Batch Windows DLSS GPU inputs and add deferred kernel diagnostics
This commit is contained in:
xdfnx-dev committed
1 parent
4f3b3a9fe6
commit
973eb5ecd2
15 files changed
+692
-37
No files matched your search
@@ -11,6 +11,7 @@ if (!$ZludaRoot) { $ZludaRoot=Join-Path $repo 'dist/zluda-windows-final' }
|
||||
if (!$PackageRoot) { $PackageRoot=Join-Path $repo 'dist/windows-rdna4-command-list' }
|
||||
if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo ('test-results/profile-' + $Preset + '-' + (Get-Date -Format 'yyyyMMdd-HHmmss-fff')) }
|
||||
$settings=@{D4R_ZLUDA_PROFILE='1'; D4R_PROFILE_STAGES='1'; D4R_VALIDATE_OUTPUT='1';
|
||||
D4R_ZLUDA_PROFILE_DEFERRED=$null; D4R_ZLUDA_PROFILE_ALLOW_LEGACY=$null; D4R_ZLUDA_PROFILE_EVERY=$null;
|
||||
D4R_ZLUDA_NATIVE_DIR=$(if ($Translated) { $null } elseif ($Preset -eq 11) { Join-Path $repo 'build/native-k-gfx1201' } else { Join-Path $repo 'build/native-m-gfx1201' })}
|
||||
$old=@{}
|
||||
try {
|
||||
|
||||
@@ -4,6 +4,9 @@ param(
|
||||
[string]$ZludaRoot, [string]$PackageRoot,
|
||||
[string]$Resolution = '3840x2160',
|
||||
[switch]$ProfileGpuBoundary,
|
||||
[switch]$ProfileKernelsDeferred,
|
||||
[switch]$BatchInputCopies,
|
||||
[ValidateSet('baseline','packed','unorm','depth-stencil')][string]$PixelProfile = 'depth-stencil',
|
||||
[string]$OutputDirectory
|
||||
)
|
||||
$ErrorActionPreference = 'Stop'
|
||||
@@ -18,8 +21,12 @@ if ($Resolution -notmatch '^([0-9]+)x([0-9]+)$') { throw 'Resolution must be WID
|
||||
$width=$Matches[1]; $height=$Matches[2]
|
||||
New-Item -ItemType Directory -Force $OutputDirectory | Out-Null
|
||||
$settings = @{D4R_DIAG_BURST='1'; D4R_DIAG_RECREATE=$null; D4R_ASYNC_INTEROP=$null;
|
||||
D4R_BATCH_INPUT_COPIES=$null;
|
||||
D4R_ZLUDA_NATIVE_DIR=$NativeRoot; D4R_QUIET_API='1'; D4R_VALIDATE_OUTPUT='1';
|
||||
D4R_PROFILE_STAGES='1'; D4R_ZLUDA_PROFILE=$null; D4R_ZLUDA_PROFILE_API=$null;
|
||||
D4R_ZLUDA_PROFILE_DEFERRED=$(if ($ProfileKernelsDeferred) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_ALLOW_LEGACY=$(if ($ProfileKernelsDeferred) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_EVERY=$(if ($ProfileKernelsDeferred) { '1' } else { $null });
|
||||
D4R_PROFILE_GPU_BOUNDARY=$(if ($ProfileGpuBoundary) { '1' } else { $null });
|
||||
ZLUDA_CACHE_DIR=(Join-Path $repo 'build/zluda-cache-windows');
|
||||
PYTHONPATH=(Join-Path $repo '.tools/python/vendor')}
|
||||
@@ -33,15 +40,25 @@ try {
|
||||
[Environment]::SetEnvironmentVariable('D4R_DIAG_RECREATE', $(if ($mode -eq 'recreate') { '1' } else { $null }), 'Process')
|
||||
foreach ($variant in @('sync','async')) {
|
||||
[Environment]::SetEnvironmentVariable('D4R_ASYNC_INTEROP', $(if ($variant -eq 'async') { '1' } else { $null }), 'Process')
|
||||
[Environment]::SetEnvironmentVariable('D4R_BATCH_INPUT_COPIES', $(if ($BatchInputCopies -and $variant -eq 'async') { '1' } else { $null }), 'Process')
|
||||
$output=Join-Path $OutputDirectory "$variant-$mode"
|
||||
$arguments=@{RuntimeProfile='therock'; ZludaRoot=$ZludaRoot; PackageRoot=$PackageRoot;
