Fr0zka/VoxelForge
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

standalone: speed round closed -- full-payload whole view 2.16 s @8 workers; UV/colour/groups cost 0.62 s

Browse Source 
Takeover after the PC reset. Verified at 1 and 8 workers: density, geometry, full payload and
topology hashes equal for all nine outputs; routes 5642/5642; crater transaction 17 ms; player
neighbourhood mesh-ready 23 ms after streaming starts.
- The plugin's materials consume UV, the packed biome/slope/blend colours and the ceiling/ground
  sections, so the viewer-only skips stay off by default (diagnostic only: 1.53 s without them).
- UVs staged as FVector2f (matches the game stream; -20 MB, no speed change). Far-bin reserve 24x.
- LOD6 is the long pole: 32.7 M density samples, 1.83 M vertices, ~1.1 s.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MmSoF64BbRFmk9C3p1VsBJ
This commit is contained in:
Fr0zkaandClaude Opus 5.5 committed 2026-10-04 13:27:03 +02:00
1 parent ee5b05b357
commit 6ec4a8f856
10 files changed
+417 -166
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

Standalone/Source/StandaloneViewer.cpp
+51 -13
View File
@@ -1704,7 +1704,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
int RunStreamingBenchmark(FStandaloneOwnerWorld& World,const FVector& CameraPositionVoxels,
int32 WorkerCount,int32 MaxLevel,bool bRoundTunnels,
bool bEnhancedWalls,const FStandaloneMeshCache* Cache,
bool bHashDensity,bool bShardAudit,float CameraYaw,float CameraPitch,
bool bHashDensity,bool bSkipUvAndColors,bool bSkipMaterialGroups,
bool bShardAudit,float CameraYaw,float CameraPitch,
const std::string& BakeCachePath,
const FStandaloneMeshCacheMetadata& CacheMetadata)
{
@@ -1723,6 +1724,8 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
{return Tile.Level<World.FullResClipLevels;}));
std::array<std::vector<FHashedTile>,MaxLevels+1> HashRows;
std::array<std::vector<FHashedTile>,MaxLevels+1> MeshHashRows;
std::array<std::vector<FHashedTile>,MaxLevels+1> PayloadHashRows;
std::array<std::vector<FHashedTile>,MaxLevels+1> TopologyHashRows;
std::array<uint64,MaxLevels+1> SamplesByLevel{};
std::array<uint64,MaxLevels+1> VerticesByLevel{};
std::array<uint64,MaxLevels+1> IndicesByLevel{};
@@ -1731,6 +1734,7 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
std::array<double,MaxLevels+1> FirstCompletionByLevel{};
std::array<double,MaxLevels+1> LastCompletionByLevel{};
std::array<uint64,MaxLevels+1> OutputBytesByLevel{};
std::array<uint64,MaxLevels+1> MeshPayloadAllocatedBytesByLevel{};
FirstCompletionByLevel.fill(std::numeric_limits<double>::infinity());
std::unordered_set<FVoxelTileKey,FStandaloneTileKeyHash> PlayerNeighborhoodTiles;
for(const FVoxelTileKey& Tile:Desired.Tiles)
@@ -1744,14 +1748,16 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
if(!BakeCachePath.empty())CacheTiles.reserve(Desired.Tiles.size());
const auto Start=std::chrono::steady_clock::now();
FStandaloneStreamingGenerator Streamer(World,WorkerCount,
bHashDensity||!BakeCachePath.empty(),Cache,MaxLevel);
bHashDensity||!BakeCachePath.empty(),Cache,MaxLevel,
bSkipUvAndColors,bSkipMaterialGroups);
const FStandaloneStreamingUpdate Update=Streamer.Start(CameraPositionVoxels);
const double LOD0Width=static_cast<double>(2*World.ClipRadius+2)
*CHUNK_SIZE*VOXEL_SIZE/100.0;
std::printf("[StreamBenchmarkConfig] clip_radius=%d lod0_cube=%.0fm voxel=25cm fullres_levels=%d max_level_filter=%d workers=%d full_detail_tiles=%d desired_tiles=%d variant=%s hash=%s\n",
