standalone: whole view under one second -- 0.955 s cold @8 workers, full payload, world unchanged

- Eight-sample X batching of fine density rows, reuse of solved Z intervals in the candidate mask,
  AVX2 marching-cubes cell classification. LOD0/1 density-grid time -61/-62%; interval/sign stage
  140 -> 97 ms; candidate-axis allocation -18 MiB. Shape stage ~413 ms, detail band ~219 ms.
- W1/W8 hashes equal across 44 fields and equal to round 8; routes 5642/5642; look and far-survival
  audits pass; bad-shell control still fails; six fixed captures pixel-identical.
  Remote-view recapture pending (camera 500,0,0).
Verified by me, interleaved (8 workers, cold, BelowNormal 0xFF00, 2,226 tiles, 110.9 MiB payload):
1.012 / 0.927 / 0.926 s vs round 8 1.100 / 1.099 / 1.088 s.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MmSoF64BbRFmk9C3p1VsBJ

Standalone/Source/StandaloneShapeWorld.h

@@ -22,6 +22,7 @@
 #include <type_traits>
 #include <unordered_map>
 #include <unordered_set>
+#include <utility>
 #include <vector>
 
 // Standalone-only world compiler. It compiles the runtime room/tunnel/passages into
@@ -510,6 +511,55 @@ public:
             static_cast<float>(Z));
     }
 
+    void DensityAtLatticeX8(int32 XStart,int32 XStep,int32 Y,int32 Z,
+                            int32 Count,float OutDensity[8]) const
+    {
+        Count=std::clamp(Count,0,8);
+        if(Count==0)return;
+        bool bFast=EditBrushes.empty()&&Y>=Min[1]&&Y<=Max[1]
+            &&Z>=Min[2]&&Z<=Max[2]
+            &&XStart>=Min[0]
+            &&XStart+static_cast<int64>(Count-1)*XStep<=Max[0];
+        if(bFast)
+        {
+            for(int32 Lane=0;Lane<Count;++Lane)
+                if(IsForcedFarAirSample(XStart+Lane*XStep,Y,Z))
+                {bFast=false;break;}
+        }
+        if(!bFast)
+        {
+            for(int32 Lane=0;Lane<Count;++Lane)
+                OutDensity[Lane]=DensityAtLattice(XStart+Lane*XStep,Y,Z);
+            return;
+        }
+
+        const size_t ColumnStart=static_cast<size_t>(Y-Min[1])*Size[0]
+            +static_cast<size_t>(XStart-Min[0]);
+        const size_t Zi=static_cast<size_t>(Z-Min[2]);
+        const size_t WordOffset=Zi>>6;
+        const uint64 Mask=uint64{1}<<(Zi&63u);
+        const size_t NodeBase=Zi*static_cast<size_t>(Size[1])*Size[0]+ColumnStart;
+        constexpr float ProxyBandEdge=DetailSupremum+0.125f;
+        for(int32 Lane=0;Lane<Count;++Lane)
+        {
+            const size_t Column=ColumnStart+static_cast<size_t>(Lane*XStep);
+            const size_t Word=Column*WordsPerZ+WordOffset;
+            const bool bRock=(RockWords[Word]&Mask)!=0;
+            float Density;
+            if(CandidateWords[Word]&Mask)
+            {
+                const int8 Proxy=SurfaceDistanceQ[NodeBase
+                    +static_cast<size_t>(Lane*XStep)];
+                Density=static_cast<float>(Proxy)*(1.0f/16.0f);
+                if((Density<0.0f)!=bRock)
+                    Density=(bRock?-1.0f:1.0f)*std::max(std::abs(Density),1.0f/16.0f);
+            }
+            else
+                Density=bRock?-ProxyBandEdge:ProxyBandEdge;
+            OutDensity[Lane]=Density;
+        }
+    }
+
 private:
     static uint64 PackLatticeKey(int32 X,int32 Y,int32 Z)
     {
@@ -2378,17 +2428,44 @@ private:
     void BuildPackedRockIntervals(FParallelTiming& Timing)
     {
         const int32 NX=Size[0],NY=Size[1],NZ=Size[2];
-        ParallelLines(static_cast<size_t>(NX)*NY,[&](size_t Line)
+        CandidateAxisWords[2].assign(static_cast<size_t>(NX)*NY*WordsPerZ,0);
+        struct FIntervalScratch
+        {
+            std::vector<FInterval> Carve,Solid,ProtectedAir;
+        };
+        std::array<FIntervalScratch,16> WorkerScratch;
+        for(int32 Worker=0;Worker<WorkerCount;++Worker)
+        {
+            WorkerScratch[static_cast<size_t>(Worker)].Carve.reserve(24);
+            WorkerScratch[static_cast<size_t>(Worker)].Solid.reserve(8);
+            WorkerScratch[static_cast<size_t>(Worker)].ProtectedAir.reserve(4);
+        }
+        ParallelLines(static_cast<size_t>(NX)*NY,[&](size_t Line,int32 Worker)
         {
             const int32 X=Min[0]+static_cast<int32>(Line%NX),Y=Min[1]+static_cast<int32>(Line/NX);
