wip(assembler): round L7 -- shared column cache across workers: whole view 16-19% faster, world unchanged

SharedColumnCache.h: a world-owned, bounded 4-way second-tier cache of exact column values (heightfield and floating islands), keyed by recipe/plan identity plus content hash, XY and island id. Lock-free seqlock reads; set-local spin lock on misses. The FLazy thread-local tier stays first. 83.6% of repeated column work was cross-worker; formula evaluations -60.9%. W12 L1 view: Luna 2.165 -> 1.754 s; reviewer interleaved 2.059 -> 1.722 s. 8 m crossing new tiles 82 -> 52 ms. +66 MiB peak RSS. All hashes (whole view, per-LOD, exact queries, islands seed 0) identical at W1/W8/W12, Clang off and GCC default. MSVC/UBT not compiled here. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CSFYgsdW8ejZSyiMf4qRSX
2026-10-19 21:46:15 +02:00
1 parent 9898e057fd
commit 4b1108bf86
@@ -0,0 +1,183 @@
+#pragma once
+
+#include <array>
+#include <atomic>
+#include <cstddef>
+#include <cstdint>
+#include <cstring>
+#include <memory>
+#include <thread>
+#include <type_traits>
+#include <utility>
+
+namespace VoxelForgeCoreShared
+{
+    // Exact input identity for a pure XY column value. LOD is deliberately not part of this key:
+    // the same recipe/plan column has the same bits at every sampling step.
+    struct FColumnCacheKey
+    {
+        std::uint64_t recipeIdentity = 0;
+        std::uint64_t recipeContentHash = 0;
+        std::uint64_t planIdentity = 0;
+        std::uint64_t planContentHash = 0;
+        std::int64_t xSubvoxels = 0;
+        std::int64_t ySubvoxels = 0;
+        // Optional exact sub-domain identity for recipes with several independent columns
+        // at the same XY (for example, a floating-island anchor).
+        std::uint64_t contextIdentity = 0;
+
+        std::array<std::uint64_t, 7> words() const noexcept
+        {
+            return {recipeIdentity, recipeContentHash, planIdentity, planContentHash,
+                static_cast<std::uint64_t>(xSubvoxels), static_cast<std::uint64_t>(ySubvoxels),
+                contextIdentity};
+        }
+    };
+
+    // A bounded, world-owned second-level cache. Existing thread-local caches stay first, so
+    // their ordinary hit path remains private and lock-free. Shared hits read atomic words; only
+    // a shared miss takes the set spin lock. Entries are four-way set associative, evict on
+    // collision, and carry pointer identities plus content hashes to reject stale reuse.
+    // Les caches TLS restent le premier niveau; seul un defaut partage prend le verrou du groupe.
+    template <typename TValue, std::size_t SetCount, std::size_t Ways = 4>
+    class TSharedColumnValueCache
+    {
+        static_assert(SetCount > 0 && (SetCount & (SetCount - 1)) == 0,
+            "column cache set count must be a power of two");
+        static_assert(Ways > 0 && Ways <= 16, "unsupported column cache associativity");
+        static_assert(std::is_trivially_copyable_v<TValue>,
+            "shared column values must be trivially copyable");
+
+        static constexpr std::size_t ValueWordCount = (sizeof(TValue) + 7) / 8;
+        using FKeyWords = std::array<std::uint64_t, 7>;
+        using FValueWords = std::array<std::uint64_t, ValueWordCount>;
+
+        struct FEntry
+        {
+            std::atomic<std::uint64_t> Version{0};
+            std::atomic<std::uint64_t> Tag{0};
+            std::array<std::atomic<std::uint64_t>, 7> Key{};
+            std::array<std::atomic<std::uint64_t>, ValueWordCount> Value{};
+        };
+
+        struct FSet
+        {
+            std::atomic_flag Writer = ATOMIC_FLAG_INIT;
+            std::uint8_t NextWay = 0;
+            std::array<FEntry, Ways> Entries{};
+        };
+
+        struct FSpinGuard
+        {
+            explicit FSpinGuard(std::atomic_flag& value) : Flag(value)
+            {
+                while (Flag.test_and_set(std::memory_order_acquire))
+                    std::this_thread::yield();
+            }
+            ~FSpinGuard() { Flag.clear(std::memory_order_release); }
+            std::atomic_flag& Flag;
+        };
+
+    public:
+        TSharedColumnValueCache() : Sets(std::make_unique<FSet[]>(SetCount)) {}
+        TSharedColumnValueCache(const TSharedColumnValueCache&) = delete;
+        TSharedColumnValueCache& operator=(const TSharedColumnValueCache&) = delete;
+
+        static TSharedColumnValueCache* setThreadActive(TSharedColumnValueCache* value) noexcept
+        {
+            TSharedColumnValueCache* previous = Active;
+            Active = value;
+            return previous;
+        }
+
+        static TSharedColumnValueCache* threadActive() noexcept { return Active; }
+
+        template <typename TFactory>
+        TValue getOrCompute(const FColumnCacheKey& key, TFactory&& factory,
+            bool& computed)
+        {
+            computed = false;
+            const FKeyWords keyWords = key.words();
+            const std::uint64_t tag = Hash(keyWords);
+            const std::size_t setIndex = static_cast<std::size_t>(tag) & (SetCount - 1);
+            FSet& set = Sets[setIndex];
+            TValue value{};
+            if (TryReadSet(set, keyWords, tag, value)) return value;
+
+            FSpinGuard lock(set.Writer);
+            if (TryReadSet(set, keyWords, tag, value)) return value;
+
+            value = std::forward<TFactory>(factory)();
+            computed = true;
+            FValueWords valueWords{};
+            std::memcpy(valueWords.data(), &value, sizeof(TValue));
+
+            std::size_t replacement = Ways;
+            for (std::size_t way = 0; way < Ways; ++way)
+                if (set.Entries[way].Version.load(std::memory_order_seq_cst) == 0)
+                { replacement = way; break; }
+            if (replacement == Ways)
+            {
+                replacement = set.NextWay;
+                set.NextWay = static_cast<std::uint8_t>((set.NextWay + 1) % Ways);
+            }
+            FEntry& entry = set.Entries[replacement];
+            std::uint64_t version = entry.Version.load(std::memory_order_seq_cst);
+            if (version & 1u) ++version;
+            entry.Version.store(version + 1, std::memory_order_seq_cst);
+            for (std::size_t word = 0; word < keyWords.size(); ++word)
+                entry.Key[word].store(keyWords[word], std::memory_order_seq_cst);
+            for (std::size_t word = 0; word < valueWords.size(); ++word)
+                entry.Value[word].store(valueWords[word], std::memory_order_seq_cst);
+            entry.Tag.store(tag, std::memory_order_seq_cst);
+            entry.Version.store(version + 2, std::memory_order_seq_cst);
+            return value;
+        }
+
+    private:
+        static std::uint64_t Hash(const FKeyWords& words) noexcept
+        {
+            std::uint64_t hash = 0x9E3779B185EBCA87ull;
+            for (const std::uint64_t word : words)
+            {
+                hash ^= word + 0x9E3779B97F4A7C15ull + (hash << 6) + (hash >> 2);
+                hash ^= hash >> 30;
+                hash *= 0xBF58476D1CE4E5B9ull;
+                hash ^= hash >> 27;
+                hash *= 0x94D049BB133111EBull;
+                hash ^= hash >> 31;
+            }
+            return hash == 0 ? 1 : hash;
+        }
+
+        static bool TryRead(const FEntry& entry, const FKeyWords& keyWords,
+            std::uint64_t tag, TValue& out)
+        {
+            const std::uint64_t before = entry.Version.load(std::memory_order_seq_cst);
+            if (before == 0 || (before & 1u)
+                || entry.Tag.load(std::memory_order_seq_cst) != tag) return false;
+            FKeyWords foundKey{};
+            for (std::size_t word = 0; word < foundKey.size(); ++word)
+                foundKey[word] = entry.Key[word].load(std::memory_order_seq_cst);
+            if (foundKey != keyWords) return false;
+            FValueWords foundValue{};
+            for (std::size_t word = 0; word < foundValue.size(); ++word)
+                foundValue[word] = entry.Value[word].load(std::memory_order_seq_cst);
+            const std::uint64_t after = entry.Version.load(std::memory_order_seq_cst);
+            if (before != after || (after & 1u)) return false;
+            std::memcpy(&out, foundValue.data(), sizeof(TValue));
+            return true;
+        }
+
+        static bool TryReadSet(const FSet& set, const FKeyWords& keyWords,
+            std::uint64_t tag, TValue& out)
+        {
+            for (const FEntry& entry : set.Entries)
+                if (TryRead(entry, keyWords, tag, out)) return true;
+            return false;
+        }
+
+        std::unique_ptr<FSet[]> Sets;
+        inline static thread_local TSharedColumnValueCache* Active = nullptr;
+    };
+}
@@ -110,6 +110,13 @@ namespace VoxelForgeCore

    enum class TileClass : std::uint8_t { allSolid, allAir, mixed, unknown };