std::printf("[StreamBenchmarkConfig] clip_radius=%d lod0_cube=%.0fm voxel=25cm fullres_levels=%d max_level_filter=%d workers=%d full_detail_tiles=%d desired_tiles=%d variant=%s uv_colors=%s material_groups=%s hash=%s\n",
World.ClipRadius,LOD0Width,World.FullResClipLevels,MaxLevel<0?World.MaxClipLevel:MaxLevel,
Streamer.GetWorkerCount(),FullDetailExpected,Update.DesiredTiles,
bRoundTunnels?(bEnhancedWalls?"round-detailed":"round-legacy"):"base",
bSkipUvAndColors?"skipped":"full",bSkipMaterialGroups?"skipped":"full",
(bHashDensity||!BakeCachePath.empty())?"on":"off");
std::fflush(stdout);
int32 Finished=0,FullDetailFinished=0;
@@ -1790,8 +1796,11 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
LastCompletionByLevel[Level]=std::max(LastCompletionByLevel[Level],CompletedSeconds);
OutputBytesByLevel[Level]+=static_cast<uint64>(Tile.Vertices.capacity())*sizeof(FStandaloneCpuVertex)
+static_cast<uint64>(Tile.Indices.capacity())*sizeof(uint32);
MeshPayloadAllocatedBytesByLevel[Level]+=Tile.MeshPayloadAllocatedBytes;
if(Tile.bHasDensityHash)HashRows[Level].push_back({Tile.Key,Tile.DensityHash});
if(Tile.bHasMeshHash)MeshHashRows[Level].push_back({Tile.Key,Tile.MeshHash});
if(Tile.bHasPayloadHash)PayloadHashRows[Level].push_back({Tile.Key,Tile.PayloadHash});
if(Tile.bHasTopologyHash)TopologyHashRows[Level].push_back({Tile.Key,Tile.TopologyHash});
}
if(Level<World.FullResClipLevels)++FullDetailFinished;
if(bShardAudit&&Level==0)
@@ -1820,16 +1829,22 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
std::chrono::steady_clock::now()-Start).count();
std::vector<FHashedTile> FullRows;
std::vector<FHashedTile> FullMeshRows;
std::vector<FHashedTile> FullPayloadRows;
std::vector<FHashedTile> FullTopologyRows;
for(int32 Level=0;Level<World.FullResClipLevels&&Level<=MaxLevels;++Level)
{
FullRows.insert(FullRows.end(),HashRows[Level].begin(),HashRows[Level].end());
FullMeshRows.insert(FullMeshRows.end(),MeshHashRows[Level].begin(),MeshHashRows[Level].end());
FullPayloadRows.insert(FullPayloadRows.end(),PayloadHashRows[Level].begin(),PayloadHashRows[Level].end());
FullTopologyRows.insert(FullTopologyRows.end(),TopologyHashRows[Level].begin(),TopologyHashRows[Level].end());
}
if(bHashDensity||!BakeCachePath.empty())
std::printf("[StreamFullDetail] wall=%.3fs generated=%d/%d resident_tiles_cpu_only=1 density_hash=0x%016llx mesh_hash=0x%016llx\n",
std::printf("[StreamFullDetail] wall=%.3fs generated=%d/%d resident_tiles_cpu_only=1 density_hash=0x%016llx mesh_hash=0x%016llx payload_hash=0x%016llx topology_hash=0x%016llx\n",
FullDetailSeconds,FullDetailFinished,FullDetailExpected,
static_cast<unsigned long long>(HashTileRows(FullRows)),
static_cast<unsigned long long>(HashTileRows(FullMeshRows)));
static_cast<unsigned long long>(HashTileRows(FullMeshRows)),
static_cast<unsigned long long>(HashTileRows(FullPayloadRows)),
static_cast<unsigned long long>(HashTileRows(FullTopologyRows)));
else
std::printf("[StreamFullDetail] wall=%.3fs generated=%d/%d resident_tiles_cpu_only=1 hash=off\n",
FullDetailSeconds,FullDetailFinished,FullDetailExpected);
@@ -1846,26 +1861,40 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
std::printf("[PlayerNeighborhood] lod0_tiles=%zu/%zu mesh_ready=missing collision_cook=unavailable_in_standalone\n",