-            std::vector<FInterval> Carve,Solid,ProtectedAir;
-            Carve.reserve(24);Solid.reserve(8);ProtectedAir.reserve(4);
+            FIntervalScratch& Scratch=WorkerScratch[static_cast<size_t>(Worker)];
+            std::vector<FInterval>& Carve=Scratch.Carve;
+            std::vector<FInterval>& Solid=Scratch.Solid;
+            std::vector<FInterval>& ProtectedAir=Scratch.ProtectedAir;
+            Carve.clear();Solid.clear();ProtectedAir.clear();
             const int32 Fixed[3]={X,Y,0};
             for(uint32 Id:GetLineCandidates(2,X,Y))
             {
                 const FPrimitive& P=Primitives[Id];FInterval R;
                 if(SolveLine(P,2,Fixed,R))
                 {
+                    if(!P.bCritical)
+                    {
+                        const size_t CandidateBase=Line*WordsPerZ;
+                        const int32 CandidateLo=std::max(Min[2],R.Lo-DetailBand);
+                        const int32 CandidateHi=std::min(Max[2],R.Lo+DetailBand);
+                        const int32 CandidateLo2=std::max(Min[2],R.Hi-DetailBand);
+                        const int32 CandidateHi2=std::min(Max[2],R.Hi+DetailBand);
+                        FillBits(CandidateAxisWords[2],CandidateBase,
+                            CandidateLo-Min[2],CandidateHi-Min[2],true);
+                        FillBits(CandidateAxisWords[2],CandidateBase,
+                            CandidateLo2-Min[2],CandidateHi2-Min[2],true);
+                    }
                     R.Lo=std::max(R.Lo,Min[2])-Min[2];R.Hi=std::min(R.Hi,Max[2])-Min[2];
                     if(R.Lo<=R.Hi)
                     {
@@ -2407,7 +2484,7 @@ private:
             for(const FInterval& R:Solid)FillBits(RockWords,Base,R.Lo,R.Hi,true);
             // Critical passage air is the final authored override, including at landing floors.
             for(const FInterval& R:ProtectedAir)FillBits(RockWords,Base,R.Lo,R.Hi,false);
-        },&Timing);
+        },&Timing,nullptr,16);
     }
 
     void BuildCandidateBands(FParallelTiming& AxisTiming,FParallelTiming& MergeTiming,
@@ -2416,6 +2493,7 @@ private:
         const int32 N[3]={Size[0],Size[1],Size[2]};
         for(int32 Axis=0;Axis<3;++Axis)
         {
+            if(Axis==2)continue;
             const int32 A=(Axis+1)%3,B=(Axis+2)%3;
             const size_t Lines=static_cast<size_t>(Size[A])*Size[B];
             const size_t Words=(static_cast<size_t>(N[Axis])+63u)/64u;
@@ -2437,10 +2515,10 @@ private:
                     FillBits(CandidateAxisWords[Axis],Base,Lo-Min[Axis],Hi-Min[Axis],true);
                     FillBits(CandidateAxisWords[Axis],Base,Lo2-Min[Axis],Hi2-Min[Axis],true);
                 }
-            },&AxisTiming);
+            },&AxisTiming,nullptr,16);
         }
         const auto MergeStart=std::chrono::steady_clock::now();
-        CandidateWords=CandidateAxisWords[2];
+        CandidateWords=std::move(CandidateAxisWords[2]);
         for(int32 Axis=0;Axis<2;++Axis)
         {
             const int32 A=(Axis+1)%3,B=(Axis+2)%3;
@@ -2465,7 +2543,7 @@ private:
                             .fetch_or(uint64{1}<<(Zi&63u),std::memory_order_relaxed);
                     }
                 }
-            },&MergeTiming);
+            },&MergeTiming,nullptr,16);
         }
         const int32 LayerLo=LayerRanges.empty()?1:LayerRanges[0].Lo;
         const int32 LayerHi=LayerRanges.empty()?0:LayerRanges[0].Hi;
@@ -2500,6 +2578,18 @@ private:
             const int32 Y=Min[1]+static_cast<int32>(Line/Size[0]);
             FDetailNoiseLineContext NoiseLine(static_cast<float>(X),static_cast<float>(Y),
                 static_cast<uint32>(Owner->Seed));
+            const FLayerField* LineField=nullptr;
+            bool bLineFieldKnown=false;
+            int32 LineFieldLo=0,LineFieldHi=-1;
+            const auto FindLineLayerField=[&](double Z)->const FLayerField*
+            {
+                if(bLineFieldKnown&&LineField&&Z>=LineFieldLo&&Z<=LineFieldHi)
+                    return LineField;
+                LineField=FindLayerField(Z);
+                bLineFieldKnown=LineField!=nullptr;
+                if(LineField){LineFieldLo=LineField->Lo;LineFieldHi=LineField->Hi;}
+                return LineField;
+            };
