Queue native Windows DLSS asynchronously and drain feature consumers

scripts/windows/test-async-k.ps1

@@ -0,0 +1,54 @@
+[CmdletBinding()]
+param(
+    [string]$NgxCore, [string]$DlssDll, [string]$NativeRoot,
+    [string]$ZludaRoot, [string]$PackageRoot,
+    [string]$Resolution = '3840x2160',
+    [string]$OutputDirectory
+)
+$ErrorActionPreference = 'Stop'
+$repo = [IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
+if (!$NgxCore) { $NgxCore = Join-Path $repo '_nvngx.dll' }
+if (!$DlssDll) { $DlssDll = Join-Path $repo 'nvngx_dlss.dll' }
+if (!$NativeRoot) { $NativeRoot = Join-Path $repo 'build/native-k-gfx1201' }
+if (!$ZludaRoot) { $ZludaRoot = Join-Path $repo 'dist/zluda-windows-api-profile' }
+if (!$PackageRoot) { $PackageRoot = Join-Path $repo 'dist/windows-rdna4-command-list' }
+if (!$OutputDirectory) { $OutputDirectory = Join-Path $repo ('test-results/async-k-' + (Get-Date -Format 'yyyyMMdd-HHmmss-fff')) }
+if ($Resolution -notmatch '^([0-9]+)x([0-9]+)$') { throw 'Resolution must be WIDTHxHEIGHT' }
+$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_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;
+    ZLUDA_CACHE_DIR=(Join-Path $repo 'build/zluda-cache-windows');
+    PYTHONPATH=(Join-Path $repo '.tools/python/vendor')}
+$old=@{}
+try {
+    foreach ($key in $settings.Keys) {
+        $old[$key]=[Environment]::GetEnvironmentVariable($key,'Process')
+        [Environment]::SetEnvironmentVariable($key,$settings[$key],'Process')
+    }
+    foreach ($mode in @('burst','recreate')) {
+        [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')
+            $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';
+                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" }
+        }
+        & python.exe (Join-Path $repo 'tools/windows/frame_compare.py') --reference (Join-Path $OutputDirectory "sync-$mode") --actual (Join-Path $OutputDirectory "async-$mode") --width $width --height $height --exact |
+            Tee-Object -FilePath (Join-Path $OutputDirectory "$mode-comparison.log")
+        if ($LASTEXITCODE) { throw "Async $mode output mismatch" }
+    }
+    @{passed=$true; architecture='gfx1201'; preset=11; resolution=$Resolution;
+        modes=@('burst','recreate'); framesPerMode=3; exactRgb=$true} |
+        ConvertTo-Json | Set-Content -LiteralPath (Join-Path $OutputDirectory 'validation.json') -Encoding UTF8
+    Write-Host "PASS asynchronous K burst/recreate: $OutputDirectory"
+} finally {
+    foreach ($key in $old.Keys) { [Environment]::SetEnvironmentVariable($key,$old[$key],'Process') }
+}

scripts/windows/windows-game.ps1

@@ -12,6 +12,9 @@ param(
     [switch]$ProfileStages,
     [switch]$ProfileKernels,
     [switch]$ProfileCommandHooks,
+    [switch]$ProfileCudaApi,
+    [switch]$UncachedInteropLists,
+    [switch]$AsyncInterop,
     [switch]$VerboseRuntime,
     [switch]$CaptureExceptions,
     [string[]]$GameArguments = @('-dx12'),
@@ -178,6 +181,9 @@ $settings = @{
     D4R_PROFILE_STAGES=$(if ($ProfileStages) { '1' } else { $null });
     D4R_ZLUDA_PROFILE=$(if ($ProfileKernels) { '1' } else { $null });
     D4R_PROFILE_COMMAND_HOOKS=$(if ($ProfileCommandHooks) { '1' } else { $null });
+    D4R_ZLUDA_PROFILE_API=$(if ($ProfileCudaApi) { '1' } else { $null });
+    D4R_DISABLE_INTEROP_LIST_CACHE=$(if ($UncachedInteropLists) { '1' } else { $null });
+    D4R_ASYNC_INTEROP=$(if ($AsyncInterop) { '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)
 }
@@ -246,6 +252,19 @@ try {
     $stdout = Get-Content -LiteralPath (Join-Path $OutputDirectory 'd4r.stdout.log') -Raw
     $debugger = Get-Content -LiteralPath (Join-Path $OutputDirectory 'debugger.log') -Raw
     $gameExit = [regex]::Match($debugger, 'EXIT code=0x([0-9a-f]+)')
+    $gameCrash = $null
+    if ([IO.Path]::GetFileName($GameExe) -eq 'SHProto-Win64-Shipping.exe' -and $gameExit.Success -and $gameExit.Groups[1].Value -ne '0') {
+        $crashRoot = Join-Path $env:LOCALAPPDATA 'SilentHill2/Saved/Crashes'
+        $latest = Get-ChildItem -LiteralPath $crashRoot -Directory -ErrorAction SilentlyContinue |
+            Where-Object { $_.LastWriteTime -ge (Get-Date).AddSeconds(-$timer.Elapsed.TotalSeconds-5) } |
+            Sort-Object LastWriteTime -Descending | Select-Object -First 1
+        if ($latest) {
+            Copy-Item -LiteralPath $latest.FullName -Destination (Join-Path $OutputDirectory 'ue-crash') -Recurse
+            [xml]$context = Get-Content -LiteralPath (Join-Path $latest.FullName 'CrashContext.runtime-xml') -Raw
+            $gameCrash = @{type=[string]$context.FGenericCrashContext.RuntimeProperties.CrashType;
+                reason=[string]$context.FGenericCrashContext.RuntimeProperties.ErrorMessage}
+        }
+    }
     # A bounded stop can interrupt the last printf; count only complete records.
     $frames = [regex]::Matches($stdout, '(?m)^D4R_FRAME cpu_frame_copies=([0-9]+) frame_age=([0-9]+) interop_ngx_ms=([0-9.]+)\r?$')
     $checks = [regex]::Matches($stdout, '(?m)^D4R_OUTPUT_VALIDATION elements=([0-9]+) nan=([0-9]+) inf=([0-9]+) diagnostics_cpu_bytes=8\r?$')
@@ -254,7 +273,7 @@ try {
     $kernels = @($launches | ForEach-Object { $_.Groups[1].Value + ' ' + $_.Groups[2].Value } | Group-Object | ForEach-Object {
         $parts=$_.Name.Split(' '); @{kernel=$parts[0]; backend=$parts[1]; launches=$_.Count}
     })
-    @{exitCode=$(if ($gameExit.Success) { '0x' + $gameExit.Groups[1].Value } else { 'diagnostic_timeout' }); runSeconds=$timer.Elapsed.TotalSeconds; preset=$Preset;
+    @{exitCode=$(if ($gameExit.Success) { '0x' + $gameExit.Groups[1].Value } else { 'diagnostic_timeout' }); runSeconds=$timer.Elapsed.TotalSeconds; preset=$Preset; gameCrash=$gameCrash;
         nativeLaunches=([regex]::Matches($stderr, '\[d4r-launch\].*backend=native')).Count;
         completedFrames=$frames.Count; outputValidationRequested=[bool]$ValidateOutput;
         outputGpuChecks=$checks.Count; nonfiniteOutputs=$nonfinite; kernels=$kernels;