu_mesh,
 | |
|             None => return RenderCommandResult::Failure,
 | |
|         };
 | |
| 
 | |
|         pass.set_vertex_buffer(0, gpu_mesh.vertex_buffer.slice(..));
 | |
|         pass.set_vertex_buffer(1, instance_buffer.buffer.slice(..));
 | |
| 
 | |
|         match &gpu_mesh.buffer_info {
 | |
|             GpuBufferInfo::Indexed {
 | |
|                 buffer,
 | |
|                 index_format,
 | |
|                 count,
 | |
|             } => {
 | |
|                 pass.set_index_buffer(buffer.slice(..), 0, *index_format);
 | |
|                 pass.draw_indexed(0..*count, 0, 0..instance_buffer.length as u32);
 | |
|             }
 | |
|             GpuBufferInfo::NonIndexed => {
 | |
|                 pass.draw(0..gpu_mesh.vertex_count, 0..instance_buffer.length as u32);
 | |
|             }
 | |
|         }
 | |
|         RenderCommandResult::Success
 | |
|     }
 | |
| }
 |