Merge pull request #360 from linebender/indirect

Add indirect dispatch and CPU shaders

examples/headless/src/main.rs

@@ -90,6 +90,7 @@ async fn render(mut scenes: SceneSet, index: usize, args: &Args) -> Result<()> {
         &RendererOptions {
             surface_format: None,
             timestamp_period: queue.get_timestamp_period(),
+            use_cpu: false,
         },
     )
     .or_else(|_| bail!("Got non-Send/Sync error from creating renderer"))?;

examples/with_winit/Cargo.toml

@@ -47,3 +47,4 @@ console_error_panic_hook = "0.1.7"
 console_log = "1"
 wasm-bindgen-futures = "0.4.33"
 web-sys = { version = "0.3.60", features = [ "HtmlCollection", "Text" ] }
+getrandom = { version = "0.2.10", features = ["js"] }

examples/with_winit/src/lib.rs

@@ -48,6 +48,9 @@ struct Args {
     scene: Option<i32>,
     #[command(flatten)]
     args: scenes::Arguments,
+    #[arg(long)]
+    /// Whether to use CPU shaders
+    use_cpu: bool,
 }
 
 struct RenderState {
@@ -70,6 +73,7 @@ fn run(
     let mut render_cx = render_cx;
     #[cfg(not(target_arch = "wasm32"))]
     let mut render_state = None::<RenderState>;
+    let use_cpu = args.use_cpu;
     // The design of `RenderContext` forces delayed renderer initialisation to
     // not work on wasm, as WASM futures effectively must be 'static.
     // Otherwise, this could work by sending the result to event_loop.proxy
@@ -84,6 +88,7 @@ fn run(
                 &RendererOptions {
                     surface_format: Some(render_state.surface.format),
                     timestamp_period: render_cx.devices[id].queue.get_timestamp_period(),
+                    use_cpu: use_cpu,
                 },
             )
             .expect("Could create renderer"),
@@ -492,6 +497,7 @@ fn run(
                                 timestamp_period: render_cx.devices[id]
                                     .queue
                                     .get_timestamp_period(),
+                                use_cpu,
                             },
                         )
                         .expect("Could create renderer")

src/cpu_dispatch.rs

@@ -0,0 +1,72 @@
+// Copyright 2023 The Vello authors
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! Support for CPU implementations of compute shaders.
+
+use std::{
+    cell::{RefCell, RefMut},
+    ops::Deref,
+};
+
+#[derive(Clone, Copy)]
+pub enum CpuBinding<'a> {
+    Buffer(&'a [u8]),
+    BufferRW(&'a RefCell<Vec<u8>>),
+    #[allow(unused)]
+    Texture(&'a CpuTexture),
+}
+
+pub enum CpuBufGuard<'a> {
+    Slice(&'a [u8]),
+    Interior(RefMut<'a, Vec<u8>>),
+}
+
+impl<'a> Deref for CpuBufGuard<'a> {
+    type Target = [u8];
+
+    fn deref(&self) -> &Self::Target {
+        match self {
+            CpuBufGuard::Slice(s) => s,
+            CpuBufGuard::Interior(r) => r,
+        }
+    }
+}
+
+impl<'a> CpuBufGuard<'a> {
+    /// Get a mutable reference to the buffer.
+    ///
+    /// Panics if the underlying resource is read-only.
+    pub fn as_mut(&mut self) -> &mut [u8] {
+        match self {
+            CpuBufGuard::Interior(r) => &mut *r,
+            _ => panic!("tried to borrow immutable buffer as mutable"),
+        }
+    }
+}
+
+impl<'a> CpuBinding<'a> {
+    pub fn as_buf(&self) -> CpuBufGuard {
+        match self {
+            CpuBinding::Buffer(b) => CpuBufGuard::Slice(b),
+            CpuBinding::BufferRW(b) => CpuBufGuard::Interior(b.borrow_mut()),
+            _ => panic!("resource type mismatch"),
+        }
+    }
+
+    // TODO: same guard as buf to make mutable
+    #[allow(unused)]
+    pub fn as_tex(&self) -> &CpuTexture {
+        match self {
+            CpuBinding::Texture(t) => t,
+            _ => panic!("resource type mismatch"),
+        }
+    }
+}
+
+/// Structure used for binding textures to CPU shaders.
+pub struct CpuTexture {
+    pub width: usize,
+    pub height: usize,
+    // In RGBA format. May expand in the future.
+    pub pixels: Vec<u32>,
+}

src/cpu_shader/mod.rs

@@ -0,0 +1,8 @@
+// Copyright 2023 The Vello authors
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+//! CPU implementations of shader stages.
+
+mod pathtag_reduce;
+
+pub use pathtag_reduce::pathtag_reduce;

src/cpu_shader/pathtag_reduce.rs

@@ -0,0 +1,35 @@
+// Copyright 2023 The Vello authors
+// SPDX-License-Identifier: Apache-2.0 OR MIT
+
+use vello_encoding::{ConfigUniform, Monoid, PathMonoid};
+
+use crate::cpu_dispatch::CpuBinding;
+
+const WG_SIZE: usize = 256;
+
+fn pathtag_reduce_main(
+    n_wg: u32,
+    config: &ConfigUniform,
+    scene: &[u32],
+    reduced: &mut [PathMonoid],
+) {
+    let pathtag_base = config.layout.path_tag_base;
+    for i in 0..n_wg {
+        let mut m = PathMonoid::default();
+        for j in 0..WG_SIZE {
+            let tag = scene[(pathtag_base + i * WG_SIZE as u32) as usize + j];
+            m = m.combine(&PathMonoid::new(tag));
+        }
+        reduced[i as usize] = m;
+    }
+}
+
+pub fn pathtag_reduce(n_wg: u32, resources: &[CpuBinding]) {
+    let r0 = resources[0].as_buf();
+    let r1 = resources[1].as_buf();
+    let mut r2 = resources[2].as_buf();
+    let config = bytemuck::from_bytes(&r0);
+    let scene = bytemuck::cast_slice(&r1);
+    let reduced = bytemuck::cast_slice_mut(r2.as_mut());
+    pathtag_reduce_main(n_wg, config, scene, reduced);
+}