+    struct HeightfieldColumnEvaluation
+    {
+        std::int64_t x = 0, y = 0;
+        std::uint64_t sequence = 0;
+        bool outsideTileFootprint = false;
+    };
+
    struct TileGenerationStats
    {
        TileClass tileClass = TileClass::unknown;
@@ -124,6 +131,8 @@ namespace VoxelForgeCore
        std::uint64_t columnCacheHits = 0;
        std::uint64_t columnCacheMisses = 0;
        std::uint64_t columnCacheConflictMisses = 0;
+        std::uint64_t sharedColumnCacheHits = 0;
+        std::uint64_t columnEvaluations = 0;
        double classificationMilliseconds = 0.0;
        double columnComputeMilliseconds = 0.0;
        double columnEvaluationExclusiveMilliseconds = 0.0;
@@ -168,7 +177,7 @@ namespace VoxelForgeCore
        bool capRefined = false;
        std::uint64_t columnEvaluationWorkerHash = 0;
        bool columnCoordinateCaptureComplete = true;
-        std::vector<std::array<std::int64_t, 2>> evaluatedColumnCoordinates;
+        std::vector<HeightfieldColumnEvaluation> evaluatedColumnCoordinates;
    };

    struct TileMesh
@@ -651,10 +660,12 @@ namespace VoxelForgeCore
        std::uint64_t columnHits = 0;
        std::uint64_t columnMisses = 0;
        std::uint64_t columnConflictMisses = 0;
+        std::uint64_t sharedColumnHits = 0;
+        std::uint64_t columnEvaluations = 0;
        double columnComputeMilliseconds = 0.0;
        bool captureCoordinates = false;
        bool coordinateCaptureComplete = true;
-        std::vector<std::array<std::int64_t, 2>> evaluatedCoordinates;
+        std::vector<HeightfieldColumnEvaluation> evaluatedCoordinates;
    };

    struct FieldInfluenceBounds
@@ -705,6 +716,9 @@ namespace VoxelForgeCore
            std::int64_t maximumZSubvoxels, std::int32_t stepVoxels) const noexcept;
        static void resetThreadColumnCacheStats(bool captureCoordinates = false,
            bool clearCache = false, std::uint32_t octaveDrop = 0) noexcept;
+        static void setThreadColumnCaptureBounds(std::int64_t minimumXSubvoxels,
+            std::int64_t minimumYSubvoxels, std::int64_t maximumXSubvoxels,
+            std::int64_t maximumYSubvoxels) noexcept;
        static void setThreadColumnOctaveDrop(std::uint32_t octaveDrop) noexcept;
        static std::uint32_t threadColumnOctaveDrop() noexcept;
        static void setThreadColumnInterpolationStrideSubvoxels(std::int64_t stride) noexcept;
@@ -1038,6 +1052,7 @@ namespace VoxelForgeCore
        // Opt-in diagnostic only; records XY columns evaluated by this LOD8 tile.
        // Diagnostic seulement; enregistre les colonnes XY evaluees par cette tuile LOD8.
        bool captureColumnCoordinates = false;
+        bool useSharedColumnCache = true;
        // Separate cold pass only; samples the MC inner stages without changing output.
        // Passe froide separee seulement; mesure les etapes internes MC sans changer la sortie.
        bool profileMesherStages = false;
@@ -55,6 +55,7 @@
 #include "Json.h"
 #include "VoxelForgeCore/VoxelForgeCore.h"
 #include "VoxelForgeCore/ThreadLocalStorage.h"
+#include "VoxelForgeCore/SharedColumnCache.h"

 // Keep Core's expression-level FMA behavior fixed regardless of the toolchain setting.
 // Clang's "fast" mode ignores the pragma, so Core's runtime self-test rejects that build.
@@ -425,6 +425,9 @@ namespace floating_island_detail
    struct FIslandColumnCacheEntry
    {
        bool bValid=false;
+        const FloatingIslandRecipeV1* RecipeIdentity=nullptr;
+        const FloatingIslandPlanV1* PlanIdentity=nullptr;
+        std::uint64_t RecipeContentHash=0,PlanContentHash=0;
        std::uint32_t Seed=0;
        std::uint64_t StableId=0;
        std::int64_t SampleX=0,SampleY=0,CenterX=0,CenterY=0,TopZ=0,Radius=0,TopHalf=0;
@@ -432,9 +435,12 @@ namespace floating_island_detail
        double DeltaX=0.0,DeltaY=0.0,Radial=0.0,Angle=0.0,LobePhase=0.0,TopSurface=0.0;
    };

+    using FSharedIslandColumnCache =
+        VoxelForgeCoreShared::TSharedColumnValueCache<FIslandColumnCacheEntry,16384,4>;
+
    inline const FIslandColumnCacheEntry& IslandColumnCache(
-        const FloatingIslandRecipeV1& recipe,const FloatingIslandAnchorV1& island,
-        double x,double y)
+        const FloatingIslandRecipeV1& recipe,const FloatingIslandPlanV1& plan,
+        const FloatingIslandAnchorV1& island,double x,double y)
    {
        // Density samples arrive on integer Core lattice columns; reuse the exact column metrics
        // across Z samples without changing the field value or touching shared world state.
@@ -450,7 +456,10 @@ namespace floating_island_detail
        std::uint64_t IndexKey=island.stableId
            ^(static_cast<std::uint64_t>(SampleX)*0x9e3779b97f4a7c15ull)
            ^(static_cast<std::uint64_t>(SampleY)*0xc2b2ae3d27d4eb4full)
-            ^(static_cast<std::uint64_t>(recipe.seed)<<23);
+            ^(static_cast<std::uint64_t>(recipe.seed)<<23)
+            ^recipe.contentHash^std::rotl(plan.contentHash,17)
+            ^static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&recipe))
+            ^std::rotl(static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&plan)),31);
        IndexKey^=IndexKey>>33;
        IndexKey*=0xff51afd7ed558ccdull;
        IndexKey^=IndexKey>>33;
@@ -459,7 +468,9 @@ namespace floating_island_detail
        for(std::size_t Way=0;Way<Ways;++Way)
        {
            FIslandColumnCacheEntry& Entry=cache[Base+Way];
-            const bool bKeyMatches=Entry.bValid&&Entry.Seed==recipe.seed
+            const bool bKeyMatches=Entry.bValid&&Entry.RecipeIdentity==&recipe
+                &&Entry.PlanIdentity==&plan&&Entry.RecipeContentHash==recipe.contentHash
+                &&Entry.PlanContentHash==plan.contentHash&&Entry.Seed==recipe.seed
                &&Entry.StableId==island.stableId
                &&Entry.SampleX==SampleX&&Entry.SampleY==SampleY
                &&Entry.CenterX==island.centerSubvoxels[0]
@@ -473,32 +484,53 @@ namespace floating_island_detail
            if(!Entry.bValid)Replacement=&Entry;
        }

-        FIslandColumnCacheEntry& Entry=*Replacement;
-        Entry.bValid=true;
-        Entry.Seed=recipe.seed;
-        Entry.StableId=island.stableId;
-        Entry.SampleX=SampleX;
-        Entry.SampleY=SampleY;
-        Entry.CenterX=island.centerSubvoxels[0];
-        Entry.CenterY=island.centerSubvoxels[1];
-        Entry.TopZ=island.topZSubvoxels;
-        Entry.Radius=island.radiusSubvoxels;
-        Entry.TopHalf=island.topHalfSubvoxels;
-        Entry.TopFlattenQ16=recipe.topFlattenQ16;
-        Entry.ContourWarp=recipe.contourWarpSubvoxels;
-        Entry.DeltaX=x-static_cast<double>(island.centerSubvoxels[0]);
-        Entry.DeltaY=y-static_cast<double>(island.centerSubvoxels[1]);
-        Entry.Radial=std::hypot(Entry.DeltaX,Entry.DeltaY);
-        Entry.Angle=std::atan2(Entry.DeltaY,Entry.DeltaX);
-        Entry.LobePhase=LobePhase(recipe,island);
-        const double EffectiveRadius=std::max(1.0,static_cast<double>(island.radiusSubvoxels)
-            +LobeOffsetWithPhase(recipe,Entry.Angle,static_cast<double>(island.topZSubvoxels),
-                Entry.LobePhase));
-        const double Edge=std::clamp(Entry.Radial/EffectiveRadius,0.0,1.0);
-        const double Drop=(1.0-Q16ToDouble(recipe.topFlattenQ16))
-            *static_cast<double>(island.topHalfSubvoxels)*2.0*Edge*Edge;
-        Entry.TopSurface=static_cast<double>(island.topZSubvoxels)-Drop;
-        return Entry;
+        const auto build=[&]()
+        {
+            FIslandColumnCacheEntry Entry;
+            Entry.bValid=true;
+            Entry.RecipeIdentity=&recipe;
+            Entry.PlanIdentity=&plan;
+            Entry.RecipeContentHash=recipe.contentHash;
+            Entry.PlanContentHash=plan.contentHash;
+            Entry.Seed=recipe.seed;
+            Entry.StableId=island.stableId;
+            Entry.SampleX=SampleX;
+            Entry.SampleY=SampleY;
+            Entry.CenterX=island.centerSubvoxels[0];
+            Entry.CenterY=island.centerSubvoxels[1];
+            Entry.TopZ=island.topZSubvoxels;
+            Entry.Radius=island.radiusSubvoxels;
+            Entry.TopHalf=island.topHalfSubvoxels;
+            Entry.TopFlattenQ16=recipe.topFlattenQ16;
+            Entry.ContourWarp=recipe.contourWarpSubvoxels;
+            Entry.DeltaX=x-static_cast<double>(island.centerSubvoxels[0]);
+            Entry.DeltaY=y-static_cast<double>(island.centerSubvoxels[1]);
+            Entry.Radial=std::hypot(Entry.DeltaX,Entry.DeltaY);
+            Entry.Angle=std::atan2(Entry.DeltaY,Entry.DeltaX);
+            Entry.LobePhase=LobePhase(recipe,island);
+            const double EffectiveRadius=std::max(1.0,static_cast<double>(island.radiusSubvoxels)
+                +LobeOffsetWithPhase(recipe,Entry.Angle,static_cast<double>(island.topZSubvoxels),
+                    Entry.LobePhase));
+            const double Edge=std::clamp(Entry.Radial/EffectiveRadius,0.0,1.0);
+            const double Drop=(1.0-Q16ToDouble(recipe.topFlattenQ16))
+                *static_cast<double>(island.topHalfSubvoxels)*2.0*Edge*Edge;
+            Entry.TopSurface=static_cast<double>(island.topZSubvoxels)-Drop;
+            return Entry;
+        };
+        FIslandColumnCacheEntry Entry{};
+        if(auto* shared=FSharedIslandColumnCache::threadActive())
+        {
+            const VoxelForgeCoreShared::FColumnCacheKey key{
+                static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&recipe)),
+                recipe.contentHash,
+                static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&plan)),
+                plan.contentHash,SampleX,SampleY,island.stableId};
+            bool computed=false;
+            Entry=shared->getOrCompute(key,build,computed);
+        }
+        else Entry=build();
+        *Replacement=Entry;
+        return *Replacement;
    }

