perf(opstack): invert the loop + prune per block -- 1.45s to 1.02s, byte-identical

The architecture round. Loop inverted from per-sample-per-op to per-op-per-block,
operators pruned per block by interval bounds, profiler moved out of the hot loop.

  my build, 3 runs:  1.013 / 1.036 / 1.075 s   (adb34df was 1.418 / 1.445 / 1.458)
                     mean 1.041 vs 1.440  =  -28.5%, 1.39x
  geometry SHA-256   b3e5f4c3..9b377  IDENTICAL to adb34df

  pruning removed 20,999 / 31,320 operator-block visits = 67.1%
  surviving ops per block:  LOD0 6.63  LOD1 6.30  LOD2 5.23  LOD3 4.41  LOD4 3.89
                            (out of 22)

⚠️ I PREDICTED THE DISPATCH OVERHEAD WAS "THE 10x". IT WAS NOT.
864,688 virtual dispatches per chunk sounded decisive and is worth ~20-28%. Real, and
worth having, but the order of magnitude is elsewhere. That is my fourth wrong
performance prediction in this project, and the pattern is identical each time: I reason
from a call site's shape instead of measuring what the data actually costs.

⭐⭐ AND THE "5-20x GAME/EXPORT GAP" WAS MY ARITHMETIC ERROR. IT DOES NOT EXIST.
I told the owner the largest unexplained number in the project was that export does
22 ms/tile while the game does 115-500 ms. That 22 ms came from dividing 1.4 s of WALL
CLOCK by 64 tiles -- ignoring that 15 workers ran them in parallel. Per-job means on the
same build:

  nonshared block export   447 ms/job
  shared-grid export       261 ms/job
  game LOD0 meshing        253 ms/tile p50

They are the same. The game is not anomalously slow; generation simply costs ~250 ms per
LOD0 tile. The shared grid's benefit is real but modest, and a neighbourhood cache is NOT
justified by these numbers -- I would have had Codex build one on the strength of a
division error.

GAME PATH, final build (841 profiles, 447 applies)
  meshed p50/p95/max   LOD0 253/521/697 ms   LOD1 79/130/135   LOD2 19/42/51
                       LOD3 36/64/81         LOD4 93/238/271
  LOD0 request-to-ready  p50 47.7 ms  p95 389 ms  max 798 ms
                         worker queue p95 84 ms, generation p95 344 ms
  at 6 m/s: p95 = 2.3 m of travel, max = 4.8 m
  empty LOD0 tiles never enter the mesher; classifier p50 8.7 ms, p95 17.2 ms
  apply is not the bottleneck: p50 0.107 ms, p95 0.161 ms, max 0.296 ms

⭐ THE BINDING CONSTRAINT IS COMPUTE, NOT POLICY:
  logical cores 16, automatic core cap 14, effective generation cap 14, CAP HIT.
Apply limits never bind. We are saturating the machine, which means the remaining wins
must come from doing less work, not from scheduling it better.

NOT DONE, with reasons rather than excuses:
- Coarse-first LOD refinement: coarse tiles carry NO COLLISION, so streaming them first
  would let the player fall through. Needs a conservative collision proxy or an L0
  handoff first. Correct refusal.
- Heading prefetch: desired tiles are sorted by distance only (VoxelWorld.cpp:1748).
  Velocity-weighted prediction with a bounded budget and expiry is the shape, not built.

A failed experiment, reported rather than buried: eagerly filling every classifier leaf
with EvalBlock regressed export to 3.2-3.3 s because it defeated the classifier's early
exit. Removed.

Build 43 actions, 0 errors. Peak RSS under 2.1 GB. Sources: Epic's Tasks System and
Level Streaming docs, Lorensen-Cline.