PlayerNeighborhoodReady.size(),PlayerNeighborhoodTiles.size());
const double TotalWorkerSeconds=std::accumulate(WorkerSecondsByLevel.begin(),WorkerSecondsByLevel.end(),0.0);
const uint64 TotalMeshPayloadAllocatedBytes=std::accumulate(
MeshPayloadAllocatedBytesByLevel.begin(),MeshPayloadAllocatedBytesByLevel.end(),uint64{0});
const uint64 TotalViewerOutputBytes=std::accumulate(
OutputBytesByLevel.begin(),OutputBytesByLevel.end(),uint64{0});
const double WorkerBusyPercent=100.0*TotalWorkerSeconds
/(std::max(1,WorkerCount)*std::max(0.001,FullClipSeconds));
std::vector<FHashedTile> AllRows;
std::vector<FHashedTile> AllMeshRows;
std::vector<FHashedTile> AllPayloadRows;
std::vector<FHashedTile> AllTopologyRows;
if(bHashDensity||!BakeCachePath.empty())
for(int32 Level=0;Level<=MaxLevels;++Level)
{
AllRows.insert(AllRows.end(),HashRows[Level].begin(),HashRows[Level].end());
AllMeshRows.insert(AllMeshRows.end(),MeshHashRows[Level].begin(),MeshHashRows[Level].end());
AllPayloadRows.insert(AllPayloadRows.end(),PayloadHashRows[Level].begin(),PayloadHashRows[Level].end());
AllTopologyRows.insert(AllTopologyRows.end(),TopologyHashRows[Level].begin(),TopologyHashRows[Level].end());
}
if(bHashDensity||!BakeCachePath.empty())
std::printf("[StreamFullClipmap] wall=%.3fs generated=%d/%d worker_sum=%.3fs worker_busy=%.1f%% worker_idle=%.1f%% tiles=%d density_hash=0x%016llx mesh_hash=0x%016llx\n",
std::printf("[StreamFullClipmap] wall=%.3fs generated=%d/%d worker_sum=%.3fs worker_busy=%.1f%% worker_idle=%.1f%% payload_alloc=%.2fMiB viewer_output=%.2fMiB tiles=%d density_hash=0x%016llx mesh_hash=0x%016llx payload_hash=0x%016llx topology_hash=0x%016llx\n",
FullClipSeconds,Finished,DesiredTotal,TotalWorkerSeconds,WorkerBusyPercent,
std::max(0.0,100.0-WorkerBusyPercent),
static_cast<double>(TotalMeshPayloadAllocatedBytes)/1048576.0,
static_cast<double>(TotalViewerOutputBytes)/1048576.0,
DesiredTotal,static_cast<unsigned long long>(HashTileRows(AllRows)),
static_cast<unsigned long long>(HashTileRows(AllMeshRows)));
static_cast<unsigned long long>(HashTileRows(AllMeshRows)),
static_cast<unsigned long long>(HashTileRows(AllPayloadRows)),
static_cast<unsigned long long>(HashTileRows(AllTopologyRows)));
else
std::printf("[StreamFullClipmap] wall=%.3fs generated=%d/%d worker_sum=%.3fs worker_busy=%.1f%% worker_idle=%.1f%% tiles=%d hash=off\n",
std::printf("[StreamFullClipmap] wall=%.3fs generated=%d/%d worker_sum=%.3fs worker_busy=%.1f%% worker_idle=%.1f%% payload_alloc=%.2fMiB viewer_output=%.2fMiB tiles=%d hash=off\n",
FullClipSeconds,Finished,DesiredTotal,TotalWorkerSeconds,WorkerBusyPercent,
std::max(0.0,100.0-WorkerBusyPercent),DesiredTotal);
std::max(0.0,100.0-WorkerBusyPercent),
static_cast<double>(TotalMeshPayloadAllocatedBytes)/1048576.0,
static_cast<double>(TotalViewerOutputBytes)/1048576.0,DesiredTotal);
std::printf("[StreamCacheUse] hits=%llu requested=%d\n",
static_cast<unsigned long long>(Streamer.GetCacheHits()),DesiredTotal);
if(bShardAudit)
@@ -1882,22 +1911,26 @@ float3 Lit=Rock*(Ambient+0.88*Diffuse)+float3(0.50,0.69,0.82)*Head*0.75;
{
if(TilesByLevel[Level]==0)continue;
if(bHashDensity||!BakeCachePath.empty())
std::printf("[StreamLevel] lod=%d tiles=%llu samples=%.3fM worker_sum=%.3fs first_ready=%.3fs complete=%.3fs worker_busy=%.1f%% output=%.2fMiB vertices=%llu indices=%llu density_hash=0x%016llx mesh_hash=0x%016llx\n",
