wouter/d4r
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Validate Windows native M FP8 and reduce operand packing cost

Browse Source
This commit is contained in:
Codex committed 2026-10-01 21:16:28 +03:00
1 parent 74aad12938
commit 0c18df6253
20 files changed
+486 -33
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/windows/build-native-m-fp8.ps1
+59
View File
@@ -0,0 +1,59 @@
[CmdletBinding()]
param([Parameter(Mandatory=$true)][string]$DlssDll, [string]$HipRoot, [string]$OutputDirectory, [switch]$HardwarePacking)
$ErrorActionPreference='Stop'
$repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$HipRoot) { $HipRoot=Join-Path $repo '.tools/therock-10.2.0a20260929/_rocm_sdk_core' }
if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo $(if ($HardwarePacking) { 'build/native-m-fp8-hardware-pack' } else { 'build/native-m-fp8-experimental' }) }
$OutputDirectory=[IO.Path]::GetFullPath($OutputDirectory)
if ($OutputDirectory -eq [IO.Path]::GetFullPath((Join-Path $repo 'build/native-m-gfx1201'))) {
throw 'Keep the validated FP16 baseline separate from the experimental FP8 build.'
}
$DlssDll=(Get-Item -LiteralPath $DlssDll -ErrorAction Stop).FullName
$compiler=Join-Path $HipRoot 'lib/llvm/bin/clang++.exe'
if (!(Test-Path -LiteralPath $compiler)) { $compiler=Join-Path $HipRoot 'bin/clang++.exe' }
if (!(Test-Path -LiteralPath $compiler)) { throw "HIP compiler missing under $HipRoot" }
New-Item -ItemType Directory -Force $OutputDirectory | Out-Null
$disassembler=Join-Path (Split-Path $compiler) 'llvm-objdump.exe'
if (!(Test-Path -LiteralPath $disassembler)) { throw 'HIP llvm-objdump is required to confirm native FP8 instructions.' }
foreach ($source in Get-ChildItem -LiteralPath (Join-Path $repo 'kernels/m') -Filter '*.hip' | Sort-Object Name) {
$flags=@()
if ((Get-Content -LiteralPath $source.FullName -Raw) -match '// d4r-build-flags: ([^\r\n]+)') { $flags=$Matches[1].Trim().Split(' ') }
if ($HardwarePacking) { $flags+='-DD4R_FP8_HW_PACK' }
$object=Join-Path $OutputDirectory ($source.BaseName+'.hsaco')
$ErrorActionPreference='Continue'
& $compiler -x hip -std=c++17 --offload-arch=gfx1201 --offload-device-only --no-gpu-bundle-output `
-mno-wavefrontsize64 -nogpuinc -nogpulib -O3 -DD4R_DEVICE_ONLY_MINIMAL `
-DSWIN_EXACT -DSWIN_EXACT_PV -DD4R_FP8_WMMA @flags $source.FullName `
-o $object > (Join-Path $OutputDirectory ($source.BaseName+'.build.stdout.log')) `
2> (Join-Path $OutputDirectory ($source.BaseName+'.build.stderr.log'))
$ErrorActionPreference='Stop'
if ($LASTEXITCODE) { throw "Experimental FP8 compile failed: $($source.Name)" }
$isa=Join-Path $OutputDirectory ($source.BaseName+'.isa.txt')
& $disassembler --disassemble --mcpu=gfx1201 $object > $isa
if ($LASTEXITCODE -or !(Select-String -LiteralPath $isa -Pattern 'v_wmma_f32_16x16x16_fp8_fp8')) {
throw "Native FP8 WMMA is absent from $($source.Name); no FP16 fallback is accepted."