             const int32 QueryBinX=FloorDiv(X,ActiveSpatialBinSize);
             const int32 QueryBinY=FloorDiv(Y,ActiveSpatialBinSize);
             int32 CachedQueryBinZ=std::numeric_limits<int32>::min();
@@ -2511,80 +2601,114 @@ private:
             for(size_t W=0;W<WordsPerZ;++W)
             {
                 uint64 Bits=CandidateWords[WordBase+W];
+                const uint64 OriginalBits=Bits;
                 uint64 ValidBits=0;
+                int32 BatchZ[8]{};
+                int32 BatchCount=0,BatchQueryBinZ=std::numeric_limits<int32>::min();
+                const FBinItems* BatchBinItems=nullptr;
+                const auto ProcessBatch=[&]()
+                {
+                    if(BatchCount==0)return;
+                    FEffectiveRockSample Samples[8];
+                    int32 ProfileDistanceSamples=0;
+                    if(bProfile)
+                    {
+                        for(int32 Lane=0;Lane<BatchCount;++Lane)
+                            if((Profile.Candidates++&255u)==0)++ProfileDistanceSamples;
+                    }
+                    const auto DistanceStart=ProfileDistanceSamples>0
+                        ?Clock::now():Clock::time_point{};
+                    EffectiveRockDistanceZ8(X,Y,BatchZ,BatchCount,BatchBinItems,Samples);
+                    if(ProfileDistanceSamples>0)
+                    {
+                        Profile.DistanceSampleNanoseconds+=static_cast<uint64>(
+                            std::chrono::duration_cast<std::chrono::nanoseconds>(
+                                Clock::now()-DistanceStart).count());
+                        Profile.DistanceSamples+=static_cast<uint64>(BatchCount);
+                    }
+                    for(int32 Lane=0;Lane<BatchCount;++Lane)
+                    {
+                        const int32 Z=BatchZ[Lane];
+                        const size_t Zi=static_cast<size_t>(Z-Min[2]);
+                        ++LocalCandidates;
+                        const FEffectiveRockSample& Sample=Samples[Lane];
+                        const float SDF=Sample.Distance;
+                        if(std::abs(SDF)>DetailSupremum+0.125f)continue;
+                        const float SurfaceSDF=Sample.SurfaceSDF;
+                        const float CaveInfluence=Sample.CaveInfluence;
+                        const float FloorInfluence=Sample.FloorInfluence;
+                        const bool bCriticalAir=Sample.bCriticalAir;
+                        float DetailFade=DetailBandFade(SDF);
+                        float MacroValue=0.0f;
+                        bool bMacroKnown=false;
+                        const FLayerField* DetailField=nullptr;
+                        bool bDetailFieldKnown=false;
+                        if(DetailVariant==EDetailVariant::Coherent
+                            &&std::abs(SDF)>DetailBandInnerRadius)
+                        {
+                            MacroValue=NoiseLine.Macro.Sample(static_cast<float>(Z));
+                            bMacroKnown=true;
+                            DetailField=FindLineLayerField(Z);
+                            bDetailFieldKnown=true;
+                            DetailFade=DetailBandFade(SDF,LocalDetailBandEdge(MacroValue,
+                                SurfaceSDF,CaveInfluence,FloorInfluence,DetailField));
+                        }
+                        if(DetailFade<=0.0f&&bProfile)++Profile.LocalBandSkips;
+                        const bool bTimeDetail=DetailFade>0.0f&&bProfile
+                            &&((Profile.DetailEvaluations&63u)==0);
+                        const auto DetailStart=bTimeDetail?Clock::now():Clock::time_point{};
+                        float Displaced=SDF;
+                        if(DetailFade>0.0f)
+                        {
+                            if(bProfile)++Profile.DetailEvaluations;
+                            Displaced+=DetailNoiseOnLine(X,Y,Z,Sample.SurfaceSDF,
+                                CaveInfluence,FloorInfluence,NoiseLine,bTimeDetail?&Profile:nullptr,
+                                DetailField,bDetailFieldKnown,bMacroKnown,MacroValue)*DetailFade;
+                        }
+                        if(bTimeDetail)
+                        {
+                            Profile.DetailSampleNanoseconds+=static_cast<uint64>(