    inline std::int64_t ScaledQ16(std::int64_t value, std::int64_t scaleQ16)
@@ -641,6 +673,7 @@ namespace floating_island_detail
    }

    inline double IslandDensity(const FloatingIslandRecipeV1& recipe,
+                                const FloatingIslandPlanV1& plan,
                                const FloatingIslandAnchorV1& island,
                                double x, double y, double z)
    {
@@ -665,7 +698,7 @@ namespace floating_island_detail
                std::max({z - top, radial - envelope, bottomZ - z}), x, y, z);
        }

-        const FIslandColumnCacheEntry& Column=IslandColumnCache(recipe,island,x,y);
+        const FIslandColumnCacheEntry& Column=IslandColumnCache(recipe,plan,island,x,y);
        const double dx=Column.DeltaX;
        const double dy=Column.DeltaY;
        const double radial=Column.Radial;
@@ -733,7 +766,7 @@ namespace floating_island_detail
        double result = static_cast<double>(MaxDensity);
        for (const auto& island : plan.islands)
        {
-            double group = IslandDensity(recipe, island,
+            double group = IslandDensity(recipe, plan, island,
                static_cast<double>(x), static_cast<double>(y), static_cast<double>(z));
            for (const auto& edge : plan.clusterEdges)
            {
@@ -769,7 +802,7 @@ namespace floating_island_detail
        const auto evaluateLocalGroup = [&](std::size_t islandIndex)
        {
            const auto& island = plan.islands[islandIndex];
-            double group = IslandDensity(recipe, island,
+            double group = IslandDensity(recipe, plan, island,
                static_cast<double>(x), static_cast<double>(y), static_cast<double>(z));
            for (const std::uint32_t edgeIndex : featureIndices)
            {
@@ -795,7 +828,7 @@ namespace floating_island_detail
        const auto evaluateDistantGroup = [&](std::size_t islandIndex)
        {
            const auto& island = plan.islands[islandIndex];
-            double group = IslandDensity(recipe, island,
+            double group = IslandDensity(recipe, plan, island,
                static_cast<double>(x), static_cast<double>(y), static_cast<double>(z));
            for (const auto& edge : plan.clusterEdges)
            {
@@ -943,6 +943,10 @@ namespace VoxelForgeCore
        std::shared_ptr<const WorldAssemblyManifest> worldAssembly;
        WorldConfiguration configuration;
        std::unique_ptr<FStandaloneShapeWorld> shape;
+        std::unique_ptr<world_assembly_detail::FSharedHeightfieldColumnCache>
+            sharedHeightfieldColumns;
+        std::unique_ptr<floating_island_detail::FSharedIslandColumnCache>
+            sharedIslandColumns;
        ShapeBuildRequest buildRequest;
        mutable std::shared_mutex tileRegionMutex;
        std::unordered_map<TileKey,std::shared_ptr<FStandaloneShapeWorld>,TileKeyHash> tileRegions;
@@ -953,6 +957,23 @@ namespace VoxelForgeCore
        std::uint64_t lastSequence=0;
    };

+    struct FScopedSharedColumnCaches
+    {
+        using FHeightfieldCache=world_assembly_detail::FSharedHeightfieldColumnCache;
+        using FIslandCache=floating_island_detail::FSharedIslandColumnCache;
+        FHeightfieldCache* PreviousHeightfield=nullptr;
+        FIslandCache* PreviousIslands=nullptr;
+
+        FScopedSharedColumnCaches(FHeightfieldCache* Heightfield,FIslandCache* Islands)
+            : PreviousHeightfield(FHeightfieldCache::setThreadActive(Heightfield)),
+              PreviousIslands(FIslandCache::setThreadActive(Islands)) {}
+        ~FScopedSharedColumnCaches()
+        {
+            FHeightfieldCache::setThreadActive(PreviousHeightfield);
+            FIslandCache::setThreadActive(PreviousIslands);
+        }
+    };
+
    World::World(ResolvedWorldSnapshot snapshot):impl_(std::make_unique<Impl>())
    {
        if(snapshot.data_)
@@ -960,6 +981,15 @@ namespace VoxelForgeCore
            impl_->owner=snapshot.data_->owner;
            impl_->worldAssembly=snapshot.data_->worldAssembly;
            impl_->configuration=snapshot.data_->configuration;
+            if(impl_->worldAssembly)
+            {
+                if(!impl_->worldAssembly->plan.strates.empty())
+                    impl_->sharedHeightfieldColumns=
+                        std::make_unique<world_assembly_detail::FSharedHeightfieldColumnCache>();
+                if(!impl_->worldAssembly->floatingIslands.empty())
+                    impl_->sharedIslandColumns=
+                        std::make_unique<floating_island_detail::FSharedIslandColumnCache>();
+            }
        }
    }
    World::~World()=default;
@@ -1337,6 +1367,9 @@ namespace VoxelForgeCore
            options.legacyDirectMappedColumnCache||key.lod<=2);
        if(!impl_||!impl_->owner||!impl_->shape||!impl_->shape->IsBuilt())
        { error="world must be compiled before generating tiles";return std::nullopt; }
+        FScopedSharedColumnCaches sharedColumnCaches(options.useSharedColumnCache
+                ?impl_->sharedHeightfieldColumns.get():nullptr,
+            options.useSharedColumnCache?impl_->sharedIslandColumns.get():nullptr);
        const auto& world=*impl_->owner;
        std::shared_ptr<FStandaloneShapeWorld> page;
        if(impl_->tileRegionCount.load(std::memory_order_acquire)!=0)
@@ -1500,6 +1533,15 @@ namespace VoxelForgeCore
        FStandaloneShapeWorld::ResetThreadClassificationStats();
        VoxelForgeCore::Heightfield2D::resetThreadColumnCacheStats(
            options.captureColumnCoordinates);
+        if(options.captureColumnCoordinates)
+        {
+            constexpr std::int64_t SubvoxelsPerVoxel=WorldAssemblySubvoxelsPerVoxel;
+            VoxelForgeCore::Heightfield2D::setThreadColumnCaptureBounds(
+                static_cast<std::int64_t>(origin.X)*SubvoxelsPerVoxel,
+                static_cast<std::int64_t>(origin.Y)*SubvoxelsPerVoxel,
+                static_cast<std::int64_t>(origin.X+extent)*SubvoxelsPerVoxel,
+                static_cast<std::int64_t>(origin.Y+extent)*SubvoxelsPerVoxel);
+        }
        bool bNativeSurfaceTile=false;
        bool bNativeSurfaceBandSafe=false;
        double classificationColumnComputeMilliseconds=0.0;
@@ -1544,6 +1586,8 @@ namespace VoxelForgeCore
                    out.diagnostics.columnCacheHits=Columns.columnHits;
                    out.diagnostics.columnCacheMisses=Columns.columnMisses;
                    out.diagnostics.columnCacheConflictMisses=Columns.columnConflictMisses;
+                    out.diagnostics.sharedColumnCacheHits=Columns.sharedColumnHits;
+                    out.diagnostics.columnEvaluations=Columns.columnEvaluations;
                    out.diagnostics.classificationMilliseconds=Counts.Milliseconds;
                    out.diagnostics.classificationExclusiveMilliseconds=std::max(0.0,
                        Counts.Milliseconds-classificationColumnComputeMilliseconds);
@@ -1829,6 +1873,8 @@ namespace VoxelForgeCore
            out.diagnostics.columnCacheHits=Columns.columnHits;
            out.diagnostics.columnCacheMisses=Columns.columnMisses;
            out.diagnostics.columnCacheConflictMisses=Columns.columnConflictMisses;
+            out.diagnostics.sharedColumnCacheHits=Columns.sharedColumnHits;
+            out.diagnostics.columnEvaluations=Columns.columnEvaluations;
            out.diagnostics.columnComputeMilliseconds=Columns.columnComputeMilliseconds;
            out.diagnostics.columnEvaluationExclusiveMilliseconds=Columns.columnComputeMilliseconds;
            out.diagnostics.classificationMilliseconds=Counts.Milliseconds;
@@ -5,6 +5,7 @@
 #include "VoxelForgeCore/VoxelForgeCore.h"