|
||||
NgxCore=$NgxCore; DlssDll=$DlssDll; NgxOnly=$true; NgxMode='d3d12'; NgxAbi='project-legacy';
|
||||
Preset=11; NgxCreateFlags=11; NgxOutputResolution=$Resolution; RequireNativeNetwork=$true;
|
||||
CommandListBackend=$true; EarlyIndirectProbe=$true; PixelProfile='depth-stencil';
|
||||
CommandListBackend=$true; EarlyIndirectProbe=$true; PixelProfile=$PixelProfile;
|
||||
BarrierMode='inherited-legacy'; Iterations=3; CaptureExceptions=$true; TimeoutSeconds=600;
|
||||
OptiScalerDll=(Join-Path $repo 'dist/optiscaler-windows-d4r/OptiScaler.dll'); OutputDirectory=$output}
|
||||
& (Join-Path $PSScriptRoot 'test-windows-rdna4.ps1') @arguments
|
||||
if ($LASTEXITCODE) { throw "Failed $variant-$mode; logs: $output" }
|
||||
if ($ProfileKernelsDeferred) {
|
||||
$stderr=Get-Content -LiteralPath (Join-Path $output 'd3d12-evaluate-preset-11.stderr.log') -Raw
|
||||
if ($stderr -match '(?m)^D4R_KERNEL_PROFILE .*serializing=1') { throw 'Unexpected serializing kernel profiler.' }
|
||||
foreach ($layer in @('enc0','enc1','enc2','enc3','enc4','dec5','dec4','dec3','dec2','dec1','dec0')) {
|
||||
$pattern='(?m)^D4R_KERNEL_PROFILE(?:_INVALID)? kernel="dltss_pwin_' + $layer + '_layer" backend=native phase=main '
|
||||
$events=[regex]::Matches($stderr,$pattern)
|
||||
if ($events.Count -ne 3) { throw "Expected three collected $layer events for $variant-$mode, found $($events.Count)." }
|
||||
}
|
||||
}
|
||||
if ($ProfileGpuBoundary -and $variant -eq 'async') {
|
||||
$stdout=Get-Content -LiteralPath (Join-Path $output 'd3d12-evaluate-preset-11.stdout.log') -Raw
|
||||
$timings=[regex]::Matches($stdout, '(?m)^D4R_GPU_BOUNDARY [^\r\n]*diagnostics_cpu_bytes=32 serializing=0\r?$')
|
||||
@@ -53,7 +70,8 @@ try {
|
||||
if ($LASTEXITCODE) { throw "Async $mode output mismatch" }
|
||||
}
|
||||
@{passed=$true; architecture='gfx1201'; preset=11; resolution=$Resolution;
|
||||
modes=@('burst','recreate'); framesPerMode=3; exactRgb=$true; gpuBoundaryTiming=[bool]$ProfileGpuBoundary} |
|
||||
modes=@('burst','recreate'); framesPerMode=3; exactRgb=$true; gpuBoundaryTiming=[bool]$ProfileGpuBoundary;
|
||||
deferredKernelTiming=[bool]$ProfileKernelsDeferred; batchInputs=[bool]$BatchInputCopies; pixelProfile=$PixelProfile} |
|
||||
ConvertTo-Json | Set-Content -LiteralPath (Join-Path $OutputDirectory 'validation.json') -Encoding UTF8
|
||||
Write-Host "PASS asynchronous K burst/recreate: $OutputDirectory"
|
||||
} finally {
|
||||
|
||||
@@ -0,0 +1,101 @@
|
||||
[CmdletBinding()]
|
||||
param([string]$ZludaRoot, [string]$PackageRoot, [string]$HipRoot, [string]$OutputDirectory)
|
||||
$ErrorActionPreference = 'Stop'
|
||||
$repo = [IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
|
||||
if (!$ZludaRoot) { $ZludaRoot = Join-Path $repo 'dist/zluda-windows-deferred-profile' }
|
||||
if (!$PackageRoot) { $PackageRoot = Join-Path $repo 'dist/windows-rdna4-command-list' }
|
||||
if (!$HipRoot) { $HipRoot = Join-Path $repo '.tools/therock-10.2.0a20260929/_rocm_sdk_core' }