+                                std::chrono::duration_cast<std::chrono::nanoseconds>(
+                                    Clock::now()-DetailStart).count());
+                            ++Profile.DetailSamples;
+                        }
+                        if(bCriticalAir)Displaced=std::min(Displaced,-1.0f/16.0f);
+                        const bool bNewRock=Displaced>=0.0f;
+                        const bool bOldRock=((RockWords[WordBase+(Zi>>6)]>>(Zi&63u))&1u)!=0;
+                        if(bNewRock!=bOldRock)
+                        {
+                            RockWords[WordBase+(Zi>>6)]^=uint64{1}<<(Zi&63u);
+                            ++LocalFlips;
+                            if(bProfile)++Profile.Flips;
+                        }
+                        const size_t Node=(Zi*static_cast<size_t>(Size[1])
+                            +static_cast<size_t>(Y-Min[1]))*Size[0]
+                            +static_cast<size_t>(X-Min[0]);
+                        StoreSurfaceDistance(Node,-Displaced);
+                        ValidBits|=uint64{1}<<(Zi&63u);
+                        ++LocalProxies;
+                    }
+                    BatchCount=0;
+                };
                 while(Bits)
                 {
                     const uint32 Bit=std::countr_zero(Bits);Bits&=Bits-1;
                     const size_t Zi=W*64+Bit;if(Zi>=static_cast<size_t>(Size[2]))continue;
                     const int32 Z=Min[2]+static_cast<int32>(Zi);
-                    ++LocalCandidates;
                     const int32 QueryBinZ=FloorDiv(Z,ActiveSpatialBinSize);
+                    if(BatchCount>0&&QueryBinZ!=BatchQueryBinZ)ProcessBatch();
                     if(QueryBinZ!=CachedQueryBinZ)
                     {
                         const auto Bin=SpatialBins.find({QueryBinX,QueryBinY,QueryBinZ});
                         CachedQueryBinItems=Bin==SpatialBins.end()?nullptr:&Bin->second;
                         CachedQueryBinZ=QueryBinZ;
                     }
-                    const bool bTimeDistance=bProfile&&((Profile.Candidates++&255u)==0);
-                    const auto DistanceStart=bTimeDistance?Clock::now():Clock::time_point{};
-                    ESurfaceFamily SurfaceFamily=ESurfaceFamily::Strata;float SurfaceSDF=100000.0f;
-                    bool bFloorSurface=false,bCriticalAir=false;float CaveInfluence=0.0f,FloorInfluence=0.0f;
-                    const float SDF=EffectiveRockDistance(X,Y,Z,&SurfaceFamily,&SurfaceSDF,
-                        &bFloorSurface,&CaveInfluence,&FloorInfluence,&bCriticalAir,
-                        CachedQueryBinItems,true);
-                    if(bTimeDistance)
-                    {
-                        Profile.DistanceSampleNanoseconds+=static_cast<uint64>(
-                            std::chrono::duration_cast<std::chrono::nanoseconds>(Clock::now()-DistanceStart).count());
-                        ++Profile.DistanceSamples;
-                    }
-                    if(std::abs(SDF)>DetailSupremum+0.125f)continue;
-                    float DetailFade=DetailBandFade(SDF);
-                    const FLayerField* DetailField=nullptr;
-                    bool bDetailFieldKnown=false;
-                    if(DetailVariant==EDetailVariant::Coherent
-                        &&std::abs(SDF)>DetailBandInnerRadius)
-                    {
-                        const float MacroValue=NoiseLine.Macro.Sample(static_cast<float>(Z));
-                        DetailField=FindLayerField(Z);
-                        bDetailFieldKnown=true;
-                        DetailFade=DetailBandFade(SDF,LocalDetailBandEdge(MacroValue,SurfaceSDF,
-                            CaveInfluence,FloorInfluence,DetailField));
-                    }
-                    if(DetailFade<=0.0f&&bProfile)++Profile.LocalBandSkips;
-                    const bool bTimeDetail=DetailFade>0.0f&&bProfile
-                        &&((Profile.DetailEvaluations&63u)==0);
-                    const auto DetailStart=bTimeDetail?Clock::now():Clock::time_point{};
-                    float Displaced=SDF;
-                    if(DetailFade>0.0f)
-                    {
-                        if(bProfile)++Profile.DetailEvaluations;
