ayo
7c5d3c9157
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.
329 lines
16 KiB
Diff
329 lines
16 KiB
Diff
From 33bbac250ac7e2ca4eff67e8817ada9dad578208 Mon Sep 17 00:00:00 2001
|
|
From: Codex <codex@localhost>
|
|
Date: Thu, 1 Oct 2026 16:10:08 +0300
|
|
Subject: [PATCH] Support explicitly selected Windows d4r DLSS backend on
|
|
physical AMD adapters
|
|
|
|
---
|
|
OptiScaler/Config.cpp | 3 ++
|
|
OptiScaler/Config.h | 1 +
|
|
OptiScaler/OptiScaler.vcxproj | 4 +--
|
|
OptiScaler/State.h | 1 +
|
|
OptiScaler/Util.cpp | 12 +++++--
|
|
OptiScaler/dllmain.cpp | 33 +++++++++++++++++--
|
|
OptiScaler/hooks/LibraryLoad_Hooks.cpp | 17 ++++++++++
|
|
OptiScaler/inputs/NVNGX_DLSS_Dx12.cpp | 17 ++++++++++
|
|
OptiScaler/misc/IdentifyGpu.cpp | 20 +++++++++++
|
|
OptiScaler/proxies/NVNGX_Proxy.h | 5 ++-
|
|
OptiScaler/upscalers/FeatureProvider_Dx12.cpp | 10 ++++++
|
|
11 files changed, 115 insertions(+), 8 deletions(-)
|
|
|
|
diff --git a/OptiScaler/Config.cpp b/OptiScaler/Config.cpp
|
|
index d8c62d3..f444387 100644
|
|
--- a/OptiScaler/Config.cpp
|
|
+++ b/OptiScaler/Config.cpp
|
|
@@ -323,6 +323,7 @@ bool Config::Reload(std::filesystem::path iniPath)
|
|
{
|
|
// Don't enable again if set false because of no nvngx found
|
|
DLSSEnabled.set_from_config(readBool("DLSS", "Enabled"));
|
|
+ DLSSAllowExternalBackend.set_from_config(readBool("DLSS", "AllowExternalBackend"));
|
|
UseGenericAppIdWithDlss.set_from_config(readBool("DLSS", "UseGenericAppIdWithDlss"));
|
|
|
|
RenderPresetOverride.set_from_config(readBool("DLSS", "RenderPresetOverride"));
|
|
@@ -1168,6 +1169,8 @@ bool Config::SaveIni()
|
|
// DLSS
|
|
{
|
|
ini.SetValue("DLSS", "Enabled", GetBoolValue(Instance()->DLSSEnabled.value_for_config()).c_str());
|
|
+ ini.SetValue("DLSS", "AllowExternalBackend",
|
|
+ GetBoolValue(Instance()->DLSSAllowExternalBackend.value_for_config()).c_str());
|
|
ini.SetValue("DLSS", "RenderPresetOverride",
|
|
GetBoolValue(Instance()->RenderPresetOverride.value_for_config()).c_str());
|
|
ini.SetValue("DLSS", "RenderPresetForAll",
|
|
diff --git a/OptiScaler/Config.h b/OptiScaler/Config.h
|
|
index 4ab62a4..0caf8c8 100644
|
|
--- a/OptiScaler/Config.h
|
|
+++ b/OptiScaler/Config.h
|
|
@@ -275,6 +275,7 @@ class Config
|
|
|
|
// DLSS
|
|
CustomOptional<bool> DLSSEnabled { true };
|
|
+ CustomOptional<bool> DLSSAllowExternalBackend { false };
|
|
CustomOptional<bool> RenderPresetOverride { false };
|
|
CustomOptional<uint32_t> RenderPresetForAll { 0 };
|
|
CustomOptional<uint32_t> RenderPresetDLAA { 0 };
|
|
diff --git a/OptiScaler/OptiScaler.vcxproj b/OptiScaler/OptiScaler.vcxproj
|
|
index 24ca80b..dfbfc97 100644
|
|
--- a/OptiScaler/OptiScaler.vcxproj
|
|
+++ b/OptiScaler/OptiScaler.vcxproj
|
|
@@ -236,7 +236,7 @@
|
|
<SubSystem>Windows</SubSystem>
|
|
<EnableCOMDATFolding>true</EnableCOMDATFolding>
|
|
<OptimizeReferences>true</OptimizeReferences>
|
|
- <GenerateDebugInformation>false</GenerateDebugInformation>
|
|
+ <GenerateDebugInformation>true</GenerateDebugInformation>
|
|
<EnableUAC>false</EnableUAC>
|
|