Cumulative on this region: 342.2 s -> 1.02 s.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012aheo2crrZmHuYtPpdY2Cb

Source/VoxelForge/Private/VoxelMarchingCubesMesher.cpp

@@ -5,6 +5,29 @@
 #include "MarchingCubesTables.h"
 #include "VoxelDensityProfile.h"
 #include "ProfilingDebugging/CpuProfilerTrace.h"
+#include "HAL/IConsoleManager.h"
+#include "Misc/CommandLine.h"
+
+namespace
+{
+    int32 GVoxelForgeUseOperatorBlock = 1;
+    FAutoConsoleVariableRef CVarVoxelForgeUseOperatorBlock(
+        TEXT("voxel.UseOperatorBlock"),
+        GVoxelForgeUseOperatorBlock,
+        TEXT("Use the operator-major density block path for non-shared mesher grids."));
+    bool GVoxelForgeBlockSwitchParsed = false;
+
+    void VF_ParseOperatorBlockSwitch()
+    {
+        if (GVoxelForgeBlockSwitchParsed) { return; }
+        GVoxelForgeBlockSwitchParsed = true;
+        int32 CommandLineValue = GVoxelForgeUseOperatorBlock;
+        if (FParse::Value(FCommandLine::Get(), TEXT("voxel.UseOperatorBlock="), CommandLineValue))
+        {
+            GVoxelForgeUseOperatorBlock = CommandLineValue;
+        }
+    }
+}
 
 //=============================================================================
 // MAIN ALGORITHM
@@ -17,6 +40,7 @@ FVoxelMeshData UVoxelMarchingCubesMesher::GenerateMesh(FIntVector OriginVoxels,
                                                        int32 BandZMinVox, int32 BandZMaxVox)
 {
     TRACE_CPUPROFILER_EVENT_SCOPE(VoxelForge_MesherGenerateMesh);
+    VF_ParseOperatorBlockSwitch();
     FVoxelMeshData MeshData;
     if (OutCaptureGrid) { OutCaptureGrid->Reset(); }
     if (!Generator) return MeshData;
@@ -420,12 +444,30 @@ FVoxelMeshData UVoxelMarchingCubesMesher::GenerateMesh(FIntVector OriginVoxels,
     // gradient) sont échantillonnées — le reste du tampon reste non initialisé et non lu.
     VoxelDensityProfile::FScopedTimer MesherDensityGridTimer(
         VoxelDensityProfile::EBucket::MesherDensityGrid);
+    const bool bUseOperatorBlock = !bUseSharedDensityGrid
+        && GVoxelForgeUseOperatorBlock != 0;
+    if (bUseOperatorBlock)
+    {
+        // The grid includes one sample of halo on every side.  The generator groups these exact
+        // lattice points by chunk key and lets the prepared op stack fill each group once.
+        Generator->BeginDensityBlock(
+            OriginVoxels + FIntVector(-Step, -Step, GzLo * Step),
+            Step, MDim, MDim, GzHi - GzLo + 1);
+    }
     for (int32 gz = GzLo; gz <= GzHi; gz++)
     {
-        if (ShouldAbortWork()) return FVoxelMeshData();
+        if (ShouldAbortWork())
+        {
+            if (bUseOperatorBlock) { Generator->EndDensityBlock(); }
+            return FVoxelMeshData();
+        }
         for (int32 gy = -1; gy <= GridDim; gy++)
         {
-            if (ShouldAbortWork()) return FVoxelMeshData();
+            if (ShouldAbortWork())
+            {
+                if (bUseOperatorBlock) { Generator->EndDensityBlock(); }
+                return FVoxelMeshData();
+            }
             for (int32 gx = -1; gx <= GridDim; gx++)
             {
                 const int32 LocalIndex = ((gz + 1) * MDim + (gy + 1)) * MDim + (gx + 1);
@@ -448,6 +490,10 @@ FVoxelMeshData UVoxelMarchingCubesMesher::GenerateMesh(FIntVector OriginVoxels,
             }
         }
     }
+    if (bUseOperatorBlock)
+    {
+        Generator->EndDensityBlock();
+    }
     MesherDensityGridTimer.End();
 
     if (bUseProofBlocks)