|
||||
if (!$OutputDirectory) { $OutputDirectory = Join-Path $repo ('test-results/deferred-profile-' + (Get-Date -Format 'yyyyMMdd-HHmmss-fff')) }
|
||||
New-Item -ItemType Directory -Force $OutputDirectory | Out-Null
|
||||
$settings = @{
|
||||
D4R_ZLUDA_PROFILE=$null; D4R_ZLUDA_PROFILE_DEFERRED='1'; D4R_ZLUDA_PROFILE_EVERY='1';
|
||||
D4R_ZLUDA_PROFILE_ALLOW_LEGACY=$null;
|
||||
D4R_DIAG_NONBLOCKING_STREAM='1'; D4R_DIAG_QUEUE_PTX=$null;
|
||||
D4R_DIAG_DIR=$OutputDirectory;
|
||||
ZLUDA_CACHE_DIR=(Join-Path $repo 'build/zluda-cache-windows');
|
||||
PATH=((Join-Path $HipRoot 'bin') + ';' + $ZludaRoot + ';' + $env:PATH)
|
||||
}
|
||||
$old=@{}; $cases=@()
|
||||
function RunProbe([string[]]$Arguments, [string]$Stdout, [string]$Stderr) {
|
||||
$info=[Diagnostics.ProcessStartInfo]::new()
|
||||
$info.FileName=Join-Path $PackageRoot 'bin/d4r_cuda_driver_probe.exe'
|
||||
$info.Arguments=$Arguments -join ' '
|
||||
$info.UseShellExecute=$false; $info.CreateNoWindow=$true
|
||||
$info.RedirectStandardOutput=$true; $info.RedirectStandardError=$true
|
||||
$p=[Diagnostics.Process]::new(); $p.StartInfo=$info
|
||||
$outFile=$null; $errFile=$null; $outTask=$null; $errTask=$null
|
||||
try {
|
||||
if (!$p.Start()) { throw 'Could not launch the CUDA diagnostic.' }
|
||||
$outFile=[IO.File]::Open($Stdout,[IO.FileMode]::Create,[IO.FileAccess]::Write,[IO.FileShare]::Read)
|
||||
$errFile=[IO.File]::Open($Stderr,[IO.FileMode]::Create,[IO.FileAccess]::Write,[IO.FileShare]::Read)
|
||||
$outTask=$p.StandardOutput.BaseStream.CopyToAsync($outFile)
|
||||
$errTask=$p.StandardError.BaseStream.CopyToAsync($errFile)
|
||||
$timer=[Diagnostics.Stopwatch]::StartNew()
|
||||
while (!$p.WaitForExit(1000)) {
|
||||
if ($timer.Elapsed.TotalSeconds -ge 120) { throw "CUDA diagnostic timed out; logs: $OutputDirectory" }
|
||||
}
|
||||
$p.WaitForExit()
|
||||
[void]$outTask.GetAwaiter().GetResult(); [void]$errTask.GetAwaiter().GetResult()
|
||||
return $p.ExitCode
|
||||
} finally {
|
||||
if (!$p.HasExited) { $p.Kill(); $p.WaitForExit() }
|
||||
if ($outTask) { try { [void]$outTask.GetAwaiter().GetResult() } catch {} }
|
||||
if ($errTask) { try { [void]$errTask.GetAwaiter().GetResult() } catch {} }
|
||||
if ($outFile) { $outFile.Dispose() }; if ($errFile) { $errFile.Dispose() }
|
||||
$p.Dispose()
|
||||
}
|
||||
}
|
||||
try {
|
||||
foreach ($key in $settings.Keys) {
|
||||
$old[$key]=[Environment]::GetEnvironmentVariable($key,'Process')
|
||||
[Environment]::SetEnvironmentVariable($key,$settings[$key],'Process')
|
||||
}
|
||||
foreach ($context in @('primary','created')) {
|
||||
foreach ($queued in @($false,$true)) {
|
||||
$name="$context-$(if ($queued) { 'queued' } else { 'single' })"
|
||||
[Environment]::SetEnvironmentVariable('D4R_DIAG_QUEUE_PTX', $(if ($queued) { '1' } else { $null }), 'Process')
|
||||
$iterations=129
|
||||
$stdout=Join-Path $OutputDirectory "$name.stdout.log"
|
||||
$stderr=Join-Path $OutputDirectory "$name.stderr.log"