<AdditionalDependencies>winhttp.lib;WindowsApp.lib;Dbghelp.lib;dxgi.lib;d3d11.lib;d3d12.lib;vulkan-1.lib;dxguid.lib;freetype.lib;ffx_fsr2_api_x64.lib;ffx_fsr2_api_dx11_x64.lib;ffx_fsr2_api_dx12_x64.lib;ffx_fsr2_api_vk_x64.lib;ffx_fsr2_212_api_dx12_x64.lib;ffx_fsr2_212_api_vk_x64.lib;ffx_fsr2_212_api_x64.lib;d3dcompiler.lib;ffx_backend_dx11_x64.lib;ffx_fsr3_x64.lib;ffx_frameinterpolation_x64.lib;ffx_fsr3upscaler_x64.lib;ffx_opticalflow_x64.lib;%(AdditionalDependencies)</AdditionalDependencies>
|
|
<ModuleDefinitionFile>Source.def</ModuleDefinitionFile>
|
|
@@ -873,4 +873,4 @@ copy NUL "$(SolutionDir)x64\Release\a\!! EXTRACT ALL FILES TO GAME FOLDER !!" /Y
|
|
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
|
|
<ImportGroup Label="ExtensionTargets">
|
|
</ImportGroup>
|
|
-</Project>
|
|
\ No newline at end of file
|
|
+</Project>
|
|
diff --git a/OptiScaler/State.h b/OptiScaler/State.h
|
|
index 42164de..84f8263 100644
|
|
--- a/OptiScaler/State.h
|
|
+++ b/OptiScaler/State.h
|
|
@@ -265,6 +265,7 @@ class State
|
|
int dlssgDetectedInterpolationCount = 0;
|
|
|
|
// DLSS
|
|
+ bool dlssExternalBackend = false;
|
|
bool dlssPresetsOverriddenExternally = false;
|
|
bool dlssPresetsOverridenByOpti = false;
|
|
uint32_t dlssRenderPresetExternal = 0;
|
|
diff --git a/OptiScaler/Util.cpp b/OptiScaler/Util.cpp
|
|
index f7ac6fa..7367a91 100644
|
|
--- a/OptiScaler/Util.cpp
|
|
+++ b/OptiScaler/Util.cpp
|
|
@@ -486,8 +486,16 @@ bool Util::GetFileVersion(std::wstring dllPath, version_t* fileVersionOut, versi
|
|
|
|
bool Util::IsSubpath(const std::filesystem::path& path, const std::filesystem::path& base)
|
|
{
|
|
- auto rel = std::filesystem::relative(path, base);
|
|
- auto first = *rel.begin();
|
|
+ // Called by LdrLoadDll hooks: relative()/weakly_canonical() perform file
|
|
+ // queries, can re-enter the hooks, and throw when an optional directory or
|
|
+ // a bare DLL search name cannot be resolved. This is a lexical routing
|
|
+ // check, not a filesystem access control decision.
|
|
+ auto normalizedPath = std::filesystem::path(ToLower(path.lexically_normal().wstring()));
|
|
+ auto normalizedBase = std::filesystem::path(ToLower(base.lexically_normal().wstring()));
|
|
+ auto rel = normalizedPath.lexically_relative(normalizedBase);
|
|
+ if (rel.empty())
|
|
+ return false;
|
|
+ const auto first = *rel.begin();
|
|
return first != "." && first != "..";
|
|
}
|
|
|
|
diff --git a/OptiScaler/dllmain.cpp b/OptiScaler/dllmain.cpp
|
|
index cba14b1..b4b786e 100644
|
|
--- a/OptiScaler/dllmain.cpp
|
|
+++ b/OptiScaler/dllmain.cpp
|
|
@@ -948,7 +948,7 @@ static void CheckWorkingMode()
|
|
|
|
// NVAPI
|
|
// Doesn't seem to like GetModuleHandle for some reason, so call our load to make sure
|
|
- if (GetDllNameWModule(&nvapiNamesW) != nullptr)
|
|
+ if (!State::Instance().dlssExternalBackend && GetDllNameWModule(&nvapiNamesW) != nullptr)
|
|
{
|
|
// This hooks nvapi as well when possible
|
|
auto nvapi64 = LibraryLoadHooks::LoadNvApi();
|
|
@@ -1958,7 +1958,33 @@ BOOL APIENTRY DllMain(HMODULE hModule, DWORD ul_reason_for_call, LPVOID lpReserv
|
|
return nvidiaDetected;
|
|
};
|
|
|
|
- bool possibleNvidia = isNvidiaViaNvapi();
|
|
+ // Opt in only to a configured, versioned Windows d4r backend. The
|
|
+ // marker performs no HIP/NGX initialization under DLL_PROCESS_ATTACH.