 #include <algorithm>
+#include <atomic>
 #include <bit>
 #include <charconv>
 #include <chrono>
@@ -121,6 +122,9 @@ WorldAssemblyFeatureColumnRangeV1 BuildWorldAssemblyFeatureColumnRangeV1(

 namespace world_assembly_detail
 {
+    using FSharedHeightfieldColumnCache =
+        VoxelForgeCoreShared::TSharedColumnValueCache<HeightfieldPointSample,131072,4>;
+
    // Preserve recipe order without allocating or looking up metadata in the point loop.
    // Garder l'ordre de recette sans allocation ni recherche de metadonnees par point.
    struct FeatureRange
@@ -1375,6 +1379,9 @@ namespace world_assembly_detail
        std::array<std::uint8_t, HeightfieldColumnCacheSetCount>> HeightfieldColumnCacheNextWay;
    inline thread_local HeightfieldColumnCacheStats HeightfieldColumnStats{};
    inline thread_local bool HeightfieldColumnCacheLegacyDirectMapped=false;
+    inline thread_local std::array<std::int64_t,4> HeightfieldColumnCaptureBounds{};
+    inline thread_local bool HeightfieldColumnCaptureBoundsValid=false;
+    inline std::atomic<std::uint64_t> HeightfieldColumnCaptureSequence{0};

    inline std::size_t HeightfieldColumnCacheSet(const WorldAssemblyRecipeV1& recipe,
        const WorldAssemblyStratumPlanV1& plan,std::int64_t x,std::int64_t y) noexcept
@@ -1587,22 +1594,46 @@ namespace world_assembly_detail
            replacement=&cache[first+replacementWay];
        }
        auto& entry=*replacement;
-        const auto start=std::chrono::steady_clock::now();
-        HeightfieldPointSample column=EvaluateColumn(recipe,plan,x,y);
-        HeightfieldColumnStats.columnComputeMilliseconds+=std::chrono::duration<double,std::milli>(
-            std::chrono::steady_clock::now()-start).count();
        ++HeightfieldColumnStats.columnMisses;
-        if(HeightfieldColumnStats.captureCoordinates&&HeightfieldColumnStats.coordinateCaptureComplete)
+        const auto compute=[&]()
        {
-            try
+            const std::uint64_t sequence=HeightfieldColumnStats.captureCoordinates
+                ?HeightfieldColumnCaptureSequence.fetch_add(1,std::memory_order_relaxed):0;
+            const auto start=std::chrono::steady_clock::now();
+            HeightfieldPointSample result=EvaluateColumn(recipe,plan,x,y);
+            HeightfieldColumnStats.columnComputeMilliseconds+=std::chrono::duration<double,std::milli>(
+                std::chrono::steady_clock::now()-start).count();
+            ++HeightfieldColumnStats.columnEvaluations;
+            if(HeightfieldColumnStats.captureCoordinates
+                &&HeightfieldColumnStats.coordinateCaptureComplete)
            {
-                HeightfieldColumnStats.evaluatedCoordinates.push_back({x,y});
-            }
-            catch(...)
-            {
-                HeightfieldColumnStats.coordinateCaptureComplete=false;
+                try
+                {
+                    const bool outside=HeightfieldColumnCaptureBoundsValid
+                        &&(x<HeightfieldColumnCaptureBounds[0]||x>HeightfieldColumnCaptureBounds[2]
+                            ||y<HeightfieldColumnCaptureBounds[1]||y>HeightfieldColumnCaptureBounds[3]);
+                    HeightfieldColumnStats.evaluatedCoordinates.push_back({x,y,sequence,outside});
+                }
+                catch(...)
+                {
+                    HeightfieldColumnStats.coordinateCaptureComplete=false;
+                }
            }
+            return result;
+        };
+        HeightfieldPointSample column{};
+        if(auto* shared=FSharedHeightfieldColumnCache::threadActive())
+        {
+            const VoxelForgeCoreShared::FColumnCacheKey key{
+                static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&recipe)),
+                recipe.contentHash,
+                static_cast<std::uint64_t>(reinterpret_cast<std::uintptr_t>(&plan)),
+                plan.contentHash,x,y};
+            bool computed=false;
+            column=shared->getOrCompute(key,compute,computed);
+            if(!computed)++HeightfieldColumnStats.sharedColumnHits;
        }
+        else column=compute();
        entry={&recipe,&plan,recipe.contentHash,plan.contentHash,x,y,column};
        return column;
    }
@@ -2087,10 +2118,22 @@ void Heightfield2D::resetThreadColumnCacheStats(bool captureCoordinates, bool cl
    Stats.columnHits=0;
    Stats.columnMisses=0;
    Stats.columnConflictMisses=0;
+    Stats.sharedColumnHits=0;
+    Stats.columnEvaluations=0;
    Stats.columnComputeMilliseconds=0.0;
    Stats.captureCoordinates=captureCoordinates;
    Stats.coordinateCaptureComplete=true;
    Stats.evaluatedCoordinates.clear();
+    world_assembly_detail::HeightfieldColumnCaptureBoundsValid=false;
+}
+
+void Heightfield2D::setThreadColumnCaptureBounds(std::int64_t minimumXSubvoxels,
+    std::int64_t minimumYSubvoxels,std::int64_t maximumXSubvoxels,
+    std::int64_t maximumYSubvoxels) noexcept
+{
+    world_assembly_detail::HeightfieldColumnCaptureBounds={minimumXSubvoxels,
+        minimumYSubvoxels,maximumXSubvoxels,maximumYSubvoxels};
+    world_assembly_detail::HeightfieldColumnCaptureBoundsValid=true;
 }