std::printf("[StreamLevel] lod=%d tiles=%llu samples=%.3fM worker_sum=%.3fs first_ready=%.3fs complete=%.3fs worker_busy=%.1f%% payload_alloc=%.2fMiB viewer_output=%.2fMiB vertices=%llu indices=%llu density_hash=0x%016llx mesh_hash=0x%016llx payload_hash=0x%016llx topology_hash=0x%016llx\n",
Level,static_cast<unsigned long long>(TilesByLevel[Level]),
static_cast<double>(SamplesByLevel[Level])/1.0e6,WorkerSecondsByLevel[Level],
FirstCompletionByLevel[Level],LastCompletionByLevel[Level],
100.0*WorkerSecondsByLevel[Level]/(WorkerCount*std::max(0.001,LastCompletionByLevel[Level])),
static_cast<double>(MeshPayloadAllocatedBytesByLevel[Level])/1048576.0,
static_cast<double>(OutputBytesByLevel[Level])/1048576.0,
static_cast<unsigned long long>(VerticesByLevel[Level]),
static_cast<unsigned long long>(IndicesByLevel[Level]),
static_cast<unsigned long long>(HashTileRows(HashRows[Level])),
static_cast<unsigned long long>(HashTileRows(MeshHashRows[Level])));
static_cast<unsigned long long>(HashTileRows(MeshHashRows[Level])),
static_cast<unsigned long long>(HashTileRows(PayloadHashRows[Level])),
static_cast<unsigned long long>(HashTileRows(TopologyHashRows[Level])));
else
std::printf("[StreamLevel] lod=%d tiles=%llu samples=%.3fM worker_sum=%.3fs first_ready=%.3fs complete=%.3fs worker_busy=%.1f%% output=%.2fMiB vertices=%llu indices=%llu hash=off\n",
std::printf("[StreamLevel] lod=%d tiles=%llu samples=%.3fM worker_sum=%.3fs first_ready=%.3fs complete=%.3fs worker_busy=%.1f%% payload_alloc=%.2fMiB viewer_output=%.2fMiB vertices=%llu indices=%llu hash=off\n",
Level,static_cast<unsigned long long>(TilesByLevel[Level]),
static_cast<double>(SamplesByLevel[Level])/1.0e6,WorkerSecondsByLevel[Level],
FirstCompletionByLevel[Level],LastCompletionByLevel[Level],
100.0*WorkerSecondsByLevel[Level]/(WorkerCount*std::max(0.001,LastCompletionByLevel[Level])),
static_cast<double>(MeshPayloadAllocatedBytesByLevel[Level])/1048576.0,
static_cast<double>(OutputBytesByLevel[Level])/1048576.0,
static_cast<unsigned long long>(VerticesByLevel[Level]),
static_cast<unsigned long long>(IndicesByLevel[Level]));
@@ -2004,6 +2037,8 @@ int main(int Argc,char** Argv)
bool bStreamBenchmark=false;
bool bShardAudit=false;
bool bStreamHash=false;
bool bSkipUvAndColors=false;
bool bSkipMaterialGroups=false;
bool bEditBenchmark=false;
bool bRoundWallCompare=false;
int32 RoundCompareTileCount=16;
@@ -2037,6 +2072,8 @@ int main(int Argc,char** Argv)
else if(Arg=="--edit-benchmark")
{bEditBenchmark=true;bStreamBenchmark=true;App.bShapeWorld=true;}
else if(Arg=="--stream-hash")bStreamHash=true;
else if(Arg=="--skip-uv-colors")bSkipUvAndColors=true;
else if(Arg=="--skip-material-groups")bSkipMaterialGroups=true;
else if(Arg=="--shard-audit")bShardAudit=true;
else if(Arg=="--compare-round-walls")
{bRoundWallCompare=true;App.bRoundTunnels=true;}
@@ -2125,7 +2162,8 @@ int main(int Argc,char** Argv)
FVector(App.Position.X*4.0,App.Position.Y*4.0,App.Position.Z*4.0),
App.WorkerCount,StreamBenchmarkMaxLevel,App.bRoundTunnels,
App.bRoundTunnelEnhanced,(!App.bShapeWorld&&App.MeshCache.IsLoaded())?&App.MeshCache:nullptr,
bStreamHash,bShardAudit,App.Yaw,App.Pitch,BakeMeshCachePath,App.MakeMeshCacheMetadata());
bStreamHash,bSkipUvAndColors,bSkipMaterialGroups,bShardAudit,
App.Yaw,App.Pitch,BakeMeshCachePath,App.MakeMeshCacheMetadata());
}
if(BenchmarkLevel>=0)
return RunTileBenchmark(*App.World,App.Position,BenchmarkLevel,BenchmarkCount,