-                        Displaced+=DetailNoiseOnLine(X,Y,Z,SurfaceSDF,CaveInfluence,
-                            FloorInfluence,NoiseLine,bTimeDetail?&Profile:nullptr,
-                            DetailField,bDetailFieldKnown)*DetailFade;
-                    }
-                    if(bTimeDetail)
-                    {
-                        Profile.DetailSampleNanoseconds+=static_cast<uint64>(
-                            std::chrono::duration_cast<std::chrono::nanoseconds>(Clock::now()-DetailStart).count());
-                        ++Profile.DetailSamples;
-                    }
-                    if(bCriticalAir)Displaced=std::min(Displaced,-1.0f/16.0f);
-                    const bool bNewRock=Displaced>=0.0f;
-                    const bool bOldRock=((RockWords[WordBase+(Zi>>6)]>>(Zi&63u))&1u)!=0;
-                    if(bNewRock!=bOldRock)
-                    {
-                        RockWords[WordBase+(Zi>>6)]^=uint64{1}<<(Zi&63u);
-                        ++LocalFlips;
-                        if(bProfile)++Profile.Flips;
-                    }
-                    const size_t Node=(Zi*static_cast<size_t>(Size[1])+static_cast<size_t>(Y-Min[1]))
-                        *Size[0]+static_cast<size_t>(X-Min[0]);
-                    StoreSurfaceDistance(Node,-Displaced);
-                    ValidBits|=uint64{1}<<Bit;
-                    ++LocalProxies;
+                    if(BatchCount==0)BatchQueryBinZ=QueryBinZ,BatchBinItems=CachedQueryBinItems;
+                    BatchZ[BatchCount++]=Z;
+                    if(BatchCount==8)ProcessBatch();
                 }
-                CandidateWords[WordBase+W]=ValidBits;
+                ProcessBatch();
+                if(OriginalBits!=ValidBits)CandidateWords[WordBase+W]=ValidBits;
             }
             CandidateCount.fetch_add(LocalCandidates,std::memory_order_relaxed);
             ProxyCount.fetch_add(LocalProxies,std::memory_order_relaxed);
@@ -2853,6 +2977,220 @@ private:
         return RockDistance;
     }
 
+    struct FEffectiveRockSample
+    {
+        float Distance=0.0f;
+        float SurfaceSDF=0.0f;
+        float CaveInfluence=0.0f;
+        float FloorInfluence=0.0f;
+        ESurfaceFamily Family=ESurfaceFamily::Strata;
+        bool bFloorSurface=false;
+        bool bCriticalAir=false;
+    };
+
+    void ShapeDistanceZ8(const FPrimitive& P,int32 X,int32 Y,const int32 Z[8],int32 Count,
+                         float OutDistance[8]) const
+    {
+        const __m256d Zero=_mm256_setzero_pd();
+        const __m256d One=_mm256_set1_pd(1.0);
+        const __m256d SignMask=_mm256_set1_pd(-0.0);
+        for(int32 Base=0;Base<Count;Base+=4)
+        {
+            double ZLane[4];
+            const int32 Lanes=std::min(4,Count-Base);
+            for(int32 Lane=0;Lane<4;++Lane)
+                ZLane[Lane]=static_cast<double>(Z[Base+std::min(Lane,Lanes-1)]);
+            const __m256d VZ=_mm256_setr_pd(ZLane[0],ZLane[1],ZLane[2],ZLane[3]);
+            __m256d Distance;
+            if(P.bCapsule)
+            {
+                const double VX=static_cast<double>(X)-P.CapsuleStartWorld[0];
+                const double VY=static_cast<double>(Y)-P.CapsuleStartWorld[1];
+                const __m256d VXv=_mm256_set1_pd(VX);
+                const __m256d VYv=_mm256_set1_pd(VY);
+                const __m256d VZv=_mm256_sub_pd(VZ,_mm256_set1_pd(P.CapsuleStartWorld[2]));
+                __m256d VD=_mm256_mul_pd(VXv,_mm256_set1_pd(P.CapsuleAxisDelta[0]));
+                VD=_mm256_add_pd(VD,_mm256_mul_pd(VYv,_mm256_set1_pd(P.CapsuleAxisDelta[1])));
+                VD=_mm256_add_pd(VD,_mm256_mul_pd(VZv,_mm256_set1_pd(P.CapsuleAxisDelta[2])));
+                const __m256d T=P.CapsuleAxisLengthSquared>1.0e-12
+                    ?_mm256_max_pd(Zero,_mm256_min_pd(One,
+                        _mm256_div_pd(VD,_mm256_set1_pd(P.CapsuleAxisLengthSquared))))
+                    :Zero;
+                const __m256d EX=_mm256_sub_pd(VXv,
+                    _mm256_mul_pd(T,_mm256_set1_pd(P.CapsuleAxisDelta[0])));
+                const __m256d EY=_mm256_sub_pd(VYv,
+                    _mm256_mul_pd(T,_mm256_set1_pd(P.CapsuleAxisDelta[1])));
+                const __m256d EZ=_mm256_sub_pd(VZv,
