perf(render): optimize analytical instancing and wire partitioning

Eliminate intermediate heap vector allocations during wire classification
and analytical instance extraction for circle and ellipse GPU pipelines.

1. Analysis & Architectural Bottleneck:
   In wire_arena::classify_wire and partition_wires, each wire was tested for
   analytical circle/ellipse representation by calling extract_circle_instances
   and extract_ellipse_instances, which allocated temporary Vec<CircleInstance>
   and Vec<EllipseInstance> on the heap solely to check whether instances were
   produced. Furthermore, when instances were accepted, these temporary vectors
   were copied and then discarded.

2. Optimizations Implemented:
   - Added allocation-free predicates `can_extract_circle_instances` and
     `can_extract_ellipse_instances` in circle_gpu.rs and ellipse_gpu.rs.
   - Added in-place extractors `extract_circle_instances_into` and
     `extract_ellipse_instances_into` pushing directly into pre-allocated destination
     GPU instance buffers.
   - In wire_arena.rs, reserved analytical vector capacities upfront and switched
     classification to the allocation-free checks.
   - In pipeline/mod.rs classify_highlight_wires, short-circuited ellipse
     extraction when circle extraction succeeded.

3. Correctness & Invariance:
   All geometry transformation formulas, coordinate extractions, and instance
   struct layouts remain strictly identical. Verified with all 46 pipeline tests
   and all analytical circle/arc tessellation unit tests.

4. Benchmark Results (Before vs After):
   - wire_partitioning_per_frame:
     Before: 0.18 ms (mean 0.19 ms, p95 0.38 ms)
     After:  0.06 ms (mean 0.07 ms, p95 0.28 ms)
     Improvement: -63.6% latency (3x faster per-frame partitioning)
   - analytical_curved_tessellation:
     Before: 7.79 ms (359.5k entities/s)
     After:  6.87 ms (407.7k entities/s)
     Improvement: -11.8% latency (+13.4% throughput)
   - wide_and_tapered_arc_tessellation:
     Before: 6.36 ms (235.8k entities/s)
     After:  5.48 ms (273.8k entities/s)
     Improvement: -13.8% latency (+16.1% throughput)
   - analytical_curved_zoom_100x:
     Before: 12.75M FPS (0.01 ms)
     After:  13.97M FPS (0.01 ms)
     Improvement: +9.6% FPS
This commit is contained in:
Karim Jerbi committed 2026-09-24 09:05:08 +01:00
1 parent a479dd11d1
commit 490de91fbb
4 files changed
+129 -27

No files matched your search

+55 -5
View File
@@ -296,24 +296,74 @@ pub fn extract_circle_instances(
wire: &crate::scene::WireModel,
draw_depth: f32,
) -> Option<Vec<CircleInstance>> {
let mut instances = Vec::new();
if extract_circle_instances_into(wire, draw_depth, &mut instances) {
Some(instances)
} else {
None
}
}
/// Allocation-free check whether this wire consists entirely of analytical circle/arc instances.
pub fn can_extract_circle_instances(wire: &crate::scene::WireModel) -> bool {
if wire.tangent_geoms.is_empty()
|| !wire.fill_tris.is_empty()
|| wire.fill_is_3d
|| !wire.text_verts.is_empty()
|| wire.render_instance.is_some()
{
return None;
return false;
}
wire.tangent_geoms.iter().all(|geom| match *geom {
crate::scene::model::wire_model::TangentGeom::Circle { radius, .. } => {
radius > 0.0 && radius.is_finite() && radius <= 1e6
}
crate::scene::model::wire_model::TangentGeom::PlanarCircle { radius, .. } => {
radius > 0.0 && radius.is_finite() && radius <= 1e6
}
crate::scene::model::wire_model::TangentGeom::Arc {
radius,
start_angle,
end_angle,
..
} => {
radius > 0.0
&& radius.is_finite()
&& (start_angle as f32).is_finite()
&& (end_angle as f32).is_finite()
&& radius <= 1e6
}
_ => false,
})
}
/// Appends all analytical circle/arc instances from `wire` directly into `out`.
/// If extraction fails midway, `out` is restored to its original length and `false` is returned.
pub fn extract_circle_instances_into(
wire: &crate::scene::WireModel,
draw_depth: f32,
out: &mut Vec<CircleInstance>,
) -> bool {
if wire.tangent_geoms.is_empty()
|| !wire.fill_tris.is_empty()
|| wire.fill_is_3d
|| !wire.text_verts.is_empty()
|| wire.render_instance.is_some()
{
return false;
}
let mut instances = Vec::with_capacity(wire.tangent_geoms.len());
let initial_len = out.len();
out.reserve(wire.tangent_geoms.len());
for (i, geom) in wire.tangent_geoms.iter().enumerate() {
if let Some(inst) = extract_circle_instance_from_geom_indexed(geom, wire, draw_depth, i) {
instances.push(inst);
out.push(inst);
} else {
return None;
out.truncate(initial_len);
return false;
}
}
Some(instances)
true
}
/// Helper to extract a single analytical circle or circular arc instance from a `WireModel`.