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.

engine/game_rr.h

@@ -0,0 +1,29 @@
+// Adapter between a game's own textures and the Ray Reconstruction engine (REngine): input conversion where a
+// texture cannot be sampled directly, the frame and the copy into the game's output texture, all recorded into the
+// game's command buffer.
+#pragma once
+#include "game.h"
+
+namespace d4r {
+struct GameFrameR {
+    GameImage color, depth, motion, normals, roughness, diffuseAlbedo, specularAlbedo, output;
+    // optional (image null: the game passes none): DLSSD.SpecularHitDistance, DLSS.DisocclusionMask
+    GameImage specularHitDistance, disocclusionMask;
+    // optional too: DLSSD.ScreenSpaceSubsurfaceScatteringGuide, DLSSD.ColorBeforeParticles
+    GameImage subsurfaceGuide, colorBeforeParticles;
+    RFrameSettings settings;
+};
+class GameDenoiser {
+public:
+    // The model must outlive this object. The render size is fixed.
+    GameDenoiser(RModel& model, VkPhysicalDevice physical, VkDevice device, uint32_t outputWidth, uint32_t outputHeight,
+                 uint32_t renderWidth, uint32_t renderHeight);
+    ~GameDenoiser(); // only once every recorded frame has completed on the GPU
+    GameDenoiser(const GameDenoiser&) = delete;
+    GameDenoiser& operator=(const GameDenoiser&) = delete;
+    void record(VkCommandBuffer command, const GameFrameR& frame);
+private:
+    struct Impl;
+    std::unique_ptr<Impl> impl;
+};
+} // namespace d4r