erik/acdream
1
0
Fork 0
Code Issues Pull requests Projects Releases 6 Packages Wiki Activity Actions

perf(render) Campaign FW3.4a: one walk pass; prepare-once/draw-ranges; arena records

Browse source 
The FW3.4 dense-Arwic pair triggered the +/-20% stop rule (+33.5% CPU
p50, 14x frame allocation). This slice removes the three measured
costs without changing GPU command order (the referee suites assert
identical recorded call sequences):

- WalkFrameDriver: Collect (ONE walk per frame - no GPU work; leaf
  calls and flush points become a recorded event list; the driver
  absorbed the renderer collection pass and exposes the visited sets)
  + Replay (prepare the whole stream once, then replay events,
  interleaving DrawOrderedRange with leaf calls in the exact recorded
  order). RunFrame = Collect+Replay for existing callers.
- WbDrawDispatcher: SubmitOrderedStream split into PrepareOrderedStream
  (all sections + commands + merge runs uploaded once per frame) and
  DrawOrderedRange (bind-once latch; per-run pipeline + DrawIdOffset +
  DrawIndirectRangeRhi). Load-bearing correctness catch from the
  implementation round: merge runs take FORCED BREAKS at the recorded
  event marks - whole-stream merging must not fuse two segments that
  retail separates with a leaf GPU call (shell, punch); the straddle
  assert stays as a dead-code safety net.
- WalkProductionWorldData: WalkFrameStaticRecords carries an
  ArraySegment into a per-frame grow-only arena; the per-cell
  fresh-array copies (the 1.9 MB/frame alloc p50) are gone - zero
  steady-state allocation after warmup.

Suites (lead-verified): full Release build 0 warnings; hermetic
6,758/0; Walk lane 209/1; InstalledDat Walk conformance 40/1
untouched. Next: the dense-Arwic re-measure against the same-session
baseline.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Erik 2026-08-30 17:01:26 +02:00
parent 6301e4dbea
commit 212f5a12e5
7 changed files with 1051 additions and 359 deletions
Download patch file Download diff file Expand all files Collapse all files

16
tests/AcDream.App.Tests/Rendering/Walk/WalkStaticStreamPopulatorTests.cs
View file

@ -27,8 +27,9 @@ namespace AcDream.App.Tests.Rendering.Walk;
/// equivalence referee. Covers <see cref="WbDrawDispatcher.ClassifyEntityForWalk"/>
/// (the shared per-entity classify seam), <see cref="WalkStaticStreamPopulator"/>
/// (opaque → <see cref="OrderedDrawStream"/>, translucent → the alpha queue,
/// selection publish), and the FW3.2a own-cull-scratch fix to
/// <c>SubmitOrderedStream</c>.
/// selection publish), and the FW3.2a own-cull-scratch fix to the ordered
/// submitter (<c>PrepareOrderedStream</c>/<c>DrawOrderedRange</c> as of
/// Campaign FW stage FW3.4a).
/// </summary>
public sealed class WalkStaticStreamPopulatorTests
{
@ -364,18 +365,18 @@ public sealed class WalkStaticStreamPopulatorTests
fx.AlphaQueue.AbortFrame();
}
// ── Deliverable 3: SubmitOrderedStream's own cull scratch ──────────────
// ── Deliverable 3: the ordered submitter's own cull scratch ────────────
[Fact]
public void SubmitOrderedStream_DoesNotReadOrCorruptTheSharedAlphaCullScratch()
public void PrepareThenDrawOrderedStream_DoesNotReadOrCorruptTheSharedAlphaCullScratch()
{
using var fx = new DispatcherFixture();
using DrawScope draw = fx.BeginDraw();
// Poison the SHARED _drawCullModes scratch the alpha path owns — the
// exact array SubmitOrderedStream used to write into before FW3.2a.
// exact array the ordered submitter used to write into before FW3.2a.
// Under the OLD shared-scratch behavior this test's second assertion
// fails: SubmitOrderedStream's own command overwrites index 0 with
// fails: the ordered path's own command overwrites index 0 with
// its own cull mode (Clockwise), destroying the alpha path's poison.
FieldInfo field = typeof(WbDrawDispatcher).GetField(
"_drawCullModes", BindingFlags.NonPublic | BindingFlags.Instance)!;
@ -388,7 +389,8 @@ public sealed class WalkStaticStreamPopulatorTests
Matrix4x4.Identity, WalkDrawStage.Terrain, 0, 0,
WbDrawDispatcher.InstanceLightSet.Disabled, 0, 1f, Vector2.Zero, 0));
fx.Dispatcher.SubmitOrderedStream(draw.Frame, draw.Pass, stream, Matrix4x4.Identity);
fx.Dispatcher.PrepareOrderedStream(draw.Frame, stream, Matrix4x4.Identity);
fx.Dispatcher.DrawOrderedRange(draw.Pass, 0, stream.Count);
// (1) The ordered submission's OWN recorded cull call reflects the
// STREAM's cull mode (Clockwise -> GpuCullMode.Front), not the