wip(standalone): GPU step 7 partial -- parity check deferred off cold path (stopped early)
Luna measured the startup density-parity check at 1,049 ms, nearly all of the ~1.13 s before shape compile; it now runs after first display and still passes 3,436/3,436. CPU hashes 44/44 at 1 and 8 workers, walkability 5,642/5,642, headless 8-worker clipmap 0.769 s. Stopped by the owner mid-round, while auditing the remote far holes; first-launch stall and hybrid speed untouched. 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
1 parent
b0a14262b1
commit
41716f00b8
6 files changed
+198
-24
No files matched your search
@@ -554,36 +554,46 @@ namespace
|
||||
|
||||
void CompileShaders(const std::filesystem::path& shaderPath)
|
||||
{
|
||||
const auto PipelineStart=std::chrono::steady_clock::now();
|
||||
const auto Load=[&](const char* entry)
|
||||
{
|
||||
const auto LoadStart=std::chrono::steady_clock::now();
|
||||
const std::filesystem::path binary=shaderPath.parent_path().parent_path()
|
||||
/"gpu_field_port"/"precompiled"/(std::string(entry)+".cso");
|
||||
ComPtr<ID3DBlob> code;
|
||||
if(std::filesystem::exists(binary)
|
||||
&&SUCCEEDED(D3DReadFileToBlob(binary.c_str(),&code)))return code;
|
||||
return CompileShader(shaderPath,entry);
|
||||
bool precompiled=std::filesystem::exists(binary)
|
||||
&&SUCCEEDED(D3DReadFileToBlob(binary.c_str(),&code));
|
||||
if(!precompiled)code=CompileShader(shaderPath,entry);
|
||||
std::printf("[GpuPipelineProfile] stage=bytecode_load entry=%s source=%s duration_ms=%.3f\n",
|
||||
entry,precompiled?"precompiled":"runtime_compile",
|
||||
std::chrono::duration<double,std::milli>(std::chrono::steady_clock::now()-LoadStart).count());
|
||||
return code;
|
||||
};
|
||||
ComPtr<ID3DBlob> code = Load("EvaluateFarFieldCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &fieldEval), "CreateComputeShader(EvaluateFarFieldCS)");
|
||||
code = Load("ClassifyCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &classify), "CreateComputeShader(ClassifyCS)");
|
||||
code = Load("ClassifyFarCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &fieldClassify), "CreateComputeShader(ClassifyFarCS)");
|
||||
code = Load("ScanGroupsCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &scan), "CreateComputeShader(ScanGroupsCS)");
|
||||
code = Load("EmitCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &emit), "CreateComputeShader(EmitCS)");
|
||||
code = Load("NoiseProbeCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &noiseProbe), "CreateComputeShader(NoiseProbeCS)");
|
||||
code = Load("BuildFarConnectorRingsCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &connectorRings), "CreateComputeShader(BuildFarConnectorRingsCS)");
|
||||
code = Load("EmitFarConnectorPanelsCS");
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(), code->GetBufferSize(), nullptr, &connectorPanels), "CreateComputeShader(EmitFarConnectorPanelsCS)");
|
||||
const auto Create=[&](const char* entry,ComPtr<ID3D11ComputeShader>& shader)
|
||||
{
|
||||
ComPtr<ID3DBlob> code=Load(entry);
