feat: add d4r inference engines and Windows parity tooling

Add native K/M/RR inference engines, HIP kernels, replay and validation harnesses, and Windows DLSS setup and runtime support. Include GPU profiling tools, build and packaging scripts, platform integration patches, and implementation documentation.
2026-10-16 08:54:47 -04:00
1 parent 25493b3198
commit 7c5d3c9157
@@ -0,0 +1,44 @@
+[CmdletBinding()]
+param(
+    [ValidateSet(5,11,12,13)][int]$Preset = 11,
+    [string]$ZludaRoot, [string]$PackageRoot, [string]$OutputDirectory,
+    [string]$NativeKernelDirectory,
+    [int]$Iterations = 4,
+    [switch]$Translated, [switch]$NativeFp8
+)
+$ErrorActionPreference='Stop'
+. (Join-Path $PSScriptRoot 'gpu-target.ps1')
+$repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
+if (!$ZludaRoot) { $ZludaRoot=Join-Path $repo 'dist/zluda-windows-final' }
+if (!$PackageRoot) { $PackageRoot=Join-Path $repo 'dist/windows-rdna4-command-list' }
+$GpuArch=Get-D4RGpuTarget $PackageRoot $null
+if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo ('test-results/profile-' + $Preset + '-' + (Get-Date -Format 'yyyyMMdd-HHmmss-fff')) }
+$nativeDirectory=if ($NativeFp8) {
+    if ($GpuArch -notmatch '^gfx12' -or $Preset -notin @(12,13)) { throw '-NativeFp8 requires gfx12 and preset L/M.' }
+    if (!$NativeKernelDirectory) { $NativeKernelDirectory=Join-Path $repo 'build/native-m-fp8-token-lane-hwpack' }
+    $info=Get-Content -LiteralPath (Join-Path $NativeKernelDirectory 'build-info.json') -Raw | ConvertFrom-Json
+    if ($info.architecture -ne $GpuArch -or !$info.nativeFp8 -or !$info.tokenLanes) { throw 'NativeFp8 needs the matching gfx12 token-lane M kernel bundle.' }
+    [IO.Path]::GetFullPath($NativeKernelDirectory)
+} elseif ($Translated -or $Preset -eq 5) { $null }
+elseif ($Preset -eq 11) { Join-Path $repo "build/native-k-$GpuArch" }
+else { Join-Path $repo "build/native-m-$GpuArch" }
+$settings=@{D4R_ZLUDA_PROFILE='1'; D4R_PROFILE_STAGES='1'; D4R_VALIDATE_OUTPUT='1';
+    D4R_ZLUDA_PROFILE_DEFERRED=$null; D4R_ZLUDA_PROFILE_ALLOW_LEGACY=$null; D4R_ZLUDA_PROFILE_EVERY=$null;
+    D4R_ZLUDA_NATIVE_DIR=$nativeDirectory}
+$settings['D4R_ZLUDA_WMMA_FP8_NATIVE']=if ($NativeFp8) { '1' } else { $null }
+$old=@{}
+try {
+    foreach ($key in $settings.Keys) { $old[$key]=[Environment]::GetEnvironmentVariable($key,'Process'); [Environment]::SetEnvironmentVariable($key,$settings[$key],'Process') }
+    $arguments=@{RuntimeProfile='therock'; ZludaRoot=$ZludaRoot; PackageRoot=$PackageRoot; OutputDirectory=$OutputDirectory;
+        NgxCore=(Join-Path $repo '_nvngx.dll'); DlssDll=(Join-Path $repo 'nvngx_dlss.dll'); NgxMode='d3d12';
+        NgxAbi='project-legacy'; Preset=$Preset; NgxOnly=$true; RequireNativeNetwork=(!$Translated -and $Preset -ne 5); NativeFp8=$NativeFp8; CommandListBackend=$true;
+        CaptureExceptions=$true; EarlyIndirectProbe=$true; PixelProfile='depth-stencil'; BarrierMode='inherited-legacy';
+        Iterations=$Iterations; TimeoutSeconds=300; OptiScalerDll=(Join-Path $repo 'dist/optiscaler-windows-d4r/OptiScaler.dll')}
+    & (Join-Path $PSScriptRoot 'test-windows-rdna4.ps1') @arguments
+    if ($LASTEXITCODE) { throw 'Profiling workload failed; see diagnostic bundle.' }
+    $python=(Get-Command python.exe -ErrorAction Stop).Source
+    & $python (Join-Path $repo 'tools/windows/profile_report.py') $OutputDirectory --output (Join-Path $OutputDirectory 'profile.json')
+    if ($LASTEXITCODE) { throw 'No usable profile records.' }
+} finally {
+    foreach ($key in $old.Keys) { [Environment]::SetEnvironmentVariable($key,$old[$key],'Process') }
+}