TL;DR: Add an experimental FSR Ray Regeneration backend on Windows, run the K

network natively on HIP with Vulkan->HIP shared memory, extend K kernels to
gfx11 (RDNA3), and add dependency/packaging/test tooling around them.

Windows: FSR RR backend, native HIP K runner, gfx11 K kernels, tooling

FSR Ray Regeneration (experimental)
- Add fsr_rr_backend.{h,cpp}, fsr_rr_passes.h and the fsr_rr/ prepare and
  compose compute shaders. They run AMD's FidelityFX denoiser
  (amd_fidelityfx_denoiser_dx12.dll, SDK 2.3, not bundled) on a private
  vkd3d-proton device.
- Add the amdxc64 shim (tools/windows/amdxc64_shim) and two vkd3d-proton
  patches for libcxx includes. AMD's amdxc64.dll is never loaded.
- d4r_nvngx_windows: RrFeature now selects between the native DLSS RR
  backend and the FSR backend (D4R_RR_BACKEND=fsr). After the denoiser it
  runs an internal Super Sampling stage (feature 1) to upscale. If SR is
  unavailable and output != render size, the frame fails; it is never
  returned noisy.
- d4r.ini / player_config: new [RayReconstruction] FsrDenoiser,
  FsrStabilityBias (auto or >= 0) and FsrDetail (0-1), with validation, and
  matching D4R_FSR_* environment variables.
- Add the FSR RR fixture, output-check and ngx test scripts, and a shader
  compile script.

Native HIP K runner (Windows)
- CMake: add d4r_engine_k_hip (d4r-k-hip) plus separate volk/engine copies,
  because VK_USE_PLATFORM_WIN32_KHR changes volk's entry points.
- Share Vulkan memory with HIP via Win32 opaque handles on Windows
  (VK_KHR_external_memory_win32) and via fds on Linux. Handle types are now
  intptr_t, and the platform choice is in D4R_EXT_MEMORY_* macros.
- HipNetwork: add debugRepeatHashes and debugNodeMicros, exposed as
  D4R_HIP_REPEAT_CHECK, D4R_HIP_REPEAT_ALL and D4R_HIP_NODE_PROFILE in
  replay.cpp.
- replay.cpp: display-resolution-motion frames (FrameFlagDisplayMotion) no
  longer require near2rnd == out2rnd. Both values must still be in (0, 1].

K kernels on gfx11
- Allow position-token and enc1 tiling on __GFX11__ as well as gfx12.
- Add an opt-in ds_bpermute cross-half exchange
  (D4R_WINDOWS_GFX11_DS_EXCHANGE, enabled for K on Windows gfx11). M keeps
  its LDS path.
- Fix a block-barrier race in the position layer. Without POS_VSHARE a fast
  wave could overwrite its hb rows while a slower wave still read them for a
  later head, giving rare wrong results on gfx1101 (enc0 outputs differing
  between identical launches).

Packaging and install
- install.bat, d4r.ini, WINDOWS_README: FSR option, and
  install_dependencies.py to install pinned NVIDIA dependencies with staged,
  hash-verified replacement and rollback.
- Update the release package, local package refresh and test scripts.
- Add the InteropBatchInputCopies option (default false). Batching is faster
  on some synthetic runs, but player temporal exactness is unresolved.

Tooling and tests
- K model: capture_k_weights, build_k_model, compare_k_outputs,
  benchmark_k_hip, build_capture_runtime, test_k_model and the
  zluda-k-output-capture patch. Captured weights and models are private
  local assets and must not enter release archives.
- Synthetic probes: test_m_ngx, test_sr_dynamic,
  prepare_rr_dynamic_fixture and the d3d12/rr_ngx probe updates.
- Add tests/windows/test_install_dependencies.py.