|
||||
# Native Windows argument parsing: quote absolute paths explicitly.
|
||||
$arguments=@('--hip-root', ('"' + $HipRoot + '"'), '--cuda-dll', ('"' + (Join-Path $ZludaRoot 'nvcuda.dll') + '"'),
|
||||
'--context', $context, '--iterations', "$iterations")
|
||||
$exitCode=RunProbe $arguments $stdout $stderr
|
||||
if ($exitCode) { throw "$name failed ($exitCode); logs: $OutputDirectory" }
|
||||
$out=Get-Content -LiteralPath $stdout -Raw
|
||||
$err=Get-Content -LiteralPath $stderr -Raw
|
||||
if ($out -notmatch 'PASS CUDA architecture=gfx1201' -or $out -notmatch 'guard_verified=1') { throw "$name did not verify PTX output" }
|
||||
$records=[regex]::Matches($err, '(?m)^D4R_KERNEL_PROFILE kernel="d4r_ptx_pattern" [^\r\n]*serializing=0 deferred=1 [^\r\n]+')
|
||||
$invalid=[regex]::Matches($err, '(?m)^D4R_KERNEL_PROFILE_INVALID kernel="d4r_ptx_pattern" [^\r\n]*reason=invalid_elapsed_time serializing=0 deferred=1 [^\r\n]+')
|
||||
if ($records.Count + $invalid.Count -ne $iterations -or $err -match 'serializing=1|D4R_KERNEL_PROFILE_SKIPPED') {
|
||||
throw "$name expected $iterations collected deferred records, found $($records.Count) valid / $($invalid.Count) invalid"
|
||||
}
|
||||
foreach ($record in $records) {
|
||||
if ($record.Value -notmatch 'gpu_ms=([0-9.]+)') {
|
||||
throw "$name contains an invalid GPU time"
|
||||
}
|
||||
$gpuMs=[double]::Parse($Matches[1], [Globalization.CultureInfo]::InvariantCulture)
|
||||
if ([double]::IsNaN($gpuMs) -or [double]::IsInfinity($gpuMs)) { throw "$name contains an invalid GPU time" }
|
||||
}
|
||||
$cases += @{context=$context; queued=$queued; launches=$iterations; collected=($records.Count+$invalid.Count);
|
||||
validTimings=$records.Count; invalidTimings=$invalid.Count; exitCode=$exitCode}
|
||||
Write-Host "PASS ${name}: $($records.Count) valid / $($invalid.Count) invalid deferred timings; exact PTX output and guards"
|
||||
}
|
||||
}
|
||||
# Legacy default-stream timing markers would add stream dependencies.
|
||||
[Environment]::SetEnvironmentVariable('D4R_DIAG_NONBLOCKING_STREAM',$null,'Process')
|
||||
[Environment]::SetEnvironmentVariable('D4R_DIAG_QUEUE_PTX',$null,'Process')
|
||||
$stdout=Join-Path $OutputDirectory 'default-stream.stdout.log'; $stderr=Join-Path $OutputDirectory 'default-stream.stderr.log'
|
||||
$arguments=@('--hip-root', ('"' + $HipRoot + '"'), '--cuda-dll', ('"' + (Join-Path $ZludaRoot 'nvcuda.dll') + '"'), '--iterations', '3')
|
||||
$exitCode=RunProbe $arguments $stdout $stderr
|
||||
$out=Get-Content -LiteralPath $stdout -Raw; $err=Get-Content -LiteralPath $stderr -Raw
|
||||
if ($exitCode -or $out -notmatch 'PASS CUDA architecture=gfx1201' -or
|
||||
$err -notmatch 'reason=legacy_default_stream' -or $err -match '(?m)^D4R_KERNEL_PROFILE ') {
|
||||
throw 'Default-stream diagnostics did not safely skip timing events.'
|
||||
}
|
||||
@{passed=$true; architecture='gfx1201'; cases=$cases; defaultStreamSkipped=$true; addedCompletionWaits=0} |
|
||||
ConvertTo-Json -Depth 5 | Set-Content -LiteralPath (Join-Path $OutputDirectory 'validation.json') -Encoding UTF8
|
||||
Write-Host "PASS deferred kernel profiling: $OutputDirectory"
|
||||
} finally {
|
||||
foreach ($key in $old.Keys) { [Environment]::SetEnvironmentVariable($key,$old[$key],'Process') }
|
||||
}
|
||||
@@ -11,11 +11,15 @@ param(
|
||||
[switch]$ValidateOutput,
|
||||
[switch]$ProfileStages,
|
||||
[switch]$ProfileKernels,
|
||||
[switch]$ProfileKernelsDeferred,
|
||||
[switch]$ProfileLegacyStream,
|
||||
[ValidateRange(1,1000000)][int]$KernelProfileEvery = 17,
|
||||
[switch]$ProfileCommandHooks,
|
||||
[switch]$ProfileCudaApi,
|
||||
[switch]$ProfileGpuBoundary,
|
||||
[switch]$UncachedInteropLists,
|