 void Heightfield2D::setThreadColumnCacheLegacyDirectMapped(bool enabled) noexcept
@@ -0,0 +1,171 @@
+# Linux7 — shared terrain columns
+
+**Decision: keep the shared second tier.** On the L1 view it cut median W12 whole-view time by
+19.0%, well above the 3% threshold, and the 8 m camera crossing was also faster. All final output
+hashes match the `9898e05` binary.
+
+Runs used the `linux6` base, Clang 19 with FP contraction off, GCC 14 defaults, CPUs 0–11, normal
+priority, a 6 GiB address-space cap, and the unchanged `powersave` governor. Static timings below
+are three alternating base/candidate W12 runs of 2,553 tiles.
+
+## 1. What was recomputed
+
+Three complete W12 captures per mode on the L1 view. Counts below are medians of actual column
+formula executions after worker-local cache misses, grouped by LOD. “Same worker” means the worker
+had computed that XY before and later missed its local entry. Halo/normal repeats are separated
+before worker attribution; the parenthesized value is the total computed halo/normal probes,
+including unique ones. Each field's median is independent, so row medians can differ slightly from
+their sums.
+
+| LOD | Base total / unique XY | Same worker | Different worker | Halo repeats / probes | Shared total / unique XY |
+|---:|---:|---:|---:|---:|---:|
+| 0 | 556,134 / 128,240 | 22,307 | 358,908 | 46,679 / 70,972 | 135,720 / 127,370 |
+| 1 | 452,626 / 104,284 | 16,393 | 287,791 | 39,245 / 59,082 | 85,658 / 85,479 |
+| 2 | 144,251 / 32,274 | 14,667 | 74,377 | 22,933 / 30,942 | 28,019 / 28,019 |
+| 3 | 91,158 / 33,256 | 0 | 46,387 | 11,564 / 20,339 | 16,213 / 16,213 |
+| 4 | 272,776 / 91,325 | 100 | 167,083 | 14,266 / 28,089 | 90,105 / 90,065 |
+| 5 | 178,511 / 71,957 | 1 | 98,687 | 7,892 / 20,042 | 70,932 / 70,930 |
+| 6 | 342,763 / 280,334 | 20 | 56,204 | 6,205 / 19,977 | 279,266 / 279,202 |
+| 7 | 79,400 / 71,468 | 1 | 4,951 | 2,980 / 14,329 | 70,492 / 70,492 |
+| 8 | 137,062 / 106,219 | 0 | 22,138 | 8,704 / 22,609 | 106,219 / 106,219 |
+
+Across the per-LOD medians, the base made 2.255 million formula evaluations: 919 thousand unique
+XYs and 1.336 million repeats. Of the repeats, 83.6% were from another worker, 4.0% were same-worker
+evictions, and 12.0% were halo/normal probes. The shared candidate made 883 thousand evaluations,
+60.9% fewer; about 8.6 thousand repeats remained. This is mostly a worker-sharing problem, not a
+local-cache-capacity problem.
+
+## 2. Design
+
+`SharedColumnCache.h` is a bounded, four-way second-tier value cache used by both `Heightfield2D`
+and FloatingIslands. Its key includes recipe and plan pointer identity plus content hash, exact XY,
+and an optional exact sub-domain identity; FloatingIslands supplies the island stable ID because
+different anchors can use the same XY. LOD is omitted because the column value is LOD-independent.
+The heightfield table has 524,288 slots and the island table has 65,536. Both are allocated with
+the `World::Impl` and destroyed with it. The Standalone streamer stops and joins workers before
+world teardown; engine shutdown must keep the same drain-before-destroy ordering as the existing
+generator state.
+
+The S14 `FLazy` thread-local caches stay first, so their hits remain worker-private. Shared hits read
+versioned atomic entries without taking a lock; a miss takes a set-local spin lock, rechecks, then
+computes and publishes. A hit racing with a slot replacement can fall through as a miss. Fixed
+capacity bounds memory and replacement bounds reuse as the player moves. No page ring, prefetch, or
+neighbor affinity was needed. The shared table is not an immutable page store; atomic fields and
+version checks give readers a consistent value while a slot can be replaced. Workers only read
+recipe/plan identity and content hashes; they do not mutate generator state or call UObject/engine
+APIs. Epoch, shutdown, and MPSC result handling were not changed. The L3 FP-contract preamble and
+self-test remain intact, as does the `FLazy` rule for large thread-local storage.
+
+## 3. Speed and memory
+
+| W12 static whole view | Base | Shared | Change |
+|---|---:|---:|---:|
+| `whole_view_ready` median | 2.165 s | 1.754 s | −19.0% |
+| Peak RSS median (max) | 401.5 MiB (402.6) | 467.8 MiB (468.0) | +66.3 MiB median |
+
+Per-LOD worker sum is the sum of tile worker seconds, not wall time. Values are medians across the
+same three static runs.
+
+| LOD | Base worker sum | Shared worker sum | Change |
+|---:|---:|---:|---:|
+| 0 | 3.830 s | 2.667 s | −30.4% |
+| 1 | 5.301 s | 4.085 s | −22.9% |
+| 2 | 1.296 s | 0.795 s | −38.7% |
+| 3 | 1.116 s | 0.725 s | −35.1% |
+| 4 | 2.692 s | 1.674 s | −37.8% |
+| 5 | 1.911 s | 1.459 s | −23.7% |
+| 6 | 2.903 s | 2.621 s | −9.7% |
+| 7 | 1.242 s | 1.227 s | −1.2% |
+| 8 | 2.318 s | 2.271 s | −2.0% |
+
+The moving trial warmed the first view, moved the camera 8 m, then generated 144 entering tiles
+(128 LOD0, 16 LOD1) on the same world and worker pool. It ran three times per cache mode.
+
+| Moving check | Shared | Thread-local | Change |
+|---|---:|---:|---:|
+| New-tile wall median | 52.39 ms | 82.00 ms | −36.1% |
+| LOD0 worker sum median | 403.44 ms | 693.67 ms | −41.8% |
+| LOD1 worker sum median | 138.34 ms | 182.29 ms | −24.1% |
+| Peak RSS median (max) | 466.1 MiB (466.9) | 466.1 MiB (467.6) | Same cache allocation in both modes |
+
+## 4. Hashes
+
+Every W1/W12 result matched the base for Clang FP contraction off and GCC default: full detail,
+whole view, each LOD, and exact queries. The L1 base hashes are:
+
+| Scope | Density | Mesh | Payload | Topology |
+|---|---|---|---|---|
+| Full detail, 960 tiles | `0x0ee0579bd15cbbe4` | `0x32e5d4964d610fee` | `0x1932b96ee4b1d910` | `0x69743c6bad3447dc` |
+| Whole view, 2,553 tiles | `0xc10697a8f48380c7` | `0xe75c9119a1498cd5` | `0x49a9a8d1835a6c8c` | `0xedcb23288b5e8724` |
+
+| LOD | Density | Mesh | Payload | Topology |
+|---:|---|---|---|---|
+| 0 | `0x769f2a706d585a72` | `0x33eeeb39fa443816` | `0x645621a1d968983f` | `0xc2457ed905036c9d` |
+| 1 | `0x69cc5a5c0a2c60af` | `0xb48335f5410c57d5` | `0xd15c5480162ab8ba` | `0xfeca1bd025823604` |
+| 2 | `0x85deed5683a77202` | `0x53469895987aeea2` | `0xe55f8ae7e1532033` | `0xd5feb12a0e85c09b` |
+| 3 | `0x6518caefb3be7e7f` | `0xec513c90b853a614` | `0xf62fa1137ff17f82` | `0xccf1dcf681965816` |
+| 4 | `0x62d4be96021992f4` | `0xf1e4c6efcc2615a9` | `0x9dc5f9c88be02f33` | `0xfe6f55125a07c3bf` |
+| 5 | `0x5e4a8c38b8cea6fc` | `0x08ee56998aaf21e5` | `0x541eea8558f26cc8` | `0x6539374a8b3336d8` |
+| 6 | `0xe036e95b9006945b` | `0x624a33f941a99b02` | `0x81b73e14f68bdf86` | `0x4de4c63ce1f80a56` |
+| 7 | `0x8ee358af56a30d8d` | `0x46ab3c6184048b7c` | `0x0a6164b7e68e80c5` | `0x0c26b85bb03bc831` |
+| 8 | `0xc3458e1cbdb9c471` | `0x46c03d0994d75192` | `0x8f89fc5bde12d230` | `0xd16dc0cf62031898` |
+
+Exact queries (9 probes): density and unclamped `0xe4d4a8eb95b35933`, detail
+`0xefcba20c0c70c415`, collision `0xe604823a249029bf`. The FloatingIslands seed-0 fixture also
+passes at Clang/GCC W1/W12 with recipe hash `0x39a24198ad8cf88f`; its whole-view hash matches the
+base: density `0xa8fc5f8f4eaf77a3`, mesh `0xfff7d8ac8923eb9a`, payload `0xd730c51d959c1c59`,
+topology `0xbb33ddb76cd386be`.
+
+## 5. Transfer estimate and Windows work
+
+The majority of the opportunity is cross-worker, so it does not disappear just because the 5800X3D
+has a larger L3. Same-worker evictions are only 4% of baseline repeats; that capacity-driven part
+may shrink. The candidate adds about 66 MiB peak RSS, and a 96 MiB L3 could keep much of the shared
+table resident, though other game data will compete for it. I expect the win to transfer and clear
+3%, likely landing in the mid-single to low-double digits; that percentage is an estimate until the
+5800X3D run.
+
+Windows to-do:
+
+1. Build the Core route with MSVC `/fp:precise`; keep the FP-contract self-test and check the
+   64-bit atomic slot path on the supported Windows target.
+2. Run the W1/W12 whole-view, full-detail, per-LOD, exact-query, and seed-0 FloatingIslands checks
+   against the base binary.
+3. Interleave three static W12 A/B runs on the 5800X3D, then repeat the 8 m camera crossing; record
+   peak RSS and the machine's unchanged governor.
+4. Exercise real streaming shutdown/profile changes and confirm workers drain before world/cache
+   destruction, with Epoch checks and MPSC result queues still intact.
+
+## 6. Failed and corrected runs
+
+- The first Clang W1 hash invocation omitted the explicit data path; it exited 2 after resolving
+  `Standalone/bin/data/owner_world.json`. The retry passed with
+  `Standalone/data/owner_world.json` supplied.
+- The first moving step was 32 m and failed the shape interval 160-million-node safety bound. The
+  benchmark was retried at 8 m, which completed three times in each cache mode.
+- The first shared FloatingIslands cache key omitted the island stable ID. The W12 fixture exposed
+  an LOD4 hash mismatch. Adding the exact sub-domain ID fixed it; final hashes match at W1/W12 for
+  both compilers.
+- An early fixture command passed `--seed=0`, which also overrode the surface-world seed. The final
+  fixture comparison omits that override; FloatingIslands itself still runs its seed-0 check.
+- No run exceeded 30 minutes or remained stuck for 15 minutes. All final Clang and GCC builds
+  succeeded with 12 jobs.
+
+## Owner note
+
+Linux measured a 19.0% W12 whole-view gain and a 36.1% gain on the 8 m crossing, at about 66 MiB
+more peak RSS. Please run the Windows hash matrix and static/moving A/B on the 5800X3D before using
+the laptop percentage as an owner-machine estimate.
+
+## Orchestrator review (Claude)
+
+- **Concurrency read:** a seqlock over all-atomic fields (seq_cst), with the version checked before
+  and after the key/value loads; readers fall back to a miss on any mismatch. Writers hold the set
+  spin lock and mark the version odd while writing. There is no non-atomic shared access, so a
+  reader can't return a torn value. The per-tile scoped `setThreadActive`/restore binds each thread
+  to its own world's table. Default on (`useSharedColumnCache = true`).
+- **Re-run by me** (W12, L1 view, interleaved): base `linux6` 2.014/2.059/2.092 s vs L7 `linux7shared`
+  1.657/1.730/1.729 s, then 1.718/1.705/1.722 s (median 2.059 → 1.722 s, -16%). The whole-view hash was
+  identical in all 8 L7 runs at W12, plus W1 (8.036 s) and W8 (1.799 s).
+- Luna's island-key bug was caught by the W12 hash fixture before review, so the determinism check
+  works as intended.
@@ -35,6 +35,7 @@ namespace
        bool StreamPipeline=false;
        bool StreamHash=false;
        bool ProfileColumnOverlap=false;
+        bool UseSharedColumnCache=true;
        bool ForceGenerate=false;
        bool MeshCoverage=false;
        bool ScreenSpaceGate=false;
@@ -47,8 +48,10 @@ namespace
        int TlsProbeWorkers=0;
        std::string TlsProbeTouch="none";
        bool HasCamera=false;
+        bool HasCameraStep=false;
        bool AutoSurfaceCamera=false;
        FVector CameraMeters=FVector::ZeroVector;
+        FVector CameraStepMeters=FVector::ZeroVector;
        float CameraYawDegrees=0.0f;
        float CameraPitchDegrees=0.0f;
        std::filesystem::path MeshExportPath;
@@ -77,6 +80,15 @@ namespace
        return true;
    }