|
||||
const auto CreateStart=std::chrono::steady_clock::now();
|
||||
const std::string operation="CreateComputeShader("+std::string(entry)+")";
|
||||
Check(device->CreateComputeShader(code->GetBufferPointer(),code->GetBufferSize(),nullptr,&shader),operation.c_str());
|
||||
std::printf("[GpuPipelineProfile] stage=shader_object_create entry=%s duration_ms=%.3f\n",
|
||||
entry,std::chrono::duration<double,std::milli>(std::chrono::steady_clock::now()-CreateStart).count());
|
||||
};
|
||||
Create("EvaluateFarFieldCS",fieldEval);
|
||||
Create("ClassifyCS",classify);
|
||||
Create("ClassifyFarCS",fieldClassify);
|
||||
Create("ScanGroupsCS",scan);
|
||||
Create("EmitCS",emit);
|
||||
Create("NoiseProbeCS",noiseProbe);
|
||||
Create("BuildFarConnectorRingsCS",connectorRings);
|
||||
Create("EmitFarConnectorPanelsCS",connectorPanels);
|
||||
std::printf("[GpuPipelineProfile] stage=shader_pipeline_total duration_ms=%.3f\n",
|
||||
std::chrono::duration<double,std::milli>(std::chrono::steady_clock::now()-PipelineStart).count());
|
||||
}
|
||||
|
||||
void InitializeExternal(ID3D11Device* inDevice, ID3D11DeviceContext* inContext,
|
||||
const std::filesystem::path& shaderPath)
|
||||
{
|
||||
const auto InitializeStart=std::chrono::steady_clock::now();
|
||||
device = inDevice;
|
||||
immediateContext = inContext;
|
||||
context = immediateContext;
|
||||
@@ -595,6 +605,8 @@ namespace
|
||||
if(SUCCEEDED(device.As(&dxgiDevice))&&SUCCEEDED(dxgiDevice->GetAdapter(&adapter)))
|
||||
adapter.As(&memoryAdapter);
|
||||
CompileShaders(shaderPath);
|
||||
std::printf("[GpuPipelineProfile] stage=external_device_init device=%s duration_ms=%.3f\n",
|
||||
name.c_str(),std::chrono::duration<double,std::milli>(std::chrono::steady_clock::now()-InitializeStart).count());
|
||||
}
|
||||
|
||||
void BeginFarTileBatch()
|
||||
@@ -639,6 +651,7 @@ namespace
|
||||
|
||||
void Initialize(const std::filesystem::path& shaderPath, bool warp)
|
||||
{
|
||||
const auto InitializeStart=std::chrono::steady_clock::now();
|
||||
D3D_FEATURE_LEVEL requested[] = {D3D_FEATURE_LEVEL_11_1, D3D_FEATURE_LEVEL_11_0};
|
||||
D3D_FEATURE_LEVEL created{};
|
||||
HRESULT hr = D3D11CreateDevice(nullptr,
|
||||
@@ -664,6 +677,8 @@ namespace
|
||||
adapter.As(&memoryAdapter);
|
||||
}
|
||||
CompileShaders(shaderPath);
|
||||
std::printf("[GpuPipelineProfile] stage=audit_device_init device=%s duration_ms=%.3f\n",
|
||||
name.c_str(),std::chrono::duration<double,std::milli>(std::chrono::steady_clock::now()-InitializeStart).count());
|
||||
}
|
||||
|
||||
bool QueryLocalMemory(std::uint64_t& usage, std::uint64_t& budget) const
|
||||
|
||||
@@ -0,0 +1,58 @@
|
||||
[CmdletBinding()]
|
||||
param([string]$ExecutableName='VoxelForgeGpuFieldStep7NearTimeline.exe')
|
||||
|
||||
$ErrorActionPreference='Stop'
|
||||
$HostProcess=Get-Process -Id $PID
|
||||
$HostProcess.PriorityClass='BelowNormal'
|
||||
$HostProcess.ProcessorAffinity=[IntPtr]0xFF00
|
||||
$StandaloneRoot=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '..\..\..'))