|
|
+ // GPU support is still checked by its public NGX requirements API.
|
|
+ if (Config::Instance()->DLSSEnabled.value_or_default() &&
|
|
+ Config::Instance()->DLSSAllowExternalBackend.value_or_default() &&
|
|
+ Config::Instance()->NvngxPath.has_value())
|
|
+ {
|
|
+ auto backendPath = std::filesystem::path(Config::Instance()->NvngxPath.value()) / L"_nvngx.dll";
|
|
+ if (backendPath.is_absolute())
|
|
+ {
|
|
+ auto module = NtdllProxy::LoadLibraryExW_Ldr(backendPath.c_str(), nullptr,
|
|
+ LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR | LOAD_LIBRARY_SEARCH_DEFAULT_DIRS);
|
|
+ if (module)
|
|
+ {
|
|
+ using BackendVersion = unsigned (*)();
|
|
+ auto version = reinterpret_cast<BackendVersion>(
|
|
+ KernelBaseProxy::GetProcAddress_()(module, "d4r_WindowsBackendVersion"));
|
|
+ State::Instance().dlssExternalBackend = version && version() == 1;
|
|
+ NtdllProxy::FreeLibrary_Ldr(module);
|
|
+ }
|
|
+ }
|
|
+ if (State::Instance().dlssExternalBackend)
|
|
+ spdlog::info("Validated external Windows d4r DLSS backend; retaining physical GPU identity");
|
|
+ else
|
|
+ spdlog::error("AllowExternalBackend requires an absolute NvngxPath containing Windows d4r ABI 1");
|
|
+ }
|
|
+ bool possibleNvidia = !State::Instance().dlssExternalBackend && isNvidiaViaNvapi();
|
|
|
|
spdlog::info("");
|
|
spdlog::info("Check for DLSS files");
|
|
@@ -1992,7 +2018,8 @@ BOOL APIENTRY DllMain(HMODULE hModule, DWORD ul_reason_for_call, LPVOID lpReserv
|
|
State::Instance().NVNGX_DLSSG_Path = Util::FindFilePath(exePath, "nvngx_dlssg.dll");
|
|
|
|
// Not 100% accurate for Nvidia cards without DLSS
|
|
- if (Config::Instance()->DLSSEnabled.value_or_default() && possibleNvidia)
|
|
+ if (Config::Instance()->DLSSEnabled.value_or_default() &&
|
|
+ (possibleNvidia || State::Instance().dlssExternalBackend))
|
|
{
|
|
if (State::Instance().NVNGX_DLSS_Path.has_value())
|
|
{
|
|
diff --git a/OptiScaler/hooks/LibraryLoad_Hooks.cpp b/OptiScaler/hooks/LibraryLoad_Hooks.cpp
|
|
index 90bdb89..108ea5b 100644
|
|
--- a/OptiScaler/hooks/LibraryLoad_Hooks.cpp
|
|
+++ b/OptiScaler/hooks/LibraryLoad_Hooks.cpp
|
|
@@ -46,6 +46,18 @@ HMODULE LibraryLoadHooks::LoadLibraryCheckW(std::wstring libName, LPCWSTR lpLibF
|
|
{
|
|
auto libNameA = wstring_to_string(libName);
|
|
|
|
+ // The external D3D12 shim itself uses a locally supplied CUDA NGX core.
|
|
+ // Keep that exact absolute path distinct from game-facing NGX interception.
|
|
+ if (State::Instance().dlssExternalBackend)
|
|
+ {
|
|
+ wchar_t corePath[32768] {};
|
|
+ const auto length = GetEnvironmentVariableW(L"D4R_NGX_CORE", corePath, 32768);
|
|
+ if (length && length < 32768 &&
|
|
+ Util::ToLower(std::filesystem::path(libName).lexically_normal().wstring()) ==
|
|
+ Util::ToLower(std::filesystem::path(corePath).lexically_normal().wstring()))
|
|
+ return nullptr;
|
|
+ }
|
|
+
|
|
#ifdef LOG_LIB_OPERATIONS
|
|
LOG_TRACE("{}", libNameA);
|
|
#endif
|
|
@@ -132,6 +144,11 @@ HMODULE LibraryLoadHooks::LoadLibraryCheckW(std::wstring libName, LPCWSTR lpLibF
|
|
// NvApi64.dll
|
|
if (CheckDllNameW(&libName, &nvapiNamesW))
|
|
{
|
|
+ // An explicit external CUDA backend owns its NVAPI topology provider.