+                    _mm256_mul_pd(T,_mm256_set1_pd(P.CapsuleAxisDelta[2])));
+                __m256d DistanceSquared=_mm256_mul_pd(EX,EX);
+                DistanceSquared=_mm256_add_pd(DistanceSquared,_mm256_mul_pd(EY,EY));
+                DistanceSquared=_mm256_add_pd(DistanceSquared,_mm256_mul_pd(EZ,EZ));
+                const __m256d Root=_mm256_sqrt_pd(DistanceSquared);
+                double TValues[4],RootValues[4];
+                _mm256_storeu_pd(TValues,T);
+                _mm256_storeu_pd(RootValues,Root);
+                for(int32 Lane=0;Lane<Lanes;++Lane)
+                    OutDistance[Base+Lane]=static_cast<float>(RootValues[Lane]
+                        -CapsuleRadiusAtT(P,TValues[Lane],P.CapsuleAxisLength));
+                continue;
+            }
+            if(P.bRoundedBox)
+            {
+                const double DX=std::abs(static_cast<double>(X)-P.CenterSub[0]/16.0)
+                    -P.RoundedHalfExtent[0];
+                const double DY=std::abs(static_cast<double>(Y)-P.CenterSub[1]/16.0)
+                    -P.RoundedHalfExtent[1];
+                const double DZCenter=P.CenterSub[2]/16.0;
+                const __m256d DZv=_mm256_sub_pd(_mm256_andnot_pd(SignMask,
+                    _mm256_sub_pd(VZ,_mm256_set1_pd(DZCenter))),
+                    _mm256_set1_pd(P.RoundedHalfExtent[2]));
+                const __m256d DXv=_mm256_set1_pd(DX),DYv=_mm256_set1_pd(DY);
+                const __m256d Ox=_mm256_max_pd(DXv,Zero),Oy=_mm256_max_pd(DYv,Zero);
+                const __m256d Oz=_mm256_max_pd(DZv,Zero);
+                __m256d OutsideSquared=_mm256_mul_pd(Ox,Ox);
+                OutsideSquared=_mm256_add_pd(OutsideSquared,_mm256_mul_pd(Oy,Oy));
+                OutsideSquared=_mm256_add_pd(OutsideSquared,_mm256_mul_pd(Oz,Oz));
+                const __m256d MaxXY=_mm256_max_pd(DXv,DYv);
+                const __m256d MaxQ=_mm256_max_pd(MaxXY,DZv);
+                const __m256d Inside=_mm256_min_pd(MaxQ,Zero);
+                Distance=_mm256_sub_pd(_mm256_add_pd(_mm256_sqrt_pd(OutsideSquared),Inside),
+                    _mm256_set1_pd(P.Rounding));
+            }
+            else
+            {
+                const __m256d D[3]={
+                    _mm256_set1_pd(static_cast<double>(X)-P.CenterSub[0]/16.0),
+                    _mm256_set1_pd(static_cast<double>(Y)-P.CenterSub[1]/16.0),
+                    _mm256_sub_pd(VZ,_mm256_set1_pd(P.CenterSub[2]/16.0))};
+                __m256d Q=_mm256_setzero_pd();
+                for(int32 I=0;I<3;++I)for(int32 J=0;J<3;++J)
+                {
+                    const double Coefficient=static_cast<double>(P.Q[I][J])/QScale;
+                    __m256d Term=_mm256_mul_pd(_mm256_set1_pd(Coefficient),D[I]);
+                    Term=_mm256_mul_pd(Term,D[J]);
+                    Term=_mm256_mul_pd(Term,_mm256_set1_pd(256.0));
+                    Q=_mm256_add_pd(Q,Term);
+                }
+                Distance=_mm256_mul_pd(_mm256_sub_pd(
+                    _mm256_sqrt_pd(_mm256_max_pd(Q,Zero)),_mm256_set1_pd(1.0)),
+                    _mm256_set1_pd(P.MinRadius));
+            }
+            double Values[4];
+            _mm256_storeu_pd(Values,Distance);
+            for(int32 Lane=0;Lane<Lanes;++Lane)
+                OutDistance[Base+Lane]=static_cast<float>(Values[Lane]);
+        }
+    }
+
+    void EffectiveRockDistanceZ8(int32 X,int32 Y,const int32 Z[8],int32 Count,
+                                 const FBinItems* BinItems,FEffectiveRockSample Out[8]) const
+    {
+        float Base[8],Cave[8],Overlay[8],CaveFloorInfluence[8];
+        bool CriticalAir[8]{};
+        for(int32 Lane=0;Lane<Count;++Lane)
+        {
+            Base[Lane]=StrataDistance(Z[Lane]);
+            Cave[Lane]=100000.0f;
+            Overlay[Lane]=-100000.0f;
+            CaveFloorInfluence[Lane]=0.0f;
+        }
+        if(BinItems)
+        {
+            for(uint32 Id:*BinItems)
+            {
+                const FPrimitive& P=Primitives[Id];
+                bool Eligible[8]{};
+                bool AnyEligible=false;
+                if(P.bCarve)
+                {
+                    for(int32 Lane=0;Lane<Count;++Lane)
+                    {
+                        const int32 ZValue=Z[Lane];