Docs
- Update the windows-fsr-rr, k-performance, local-package, rr-interop and
  rr-model-cache docs. Add windows-parity-handoff.md and
  windows-parity-continuation-prompt.md.

scripts/windows/build-native-k-experiment.ps1

@@ -3,7 +3,7 @@ param([ValidateSet('enc0','enc1','enc2','enc3','enc4','dec5','dec4','dec3','dec2
     [string]$Layer='enc1', [ValidateSet('source','cu','wgp')][string]$Mode='source',
     [ValidateSet('baseline','load','store','both')][string]$NonTemporal='baseline',
     [ValidateSet(0,1,2,4)][int]$PosTiles=0, [switch]$ShareValues, [switch]$PrivateValues,
-    [switch]$PackedAccumulator,
+    [switch]$PackedAccumulator, [ValidateSet('lds','ds')][string]$LaneExchange='lds',
     [ValidateSet('gfx1100','gfx1101','gfx1102','gfx1103','gfx1150','gfx1151','gfx1152','gfx1153','gfx1154','gfx1200','gfx1201')]
     [string]$GpuArch='gfx1201',
     [string]$HipRoot, [string]$OutputDirectory)
@@ -11,8 +11,8 @@ $ErrorActionPreference='Stop'
 $repo=[IO.Path]::GetFullPath((Join-Path $PSScriptRoot '../..'))
 if (!$HipRoot) { $HipRoot=Join-Path $repo '.tools/therock-10.2.0a20260929/_rocm_sdk_core' }
 if ($ShareValues -and $PrivateValues) { throw 'Choose shared or private V storage.' }
-if ($GpuArch -notmatch '^gfx12' -and ($PosTiles -or $ShareValues -or $PrivateValues -or $PackedAccumulator)) {
-    throw 'Token tiling and accumulator/storage experiments require gfx12.'
+if ($GpuArch -notmatch '^gfx12' -and $PackedAccumulator) {
+    throw 'Packed accumulator experiments require gfx12.'
 }
 if (!$OutputDirectory) { $OutputDirectory=Join-Path $repo "build/native-k-experiment-$GpuArch-$Layer-$Mode-$NonTemporal-pos$PosTiles-share$([int][bool]$ShareValues)-private$([int][bool]$PrivateValues)-packed$([int][bool]$PackedAccumulator)" }
 $OutputDirectory=[IO.Path]::GetFullPath($OutputDirectory)
@@ -46,6 +46,10 @@ if ($ShareValues) {
 if ($PackedAccumulator) { $flags+='-DD4R_K_PACKED_ACC' }
 if ($PrivateValues) { $flags+='-DD4R_K_PRIVATE_V' }
 if ($GpuArch -match '^gfx11') { $flags+='-DD4R_WINDOWS_GFX11_LANE_EXCHANGE' }
+if ($LaneExchange -eq 'ds') {
+    if ($GpuArch -notmatch '^gfx11') { throw 'DS lane exchange experiment requires gfx11.' }
+    $flags+='-DD4R_WINDOWS_GFX11_DS_EXCHANGE'
+}
 New-Item -ItemType Directory -Force $OutputDirectory | Out-Null
 $object=Join-Path $OutputDirectory "$name.hsaco"
 $arguments=@('-x','hip','-std=c++17',"--offload-arch=$GpuArch",'--offload-device-only',
@@ -64,7 +68,7 @@ if ($LASTEXITCODE) { throw 'Native object metadata extraction failed.' }
 @{layer=$Layer; architecture=$GpuArch; experimental=$true; numericalValidation='pending';
     mode=$Mode; nonTemporal=$NonTemporal; tokenTilesPerWave=$PosTiles; shareValues=[bool]$ShareValues;
     privateValues=[bool]$PrivateValues;
-    packedAccumulator=[bool]$PackedAccumulator;
+    packedAccumulator=[bool]$PackedAccumulator; laneExchange=$LaneExchange;
     compiler=$compiler; arguments=$arguments;
     sourceCommit=(git -C $repo rev-parse HEAD); workingTreeDirty=[bool](& git -C $repo status --porcelain);
     compilerVersion=(& $compiler --version | Out-String).Trim();