+    bool ParseCameraStep(std::string_view text,FVector& meters)
+    {
+        const std::string values(text);
+        float x=0.0f,y=0.0f,z=0.0f;
+        if(std::sscanf(values.c_str(),"%f,%f,%f",&x,&y,&z)!=3)return false;
+        meters={x,y,z};
+        return true;
+    }
+
    bool ParseOptions(int argc,char** argv,FOptions& options)
    {
        const std::filesystem::path executable=std::filesystem::absolute(argv[0]);
@@ -91,6 +103,8 @@ namespace
                std::printf("Usage: %s [owner_world.json] --world-assembler-prototype --stream-benchmark --stream-pipeline [options]\n"
                    "  --workers=N --clip-radius=N --max-clip-level=N --max-level=N\n"
                    "  --camera=X,Y,Z,YAW,PITCH (position in metres) --stream-hash\n"
+                    "  --camera-step=X,Y,Z (optional second view step in metres)\n"
+                    "  --column-cache=shared|thread-local (default: shared)\n"
                    "  --mesh-export=FILE (write the exact generated tile meshes for offline rendering)\n"
                    "  --profile-column-overlap --far-horizon-lod8-step=N --force-generate\n"
                    "  --seed=N --recipe=surface-world|floating-islands\n"
@@ -149,6 +163,20 @@ namespace
                {std::fprintf(stderr,"Invalid --camera value: %.*s\n",static_cast<int>(arg.size()),arg.data());return false;}
                options.HasCamera=true;
            }
+            else if(arg.starts_with("--camera-step="))
+            {
+                if(!ParseCameraStep(arg.substr(std::string_view("--camera-step=").size()),
+                    options.CameraStepMeters))
+                {std::fprintf(stderr,"Invalid --camera-step value: %.*s\n",static_cast<int>(arg.size()),arg.data());return false;}
+                options.HasCameraStep=true;
+            }
+            else if(arg.starts_with("--column-cache="))
+            {
+                const std::string_view mode=arg.substr(std::string_view("--column-cache=").size());
+                if(mode=="shared")options.UseSharedColumnCache=true;
+                else if(mode=="thread-local")options.UseSharedColumnCache=false;
+                else {std::fprintf(stderr,"Invalid --column-cache value: %.*s\n",static_cast<int>(arg.size()),arg.data());return false;}
+            }
            else if(arg.starts_with("--mesh-export="))
            {
                options.MeshExportPath=std::filesystem::path(arg.substr(14));
@@ -199,10 +227,12 @@ int main(int argc,char** argv)
    if(!ParseOptions(argc,argv,options))return 2;
    if(options.TlsProbeRequested)
        return StandaloneTlsProbe::Run(options.TlsProbeWorkers,options.TlsProbeTouch);
-    std::printf("[HeadlessConfig] data=%s workers=%d clip_radius=%d max_clip_level=%d max_level=%d hash=%s column_overlap=%s force_generate=%s recipe=%s seed_override=%s render_distance_override=%s\n",
+    std::printf("[HeadlessConfig] data=%s workers=%d clip_radius=%d max_clip_level=%d max_level=%d hash=%s column_overlap=%s force_generate=%s recipe=%s shared_column_cache=%s camera_step_m=(%.3f,%.3f,%.3f) seed_override=%s render_distance_override=%s\n",
        options.DataPath.string().c_str(),options.WorkerCount,options.ClipRadius,options.MaxClipLevel,
        options.MaxLevel,options.StreamHash?"on":"off",options.ProfileColumnOverlap?"on":"off",
        options.ForceGenerate?"on":"off",options.FloatingIslandsRecipe?"floating-islands":"surface-world",
+        options.UseSharedColumnCache?"on":"off",options.CameraStepMeters.X,options.CameraStepMeters.Y,
+        options.CameraStepMeters.Z,
        options.HasSeedOverride?"yes":"no",options.HasRenderDistanceOverride?"yes":"no");
    std::printf("[ColdTimeline] stage=owner_data_load begin_ms=%.3f\n",
        std::chrono::duration<double,std::milli>(Clock::now()-coldStart).count());
@@ -309,10 +339,14 @@ int main(int argc,char** argv)
    {std::fprintf(stderr,"Shape interval build failed: %s\n",error.c_str());return 2;}

    FStandaloneCoreScheduler scheduler;
+    const FVector cameraStepVoxels=options.HasCameraStep
+        ?FVector(options.CameraStepMeters.X*4.0f,options.CameraStepMeters.Y*4.0f,
+            options.CameraStepMeters.Z*4.0f):FVector::ZeroVector;
    return StandaloneStreamBenchmark::RunPipelinedStreamingBenchmark(ownerWorld,snapshot,
        cameraVoxels,options.WorkerCount,options.MaxLevel,VoxelForgeCore::DetailVariant::coherent,
        scheduler,options.StreamHash,false,false,false,false,coldStart,
        options.ProfileColumnOverlap,options.FarHorizonLOD8InteriorStepVoxels,
        options.MeshCoverage,options.MeshExportPath,options.CameraYawDegrees,
-        options.CameraPitchDegrees,options.ScreenSpaceGate);
+        options.CameraPitchDegrees,options.ScreenSpaceGate,options.UseSharedColumnCache,
+        cameraStepVoxels);
 }
@@ -137,7 +137,8 @@ namespace StandaloneStreamBenchmark
        std::chrono::steady_clock::time_point ColdStart,bool bProfileColumnOverlap,
        int32 FarHorizonLOD8InteriorStepVoxels,bool bReportMeshCoverage=false,
        const std::filesystem::path& MeshExportPath={},float CameraYawDegrees=0.0f,
-        float CameraPitchDegrees=0.0f,bool bScreenSpaceGate=false)
+        float CameraPitchDegrees=0.0f,bool bScreenSpaceGate=false,
+        bool bUseSharedColumnCache=true,FVector CameraStepVoxels=FVector::ZeroVector)
    {
        using Clock=std::chrono::steady_clock;
        FStandaloneOwnerWorld& World=*OwnerWorld;
@@ -167,6 +168,21 @@ namespace StandaloneStreamBenchmark
        if(MaxLevel>=0)
            Desired.Tiles.erase(std::remove_if(Desired.Tiles.begin(),Desired.Tiles.end(),
                [&](const FVoxelTileKey& Tile){return Tile.Level>MaxLevel;}),Desired.Tiles.end());
+        const bool bHasCameraStep=std::abs(CameraStepVoxels.X)+std::abs(CameraStepVoxels.Y)
+            +std::abs(CameraStepVoxels.Z)>1.0e-6f;
+        FStandaloneDesiredTileSet MovedDesired;
+        if(bHasCameraStep)
+        {
+            const FVector MovedCamera=CameraPositionVoxels+CameraStepVoxels;
+            MovedDesired=StandaloneWorldMesher::BuildDesiredSet(World,MovedCamera);
+            const auto MovedCoreTiles=Shape.desiredTiles({MovedCamera.X,MovedCamera.Y,MovedCamera.Z});
+            MovedDesired.Tiles.clear();MovedDesired.Tiles.reserve(MovedCoreTiles.size());
+            for(const auto& Key:MovedCoreTiles)
+                MovedDesired.Tiles.emplace_back(FIntVector(Key.coordinate.x,Key.coordinate.y,Key.coordinate.z),Key.lod);
+            if(MaxLevel>=0)
+                MovedDesired.Tiles.erase(std::remove_if(MovedDesired.Tiles.begin(),MovedDesired.Tiles.end(),
+                    [&](const FVoxelTileKey& Tile){return Tile.Level>MaxLevel;}),MovedDesired.Tiles.end());
+        }
        if(!Desired.Tiles.empty())
        {
            FIntVector volumeMin(INT32_MAX,INT32_MAX,INT32_MAX);
@@ -191,17 +207,22 @@ namespace StandaloneStreamBenchmark
        }
        FIntVector FineMin(INT32_MAX,INT32_MAX,INT32_MAX),FineMax(INT32_MIN,INT32_MIN,INT32_MIN);
        FIntVector ClipMin(INT32_MAX,INT32_MAX,INT32_MAX),ClipMax(INT32_MIN,INT32_MIN,INT32_MIN);
-        for(const FVoxelTileKey& Tile:Desired.Tiles)
+        const auto AccumulateBounds=[&](const std::vector<FVoxelTileKey>& Tiles)
        {
-            const FIntVector Origin=Tile.OriginVoxels();const int32 Extent=Tile.ExtentVoxels();
-            ClipMin.X=std::min(ClipMin.X,Origin.X);ClipMin.Y=std::min(ClipMin.Y,Origin.Y);ClipMin.Z=std::min(ClipMin.Z,Origin.Z);
-            ClipMax.X=std::max(ClipMax.X,Origin.X+Extent);ClipMax.Y=std::max(ClipMax.Y,Origin.Y+Extent);ClipMax.Z=std::max(ClipMax.Z,Origin.Z+Extent);
-            if(Tile.Level<World.FullResClipLevels)
+            for(const FVoxelTileKey& Tile:Tiles)
            {
-                FineMin.X=std::min(FineMin.X,Origin.X);FineMin.Y=std::min(FineMin.Y,Origin.Y);FineMin.Z=std::min(FineMin.Z,Origin.Z);
-                FineMax.X=std::max(FineMax.X,Origin.X+Extent);FineMax.Y=std::max(FineMax.Y,Origin.Y+Extent);FineMax.Z=std::max(FineMax.Z,Origin.Z+Extent);
+                const FIntVector Origin=Tile.OriginVoxels();const int32 Extent=Tile.ExtentVoxels();
+                ClipMin.X=std::min(ClipMin.X,Origin.X);ClipMin.Y=std::min(ClipMin.Y,Origin.Y);ClipMin.Z=std::min(ClipMin.Z,Origin.Z);
+                ClipMax.X=std::max(ClipMax.X,Origin.X+Extent);ClipMax.Y=std::max(ClipMax.Y,Origin.Y+Extent);ClipMax.Z=std::max(ClipMax.Z,Origin.Z+Extent);
+                if(Tile.Level<World.FullResClipLevels)
+                {
+                    FineMin.X=std::min(FineMin.X,Origin.X);FineMin.Y=std::min(FineMin.Y,Origin.Y);FineMin.Z=std::min(FineMin.Z,Origin.Z);
+                    FineMax.X=std::max(FineMax.X,Origin.X+Extent);FineMax.Y=std::max(FineMax.Y,Origin.Y+Extent);FineMax.Z=std::max(FineMax.Z,Origin.Z+Extent);
+                }
            }
-        }
+        };
+        AccumulateBounds(Desired.Tiles);
+        if(bHasCameraStep)AccumulateBounds(MovedDesired.Tiles);
        if(FineMin.X==INT32_MAX||ClipMin.X==INT32_MAX)
        {std::fprintf(stderr,"[StreamPipeline] no desired detail or clipmap tiles.\n");return 7;}

