fix #225: stabilize render pacing and frame CPU

Replace scheduler-quantized software sleeps with a reusable Windows high-resolution deadline timer, expose pacing in the frame profiler, and make shutdown wake every persistent mesh worker without losing the shared signal.

Preserve retail alpha order while using a stable radix, skip duplicate deferred-alpha SSBO packing, pack light sets, cache static selection descriptors, and retire historical material groups at the whole-frame boundary. The fixed dense-Caul sample improved from roughly 9-12 ms CPU to 5.3-6.2 ms without reducing visual quality.

Release build succeeds with zero warnings and all 6,300 tests pass with five intentional skips. Three independent retail, architecture, and adversarial reviews are clean; the post-review connected route remains pending because local ACE is offline.

Co-authored-by: OpenAI Codex <codex@openai.com>
This commit is contained in:
Erik 2026-07-19 06:29:30 +02:00
parent 47d7086a74
commit 3718e341be
17 changed files with 1103 additions and 225 deletions

View file

@ -1,6 +1,7 @@
using System;
using System.Collections.Generic;
using System.Numerics;
using System.Runtime.InteropServices;
namespace AcDream.App.Rendering;
@ -38,8 +39,7 @@ internal interface IRetailAlphaDrawSource
internal readonly record struct RetailAlphaSubmission(
IRetailAlphaDrawSource Source,
int Token,
float ViewerDistance,
long Sequence);
float ViewerDistance);
/// <summary>
/// Frame-scoped port of retail's shared <c>D3DPolyRender</c> alpha list.
@ -62,7 +62,8 @@ internal sealed class RetailAlphaQueue
private readonly List<IRetailAlphaDrawSource> _sources = new(4);
private int[] _tokenScratch = new int[256];
private int[] _sourceDrawOffsets = new int[4];
private long _nextSequence;
private RetailAlphaSubmission[] _sortScratch = new RetailAlphaSubmission[256];
private readonly int[] _radixOffsets = new int[256];
public bool IsCollecting { get; private set; }
internal int PendingCount => _submissions.Count;
@ -74,7 +75,6 @@ internal sealed class RetailAlphaQueue
if (_submissions.Count != 0 || _sources.Count != 0)
throw new InvalidOperationException("Retail alpha queue retained payload outside a frame.");
_nextSequence = 0;
IsCollecting = true;
}
@ -89,8 +89,7 @@ internal sealed class RetailAlphaQueue
_submissions.Add(new RetailAlphaSubmission(
source,
token,
NormalizeDistance(viewerDistance),
_nextSequence++));
NormalizeDistance(viewerDistance)));
for (int i = 0; i < _sources.Count; i++)
if (ReferenceEquals(_sources[i], source))
@ -114,7 +113,7 @@ internal sealed class RetailAlphaQueue
if (_submissions.Count == 0)
return;
_submissions.Sort(CompareRetailOrder);
SortRetailOrder();
EnsureTokenCapacity(_submissions.Count);
EnsureSourceCapacity(_sources.Count);
Array.Clear(_sourceDrawOffsets, 0, _sources.Count);
@ -178,17 +177,61 @@ internal sealed class RetailAlphaQueue
}
}
private static int CompareRetailOrder(RetailAlphaSubmission left, RetailAlphaSubmission right)
private void SortRetailOrder()
{
// CShadowPart::insertion_sort 0x006B5130 produces descending CYpt
// (far-to-near). Sequence makes the List.Sort result stable for equal
// distances, preserving part/surface append order like retail.
int distance = right.ViewerDistance.CompareTo(left.ViewerDistance);
return distance != 0 ? distance : left.Sequence.CompareTo(right.Sequence);
int count = _submissions.Count;
if (count <= 1)
return;
EnsureSortCapacity(count);
Span<RetailAlphaSubmission> submissions = CollectionsMarshal.AsSpan(_submissions);
Span<RetailAlphaSubmission> scratch = _sortScratch.AsSpan(0, count);
// Positive IEEE-754 float bits sort in the same order as their numeric
// values. Complementing those bits turns an ascending stable radix pass
// into retail's descending CYpt order. Four stable byte passes preserve
// original submission order for equal distances, matching
// CShadowPart::insertion_sort without List.Sort's O(n log n) interface
// comparator overhead in particle-heavy views.
RadixPass(submissions, scratch, shift: 0);
RadixPass(scratch, submissions, shift: 8);
RadixPass(submissions, scratch, shift: 16);
RadixPass(scratch, submissions, shift: 24);
}
private static float NormalizeDistance(float value)
=> float.IsFinite(value) && value >= 0f ? value : 0f;
// value > 0 also canonicalizes -0 to +0 so its IEEE sort key joins the
// same stable equal-distance run as ordinary zero.
=> float.IsFinite(value) && value > 0f ? value : 0f;
private void RadixPass(
ReadOnlySpan<RetailAlphaSubmission> source,
Span<RetailAlphaSubmission> destination,
int shift)
{
Array.Clear(_radixOffsets);
for (int i = 0; i < source.Length; i++)
{
uint key = ~BitConverter.SingleToUInt32Bits(source[i].ViewerDistance);
_radixOffsets[(int)((key >> shift) & 0xFF)]++;
}
int prefix = 0;
for (int bucket = 0; bucket < _radixOffsets.Length; bucket++)
{
int bucketCount = _radixOffsets[bucket];
_radixOffsets[bucket] = prefix;
prefix += bucketCount;
}
for (int i = 0; i < source.Length; i++)
{
RetailAlphaSubmission submission = source[i];
uint key = ~BitConverter.SingleToUInt32Bits(submission.ViewerDistance);
int bucket = (int)((key >> shift) & 0xFF);
destination[_radixOffsets[bucket]++] = submission;
}
}
private void EnsureTokenCapacity(int count)
{
@ -204,6 +247,13 @@ internal sealed class RetailAlphaQueue
Array.Resize(ref _sourceDrawOffsets, count + 4);
}
private void EnsureSortCapacity(int count)
{
if (_sortScratch.Length >= count)
return;
Array.Resize(ref _sortScratch, count + 256);
}
private int FindSourceIndex(IRetailAlphaDrawSource source)
{
for (int i = 0; i < _sources.Count; i++)