|
||||
$ExecutablePath=Join-Path $StandaloneRoot ('bin\'+$ExecutableName)
|
||||
if([IO.Path]::GetFileName($ExecutableName)-ne$ExecutableName-or[IO.Path]::GetExtension($ExecutableName)-ne'.exe')
|
||||
{throw 'ExecutableName must be an executable filename.'}
|
||||
if(-not(Test-Path -LiteralPath $ExecutablePath -PathType Leaf)){throw "Viewer not found: $ExecutablePath"}
|
||||
$Sequence=@(
|
||||
@{Mode='cpu';Name='step7_interleaved_cpu_A'},
|
||||
@{Mode='gpu';Name='step7_interleaved_gpu_A'},
|
||||
@{Mode='gpu';Name='step7_interleaved_gpu_B'},
|
||||
@{Mode='cpu';Name='step7_interleaved_cpu_B'},
|
||||
@{Mode='cpu';Name='step7_interleaved_cpu_C'},
|
||||
@{Mode='gpu';Name='step7_interleaved_gpu_C'}
|
||||
)
|
||||
foreach($Run in $Sequence)
|
||||
{
|
||||
$Arguments=@('--clip-radius=3','--workers=8','--quit-after-clipmap',"--$($Run.Mode)-far")
|
||||
$StdoutPath=Join-Path $PSScriptRoot ($Run.Name+'.stdout.log')
|
||||
$StderrPath=Join-Path $PSScriptRoot ($Run.Name+'.stderr.log')
|
||||
Write-Output "COLD_RUN mode=$($Run.Mode) command=`"$ExecutablePath`" $($Arguments -join ' ')"
|
||||
for($Attempt=0;$Attempt-lt2;$Attempt++)
|
||||
{
|
||||
if($Attempt-gt0)
|
||||
{Write-Host '0xC0000142 encountered; waiting 60 seconds before the single permitted retry.';Start-Sleep -Seconds 60}
|
||||
Remove-Item -LiteralPath $StdoutPath,$StderrPath -Force -ErrorAction SilentlyContinue
|
||||
$Child=Start-Process -FilePath $ExecutablePath -ArgumentList $Arguments -WorkingDirectory $StandaloneRoot `
|
||||
-WindowStyle Hidden -PassThru -RedirectStandardOutput $StdoutPath -RedirectStandardError $StderrPath
|
||||
$PeakWorkingSet=0L;$PeakPrivateMemory=0L;$OverMemoryLimit=$false
|
||||
while(-not$Child.HasExited)
|
||||
{
|
||||
$Child.Refresh();if($Child.HasExited){break}
|
||||
$Child.PriorityClass='BelowNormal';$Child.ProcessorAffinity=[IntPtr]0xFF00
|
||||
$PeakWorkingSet=[Math]::Max($PeakWorkingSet,$Child.WorkingSet64)
|
||||
$PeakPrivateMemory=[Math]::Max($PeakPrivateMemory,$Child.PrivateMemorySize64)
|
||||
if($Child.PrivateMemorySize64-ge8GB)
|
||||
{$OverMemoryLimit=$true;$Child.Kill();$Child.WaitForExit();break}
|
||||
Start-Sleep -Milliseconds 100
|
||||
}
|
||||
$Child.WaitForExit();$Child.Refresh()
|
||||
$ExitCode=0
|
||||
if($null-ne$Child.ExitCode){$ExitCode=[int]$Child.ExitCode}
|
||||
if($ExitCode-eq-1073741502-and$Attempt-eq0){continue}
|
||||
if($ExitCode-eq-1073741502){throw '0xC0000142 repeated after its single retry; stopping.'}
|
||||
if($OverMemoryLimit){throw "Viewer stopped at the private-memory limit: $($Run.Name)"}
|
||||
$LogText=Get-Content -LiteralPath $StdoutPath -Raw
|
||||
if(-not$LogText.Contains('[InitialClipmapReady]'))
|
||||
{throw "Clipmap was not ready in $($Run.Name); exit=$ExitCode"}
|
||||
Write-Output "RUN_EXIT mode=$($Run.Mode) log=$($Run.Name) pid=$($Child.Id) priority=BelowNormal affinity=0xFF00 peak_working_set_gb=$([math]::Round($PeakWorkingSet/1GB,2)) peak_private_gb=$([math]::Round($PeakPrivateMemory/1GB,2)) exit=$ExitCode"
|
||||
if($ExitCode-ne0){throw "Cold run returned $ExitCode`: $($Run.Name)"}
|
||||
break
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,51 @@
|
||||
[CmdletBinding()]
|
||||
param(
|
||||
[Parameter(Mandatory=$true)][string]$ExecutableName,
|
||||
[Parameter(Mandatory=$true)][string]$LogStem,
|
||||
[string[]]$Arguments=@(),
|
||||
[string]$RequiredText=''
|
||||
)
|
||||
|
||||
$ErrorActionPreference='Stop'
|
||||
$HostProcess=Get-Process -Id $PID
|
||||
$HostProcess.PriorityClass='BelowNormal'
|
||||
$HostProcess.ProcessorAffinity=[IntPtr]0xFF00
|
||||
$StandaloneRoot=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '..\..\..'))