@@ -242,7 +263,7 @@ namespace StandaloneStreamBenchmark
        const double ShapeSeconds=std::chrono::duration<double>(ShapeReady-ShapeBuildStart).count();
        FStandaloneStreamingGenerator Streamer(World,WorkerCount,bHashDensity,nullptr,MaxLevel,
            bSkipUvAndColors,bSkipMaterialGroups,bSkipUV,bSkipColors,&Shape,bProfileColumnOverlap,
-            FarHorizonLOD8InteriorStepVoxels);
+            FarHorizonLOD8InteriorStepVoxels,bUseSharedColumnCache);
        if(bScreenSpaceGate)Streamer.SetMesherStageProfilingEnabled(true);
        const auto StreamStart=Clock::now();
        const FStandaloneStreamingUpdate Update=Streamer.StartWithDesired(Desired);
@@ -287,13 +308,19 @@ namespace StandaloneStreamBenchmark
                return X^(Y+static_cast<std::size_t>(0x9E3779B9u)+(X<<6)+(X>>2));
            }
        };
-        struct FFirstColumnUse
+        struct FColumnEvaluationEvent
        {
+            FColumnXY XY;
            FVoxelTileKey Tile;
            std::uint64_t WorkerHash=0;
+            std::uint64_t Sequence=0;
+            bool bOutsideTileFootprint=false;
        };
-        std::array<std::unordered_map<FColumnXY,std::vector<FFirstColumnUse>,FColumnXYHash>,9> ColumnUsesByLOD;
-        std::array<std::uint64_t,9> ColumnDuplicateEventsByLOD{},NeighbourDuplicateEventsByLOD{};
+        std::array<std::vector<FColumnEvaluationEvent>,9> ColumnEventsByLOD;
+        std::array<std::uint64_t,9> ColumnEvaluationEventsByLOD{},UniqueColumnCoordinatesByLOD{};
+        std::array<std::uint64_t,9> ColumnDuplicateEventsByLOD{},SameWorkerEvictedRepeatsByLOD{};
+        std::array<std::uint64_t,9> DifferentWorkerRepeatsByLOD{},HaloNormalRepeatsByLOD{};
+        std::array<std::uint64_t,9> HaloNormalEvaluationsByLOD{},NeighbourDuplicateEventsByLOD{};
        std::array<std::uint64_t,9> CrossWorkerNeighbourDuplicateEventsByLOD{};
        std::array<std::uint64_t,9> ColumnCaptureTilesByLOD{},ExpectedTilesByLOD{};
        std::array<bool,9> ColumnCaptureCompleteByLOD{};
@@ -376,33 +403,12 @@ namespace StandaloneStreamBenchmark
                    ++ColumnCaptureTilesByLOD[LOD];
                    ColumnCaptureCompleteByLOD[LOD]=ColumnCaptureCompleteByLOD[LOD]
                        &&Tile.CoreDiagnostics.columnCoordinateCaptureComplete;
-                    std::vector<std::array<std::int64_t,2>> Coordinates=
-                        Tile.CoreDiagnostics.evaluatedColumnCoordinates;
-                    std::sort(Coordinates.begin(),Coordinates.end());
-                    Coordinates.erase(std::unique(Coordinates.begin(),Coordinates.end()),Coordinates.end());
-                    for(const auto& Coordinate:Coordinates)
+                    auto& Events=ColumnEventsByLOD[LOD];
+                    for(const auto& Coordinate:Tile.CoreDiagnostics.evaluatedColumnCoordinates)
                    {
-                        const FColumnXY XY{Coordinate[0],Coordinate[1]};
-                        auto [Uses,Inserted]=ColumnUsesByLOD[LOD].try_emplace(XY);
-                        std::vector<FFirstColumnUse>& PriorUses=Uses->second;
-                        if(Inserted)
-                        {
-                            PriorUses.push_back({Tile.Key,Tile.CoreDiagnostics.columnEvaluationWorkerHash});
-                            continue;
-                        }
-                        ++ColumnDuplicateEventsByLOD[LOD];
-                        bool bHasNeighbourDuplicate=false,bHasCrossWorkerNeighbourDuplicate=false;
-                        for(const FFirstColumnUse& Prior:PriorUses)
-                        {
-                            if(!AreSameLODNeighbours(Prior.Tile,Tile.Key))continue;
-                            bHasNeighbourDuplicate=true;
-                            bHasCrossWorkerNeighbourDuplicate=bHasCrossWorkerNeighbourDuplicate
-                                ||Prior.WorkerHash!=Tile.CoreDiagnostics.columnEvaluationWorkerHash;
-                        }
-                        if(bHasNeighbourDuplicate)++NeighbourDuplicateEventsByLOD[LOD];
-                        if(bHasCrossWorkerNeighbourDuplicate)
-                            ++CrossWorkerNeighbourDuplicateEventsByLOD[LOD];
-                        PriorUses.push_back({Tile.Key,Tile.CoreDiagnostics.columnEvaluationWorkerHash});
+                        Events.push_back({{Coordinate.x,Coordinate.y},Tile.Key,
+                            Tile.CoreDiagnostics.columnEvaluationWorkerHash,Coordinate.sequence,
+                            Coordinate.outsideTileFootprint});
                    }
                }
                WholeViewReady=std::max(WholeViewReady,Tile.CompletedAt);
@@ -449,6 +455,45 @@ namespace StandaloneStreamBenchmark
                bFullDetailReported=true;
            }
        }
+        if(bHasCameraStep)
+        {
+            const auto MovingStart=Clock::now();
+            const auto MovingUpdate=Streamer.UpdateDesiredWithSet(MovedDesired,Desired.Tiles,1);
+            std::array<std::uint64_t,9> MovingTilesByLOD{};
+            std::array<double,9> MovingWorkerSecondsByLOD{};
+            int32 MovingFinished=0;
+            while(MovingFinished<MovingUpdate.NewJobs)
+            {
+                std::vector<FStandaloneCpuTile> Ready=Streamer.TakeReady();
+                if(Ready.empty())
+                {std::this_thread::sleep_for(std::chrono::milliseconds(1));continue;}
+                for(const FStandaloneCpuTile& Tile:Ready)
+                {
+                    ++MovingFinished;
+                    if(Tile.Key.Level>=0&&Tile.Key.Level<static_cast<int32>(MovingTilesByLOD.size()))
+                    {
+                        const std::size_t LOD=static_cast<std::size_t>(Tile.Key.Level);
+                        ++MovingTilesByLOD[LOD];
+                        MovingWorkerSecondsByLOD[LOD]+=Tile.WorkerSeconds;
+                    }
+                }
+            }
+            const double MovingWallSeconds=std::chrono::duration<double>(Clock::now()-MovingStart).count();
+            const double StepDistanceMeters=std::sqrt(
+                static_cast<double>(CameraStepVoxels.X)*CameraStepVoxels.X
+                +static_cast<double>(CameraStepVoxels.Y)*CameraStepVoxels.Y
+                +static_cast<double>(CameraStepVoxels.Z)*CameraStepVoxels.Z)
+                *static_cast<double>(World.CoreVoxelSizeMicrons)/1000000.0;
+            std::printf("[MovingCameraStep] step_voxels=(%.3f,%.3f,%.3f) distance_m=%.3f desired_tiles=%zu new_tiles=%d completed=%d wall_s=%.6f shared_column_cache=%s\n",
+                CameraStepVoxels.X,CameraStepVoxels.Y,CameraStepVoxels.Z,StepDistanceMeters,
+                MovedDesired.Tiles.size(),MovingUpdate.NewJobs,MovingFinished,MovingWallSeconds,
+                bUseSharedColumnCache?"on":"off");
+            for(std::size_t LOD=0;LOD<MovingTilesByLOD.size();++LOD)
+                if(MovingTilesByLOD[LOD]!=0)
+                    std::printf("[MovingCameraStepLOD] lod=%zu tiles=%llu worker_sum_s=%.6f\n",
+                        LOD,static_cast<unsigned long long>(MovingTilesByLOD[LOD]),
+                        MovingWorkerSecondsByLOD[LOD]);
