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

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

Browse Source 
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
This commit is contained in:
Fr0zkaandClaude Opus 5.5 committed 2026-10-19 21:46:15 +02:00
1 parent 9898e057fd
commit 4b1108bf86
12 files changed
+751 -92
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

Standalone/Source/StreamBenchmarkHeadless.cpp
+36 -2
View File
@@ -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);
}