+                        if(P.bCritical&&X>=P.Min[0]&&X<=P.Max[0]
+                            &&Y>=P.Min[1]&&Y<=P.Max[1]
+                            &&ZValue>=P.Min[2]&&ZValue<=P.Max[2]
+                            &&ShapeContains(P,X,Y,ZValue))
+                            CriticalAir[Lane]=true;
+                        if(X<P.Min[0]-DetailBand||X>P.Max[0]+DetailBand
+                            ||Y<P.Min[1]-DetailBand||Y>P.Max[1]+DetailBand
+                            ||ZValue<P.Min[2]-DetailBand||ZValue>P.Max[2]+DetailBand)
+                            continue;
+                        Eligible[Lane]=true;
+                        AnyEligible=true;
+                    }
+                }
+                else
+                {
+                    for(int32 Lane=0;Lane<Count;++Lane)
+                    {
+                        const int32 ZValue=Z[Lane];
+                        Eligible[Lane]=X>=P.Min[0]&&X<=P.Max[0]
+                            &&Y>=P.Min[1]&&Y<=P.Max[1]
+                            &&ZValue>=P.Min[2]&&ZValue<=P.Max[2];
+                        AnyEligible=AnyEligible||Eligible[Lane];
+                    }
+                }
+                if(!AnyEligible)continue;
+
+                float Distances[8];
+                ShapeDistanceZ8(P,X,Y,Z,Count,Distances);
+                if(P.bCarve)
+                {
+                    const double Floor=P.bHasFloorClip?FloorAt(P,X,Y):0.0;
+                    const float MetadataWidth=static_cast<float>(std::max(P.BlendRadius,6.0));
+                    for(int32 Lane=0;Lane<Count;++Lane)
+                    {
+                        if(!Eligible[Lane])continue;
+                        float Distance=Distances[Lane];
+                        float PrimitiveFloorInfluence=0.0f;
+                        if(P.bHasFloorClip)
+                        {
+                            const float FloorT=(static_cast<float>(std::abs(Z[Lane]-Floor))
+                                -static_cast<float>(P.FloorBlendRadius))
+                                /static_cast<float>(std::max(DetailBand*2,1));
+                            PrimitiveFloorInfluence=1.0f-SmoothUnit(FloorT);
+                            Distance=SmoothMaxDistance(Distance,static_cast<float>(Floor-Z[Lane]),
+                                static_cast<float>(P.FloorBlendRadius));
+                        }
+                        const float PrimitiveWeight=SmoothUnit(0.5f
+                            +(Cave[Lane]-Distance)/(2.0f*MetadataWidth));
+                        const float Combined=SmoothMinDistance(Cave[Lane],Distance,
+                            static_cast<float>(P.BlendRadius));
+                        CaveFloorInfluence[Lane]=std::lerp(CaveFloorInfluence[Lane],
+                            PrimitiveFloorInfluence,PrimitiveWeight);
+                        Cave[Lane]=Combined;
+                    }
+                }
+                else
+                {
+                    for(int32 Lane=0;Lane<Count;++Lane)
+                        if(Eligible[Lane])Overlay[Lane]=std::max(Overlay[Lane],-Distances[Lane]);
+                }
+            }
+        }
+        for(int32 Lane=0;Lane<Count;++Lane)
+        {
+            const float CarveOrOverlay=std::max(Cave[Lane],Overlay[Lane]);
+            const ESurfaceFamily Family=Base[Lane]<=CarveOrOverlay?ESurfaceFamily::Strata:
+                (Cave[Lane]>=Overlay[Lane]?ESurfaceFamily::Cave:ESurfaceFamily::SolidOverlay);
+            constexpr float FamilyBlendWidth=6.0f;
+            const float CaveVsOverlay=SmoothUnit(0.5f
+                +(Cave[Lane]-Overlay[Lane])/(2.0f*FamilyBlendWidth));
+            const float CarveInfluence=SmoothUnit(0.5f
+                +(Base[Lane]-CarveOrOverlay)/(2.0f*FamilyBlendWidth));
+            const float CaveInfluence=CarveInfluence*CaveVsOverlay;
+            const float FloorInfluence=CaveInfluence*CaveFloorInfluence[Lane];
+            Out[Lane].Distance=SmoothMinDistance(Base[Lane],CarveOrOverlay,StrataCaveBlendRadius);
+            Out[Lane].Family=Family;
+            Out[Lane].SurfaceSDF=Family==ESurfaceFamily::Strata?Base[Lane]:
+                (Family==ESurfaceFamily::Cave?Cave[Lane]:Overlay[Lane]);