+        }
        Streamer.Stop();
        bool bScreenSpaceGatePassing=true;
        if(bScreenSpaceGate)
@@ -472,6 +517,58 @@ namespace StandaloneStreamBenchmark
                bSceneExportPassing?"PASS":"FAIL",MeshExportPath.string().c_str());
            bSceneExportPassing=bSceneExportPassing&&!FileSizeError;
        }
+        if(bProfileColumnOverlap)
+        {
+            struct FColumnPriorUse
+            {
+                FVoxelTileKey Tile;
+                std::uint64_t WorkerHash=0;
+            };
+            for(std::size_t LOD=0;LOD<ColumnEventsByLOD.size();++LOD)
+            {
+                auto& Events=ColumnEventsByLOD[LOD];
+                std::sort(Events.begin(),Events.end(),[](const FColumnEvaluationEvent& A,
+                    const FColumnEvaluationEvent& B){return A.Sequence<B.Sequence;});
+                std::unordered_map<FColumnXY,std::vector<FColumnPriorUse>,FColumnXYHash> UsesByXY;
+                UsesByXY.reserve(Events.size());
+                for(const FColumnEvaluationEvent& Event:Events)
+                {
+                    ++ColumnEvaluationEventsByLOD[LOD];
+                    if(Event.bOutsideTileFootprint)++HaloNormalEvaluationsByLOD[LOD];
+                    auto [Found,Inserted]=UsesByXY.try_emplace(Event.XY);
+                    auto& PriorUses=Found->second;
+                    if(Inserted)
+                    {
+                        ++UniqueColumnCoordinatesByLOD[LOD];
+                        PriorUses.push_back({Event.Tile,Event.WorkerHash});
+                        continue;
+                    }
+                    ++ColumnDuplicateEventsByLOD[LOD];
+                    if(Event.bOutsideTileFootprint)
+                        ++HaloNormalRepeatsByLOD[LOD];
+                    else
+                    {
+                        const bool bSameWorkerSeen=std::any_of(PriorUses.begin(),PriorUses.end(),
+                            [&](const FColumnPriorUse& Prior)
+                            {return Prior.WorkerHash==Event.WorkerHash;});
+                        if(bSameWorkerSeen)++SameWorkerEvictedRepeatsByLOD[LOD];
+                        else ++DifferentWorkerRepeatsByLOD[LOD];
+                    }
+                    bool bHasNeighbourDuplicate=false,bHasCrossWorkerNeighbourDuplicate=false;
+                    for(const FColumnPriorUse& Prior:PriorUses)
+                    {
+                        if(!AreSameLODNeighbours(Prior.Tile,Event.Tile))continue;
+                        bHasNeighbourDuplicate=true;
+                        bHasCrossWorkerNeighbourDuplicate=bHasCrossWorkerNeighbourDuplicate
+                            ||Prior.WorkerHash!=Event.WorkerHash;
+                    }
+                    if(bHasNeighbourDuplicate)++NeighbourDuplicateEventsByLOD[LOD];
+                    if(bHasCrossWorkerNeighbourDuplicate)
+                        ++CrossWorkerNeighbourDuplicateEventsByLOD[LOD];
+                    PriorUses.push_back({Event.Tile,Event.WorkerHash});
+                }
+            }
+        }
        bool bColumnOverlapCapturePassing=true;
        if(bProfileColumnOverlap)
        {
@@ -480,11 +577,16 @@ namespace StandaloneStreamBenchmark
                const bool bLODComplete=ColumnCaptureCompleteByLOD[LOD]
                    &&ColumnCaptureTilesByLOD[LOD]==ExpectedTilesByLOD[LOD];
                bColumnOverlapCapturePassing=bColumnOverlapCapturePassing&&bLODComplete;
-                std::printf("[WorldAssemblerLODColumnOverlap] lod=%zu tiles=%llu expected_tiles=%llu unique_xy_columns=%zu repeated_tile_evaluations=%llu neighbouring_duplicate_evaluations=%llu cross_worker_neighbouring_duplicates=%llu capture_complete=%d\n",
+                std::printf("[WorldAssemblerLODColumnOverlap] lod=%zu tiles=%llu expected_tiles=%llu total_column_evaluations=%llu unique_xy_columns=%llu repeated_column_evaluations=%llu same_worker_evicted_repeats=%llu different_worker_repeats=%llu halo_normal_repeats=%llu halo_normal_evaluations=%llu neighbouring_duplicate_evaluations=%llu cross_worker_neighbouring_duplicates=%llu capture_complete=%d\n",
                    LOD,static_cast<unsigned long long>(ColumnCaptureTilesByLOD[LOD]),
                    static_cast<unsigned long long>(ExpectedTilesByLOD[LOD]),
-                    ColumnUsesByLOD[LOD].size(),
+                    static_cast<unsigned long long>(ColumnEvaluationEventsByLOD[LOD]),
+                    static_cast<unsigned long long>(UniqueColumnCoordinatesByLOD[LOD]),
                    static_cast<unsigned long long>(ColumnDuplicateEventsByLOD[LOD]),
+                    static_cast<unsigned long long>(SameWorkerEvictedRepeatsByLOD[LOD]),
+                    static_cast<unsigned long long>(DifferentWorkerRepeatsByLOD[LOD]),
+                    static_cast<unsigned long long>(HaloNormalRepeatsByLOD[LOD]),
+                    static_cast<unsigned long long>(HaloNormalEvaluationsByLOD[LOD]),
                    static_cast<unsigned long long>(NeighbourDuplicateEventsByLOD[LOD]),
                    static_cast<unsigned long long>(CrossWorkerNeighbourDuplicateEventsByLOD[LOD]),
                    bLODComplete?1:0);
@@ -428,12 +428,14 @@ public:
                                           bool bInSkipColors=false,
                                           VoxelForgeCore::World* InCoreWorld=nullptr,
                                           bool bInCaptureColumnCoordinates=false,
-                                           int32 InLod8HorizonInteriorStepVoxels=0)
+                                           int32 InLod8HorizonInteriorStepVoxels=0,
+                                           bool bInSharedColumnCache=true)
        :World(&InWorld),WorkerCount(FMath::Clamp(InWorkerCount,1,16)),bHashDensity(bInHashDensity),
         MeshCache(InMeshCache),MaxLevelFilter(InMaxLevelFilter),
         CoreWorld(InCoreWorld),bSkipUvAndColors(bInSkipUvAndColors),bSkipMaterialGroups(bInSkipMaterialGroups),
         bSkipUV(bInSkipUV),bSkipColors(bInSkipColors),
         bCaptureColumnCoordinates(bInCaptureColumnCoordinates),
+         bSharedColumnCache(bInSharedColumnCache),
         Lod8HorizonInteriorStepVoxels(std::max(0,InLod8HorizonInteriorStepVoxels))
    {
        VoxelGenLOD::InitializeConsoleSwitches();
@@ -816,6 +818,7 @@ private:
            Options.skipUvAndColors=bSkipUvAndColors;
            Options.skipMaterialGroups=bSkipMaterialGroups;Options.skipUv=bSkipUV;Options.skipColors=bSkipColors;
            Options.captureColumnCoordinates=bCaptureColumnCoordinates;
+            Options.useSharedColumnCache=bSharedColumnCache;
            Options.lod8HorizonInteriorStepVoxels=Lod8HorizonInteriorStepVoxels;
            Options.profileMesherStages=bProfileMesherStages&&!ForceGenerate;
            Options.diagnosticGlobalOctaveDrop=DiagnosticGlobalOctaveDrop;
@@ -993,6 +996,7 @@ private:
    bool bSkipUV=false;
    bool bSkipColors=false;
    bool bCaptureColumnCoordinates=false;
+    bool bSharedColumnCache=true;
    int32 Lod8HorizonInteriorStepVoxels=0;
    bool bProfileMesherStages=false;
    std::atomic<uint64> CacheHitCount{0};