||||
[switch]$AsyncInterop,
|
||||
[switch]$BatchInputCopies,
|
||||
[switch]$VerboseRuntime,
|
||||
[switch]$CaptureExceptions,
|
||||
[string[]]$GameArguments = @('-dx12'),
|
||||
@@ -23,6 +27,8 @@ param(
|
||||
)
|
||||
$ErrorActionPreference = 'Stop'
|
||||
if ($ProfileGpuBoundary -and !$AsyncInterop) { throw '-ProfileGpuBoundary requires -AsyncInterop.' }
|
||||
if ($ProfileKernels -and $ProfileKernelsDeferred) { throw 'Choose either serializing or deferred kernel profiling.' }
|
||||
if ($ProfileLegacyStream -and !$ProfileKernelsDeferred) { throw '-ProfileLegacyStream requires -ProfileKernelsDeferred.' }
|
||||
$package = [IO.Path]::GetFullPath($PSScriptRoot)
|
||||
$GameExe = (Get-Item -LiteralPath $GameExe -ErrorAction Stop).FullName
|
||||
$game = Split-Path $GameExe
|
||||
@@ -182,11 +188,15 @@ $settings = @{
|
||||
D4R_VALIDATE_OUTPUT=$(if ($ValidateOutput) { '1' } else { $null });
|
||||
D4R_PROFILE_STAGES=$(if ($ProfileStages) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE=$(if ($ProfileKernels) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_DEFERRED=$(if ($ProfileKernelsDeferred) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_ALLOW_LEGACY=$(if ($ProfileLegacyStream) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_EVERY=$(if ($ProfileKernelsDeferred) { "$KernelProfileEvery" } else { $null });
|
||||
D4R_PROFILE_COMMAND_HOOKS=$(if ($ProfileCommandHooks) { '1' } else { $null });
|
||||
D4R_ZLUDA_PROFILE_API=$(if ($ProfileCudaApi) { '1' } else { $null });
|
||||
D4R_PROFILE_GPU_BOUNDARY=$(if ($ProfileGpuBoundary) { '1' } else { $null });
|
||||
D4R_DISABLE_INTEROP_LIST_CACHE=$(if ($UncachedInteropLists) { '1' } else { $null });
|
||||
D4R_ASYNC_INTEROP=$(if ($AsyncInterop) { '1' } else { $null });
|
||||
D4R_BATCH_INPUT_COPIES=$(if ($BatchInputCopies) { '1' } else { $null });
|
||||
D4R_DIAG_DIR=$OutputDirectory; ZLUDA_LOG_DIR=(Join-Path $OutputDirectory 'zluda-trace');
|
||||
ZLUDA_CACHE_DIR=$CacheDirectory; PATH=((GamePath 'd4r/hip/bin') + ';' + (GamePath 'd4r/zluda') + ';' + $env:PATH)
|
||||
}
|
||||
@@ -222,7 +232,12 @@ try {
|
||||
Write-Host "Temporary diagnostic resolution: $DiagnosticResolution; original settings restore at exit."
|
||||
}
|
||||
foreach ($key in $settings.Keys) { $old[$key] = [Environment]::GetEnvironmentVariable($key,'Process'); [Environment]::SetEnvironmentVariable($key,$settings[$key],'Process') }
|
||||
@{preset=$Preset; game=$GameExe; package=$metadata; attachedDebugger=[bool]$CaptureExceptions; driver=@(Get-CimInstance Win32_VideoController | Select-Object Name,DriverVersion,DriverDate); arguments=$GameArguments} |
|
||||
@{preset=$Preset; game=$GameExe; package=$metadata; attachedDebugger=[bool]$CaptureExceptions;
|
||||
diagnostics=@{asyncInterop=[bool]$AsyncInterop; batchInputCopies=[bool]$BatchInputCopies; validateOutput=[bool]$ValidateOutput;
|
||||
profileGpuBoundary=[bool]$ProfileGpuBoundary; profileStages=[bool]$ProfileStages; profileCudaApi=[bool]$ProfileCudaApi;
|
||||
profileKernels=[bool]$ProfileKernels; profileKernelsDeferred=[bool]$ProfileKernelsDeferred;
|
||||
profileLegacyStream=[bool]$ProfileLegacyStream; kernelProfileEvery=$KernelProfileEvery};
|
||||
driver=@(Get-CimInstance Win32_VideoController | Select-Object Name,DriverVersion,DriverDate); arguments=$GameArguments} |
|
||||
ConvertTo-Json -Depth 12 | Set-Content -LiteralPath (Join-Path $OutputDirectory 'environment.json') -Encoding UTF8
|
||||
function Quote([string]$value) { if ($value.Contains('"')) { throw 'A command argument contains an unsupported quote.' }; return '"' + $value + '"' }
|
||||
$arguments = @('--output-directory', (Quote $OutputDirectory))
|
||||
|
||||
Reference in new issue
Block a user