+            Out[Lane].CaveInfluence=CaveInfluence;
+            Out[Lane].FloorInfluence=FloorInfluence;
+            Out[Lane].bFloorSurface=FloorInfluence>=0.5f;
+            Out[Lane].bCriticalAir=CriticalAir[Lane];
+        }
+    }
+
     float CoarseRockDistance(double X,double Y,double Z,bool* OutCriticalAir) const
     {
         const float Base=StrataDistance(Z);
@@ -3065,8 +3403,8 @@ private:
             {
                 if(NewZ0==Z0+1)
                 {
-                    Corners[0]=Corners[4];Corners[1]=Corners[5];
-                    Corners[2]=Corners[6];Corners[3]=Corners[7];
+                    Corners[0]=Corners[4];Corners[2]=Corners[6];
+                    Corners[1]=Corners[5];Corners[3]=Corners[7];
                     SetPlane(NewZ0+1,true);
                 }
                 else
@@ -3092,14 +3430,15 @@ private:
              Fine(X,Y,6,Seed^0xA511E9B3u)
         {}
 
-        float SurfaceReliefAt(float Z)
+        float SurfaceReliefAt(float Z,bool bMacroKnown=false,float KnownMacro=0.0f)
         {
-            const float MacroValue=Macro.Sample(Z);
+            const float MacroValue=bMacroKnown?KnownMacro:Macro.Sample(Z);
             const float MidValue=Mid.Sample(Z);
             const float FineValue=Fine.Sample(Z);
             return 1.00f*MacroValue+(0.80f+0.25f*MacroValue)
                 *(0.85f*MidValue+0.18f*FineValue);
         }
+
     };
 
     float DetailNoise(double X,double Y,double Z,float SurfaceSDF,
@@ -3127,13 +3466,14 @@ private:
                             FDetailNoiseLineContext& NoiseLine,
                             FDetailWorkerProfile* Profile=nullptr,
                             const FLayerField* KnownField=nullptr,
-                            bool bFieldKnown=false) const
+                            bool bFieldKnown=false,bool bMacroKnown=false,
+                            float KnownMacro=0.0f) const
     {
         if(DetailVariant!=EDetailVariant::Coherent)
             return DetailNoise(X,Y,Z,SurfaceSDF,CaveInfluence,FloorInfluence);
         using Clock=std::chrono::steady_clock;
         const auto ReliefStart=Profile?Clock::now():Clock::time_point{};
-        const float Relief=NoiseLine.SurfaceReliefAt(static_cast<float>(Z));
+        const float Relief=NoiseLine.SurfaceReliefAt(static_cast<float>(Z),bMacroKnown,KnownMacro);
         if(Profile)
             Profile->ReliefSampleNanoseconds+=static_cast<uint64>(
                 std::chrono::duration_cast<std::chrono::nanoseconds>(Clock::now()-ReliefStart).count());
@@ -3225,7 +3565,7 @@ private:
     }
 
     template<class Fn> void ParallelLines(size_t Count,Fn&& Work,FParallelTiming* Timing=nullptr,
-        std::array<double,16>* WorkerActiveSeconds=nullptr) const
+        std::array<double,16>* WorkerActiveSeconds=nullptr,size_t WorkBatch=1) const
     {
         const auto WallStart=std::chrono::steady_clock::now();
         if(WorkerCount<=1||Count<512)
@@ -3247,6 +3587,7 @@ private:
             }
             return;
         }
+        WorkBatch=std::max<size_t>(WorkBatch,1);
         std::atomic<size_t> Next{0};std::atomic<uint64> WorkerNanoseconds{0};
         std::vector<std::thread> Threads;Threads.reserve(WorkerCount);
         for(int32 W=0;W<WorkerCount;++W)
@@ -3255,9 +3596,14 @@ private:
                 const auto WorkerStart=std::chrono::steady_clock::now();
                 for(;;)
                 {
-                    const size_t I=Next.fetch_add(1,std::memory_order_relaxed);if(I>=Count)break;
-                    if constexpr(std::is_invocable_v<Fn&,size_t,int32>)Work(I,W);
-                    else Work(I);
+                    const size_t First=Next.fetch_add(WorkBatch,std::memory_order_relaxed);
+                    if(First>=Count)break;
+                    const size_t Last=First+std::min(WorkBatch,Count-First);
+                    for(size_t I=First;I<Last;++I)
+                    {
+                        if constexpr(std::is_invocable_v<Fn&,size_t,int32>)Work(I,W);
+                        else Work(I);
+                    }
                 }
                 const uint64 WorkerNs=static_cast<uint64>(std::chrono::duration_cast<std::chrono::nanoseconds>(
                     std::chrono::steady_clock::now()-WorkerStart).count());