bevy/examples/stress_tests/many_lights.rs
BD103 fa179ba475
Use spawn_batch in many_lights example (#11979)
# Objective

- The `many_lights` example uses a for-loop around `commands.spawn`.
- It is generally recommended to use `spawn_batch` instead to lazily
spawn entities, because it doesn't massively grow the command queue.

## Solution

- Use `spawn_batch` in `many_lights` example.

---

## Discussion

- `thread_rng` is called for each light spawned. This is a simple
thread-local `Rc` clone, so it should compile down to a copy and an
increment + decrement instruction.
- I created `golden_ration` outside of the closure and `move`d it in.
This should just be a copy and hopefully will get const-evaluated away.
Would it be better to just move it into the closure itself?

## Performance

Using `spawn_batch` seems to decrease time-to-first-`Update` by 0.1s:
1.3s to 1.2s.

<details>
  <summary>Raw data and how it was collected.</summary>

Before:

- 2024-02-19T15:18:57.650987Z to 2024-02-19T15:18:58.912244Z : 1.3
- 2024-02-19T15:19:25.277135Z to 2024-02-19T15:19:26.542092Z : 1.3
- 2024-02-19T15:19:46.841460Z to 2024-02-19T15:19:48.137560Z : 1.3

After:

- 2024-02-19T15:17:05.749521Z to 2024-02-19T15:17:06.993221Z : 1.2
- 2024-02-19T15:17:38.153049Z to 2024-02-19T15:17:39.393760Z : 1.2
- 2024-02-19T15:18:10.691562Z to 2024-02-19T15:18:11.891430Z : 1.2

To time performance, I tracked the time from the first `Startup` logged
message to the first `Update` logged message.

```shell
$ cargo run --release --example many_lights
Compiling bevy v0.13.0 (/Users/bdeep/dev/bevy/bevy)
    Finished release [optimized] target(s) in 1.54s
     Running `target/release/examples/many_lights`
# THIS TIME
2024-02-19T15:30:13.429609Z  INFO bevy_render::renderer: AdapterInfo { name: "Apple M1", vendor: 0, device: 0, device_type: IntegratedGpu, driver: "", driver_info: "", backend: Metal }
2024-02-19T15:30:13.566856Z  INFO bevy_winit::system: Creating new window "many_lights" (0v1)
2024-02-19T15:30:13.592371Z  WARN many_lights: This is a stress test used to push Bevy to its limit and debug performance issues. It is not representative of an actual game. It must be run in release mode using --release or it will be very slow.
2024-02-19T15:30:13.592572Z  INFO bevy_diagnostic::system_information_diagnostics_plugin::internal: SystemInfo { os: "MacOS 14.2.1 ", kernel: "23.2.0", cpu: "Apple M1", core_count: "8", memory: "16.0 GiB" }
# TO THIS TIME
2024-02-19T15:30:15.429900Z  INFO many_lights: Lights: 100000
2024-02-19T15:30:15.430139Z  INFO bevy diagnostic: fps        :    0.982693   (avg 43.026557)
2024-02-19T15:30:15.430157Z  INFO bevy diagnostic: frame_time : 1017.611750ms (avg 149.456476ms)
2024-02-19T15:30:15.430165Z  INFO bevy diagnostic: frame_count:   12.000000   (avg 6.000000)
```

