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

Build native Windows packages for both RDNA4 targets

Browse Source 
Add explicit gfx1200/gfx1201 builds, runtime selection and per-target
code objects. Guard staging, packaging and installation against mixed
architectures; retain gfx1201 compatibility and strict K/M arithmetic.

Adapt realdody's target configuration and MSVC binary16/BOOL portability
fixes from ae530b0. Do not import its forced gfx12 layout on RDNA3.
Add exhaustive binary16 and C++/PowerShell target contract regressions.

Validation: 20 CTest gates on RX 9070 XT; four software-only gfx1200 gates;
MSVC portability compile checks; exact 4K K async and M control outputs;
isolated package install/restore and mixed-target rejection tests.
No physical gfx1200 validation is claimed.

Co-authored-by: realdody <[email protected]>
This commit is contained in:
xdfnx-devandrealdody committed 2026-10-02 16:18:18 +03:00
1 parent 8f7058d2ba
commit 98de8e3a3e
51 files changed
+636 -127
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/windows/test-deferred-kernel-profile.ps1
+5 -3
View File
@@ -1,9 +1,11 @@
[CmdletBinding()]
param([string]$ZludaRoot, [string]$PackageRoot, [string]$HipRoot, [string]$OutputDirectory)
$ErrorActionPreference = 'Stop'
. (Join-Path $PSScriptRoot 'gpu-target.ps1')
$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' }
$GpuArch=Get-D4RGpuTarget $PackageRoot $null
if (!$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 $OutputDirectory | Out-Null
@@ -64,7 +66,7 @@ try {
if ($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" }
if ($out -notmatch "PASS CUDA architecture=$GpuArch" -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') {
@@ -89,11 +91,11 @@ try {
$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 $out -notmatch 'PASS CUDA architecture=gfx1201' -or
if ($exitCode -or $out -notmatch "PASS CUDA architecture=$GpuArch" -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} |
@{passed=$true; architecture=$GpuArch; 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 {