|
|
+ // Returning OptiScaler's fake-NVAPI would replace that provider and can
|
|
+ // recurse into DXGI while the NGX loader holds the loader lock.
|
|
+ if (State::Instance().dlssExternalBackend)
|
|
+ return nullptr; // Continue through the original loader.
|
|
LOG_INFO("{} call!", libNameA);
|
|
|
|
return LibraryLoadHooks::LoadNvApi();
|
|
diff --git a/OptiScaler/inputs/NVNGX_DLSS_Dx12.cpp b/OptiScaler/inputs/NVNGX_DLSS_Dx12.cpp
|
|
index 68e1b42..89c9ba8 100644
|
|
--- a/OptiScaler/inputs/NVNGX_DLSS_Dx12.cpp
|
|
+++ b/OptiScaler/inputs/NVNGX_DLSS_Dx12.cpp
|
|
@@ -687,6 +687,7 @@ static NVSDK_NGX_Result TryCreateOptiFeature(ID3D12GraphicsCommandList* InCmdLis
|
|
}
|
|
|
|
// Assign handle
|
|
+ const bool allocatedHandle = *OutHandle == nullptr;
|
|
if (*OutHandle == nullptr)
|
|
*OutHandle = new NVSDK_NGX_Handle { handleId };
|
|
else
|
|
@@ -705,6 +706,16 @@ static NVSDK_NGX_Result TryCreateOptiFeature(ID3D12GraphicsCommandList* InCmdLis
|
|
}
|
|
else
|
|
{
|
|
+ if (state.dlssExternalBackend && upscalerBackend == Upscaler::DLSS)
|
|
+ {
|
|
+ LOG_ERROR("External DLSS initialization failed; refusing FSR fallback");
|
|
+ if (shouldRestoreSigs)
|
|
+ D3D12Hooks::RestoreRoot(InCmdList);
|
|
+ D3D12Hooks::SetRootSignatureTracking(true);
|
|
+ Dx12Contexts.erase(handleId);
|
|
+ if (allocatedHandle) { delete *OutHandle; *OutHandle = nullptr; }
|
|
+ return NVSDK_NGX_Result_Fail;
|
|
+ }
|
|
LOG_ERROR("Feature '{}' initialization failed falling back to FSR 2.1.2", UpscalerDisplayName(upscalerBackend));
|
|
state.newBackend = Upscaler::FSR21;
|
|
state.changeBackend[handleId] = true;
|
|
@@ -1027,6 +1038,12 @@ static NVSDK_NGX_Result TryEvaluateOptiFeature(ID3D12GraphicsCommandList* InCmdL
|
|
// Fallback to FSR 2.1.2 if feature failed to initialize and user didn't explicitly request it
|
|
if (!feature->IsInited() && cfg.Dx12Upscaler.value_or_default() != Upscaler::FSR21)
|
|
{
|
|
+ if (state.dlssExternalBackend && cfg.Dx12Upscaler.value_or_default() == Upscaler::DLSS)
|
|
+ {
|
|
+ LOG_ERROR("External DLSS feature is not initialized; refusing FSR fallback");
|
|
+ D3D12Hooks::SetRootSignatureTracking(true);
|
|
+ return NVSDK_NGX_Result_Fail;
|
|
+ }
|
|
LOG_WARN("Feature '{}' failed to initialize. Falling back to FSR 2.1.2", feature->Name());
|
|
ImGui::InsertNotification({ ImGuiToastType::Warning, 10000, "Falling back to FSR 2.1.2" });
|
|
|
|
diff --git a/OptiScaler/misc/IdentifyGpu.cpp b/OptiScaler/misc/IdentifyGpu.cpp
|
|
index 3877f9f..6c05904 100644
|
|
--- a/OptiScaler/misc/IdentifyGpu.cpp
|
|
+++ b/OptiScaler/misc/IdentifyGpu.cpp
|
|
@@ -8,6 +8,7 @@
|
|
#include <proxies/D3d12_Proxy.h>
|
|
#include "nvapi/NvApiTypes.h"
|
|
#include <hooks/Amdxc64_Hooks.h>
|
|
+#include <proxies/NVNGX_Proxy.h>
|
|
|
|
using Microsoft::WRL::ComPtr;
|
|
|
|
@@ -187,6 +188,25 @@ std::vector<GpuInformation> IdentifyGpu::checkGpuInfo()
|
|
|
|
for (auto& gpuInfo : localCachedInfo)
|
|
{
|
|
+ if (State::Instance().dlssExternalBackend && !gpuInfo.softwareAdapter)
|
|
+ {
|
|
+ // Query the configured D3D12 backend outside DLL_PROCESS_ATTACH.