</details>
2024-02-26 16:02:27 +00:00

191 lines
6.1 KiB
Rust

//! Simple benchmark to test rendering many point lights.
//! Run with `WGPU_SETTINGS_PRIO=webgl2` to restrict to uniform buffers and max 256 lights.
use std::f64::consts::PI;
use bevy::{
diagnostic::{FrameTimeDiagnosticsPlugin, LogDiagnosticsPlugin},
math::{DVec2, DVec3},
pbr::{ExtractedPointLight, GlobalLightMeta},
prelude::*,
render::{camera::ScalingMode, Render, RenderApp, RenderSet},
window::{PresentMode, WindowPlugin, WindowResolution},
winit::{UpdateMode, WinitSettings},
};
use rand::{thread_rng, Rng};
fn main() {
App::new()
.add_plugins((
DefaultPlugins.set(WindowPlugin {
primary_window: Some(Window {
resolution: WindowResolution::new(1920.0, 1080.0)
.with_scale_factor_override(1.0),
title: "many_lights".into(),
present_mode: PresentMode::AutoNoVsync,
..default()
}),
..default()
}),
FrameTimeDiagnosticsPlugin,
LogDiagnosticsPlugin::default(),
LogVisibleLights,
))
.insert_resource(WinitSettings {
focused_mode: UpdateMode::Continuous,
unfocused_mode: UpdateMode::Continuous,
})
.add_systems(Startup, setup)
.add_systems(Update, (move_camera, print_light_count))
.run();
}
fn setup(
mut commands: Commands,
mut meshes: ResMut<Assets<Mesh>>,
mut materials: ResMut<Assets<StandardMaterial>>,
) {
warn!(include_str!("warning_string.txt"));
const LIGHT_RADIUS: f32 = 0.3;
const LIGHT_INTENSITY: f32 = 1000.0;
const RADIUS: f32 = 50.0;
const N_LIGHTS: usize = 100_000;
commands.spawn(PbrBundle {
mesh: meshes.add(Sphere::new(RADIUS).mesh().ico(9).unwrap()),
material: materials.add(LegacyColor::WHITE),
transform: Transform::from_scale(Vec3::NEG_ONE),
..default()
});
let mesh = meshes.add(Cuboid::default());
let material = materials.add(StandardMaterial {
base_color: LegacyColor::PINK,
..default()
});
// NOTE: This pattern is good for testing performance of culling as it provides roughly
// the same number of visible meshes regardless of the viewing angle.
// NOTE: f64 is used to avoid precision issues that produce visual artifacts in the distribution
let golden_ratio = 0.5f64 * (1.0f64 + 5.0f64.sqrt());
// Spawn N_LIGHTS many lights
commands.spawn_batch((0..N_LIGHTS).map(move |i| {
let mut rng = thread_rng();
let spherical_polar_theta_phi = fibonacci_spiral_on_sphere(golden_ratio, i, N_LIGHTS);
let unit_sphere_p = spherical_polar_to_cartesian(spherical_polar_theta_phi);
PointLightBundle {
point_light: PointLight {
range: LIGHT_RADIUS,
intensity: LIGHT_INTENSITY,
color: LegacyColor::hsl(rng.gen_range(0.0..360.0), 1.0, 0.5),
..default()
},
transform: Transform::from_translation((RADIUS as f64 * unit_sphere_p).as_vec3()),
..default()
}
}));
// camera
match std::env::args().nth(1).as_deref() {
Some("orthographic") => commands.spawn(Camera3dBundle {
projection: OrthographicProjection {
scale: 20.0,
scaling_mode: ScalingMode::FixedHorizontal(1.0),
..default()
}
.into(),
..default()
}),
_ => commands.spawn(Camera3dBundle::default()),
};
// add one cube, the only one with strong handles
// also serves as a reference point during rotation
commands.spawn(PbrBundle {
mesh,
material,
transform: Transform {
translation: Vec3::new(0.0, RADIUS, 0.0),
scale: Vec3::splat(5.0),
..default()
},
..default()
});
}
// NOTE: This epsilon value is apparently optimal for optimizing for the average
// nearest-neighbor distance. See:
// http://extremelearning.com.au/how-to-evenly-distribute-points-on-a-sphere-more-effectively-than-the-canonical-fibonacci-lattice/
// for details.
const EPSILON: f64 = 0.36;
fn fibonacci_spiral_on_sphere(golden_ratio: f64, i: usize, n: usize) -> DVec2 {
DVec2::new(
PI * 2. * (i as f64 / golden_ratio),
(1.0 - 2.0 * (i as f64 + EPSILON) / (n as f64 - 1.0 + 2.0 * EPSILON)).acos(),
)
}
fn spherical_polar_to_cartesian(p: DVec2) -> DVec3 {
let (sin_theta, cos_theta) = p.x.sin_cos();
let (sin_phi, cos_phi) = p.y.sin_cos();
DVec3::new(cos_theta * sin_phi, sin_theta * sin_phi, cos_phi)
}
// System for rotating the camera
fn move_camera(time: Res<Time>, mut camera_query: Query<&mut Transform, With<Camera>>) {
let mut camera_transform = camera_query.single_mut();
let delta = time.delta_seconds() * 0.15;
camera_transform.rotate_z(delta);
camera_transform.rotate_x(delta);
}
// System for printing the number of meshes on every tick of the timer
fn print_light_count(time: Res<Time>, mut timer: Local<PrintingTimer>, lights: Query<&PointLight>) {
timer.0.tick(time.delta());
if timer.0.just_finished() {
info!("Lights: {}", lights.iter().len());
}
}
struct LogVisibleLights;
impl Plugin for LogVisibleLights {
fn build(&self, app: &mut App) {
let Ok(render_app) = app.get_sub_app_mut(RenderApp) else {
return;
};
render_app.add_systems(Render, print_visible_light_count.in_set(RenderSet::Prepare));
}
}
// System for printing the number of meshes on every tick of the timer
fn print_visible_light_count(
time: Res<Time>,
mut timer: Local<PrintingTimer>,
visible: Query<&ExtractedPointLight>,
global_light_meta: Res<GlobalLightMeta>,
) {
timer.0.tick(time.delta());
if timer.0.just_finished() {
info!(
"Visible Lights: {}, Rendered Lights: {}",
visible.iter().len(),
global_light_meta.entity_to_index.len()
);
}
}
struct PrintingTimer(Timer);
impl Default for PrintingTimer {
fn default() -> Self {
Self(Timer::from_seconds(1.0, TimerMode::Repeating))
}
}