}
if ($HardwarePacking -and !(Select-String -LiteralPath $isa -Pattern 'v_cvt_pk_fp8_f32')) { throw 'Native FP8 operand packing is absent from ISA.' }
Write-Host "Compiled gfx1201 FP8 WMMA: $($source.BaseName)"
}
if ($HardwarePacking) {
$probeDirectory=Join-Path $OutputDirectory 'packing-probe'
New-Item -ItemType Directory -Force $probeDirectory | Out-Null
& $compiler -x hip -std=c++17 --offload-arch=gfx1201 --offload-device-only --no-gpu-bundle-output `
-mno-wavefrontsize64 -nogpuinc -nogpulib -O3 -DD4R_DEVICE_ONLY_MINIMAL `
-DD4R_FP8_WMMA -DD4R_FP8_HW_PACK -DSWIN_EXACT -DSWIN_EXACT_PV `
(Join-Path $repo 'tools/windows/fp8_pack_probe.hip') -o (Join-Path $probeDirectory 'fp8_pack_probe.hsaco')
if ($LASTEXITCODE) { throw 'Native hardware packing diagnostic compile failed.' }
}
& python (Join-Path $repo 'kernels/tools/kernel_manifest.py') $OutputDirectory $DlssDll
if ($LASTEXITCODE) { throw 'Experimental FP8 manifest generation failed.' }
@{architecture='gfx1201'; family='M'; experimental=$true; nativeFp8=$true; accuracy=$true;
numerics='SWIN_EXACT; SWIN_EXACT_PV; FP8 WMMA for e4m3 GEMMs; exact FP16 attention';
validation='not validated; do not install before layer/full-network checks';
compiler=$compiler; compilerVersion=(& $compiler --version | Select-Object -First 1);
sourceCommit=(& git -C $repo rev-parse HEAD).Trim(); nativeFp8IsaVerified=$true; hardwarePacking=[bool]$HardwarePacking;
sourceWorkingTreeDirty=[bool](& git -C $repo status --porcelain);
dlssSha256=(Get-FileHash -LiteralPath $DlssDll -Algorithm SHA256).Hash;
modules=@(Get-ChildItem -LiteralPath $OutputDirectory -Filter '*.hsaco' | Get-FileHash -Algorithm SHA256)} |
ConvertTo-Json -Depth 5 | Set-Content -LiteralPath (Join-Path $OutputDirectory 'build-info.json') -Encoding UTF8
Write-Host "Experimental native FP8 M objects: $OutputDirectory (baseline unchanged)"
scripts/windows/build-native-texture.ps1
+1 -1
View File
@@ -8,7 +8,7 @@ param(
)
$ErrorActionPreference='Stop'
$repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$ZludaRoot) { $ZludaRoot=Join-Path $repo 'dist/zluda-windows-profile' }
if (!$ZludaRoot) { $ZludaRoot=Join-Path $repo 'dist/zluda-windows-final' }
if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo 'build/private-textures-gfx1201' }
& python (Join-Path $repo 'tools/windows/build_native_texture.py') --dlss-dll $DlssDll --hip-root $HipRoot `
--zluda-root $ZludaRoot --kernel $Kernel --output-directory $OutputDirectory
scripts/windows/build-zluda-windows.ps1
+1 -1
View File
@@ -4,7 +4,7 @@ $ErrorActionPreference = 'Stop'
$repo = [IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$SourceRoot) { $SourceRoot = Join-Path $repo 'external/ZLUDA' }
if (!$LlvmBuildRoot) { $LlvmBuildRoot = Join-Path $repo 'build/zluda-llvm-windows-gnu' }
if (!$InstallRoot) { $InstallRoot = Join-Path $repo 'dist/zluda-windows-native' }
if (!$InstallRoot) { $InstallRoot = Join-Path $repo 'dist/zluda-windows-final' }
$rust = Join-Path $repo '.tools/rust-1.98.1-gnu'
$toolchain = Join-Path $repo '.tools/llvm-mingw-20260922-ucrt-x86_64'
$target = Join-Path $repo 'build/zluda-rust-windows-gnu'
scripts/windows/package-windows-game.ps1
+11 -3
View File
@@ -7,13 +7,16 @@ param(
$ErrorActionPreference = 'Stop'
$repo = [IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
$defaults = @{PackageRoot='dist/windows-rdna4-game'; DiagnosticRoot='dist/windows-rdna4-command-list';
OptiScalerRoot='dist/optiscaler-windows-d4r'; ZludaRoot='dist/zluda-windows-profile';
