2023-07-21 16:46:56 +00:00
|
|
|
use crate::{
|
|
|
|
|
render_resource::{GpuArrayBuffer, GpuArrayBufferable},
|
|
|
|
|
renderer::{RenderDevice, RenderQueue},
|
|
|
|
|
Render, RenderApp, RenderSet,
|
|
|
|
|
};
|
|
|
|
|
use bevy_app::{App, Plugin};
|
|
|
|
|
use bevy_ecs::{
|
|
|
|
|
prelude::{Component, Entity},
|
|
|
|
|
schedule::IntoSystemConfigs,
|
|
|
|
|
system::{Commands, Query, Res, ResMut},
|
|
|
|
|
};
|
2024-09-27 00:59:59 +00:00
|
|
|
use core::marker::PhantomData;
|
2023-07-21 16:46:56 +00:00
|
|
|
|
|
|
|
|
/// This plugin prepares the components of the corresponding type for the GPU
|
|
|
|
|
/// by storing them in a [`GpuArrayBuffer`].
|
|
|
|
|
pub struct GpuComponentArrayBufferPlugin<C: Component + GpuArrayBufferable>(PhantomData<C>);
|
|
|
|
|
|
|
|
|
|
impl<C: Component + GpuArrayBufferable> Plugin for GpuComponentArrayBufferPlugin<C> {
|
|
|
|
|
fn build(&self, app: &mut App) {
|
2024-03-31 03:16:10 +00:00
|
|
|
if let Some(render_app) = app.get_sub_app_mut(RenderApp) {
|
Use GpuArrayBuffer for MeshUniform (#9254)
# Objective
- Reduce the number of rebindings to enable batching of draw commands
## Solution
- Use the new `GpuArrayBuffer` for `MeshUniform` data to store all
`MeshUniform` data in arrays within fewer bindings
- Sort opaque/alpha mask prepass, opaque/alpha mask main, and shadow
phases also by the batch per-object data binding dynamic offset to
improve performance on WebGL2.
---
## Changelog
- Changed: Per-object `MeshUniform` data is now managed by
`GpuArrayBuffer` as arrays in buffers that need to be indexed into.
## Migration Guide
Accessing the `model` member of an individual mesh object's shader
`Mesh` struct the old way where each `MeshUniform` was stored at its own
dynamic offset:
```rust
struct Vertex {
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh.model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
The new way where one needs to index into the array of `Mesh`es for the
batch:
```rust
struct Vertex {
@builtin(instance_index) instance_index: u32,
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh[vertex.instance_index].model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
Note that using the instance_index is the default way to pass the
per-object index into the shader, but if you wish to do custom rendering
approaches you can pass it in however you like.
---------
Co-authored-by: robtfm <50659922+robtfm@users.noreply.github.com>
Co-authored-by: Elabajaba <Elabajaba@users.noreply.github.com>
2023-07-30 13:17:08 +00:00
|
|
|
render_app.add_systems(
|
|
|
|
|
Render,
|
Reorder render sets, refactor bevy_sprite to take advantage (#9236)
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>
2023-08-27 14:33:49 +00:00
|
|
|
prepare_gpu_component_array_buffers::<C>.in_set(RenderSet::PrepareResources),
|
Use GpuArrayBuffer for MeshUniform (#9254)
# Objective
- Reduce the number of rebindings to enable batching of draw commands
## Solution
- Use the new `GpuArrayBuffer` for `MeshUniform` data to store all
`MeshUniform` data in arrays within fewer bindings
- Sort opaque/alpha mask prepass, opaque/alpha mask main, and shadow
phases also by the batch per-object data binding dynamic offset to
improve performance on WebGL2.
---
## Changelog
- Changed: Per-object `MeshUniform` data is now managed by
`GpuArrayBuffer` as arrays in buffers that need to be indexed into.
## Migration Guide
Accessing the `model` member of an individual mesh object's shader
`Mesh` struct the old way where each `MeshUniform` was stored at its own
dynamic offset:
```rust
struct Vertex {
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh.model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
The new way where one needs to index into the array of `Mesh`es for the
batch:
```rust
struct Vertex {
@builtin(instance_index) instance_index: u32,
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh[vertex.instance_index].model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
Note that using the instance_index is the default way to pass the
per-object index into the shader, but if you wish to do custom rendering
approaches you can pass it in however you like.