|
||||
$ExecutablePath=Join-Path $StandaloneRoot ('bin\'+$ExecutableName)
|
||||
if([IO.Path]::GetFileName($ExecutableName)-ne$ExecutableName-or[IO.Path]::GetExtension($ExecutableName)-ne'.exe')
|
||||
{throw 'ExecutableName must be an executable filename.'}
|
||||
if(-not(Test-Path -LiteralPath $ExecutablePath -PathType Leaf)){throw "Executable not found: $ExecutablePath"}
|
||||
$StdoutPath=Join-Path $PSScriptRoot ($LogStem+'.stdout.log')
|
||||
$StderrPath=Join-Path $PSScriptRoot ($LogStem+'.stderr.log')
|
||||
Write-Output "STEP7_COMMAND `"$ExecutablePath`" $($Arguments -join ' ')"
|
||||
for($Attempt=0;$Attempt-lt2;$Attempt++)
|
||||
{
|
||||
if($Attempt-gt0)
|
||||
{Write-Output '0xC0000142 encountered; waiting 60 seconds before the single permitted retry.';Start-Sleep -Seconds 60}
|
||||
Remove-Item -LiteralPath $StdoutPath,$StderrPath -Force -ErrorAction SilentlyContinue
|
||||
$Child=Start-Process -FilePath $ExecutablePath -ArgumentList $Arguments -WorkingDirectory $StandaloneRoot `
|
||||
-WindowStyle Hidden -PassThru -RedirectStandardOutput $StdoutPath -RedirectStandardError $StderrPath
|
||||
$PeakWorkingSet=0L;$PeakPrivateMemory=0L;$OverMemoryLimit=$false
|
||||
while(-not$Child.HasExited)
|
||||
{
|
||||
$Child.Refresh();if($Child.HasExited){break}
|
||||
$Child.PriorityClass='BelowNormal';$Child.ProcessorAffinity=[IntPtr]0xFF00
|
||||
$PeakWorkingSet=[Math]::Max($PeakWorkingSet,$Child.WorkingSet64)
|
||||
$PeakPrivateMemory=[Math]::Max($PeakPrivateMemory,$Child.PrivateMemorySize64)
|
||||
if($Child.PrivateMemorySize64-ge8GB)
|
||||
{$OverMemoryLimit=$true;$Child.Kill();$Child.WaitForExit();break}
|
||||
Start-Sleep -Milliseconds 100
|
||||
}
|
||||
$Child.WaitForExit();$Child.Refresh()
|
||||
$ExitCode=0
|
||||
if($null-ne$Child.ExitCode){$ExitCode=[int]$Child.ExitCode}
|
||||
if($ExitCode-eq-1073741502-and$Attempt-eq0){continue}
|
||||
if($ExitCode-eq-1073741502){throw '0xC0000142 repeated after its single retry; stopping.'}
|
||||
if($OverMemoryLimit){throw "Process stopped at the 8 GiB private-memory limit: $LogStem"}
|
||||
$LogText=Get-Content -LiteralPath $StdoutPath -Raw
|
||||
if($RequiredText-and-not$LogText.Contains($RequiredText))
|
||||
{throw "Required output '$RequiredText' missing from $LogStem; exit=$($Child.ExitCode)"}
|
||||
Write-Output "STEP7_EXIT log=$LogStem pid=$($Child.Id) priority=BelowNormal affinity=0xFF00 peak_working_set_gb=$([math]::Round($PeakWorkingSet/1GB,2)) peak_private_gb=$([math]::Round($PeakPrivateMemory/1GB,2)) exit=$ExitCode stdout=$StdoutPath stderr=$StderrPath"
|
||||
if($ExitCode-ne0){throw "Process returned $ExitCode`: $LogStem"}
|
||||
break
|
||||
}
|
||||
Reference in new issue
Block a user