OptiScalerRoot='dist/optiscaler-windows-d4r'; ZludaRoot='dist/zluda-windows-final';
HipRoot='.tools/therock-10.2.0a20260929/_rocm_sdk_core';
KernelKRoot='build/native-k-gfx1201'; KernelMRoot='build/native-m-gfx1201'}
foreach ($name in $defaults.Keys) {
if (!(Get-Variable -Name $name -ValueOnly)) { Set-Variable -Name $name -Value (Join-Path $repo $defaults[$name]) }
}
$PackageRoot = [IO.Path]::GetFullPath($PackageRoot)
$sourceCommit=(& git -C $repo rev-parse HEAD).Trim()
$sourceDirty=[bool](& git -C $repo status --porcelain)
if ($ArchivePath -and $sourceDirty) { throw 'Commit source changes before creating the distributable archive.' }
New-Item -ItemType Directory -Force $PackageRoot | Out-Null
$stagedFiles = [Collections.Generic.List[string]]::new()
function Stage([string]$source, [string]$relative) {
@@ -61,10 +64,15 @@ Stage (Join-Path $HipRoot 'share/doc/amd_comgr/LICENSE.txt') 'licenses/amd_comgr
Stage (Join-Path $repo 'external/clr/LICENSE.md') 'licenses/HIP-CLR.txt'
foreach ($patch in Get-ChildItem -LiteralPath (Join-Path $repo 'patches/optiscaler') -Filter '*.patch') { Stage $patch.FullName ('source-patches/optiscaler/' + $patch.Name) }
foreach ($patch in Get-ChildItem -LiteralPath (Join-Path $repo 'patches/zluda') -Filter '*.patch') { Stage $patch.FullName ('source-patches/zluda/' + $patch.Name) }
$sourceArchive=Join-Path $repo 'build/d4r-windows-rdna4-source.zip'
New-Item -ItemType Directory -Force (Split-Path $sourceArchive) | Out-Null
& git -C $repo archive --format=zip --output $sourceArchive $sourceCommit
if ($LASTEXITCODE) { throw 'Cannot archive the committed d4r source.' }
Stage $sourceArchive 'source/d4r-windows-rdna4-source.zip'
$metadata = [ordered]@{
architecture='gfx1201'; nativeKernels=16; dlssSha256='3975567b8943c53acce397f2b72380092f84f162d00b0d2c7d08a1025c563983';
d4rCommit=(& git -C $repo rev-parse HEAD).Trim();
d4rWorkingTreeDirty=[bool](& git -C $repo status --porcelain);
d4rCommit=$sourceCommit;
d4rWorkingTreeDirty=$sourceDirty;
optiScaler=(Get-Content -LiteralPath (Join-Path $OptiScalerRoot 'build-info.json') -Raw | ConvertFrom-Json);
zludaBuild=(Get-Content -LiteralPath (Join-Path $ZludaRoot 'build-info.json') -Raw | ConvertFrom-Json);
hipRuntime='TheRock 10.2.0a20260929 / HIP 7.17.26386';
scripts/windows/profile-windows-rdna4.ps1
+1 -1
View File
@@ -7,7 +7,7 @@ param(
)
$ErrorActionPreference='Stop'
$repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$ZludaRoot) { $ZludaRoot=Join-Path $repo 'dist/zluda-windows-profile' }
if (!$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')) }
$settings=@{D4R_ZLUDA_PROFILE='1'; D4R_PROFILE_STAGES='1'; D4R_VALIDATE_OUTPUT='1';
scripts/windows/test-native-m-fp8.ps1
+28
View File
@@ -0,0 +1,28 @@
[CmdletBinding()]
param([Parameter(Mandatory=$true)][string]$CaptureDirectory,
[Parameter(Mandatory=$true)][string]$BaselineValidation,
[string]$ModuleDirectory, [string]$HipRoot, [string]$OutputDirectory, [switch]$Benchmark)
$ErrorActionPreference='Stop'
$repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$ModuleDirectory) { $ModuleDirectory=Join-Path $repo 'build/native-m-fp8-experimental' }
if (!$HipRoot) { $HipRoot=Join-Path $repo '.tools/therock-10.2.0a20260929/_rocm_sdk_core' }
if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo 'test-results/m-native-fp8-replay' }
$previousPython=$env:PYTHONPATH
try {
$env:PYTHONPATH="$(Join-Path $repo '.tools/python/vendor');$previousPython"