---------
Co-authored-by: robtfm <50659922+robtfm@users.noreply.github.com>
Co-authored-by: Elabajaba <Elabajaba@users.noreply.github.com>
2023-07-30 13:17:08 +00:00
|
|
|
);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn finish(&self, app: &mut App) {
|
2024-03-31 03:16:10 +00:00
|
|
|
if let Some(render_app) = app.get_sub_app_mut(RenderApp) {
|
Use GpuArrayBuffer for MeshUniform (#9254)
# Objective
- Reduce the number of rebindings to enable batching of draw commands
## Solution
- Use the new `GpuArrayBuffer` for `MeshUniform` data to store all
`MeshUniform` data in arrays within fewer bindings
- Sort opaque/alpha mask prepass, opaque/alpha mask main, and shadow
phases also by the batch per-object data binding dynamic offset to
improve performance on WebGL2.
---
## Changelog
- Changed: Per-object `MeshUniform` data is now managed by
`GpuArrayBuffer` as arrays in buffers that need to be indexed into.
## Migration Guide
Accessing the `model` member of an individual mesh object's shader
`Mesh` struct the old way where each `MeshUniform` was stored at its own
dynamic offset:
```rust
struct Vertex {
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh.model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
The new way where one needs to index into the array of `Mesh`es for the
batch:
```rust
struct Vertex {
@builtin(instance_index) instance_index: u32,
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh[vertex.instance_index].model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
Note that using the instance_index is the default way to pass the
per-object index into the shader, but if you wish to do custom rendering
approaches you can pass it in however you like.
---------
Co-authored-by: robtfm <50659922+robtfm@users.noreply.github.com>
Co-authored-by: Elabajaba <Elabajaba@users.noreply.github.com>
2023-07-30 13:17:08 +00:00
|
|
|
render_app.insert_resource(GpuArrayBuffer::<C>::new(
|
2024-03-31 03:16:10 +00:00
|
|
|
render_app.world().resource::<RenderDevice>(),
|
Use GpuArrayBuffer for MeshUniform (#9254)
# Objective
- Reduce the number of rebindings to enable batching of draw commands
## Solution
- Use the new `GpuArrayBuffer` for `MeshUniform` data to store all
`MeshUniform` data in arrays within fewer bindings
- Sort opaque/alpha mask prepass, opaque/alpha mask main, and shadow
phases also by the batch per-object data binding dynamic offset to
improve performance on WebGL2.
---
## Changelog
- Changed: Per-object `MeshUniform` data is now managed by
`GpuArrayBuffer` as arrays in buffers that need to be indexed into.
## Migration Guide
Accessing the `model` member of an individual mesh object's shader
`Mesh` struct the old way where each `MeshUniform` was stored at its own
dynamic offset:
```rust
struct Vertex {
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh.model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
The new way where one needs to index into the array of `Mesh`es for the
batch:
```rust
struct Vertex {
@builtin(instance_index) instance_index: u32,
@location(0) position: vec3<f32>,
};
fn vertex(vertex: Vertex) -> VertexOutput {
var out: VertexOutput;
out.clip_position = mesh_position_local_to_clip(
mesh[vertex.instance_index].model,
vec4<f32>(vertex.position, 1.0)
);
return out;
}
```
Note that using the instance_index is the default way to pass the
per-object index into the shader, but if you wish to do custom rendering
approaches you can pass it in however you like.
---------
Co-authored-by: robtfm <50659922+robtfm@users.noreply.github.com>
Co-authored-by: Elabajaba <Elabajaba@users.noreply.github.com>
2023-07-30 13:17:08 +00:00
|
|
|
));
|
2023-07-21 16:46:56 +00:00
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
impl<C: Component + GpuArrayBufferable> Default for GpuComponentArrayBufferPlugin<C> {
|
|
|
|
|
fn default() -> Self {
|
|
|
|
|
Self(PhantomData::<C>)
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
fn prepare_gpu_component_array_buffers<C: Component + GpuArrayBufferable>(
|
|
|
|
|
mut commands: Commands,
|
|
|
|
|
render_device: Res<RenderDevice>,
|
|
|
|
|
render_queue: Res<RenderQueue>,
|
|
|
|
|
mut gpu_array_buffer: ResMut<GpuArrayBuffer<C>>,
|
|
|
|
|
components: Query<(Entity, &C)>,
|
|
|
|
|
) {
|
|
|
|
|
gpu_array_buffer.clear();
|
|
|
|
|
|
|
|
|
|
let entities = components
|
|
|
|
|
.iter()
|
|
|
|
|
.map(|(entity, component)| (entity, gpu_array_buffer.push(component.clone())))
|
|
|
|
|
.collect::<Vec<_>>();
|
|
|
|
|
commands.insert_or_spawn_batch(entities);
|
|
|
|
|
|
|
|
|
|
gpu_array_buffer.write_buffer(&render_device, &render_queue);
|
|
|
|
|
}
|