|
|
+ // Preserve vendor/device/architecture data obtained from DXGI.
|
|
+ auto requirements = NVNGXProxy::D3D12_GetFeatureRequirements();
|
|
+ ComPtr<IDXGIAdapter1> physicalAdapter;
|
|
+ if (requirements && SUCCEEDED(factory->EnumAdapterByLuid(gpuInfo.luid, IID_PPV_ARGS(&physicalAdapter))))
|
|
+ {
|
|
+ NVSDK_NGX_FeatureDiscoveryInfo discovery {};
|
|
+ discovery.SDKVersion = NVSDK_NGX_Version_API;
|
|
+ discovery.FeatureID = NVSDK_NGX_Feature_SuperSampling;
|
|
+ NVSDK_NGX_FeatureRequirement supported {};
|
|
+ const auto result = requirements(physicalAdapter.Get(), &discovery, &supported);
|
|
+ gpuInfo.dlssCapable = result == NVSDK_NGX_Result_Success &&
|
|
+ supported.FeatureSupported == NVSDK_NGX_FeatureSupportResult_Supported;
|
|
+ LOG_INFO("External D3D12 DLSS backend: {} support={} result={:X}",
|
|
+ gpuInfo.name, gpuInfo.dlssCapable, (unsigned) result);
|
|
+ }
|
|
+ }
|
|
if (gpuInfo.vendorId == VendorId::Nvidia)
|
|
{
|
|
queryNvapi(gpuInfo);
|
|
diff --git a/OptiScaler/proxies/NVNGX_Proxy.h b/OptiScaler/proxies/NVNGX_Proxy.h
|
|
index f6c08e5..7892009 100644
|
|
--- a/OptiScaler/proxies/NVNGX_Proxy.h
|
|
+++ b/OptiScaler/proxies/NVNGX_Proxy.h
|
|
@@ -500,7 +500,10 @@ class NVNGXProxy
|
|
{
|
|
LOG_INFO("Getting nvngx method addresses");
|
|
|
|
- HookNgxApi(_module.dll);
|
|
+ // The external bridge reports physical adapter support itself.
|
|
+ // Do not overwrite its unsupported result with NVIDIA spoofing.
|
|
+ if (!State::Instance().dlssExternalBackend)
|
|
+ HookNgxApi(_module.dll);
|
|
|
|
_module.D3D11_Init =
|
|
(PFN_D3D11_Init) KernelBaseProxy::GetProcAddress_()(_module.dll, "NVSDK_NGX_D3D11_Init");
|
|
diff --git a/OptiScaler/upscalers/FeatureProvider_Dx12.cpp b/OptiScaler/upscalers/FeatureProvider_Dx12.cpp
|
|
index d738498..1191b29 100644
|
|
--- a/OptiScaler/upscalers/FeatureProvider_Dx12.cpp
|
|
+++ b/OptiScaler/upscalers/FeatureProvider_Dx12.cpp
|
|
@@ -42,6 +42,11 @@ bool FeatureProvider_Dx12::GetFeature(Upscaler upscaler, UINT handleId, NVSDK_NG
|
|
break;
|
|
|
|
case Upscaler::DLSS:
|
|
+ if (state.dlssExternalBackend && (!primaryGpu.dlssCapable || !state.NVNGX_DLSS_Path.has_value()))
|
|
+ {
|
|
+ LOG_ERROR("Configured external D3D12 DLSS backend is unavailable; refusing FSR fallback");
|
|
+ return false;
|
|
+ }
|
|
if (primaryGpu.dlssCapable && state.NVNGX_DLSS_Path.has_value())
|
|
{
|
|
*feature = std::make_unique<DLSSFeatureDx12>(handleId, parameters);
|
|
@@ -77,6 +82,11 @@ bool FeatureProvider_Dx12::GetFeature(Upscaler upscaler, UINT handleId, NVSDK_NG
|
|
|
|
if (!loaded)
|
|
{
|
|
+ if (state.dlssExternalBackend && upscaler == Upscaler::DLSS)
|
|
+ {
|
|
+ LOG_ERROR("External D3D12 DLSS module failed to load; refusing FSR fallback");
|
|
+ return false;
|
|
+ }
|
|
// Fail after the constructor
|
|
ImGui::InsertNotification({ ImGuiToastType::Warning, 10000, "Falling back to FSR 2.1.2" });
|
|
*feature = std::make_unique<FSR2FeatureDx12_212>(handleId, parameters);
|
|
--
|
|
2.55.0.windows.5
|
|
|