$metadata=Get-Content -LiteralPath (Join-Path $ModuleDirectory 'build-info.json') -Raw | ConvertFrom-Json
if ($metadata.hardwarePacking) {
& python -u (Join-Path $repo 'tools/windows/fp8_pack_validate.py') `
--probe (Join-Path $repo 'dist/windows-rdna4-command-list/bin/d4r_native_replay_probe.exe') `
--module (Join-Path $ModuleDirectory 'packing-probe/fp8_pack_probe.hsaco') `
--hip-root $HipRoot --output-dir (Join-Path $OutputDirectory 'packing-check')
if ($LASTEXITCODE) { throw 'Hardware packing does not preserve every finite FP8 encoding; stopping before network replay.' }
}
$benchmarkArguments=@()
if ($Benchmark) { $benchmarkArguments=@('--benchmark-control-dir',(Join-Path $repo 'build/native-m-gfx1201')) }
& python -u (Join-Path $repo 'tools/windows/m_native_replay_compare.py') `
--capture-dir $CaptureDirectory --module-dir $ModuleDirectory --hip-root $HipRoot `
--probe (Join-Path $repo 'dist/windows-rdna4-command-list/bin/d4r_native_replay_probe.exe') `
--baseline-validation $BaselineValidation --output-dir $OutputDirectory @benchmarkArguments
if ($LASTEXITCODE) { throw "Experimental FP8 validation failed; baseline unchanged. Logs: $OutputDirectory" }
} finally { $env:PYTHONPATH=$previousPython }
scripts/windows/test-native-overrides.ps1
+1 -1
View File
@@ -4,7 +4,7 @@ $ErrorActionPreference = 'Stop'
$repo = [IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
if (!$HipRoot) { $HipRoot = Join-Path $repo '.tools/therock-10.2.0a20260929/_rocm_sdk_core' }
if (!$PackageRoot) { $PackageRoot = Join-Path $repo 'dist/windows-rdna4-therock' }
if (!$ZludaRoot) { $ZludaRoot = Join-Path $repo 'dist/zluda-windows-native' }
if (!$ZludaRoot) { $ZludaRoot = Join-Path $repo 'dist/zluda-windows-final' }
if (!$OutputDirectory) { $OutputDirectory = Join-Path $repo ('test-results/native-identity-' + (Get-Date -Format 'yyyyMMdd-HHmmss')) }
New-Item -ItemType Directory -Force $OutputDirectory | Out-Null
$previous = @{D4R_ZLUDA_NATIVE_DIR=$env:D4R_ZLUDA_NATIVE_DIR; D4R_ZLUDA_VERBOSE=$env:D4R_ZLUDA_VERBOSE; D4R_DIAG_DIR=$env:D4R_DIAG_DIR}
scripts/windows/test-native-texture.ps1
+1 -1
View File
@@ -22,7 +22,7 @@ try {
foreach ($flags in @(0,11)) {
foreach ($mode in @('control','candidate')) {
$env:D4R_ZLUDA_NATIVE_DIR=if ($mode -eq 'control') { Join-Path $repo 'build/native-k-gfx1201' } else { $combined }
$arguments=@{RuntimeProfile='therock'; ZludaRoot=(Join-Path $repo 'dist/zluda-windows-profile');
$arguments=@{RuntimeProfile='therock'; ZludaRoot=(Join-Path $repo 'dist/zluda-windows-final');
PackageRoot=(Join-Path $repo 'dist/windows-rdna4-command-list'); NgxCore=(Join-Path $repo '_nvngx.dll');
DlssDll=(Join-Path $repo 'nvngx_dlss.dll'); NgxMode='d3d12'; NgxAbi='project-legacy'; Preset=11;
NgxCreateFlags=$flags; NgxOutputResolution=$OutputResolution; NgxOnly=$true; RequireNativeNetwork=$true; CommandListBackend=$true;
scripts/windows/test-windows-rdna4.ps1
+1 -1
View File
@@ -42,7 +42,7 @@ $PackageRoot = [IO.Path]::GetFullPath($PackageRoot)
if (!$HipRoot) { $HipRoot = 'C:\Program Files\AMD\ROCm\7.2' }
$HipRoot = [IO.Path]::GetFullPath($HipRoot)
if (!$ZludaRoot) {
$builtZluda = Join-Path $repoRoot 'dist/zluda-windows-native'
$builtZluda = Join-Path $repoRoot 'dist/zluda-windows-final'
$localZluda = [IO.Path]::GetFullPath((Join-Path $PackageRoot '../../.tools/zluda/zluda'))
if (Test-Path (Join-Path $builtZluda 'build-info.json')) { $ZludaRoot = $builtZluda }
elseif (Test-Path (Join-Path $localZluda 'nvcuda.dll')) { $ZludaRoot = $localZluda }